diff --git a/.gitignore b/.gitignore deleted file mode 100644 index 7de58a5..0000000 --- a/.gitignore +++ /dev/null @@ -1,25 +0,0 @@ -# build outputs -/build/ -/dist/ -*.o -*.a -*.so -*.dylib -*.dll -*.exe -*.vsix -test_yapf_tmp.yapf - -# generated: copied from bindings/js/yapf.js when packaging -/extensions/vscode/media/yapf.js -node_modules/ -__pycache__/ -*.pyc - -# Rust -/bindings/rust/target/ -/bindings/rust/Cargo.lock -# C# / Go / Java build outputs -bin/ -obj/ -*.class diff --git a/LICENSE b/LICENSE index 261eeb9..c400177 100644 --- a/LICENSE +++ b/LICENSE @@ -1,201 +1,21 @@ - Apache License - Version 2.0, January 2004 - http://www.apache.org/licenses/ +MIT License - TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION +Copyright (c) 2026 Nexoniarz - 1. Definitions. +Permission is hereby granted, free of charge, to any person obtaining a copy +of this software and associated documentation files (the "Software"), to deal +in the Software without restriction, including without limitation the rights +to use, copy, modify, merge, publish, distribute, sublicense, and/or sell +copies of the Software, and to permit persons to whom the Software is +furnished to do so, subject to the following conditions: - "License" shall mean the terms and conditions for use, reproduction, - and distribution as defined by Sections 1 through 9 of this document. +The above copyright notice and this permission notice shall be included in all +copies or substantial portions of the Software. - "Licensor" shall mean the copyright owner or entity authorized by - the copyright owner that is granting the License. - - "Legal Entity" shall mean the union of the acting entity and all - other entities that control, are controlled by, or are under common - control with that entity. For the purposes of this definition, - "control" means (i) the power, direct or indirect, to cause the - direction or management of such entity, whether by contract or - otherwise, or (ii) ownership of fifty percent (50%) or more of the - outstanding shares, or (iii) beneficial ownership of such entity. - - "You" (or "Your") shall mean an individual or Legal Entity - exercising permissions granted by this License. - - "Source" form shall mean the preferred form for making modifications, - including but not limited to software source code, documentation - source, and configuration files. - - "Object" form shall mean any form resulting from mechanical - transformation or translation of a Source form, including but - not limited to compiled object code, generated documentation, - and conversions to other media types. - - "Work" shall mean the work of authorship, whether in Source or - Object form, made available under the License, as indicated by a - copyright notice that is included in or attached to the work - (an example is provided in the Appendix below). - - "Derivative Works" shall mean any work, whether in Source or Object - form, that is based on (or derived from) the Work and for which the - editorial revisions, annotations, elaborations, or other modifications - represent, as a whole, an original work of authorship. For the purposes - of this License, Derivative Works shall not include works that remain - separable from, or merely link (or bind by name) to the interfaces of, - the Work and Derivative Works thereof. - - "Contribution" shall mean any work of authorship, including - the original version of the Work and any modifications or additions - to that Work or Derivative Works thereof, that is intentionally - submitted to Licensor for inclusion in the Work by the copyright owner - or by an individual or Legal Entity authorized to submit on behalf of - the copyright owner. For the purposes of this definition, "submitted" - means any form of electronic, verbal, or written communication sent - to the Licensor or its representatives, including but not limited to - communication on electronic mailing lists, source code control systems, - and issue tracking systems that are managed by, or on behalf of, the - Licensor for the purpose of discussing and improving the Work, but - excluding communication that is conspicuously marked or otherwise - designated in writing by the copyright owner as "Not a Contribution." - - "Contributor" shall mean Licensor and any individual or Legal Entity - on behalf of whom a Contribution has been received by Licensor and - subsequently incorporated within the Work. - - 2. Grant of Copyright License. Subject to the terms and conditions of - this License, each Contributor hereby grants to You a perpetual, - worldwide, non-exclusive, no-charge, royalty-free, irrevocable - copyright license to reproduce, prepare Derivative Works of, - publicly display, publicly perform, sublicense, and distribute the - Work and such Derivative Works in Source or Object form. - - 3. Grant of Patent License. Subject to the terms and conditions of - this License, each Contributor hereby grants to You a perpetual, - worldwide, non-exclusive, no-charge, royalty-free, irrevocable - (except as stated in this section) patent license to make, have made, - use, offer to sell, sell, import, and otherwise transfer the Work, - where such license applies only to those patent claims licensable - by such Contributor that are necessarily infringed by their - Contribution(s) alone or by combination of their Contribution(s) - with the Work to which such Contribution(s) was submitted. If You - institute patent litigation against any entity (including a - cross-claim or counterclaim in a lawsuit) alleging that the Work - or a Contribution incorporated within the Work constitutes direct - or contributory patent infringement, then any patent licenses - granted to You under this License for that Work shall terminate - as of the date such litigation is filed. - - 4. Redistribution. You may reproduce and distribute copies of the - Work or Derivative Works thereof in any medium, with or without - modifications, and in Source or Object form, provided that You - meet the following conditions: - - (a) You must give any other recipients of the Work or - Derivative Works a copy of this License; and - - (b) You must cause any modified files to carry prominent notices - stating that You changed the files; and - - (c) You must retain, in the Source form of any Derivative Works - that You distribute, all copyright, patent, trademark, and - attribution notices from the Source form of the Work, - excluding those notices that do not pertain to any part of - the Derivative Works; and - - (d) If the Work includes a "NOTICE" text file as part of its - distribution, then any Derivative Works that You distribute must - include a readable copy of the attribution notices contained - within such NOTICE file, excluding those notices that do not - pertain to any part of the Derivative Works, in at least one - of the following places: within a NOTICE text file distributed - as part of the Derivative Works; within the Source form or - documentation, if provided along with the Derivative Works; or, - within a display generated by the Derivative Works, if and - wherever such third-party notices normally appear. The contents - of the NOTICE file are for informational purposes only and - do not modify the License. You may add Your own attribution - notices within Derivative Works that You distribute, alongside - or as an addendum to the NOTICE text from the Work, provided - that such additional attribution notices cannot be construed - as modifying the License. - - You may add Your own copyright statement to Your modifications and - may provide additional or different license terms and conditions - for use, reproduction, or distribution of Your modifications, or - for any such Derivative Works as a whole, provided Your use, - reproduction, and distribution of the Work otherwise complies with - the conditions stated in this License. - - 5. Submission of Contributions. Unless You explicitly state otherwise, - any Contribution intentionally submitted for inclusion in the Work - by You to the Licensor shall be under the terms and conditions of - this License, without any additional terms or conditions. - Notwithstanding the above, nothing herein shall supersede or modify - the terms of any separate license agreement you may have executed - with Licensor regarding such Contributions. - - 6. Trademarks. This License does not grant permission to use the trade - names, trademarks, service marks, or product names of the Licensor, - except as required for reasonable and customary use in describing the - origin of the Work and reproducing the content of the NOTICE file. - - 7. Disclaimer of Warranty. Unless required by applicable law or - agreed to in writing, Licensor provides the Work (and each - Contributor provides its Contributions) on an "AS IS" BASIS, - WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or - implied, including, without limitation, any warranties or conditions - of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A - PARTICULAR PURPOSE. You are solely responsible for determining the - appropriateness of using or redistributing the Work and assume any - risks associated with Your exercise of permissions under this License. - - 8. Limitation of Liability. In no event and under no legal theory, - whether in tort (including negligence), contract, or otherwise, - unless required by applicable law (such as deliberate and grossly - negligent acts) or agreed to in writing, shall any Contributor be - liable to You for damages, including any direct, indirect, special, - incidental, or consequential damages of any character arising as a - result of this License or out of the use or inability to use the - Work (including but not limited to damages for loss of goodwill, - work stoppage, computer failure or malfunction, or any and all - other commercial damages or losses), even if such Contributor - has been advised of the possibility of such damages. - - 9. Accepting Warranty or Additional Liability. While redistributing - the Work or Derivative Works thereof, You may choose to offer, - and charge a fee for, acceptance of support, warranty, indemnity, - or other liability obligations and/or rights consistent with this - License. However, in accepting such obligations, You may act only - on Your own behalf and on Your sole responsibility, not on behalf - of any other Contributor, and only if You agree to indemnify, - defend, and hold each Contributor harmless for any liability - incurred by, or claims asserted against, such Contributor by reason - of your accepting any such warranty or additional liability. - - END OF TERMS AND CONDITIONS - - APPENDIX: How to apply the Apache License to your work. - - To apply the Apache License to your work, attach the following - boilerplate notice, with the fields enclosed by brackets "[]" - replaced with your own identifying information. (Don't include - the brackets!) The text should be enclosed in the appropriate - comment syntax for the file format. We also recommend that a - file or class name and description of purpose be included on the - same "printed page" as the copyright notice for easier - identification within third-party archives. - - Copyright [yyyy] [name of copyright owner] - - Licensed under the Apache License, Version 2.0 (the "License"); - you may not use this file except in compliance with the License. - You may obtain a copy of the License at - - http://www.apache.org/licenses/LICENSE-2.0 - - Unless required by applicable law or agreed to in writing, software - distributed under the License is distributed on an "AS IS" BASIS, - WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. - See the License for the specific language governing permissions and - limitations under the License. +THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR +IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, +FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE +AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER +LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, +OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE +SOFTWARE. diff --git a/Makefile b/Makefile deleted file mode 100644 index 0c2322e..0000000 --- a/Makefile +++ /dev/null @@ -1,65 +0,0 @@ -# YAPF — simple build for Linux, macOS and other Unix systems. -# -# make library (static + shared) and the `yapf` tool, in build/ -# make test run the C test suite (and the JS one if node is present) -# sudo make install install header, libraries and tool under $(PREFIX) -# make NO_SIMD=1 plain C only -# -# Windows: use build.bat (LLVM) or any MinGW / MSVC compiler on yapf.c. - -CC ?= cc -CFLAGS ?= -O2 -PREFIX ?= /usr/local -BUILD ?= build - -YAPF_CFLAGS = -std=c99 -Wall -Wextra $(CFLAGS) $(if $(NO_SIMD),-DYAPF_NO_SIMD) -LDLIBS = -lm -pthread - -ifeq ($(shell uname -s),Darwin) - SHARED = libyapf.dylib - SHARED_FLAGS = -dynamiclib -install_name $(PREFIX)/lib/libyapf.dylib -else - SHARED = libyapf.so - SHARED_FLAGS = -shared -endif - -all: $(BUILD)/libyapf.a $(BUILD)/$(SHARED) $(BUILD)/yapf - -$(BUILD): - mkdir -p $(BUILD) - -$(BUILD)/yapf.o: yapf.c yapf.h | $(BUILD) - $(CC) $(YAPF_CFLAGS) -fPIC -c yapf.c -o $@ - -$(BUILD)/libyapf.a: $(BUILD)/yapf.o - $(AR) rcs $@ $^ - -$(BUILD)/$(SHARED): $(BUILD)/yapf.o - $(CC) $(SHARED_FLAGS) $^ -o $@ -pthread - -$(BUILD)/yapf: tools/yapf_cli.c yapf.c yapf.h | $(BUILD) - $(CC) $(YAPF_CFLAGS) tools/yapf_cli.c yapf.c -o $@ $(LDLIBS) - -$(BUILD)/test_yapf: tests/test_yapf.c yapf.c yapf.h | $(BUILD) - $(CC) $(YAPF_CFLAGS) tests/test_yapf.c yapf.c -o $@ $(LDLIBS) - -test: $(BUILD)/test_yapf - $(BUILD)/test_yapf other/YAPF.YAPF - @if command -v node >/dev/null 2>&1; then node bindings/js/test.js; \ - else echo "(node not found: skipped the JavaScript tests)"; fi - -install: all - install -d $(DESTDIR)$(PREFIX)/include $(DESTDIR)$(PREFIX)/lib $(DESTDIR)$(PREFIX)/bin - install -m 644 yapf.h $(DESTDIR)$(PREFIX)/include/yapf.h - install -m 644 $(BUILD)/libyapf.a $(DESTDIR)$(PREFIX)/lib/libyapf.a - install -m 755 $(BUILD)/$(SHARED) $(DESTDIR)$(PREFIX)/lib/$(SHARED) - install -m 755 $(BUILD)/yapf $(DESTDIR)$(PREFIX)/bin/yapf - -uninstall: - rm -f $(DESTDIR)$(PREFIX)/include/yapf.h $(DESTDIR)$(PREFIX)/lib/libyapf.a \ - $(DESTDIR)$(PREFIX)/lib/$(SHARED) $(DESTDIR)$(PREFIX)/bin/yapf - -clean: - rm -rf $(BUILD) - -.PHONY: all test install uninstall clean diff --git a/README.md b/README.md deleted file mode 100644 index f020c69..0000000 --- a/README.md +++ /dev/null @@ -1,457 +0,0 @@ -# YAPF — Yet Another Picture Format - -**Lossless images that decode several times faster than PNG — on one core.** - -YAPF is a lossless image format for photos, UI and game assets, built for -decode speed first. There is no entropy coder, no bit reader and no context -model: every structure is byte aligned, and the decoder runs short loops that -modern CPUs execute at memory speed — with SSE / NEON where available. The -encoder does the hard work, so the decoder only follows instructions. - -- **5–12× faster decoding than PNG** (stb_image), single-threaded; a 4K image - decodes in about 6–7 ms (around 5 GB/s). Multithreaded decoding is optional. -- **Smaller than PNG** on UI, icons and screenshots; 20–45 % larger on photos - and natural textures — the price of having no entropy coder. -- **Made for games and tools too**: mipmaps, GPU format hint, sRGB / - premultiplied flags, and random access to 64×64 tiles. -- **A real texture format (YAPF 2)**: GPU-ready BC1–BC7 / BC6H / ETC2 / - ASTC blocks, 16-bit and float pixels, cubemaps, arrays and volumes, - channel meanings (normal X/Y, roughness, AO, …), coverage-preserving - mips, small-mips-first streaming, per-tile checksums, notes and - animation — see [Textures](#textures-yapf-2). -- **Tiny and portable**: two C99 files, no dependencies. Plus a CLI, Python, - JavaScript and plugins for the tools you already use. - -Two format versions: **version 1** (an 8-bit image, the first stable -format) and **version 2** (the texture container). Plain 8-bit images are -still written as version 1, so every existing YAPF reader keeps working. - ---- - -## Use it in… - -| Where | What you get | Guide | Status | -| :---- | :----------- | :---- | :----- | -| **C / C++** | `yapf.h` + `yapf.c`, drop into any project (compiles as C or C++) | [below](#c--c) | ✅ tested — see [platforms](#platforms) | -| **Command line** | convert PNG/JPG/TGA/BMP/PSD/GIF ↔ YAPF, `compare`, `info`, `bench`, `thumbnail` | [below](#command-line) | ✅ tested on Linux and Windows | -| **Your language** | Python, C#, Rust, Go, Java, Zig, Lua, JavaScript / TypeScript, … | [docs/LANGUAGES.md](docs/LANGUAGES.md) | ✅ every binding tested | -| **GIMP 3** | open, export (flattened, optional mipmaps) | [extensions/gimp](extensions/gimp) | ✅ tested in GIMP 3.0.8 | -| **Blender 4.2+** | import, export, drag & drop, image as plane | [extensions/blender](extensions/blender) | ✅ tested in Blender 5.1 | -| **KDE Dolphin** | thumbnails for `.yapf` files | [extensions/kde](extensions/kde) | ⚠️ tested through KDE's plugin loader (KF6); not yet inside a running Dolphin | -| **Linux desktop** | file type + thumbnails in GNOME Files, Nemo, Caja, Thunar | [extensions/linux](extensions/linux) | ⚠️ thumbnail command tested; not yet in a file manager | -| **VS Code** | image preview with zoom and mip picker | [extensions/vscode](extensions/vscode) | ⚠️ packaged; preview code tested in a browser engine (Chromium); **not yet run inside VS Code** | -| **Figma** | import `.yapf`, export selection as `.yapf` | [extensions/figma](extensions/figma) | ⚠️ plugin UI tested in a browser engine with a simulated Figma; **not yet run inside Figma** | -| **Photoshop** | File → Scripts → Open YAPF / Save as YAPF | [extensions/photoshop](extensions/photoshop) | ⚠️ **syntax-checked only; not yet run in Photoshop** | - -Pre-built downloads (command-line tool and libraries for Windows, macOS and -Linux, plus the plugin packages) are published on the -[Releases](https://github.com/Nexoniarz/YAPF/releases) page; everything can -also be built from source as described below. - -### Platforms - -| Platform | Status | -| :------- | :----- | -| Linux x64 | ✅ built and fully tested | -| Windows x64 | ✅ built and fully tested (MinGW and Zig builds, run under Wine) | -| Linux ARM64 | ✅ built and fully tested (NEON, run under qemu) | -| Windows ARM64 | ⚠️ built only, not run | -| macOS x64 / ARM64 | ⚠️ **cross-compiled only, not yet run on a Mac** | - ---- - -## Command line - -```sh -yapf photo.png photo.yapf # encode (formats by file extension) -yapf texture.png texture.yapf --mips # with a full mip chain -yapf photo.yapf photo.png # decode to PNG / JPG / BMP / TGA -yapf texture.yapf mip2.png --mip 2 # export one mip level -yapf info photo.yapf # size, channels, mips, flags, ratio -yapf bench photo.yapf # decode speed, 1 thread and all cores -yapf thumbnail photo.yapf thumb.png 256 -yapf compare photo.png ui.png # size and decode speed vs the original format -``` - -Options when writing `.yapf`: `--mips`, `--linear` (pixels are not sRGB), -`--premult` (alpha is premultiplied), and the texture options below. - ---- - -## Textures (YAPF 2) - -Version 2 turns YAPF into a texture container for engines, designed our own -way rather than copied from KTX2 or DDS (the design and the full -specification are in [docs/FORMAT.md](docs/FORMAT.md)): - -| Need | YAPF 2 | -| :--- | :----- | -| **GPU-compressed payloads** | BC1, BC2, BC3, BC4, BC5, BC6H, BC7, ETC2 / EAC and ASTC 4×4–12×12 blocks, stored as the GPU takes them. Built-in encoders for BC1, BC3, BC4, BC5, BC7 and BC6H; or bring blocks from your own encoder. | -| **More than 8 bits** | lossless 16-bit, half and float pixels, coded as byte planes with the same fast machinery | -| **Cubes, arrays, volumes** | cubemaps and cube arrays (reflection probes, skies), texture arrays (terrain layers), 3D textures (colour-grading LUTs) | -| **Channel meaning** | per channel: normal X/Y/Z, roughness, metalness, AO, height, opacity, …; OpenGL or DirectX normal convention; linear channels inside sRGB images | -| **Streaming** | small mips are stored first: a file prefix is a complete low-resolution texture (`yapf info` prints the prefix sizes); single 64 × 64 tiles decode on their own for virtual texturing | -| **Alpha-tested mips** | `--coverage REF` keeps fences and foliage from thinning out with distance; the filter used is recorded | -| **Entropy coding (optional)** | `--entropy`: shared per-surface Huffman code books with a neighbourhood context — about 10 % smaller photos, about 3× smaller GPU blocks on disk; tiles stay independent | -| **Metadata** | notes (author, licence, source, tool, ICC profile, orientation, DPI, HDR light levels, your own tags), colour primaries and transfer (sRGB, Display P3, BT.2020, PQ, HLG, …) | -| **Integrity** | yapf-sum checksums on the header, tables and every tile; *needs* bits make an older decoder refuse cleanly what it cannot read | -| **Animation** | frames with per-frame durations and a loop count | - -```sh -yapf albedo.png albedo.yapf --format bc7 --mips # GPU-ready colour -yapf normal.png normal.yapf --format bc5 --mips --normal dx # normal map, DirectX Y -yapf orm.png orm.yapf --map ao,rough,metal --linear --mips # packed masks -yapf foliage.png foliage.yapf --format bc7 --coverage 128 # alpha-tested mips -yapf sky.hdr sky.yapf --format bc6h --mips # HDR, no RGBM tricks -yapf sky.hdr sky_lossless.yapf # lossless half float -yapf pack cube px.png nx.png py.png ny.png pz.png nz.png probe.yapf --mips -yapf pack array grass.png rock.png sand.png terrain.yapf --format bc7 --mips -yapf pack volume lut_00.png lut_01.png ... grading.yapf --linear -yapf pack anim f0.png f1.png f2.png fx.yapf --frame-ms 50 -yapf albedo.png albedo.yapf --entropy --author "Keel" --license CC-BY-4.0 -yapf info albedo.yapf # everything in the header, notes, stream prefix sizes -yapf verify albedo.yapf # check every checksum -yapf probe.yapf face2.png --face 2 --mip 1 # export one surface -``` - -In C: - -```c -int err; -yapf_texture_t *t = yapf_tex_load("albedo.yapf", 0, 0, &err); -for (uint32_t m = 0; m < t->mip_levels; m++) { - uint32_t s = yapf_tex_surface(t, 0, 0, 0, m), w, h; - yapf_tex_mip_size(t, m, &w, &h, NULL); - if (t->payload == YAPF_PAYLOAD_BLOCKS) /* e.g. YAPF_GPU_BC7 */ - glCompressedTexImage2D(GL_TEXTURE_2D, m, gl_format(t->format, t->flags), - w, h, 0, (GLsizei)yapf_tex_surface_bytes(t, m), t->data[s]); -} -yapf_tex_free(t); -``` - -Every extension opens version 2 files: GIMP (at full 16-bit / float -precision, faces and frames as layers), Blender (HDR as float images), -KDE and Linux thumbnails, VS Code (with face / layer / frame / slice -pickers), Figma and Photoshop. The Python binding (`yapf.load_texture`) -and the JavaScript port (`YAPF.decodeTexture`) read every texture; the -other bindings wrap the v1 functions, which also read 8-bit version 2 -files (2D, cube face 0, array layer 0). - ---- - -## Benchmark - -`yapf compare` on a mixed set of images: one binary (`make`, gcc -O2) for -both formats, PNG decoded with stb_image, one core, AMD Ryzen 7 5700G. -Every result is checked to decode back to the exact original pixels. - -| Image | PNG | YAPF | YAPF / PNG size | PNG decode | YAPF decode | Faster | -| :---- | --: | ---: | --------------: | ---------: | ----------: | -----: | -| UI screenshot 261×430 | 176.6 KB | 143.7 KB | **81 %** | 2.05 ms | 0.17 ms | **12×** | -| UI screenshot 305×529 | 201.5 KB | 185.0 KB | **92 %** | 2.55 ms | 0.24 ms | **11×** | -| App icon 128×128 | 24.9 KB | 23.1 KB | **93 %** | 0.30 ms | 0.026 ms | **11×** | -| Wallpaper 3840×2160 | 1.77 MB | 2.21 MB | 125 % | 73.7 ms | 6.8 ms | **11×** | -| Rock texture 512×512 | 182.6 KB | 221.8 KB | 121 % | 1.64 ms | 0.17 ms | **10×** | -| Wood texture 512×512 | 185.8 KB | 234.1 KB | 126 % | 1.64 ms | 0.17 ms | **10×** | -| Canvas texture 512×512 | 171.5 KB | 245.6 KB | 143 % | 1.36 ms | 0.16 ms | **9×** | -| YAPF logo 512×512 | 60.5 KB | 89.3 KB | 148 % | 1.25 ms | 0.25 ms | **5×** | - -Smaller than PNG on UI-style images, 20–50 % larger on photos and textures -(the price of having no entropy coder), and 5–12× faster to decode. More -in [examples/](examples) — and run `yapf compare` on your own images. - ---- - -## C / C++ - -The library is two files. Add them to your project: - -``` -yapf.h — public API and the complete format specification -yapf.c — encoder and decoder -``` - -```c -#include "yapf.h" - -yapf_image_t *img = yapf_load("texture.yapf"); /* or yapf_load_memory(buf, len) */ -if (img) { - /* img->pixels: width × height × channels bytes, rows top to bottom */ - upload_texture(img->width, img->height, img->channels, img->pixels); - yapf_free(img); -} - -yapf_image_t out = { .width = w, .height = h, .channels = 4, - .mip_levels = 1, .pixels = rgba, .flags = YAPF_FLAG_SRGB }; -yapf_save("out.yapf", &out); -``` - -Compile with any C99 compiler (`-pthread` on Unix for the `_mt` loaders): - -```sh -cc -O2 -std=c99 main.c yapf.c -o app -pthread -``` - -SIMD is on by default: SSSE3 on x86 / x64 (chosen at run time with CPUID, -so binaries still run on older CPUs) and NEON on ARM64, with GCC, Clang, -MSVC and MinGW. - -| Define | Effect | -| :------------------ | :----- | -| `-DYAPF_NO_SIMD` | plain C only | -| `-DYAPF_NO_THREADS` | no threads; the `_mt` loaders decode on the calling thread, and only the C standard library is needed | - -## API Reference - -### Types - -```c -typedef struct { - uint32_t width; /* pixels per row */ - uint32_t height; /* rows */ - uint8_t channels; /* 1 gray / 2 gray+alpha / 3 RGB / 4 RGBA */ - uint8_t gpu_format; /* YAPF_GPU_* hint */ - uint8_t flags; /* YAPF_FLAG_* (premultiplied alpha, sRGB) */ - uint8_t mip_levels; /* 1 = base only, up to 16 */ - uint8_t *pixels; /* base level, malloc-owned */ - uint8_t **mips; /* mips[0] == pixels, mips[1..] smaller levels */ -} yapf_image_t; -``` - -`pixels` is a tightly packed, row-major byte array of `width × height × channels` -bytes. Mip level *m* is `max(1, width >> m) × max(1, height >> m)`. The -layout per pixel matches the `channels` value: - -| `channels` | Layout per pixel | -| :--------- | :--------------- | -| 1 | `Y` | -| 2 | `Y A` | -| 3 | `R G B` | -| 4 | `R G B A` | - -### Functions - -```c -yapf_image_t *yapf_load(const char *filename); -yapf_image_t *yapf_load_memory(const void *buffer, size_t size); -``` -Decode a YAPF file from disk or from memory (e.g. a game archive). Return a -heap-allocated image on success, `NULL` on any failure (file not found, -invalid or corrupt data, out of memory). Corrupt input is rejected, never -read out of bounds. - -```c -yapf_image_t *yapf_load_mt(const char *filename, int threads); -yapf_image_t *yapf_load_memory_mt(const void *buffer, size_t size, int threads); -``` -Same, decoding tiles on up to `threads` threads (`0` = one per CPU core). -The output is identical to the single-threaded loaders. - -```c -int yapf_save(const char *filename, const yapf_image_t *img); -``` -Encodes an image to disk. Writes `img->mip_levels` -levels; `img->mips` may be `NULL` when `mip_levels == 1`. Returns `YAPF_OK` -(0) on success or a negative `YAPF_ERR_*` code on failure. - -```c -int yapf_encode(const yapf_image_t *img, void **out_data, size_t *out_size); -void yapf_free_buffer(void *data); -``` -Encodes into memory: `*out_data` receives a complete `.yapf` file of -`*out_size` bytes, to be released with `yapf_free_buffer()`. - -```c -void yapf_free(yapf_image_t *img); -``` -Releases memory returned by the loaders. Passing `NULL` is safe. - -### Textures (version 2) - -```c -yapf_texture_t *yapf_tex_load(const char *file, int flags, int threads, int *err); -yapf_texture_t *yapf_tex_load_memory(const void *buf, size_t size, int flags, int threads, int *err); -int yapf_tex_save(const char *file, const yapf_texture_t *t, int flags); -int yapf_tex_encode(const yapf_texture_t *t, int flags, void **out, size_t *size); -yapf_texture_t *yapf_tex_create(const yapf_texture_t *desc); /* zeroed storage */ -void yapf_tex_free(yapf_texture_t *t); -``` -A texture describes its shape (width, height, depth, layers, frames, -cube / volume, mips), storage (pixels with u8 / u16 / half / float samples, -or GPU blocks), meaning (channel map, linear mask, normal convention, -primaries, transfer, mip filter, alpha reference) and holds `data[s]` per -surface `s = yapf_tex_surface(t, frame, layer, face, mip)`. Load flag -`YAPF_LOAD_TRUST` skips checksum checks; encode flag `YAPF_ENC_ENTROPY` -allows the entropy stage. - -```c -yapf_texture_t *yapf_tex_open(const void *buf, size_t avail, int flags, int *err); -uint64_t yapf_tex_stream_bytes(const yapf_texture_t *t, uint32_t first_mip); -int yapf_tex_decode_surface(yapf_texture_t *t, const void *buf, size_t avail, uint32_t s, int threads); -int yapf_tex_decode_tile(const yapf_texture_t *t, const void *buf, size_t avail, uint32_t s, - uint32_t tx, uint32_t ty, uint32_t slice, void *out, size_t stride, - uint32_t *x, uint32_t *y, uint32_t *w, uint32_t *h); -``` -Streaming and virtual texturing: open a file from its first bytes, ask how -many bytes hold mip *m* and smaller, decode surfaces as their bytes arrive -(`YAPF_ERR_TRUNCATED` until then), or decode single tiles. - -```c -int yapf_tex_build_mips(yapf_texture_t *t, uint32_t levels, uint8_t alpha_ref); -int yapf_tex_compress(const yapf_texture_t *src, uint8_t format, yapf_texture_t **out); -int yapf_blocks_decode(uint8_t format, const void *blocks, uint32_t w, uint32_t h, void *out); -int yapf_tex_add_note(yapf_texture_t *t, const char tag[4], const void *data, uint32_t size); -const yapf_note_t *yapf_tex_find_note(const yapf_texture_t *t, const char tag[4]); -``` -Mip chains (linear-light sRGB, optional coverage preservation), the -built-in BCn encoders, BC1–BC7 decoding for previews, and notes. The -complete list, with sizes and helpers, is in [`yapf.h`](yapf.h). - -### Return codes - -| Constant | Value | Meaning | -| :----------------- | ----: | :----------------------------------- | -| `YAPF_OK` | 0 | Success | -| `YAPF_ERR_INVALID` | –1 | NULL or logically invalid argument | -| `YAPF_ERR_IO` | –2 | File could not be opened or written | -| `YAPF_ERR_OOM` | –3 | Out of memory | -| `YAPF_ERR_CORRUPT` | –4 | Corrupt or not a YAPF file | -| `YAPF_ERR_UNSUPPORTED` | –5 | Needs a feature this decoder lacks | -| `YAPF_ERR_CHECKSUM` | –6 | A checksum does not match (v2) | -| `YAPF_ERR_TRUNCATED` | –7 | The data is not (yet) all there | - -### Channel constants - -```c -YAPF_CHANNELS_GRAY 1 -YAPF_CHANNELS_GRAY_ALPHA 2 -YAPF_CHANNELS_RGB 3 -YAPF_CHANNELS_RGBA 4 -``` - ---- - -## Building - -| System | Command | Output | -| :----- | :------ | :----- | -| Linux, macOS, BSD | `make` · `make test` · `sudo make install` | `build/`: `libyapf.a`, `libyapf.so` / `.dylib`, `yapf` | -| NixOS / Nix | `nix-build` (or `nix-env -if .`) — see [extensions/linux](extensions/linux#nixos) | `result/`: `bin/yapf`, `lib/`, `include/`, MIME type, thumbnailer | -| Linux, macOS (LLVM) | `./build.sh` | `dist//` incl. macOS universal binaries | -| Windows (LLVM) | `build.bat` | `dist\windows-x64\`, `dist\windows-arm64\`: `yapf.dll`, `yapf.lib`, `libyapf.a`, `yapf.exe` | -| Windows (Visual Studio) | `cl /O2 /c yapf.c` and add `yapf.obj` to your project | | -| All platforms at once | `tools/build_release.sh` (needs [zig](https://ziglang.org)) | `dist/release/`: every download on the Releases page | - -The command-line tool is `tools/yapf_cli.c` + `yapf.c`; it uses the public -domain [stb](https://github.com/nothings/stb) headers in `third_party/`. - ---- - -## How it works - -1. **Two colour transforms** — per 64×64 tile, YCoCg-R or subtract-green - (`G, R−G, B−G`), whichever codes smaller. Both run mod 256, so every - plane stays one byte per sample. -2. **Twelve row filters** — per band of 8 rows: Left, Gradient (`L + A − D`), - Up-right, Up-average, or the row 1–8 rows above (catches repeating - textures and dither patterns). None depends on the previous sample by - more than one add, and the vertical ones decode as plain vector code. -3. **Groups of 8** — residuals are packed in groups of 8 at the group's bit - width: 8 values × *w* bits = exactly *w* bytes, so every group is byte - aligned and unpacks with one 64-bit load (or one SIMD shuffle). -4. **4-bit control codes** — one per group, or one per run of up to 64 groups - repeating the previous width; the encoder picks the cheapest sequence with - a small dynamic program. -5. **Validate first, then run** — all sizes in a tile are checked before the - hot loops start, so the loops need no bounds checks. Corrupt files are - rejected, never read out of bounds. -6. **Constant and stored tiles** — a plane that is constant in a tile costs - one byte; a tile that would not shrink is stored raw (noise never grows). -7. **Independent tiles** — any tile can be decoded on its own, in any order, - on any thread. - -The version 1 specification is the comment at the top of [`yapf.h`](yapf.h); -version 2 (textures) is specified in [docs/FORMAT.md](docs/FORMAT.md). Version 1: - -``` -HEADER (20 bytes) "YAPF", version 1, channels, GPU hint, mip count, - flags, 3 reserved, width u32, height u32 -MIP INDEX per level: offset u32, size u32 -LEVEL DATA tile_size u32 × tile_count, then the tiles -TILE (64×64) header byte: stored raw, or constant-plane mask + colour transform - per plane: filter byte per 8 rows, control nibbles, - w bytes per group of 8 values -``` - ---- - -## Testing - -```sh -make test # C suite: 2631 checks, plus JavaScript if node is installed -node bindings/js/test.js # JavaScript: round-trips, sample file, corrupt input -``` - -What has been verified: - -- exact round-trips for 1–4 channels, odd sizes from 1×1 up, mip chains, - single- and multi-threaded decoding, in-memory and file encoding; -- the same tests pass on Linux x64, Windows x64 (run under Wine) and Linux - ARM64 (NEON, run under qemu), with and without SIMD, compiled as C and as - C++, and under AddressSanitizer, UndefinedBehaviorSanitizer and - ThreadSanitizer; -- thousands of corrupted and truncated files are rejected without crashing; -- version 2: lossless round-trips of u8 / u16 / half / float pixels with 1–4 - channels, with and without entropy coding; cubes, cube arrays, arrays, - volumes and animations with notes and every description field; GPU block - payloads; checksum, needs-bit and truncation handling; streaming from file - prefixes and single-tile decoding; BCn encoder quality; linear-light and - coverage-preserving mips; fuzzing of entropy-coded and packed-block files; -- the BC1–BC7 decoders were checked against an independent reference decoder - (bcdec) on 300,000 random blocks: BC6H and BC7 bit-exact, BC1–BC5 within - the ±1 rounding the formats allow (a development check, not part of - `make test`); -- every language binding runs its example; JavaScript, Python, C++, C#, - Rust, Go, Java and Lua re-encode the sample to byte-identical output; -- the GIMP plugin in GIMP 3.0.8 and the Blender extension in Blender 5.1; -- the KDE thumbnailer through KDE's own plugin loader. - -**Not yet verified:** running on a Mac (macOS builds are cross-compiled -only), Windows on ARM, and running inside Photoshop, VS Code, Figma or a -live Dolphin / GNOME file manager. The version 2 code has been run on -Linux x64 (with and without SIMD, as C and C++, under ASan, UBSan and -TSan); its NEON path is compiled for ARM64 but has not been run yet, and -the Windows builds have not been rerun. ETC2 / EAC / ASTC blocks are -stored and loaded, but there is no built-in encoder or preview decoder -for them. - ---- - -## Project layout - -``` -yapf.h, yapf.c the library (v1 spec in yapf.h) -docs/FORMAT.md the full format specification, version 2 -tools/yapf_cli.c the `yapf` command-line tool -tools/build_release.sh builds every download for all platforms -tests/test_yapf.c C test suite -examples/ speed and size comparison, C example -docs/LANGUAGES.md using YAPF from other languages -bindings/ cpp, python, csharp, rust, go, java, zig, lua, js -extensions/gimp/ GIMP 3 plugin -extensions/blender/ Blender extension -extensions/kde/ Dolphin thumbnail plugin (KF6) -extensions/linux/ MIME type and freedesktop thumbnailer -extensions/vscode/ VS Code preview -extensions/figma/ Figma plugin -extensions/photoshop/ Photoshop scripts -third_party/ stb_image / stb_image_write (public domain, CLI only) -other/YAPF.YAPF sample image (the YAPF logo) -``` - ---- - -## License - -Apache License 2.0 — see [LICENSE](LICENSE). `third_party/` contains -stb_image and stb_image_write by Sean Barrett (public domain / MIT). diff --git a/bindings/cpp/README.md b/bindings/cpp/README.md deleted file mode 100644 index e6d9a77..0000000 --- a/bindings/cpp/README.md +++ /dev/null @@ -1,18 +0,0 @@ -# YAPF for C++ - -`yapf.hpp` is a header-only C++17 wrapper: RAII, exceptions, `std::vector`. -Add `../../yapf.c` to your project and include the header. - -```cpp -#include "yapf.hpp" - -yapf::Image img = yapf::Image::load("texture.yapf"); // or Image::decode(bytes) -upload(img.width(), img.height(), img.channels(), img.pixels()); - -std::vector file = yapf::Image(256, 256, 4, rgba).encode(); -``` - -`yapf.c` compiles as C or as C++, so you can simply add it to a C++ project -(Visual Studio, CMake, …). - -Example: `g++ -O2 -std=c++17 example.cpp -x c++ ../../yapf.c -o example -pthread && ./example` diff --git a/bindings/cpp/example.cpp b/bindings/cpp/example.cpp deleted file mode 100644 index 633114e..0000000 --- a/bindings/cpp/example.cpp +++ /dev/null @@ -1,33 +0,0 @@ -// g++ -O2 -std=c++17 example.cpp ../../yapf.c -o example -pthread && ./example ../../other/YAPF.YAPF -#include "yapf.hpp" - -#include -#include -#include -#include -#include - -int main(int argc, char **argv) { - const char *path = argc > 1 ? argv[1] : "../../other/YAPF.YAPF"; - std::ifstream f(path, std::ios::binary); - std::vector bytes((std::istreambuf_iterator(f)), {}); - - yapf::Image img = yapf::Image::decode(bytes); - double ms = 1e9; // best of 10, as in a running program - for (int i = 0; i < 10; i++) { - auto t0 = std::chrono::steady_clock::now(); - img = yapf::Image::decode(bytes); - ms = std::min(ms, std::chrono::duration(std::chrono::steady_clock::now() - t0).count()); - } - std::printf("%s: %ux%u, %u channels, decoded in %.2f ms, file is %.1f%% of raw\n", path, - img.width(), img.height(), img.channels(), ms, 100.0 * bytes.size() / img.size()); - - std::vector again = img.encode(); - std::printf("re-encoded: %zu bytes, identical to the file: %s\n", again.size(), - again == bytes ? "yes" : "no"); - - std::vector gray(64 * 64); - for (size_t i = 0; i < gray.size(); i++) gray[i] = uint8_t(i % 64 * 4); - yapf::Image(64, 64, 1, gray.data()).save("gray.yapf"); - std::printf("wrote gray.yapf\n"); -} diff --git a/bindings/cpp/yapf.hpp b/bindings/cpp/yapf.hpp deleted file mode 100644 index ffd09e5..0000000 --- a/bindings/cpp/yapf.hpp +++ /dev/null @@ -1,98 +0,0 @@ -// yapf.hpp — header-only C++17 wrapper for YAPF. Copyright 2026 Nexoniarz — Apache 2.0. -// -// #include "yapf.hpp" // and compile/link ../../yapf.c -// yapf::Image img = yapf::Image::load("texture.yapf"); -// img.width(); img.height(); img.channels(); img.pixels(); // span of bytes -// std::vector file = img.encode(); -// yapf::Image mine(256, 256, 4, my_rgba_bytes); mine.save("out.yapf"); -#pragma once - -extern "C" { -#include "../../yapf.h" -} - -#include -#include -#include -#include -#include -#include - -namespace yapf { - -struct Error : std::runtime_error { - using std::runtime_error::runtime_error; -}; - -class Image { -public: - /* Decode a file or a memory buffer; threads = 0 uses every core, 1 the calling thread. */ - static Image load(const std::string &path, int threads = 1) { - yapf_image_t *p = yapf_load_mt(path.c_str(), threads); - if (!p) throw Error("YAPF: cannot load " + path); - return Image(p); - } - static Image decode(const void *data, size_t size, int threads = 1) { - yapf_image_t *p = yapf_load_memory_mt(data, size, threads); - if (!p) throw Error("YAPF: invalid or corrupt data"); - return Image(p); - } - static Image decode(const std::vector &bytes, int threads = 1) { - return decode(bytes.data(), bytes.size(), threads); - } - - /* A new image from your pixels (copied). channels: 1 gray, 2 gray+A, 3 RGB, 4 RGBA. */ - Image(uint32_t width, uint32_t height, uint8_t channels, const uint8_t *pixels, - uint8_t flags = YAPF_FLAG_SRGB) - : own_(pixels, pixels + size_t(width) * height * channels) { - std::memset(&view_, 0, sizeof(view_)); - view_.width = width; view_.height = height; view_.channels = channels; - view_.flags = flags; view_.mip_levels = 1; - view_.gpu_format = channels == 4 ? YAPF_GPU_SRGB8_A8 : channels == 3 ? YAPF_GPU_SRGB8 - : channels == 2 ? YAPF_GPU_RG8 : YAPF_GPU_R8; - view_.pixels = own_.data(); - } - - Image(Image &&o) noexcept : img_(std::exchange(o.img_, nullptr)), own_(std::move(o.own_)), view_(o.view_) { - if (!img_) view_.pixels = own_.data(); - } - Image &operator=(Image &&o) noexcept { - if (this != &o) { yapf_free(img_); img_ = std::exchange(o.img_, nullptr); own_ = std::move(o.own_); - view_ = o.view_; if (!img_) view_.pixels = own_.data(); } - return *this; - } - Image(const Image &) = delete; - Image &operator=(const Image &) = delete; - ~Image() { yapf_free(img_); } - - uint32_t width() const { return raw().width; } - uint32_t height() const { return raw().height; } - uint8_t channels() const { return raw().channels; } - uint8_t flags() const { return raw().flags; } - uint8_t mipLevels() const { return raw().mip_levels; } - const uint8_t *pixels() const { return raw().pixels; } - size_t size() const { return size_t(width()) * height() * channels(); } - const uint8_t *mip(int level) const { return raw().mips ? raw().mips[level] : raw().pixels; } - - std::vector encode() const { - void *data = nullptr; - size_t n = 0; - if (yapf_encode(&raw(), &data, &n) != YAPF_OK) throw Error("YAPF: encoding failed"); - std::vector out(static_cast(data), static_cast(data) + n); - yapf_free_buffer(data); - return out; - } - void save(const std::string &path) const { - if (yapf_save(path.c_str(), &raw()) != YAPF_OK) throw Error("YAPF: cannot write " + path); - } - - const yapf_image_t &raw() const { return img_ ? *img_ : view_; } - -private: - explicit Image(yapf_image_t *p) : img_(p) { std::memset(&view_, 0, sizeof(view_)); } - yapf_image_t *img_ = nullptr; // decoded by the library - std::vector own_; // or pixels we own - yapf_image_t view_{}; -}; - -} // namespace yapf diff --git a/bindings/csharp/Example/Example.csproj b/bindings/csharp/Example/Example.csproj deleted file mode 100644 index f0d0e5a..0000000 --- a/bindings/csharp/Example/Example.csproj +++ /dev/null @@ -1,11 +0,0 @@ - - - Exe - net8.0 - enable - enable - - - - - diff --git a/bindings/csharp/Example/Program.cs b/bindings/csharp/Example/Program.cs deleted file mode 100644 index d6f1bcc..0000000 --- a/bindings/csharp/Example/Program.cs +++ /dev/null @@ -1,25 +0,0 @@ -// dotnet run -- ../../../other/YAPF.YAPF (with yapf.dll / libyapf.so on the library path) -using System.Diagnostics; -using Yapf; - -string path = args.Length > 0 ? args[0] : "../../../other/YAPF.YAPF"; -byte[] file = File.ReadAllBytes(path); - -var img = YapfImage.Decode(file); // first call also loads the library / JIT -double ms = double.MaxValue; // best of 10, as in a running program -for (int i = 0; i < 10; i++) -{ - var sw = Stopwatch.StartNew(); - img = YapfImage.Decode(file); - ms = Math.Min(ms, sw.Elapsed.TotalMilliseconds); -} -Console.WriteLine($"{path}: {img.Width}x{img.Height}, {img.Channels} channels, decoded in {ms:F2} ms"); -Console.WriteLine($"file is {file.Length} bytes, {100.0 * file.Length / img.Pixels.Length:F1}% of the raw pixels"); - -byte[] again = img.Encode(); -Console.WriteLine($"re-encoded: {again.Length} bytes, identical: {again.AsSpan().SequenceEqual(file)}"); - -var rgba = new byte[64 * 64 * 4]; -for (int i = 0; i < rgba.Length; i += 4) { rgba[i] = (byte)(i / 4 % 64 * 4); rgba[i + 1] = 100; rgba[i + 2] = 200; rgba[i + 3] = 255; } -new YapfImage(64, 64, 4, rgba).Save("csharp.yapf"); -Console.WriteLine("wrote csharp.yapf"); diff --git a/bindings/csharp/README.md b/bindings/csharp/README.md deleted file mode 100644 index 0aeb9dc..0000000 --- a/bindings/csharp/README.md +++ /dev/null @@ -1,19 +0,0 @@ -# YAPF for C# / .NET - -`Yapf.cs` is a single-file P/Invoke wrapper for .NET 6 or later (tested with -.NET 8). It should also work in Unity with the native library in -`Assets/Plugins`, but that is not tested yet. Add it to your project and put -the native library next to your program: `yapf.dll` (Windows), -`libyapf.so` (Linux) or `libyapf.dylib` (macOS) — from the -[Releases](https://github.com/Nexoniarz/YAPF/releases) or `make`. - -```csharp -using Yapf; - -var img = YapfImage.Load("texture.yapf"); // or YapfImage.Decode(bytes) -byte[] pixels = img.Pixels; // Width * Height * Channels -new YapfImage(256, 256, 4, rgba).Save("out.yapf"); // or .Encode() → byte[] -``` - -Example: `cd Example && dotnet run -- ../../../other/YAPF.YAPF` -(Linux: `LD_LIBRARY_PATH=../../../build dotnet run …` after `make`). diff --git a/bindings/csharp/Yapf.cs b/bindings/csharp/Yapf.cs deleted file mode 100644 index 64d23ef..0000000 --- a/bindings/csharp/Yapf.cs +++ /dev/null @@ -1,121 +0,0 @@ -// Yapf.cs — C# bindings for YAPF (P/Invoke). Copyright 2026 Nexoniarz — Apache 2.0. -// -// Needs the native library next to your program or on the library path: -// yapf.dll (Windows), libyapf.so (Linux), libyapf.dylib (macOS). -// -// var img = YapfImage.Load("texture.yapf"); -// byte[] pixels = img.Pixels; // Width * Height * Channels, rows top to bottom -// byte[] file = new YapfImage(256, 256, 4, myRgba).Encode(); -using System; -using System.IO; -using System.Runtime.InteropServices; - -namespace Yapf -{ - public sealed class YapfException : Exception - { - public YapfException(string message) : base(message) { } - } - - public sealed class YapfImage - { - public const byte FlagPremultipliedAlpha = 1, FlagSrgb = 2; - - public int Width { get; } - public int Height { get; } - public int Channels { get; } // 1 gray, 2 gray+alpha, 3 RGB, 4 RGBA - public byte Flags { get; } - public byte GpuFormat { get; } - public byte[] Pixels => Mips[0]; - public byte[][] Mips { get; } // Mips[0] is the full-size image - - public YapfImage(int width, int height, int channels, byte[] pixels, - byte flags = FlagSrgb, byte[][]? mips = null) - { - if (pixels.Length != width * height * channels) - throw new ArgumentException("pixels must hold width * height * channels bytes"); - Width = width; Height = height; Channels = channels; Flags = flags; - GpuFormat = channels switch { 4 => (byte)4, 3 => (byte)5, 2 => (byte)2, _ => (byte)3 }; - Mips = mips ?? new[] { pixels }; - Mips[0] = pixels; - } - - private YapfImage(Native n) - { - Width = (int)n.width; Height = (int)n.height; Channels = n.channels; - Flags = n.flags; GpuFormat = n.gpu_format; - Mips = new byte[n.mip_levels][]; - for (int m = 0; m < n.mip_levels; m++) - { - int w = Math.Max(1, Width >> m), h = Math.Max(1, Height >> m); - Mips[m] = new byte[w * h * Channels]; - Marshal.Copy(Marshal.ReadIntPtr(n.mips, m * IntPtr.Size), Mips[m], 0, Mips[m].Length); - } - } - - /// Decode YAPF bytes. threads: 1 = calling thread, 0 = all cores. - public static YapfImage Decode(byte[] data, int threads = 1) - { - IntPtr p = NativeMethods.yapf_load_memory_mt(data, (UIntPtr)data.Length, threads); - if (p == IntPtr.Zero) throw new YapfException("not a valid YAPF file"); - try { return new YapfImage(Marshal.PtrToStructure(p)); } - finally { NativeMethods.yapf_free(p); } - } - - public static YapfImage Load(string path, int threads = 1) => Decode(File.ReadAllBytes(path), threads); - - /// Encode to the bytes of a .yapf file. - public byte[] Encode() - { - var handles = new GCHandle[Mips.Length]; - IntPtr table = Marshal.AllocHGlobal(IntPtr.Size * Mips.Length); - try - { - for (int m = 0; m < Mips.Length; m++) - { - handles[m] = GCHandle.Alloc(Mips[m], GCHandleType.Pinned); - Marshal.WriteIntPtr(table, m * IntPtr.Size, handles[m].AddrOfPinnedObject()); - } - var n = new Native - { - width = (uint)Width, height = (uint)Height, channels = (byte)Channels, - gpu_format = GpuFormat, flags = Flags, mip_levels = (byte)Mips.Length, - pixels = handles[0].AddrOfPinnedObject(), mips = table, - }; - int rc = NativeMethods.yapf_encode(ref n, out IntPtr data, out UIntPtr size); - if (rc != 0) throw new YapfException($"yapf_encode failed ({rc})"); - try - { - var bytes = new byte[(int)size]; - Marshal.Copy(data, bytes, 0, bytes.Length); - return bytes; - } - finally { NativeMethods.yapf_free_buffer(data); } - } - finally - { - foreach (var h in handles) if (h.IsAllocated) h.Free(); - Marshal.FreeHGlobal(table); - } - } - - public void Save(string path) => File.WriteAllBytes(path, Encode()); - - [StructLayout(LayoutKind.Sequential)] - private struct Native - { - public uint width, height; - public byte channels, gpu_format, flags, mip_levels; - public IntPtr pixels, mips; - } - - private static class NativeMethods - { - private const string Lib = "yapf"; - [DllImport(Lib)] public static extern IntPtr yapf_load_memory_mt(byte[] data, UIntPtr size, int threads); - [DllImport(Lib)] public static extern void yapf_free(IntPtr img); - [DllImport(Lib)] public static extern int yapf_encode(ref Native img, out IntPtr data, out UIntPtr size); - [DllImport(Lib)] public static extern void yapf_free_buffer(IntPtr data); - } - } -} diff --git a/bindings/go/README.md b/bindings/go/README.md deleted file mode 100644 index f889865..0000000 --- a/bindings/go/README.md +++ /dev/null @@ -1,17 +0,0 @@ -# YAPF for Go - -A cgo package that builds the C library itself (needs a C compiler, as any -cgo package). - -```sh -go get github.com/Nexoniarz/YAPF/bindings/go -``` - -```go -import yapf "github.com/Nexoniarz/YAPF/bindings/go" - -img, err := yapf.Load("texture.yapf") // or yapf.Decode(bytes) -data, err := yapf.Encode(&yapf.Image{Width: 256, Height: 256, Channels: 4, Pixels: rgba}) -``` - -Example: `go run ./example ../../other/YAPF.YAPF` · tests: `go test`. diff --git a/bindings/go/example/main.go b/bindings/go/example/main.go deleted file mode 100644 index 5fac6ea..0000000 --- a/bindings/go/example/main.go +++ /dev/null @@ -1,47 +0,0 @@ -// go run ./example ../../other/YAPF.YAPF -package main - -import ( - "bytes" - "fmt" - "os" - "time" - - yapf "github.com/Nexoniarz/YAPF/bindings/go" -) - -func main() { - path := "../../other/YAPF.YAPF" - if len(os.Args) > 1 { - path = os.Args[1] - } - file, err := os.ReadFile(path) - if err != nil { - panic(err) - } - img, err := yapf.Decode(file) - if err != nil { - panic(err) - } - best := time.Hour // best of 10, as in a running program - for i := 0; i < 10; i++ { - t := time.Now() - img, _ = yapf.Decode(file) - best = min(best, time.Since(t)) - } - fmt.Printf("%s: %dx%d, %d channels, decoded in %.2f ms\n", path, img.Width, img.Height, - img.Channels, float64(best.Microseconds())/1000) - fmt.Printf("file is %d bytes, %.1f%% of the raw pixels\n", len(file), 100*float64(len(file))/float64(len(img.Pixels))) - - again, _ := yapf.Encode(img) - fmt.Printf("re-encoded: %d bytes, identical: %v\n", len(again), bytes.Equal(again, file)) - - px := make([]byte, 128*128) - for i := range px { - px[i] = byte(i % 128 * 2) - } - if err := yapf.Save("go.yapf", &yapf.Image{Width: 128, Height: 128, Channels: 1, Flags: yapf.FlagSRGB, Pixels: px}); err != nil { - panic(err) - } - fmt.Println("wrote go.yapf") -} diff --git a/bindings/go/go.mod b/bindings/go/go.mod deleted file mode 100644 index 13f58b7..0000000 --- a/bindings/go/go.mod +++ /dev/null @@ -1,3 +0,0 @@ -module github.com/Nexoniarz/YAPF/bindings/go - -go 1.21 diff --git a/bindings/go/yapf.go b/bindings/go/yapf.go deleted file mode 100644 index 5869d5b..0000000 --- a/bindings/go/yapf.go +++ /dev/null @@ -1,111 +0,0 @@ -// Package yapf reads and writes YAPF lossless images (cgo bindings to the C library). -// -// img, err := yapf.Load("texture.yapf") -// data, err := yapf.Encode(&yapf.Image{Width: 256, Height: 256, Channels: 4, Pixels: rgba}) -package yapf - -/* -#cgo CFLAGS: -O2 -std=c99 -I${SRCDIR}/../.. -#cgo !windows LDFLAGS: -lm -lpthread -#include -#include "yapf.h" -*/ -import "C" - -import ( - "errors" - "os" - "unsafe" -) - -const ( - FlagPremultAlpha = 1 - FlagSRGB = 2 -) - -var ErrInvalid = errors.New("yapf: not a valid YAPF file") - -// Image holds Width*Height*Channels bytes in Pixels, rows top to bottom. -// Channels: 1 gray, 2 gray+alpha, 3 RGB, 4 RGBA. Mips holds the smaller -// mip levels (1, 2, …), if any. -type Image struct { - Width, Height int - Channels int - Flags uint8 - GPUFormat uint8 - Pixels []byte - Mips [][]byte -} - -// Decode decodes YAPF bytes on the calling thread; DecodeThreads(data, 0) uses every core. -func Decode(data []byte) (*Image, error) { return DecodeThreads(data, 1) } - -func DecodeThreads(data []byte, threads int) (*Image, error) { - if len(data) == 0 { - return nil, ErrInvalid - } - p := C.yapf_load_memory_mt(unsafe.Pointer(&data[0]), C.size_t(len(data)), C.int(threads)) - if p == nil { - return nil, ErrInvalid - } - defer C.yapf_free(p) - img := &Image{Width: int(p.width), Height: int(p.height), Channels: int(p.channels), - Flags: uint8(p.flags), GPUFormat: uint8(p.gpu_format)} - mips := unsafe.Slice(p.mips, int(p.mip_levels)) - for m := range mips { - w, h := max(1, img.Width>>m), max(1, img.Height>>m) - level := C.GoBytes(unsafe.Pointer(mips[m]), C.int(w*h*img.Channels)) - if m == 0 { - img.Pixels = level - } else { - img.Mips = append(img.Mips, level) - } - } - return img, nil -} - -func Load(path string) (*Image, error) { - data, err := os.ReadFile(path) - if err != nil { - return nil, err - } - return Decode(data) -} - -// Encode returns the bytes of a .yapf file. -func Encode(img *Image) ([]byte, error) { - if img.Channels < 1 || img.Channels > 4 || len(img.Pixels) != img.Width*img.Height*img.Channels { - return nil, errors.New("yapf: pixels must hold Width*Height*Channels bytes") - } - // Copy the levels into C memory: cgo forbids passing Go pointers inside C structs. - levels := append([][]byte{img.Pixels}, img.Mips...) - table := (**C.uint8_t)(C.malloc(C.size_t(len(levels)) * C.size_t(unsafe.Sizeof(uintptr(0))))) - defer C.free(unsafe.Pointer(table)) - ptrs := unsafe.Slice(table, len(levels)) - for i, l := range levels { - ptrs[i] = (*C.uint8_t)(C.CBytes(l)) - defer C.free(unsafe.Pointer(ptrs[i])) - } - gpu := img.GPUFormat - if gpu == 0 { - gpu = map[int]uint8{4: 4, 3: 5, 2: 2, 1: 3}[img.Channels] - } - raw := C.yapf_image_t{width: C.uint32_t(img.Width), height: C.uint32_t(img.Height), - channels: C.uint8_t(img.Channels), gpu_format: C.uint8_t(gpu), flags: C.uint8_t(img.Flags), - mip_levels: C.uint8_t(len(levels)), pixels: ptrs[0], mips: table} - var data unsafe.Pointer - var size C.size_t - if rc := C.yapf_encode(&raw, &data, &size); rc != 0 { - return nil, errors.New("yapf: encoding failed") - } - defer C.yapf_free_buffer(data) - return C.GoBytes(data, C.int(size)), nil -} - -func Save(path string, img *Image) error { - data, err := Encode(img) - if err != nil { - return err - } - return os.WriteFile(path, data, 0o644) -} diff --git a/bindings/go/yapf_c.c b/bindings/go/yapf_c.c deleted file mode 100644 index 006b23c..0000000 --- a/bindings/go/yapf_c.c +++ /dev/null @@ -1,2 +0,0 @@ -// Builds the C library as part of this Go package (cgo compiles .c files here). -#include "../../yapf.c" diff --git a/bindings/go/yapf_test.go b/bindings/go/yapf_test.go deleted file mode 100644 index 7910b1c..0000000 --- a/bindings/go/yapf_test.go +++ /dev/null @@ -1,46 +0,0 @@ -package yapf - -import ( - "bytes" - "os" - "testing" -) - -func TestRoundtrip(t *testing.T) { - for ch := 1; ch <= 4; ch++ { - w, h := 97, 61 - px := make([]byte, w*h*ch) - for i := range px { - px[i] = byte(i*7 ^ i>>5) - } - data, err := Encode(&Image{Width: w, Height: h, Channels: ch, Flags: FlagSRGB, Pixels: px}) - if err != nil { - t.Fatal(err) - } - back, err := Decode(data) - if err != nil || !bytes.Equal(back.Pixels, px) { - t.Fatalf("roundtrip failed for %d channels", ch) - } - } -} - -func TestSampleReencodesIdentically(t *testing.T) { - file, err := os.ReadFile("../../other/YAPF.YAPF") - if err != nil { - t.Skip("sample not found") - } - img, err := Decode(file) - if err != nil { - t.Fatal(err) - } - again, _ := Encode(img) - if !bytes.Equal(again, file) { - t.Fatal("re-encoded sample differs from the C encoder's output") - } -} - -func TestRejectsGarbage(t *testing.T) { - if _, err := Decode([]byte("not an image")); err == nil { - t.Fatal("garbage was accepted") - } -} diff --git a/bindings/java/Example.java b/bindings/java/Example.java deleted file mode 100644 index d12f7ca..0000000 --- a/bindings/java/Example.java +++ /dev/null @@ -1,29 +0,0 @@ -// java --enable-native-access=ALL-UNNAMED -Dyapf.library=../../build/libyapf.so Example.java ../../other/YAPF.YAPF -import java.nio.file.Files; -import java.nio.file.Path; -import java.util.Arrays; - -public class Example { - public static void main(String[] args) throws Exception { - Path path = Path.of(args.length > 0 ? args[0] : "../../other/YAPF.YAPF"); - byte[] file = Files.readAllBytes(path); - - Yapf.Image img = Yapf.decode(file); // first call also loads the library - double ms = Double.MAX_VALUE; // best of 10, as in a running program - for (int i = 0; i < 10; i++) { - long t = System.nanoTime(); - img = Yapf.decode(file); - ms = Math.min(ms, (System.nanoTime() - t) / 1e6); - } - System.out.printf("%s: %dx%d, %d channels, decoded in %.2f ms%n", path, img.width(), img.height(), img.channels(), ms); - System.out.printf("file is %d bytes, %.1f%% of the raw pixels%n", file.length, 100.0 * file.length / img.pixels().length); - - byte[] again = Yapf.encode(img); - System.out.printf("re-encoded: %d bytes, identical: %b%n", again.length, Arrays.equals(again, file)); - - byte[] rgb = new byte[64 * 64 * 3]; - for (int i = 0; i < rgb.length; i++) rgb[i] = (byte) (i * 3); - Yapf.save(Path.of("java.yapf"), new Yapf.Image(64, 64, 3, rgb)); - System.out.println("wrote java.yapf"); - } -} diff --git a/bindings/java/README.md b/bindings/java/README.md deleted file mode 100644 index 605ce11..0000000 --- a/bindings/java/README.md +++ /dev/null @@ -1,16 +0,0 @@ -# YAPF for Java (and Kotlin) - -`Yapf.java` uses the Foreign Function & Memory API of **Java 22+** — no JNI, -no native glue to build; just the YAPF shared library (`yapf.dll`, -`libyapf.so`, `libyapf.dylib`) on the library path or passed with -`-Dyapf.library=/path/to/lib`. - -```java -Yapf.Image img = Yapf.load(Path.of("texture.yapf")); // or Yapf.decode(bytes) -byte[] file = Yapf.encode(new Yapf.Image(256, 256, 4, rgba)); -``` - -Kotlin can call the same class directly. Run with -`--enable-native-access=ALL-UNNAMED` to silence the native-access warning. - -Example: `java --enable-native-access=ALL-UNNAMED -Dyapf.library=../../build/libyapf.so Example.java` diff --git a/bindings/java/Yapf.java b/bindings/java/Yapf.java deleted file mode 100644 index 80e97c5..0000000 --- a/bindings/java/Yapf.java +++ /dev/null @@ -1,121 +0,0 @@ -// Yapf.java — YAPF for Java 22+ via the Foreign Function & Memory API (no JNI). -// Copyright 2026 Nexoniarz — Apache License 2.0. -// -// Needs the native library: yapf.dll / libyapf.so / libyapf.dylib on the -// library path, or its full path in the system property -Dyapf.library=... -// Run with --enable-native-access=ALL-UNNAMED to avoid the warning. -// -// Yapf.Image img = Yapf.load(Path.of("texture.yapf")); -// byte[] file = Yapf.encode(new Yapf.Image(256, 256, 4, rgba)); - -import java.io.IOException; -import java.lang.foreign.*; -import java.lang.invoke.MethodHandle; -import java.nio.file.Files; -import java.nio.file.Path; - -import static java.lang.foreign.ValueLayout.*; - -public final class Yapf { - public static final int FLAG_PREMULT_ALPHA = 1, FLAG_SRGB = 2; - - /** pixels: width*height*channels bytes, rows top to bottom. mips[0] == pixels. */ - public record Image(int width, int height, int channels, int flags, int gpuFormat, byte[][] mips) { - public Image(int width, int height, int channels, byte[] pixels) { - this(width, height, channels, FLAG_SRGB, switch (channels) { case 4 -> 4; case 3 -> 5; case 2 -> 2; default -> 3; }, - new byte[][] { pixels }); - } - public byte[] pixels() { return mips[0]; } - } - - // yapf_image_t: u32 width, u32 height, u8 channels, gpu_format, flags, mip_levels, ptr pixels, ptr mips - private static final StructLayout IMAGE = MemoryLayout.structLayout( - JAVA_INT.withName("width"), JAVA_INT.withName("height"), - JAVA_BYTE.withName("channels"), JAVA_BYTE.withName("gpu_format"), - JAVA_BYTE.withName("flags"), JAVA_BYTE.withName("mip_levels"), - MemoryLayout.paddingLayout(4), ADDRESS.withName("pixels"), ADDRESS.withName("mips")); - - private static final MethodHandle LOAD, FREE, ENCODE, FREE_BUFFER; - static { - Linker linker = Linker.nativeLinker(); - String custom = System.getProperty("yapf.library"); - SymbolLookup lib = custom != null - ? SymbolLookup.libraryLookup(Path.of(custom), Arena.global()) - : SymbolLookup.libraryLookup(System.mapLibraryName("yapf"), Arena.global()); - LOAD = linker.downcallHandle(lib.find("yapf_load_memory_mt").orElseThrow(), - FunctionDescriptor.of(ADDRESS, ADDRESS, JAVA_LONG, JAVA_INT)); - FREE = linker.downcallHandle(lib.find("yapf_free").orElseThrow(), FunctionDescriptor.ofVoid(ADDRESS)); - ENCODE = linker.downcallHandle(lib.find("yapf_encode").orElseThrow(), - FunctionDescriptor.of(JAVA_INT, ADDRESS, ADDRESS, ADDRESS)); - FREE_BUFFER = linker.downcallHandle(lib.find("yapf_free_buffer").orElseThrow(), FunctionDescriptor.ofVoid(ADDRESS)); - } - - private Yapf() {} - - /** Decode YAPF bytes; threads = 1 decodes on this thread, 0 uses every core. */ - public static Image decode(byte[] data, int threads) { - try (Arena arena = Arena.ofConfined()) { - MemorySegment in = arena.allocateFrom(JAVA_BYTE, data); - MemorySegment p = (MemorySegment) LOAD.invokeExact(in, (long) data.length, threads); - if (p.equals(MemorySegment.NULL)) throw new IllegalArgumentException("not a valid YAPF file"); - try { - MemorySegment s = p.reinterpret(IMAGE.byteSize()); - int w = s.get(JAVA_INT, 0), h = s.get(JAVA_INT, 4); - int ch = Byte.toUnsignedInt(s.get(JAVA_BYTE, 8)), levels = Byte.toUnsignedInt(s.get(JAVA_BYTE, 11)); - MemorySegment table = s.get(ADDRESS, 24).reinterpret(ADDRESS.byteSize() * levels); - byte[][] mips = new byte[levels][]; - for (int m = 0; m < levels; m++) { - long n = (long) Math.max(1, w >> m) * Math.max(1, h >> m) * ch; - mips[m] = table.getAtIndex(ADDRESS, m).reinterpret(n).toArray(JAVA_BYTE); - } - return new Image(w, h, ch, Byte.toUnsignedInt(s.get(JAVA_BYTE, 10)), - Byte.toUnsignedInt(s.get(JAVA_BYTE, 9)), mips); - } finally { - FREE.invokeExact(p); - } - } catch (RuntimeException e) { - throw e; - } catch (Throwable t) { - throw new IllegalStateException(t); - } - } - - public static Image decode(byte[] data) { return decode(data, 1); } - - public static Image load(Path path) throws IOException { return decode(Files.readAllBytes(path)); } - - /** Encode to the bytes of a .yapf file. */ - public static byte[] encode(Image img) { - if (img.pixels().length != img.width() * img.height() * img.channels()) - throw new IllegalArgumentException("pixels must hold width*height*channels bytes"); - try (Arena arena = Arena.ofConfined()) { - byte[][] mips = img.mips(); - MemorySegment table = arena.allocate(ADDRESS, mips.length); - for (int m = 0; m < mips.length; m++) table.setAtIndex(ADDRESS, m, arena.allocateFrom(JAVA_BYTE, mips[m])); - MemorySegment s = arena.allocate(IMAGE); - s.set(JAVA_INT, 0, img.width()); - s.set(JAVA_INT, 4, img.height()); - s.set(JAVA_BYTE, 8, (byte) img.channels()); - s.set(JAVA_BYTE, 9, (byte) img.gpuFormat()); - s.set(JAVA_BYTE, 10, (byte) img.flags()); - s.set(JAVA_BYTE, 11, (byte) mips.length); - s.set(ADDRESS, 16, table.getAtIndex(ADDRESS, 0)); - s.set(ADDRESS, 24, table); - MemorySegment outData = arena.allocate(ADDRESS), outSize = arena.allocate(JAVA_LONG); - int rc = (int) ENCODE.invokeExact(s, outData, outSize); - if (rc != 0) throw new IllegalStateException("yapf_encode failed (" + rc + ")"); - MemorySegment data = outData.get(ADDRESS, 0); - try { - return data.reinterpret(outSize.get(JAVA_LONG, 0)).toArray(JAVA_BYTE); - } finally { - FREE_BUFFER.invokeExact(data); - } - } catch (RuntimeException e) { - throw e; - } catch (Throwable t) { - throw new IllegalStateException(t); - } - } - - public static void save(Path path, Image img) throws IOException { Files.write(path, encode(img)); } -} diff --git a/bindings/js/README.md b/bindings/js/README.md deleted file mode 100644 index a121a1c..0000000 --- a/bindings/js/README.md +++ /dev/null @@ -1,43 +0,0 @@ -# yapf.js — YAPF in JavaScript - -Encoder (version 1) and decoder (versions 1 and 2) in one dependency-free file. Works in -browsers, Node.js, web workers, Figma plugins and VS Code webviews, and -produces exactly the same bytes as the C library. - -```js -const YAPF = require('./yapf.js'); // or - - - - diff --git a/extensions/figma/ui.html b/extensions/figma/ui.html deleted file mode 100644 index 167bd23..0000000 --- a/extensions/figma/ui.html +++ /dev/null @@ -1,1430 +0,0 @@ - - - - - - - -
- - -
- -
-

Import YAPF images

-
Drop .yapf files here
or click to choose
- -
- - - -
- - - - - - diff --git a/extensions/gimp/README.md b/extensions/gimp/README.md deleted file mode 100644 index f350ff1..0000000 --- a/extensions/gimp/README.md +++ /dev/null @@ -1,62 +0,0 @@ -# YAPF for GIMP - -Open and export `.yapf` images in **GIMP 3.0 or later**. - -- **File → Open** reads every `.yapf` file, version 1 and 2: Gray, Gray + - Alpha, RGB, RGBA in 8-bit, 16-bit, half and float precision; GPU blocks - (BC1–BC7, BC6H HDR) decoded for viewing; cube faces, array layers, volume - slices and animation frames as separate layers. When a file cannot be - opened, the message says why (damaged, truncated, not YAPF, newer format). -- **File → Export As… → `name.yapf`** writes the visible image (layers are - flattened into a copy; your document is untouched), with an optional - **Store mipmaps** checkbox for game engines. - -## Install - -You need GIMP 3 with its development files (`gimptool`). - -| System | Development files | -| :-------------- | :-------------------------------------------------- | -| Arch / Manjaro | `sudo pacman -S gimp` (includes them) | -| Debian / Ubuntu | `sudo apt install libgimp-3.0-dev` (GIMP 3 packages) | -| Fedora | `sudo dnf install gimp-devel` | -| NixOS | `nix-shell gimp-shell.nix` (in this folder), then build inside that shell | -| Windows | MSYS2: `pacman -S mingw-w64-ucrt-x86_64-gimp` | -| macOS | build GIMP 3 from source or use MacPorts/Homebrew | - -Then, from this folder: - -```sh -gimptool --install yapf-gimp.c -``` - -That compiles the plugin (it pulls in `../../yapf.c` itself) and installs it -into your personal GIMP plug-ins folder. Restart GIMP. - -On NixOS, build with the same nixpkgs channel your GIMP comes from (the -plugin links against that GIMP's libraries), and build it again after a -GIMP update. Your GIMP must be GIMP 3: `environment.systemPackages = [ -pkgs.gimp3 ];`, or `nix-shell -p gimp3 --run gimp` to try it. - -### Manual build - -```sh -gcc -O2 $(pkg-config --cflags gimpui-3.0) yapf-gimp.c $(pkg-config --libs gimpui-3.0) -o yapf-gimp -``` - -Copy `yapf-gimp` to `/plug-ins/yapf-gimp/yapf-gimp`, where the -GIMP config folder is `~/.config/GIMP/3.0` on Linux, -`%APPDATA%\GIMP\3.0` on Windows and -`~/Library/Application Support/GIMP/3.0` on macOS. - -## Notes - -- Pixels are saved with the sRGB flag, because GIMP's 8-bit buffers are - gamma encoded. Files marked linear load as linear. -- When a file has mipmaps, GIMP opens the full-size image. -- ETC2 / EAC / ASTC blocks cannot be shown yet. Export writes 8-bit - version 1 files, as before. -- Tested with GIMP 3.0.8 on Linux: opening matches the reference decoder - pixel for pixel, and export equals GIMP's own flattened PNG of the image. - The version 2 loader was tested in GIMP 3.0.6 (nixpkgs 25.05, headless): - BC7, BC5, BC6H, half float, 16-bit, cube, animation and a damaged file. diff --git a/extensions/gimp/gimp-shell.nix b/extensions/gimp/gimp-shell.nix deleted file mode 100644 index 7a8fadf..0000000 --- a/extensions/gimp/gimp-shell.nix +++ /dev/null @@ -1,7 +0,0 @@ -# Development shell for building the plugin on NixOS: nix-shell gimp-shell.nix -# `gimp3` is GIMP 3 on every channel (on unstable it is an alias of `gimp`). -with import {}; -mkShell { - nativeBuildInputs = [ pkg-config ]; - buildInputs = [ gimp3 gimp3.dev gtk3 glib gdk-pixbuf gegl babl cairo pango ]; -} diff --git a/extensions/gimp/yapf-gimp.c b/extensions/gimp/yapf-gimp.c deleted file mode 100644 index 948ee13..0000000 --- a/extensions/gimp/yapf-gimp.c +++ /dev/null @@ -1,420 +0,0 @@ -/* - * yapf-gimp.c — YAPF format plugin for GIMP. - * - * This plugin is an independent work provided under the Apache License 2.0. - * It interfaces with GIMP, which is licensed under GPLv3. Users may use, - * modify, and distribute this plugin independently of GIMP's licensing terms. - * - * Copyright 2026 Nexoniarz - * - * Licensed under the Apache License, Version 2.0 (the "License"); - * you may not use this file except in compliance with the License. - * You may obtain a copy of the License at - * - * http://www.apache.org/licenses/LICENSE-2.0 - * - * Unless required by applicable law or agreed to in writing, software - * distributed under the License is distributed on an "AS IS" BASIS, - * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. - * See the License for the specific language governing permissions and - * limitations under the License. - * - * ------------------------------------------------------------------------- - * - * Compilation (from this folder): - * gimptool --install yapf-gimp.c - * - * yapf.c (two folders up) is embedded via #include below because gimptool - * compiles a single source file. Do NOT link it separately. - */ - -#include -#include - -/* Pull in the entire encoder/decoder as a single translation unit. */ -#include "../../yapf.c" - -/* ── GIMP procedure names ────────────────────────────────────────────── */ - -#define LOAD_PROC "file-yapf-load" -#define SAVE_PROC "file-yapf-save" -#define PLUG_IN_BINARY "yapf-gimp" - -/* ── Plugin type boilerplate ─────────────────────────────────────────── */ - -struct _YapfPlugin { GimpPlugIn parent_instance; }; - -#define YAPF_PLUGIN_TYPE (yapf_plugin_get_type()) -G_DECLARE_FINAL_TYPE(YapfPlugin, yapf_plugin, YAPF, PLUGIN, GimpPlugIn) - -static GList *yapf_plugin_query_procedures (GimpPlugIn *plug_in); -static GimpProcedure *yapf_plugin_create_procedure (GimpPlugIn *plug_in, - const gchar *name); - -static GimpValueArray *yapf_load_run (GimpProcedure *procedure, - GimpRunMode run_mode, - GFile *file, - GimpMetadata *metadata, - GimpMetadataLoadFlags *flags, - GimpProcedureConfig *config, - gpointer run_data); -static GimpValueArray *yapf_save_run (GimpProcedure *procedure, - GimpRunMode run_mode, - GimpImage *image, - GFile *file, - GimpExportOptions *options, - GimpMetadata *metadata, - GimpProcedureConfig *config, - gpointer run_data); - -G_DEFINE_TYPE(YapfPlugin, yapf_plugin, GIMP_TYPE_PLUG_IN) - -static void yapf_plugin_class_init(YapfPluginClass *klass) { - GimpPlugInClass *plug_in_class = GIMP_PLUG_IN_CLASS(klass); - plug_in_class->query_procedures = yapf_plugin_query_procedures; - plug_in_class->create_procedure = yapf_plugin_create_procedure; -} - -static void yapf_plugin_init(YapfPlugin *plugin) { (void)plugin; } - -/* ── Procedure list ──────────────────────────────────────────────────── */ - -static GList *yapf_plugin_query_procedures(GimpPlugIn *plug_in) { - (void)plug_in; - GList *list = NULL; - list = g_list_append(list, g_strdup(LOAD_PROC)); - list = g_list_append(list, g_strdup(SAVE_PROC)); - return list; -} - -/* ── Procedure creation ──────────────────────────────────────────────── */ - -static GimpProcedure *yapf_plugin_create_procedure(GimpPlugIn *plug_in, - const gchar *name) { - GimpProcedure *procedure = NULL; - - if (g_strcmp0(name, LOAD_PROC) == 0) { - procedure = gimp_load_procedure_new(plug_in, name, - GIMP_PDB_PROC_TYPE_PLUGIN, - yapf_load_run, NULL, NULL); - gimp_procedure_set_menu_label(procedure, "YAPF image"); - gimp_procedure_set_documentation(procedure, - "Loads a YAPF (Yet Another Picture Format) image", - "Loads a YAPF image from disk", NULL); - gimp_procedure_set_attribution(procedure, - "Nexoniarz", "Nexoniarz", "2026"); - gimp_file_procedure_set_mime_types(GIMP_FILE_PROCEDURE(procedure), - "image/x-yapf"); - gimp_file_procedure_set_extensions(GIMP_FILE_PROCEDURE(procedure), - "yapf"); - gimp_file_procedure_set_magics(GIMP_FILE_PROCEDURE(procedure), - "0,string,YAPF"); - - } else if (g_strcmp0(name, SAVE_PROC) == 0) { - procedure = gimp_export_procedure_new(plug_in, name, - GIMP_PDB_PROC_TYPE_PLUGIN, TRUE, - (GimpRunExportFunc)yapf_save_run, NULL, NULL); - gimp_procedure_set_image_types(procedure, "RGB, RGBA, GRAY, GRAYA"); - gimp_procedure_set_menu_label(procedure, "YAPF image"); - gimp_procedure_set_documentation(procedure, - "Exports a YAPF (Yet Another Picture Format) image", - "Exports a YAPF image to disk", NULL); - gimp_procedure_set_attribution(procedure, - "Nexoniarz", "Nexoniarz", "2026"); - gimp_file_procedure_set_mime_types(GIMP_FILE_PROCEDURE(procedure), - "image/x-yapf"); - gimp_file_procedure_set_extensions(GIMP_FILE_PROCEDURE(procedure), - "yapf"); - /* GIMP flattens / converts a copy of the image for us as needed. */ - gimp_export_procedure_set_capabilities(GIMP_EXPORT_PROCEDURE(procedure), - GIMP_EXPORT_CAN_HANDLE_RGB | GIMP_EXPORT_CAN_HANDLE_GRAY | - GIMP_EXPORT_CAN_HANDLE_ALPHA, NULL, NULL, NULL); - gimp_procedure_add_boolean_argument(procedure, "mipmaps", - "Store _mipmaps", - "Also store a full mip chain (for game engines and GPUs)", - FALSE, G_PARAM_READWRITE); - } - - return procedure; -} - -static GimpValueArray *yapf_error(GimpProcedure *procedure, const gchar *msg); - -/* ── Load handler ────────────────────────────────────────────────────── */ - -/* Why a file could not be opened, in words. */ -static gchar *yapf_load_reason(const gchar *path, int err) { - FILE *f = fopen(path, "rb"); - uint8_t h[8] = {0}; - size_t n = f ? fread(h, 1, sizeof(h), f) : 0; - if (f) fclose(f); - if (!f || err == YAPF_ERR_IO) - return g_strdup("The file cannot be read."); - if (n < 5 || memcmp(h, "YAPF", 4) != 0) - return g_strdup("This is not a YAPF file (it does not start with \"YAPF\")."); - if (h[4] != 1 && h[4] != 2) - return g_strdup_printf("This YAPF file is format version %u; this plug-in reads " - "versions 1 and 2. Update the plug-in.", h[4]); - switch (err) { - case YAPF_ERR_UNSUPPORTED: - return g_strdup("This YAPF file needs a feature this plug-in does not have yet. " - "Update the plug-in."); - case YAPF_ERR_CHECKSUM: - return g_strdup("This YAPF file is damaged: a checksum does not match."); - case YAPF_ERR_TRUNCATED: - return g_strdup("This YAPF file is incomplete (truncated)."); - case YAPF_ERR_OOM: - return g_strdup("Out of memory."); - default: - return g_strdup_printf("This YAPF file (version %u) is corrupt, or was written by a " - "tool that does not follow the YAPF specification.", h[4]); - } -} - -static const gchar *yapf_face_name(uint32_t f) { - static const gchar *n[6] = { "+X", "-X", "+Y", "-Y", "+Z", "-Z" }; - return f < 6 ? n[f] : "?"; -} - -static GimpValueArray *yapf_load_run( - GimpProcedure *procedure, - GimpRunMode run_mode, - GFile *file, - GimpMetadata *metadata, - GimpMetadataLoadFlags *flags, - GimpProcedureConfig *config, - gpointer run_data) -{ - (void)run_mode; (void)metadata; (void)flags; (void)config; (void)run_data; - - gchar *path = g_file_get_path(file); - int err = 0; - yapf_texture_t *t = yapf_tex_load(path, 0, 0, &err); /* v1 and v2, all cores */ - if (!t) { - gchar *why = yapf_load_reason(path, err); - g_free(path); - GError *e = g_error_new(GIMP_PLUG_IN_ERROR, 0, "Failed to load YAPF file: %s", why); - g_free(why); - return gimp_procedure_new_return_values(procedure, GIMP_PDB_EXECUTION_ERROR, e); - } - g_free(path); - - /* What the pixels look like after decoding: GPU blocks decode to - * RGBA 8-bit, BC6H to RGB half float. */ - gboolean blocks = t->payload == YAPF_PAYLOAD_BLOCKS; - gboolean bc6 = blocks && (t->format == YAPF_GPU_BC6H || t->format == YAPF_GPU_BC6H_SF); - if (blocks && t->format >= YAPF_GPU_ETC2_RGB8) { - yapf_tex_free(t); - return yapf_error(procedure, "Failed to load YAPF file: it holds ETC2 / EAC / ASTC " - "GPU blocks, which this plug-in cannot show yet."); - } - int ch = blocks ? (bc6 ? 3 : 4) : t->channels; - int sample = blocks ? (bc6 ? YAPF_SAMPLE_F16 : YAPF_SAMPLE_U8) : t->sample; - /* sRGB data is gamma encoded; floats are always linear */ - gboolean gamma = (t->flags & YAPF_FLAG_SRGB) && - (sample == YAPF_SAMPLE_U8 || sample == YAPF_SAMPLE_U16); - - static const gchar *chn[2][4] = { { "Y", "YA", "RGB", "RGBA" }, { "Y'", "Y'A", "R'G'B'", "R'G'B'A" } }; - static const gchar *typ[4] = { "u8", "u16", "half", "float" }; - gchar *fmt_name = g_strdup_printf("%s %s", chn[gamma ? 1 : 0][ch - 1], typ[sample]); - const Babl *fmt = babl_format(fmt_name); - g_free(fmt_name); - - GimpPrecision prec; - switch (sample) { - case YAPF_SAMPLE_U16: prec = gamma ? GIMP_PRECISION_U16_NON_LINEAR : GIMP_PRECISION_U16_LINEAR; break; - case YAPF_SAMPLE_F16: prec = GIMP_PRECISION_HALF_LINEAR; break; - case YAPF_SAMPLE_F32: prec = GIMP_PRECISION_FLOAT_LINEAR; break; - default: prec = gamma ? GIMP_PRECISION_U8_NON_LINEAR : GIMP_PRECISION_U8_LINEAR; break; - } - GimpImageBaseType base = ch <= 2 ? GIMP_GRAY : GIMP_RGB; - GimpImageType ltype = ch == 1 ? GIMP_GRAY_IMAGE : ch == 2 ? GIMP_GRAYA_IMAGE - : ch == 3 ? GIMP_RGB_IMAGE : GIMP_RGBA_IMAGE; - - /* Mip 0 of every frame, layer, face and slice becomes one GIMP layer - * (the first at the bottom, as GIMP animations expect). */ - uint32_t w, h, d, faces = yapf_tex_faces(t); - yapf_tex_mip_size(t, 0, &w, &h, &d); - GimpImage *image = gimp_image_new_with_precision(w, h, base, prec); - size_t texel = (size_t)ch * yapf_sample_bytes((uint8_t)sample); - void *tmp = blocks ? g_malloc((size_t)w * h * texel) : NULL; - gint count = (gint)(t->frames * t->layers * faces * d); - - for (uint32_t fr = 0; fr < t->frames; fr++) - for (uint32_t ly = 0; ly < t->layers; ly++) - for (uint32_t fc = 0; fc < faces; fc++) - for (uint32_t z = 0; z < d; z++) { - uint32_t s = yapf_tex_surface(t, fr, ly, fc, 0); - size_t slice = yapf_tex_surface_bytes(t, 0) / d; - const uint8_t *src = (const uint8_t *)t->data[s] + slice * z; - if (blocks) { - yapf_blocks_decode(t->format, src, w, h, tmp); - src = (const uint8_t *)tmp; - } - GString *name = g_string_new(NULL); - if (t->frames > 1) { - g_string_append_printf(name, "Frame %u", fr + 1); - if (t->frame_us) - g_string_append_printf(name, " (%ums)", (t->frame_us[fr] + 500) / 1000); - } - if (t->layers > 1) g_string_append_printf(name, "%sLayer %u", name->len ? ", " : "", ly); - if (faces > 1) g_string_append_printf(name, "%sFace %s", name->len ? ", " : "", yapf_face_name(fc)); - if (d > 1) g_string_append_printf(name, "%sSlice %u", name->len ? ", " : "", z); - if (!name->len) g_string_append(name, "Background"); - - GimpLayer *layer = gimp_layer_new(image, name->str, (gint)w, (gint)h, ltype, - 100.0, gimp_image_get_default_new_layer_mode(image)); - g_string_free(name, TRUE); - gimp_image_insert_layer(image, layer, NULL, 0); - if (count > 1 && !(fr == 0 && ly == 0 && fc == 0 && z == 0)) - gimp_item_set_visible(GIMP_ITEM(layer), FALSE); - GeglBuffer *buffer = gimp_drawable_get_buffer(GIMP_DRAWABLE(layer)); - gegl_buffer_set(buffer, GEGL_RECTANGLE(0, 0, (gint)w, (gint)h), 0, fmt, - src, GEGL_AUTO_ROWSTRIDE); - g_object_unref(buffer); - } - g_free(tmp); - yapf_tex_free(t); - - GimpValueArray *ret = gimp_procedure_new_return_values(procedure, - GIMP_PDB_SUCCESS, NULL); - g_value_set_object(gimp_value_array_index(ret, 1), image); - return ret; -} - -/* ── Save handler ────────────────────────────────────────────────────── */ - -/* Full mip chain with a 2×2 box filter (edges clamp for odd sizes). - * Fills img->mips / img->mip_levels; mips[0] aliases img->pixels. */ -static gboolean yapf_build_mips(yapf_image_t *img) { - int levels = 1; - while (levels < (int)YAPF_MAX_MIPS && - ((img->width >> levels) > 0 || (img->height >> levels) > 0)) - levels++; - img->mips = (uint8_t **)calloc((size_t)levels, sizeof(uint8_t *)); - if (!img->mips) return FALSE; - img->mips[0] = img->pixels; - img->mip_levels = (uint8_t)levels; - - int ch = img->channels; - for (int m = 1; m < levels; m++) { - uint32_t pw = MAX(1u, img->width >> (m - 1)), ph = MAX(1u, img->height >> (m - 1)); - uint32_t w = MAX(1u, img->width >> m), h = MAX(1u, img->height >> m); - const uint8_t *src = img->mips[m - 1]; - uint8_t *dst = (uint8_t *)malloc((size_t)w * h * ch); - if (!dst) return FALSE; - for (uint32_t y = 0; y < h; y++) - for (uint32_t x = 0; x < w; x++) - for (int c = 0; c < ch; c++) { - uint32_t x0 = MIN(2 * x, pw - 1), x1 = MIN(2 * x + 1, pw - 1); - uint32_t y0 = MIN(2 * y, ph - 1), y1 = MIN(2 * y + 1, ph - 1); - unsigned sum = src[((size_t)y0 * pw + x0) * ch + c] + src[((size_t)y0 * pw + x1) * ch + c] - + src[((size_t)y1 * pw + x0) * ch + c] + src[((size_t)y1 * pw + x1) * ch + c]; - dst[((size_t)y * w + x) * ch + c] = (uint8_t)((sum + 2) / 4); - } - img->mips[m] = dst; - } - return TRUE; -} - -static GimpValueArray *yapf_error(GimpProcedure *procedure, const gchar *msg) { - return gimp_procedure_new_return_values(procedure, GIMP_PDB_EXECUTION_ERROR, - g_error_new_literal(GIMP_PLUG_IN_ERROR, 0, msg)); -} - -static GimpValueArray *yapf_save_run( - GimpProcedure *procedure, - GimpRunMode run_mode, - GimpImage *image, - GFile *file, - GimpExportOptions *options, - GimpMetadata *metadata, - GimpProcedureConfig *config, - gpointer run_data) -{ - (void)metadata; (void)run_data; - - if (run_mode == GIMP_RUN_INTERACTIVE) { - gimp_ui_init(PLUG_IN_BINARY); - GtkWidget *dialog = gimp_export_procedure_dialog_new( - GIMP_EXPORT_PROCEDURE(procedure), config, image); - gimp_procedure_dialog_fill(GIMP_PROCEDURE_DIALOG(dialog), NULL); - gboolean ok = gimp_procedure_dialog_run(GIMP_PROCEDURE_DIALOG(dialog)); - gtk_widget_destroy(dialog); - if (!ok) - return gimp_procedure_new_return_values(procedure, GIMP_PDB_CANCEL, NULL); - } - - gboolean mipmaps = FALSE; - g_object_get(config, "mipmaps", &mipmaps, NULL); - - /* A flattened copy when the image has several layers; the visible - * result is what gets exported. */ - GimpExportReturn export = gimp_export_options_get_image(options, &image); - GList *layers = gimp_image_list_layers(image); - if (!layers) { - if (export == GIMP_EXPORT_EXPORT) gimp_image_delete(image); - return yapf_error(procedure, "No layers to export."); - } - GimpDrawable *drawable = GIMP_DRAWABLE(layers->data); - g_list_free(layers); - - gboolean has_alpha = gimp_drawable_has_alpha(drawable); - gboolean is_gray = gimp_drawable_is_gray(drawable); - const gchar *babl_fmt; - uint8_t ch, gpu_fmt; - - /* GIMP's 8-bit buffers are gamma encoded, so pixels are written as sRGB. */ - if (is_gray) { - ch = has_alpha ? YAPF_CHANNELS_GRAY_ALPHA : YAPF_CHANNELS_GRAY; - babl_fmt = has_alpha ? "Y'A u8" : "Y' u8"; - gpu_fmt = has_alpha ? YAPF_GPU_RG8 : YAPF_GPU_R8; - } else { - ch = has_alpha ? YAPF_CHANNELS_RGBA : YAPF_CHANNELS_RGB; - babl_fmt = has_alpha ? "R'G'B'A u8" : "R'G'B' u8"; - gpu_fmt = has_alpha ? YAPF_GPU_SRGB8_A8 : YAPF_GPU_SRGB8; - } - - gint w = gimp_drawable_get_width(drawable); - gint h = gimp_drawable_get_height(drawable); - uint8_t *pixels = (uint8_t *)malloc((size_t)w * (size_t)h * ch); - if (!pixels) { - if (export == GIMP_EXPORT_EXPORT) gimp_image_delete(image); - return yapf_error(procedure, "Out of memory."); - } - - GeglBuffer *buffer = gimp_drawable_get_buffer(drawable); - gegl_buffer_get(buffer, GEGL_RECTANGLE(0, 0, w, h), 1.0, - babl_format(babl_fmt), pixels, - GEGL_AUTO_ROWSTRIDE, GEGL_ABYSS_NONE); - g_object_unref(buffer); - if (export == GIMP_EXPORT_EXPORT) gimp_image_delete(image); - - yapf_image_t img; - memset(&img, 0, sizeof(img)); - img.width = (uint32_t)w; - img.height = (uint32_t)h; - img.channels = ch; - img.gpu_format = gpu_fmt; - img.flags = YAPF_FLAG_SRGB; - img.mip_levels = 1; - img.pixels = pixels; - - int result = YAPF_ERR_OOM; - if (!mipmaps || yapf_build_mips(&img)) { - gchar *path = g_file_get_path(file); - result = yapf_save(path, &img); - g_free(path); - } - if (img.mips) { - for (int m = 1; m < img.mip_levels; m++) free(img.mips[m]); - free(img.mips); - } - free(pixels); - - if (result != YAPF_OK) - return yapf_error(procedure, "Failed to export YAPF file."); - return gimp_procedure_new_return_values(procedure, GIMP_PDB_SUCCESS, NULL); -} - -GIMP_MAIN(YAPF_PLUGIN_TYPE) diff --git a/extensions/kde/CMakeLists.txt b/extensions/kde/CMakeLists.txt deleted file mode 100644 index 453c78e..0000000 --- a/extensions/kde/CMakeLists.txt +++ /dev/null @@ -1,26 +0,0 @@ -# YAPF thumbnails for KDE Dolphin (KF6 KIO thumbnail plugin). -# cmake -B build -DCMAKE_BUILD_TYPE=Release -# cmake --build build -# sudo cmake --install build (or see README.md for a per-user install) -cmake_minimum_required(VERSION 3.16) -project(yapfthumbnail LANGUAGES C CXX) - -find_package(ECM 6.0 REQUIRED NO_MODULE) -set(CMAKE_MODULE_PATH ${ECM_MODULE_PATH}) -include(KDEInstallDirs) -include(KDECMakeSettings) -include(KDECompilerSettings NO_POLICY_SCOPE) - -find_package(Qt6 6.5 REQUIRED COMPONENTS Core Gui) -find_package(KF6 6.0 REQUIRED COMPONENTS KIO) -find_package(Threads REQUIRED) - -kcoreaddons_add_plugin(yapfthumbnail - SOURCES yapfthumbnail.cpp ../../yapf.c - INSTALL_NAMESPACE "kf6/thumbcreator") -set_source_files_properties(../../yapf.c PROPERTIES LANGUAGE C) -target_include_directories(yapfthumbnail PRIVATE ../..) -target_link_libraries(yapfthumbnail PRIVATE KF6::KIOGui Qt6::Gui Threads::Threads) - -# Register the image/x-yapf file type so Dolphin recognises .yapf files. -install(FILES ../linux/yapf-mime.xml DESTINATION ${KDE_INSTALL_MIMEDIR} RENAME yapf.xml) diff --git a/extensions/kde/README.md b/extensions/kde/README.md deleted file mode 100644 index f5b49bc..0000000 --- a/extensions/kde/README.md +++ /dev/null @@ -1,56 +0,0 @@ -# YAPF thumbnails for KDE (Dolphin) - -Shows previews of `.yapf` files in **Dolphin**, the KDE file dialogs and -anything else that uses KIO thumbnails. KDE Frameworks 6 / Plasma 6. -Files with mipmaps are thumbnailed from the nearest mip level, so even huge -textures preview instantly. - -## Build and install - -You need CMake, a C/C++ compiler and the KDE development packages: - -| System | Packages | -| :-------------- | :------- | -| Arch / Manjaro | `sudo pacman -S cmake extra-cmake-modules kio` | -| Debian / Ubuntu | `sudo apt install cmake extra-cmake-modules libkf6kio-dev qt6-base-dev` | -| Fedora | `sudo dnf install cmake extra-cmake-modules kf6-kio-devel qt6-qtbase-devel` | -| openSUSE | `sudo zypper install cmake kf6-extra-cmake-modules kf6-kio-devel qt6-base-devel` | -| NixOS | `nix-shell kde-shell.nix` (in this folder) | - -```sh -cd extensions/kde -cmake -B build -DCMAKE_BUILD_TYPE=Release -DCMAKE_INSTALL_PREFIX=/usr -cmake --build build -sudo cmake --install build -update-mime-database /usr/share/mime -``` - -This installs the plugin (`kf6/thumbcreator/yapfthumbnail.so`) and the -`image/x-yapf` file type. Then in Dolphin: **Settings → Configure Dolphin → -Interface → Previews**, tick **YAPF Images**, and turn previews on. - -### Without root (per user, also NixOS) - -```sh -cmake -B build -DCMAKE_BUILD_TYPE=Release -DCMAKE_INSTALL_PREFIX=$HOME/.local -cmake --build build && cmake --install build -update-mime-database ~/.local/share/mime -mkdir -p ~/.config/plasma-workspace/env -echo 'export QT_PLUGIN_PATH="$HOME/.local/lib/plugins:$QT_PLUGIN_PATH"' > ~/.config/plasma-workspace/env/yapf.sh -``` - -Log out and back in, then enable **YAPF Images** in Dolphin's preview settings. -(Some distributions use `lib64/plugins` or `lib/qt6/plugins`; `cmake ---install` prints the exact folder.) - -## Status - -Built against KF6 / Qt 6 and tested by loading the plugin through KDE's -plugin factory and creating thumbnails (RGBA, RGB, mipmapped, wide images; -corrupt files are rejected). Not yet tried inside a running Dolphin. - -Reads YAPF version 1 and 2: GPU blocks (BC1–BC7, BC6H), 16-bit and float -textures, cubes (face +X), arrays, volumes and animations (the first -image). Only the mip level the thumbnail needs is decoded. Tested with -KF6 from nixpkgs 25.05 on BC7, BC5, BC6H, half float, 16-bit, cube and -animation files. ETC2 / ASTC files get no thumbnail. diff --git a/extensions/kde/kde-shell.nix b/extensions/kde/kde-shell.nix deleted file mode 100644 index bcb1544..0000000 --- a/extensions/kde/kde-shell.nix +++ /dev/null @@ -1,6 +0,0 @@ -# Development shell for building the plugin on NixOS: nix-shell kde-shell.nix -with import {}; -mkShell { - nativeBuildInputs = [ cmake kdePackages.extra-cmake-modules pkg-config ]; - buildInputs = [ kdePackages.kio kdePackages.qtbase kdePackages.kcoreaddons ]; -} diff --git a/extensions/kde/yapfthumbnail.cpp b/extensions/kde/yapfthumbnail.cpp deleted file mode 100644 index fe46adc..0000000 --- a/extensions/kde/yapfthumbnail.cpp +++ /dev/null @@ -1,80 +0,0 @@ -// YAPF thumbnails for KDE Dolphin and other KIO file dialogs. -// Copyright 2026 Nexoniarz — Apache License 2.0. - -#include -#include -#include -#include - -#include - -extern "C" { -#include "yapf.h" -} - -class YapfThumbnailCreator : public KIO::ThumbnailCreator -{ - Q_OBJECT -public: - YapfThumbnailCreator(QObject *parent, const QVariantList &args) - : KIO::ThumbnailCreator(parent, args) - { - } - - KIO::ThumbnailResult create(const KIO::ThumbnailRequest &request) override - { - QFile file(request.url().toLocalFile()); - if (!file.open(QIODevice::ReadOnly)) { - return KIO::ThumbnailResult::fail(); - } - const QByteArray data = file.readAll(); - - // Version 1 and 2: read the tables, then decode only the mip we - // need (frame 0, layer 0, face 0, slice 0). - int err = 0; - yapf_texture_t *tex = yapf_tex_open(data.constData(), size_t(data.size()), 0, &err); - if (!tex) { - return KIO::ThumbnailResult::fail(); - } - - // The smallest stored mip that still covers the requested size; - // Qt scales the rest. - const QSize want = request.targetSize(); - uint32_t m = 0, w = 0, h = 0; - while (m + 1 < tex->mip_levels) { - yapf_tex_mip_size(tex, m + 1, &w, &h, nullptr); - if (int(w) < want.width() || int(h) < want.height()) { - break; - } - ++m; - } - yapf_tex_mip_size(tex, m, &w, &h, nullptr); - const uint32_t s = yapf_tex_surface(tex, 0, 0, 0, m); - - QImage image(int(w), int(h), (tex->flags & YAPF_FLAG_PREMULT_ALPHA) ? QImage::Format_RGBA8888_Premultiplied - : QImage::Format_RGBA8888); - bool ok = !image.isNull() && - yapf_tex_decode_surface(tex, data.constData(), size_t(data.size()), s, 0) == YAPF_OK; - if (ok) { - // RGBA 8-bit rows (blocks decoded, 16-bit / float converted) - QByteArray rgba(int(size_t(w) * h * 4), Qt::Uninitialized); - ok = yapf_tex_to_rgba8(tex, s, 0, reinterpret_cast(rgba.data())) == YAPF_OK; - for (int y = 0; ok && y < int(h); ++y) { - memcpy(image.scanLine(y), rgba.constData() + size_t(y) * w * 4, size_t(w) * 4); - } - } - yapf_tex_free(tex); - if (!ok) { - return KIO::ThumbnailResult::fail(); - } - - if (image.width() > want.width() || image.height() > want.height()) { - image = image.scaled(want, Qt::KeepAspectRatio, Qt::SmoothTransformation); - } - return KIO::ThumbnailResult::pass(image); - } -}; - -K_PLUGIN_CLASS_WITH_JSON(YapfThumbnailCreator, "yapfthumbnail.json") - -#include "yapfthumbnail.moc" diff --git a/extensions/kde/yapfthumbnail.json b/extensions/kde/yapfthumbnail.json deleted file mode 100644 index 4135ab1..0000000 --- a/extensions/kde/yapfthumbnail.json +++ /dev/null @@ -1,7 +0,0 @@ -{ - "CacheThumbnail": true, - "KPlugin": { - "MimeTypes": ["image/x-yapf"], - "Name": "YAPF Images" - } -} diff --git a/extensions/linux/README.md b/extensions/linux/README.md deleted file mode 100644 index b3a4d86..0000000 --- a/extensions/linux/README.md +++ /dev/null @@ -1,34 +0,0 @@ -# Linux desktop integration - -Makes file managers recognise `.yapf` files (MIME type `image/x-yapf`) and -show **thumbnails** for them. - -```sh -sh extensions/linux/install.sh # for your user -sudo sh extensions/linux/install.sh --system -``` - -Thumbnails are made by `yapf thumbnail` (from the `yapf` tool, which must be -on your `PATH` — `sudo make install` puts it in `/usr/local/bin`). They work -in file managers that use freedesktop thumbnailers: GNOME Files (Nautilus), -Nemo, Caja, and Thunar (with tumbler). KDE Dolphin uses its own plugin -system and is not covered yet. - -Thumbnails cover every YAPF file the tool reads: version 1 and 2, GPU -blocks (BC1–BC7, BC6H), 16-bit and float textures, and the first image of -cubes, arrays and animations. KDE Dolphin: see [../kde](../kde). - -### NixOS - -`/usr/share` is not used on NixOS. Install the package from the -repository's `default.nix` instead — it carries the MIME type and a -thumbnailer that calls `yapf` by its full store path: - -```nix -# configuration.nix -environment.systemPackages = [ (pkgs.callPackage /path/to/YAPF { }) ]; -environment.pathsToLink = [ "/share/thumbnailers" ]; # if your desktop does not link it already -``` - -For your user only: `nix-env -if /path/to/YAPF`, then -`sh extensions/linux/install.sh` (the per-user install). diff --git a/extensions/linux/install.sh b/extensions/linux/install.sh deleted file mode 100755 index 426b3e8..0000000 --- a/extensions/linux/install.sh +++ /dev/null @@ -1,18 +0,0 @@ -#!/bin/sh -# Registers the YAPF MIME type and thumbnailer for the current user, so file -# managers that use freedesktop thumbnailers (GNOME Files, Nemo, Caja, -# Thunar with tumbler) show .yapf previews. Needs `yapf` on your PATH. -# sh extensions/linux/install.sh (current user) -# sudo sh extensions/linux/install.sh --system -set -e -here=$(cd "$(dirname "$0")" && pwd) -if [ "$1" = "--system" ]; then data=/usr/share; else data=${XDG_DATA_HOME:-$HOME/.local/share}; fi - -command -v yapf >/dev/null 2>&1 || echo "warning: 'yapf' is not on your PATH; thumbnails need it" >&2 - -mkdir -p "$data/mime/packages" "$data/thumbnailers" -cp "$here/yapf-mime.xml" "$data/mime/packages/yapf.xml" -cp "$here/yapf.thumbnailer" "$data/thumbnailers/yapf.thumbnailer" -update-mime-database "$data/mime" >/dev/null 2>&1 || true -echo "Installed the image/x-yapf MIME type and thumbnailer into $data" -echo "Restart your file manager (e.g. 'nautilus -q') and clear ~/.cache/thumbnails/fail if needed." diff --git a/extensions/linux/yapf-mime.xml b/extensions/linux/yapf-mime.xml deleted file mode 100644 index 5049dba..0000000 --- a/extensions/linux/yapf-mime.xml +++ /dev/null @@ -1,12 +0,0 @@ - - - - - YAPF image - - - - - - - diff --git a/extensions/linux/yapf.thumbnailer b/extensions/linux/yapf.thumbnailer deleted file mode 100644 index e911922..0000000 --- a/extensions/linux/yapf.thumbnailer +++ /dev/null @@ -1,4 +0,0 @@ -[Thumbnailer Entry] -TryExec=yapf -Exec=yapf thumbnail %i %o %s -MimeType=image/x-yapf; diff --git a/extensions/photoshop/Open YAPF.jsx b/extensions/photoshop/Open YAPF.jsx deleted file mode 100644 index addfb56..0000000 --- a/extensions/photoshop/Open YAPF.jsx +++ /dev/null @@ -1,30 +0,0 @@ -// Open YAPF — opens .yapf images in Photoshop. -// Copyright 2026 Nexoniarz — Apache License 2.0. -// Install: copy this folder's .jsx / .jsxinc files (and yapf / yapf.exe) -// into Photoshop's Presets/Scripts folder; then File > Scripts > Open YAPF. - -#target photoshop -#include "yapf_common.jsxinc" - -(function () { - var filter = YAPF_IS_WINDOWS ? "YAPF images:*.yapf,All files:*.*" - : function (f) { return f instanceof Folder || /\.yapf$/i.test(f.name); }; - var files = File.openDialog("Open YAPF image", filter, true); - if (!files) return; - if (!(files instanceof Array)) files = [files]; - - for (var i = 0; i < files.length; i++) { - // 8 / 16-bit images come through PNG (16 bits are kept); half, - // float and BC6H HDR textures through Radiance .hdr (32-bit). - var tmp = yapfTempFile(yapfIsHdr(files[i]) ? ".hdr" : ".png"); - if (!yapfRun([files[i].fsName, tmp.fsName], tmp)) { - alert("Could not open " + files[i].name + ".\n\n" + yapfFailText()); - return; - } - var doc = app.open(tmp); - // The temporary PNG is no longer needed once the document is open; - // use File > Scripts > Save as YAPF to write a .yapf again. - doc.info.caption = files[i].fsName; - tmp.remove(); - } -})(); diff --git a/extensions/photoshop/README.md b/extensions/photoshop/README.md deleted file mode 100644 index 7ce8fbf..0000000 --- a/extensions/photoshop/README.md +++ /dev/null @@ -1,43 +0,0 @@ -# YAPF for Photoshop - -Two scripts that appear under **File → Scripts**: - -- **Open YAPF** — opens one or more `.yapf` files as documents. -- **Save as YAPF** — saves the visible image of the active document (a - flattened 8-bit copy; your document is not changed), keeping - transparency, with an optional mip chain. - -They convert through the `yapf` command-line tool, so Photoshop needs no -native plugin. - -## Install - -1. Download `yapf-.zip` from the - [Releases](https://github.com/Nexoniarz/YAPF/releases) (or build the tool: - `make` → `build/yapf`). -2. Copy `Open YAPF.jsx`, `Save as YAPF.jsx`, `yapf_common.jsxinc` **and** - `yapf` / `yapf.exe` into Photoshop's scripts folder: - - Windows: `C:\Program Files\Adobe\Adobe Photoshop \Presets\Scripts` - - macOS: `/Applications/Adobe Photoshop /Presets/Scripts` -3. Restart Photoshop. The scripts are under **File → Scripts**; you can give - them keyboard shortcuts in **Edit → Keyboard Shortcuts** or record them - in Actions. - -Instead of copying `yapf` next to the scripts you can put it on your `PATH`. - -## What opens how - -Every YAPF file the `yapf` tool reads (version 1 and 2): 8-bit images open -as 8-bit documents, 16-bit textures as 16-bit documents, half / float and -BC6H HDR textures as 32-bit documents (through Radiance `.hdr`), other GPU -blocks (BC1–BC7) decoded to 8-bit. Cubes, arrays and animations open their -first image. When a file cannot be opened, the alert shows the tool's -reason (for example a damaged file). Saving keeps 8 or 16 bits per -channel. - -## Status - -The scripts are written for Photoshop CC's ExtendScript and are not yet -tested inside Photoshop (the converter itself is fully tested). A native -format plugin (`.8bi` / `.plugin`, so `.yapf` shows up directly in the Open -and Save dialogs) needs Adobe's Photoshop SDK and is planned. diff --git a/extensions/photoshop/Save as YAPF.jsx b/extensions/photoshop/Save as YAPF.jsx deleted file mode 100644 index 05e7cf2..0000000 --- a/extensions/photoshop/Save as YAPF.jsx +++ /dev/null @@ -1,42 +0,0 @@ -// Save as YAPF — writes the active document as a .yapf image. -// Copyright 2026 Nexoniarz — Apache License 2.0. -// The visible result is saved: a flattened 8-bit RGB (or grayscale) copy, -// transparency kept. Your document is not modified. - -#target photoshop -#include "yapf_common.jsxinc" - -(function () { - if (!app.documents.length) { alert("Open a document first."); return; } - var doc = app.activeDocument; - - var base = doc.name.replace(/\.[^.]+$/, ""); - var start = new File((doc.saved && doc.path ? doc.path.fsName : Folder.desktop.fsName) + "/" + base + ".yapf"); - var out = start.saveDlg("Save as YAPF", YAPF_IS_WINDOWS ? "YAPF images:*.yapf" : undefined); - if (!out) return; - if (!/\.yapf$/i.test(out.name)) out = new File(out.fsName + ".yapf"); - var mips = confirm("Also store mipmaps (for game engines / GPUs)?", true, "YAPF"); - - var tmp = yapfTempFile(".png"); - var copy = doc.duplicate(base + " (YAPF export)", true); // merged copy - try { - if (copy.mode !== DocumentMode.RGB && copy.mode !== DocumentMode.GRAYSCALE) - copy.changeMode(ChangeMode.RGB); - // 8 and 16 bits per channel are kept (16-bit becomes a 16-bit - // YAPF texture); 32-bit documents are saved as 16-bit. - if (copy.bitsPerChannel === BitsPerChannelType.THIRTYTWO) - copy.bitsPerChannel = BitsPerChannelType.SIXTEEN; - var opts = new PNGSaveOptions(); - opts.interlaced = false; - copy.saveAs(tmp, opts, true, Extension.LOWERCASE); - } finally { - copy.close(SaveOptions.DONOTSAVECHANGES); - } - - var args = [tmp.fsName, out.fsName]; - if (mips) args.push("--mips"); - var ok = yapfRun(args, out); - tmp.remove(); - if (!ok) { alert("Could not write " + out.name + ".\n\n" + yapfFailText()); return; } - alert("Saved " + out.fsName + " (" + Math.round(out.length / 1024) + " KB)"); -})(); diff --git a/extensions/photoshop/yapf_common.jsxinc b/extensions/photoshop/yapf_common.jsxinc deleted file mode 100644 index 10e312e..0000000 --- a/extensions/photoshop/yapf_common.jsxinc +++ /dev/null @@ -1,77 +0,0 @@ -// Shared helpers for the YAPF Photoshop scripts. -// Copyright 2026 Nexoniarz — Apache License 2.0. -// -// The scripts convert through the `yapf` command-line tool. It is looked -// up next to these scripts first (yapf.exe / yapf), then on the PATH. - -var YAPF_IS_WINDOWS = $.os.indexOf("Windows") !== -1; - -function yapfQuote(s) { - return '"' + String(s).replace(/"/g, '\\"') + '"'; -} - -function yapfTool() { - var here = new File($.fileName).parent; - var names = YAPF_IS_WINDOWS ? ["yapf.exe"] : ["yapf"]; - for (var i = 0; i < names.length; i++) { - var f = new File(here.fsName + "/" + names[i]); - if (f.exists) return f.fsName; - } - return names[0]; // rely on the PATH -} - -// Runs the tool with its output (stdout) going to `stdoutFile` when given. -// Returns the tool's error text ("" when it printed none). -function yapfExec(args, stdoutFile) { - var errFile = yapfTempFile(".txt"); - var cmd = yapfQuote(yapfTool()); - for (var i = 0; i < args.length; i++) cmd += " " + (args[i].charAt(0) === "-" ? args[i] : yapfQuote(args[i])); - if (stdoutFile) cmd += " > " + yapfQuote(stdoutFile.fsName); - cmd += " 2> " + yapfQuote(errFile.fsName); - if (YAPF_IS_WINDOWS) cmd = '"' + cmd + '"'; // cmd.exe strips one pair of quotes - app.system(cmd); - var text = yapfReadText(errFile); - errFile.remove(); - return text; -} - -function yapfReadText(f) { - if (!f.exists || !f.open("r")) return ""; - var t = f.read(); - f.close(); - return t.replace(/\s+$/, ""); -} - -// Runs the tool; returns true when `expectOut` was produced. The tool's -// own message (why it failed) is left in yapfLastError. -var yapfLastError = ""; -function yapfRun(args, expectOut) { - if (expectOut.exists) expectOut.remove(); - yapfLastError = yapfExec(args, null); - return expectOut.exists; -} - -// The tool's message, or the help text when the tool could not be run. -function yapfFailText() { - return /yapf: /.test(yapfLastError) ? yapfLastError : YAPF_TOOL_HELP; -} - -// True when a .yapf file holds float / HDR data (half, float, BC6H), so it -// should open as a 32-bit document instead of a clamped 8-bit one. -function yapfIsHdr(file) { - var info = yapfTempFile(".txt"); - yapfExec(["info", file.fsName], info); - var text = yapfReadText(info); - info.remove(); - return /payload\s*:[^\n]*(half float|, float|BC6H)/.test(text); -} - -function yapfTempFile(ext) { - return new File(Folder.temp.fsName + "/yapf_" + new Date().getTime() + "_" + - Math.floor(Math.random() * 1e6) + ext); -} - -var YAPF_TOOL_HELP = - "The 'yapf' command-line tool was not found or failed.\n\n" + - "Put yapf" + (YAPF_IS_WINDOWS ? ".exe" : "") + " in the same folder as this script, " + - "or add it to your PATH.\nDownload or build it: https://github.com/Nexoniarz/YAPF"; diff --git a/extensions/vscode/README.md b/extensions/vscode/README.md deleted file mode 100644 index f72a9c7..0000000 --- a/extensions/vscode/README.md +++ /dev/null @@ -1,39 +0,0 @@ -# YAPF Image Preview for VS Code - -Click any `.yapf` file in VS Code to see the image. - -- Checkerboard behind transparent pixels. -- **Click** to switch between *fit to window* and *100 %*; **Ctrl + scroll** - to zoom (pixels stay sharp when enlarged). -- Opens every YAPF file, version 1 and 2: GPU blocks (BC1–BC7, BC6H) - decoded, 16-bit and float textures shown in 8-bit (floats sRGB encoded). -- Pickers for **mip level**, cube **face**, array **layer**, animation - **frame** and volume **slice**. -- Info bar: size, shape, storage (e.g. *GPU BC7*, *RGB half float*), sRGB / - linear, normal-map convention, format version, file size, decode time. - Damaged files say so (checksum mismatch). -- Reloads automatically when the file changes on disk. - -Decoding runs in plain JavaScript inside the preview; no native code. - -## Install - -- From a release: download `yapf-preview.vsix`, then in VS Code run - **Extensions: Install from VSIX…** (or `code --install-extension yapf-preview.vsix`). -- From source (needs Node.js): - - ```sh - cd extensions/vscode - npm run package # → yapf-preview-1.0.0.vsix - code --install-extension yapf-preview-1.0.0.vsix - ``` - -Should work in VS Code 1.75+ and VS Code–based editors such as VSCodium. - -## Status - -The `.vsix` packages cleanly, and the preview code was tested in a browser -engine (headless Chromium) with real files: correct pixels, mip picker, -error message for corrupt files; the YAPF 2 preview was tested the same -way (BC7, BC5, BC6H, half float, 16-bit, cube, animation, damaged and -non-YAPF files). **It has not yet been run inside VS Code itself.** diff --git a/extensions/vscode/extension.js b/extensions/vscode/extension.js deleted file mode 100644 index d2bdb19..0000000 --- a/extensions/vscode/extension.js +++ /dev/null @@ -1,65 +0,0 @@ -// YAPF image preview for VS Code — a read-only custom editor for *.yapf. -// Copyright 2026 Nexoniarz — Apache License 2.0. -const vscode = require('vscode'); - -class YapfPreviewProvider { - constructor(context) { this.context = context; } - - openCustomDocument(uri) { return { uri, dispose() {} }; } - - async resolveCustomEditor(document, panel) { - const media = vscode.Uri.joinPath(this.context.extensionUri, 'media'); - panel.webview.options = { enableScripts: true, localResourceRoots: [media] }; - panel.webview.html = this.html(panel.webview, media); - - const send = async () => { - try { - const bytes = await vscode.workspace.fs.readFile(document.uri); - panel.webview.postMessage({ type: 'file', name: document.uri.path.split('/').pop(), bytes }); - } catch (e) { - panel.webview.postMessage({ type: 'error', message: String(e.message || e) }); - } - }; - panel.webview.onDidReceiveMessage((m) => { if (m.type === 'ready') send(); }); - - // Reload when the file changes on disk. - const folder = vscode.Uri.joinPath(document.uri, '..'); - const name = document.uri.path.split('/').pop(); - const watcher = vscode.workspace.createFileSystemWatcher(new vscode.RelativePattern(folder, name)); - watcher.onDidChange(send); - panel.onDidDispose(() => watcher.dispose()); - } - - html(webview, media) { - const uri = (f) => webview.asWebviewUri(vscode.Uri.joinPath(media, f)); - const nonce = Math.random().toString(36).slice(2) + Date.now().toString(36); - return ` - - - - - - -YAPF Preview - - -
Loading…
-
- - - - -`; - } -} - -function activate(context) { - context.subscriptions.push(vscode.window.registerCustomEditorProvider( - 'yapf.preview', new YapfPreviewProvider(context), - { webviewOptions: { retainContextWhenHidden: true }, supportsMultipleEditorsPerDocument: true })); -} - -function deactivate() {} - -module.exports = { activate, deactivate }; diff --git a/extensions/vscode/media/icon.png b/extensions/vscode/media/icon.png deleted file mode 100644 index 1ff64e6..0000000 Binary files a/extensions/vscode/media/icon.png and /dev/null differ diff --git a/extensions/vscode/media/preview.css b/extensions/vscode/media/preview.css deleted file mode 100644 index c43b1a3..0000000 --- a/extensions/vscode/media/preview.css +++ /dev/null @@ -1,26 +0,0 @@ -html, body { height: 100%; margin: 0; } -body { - display: flex; flex-direction: column; - background: var(--vscode-editor-background, #1e1e1e); - color: var(--vscode-foreground, #ccc); - font: 12px var(--vscode-font-family, system-ui, sans-serif); -} -#bar { - display: flex; justify-content: space-between; align-items: center; gap: 12px; - padding: 6px 12px; border-bottom: 1px solid var(--vscode-panel-border, #333); -} -#bar select { - background: var(--vscode-dropdown-background, #3c3c3c); - color: var(--vscode-dropdown-foreground, #ccc); - border: 1px solid var(--vscode-dropdown-border, #555); -} -#stage { flex: 1; overflow: auto; display: grid; place-items: center; padding: 16px; cursor: zoom-in; } -body:not(.fit) #stage { cursor: zoom-out; } -canvas { - background-color: #fff; - background-image: conic-gradient(#ccc 25%, #fff 0 50%, #ccc 0 75%, #fff 0); - background-size: 16px 16px; - box-shadow: 0 0 0 1px var(--vscode-panel-border, #333); -} -canvas.pixelated { image-rendering: pixelated; } -#error { padding: 16px; color: var(--vscode-errorForeground, #f48771); } diff --git a/extensions/vscode/media/preview.js b/extensions/vscode/media/preview.js deleted file mode 100644 index 9e4b2dc..0000000 --- a/extensions/vscode/media/preview.js +++ /dev/null @@ -1,141 +0,0 @@ -// Webview side of the YAPF preview: decode, draw, zoom, surface pickers, info. -(function () { - const vscode = typeof acquireVsCodeApi === 'function' ? acquireVsCodeApi() : null; - const canvas = document.getElementById('canvas'); - const info = document.getElementById('info'); - const controls = document.getElementById('controls'); - const errorBox = document.getElementById('error'); - const PIXEL_HINTS = ['RGBA8', 'RGB8', 'RG8', 'R8', 'SRGB8_A8', 'SRGB8', 'RGBA16', 'RGB16', 'RG16', 'R16', - 'RGBA16F', 'RGB16F', 'RG16F', 'R16F', 'RGBA32F', 'RGB32F', 'RG32F', 'R32F']; - const BLOCKS = { 0x40: 'BC1', 0x41: 'BC2', 0x42: 'BC3', 0x43: 'BC4', 0x44: 'BC4 snorm', 0x45: 'BC5', - 0x46: 'BC5 snorm', 0x47: 'BC6H', 0x48: 'BC6H signed', 0x49: 'BC7', 0x50: 'ETC2 RGB', - 0x51: 'ETC2 RGB A1', 0x52: 'ETC2 RGBA', 0x53: 'EAC R11', 0x54: 'EAC R11 snorm', - 0x55: 'EAC RG11', 0x56: 'EAC RG11 snorm' }; - ['4×4', '5×4', '5×5', '6×5', '6×6', '8×5', '8×6', '8×8', '10×5', '10×6', '10×8', '10×10', '12×10', '12×12'] - .forEach((n, i) => { BLOCKS[0x60 + i] = 'ASTC ' + n; }); - const CH_NAMES = ['', 'Gray', 'Gray + Alpha', 'RGB', 'RGBA']; - const SAMPLES = ['8-bit', '16-bit', 'half float', 'float']; - const FACES = ['+X', '−X', '+Y', '−Y', '+Z', '−Z']; - - let tex = null, fit = true, zoom = 1; - const sel = { mip: 0, face: 0, layer: 0, frame: 0, slice: 0 }; - - function kb(n) { return n < 1024 * 1024 ? (n / 1024).toFixed(1) + ' KB' : (n / 1048576).toFixed(2) + ' MB'; } - - function mipDims(m) { - return [Math.max(1, tex.width >>> m), Math.max(1, tex.height >>> m), - tex.shape === 2 ? Math.max(1, tex.depth >>> m) : 1]; - } - - function draw() { - const s = YAPF.surfaceIndex(tex, sel.frame, sel.layer, sel.face, sel.mip); - sel.slice = Math.min(sel.slice, mipDims(sel.mip)[2] - 1); - try { - const view = YAPF.textureToRGBA(tex, s, sel.slice); - canvas.width = view.width; canvas.height = view.height; - canvas.getContext('2d').putImageData(new ImageData(view.rgba, view.width, view.height), 0, 0); - errorBox.hidden = true; - } catch (e) { - errorBox.hidden = false; - errorBox.textContent = e.message; - } - layout(); - } - - function layout() { - if (!tex) return; - const w = canvas.width, h = canvas.height; - const stage = document.getElementById('stage'); - const scale = fit ? Math.min(1, (stage.clientWidth - 32) / w, (stage.clientHeight - 32) / h) : zoom; - canvas.style.width = Math.max(1, Math.round(w * scale)) + 'px'; - canvas.style.height = Math.max(1, Math.round(h * scale)) + 'px'; - canvas.classList.toggle('pixelated', scale >= 2); - document.body.classList.toggle('fit', fit); - stage.title = fit ? 'Click for 100%, Ctrl+scroll to zoom' : 'Click to fit'; - } - - function picker(key, count, label) { - if (count <= 1) return; - const el = document.createElement('select'); - for (let i = 0; i < count; i++) { - const o = document.createElement('option'); - o.value = i; - o.textContent = label(i); - el.appendChild(o); - } - sel[key] = Math.min(sel[key], count - 1); - el.value = sel[key]; - el.onchange = () => { sel[key] = +el.value; if (key === 'mip') buildControls(); draw(); }; - controls.appendChild(el); - } - - function buildControls() { - controls.textContent = ''; - picker('mip', tex.mipLevels, (m) => { const [w, h, d] = mipDims(m); return 'Mip ' + m + ' (' + w + '×' + h + (d > 1 ? '×' + d : '') + ')'; }); - picker('face', tex.faces, (f) => 'Face ' + FACES[f]); - picker('layer', tex.layers, (l) => 'Layer ' + l); - picker('frame', tex.frames, (f) => 'Frame ' + (f + 1) + (tex.frameUs[f] ? ' (' + Math.round(tex.frameUs[f] / 1000) + ' ms)' : '')); - picker('slice', mipDims(sel.mip)[2], (z) => 'Slice ' + z); - } - - function show(name, bytes) { - errorBox.hidden = true; - const t = performance.now(); - try { - tex = YAPF.decodeTexture(bytes); - } catch (e) { - tex = null; - errorBox.hidden = false; - errorBox.textContent = name + ': ' + e.message.replace(/^YAPF: /, ''); - info.textContent = ''; - controls.textContent = ''; - return; - } - const ms = performance.now() - t; - let raw = 0; - for (let m = 0; m < tex.mipLevels; m++) { - const [w, h, d] = mipDims(m); - raw += w * h * d * (tex.payload ? 4 : tex.channels * [1, 2, 2, 4][tex.sample]); - } - raw *= tex.frames * tex.layers * tex.faces; - const [w0, h0, d0] = mipDims(0); - const shape = tex.shape === 1 ? (tex.layers > 1 ? 'cube array of ' + tex.layers : 'cubemap') - : tex.shape === 2 ? 'volume' : tex.layers > 1 ? 'array of ' + tex.layers : ''; - const storage = tex.payload === 1 ? 'GPU ' + (BLOCKS[tex.format] || '?') - : CH_NAMES[tex.channels] + ' ' + SAMPLES[tex.sample] + ', GPU ' + (PIXEL_HINTS[tex.format] || '?'); - const parts = [ - w0 + ' × ' + h0 + (d0 > 1 ? ' × ' + d0 : ''), - shape, - tex.frames > 1 ? tex.frames + ' frames' : '', - storage, - (tex.flags & 2 ? 'sRGB' : 'linear') + (tex.flags & 1 ? ', premultiplied' : ''), - tex.normal ? 'normal map (' + ((tex.normal & 3) === 2 ? 'DirectX' : (tex.normal & 3) === 1 ? 'OpenGL' : '?') + ')' : '', - tex.version === 2 ? 'YAPF 2' : 'YAPF 1', - kb(bytes.length) + (tex.payload ? '' : ' (' + (100 * bytes.length / raw).toFixed(1) + '% of raw)'), - 'decoded in ' + ms.toFixed(1) + ' ms', - ]; - const author = tex.notes.find((n) => n.tag === 'AUTH'); - if (author) parts.push('by ' + new TextDecoder().decode(author.data)); - info.textContent = parts.filter(Boolean).join(' · '); - buildControls(); - draw(); - } - - document.getElementById('stage').addEventListener('click', () => { fit = !fit; zoom = 1; layout(); }); - document.getElementById('stage').addEventListener('wheel', (e) => { - if (!e.ctrlKey || !tex) return; - e.preventDefault(); - fit = false; - zoom = Math.min(64, Math.max(1 / 64, zoom * (e.deltaY < 0 ? 1.25 : 0.8))); - layout(); - }, { passive: false }); - window.addEventListener('resize', layout); - - window.addEventListener('message', (e) => { - const m = e.data; - if (m.type === 'file') show(m.name, m.bytes instanceof Uint8Array ? m.bytes : new Uint8Array(m.bytes)); - if (m.type === 'error') { errorBox.hidden = false; errorBox.textContent = m.message; } - }); - if (vscode) vscode.postMessage({ type: 'ready' }); - window.yapfPreviewShow = show; // used by the browser test page -})(); diff --git a/extensions/vscode/package.json b/extensions/vscode/package.json deleted file mode 100644 index fd0070d..0000000 --- a/extensions/vscode/package.json +++ /dev/null @@ -1,29 +0,0 @@ -{ - "name": "yapf-preview", - "displayName": "YAPF Image Preview", - "description": "View YAPF (.yapf) lossless images inside VS Code", - "version": "1.0.0", - "publisher": "Nexoniarz", - "license": "Apache-2.0", - "icon": "media/icon.png", - "repository": { "type": "git", "url": "https://github.com/Nexoniarz/YAPF.git" }, - "engines": { "vscode": "^1.75.0" }, - "categories": ["Visualization", "Other"], - "keywords": ["yapf", "image", "texture", "preview", "viewer"], - "main": "./extension.js", - "activationEvents": [], - "contributes": { - "customEditors": [ - { - "viewType": "yapf.preview", - "displayName": "YAPF Image Preview", - "selector": [{ "filenamePattern": "*.yapf" }], - "priority": "default" - } - ] - }, - "scripts": { - "vscode:prepublish": "node scripts/copy-codec.js", - "package": "node scripts/copy-codec.js && npx --yes @vscode/vsce package --allow-missing-repository" - } -} diff --git a/extensions/vscode/scripts/copy-codec.js b/extensions/vscode/scripts/copy-codec.js deleted file mode 100644 index 7f4ab2d..0000000 --- a/extensions/vscode/scripts/copy-codec.js +++ /dev/null @@ -1,6 +0,0 @@ -// Copies the shared JavaScript codec into media/ so the extension is self-contained. -const fs = require('fs'); -const path = require('path'); -const src = path.join(__dirname, '..', '..', '..', 'bindings', 'js', 'yapf.js'); -fs.copyFileSync(src, path.join(__dirname, '..', 'media', 'yapf.js')); -console.log('copied', path.relative(process.cwd(), src), '-> media/yapf.js'); diff --git a/other/YAPF.SVG b/other/YAPF.SVG deleted file mode 100644 index 80d9a4c..0000000 --- a/other/YAPF.SVG +++ /dev/null @@ -1,211 +0,0 @@ - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - Yet Another Picture Format - YAPF - - - - diff --git a/other/YAPF.YAPF b/other/YAPF.YAPF deleted file mode 100644 index 5b8fe12..0000000 Binary files a/other/YAPF.YAPF and /dev/null differ diff --git a/pikture.c b/pikture.c new file mode 100644 index 0000000..fb2397e --- /dev/null +++ b/pikture.c @@ -0,0 +1,229 @@ +/* +pikture.c +Native PIKTURE format encoder and decoder library. +Version: 100 +License: MIT +Made by: Nexoniarz +*/ + +#include "pikture.h" +#include +#include +#include + +#define PIKT_MAGIC "PIK!" +#define PIKT_VERSION 5 +#define PIKT_HASH(r, g, b, a) (((r) * 3 + (g) * 5 + (b) * 7 + (a) * 11) % 64) + +typedef struct { + uint8_t r, g, b, a; +} pikt_pixel; + +/* Reads a 16-bit unsigned integer in Big-Endian format */ +static uint16_t read_u16_be(FILE* f) { + uint8_t bytes[2]; + fread(bytes, 1, 2, f); + return (bytes[0] << 8) | bytes[1]; +} + +/* Writes a 16-bit unsigned integer in Big-Endian format */ +static void write_u16_be(FILE* f, uint16_t value) { + uint8_t bytes[2] = { (value >> 8) & 0xFF, value & 0xFF }; + fwrite(bytes, 1, 2, f); +} + +pikture_t* pikture_load(const char* filename) { + FILE* f = fopen(filename, "rb"); + if (!f) return NULL; + + char magic[4]; + fread(magic, 1, 4, f); + if (memcmp(magic, PIKT_MAGIC, 4) != 0) { + fclose(f); + return NULL; + } + + uint8_t version; + fread(&version, 1, 1, f); + if (version != PIKT_VERSION) { + fclose(f); + return NULL; + } + + pikture_t* img = (pikture_t*)malloc(sizeof(pikture_t)); + if (!img) { + fclose(f); + return NULL; + } + + img->width = read_u16_be(f); + img->height = read_u16_be(f); + + uint8_t depth; + fread(&depth, 1, 1, f); + img->channels = 4; + + size_t data_size = (size_t)img->width * img->height * 4; + img->pixels = (uint8_t*)malloc(data_size); + if (!img->pixels) { + free(img); + fclose(f); + return NULL; + } + + pikt_pixel index[64] = {0}; + uint8_t r = 0, g = 0, b = 0, a = 255; + + size_t ptr = 0; + while (ptr < data_size) { + int b0 = fgetc(f); + if (b0 == EOF) break; + + if (b0 == 0xFE) { + r = fgetc(f); + g = fgetc(f); + b = fgetc(f); + } else if (b0 == 0xFF) { + r = fgetc(f); + g = fgetc(f); + b = fgetc(f); + a = fgetc(f); + } else { + uint8_t match = b0 & 0xC0; + if (match == 0x00) { + pikt_pixel p = index[b0 & 0x3F]; + r = p.r; g = p.g; b = p.b; a = p.a; + } else if (match == 0x40) { + r = (uint8_t)(r + ((b0 >> 4) & 0x03) - 2); + g = (uint8_t)(g + ((b0 >> 2) & 0x03) - 2); + b = (uint8_t)(b + (b0 & 0x03) - 2); + } else if (match == 0x80) { + int b1 = fgetc(f); + int8_t dg = (b0 & 0x3F) - 32; + r = (uint8_t)(r + dg + ((b1 >> 4) & 0x0F) - 8); + g = (uint8_t)(g + dg); + b = (uint8_t)(b + dg + (b1 & 0x0F) - 8); + } else if (match == 0xC0) { + int run = (b0 & 0x3F) + 1; + for (int i = 0; i < run && ptr < data_size; i++) { + img->pixels[ptr++] = r; + img->pixels[ptr++] = g; + img->pixels[ptr++] = b; + img->pixels[ptr++] = a; + } + continue; + } + } + + uint8_t idx_pos = PIKT_HASH(r, g, b, a); + index[idx_pos].r = r; + index[idx_pos].g = g; + index[idx_pos].b = b; + index[idx_pos].a = a; + + if (ptr < data_size) { + img->pixels[ptr++] = r; + img->pixels[ptr++] = g; + img->pixels[ptr++] = b; + img->pixels[ptr++] = a; + } + } + + fclose(f); + return img; +} + +int pikture_save(const char* filename, const pikture_t* img) { + if (!img || !img->pixels) return 0; + + FILE* f = fopen(filename, "wb"); + if (!f) return 0; + + fwrite(PIKT_MAGIC, 1, 4, f); + uint8_t version = PIKT_VERSION; + fwrite(&version, 1, 1, f); + write_u16_be(f, img->width); + write_u16_be(f, img->height); + uint8_t depth = 32; + fwrite(&depth, 1, 1, f); + + pikt_pixel index[64] = {0}; + uint8_t prev_r = 0, prev_g = 0, prev_b = 0, prev_a = 255; + int run = 0; + + size_t total_pixels = (size_t)img->width * img->height; + size_t px_idx = 0; + + while (px_idx < total_pixels * 4) { + uint8_t r = img->pixels[px_idx++]; + uint8_t g = img->pixels[px_idx++]; + uint8_t b = img->pixels[px_idx++]; + uint8_t a = img->pixels[px_idx++]; + + if (r == prev_r && g == prev_g && b == prev_b && a == prev_a) { + run++; + if (run == 62) { + fputc(0xC0 | (run - 1), f); + run = 0; + } + continue; + } + + if (run > 0) { + fputc(0xC0 | (run - 1), f); + run = 0; + } + + uint8_t idx_pos = PIKT_HASH(r, g, b, a); + if (index[idx_pos].r == r && index[idx_pos].g == g && + index[idx_pos].b == b && index[idx_pos].a == a) { + fputc(0x00 | idx_pos, f); + } else { + index[idx_pos].r = r; + index[idx_pos].g = g; + index[idx_pos].b = b; + index[idx_pos].a = a; + + if (a == prev_a) { + int8_t s_dr = (int8_t)(r - prev_r); + int8_t s_dg = (int8_t)(g - prev_g); + int8_t s_db = (int8_t)(b - prev_b); + + if (s_dr >= -2 && s_dr <= 1 && s_dg >= -2 && s_dg <= 1 && s_db >= -2 && s_db <= 1) { + fputc(0x40 | ((s_dr + 2) << 4) | ((s_dg + 2) << 2) | (s_db + 2), f); + } else { + int8_t dr_dg = s_dr - s_dg; + int8_t db_dg = s_db - s_dg; + + if (s_dg >= -32 && s_dg <= 31 && dr_dg >= -8 && dr_dg <= 7 && db_dg >= -8 && db_dg <= 7) { + fputc(0x80 | (s_dg + 32), f); + fputc(((dr_dg + 8) << 4) | (db_dg + 8), f); + } else { + fputc(0xFE, f); + fputc(r, f); fputc(g, f); fputc(b, f); + } + } + } else { + fputc(0xFF, f); + fputc(r, f); fputc(g, f); fputc(b, f); fputc(a, f); + } + } + prev_r = r; prev_g = g; prev_b = b; prev_a = a; + } + + if (run > 0) { + fputc(0xC0 | (run - 1), f); + } + + fclose(f); + return 1; +} + +void pikture_free(pikture_t* img) { + if (img) { + if (img->pixels) { + free(img->pixels); + } + free(img); + } +} diff --git a/pikture.h b/pikture.h new file mode 100644 index 0000000..fc8c198 --- /dev/null +++ b/pikture.h @@ -0,0 +1,45 @@ +/* +pikture.h +Native PIKTURE format encoder and decoder library. +Version: 100 +License: MIT +Made by: Nexoniarz +*/ + +#ifndef PIKTURE_H +#define PIKTURE_H + +#include +#include + +/* Image data structure */ +typedef struct { + uint16_t width; + uint16_t height; + uint8_t channels; /* Always 4 (RGBA) */ + uint8_t* pixels; /* Raw RGBA pixel array */ +} pikture_t; + +#ifdef __cplusplus +extern "C" { +#endif + +/* * Loads a PIKTURE image from the specified file path. + * Returns a pointer to a pikture_t struct, or NULL on failure. + */ +pikture_t* pikture_load(const char* filename); + +/* * Saves a PIKTURE image to the specified file path. + * Returns 1 on success, 0 on failure. + */ +int pikture_save(const char* filename, const pikture_t* img); + +/* * Frees the memory allocated for the PIKTURE image. + */ +void pikture_free(pikture_t* img); + +#ifdef __cplusplus +} +#endif + +#endif /* PIKTURE_H */ diff --git a/tests/test_yapf.c b/tests/test_yapf.c deleted file mode 100644 index c2952b2..0000000 --- a/tests/test_yapf.c +++ /dev/null @@ -1,733 +0,0 @@ -/* - * test_yapf.c — self-contained test suite for yapf.c - * - * cc -O2 -std=c99 tests/test_yapf.c yapf.c -o test_yapf -pthread - * ./test_yapf [path/to/other/YAPF.YAPF] - * - * Round-trips many sizes, channel counts and image kinds, checks mip - * chains, single- vs multi-threaded decode, the bundled sample file, and - * that corrupted or truncated files are rejected without crashing. - * Version 2: wide samples, shapes, GPU blocks, notes, checksums, needs, - * streaming, tile decode, block encoders and mip generation. - * Exit code 0 means every test passed. - */ -#include "../yapf.h" - -#include -#include -#include -#include - -/* FNV-1a of the decoded pixels of other/YAPF.YAPF (the YAPF logo). */ -#define SAMPLE_HASH 0x8891c2b4u - -static int tests, fails; - -static uint32_t rng = 12345; -static uint32_t rnd(void) { rng = rng * 1103515245u + 12345u; return rng >> 8; } - -#define CHECK(cond, ...) do { tests++; if (!(cond)) { fails++; \ - printf("FAIL: "); printf(__VA_ARGS__); printf("\n"); } } while (0) - -/* Five kinds of content: noise, smooth gradient, hard-edged blocks, - * noisy curves, and an image with an opaque alpha channel. */ -static void fill(uint8_t *p, int w, int h, int ch, int kind) { - for (int y = 0; y < h; y++) - for (int x = 0; x < w; x++) - for (int c = 0; c < ch; c++) { - uint8_t *d = p + ((size_t)y * w + x) * ch + c; - switch (kind) { - case 0: *d = (uint8_t)rnd(); break; - case 1: *d = (uint8_t)(x * 3 + y * 5 + c * 40); break; - case 2: *d = ((x / 7 + y / 5 + c) & 1) ? 200 : 30; break; - case 3: *d = (uint8_t)((x * x + y * y) / 50 + rnd() % 5); break; - default: *d = (c == ch - 1) ? 255 : (uint8_t)(x ^ y); break; - } - } -} - -static uint8_t *encode_mem(const yapf_image_t *img, size_t *n) { - void *data = NULL; - if (yapf_encode(img, &data, n) != YAPF_OK) return NULL; - uint8_t *copy = (uint8_t *)malloc(*n); - if (copy) memcpy(copy, data, *n); - yapf_free_buffer(data); - return copy; -} - -/* yapf_save() writes exactly what yapf_encode() returns. */ -static void save_matches_encode(void) { - const char *tmp = "test_yapf_tmp.yapf"; - uint8_t px[37 * 23 * 3]; - fill(px, 37, 23, 3, 3); - yapf_image_t img; - memset(&img, 0, sizeof(img)); - img.width = 37; img.height = 23; img.channels = 3; img.mip_levels = 1; img.pixels = px; - size_t len = 0; - uint8_t *mem = encode_mem(&img, &len); - int ok = mem && yapf_save(tmp, &img) == YAPF_OK; - FILE *f = ok ? fopen(tmp, "rb") : NULL; - if (f) { - uint8_t *disk = (uint8_t *)malloc(len + 1); - ok = fread(disk, 1, len + 1, f) == len && memcmp(disk, mem, len) == 0; - free(disk); - fclose(f); - } - remove(tmp); - free(mem); - CHECK(ok, "yapf_save writes the same bytes as yapf_encode"); - void *d = (void *)1; - size_t n = 1; - CHECK(yapf_encode(NULL, &d, &n) == YAPF_ERR_INVALID && d == NULL && n == 0, - "yapf_encode rejects a NULL image"); -} - -static void roundtrip(int w, int h, int ch, int kind) { - size_t n = (size_t)w * h * ch, len = 0; - uint8_t *p = (uint8_t *)malloc(n); - fill(p, w, h, ch, kind); - - yapf_image_t img; - memset(&img, 0, sizeof(img)); - img.width = (uint32_t)w; img.height = (uint32_t)h; - img.channels = (uint8_t)ch; img.mip_levels = 1; img.pixels = p; - - uint8_t *file = encode_mem(&img, &len); - CHECK(file != NULL, "encode %dx%d ch%d kind%d", w, h, ch, kind); - if (file) { - yapf_image_t *a = yapf_load_memory(file, len); - yapf_image_t *b = yapf_load_memory_mt(file, len, 0); - CHECK(a && memcmp(a->pixels, p, n) == 0, - "roundtrip %dx%d ch%d kind%d", w, h, ch, kind); - CHECK(b && memcmp(b->pixels, p, n) == 0, - "roundtrip (threads) %dx%d ch%d kind%d", w, h, ch, kind); - yapf_free(a); - yapf_free(b); - free(file); - } - free(p); -} - -static void mips(void) { - const int w = 300, h = 200, levels = 9; - uint8_t *mp[9]; - yapf_image_t img; - memset(&img, 0, sizeof(img)); - img.width = w; img.height = h; img.channels = 4; img.mip_levels = levels; - for (int l = 0; l < levels; l++) { - int mw = w >> l ? w >> l : 1, mh = h >> l ? h >> l : 1; - mp[l] = (uint8_t *)malloc((size_t)mw * mh * 4); - fill(mp[l], mw, mh, 4, l % 5); - } - img.pixels = mp[0]; - img.mips = mp; - - size_t len = 0; - uint8_t *file = encode_mem(&img, &len); - yapf_image_t *d = file ? yapf_load_memory_mt(file, len, 3) : NULL; - int ok = d && d->mip_levels == levels; - for (int l = 0; ok && l < levels; l++) { - int mw = w >> l ? w >> l : 1, mh = h >> l ? h >> l : 1; - ok = memcmp(d->mips[l], mp[l], (size_t)mw * mh * 4) == 0; - } - CHECK(ok, "mip chain of %d levels", levels); - yapf_free(d); - free(file); - for (int l = 0; l < levels; l++) free(mp[l]); -} - -/* Flip bits, truncate, scribble: the decoder must never crash, and a - * truncated file must be rejected. */ -static void corruption(void) { - const int w = 130, h = 70, ch = 4; - uint8_t *p = (uint8_t *)malloc((size_t)w * h * ch); - fill(p, w, h, ch, 3); - yapf_image_t img; - memset(&img, 0, sizeof(img)); - img.width = w; img.height = h; img.channels = ch; img.mip_levels = 1; img.pixels = p; - size_t len = 0; - uint8_t *file = encode_mem(&img, &len); - uint8_t *bad = (uint8_t *)malloc(len); - int truncated_ok = 1; - for (int it = 0; it < 3000 && file; it++) { - memcpy(bad, file, len); - size_t n = len; - switch (it % 3) { - case 0: for (int k = 0; k < 1 + it % 7; k++) bad[rnd() % len] ^= (uint8_t)(1u << (rnd() % 8)); break; - case 1: n = rnd() % len; break; - default: bad[rnd() % len] = (uint8_t)rnd(); break; - } - yapf_image_t *d = (it & 1) ? yapf_load_memory_mt(bad, n, 2) : yapf_load_memory(bad, n); - if (it % 3 == 1 && d) truncated_ok = 0; - yapf_free(d); - } - CHECK(file != NULL, "corruption test setup"); - CHECK(truncated_ok, "truncated files are rejected"); - free(bad); - free(file); - free(p); -} - -static uint32_t fnv(const uint8_t *p, size_t n) { - uint32_t h = 2166136261u; - for (size_t i = 0; i < n; i++) h = (h ^ p[i]) * 16777619u; - return h; -} - - -/* ====================================================================== - * Version 2 - * ====================================================================== */ - -static yapf_texture_t desc(uint32_t w, uint32_t h, int ch, int sample) { - yapf_texture_t d; - memset(&d, 0, sizeof(d)); - d.width = w; d.height = h; d.depth = 1; d.layers = 1; d.frames = 1; - d.mip_levels = 1; d.channels = (uint8_t)ch; d.sample = (uint8_t)sample; - return d; -} - -/* Fills every surface: noise, gradient or noisy curves, in the sample - * type; block payloads get bytes with some structure. */ -static void tex_fill(yapf_texture_t *t, int kind) { - uint32_t S = yapf_tex_surface_count(t); - for (uint32_t s = 0; s < S; s++) { - uint32_t m = s % t->mip_levels, w, h, d; - yapf_tex_mip_size(t, m, &w, &h, &d); - uint8_t *p = (uint8_t *)t->data[s]; - if (t->payload == YAPF_PAYLOAD_BLOCKS) { - size_t n = yapf_tex_surface_bytes(t, m); - for (size_t i = 0; i < n; i++) - p[i] = kind ? (uint8_t)(i % 16 < 8 ? (i / 64) & 0xFF : rnd()) : (uint8_t)rnd(); - continue; - } - size_t cnt = (size_t)w * h * d * t->channels; - for (size_t i = 0; i < cnt; i++) { - size_t px = i / t->channels; - uint32_t x = (uint32_t)(px % w), y = (uint32_t)((px / w) % h); - int c = (int)(i % t->channels); - double v = kind == 0 ? (rnd() % 1000) / 1000.0 - : kind == 1 ? (x * 3 + y * 5 + c * 40) % 600 / 600.0 - : ((x * x + y * y) / 50 % 700 + rnd() % 5) / 705.0; - switch (t->sample) { - case YAPF_SAMPLE_U8: p[i] = (uint8_t)(v * 255); break; - case YAPF_SAMPLE_U16: ((uint16_t *)p)[i] = (uint16_t)(v * 65535); break; - case YAPF_SAMPLE_F16: ((uint16_t *)p)[i] = yapf_float_to_half((float)(v * 20 - 2)); break; - default: ((float *)p)[i] = (float)(v * 100 - 10) + (kind == 0 ? (float)rnd() : 0.0f); break; - } - } - } -} - -static int tex_equal(const yapf_texture_t *a, const yapf_texture_t *b) { - uint32_t S = yapf_tex_surface_count(a); - if (S != yapf_tex_surface_count(b)) return 0; - for (uint32_t s = 0; s < S; s++) - if (!a->data[s] || !b->data[s] || - memcmp(a->data[s], b->data[s], yapf_tex_surface_bytes(a, s % a->mip_levels)) != 0) - return 0; - return 1; -} - -/* Encode, decode, compare; returns the encoded file (caller frees). */ -static uint8_t *tex_roundtrip(yapf_texture_t *t, int flags, size_t *len, const char *what) { - void *buf = NULL; - *len = 0; - int e = yapf_tex_encode(t, flags, &buf, len); - CHECK(e == YAPF_OK, "v2 encode %s (%d)", what, e); - if (e != YAPF_OK) return NULL; - int err = 0; - yapf_texture_t *a = yapf_tex_load_memory(buf, *len, 0, 1, &err); - yapf_texture_t *b = yapf_tex_load_memory(buf, *len, 0, 0, &err); - CHECK(a && tex_equal(a, t), "v2 roundtrip %s", what); - CHECK(b && tex_equal(b, t), "v2 roundtrip (threads) %s", what); - yapf_tex_free(a); - yapf_tex_free(b); - uint8_t *copy = (uint8_t *)malloc(*len); - memcpy(copy, buf, *len); - yapf_free_buffer(buf); - return copy; -} - -static void v2_pixels(void) { - static const int sizes[][2] = { {1, 1}, {7, 3}, {64, 64}, {65, 63}, {130, 70}, {200, 201} }; - static const char *sn[] = { "u8", "u16", "f16", "f32" }; - for (size_t si = 0; si < sizeof(sizes) / sizeof(sizes[0]); si++) - for (int ch = 1; ch <= 4; ch++) - for (int sample = 0; sample < 4; sample++) - for (int kind = 0; kind < 3; kind++) - for (int fl = 0; fl < 2; fl++) { - yapf_texture_t d = desc((uint32_t)sizes[si][0], (uint32_t)sizes[si][1], ch, sample); - yapf_texture_t *t = yapf_tex_create(&d); - char what[96]; - sprintf(what, "%dx%d ch%d %s kind%d%s", sizes[si][0], sizes[si][1], ch, - sn[sample], kind, fl ? " entropy" : ""); - tex_fill(t, kind); - size_t len; - free(tex_roundtrip(t, fl ? YAPF_ENC_ENTROPY : 0, &len, what)); - yapf_tex_free(t); - } -} - -/* Shapes, frames, notes and every description field survive. */ -static void v2_layout(void) { - struct { int w, h, ch, sample, shape, layers, frames, mips, depth; } c[] = { - { 64, 64, 4, 0, YAPF_SHAPE_CUBE, 1, 1, 7, 1 }, - { 32, 32, 3, 2, YAPF_SHAPE_CUBE, 2, 1, 6, 1 }, - { 40, 30, 4, 0, YAPF_SHAPE_2D, 5, 1, 3, 1 }, - { 33, 17, 1, 1, YAPF_SHAPE_VOLUME, 1, 1, 4, 9 }, - { 50, 50, 4, 0, YAPF_SHAPE_2D, 1, 6, 1, 1 }, - }; - for (size_t i = 0; i < sizeof(c) / sizeof(c[0]); i++) { - yapf_texture_t d = desc((uint32_t)c[i].w, (uint32_t)c[i].h, c[i].ch, c[i].sample); - d.shape = (uint8_t)c[i].shape; d.layers = (uint16_t)c[i].layers; d.frames = (uint16_t)c[i].frames; - d.mip_levels = (uint8_t)c[i].mips; d.depth = (uint32_t)c[i].depth; - d.channel_map[0] = YAPF_CH_NORMAL_X; d.channel_map[1] = YAPF_CH_ROUGHNESS; - d.linear_mask = 0x08; d.normal = YAPF_NORMAL_DX | YAPF_NORMAL_XY; - d.primaries = YAPF_PRIMARIES_DISPLAY_P3; d.transfer = YAPF_TRANSFER_PQ; - d.mip_filter = YAPF_MIP_KAISER; d.alpha_ref = 77; d.loop_count = 3; - d.flags = YAPF_FLAG_SRGB | YAPF_FLAG_COVERAGE; - yapf_texture_t *t = yapf_tex_create(&d); - tex_fill(t, 2); - if (t->frames > 1) for (int f = 0; f < t->frames; f++) t->frame_us[f] = 16667u * (uint32_t)(f + 1); - yapf_tex_add_note(t, "AUTH", "Keel", 4); - yapf_tex_add_note(t, "ICCP", "\0\1\2", 3); - size_t len; - char what[32]; - sprintf(what, "layout case %d", (int)i); - uint8_t *file = tex_roundtrip(t, (int)(i & 1), &len, what); - yapf_texture_t *b = file ? yapf_tex_load_memory(file, len, 0, 1, NULL) : NULL; - int ok = b && b->shape == d.shape && b->layers == d.layers && b->frames == d.frames && - b->depth == d.depth && b->mip_levels == d.mip_levels && - memcmp(b->channel_map, d.channel_map, 4) == 0 && b->linear_mask == 0x08 && - b->normal == d.normal && b->primaries == d.primaries && b->transfer == d.transfer && - b->mip_filter == d.mip_filter && b->alpha_ref == 77 && b->loop_count == 3 && - b->flags == d.flags && b->note_count == 2; - const yapf_note_t *n = b ? yapf_tex_find_note(b, "ICCP") : NULL; - ok = ok && n && n->size == 3 && memcmp(n->data, "\0\1\2", 3) == 0; - if (ok && b->frames > 1) ok = b->frame_us[b->frames - 1] == 16667u * b->frames; - CHECK(ok, "v2 fields, notes and frame times survive (%s)", what); - yapf_tex_free(b); - free(file); - yapf_tex_free(t); - } -} - -static void v2_blocks(void) { - static const uint8_t fmts[] = { YAPF_GPU_BC1, YAPF_GPU_BC7, YAPF_GPU_BC4, YAPF_GPU_ASTC_6x6, - YAPF_GPU_ASTC_12x12, YAPF_GPU_ETC2_RGBA8 }; - for (size_t f = 0; f < sizeof(fmts); f++) - for (int fl = 0; fl < 2; fl++) { - yapf_texture_t d = desc(300, 200, 4, 0); - d.payload = YAPF_PAYLOAD_BLOCKS; d.format = fmts[f]; d.mip_levels = 3; - if (f == 3) { d.shape = YAPF_SHAPE_VOLUME; d.depth = 5; } - yapf_texture_t *t = yapf_tex_create(&d); - tex_fill(t, 1); - char what[48]; - sprintf(what, "blocks 0x%02x%s", fmts[f], fl ? " packed" : ""); - size_t len; - free(tex_roundtrip(t, fl, &len, what)); - yapf_tex_free(t); - } -} - -/* Recomputes both header checks after editing a file. */ -static void reseal(uint8_t *f, size_t front) { - uint32_t a = yapf_checksum(f + 64, front - 64), b; - f[0x38] = (uint8_t)a; f[0x39] = (uint8_t)(a >> 8); f[0x3A] = (uint8_t)(a >> 16); f[0x3B] = (uint8_t)(a >> 24); - b = yapf_checksum(f, 0x3C); - f[0x3C] = (uint8_t)b; f[0x3D] = (uint8_t)(b >> 8); f[0x3E] = (uint8_t)(b >> 16); f[0x3F] = (uint8_t)(b >> 24); -} - -/* Flips, truncation, scribbles: never crash; truncation always fails. */ -static void v2_fuzz(const uint8_t *file, size_t len, const char *what) { - uint8_t *bad = (uint8_t *)malloc(len); - int truncated_ok = 1, err; - for (int it = 0; it < 2000; it++) { - memcpy(bad, file, len); - size_t n = len; - switch (it % 3) { - case 0: for (int k = 0; k < 1 + it % 7; k++) bad[rnd() % len] ^= (uint8_t)(1u << (rnd() % 8)); break; - case 1: n = rnd() % len; break; - default: bad[rnd() % len] = (uint8_t)rnd(); break; - } - int fl = (it & 4) ? YAPF_LOAD_TRUST : 0; - yapf_texture_t *x = yapf_tex_load_memory(bad, n, fl, (it & 1) ? 2 : 1, &err); - if (it % 3 == 1 && x) truncated_ok = 0; - yapf_tex_free(x); - if (it % 50 == 0) yapf_free(yapf_load_memory(bad, n)); - } - CHECK(truncated_ok, "truncated v2 files are rejected (%s)", what); - free(bad); -} - -static void v2_integrity(void) { - yapf_texture_t d = desc(150, 90, 4, YAPF_SAMPLE_F16); - yapf_texture_t *t = yapf_tex_create(&d); - tex_fill(t, 2); - size_t len; - uint8_t *file = tex_roundtrip(t, YAPF_ENC_ENTROPY, &len, "integrity setup"); - if (!file) { yapf_tex_free(t); return; } - uint8_t *bad = (uint8_t *)malloc(len); - size_t front = 64 + 16; /* header + one surface entry */ - int err; - - /* a flipped bit in tile data is caught by its yapf-sum ... */ - memcpy(bad, file, len); - bad[len - 10] ^= 0x10; - CHECK(!yapf_tex_load_memory(bad, len, 0, 1, &err) && err == YAPF_ERR_CHECKSUM, - "corrupt tile data reports YAPF_ERR_CHECKSUM (%d)", err); - yapf_texture_t *trusted = yapf_tex_load_memory(bad, len, YAPF_LOAD_TRUST, 1, &err); - yapf_tex_free(trusted); /* may or may not decode; must not crash */ - /* ... and in the header by the header check */ - memcpy(bad, file, len); - bad[0x0C] ^= 1; - CHECK(!yapf_tex_load_memory(bad, len, 0, 1, &err) && err == YAPF_ERR_CHECKSUM, - "corrupt header reports YAPF_ERR_CHECKSUM"); - /* an unknown needs bit: refused as unsupported */ - memcpy(bad, file, len); - bad[0x1F] |= 0x80; - reseal(bad, front); - CHECK(!yapf_tex_load_memory(bad, len, 0, 1, &err) && err == YAPF_ERR_UNSUPPORTED, - "unknown needs bit is refused (%d)", err); - /* a feature in use but not announced: corrupt */ - memcpy(bad, file, len); - bad[0x1C] &= (uint8_t)~YAPF_NEED_WIDE; - reseal(bad, front); - CHECK(!yapf_tex_load_memory(bad, len, 0, 1, &err) && err == YAPF_ERR_CORRUPT, - "unannounced feature is refused (%d)", err); - /* the old API refuses what it cannot represent */ - CHECK(yapf_load_memory(file, len) == NULL, "yapf_load refuses half-float textures"); - - free(bad); - v2_fuzz(file, len, "half float + entropy"); - free(file); - yapf_tex_free(t); - - /* 8-bit RGBA with entropy planes (decoded several streams at once) */ - d = desc(140, 75, 4, 0); - t = yapf_tex_create(&d); - tex_fill(t, 2); - file = tex_roundtrip(t, YAPF_ENC_ENTROPY, &len, "fuzz setup rgba8"); - if (file) v2_fuzz(file, len, "rgba8 + entropy"); - free(file); - /* BC7 blocks with packed tiles */ - yapf_texture_t *c = NULL; - if (yapf_tex_compress(t, YAPF_GPU_BC7, &c) == YAPF_OK) { - file = tex_roundtrip(c, YAPF_ENC_ENTROPY, &len, "fuzz setup bc7"); - if (file) v2_fuzz(file, len, "packed BC7"); - free(file); - } - yapf_tex_free(c); - yapf_tex_free(t); -} - -/* Streaming: a file prefix holds the small mips; tiles decode alone. */ -static void v2_streaming(void) { - yapf_texture_t d = desc(300, 260, 4, 0); - d.shape = YAPF_SHAPE_CUBE; d.width = d.height = 260; d.mip_levels = 5; - yapf_texture_t *t = yapf_tex_create(&d); - tex_fill(t, 2); - void *buf = NULL; - size_t len = 0; - yapf_tex_encode(t, 0, &buf, &len); - uint8_t *file = (uint8_t *)buf; - int ok = 1, err = 0; - for (uint32_t m = 0; m < 5 && ok; m++) { - yapf_texture_t *probe = yapf_tex_open(file, len, 0, &err); - uint64_t need = probe ? yapf_tex_stream_bytes(probe, m) : 0; - yapf_tex_free(probe); - yapf_texture_t *s = yapf_tex_open(file, (size_t)need, 0, &err); - ok = s != NULL && need <= len && (m > 0 || need == len); - for (uint32_t f = 0; ok && f < 6; f++) - for (uint32_t mm = 0; ok && mm < 5; mm++) { - uint32_t sf = yapf_tex_surface(s, 0, 0, f, mm); - int rc = yapf_tex_decode_surface(s, file, (size_t)need, sf, 1); - if (mm >= m) ok = rc == YAPF_OK && - memcmp(s->data[sf], t->data[sf], yapf_tex_surface_bytes(t, mm)) == 0; - else ok = rc == YAPF_ERR_TRUNCATED; - } - yapf_tex_free(s); - } - CHECK(ok, "stream prefixes decode exactly their small mips"); - - /* tile decode equals the matching part of the full surface */ - yapf_texture_t *s = yapf_tex_open(file, len, 0, &err); - uint32_t sf = yapf_tex_surface(s, 0, 0, 3, 0), tx, ty; - yapf_tex_tile_grid(s, 0, &tx, &ty); - uint8_t tile[64 * 64 * 4]; - ok = s && tx == 5 && ty == 5; - for (uint32_t y = 0; ok && y < ty; y++) - for (uint32_t x = 0; ok && x < tx; x++) { - uint32_t px, py, pw, ph; - ok = yapf_tex_decode_tile(s, file, len, sf, x, y, 0, tile, 64 * 4, &px, &py, &pw, &ph) == YAPF_OK; - for (uint32_t r = 0; ok && r < ph; r++) - ok = memcmp(tile + r * 64 * 4, (uint8_t *)t->data[sf] + ((size_t)(py + r) * 260 + px) * 4, - (size_t)pw * 4) == 0; - } - CHECK(ok, "single tiles decode to the same pixels"); - yapf_tex_free(s); - yapf_free_buffer(buf); - yapf_tex_free(t); -} - -/* v1 and v2 work through either API where the data allows it. */ -static void v2_compat(const char *sample) { - yapf_texture_t *t = yapf_tex_load(sample, 0, 0, NULL); - if (t) { - uint32_t h = fnv((const uint8_t *)t->data[0], yapf_tex_surface_bytes(t, 0)); - CHECK(h == SAMPLE_HASH, "yapf_tex_load reads the v1 sample"); - size_t len; - uint8_t *file = tex_roundtrip(t, YAPF_ENC_ENTROPY, &len, "sample as v2"); - yapf_image_t *img = file ? yapf_load_memory(file, len) : NULL; - CHECK(img && img->width == 512 && img->channels == 4 && - fnv(img->pixels, 512u * 512u * 4u) == SAMPLE_HASH, "yapf_load reads an 8-bit v2 file"); - yapf_free(img); - free(file); - yapf_tex_free(t); - } - /* cube: the v1 API sees face 0 with its mips */ - yapf_texture_t d = desc(40, 40, 3, 0); - d.shape = YAPF_SHAPE_CUBE; d.mip_levels = 3; - yapf_texture_t *c = yapf_tex_create(&d); - tex_fill(c, 1); - size_t len; - uint8_t *file = tex_roundtrip(c, 0, &len, "cube for v1 API"); - yapf_image_t *img = file ? yapf_load_memory_mt(file, len, 2) : NULL; - CHECK(img && img->mip_levels == 3 && memcmp(img->mips[2], c->data[2], 10 * 10 * 3) == 0 && - memcmp(img->pixels, c->data[0], 40 * 40 * 3) == 0, "yapf_load reads face 0 of a cube"); - yapf_free(img); - free(file); - yapf_tex_free(c); -} - -static double psnr8(const uint8_t *a, int sa, const uint8_t *b, int sb, size_t n, int ch) { - double se = 0; - for (size_t i = 0; i < n; i++) - for (int c = 0; c < ch; c++) { - double v = (double)a[i * sa + c] - b[i * sb + c]; - se += v * v; - } - if (se == 0) return 99.0; - return 10.0 * log10(255.0 * 255.0 * (double)(n * ch) / se); -} - -static void v2_gpu(void) { - const uint32_t w = 61, h = 47; /* not multiples of 4 */ - yapf_texture_t d = desc(w, h, 4, 0); - yapf_texture_t *t = yapf_tex_create(&d); - uint8_t *p = (uint8_t *)t->data[0]; - for (uint32_t y = 0; y < h; y++) - for (uint32_t x = 0; x < w; x++) { - uint8_t *q = p + ((size_t)y * w + x) * 4; - q[0] = (uint8_t)(x * 4); q[1] = (uint8_t)(y * 5); q[2] = (uint8_t)(255 - x * 2); - q[3] = (uint8_t)(((x / 8 + y / 8) & 1) ? 255 : 40 + x); - } - static const struct { uint8_t f; int ch; double min; } F[] = { - { YAPF_GPU_BC1, 3, 30 }, { YAPF_GPU_BC3, 4, 30 }, { YAPF_GPU_BC7, 4, 34 }, - { YAPF_GPU_BC4, 1, 38 }, { YAPF_GPU_BC5, 2, 38 } - }; - uint8_t *out = (uint8_t *)malloc((size_t)w * h * 4); - for (size_t i = 0; i < sizeof(F) / sizeof(F[0]); i++) { - yapf_texture_t *c = NULL; - int rc = yapf_tex_compress(t, F[i].f, &c); - int ok = rc == YAPF_OK && c->payload == YAPF_PAYLOAD_BLOCKS && - yapf_blocks_decode(F[i].f, c->data[0], w, h, out) == YAPF_OK; - double q = 0; - if (ok && F[i].f == YAPF_GPU_BC1) { - /* BC1 keeps alpha only as cut-out: compare opaque texels */ - for (size_t k = 0; k < (size_t)w * h; k++) if (p[k * 4 + 3] < 128) memcpy(out + k * 4, p + k * 4, 3); - } - if (ok) q = psnr8(p, 4, out, 4, (size_t)w * h, F[i].ch); - CHECK(ok && q >= F[i].min, "GPU format 0x%02x encodes (PSNR %.1f dB)", F[i].f, q); - if (c) { - size_t len; - char what[32]; - sprintf(what, "compressed 0x%02x", F[i].f); - free(tex_roundtrip(c, YAPF_ENC_ENTROPY, &len, what)); - } - yapf_tex_free(c); - } - CHECK(yapf_blocks_decode(YAPF_GPU_ASTC_4x4, out, 4, 4, out) == YAPF_ERR_UNSUPPORTED, - "ASTC blocks are carried, not decoded"); - free(out); - yapf_tex_free(t); - - /* BC6H: relative error of a smooth HDR sky gradient */ - yapf_texture_t dh = desc(32, 32, 3, YAPF_SAMPLE_F16); - yapf_texture_t *th = yapf_tex_create(&dh), *ch = NULL; - uint16_t *hp = (uint16_t *)th->data[0]; - for (int i = 0; i < 32 * 32; i++) - for (int k = 0; k < 3; k++) hp[i * 3 + k] = yapf_float_to_half((0.3f + 0.4f * (float)k) * - (1.0f + (float)(i % 32) * 0.02f + (float)(i / 32) * 0.15f)); - int ok = yapf_tex_compress(th, YAPF_GPU_BC6H, &ch) == YAPF_OK; - uint16_t back[32 * 32 * 3]; - double worst = 0; - if (ok) ok = yapf_blocks_decode(YAPF_GPU_BC6H, ch->data[0], 32, 32, back) == YAPF_OK; - for (int i = 0; ok && i < 32 * 32 * 3; i++) { - float a = yapf_half_to_float(hp[i]), b = yapf_half_to_float(back[i]); - double r = (a > b ? a - b : b - a) / a; - if (r > worst) worst = r; - } - CHECK(ok && worst < 0.05, "BC6H encodes HDR within 5%% (worst %.4f)", worst); - yapf_tex_free(ch); - yapf_tex_free(th); -} - -static void v2_mips(void) { - /* sRGB: a black / white checker averages to sRGB 188, not 128 */ - yapf_texture_t d = desc(64, 64, 4, 0); - d.flags = YAPF_FLAG_SRGB; - yapf_texture_t *t = yapf_tex_create(&d); - uint8_t *p = (uint8_t *)t->data[0]; - for (int i = 0; i < 64 * 64; i++) { - uint8_t v = ((i % 64 + i / 64) & 1) ? 255 : 0; - p[i * 4] = p[i * 4 + 1] = p[i * 4 + 2] = v; - p[i * 4 + 3] = v; /* alpha stays linear */ - } - int ok = yapf_tex_build_mips(t, 0, 0) == YAPF_OK && t->mip_levels == 7; - const uint8_t *m1 = ok ? (const uint8_t *)t->data[1] : NULL; - CHECK(ok && m1[0] == 188 && m1[3] == 128 && (t->mip_filter & YAPF_MIP_LINEAR_LIGHT), - "sRGB mips average in linear light (got %d, alpha %d)", m1 ? m1[0] : -1, m1 ? m1[3] : -1); - yapf_tex_free(t); - - /* alpha test: speckled foliage (30 % of texels opaque). A plain box - * filter thins it out with distance; with alpha_ref = 128 every mip - * keeps about the same share of texels above 128. */ - double plain[5] = {0}, kept[5] = {0}; - for (int pass = 0; pass < 2; pass++) { - d = desc(128, 128, 4, 0); - t = yapf_tex_create(&d); - p = (uint8_t *)t->data[0]; - rng = 99; - for (int i = 0; i < 128 * 128; i++) p[i * 4 + 3] = rnd() % 100 < 30 ? 255 : 0; - ok = yapf_tex_build_mips(t, 5, pass ? 128 : 0) == YAPF_OK && t->mip_levels == 5; - if (pass) ok = ok && (t->flags & YAPF_FLAG_COVERAGE) && t->alpha_ref == 128; - for (uint32_t m = 1; ok && m < 5; m++) { - uint32_t w, h, n = 0; - yapf_tex_mip_size(t, m, &w, &h, NULL); - const uint8_t *q = (const uint8_t *)t->data[m]; - for (uint32_t i = 0; i < w * h; i++) n += q[i * 4 + 3] > 128; - (pass ? kept : plain)[m] = (double)n / (w * h); - } - if (pass) { - size_t len; - free(tex_roundtrip(t, 0, &len, "mipped texture")); - } - yapf_tex_free(t); - } - for (uint32_t m = 1; ok && m < 5; m++) ok = kept[m] > 0.2 && kept[m] < 0.4; - CHECK(ok && plain[2] < 0.15, "coverage-preserving mips keep alpha-test coverage " - "(mip 2: %.2f, plain box %.2f)", kept[2], plain[2]); - - /* float volume: 2×2×2 box */ - d = desc(4, 4, 1, YAPF_SAMPLE_F32); - d.shape = YAPF_SHAPE_VOLUME; d.depth = 4; - t = yapf_tex_create(&d); - float *f = (float *)t->data[0]; - for (int i = 0; i < 64; i++) f[i] = (float)i; - ok = yapf_tex_build_mips(t, 0, 0) == YAPF_OK && t->mip_levels == 3; - CHECK(ok && ((float *)t->data[1])[0] == (0 + 1 + 4 + 5 + 16 + 17 + 20 + 21) / 8.0f && - ((float *)t->data[2])[0] == 31.5f, "volume mips filter in 3D"); - yapf_tex_free(t); -} - -static void v2_preview(void) { - uint8_t out[4 * 4 * 4]; - /* gray + alpha u16 */ - yapf_texture_t d = desc(4, 4, 2, YAPF_SAMPLE_U16); - yapf_texture_t *t = yapf_tex_create(&d); - uint16_t *p = (uint16_t *)t->data[0]; - for (int i = 0; i < 16; i++) { p[2 * i] = 65535; p[2 * i + 1] = 32896; } - int ok = yapf_tex_to_rgba8(t, 0, 0, out) == YAPF_OK && - out[0] == 255 && out[1] == 255 && out[2] == 255 && out[3] == 128; - yapf_tex_free(t); - /* linear half 0.2140 → sRGB 128, 2.0 clamps, alpha stays linear */ - d = desc(4, 4, 4, YAPF_SAMPLE_F16); - t = yapf_tex_create(&d); - p = (uint16_t *)t->data[0]; - for (int i = 0; i < 16; i++) { - p[4 * i] = yapf_float_to_half(0.2158605f); p[4 * i + 1] = yapf_float_to_half(2.0f); - p[4 * i + 2] = yapf_float_to_half(-1.0f); p[4 * i + 3] = yapf_float_to_half(0.5f); - } - ok = ok && yapf_tex_to_rgba8(t, 0, 0, out) == YAPF_OK && - out[0] == 128 && out[1] == 255 && out[2] == 0 && out[3] == 128; - /* BC7 and BC6H go through the block decoders */ - yapf_texture_t *c = NULL; - ok = ok && yapf_tex_compress(t, YAPF_GPU_BC6H, &c) == YAPF_OK && - yapf_tex_to_rgba8(c, 0, 0, out) == YAPF_OK && out[3] == 255 && out[1] == 255; - yapf_tex_free(c); - yapf_tex_free(t); - CHECK(ok, "yapf_tex_to_rgba8 converts every payload for display"); -} - -static void v2_misc(void) { - int ok = 1; - for (uint32_t h = 0; h < 0x10000 && ok; h++) { - if ((h & 0x7C00) == 0x7C00 && (h & 0x3FF)) continue; /* NaN payloads */ - ok = yapf_float_to_half(yapf_half_to_float((uint16_t)h)) == h; - } - CHECK(ok, "every half survives half -> float -> half"); - CHECK(yapf_float_to_half(1.0f) == 0x3C00 && yapf_float_to_half(65520.0f) == 0x7C00 && - yapf_float_to_half(1e-8f) == 0 && yapf_float_to_half(-2.0f) == 0xC000, "float -> half rounding"); - /* fixed vectors pin yapf-sum to the specification */ - CHECK(yapf_checksum("", 0) == 0xd7550ed0u && yapf_checksum("YAPF", 4) == 0xc8cc41d4u && - yapf_checksum("The quick brown fox jumps over the lazy dog", 43) == 0xbce4f410u, - "yapf-sum test vectors"); - /* encoding is deterministic */ - yapf_texture_t d = desc(90, 70, 3, YAPF_SAMPLE_U16); - yapf_texture_t *t = yapf_tex_create(&d); - tex_fill(t, 2); - void *a = NULL, *b = NULL; - size_t la = 0, lb = 0; - yapf_tex_encode(t, YAPF_ENC_ENTROPY, &a, &la); - yapf_tex_encode(t, YAPF_ENC_ENTROPY, &b, &lb); - CHECK(a && la == lb && memcmp(a, b, la) == 0, "v2 encoding is deterministic"); - yapf_free_buffer(a); - yapf_free_buffer(b); - yapf_tex_free(t); - d = desc(10, 12, 4, 0); - d.shape = YAPF_SHAPE_CUBE; - CHECK(yapf_tex_create(&d) == NULL, "a cube must be square"); -} - -int main(int argc, char **argv) { - static const int sizes[][2] = { - {1, 1}, {1, 7}, {7, 1}, {63, 63}, {64, 64}, {65, 65}, {127, 1}, - {1, 129}, {97, 61}, {200, 130}, {256, 256}, {513, 77}, - {1000, 700} /* 176 tiles: big enough for the threaded decoder */ - }; - for (size_t s = 0; s < sizeof(sizes) / sizeof(sizes[0]); s++) - for (int ch = 1; ch <= 4; ch++) - for (int kind = 0; kind < 5; kind++) - roundtrip(sizes[s][0], sizes[s][1], ch, kind); - mips(); - corruption(); - save_matches_encode(); - - const char *sample = argc > 1 ? argv[1] : "other/YAPF.YAPF"; - yapf_image_t *img = yapf_load(sample); - if (img) { - uint32_t h = fnv(img->pixels, (size_t)img->width * img->height * img->channels); - CHECK(img->width == 512 && img->height == 512 && img->channels == 4 && - h == SAMPLE_HASH, "sample %s decodes to the reference pixels (hash %08x)", - sample, (unsigned)h); - yapf_free(img); - } else { - printf("note: sample %s not found, skipped\n", sample); - } - - v2_pixels(); - v2_layout(); - v2_blocks(); - v2_integrity(); - v2_streaming(); - v2_compat(sample); - v2_gpu(); - v2_mips(); - v2_misc(); - v2_preview(); - - printf("%d tests, %d failures\n", tests, fails); - return fails != 0; -} diff --git a/third_party/stb_image.h b/third_party/stb_image.h deleted file mode 100644 index 9eedabe..0000000 --- a/third_party/stb_image.h +++ /dev/null @@ -1,7988 +0,0 @@ -/* stb_image - v2.30 - public domain image loader - http://nothings.org/stb - no warranty implied; use at your own risk - - Do this: - #define STB_IMAGE_IMPLEMENTATION - before you include this file in *one* C or C++ file to create the implementation. - - // i.e. it should look like this: - #include ... - #include ... - #include ... - #define STB_IMAGE_IMPLEMENTATION - #include "stb_image.h" - - You can #define STBI_ASSERT(x) before the #include to avoid using assert.h. - And #define STBI_MALLOC, STBI_REALLOC, and STBI_FREE to avoid using malloc,realloc,free - - - QUICK NOTES: - Primarily of interest to game developers and other people who can - avoid problematic images and only need the trivial interface - - JPEG baseline & progressive (12 bpc/arithmetic not supported, same as stock IJG lib) - PNG 1/2/4/8/16-bit-per-channel - - TGA (not sure what subset, if a subset) - BMP non-1bpp, non-RLE - PSD (composited view only, no extra channels, 8/16 bit-per-channel) - - GIF (*comp always reports as 4-channel) - HDR (radiance rgbE format) - PIC (Softimage PIC) - PNM (PPM and PGM binary only) - - Animated GIF still needs a proper API, but here's one way to do it: - http://gist.github.com/urraka/685d9a6340b26b830d49 - - - decode from memory or through FILE (define STBI_NO_STDIO to remove code) - - decode from arbitrary I/O callbacks - - SIMD acceleration on x86/x64 (SSE2) and ARM (NEON) - - Full documentation under "DOCUMENTATION" below. - - -LICENSE - - See end of file for license information. - -RECENT REVISION HISTORY: - - 2.30 (2024-05-31) avoid erroneous gcc warning - 2.29 (2023-05-xx) optimizations - 2.28 (2023-01-29) many error fixes, security errors, just tons of stuff - 2.27 (2021-07-11) document stbi_info better, 16-bit PNM support, bug fixes - 2.26 (2020-07-13) many minor fixes - 2.25 (2020-02-02) fix warnings - 2.24 (2020-02-02) fix warnings; thread-local failure_reason and flip_vertically - 2.23 (2019-08-11) fix clang static analysis warning - 2.22 (2019-03-04) gif fixes, fix warnings - 2.21 (2019-02-25) fix typo in comment - 2.20 (2019-02-07) support utf8 filenames in Windows; fix warnings and platform ifdefs - 2.19 (2018-02-11) fix warning - 2.18 (2018-01-30) fix warnings - 2.17 (2018-01-29) bugfix, 1-bit BMP, 16-bitness query, fix warnings - 2.16 (2017-07-23) all functions have 16-bit variants; optimizations; bugfixes - 2.15 (2017-03-18) fix png-1,2,4; all Imagenet JPGs; no runtime SSE detection on GCC - 2.14 (2017-03-03) remove deprecated STBI_JPEG_OLD; fixes for Imagenet JPGs - 2.13 (2016-12-04) experimental 16-bit API, only for PNG so far; fixes - 2.12 (2016-04-02) fix typo in 2.11 PSD fix that caused crashes - 2.11 (2016-04-02) 16-bit PNGS; enable SSE2 in non-gcc x64 - RGB-format JPEG; remove white matting in PSD; - allocate large structures on the stack; - correct channel count for PNG & BMP - 2.10 (2016-01-22) avoid warning introduced in 2.09 - 2.09 (2016-01-16) 16-bit TGA; comments in PNM files; STBI_REALLOC_SIZED - - See end of file for full revision history. - - - ============================ Contributors ========================= - - Image formats Extensions, features - Sean Barrett (jpeg, png, bmp) Jetro Lauha (stbi_info) - Nicolas Schulz (hdr, psd) Martin "SpartanJ" Golini (stbi_info) - Jonathan Dummer (tga) James "moose2000" Brown (iPhone PNG) - Jean-Marc Lienher (gif) Ben "Disch" Wenger (io callbacks) - Tom Seddon (pic) Omar Cornut (1/2/4-bit PNG) - Thatcher Ulrich (psd) Nicolas Guillemot (vertical flip) - Ken Miller (pgm, ppm) Richard Mitton (16-bit PSD) - github:urraka (animated gif) Junggon Kim (PNM comments) - Christopher Forseth (animated gif) Daniel Gibson (16-bit TGA) - socks-the-fox (16-bit PNG) - Jeremy Sawicki (handle all ImageNet JPGs) - Optimizations & bugfixes Mikhail Morozov (1-bit BMP) - Fabian "ryg" Giesen Anael Seghezzi (is-16-bit query) - Arseny Kapoulkine Simon Breuss (16-bit PNM) - John-Mark Allen - Carmelo J Fdez-Aguera - - Bug & warning fixes - Marc LeBlanc David Woo Guillaume George Martins Mozeiko - Christpher Lloyd Jerry Jansson Joseph Thomson Blazej Dariusz Roszkowski - Phil Jordan Dave Moore Roy Eltham - Hayaki Saito Nathan Reed Won Chun - Luke Graham Johan Duparc Nick Verigakis the Horde3D community - Thomas Ruf Ronny Chevalier github:rlyeh - Janez Zemva John Bartholomew Michal Cichon github:romigrou - Jonathan Blow Ken Hamada Tero Hanninen github:svdijk - Eugene Golushkov Laurent Gomila Cort Stratton github:snagar - Aruelien Pocheville Sergio Gonzalez Thibault Reuille github:Zelex - Cass Everitt Ryamond Barbiero github:grim210 - Paul Du Bois Engin Manap Aldo Culquicondor github:sammyhw - Philipp Wiesemann Dale Weiler Oriol Ferrer Mesia github:phprus - Josh Tobin Neil Bickford Matthew Gregan github:poppolopoppo - Julian Raschke Gregory Mullen Christian Floisand github:darealshinji - Baldur Karlsson Kevin Schmidt JR Smith github:Michaelangel007 - Brad Weinberger Matvey Cherevko github:mosra - Luca Sas Alexander Veselov Zack Middleton [reserved] - Ryan C. Gordon [reserved] [reserved] - DO NOT ADD YOUR NAME HERE - - Jacko Dirks - - To add your name to the credits, pick a random blank space in the middle and fill it. - 80% of merge conflicts on stb PRs are due to people adding their name at the end - of the credits. -*/ - -#ifndef STBI_INCLUDE_STB_IMAGE_H -#define STBI_INCLUDE_STB_IMAGE_H - -// DOCUMENTATION -// -// Limitations: -// - no 12-bit-per-channel JPEG -// - no JPEGs with arithmetic coding -// - GIF always returns *comp=4 -// -// Basic usage (see HDR discussion below for HDR usage): -// int x,y,n; -// unsigned char *data = stbi_load(filename, &x, &y, &n, 0); -// // ... process data if not NULL ... -// // ... x = width, y = height, n = # 8-bit components per pixel ... -// // ... replace '0' with '1'..'4' to force that many components per pixel -// // ... but 'n' will always be the number that it would have been if you said 0 -// stbi_image_free(data); -// -// Standard parameters: -// int *x -- outputs image width in pixels -// int *y -- outputs image height in pixels -// int *channels_in_file -- outputs # of image components in image file -// int desired_channels -- if non-zero, # of image components requested in result -// -// The return value from an image loader is an 'unsigned char *' which points -// to the pixel data, or NULL on an allocation failure or if the image is -// corrupt or invalid. The pixel data consists of *y scanlines of *x pixels, -// with each pixel consisting of N interleaved 8-bit components; the first -// pixel pointed to is top-left-most in the image. There is no padding between -// image scanlines or between pixels, regardless of format. The number of -// components N is 'desired_channels' if desired_channels is non-zero, or -// *channels_in_file otherwise. If desired_channels is non-zero, -// *channels_in_file has the number of components that _would_ have been -// output otherwise. E.g. if you set desired_channels to 4, you will always -// get RGBA output, but you can check *channels_in_file to see if it's trivially -// opaque because e.g. there were only 3 channels in the source image. -// -// An output image with N components has the following components interleaved -// in this order in each pixel: -// -// N=#comp components -// 1 grey -// 2 grey, alpha -// 3 red, green, blue -// 4 red, green, blue, alpha -// -// If image loading fails for any reason, the return value will be NULL, -// and *x, *y, *channels_in_file will be unchanged. The function -// stbi_failure_reason() can be queried for an extremely brief, end-user -// unfriendly explanation of why the load failed. Define STBI_NO_FAILURE_STRINGS -// to avoid compiling these strings at all, and STBI_FAILURE_USERMSG to get slightly -// more user-friendly ones. -// -// Paletted PNG, BMP, GIF, and PIC images are automatically depalettized. -// -// To query the width, height and component count of an image without having to -// decode the full file, you can use the stbi_info family of functions: -// -// int x,y,n,ok; -// ok = stbi_info(filename, &x, &y, &n); -// // returns ok=1 and sets x, y, n if image is a supported format, -// // 0 otherwise. -// -// Note that stb_image pervasively uses ints in its public API for sizes, -// including sizes of memory buffers. This is now part of the API and thus -// hard to change without causing breakage. As a result, the various image -// loaders all have certain limits on image size; these differ somewhat -// by format but generally boil down to either just under 2GB or just under -// 1GB. When the decoded image would be larger than this, stb_image decoding -// will fail. -// -// Additionally, stb_image will reject image files that have any of their -// dimensions set to a larger value than the configurable STBI_MAX_DIMENSIONS, -// which defaults to 2**24 = 16777216 pixels. Due to the above memory limit, -// the only way to have an image with such dimensions load correctly -// is for it to have a rather extreme aspect ratio. Either way, the -// assumption here is that such larger images are likely to be malformed -// or malicious. If you do need to load an image with individual dimensions -// larger than that, and it still fits in the overall size limit, you can -// #define STBI_MAX_DIMENSIONS on your own to be something larger. -// -// =========================================================================== -// -// UNICODE: -// -// If compiling for Windows and you wish to use Unicode filenames, compile -// with -// #define STBI_WINDOWS_UTF8 -// and pass utf8-encoded filenames. Call stbi_convert_wchar_to_utf8 to convert -// Windows wchar_t filenames to utf8. -// -// =========================================================================== -// -// Philosophy -// -// stb libraries are designed with the following priorities: -// -// 1. easy to use -// 2. easy to maintain -// 3. good performance -// -// Sometimes I let "good performance" creep up in priority over "easy to maintain", -// and for best performance I may provide less-easy-to-use APIs that give higher -// performance, in addition to the easy-to-use ones. Nevertheless, it's important -// to keep in mind that from the standpoint of you, a client of this library, -// all you care about is #1 and #3, and stb libraries DO NOT emphasize #3 above all. -// -// Some secondary priorities arise directly from the first two, some of which -// provide more explicit reasons why performance can't be emphasized. -// -// - Portable ("ease of use") -// - Small source code footprint ("easy to maintain") -// - No dependencies ("ease of use") -// -// =========================================================================== -// -// I/O callbacks -// -// I/O callbacks allow you to read from arbitrary sources, like packaged -// files or some other source. Data read from callbacks are processed -// through a small internal buffer (currently 128 bytes) to try to reduce -// overhead. -// -// The three functions you must define are "read" (reads some bytes of data), -// "skip" (skips some bytes of data), "eof" (reports if the stream is at the end). -// -// =========================================================================== -// -// SIMD support -// -// The JPEG decoder will try to automatically use SIMD kernels on x86 when -// supported by the compiler. For ARM Neon support, you must explicitly -// request it. -// -// (The old do-it-yourself SIMD API is no longer supported in the current -// code.) -// -// On x86, SSE2 will automatically be used when available based on a run-time -// test; if not, the generic C versions are used as a fall-back. On ARM targets, -// the typical path is to have separate builds for NEON and non-NEON devices -// (at least this is true for iOS and Android). Therefore, the NEON support is -// toggled by a build flag: define STBI_NEON to get NEON loops. -// -// If for some reason you do not want to use any of SIMD code, or if -// you have issues compiling it, you can disable it entirely by -// defining STBI_NO_SIMD. -// -// =========================================================================== -// -// HDR image support (disable by defining STBI_NO_HDR) -// -// stb_image supports loading HDR images in general, and currently the Radiance -// .HDR file format specifically. You can still load any file through the existing -// interface; if you attempt to load an HDR file, it will be automatically remapped -// to LDR, assuming gamma 2.2 and an arbitrary scale factor defaulting to 1; -// both of these constants can be reconfigured through this interface: -// -// stbi_hdr_to_ldr_gamma(2.2f); -// stbi_hdr_to_ldr_scale(1.0f); -// -// (note, do not use _inverse_ constants; stbi_image will invert them -// appropriately). -// -// Additionally, there is a new, parallel interface for loading files as -// (linear) floats to preserve the full dynamic range: -// -// float *data = stbi_loadf(filename, &x, &y, &n, 0); -// -// If you load LDR images through this interface, those images will -// be promoted to floating point values, run through the inverse of -// constants corresponding to the above: -// -// stbi_ldr_to_hdr_scale(1.0f); -// stbi_ldr_to_hdr_gamma(2.2f); -// -// Finally, given a filename (or an open file or memory block--see header -// file for details) containing image data, you can query for the "most -// appropriate" interface to use (that is, whether the image is HDR or -// not), using: -// -// stbi_is_hdr(char *filename); -// -// =========================================================================== -// -// iPhone PNG support: -// -// We optionally support converting iPhone-formatted PNGs (which store -// premultiplied BGRA) back to RGB, even though they're internally encoded -// differently. To enable this conversion, call -// stbi_convert_iphone_png_to_rgb(1). -// -// Call stbi_set_unpremultiply_on_load(1) as well to force a divide per -// pixel to remove any premultiplied alpha *only* if the image file explicitly -// says there's premultiplied data (currently only happens in iPhone images, -// and only if iPhone convert-to-rgb processing is on). -// -// =========================================================================== -// -// ADDITIONAL CONFIGURATION -// -// - You can suppress implementation of any of the decoders to reduce -// your code footprint by #defining one or more of the following -// symbols before creating the implementation. -// -// STBI_NO_JPEG -// STBI_NO_PNG -// STBI_NO_BMP -// STBI_NO_PSD -// STBI_NO_TGA -// STBI_NO_GIF -// STBI_NO_HDR -// STBI_NO_PIC -// STBI_NO_PNM (.ppm and .pgm) -// -// - You can request *only* certain decoders and suppress all other ones -// (this will be more forward-compatible, as addition of new decoders -// doesn't require you to disable them explicitly): -// -// STBI_ONLY_JPEG -// STBI_ONLY_PNG -// STBI_ONLY_BMP -// STBI_ONLY_PSD -// STBI_ONLY_TGA -// STBI_ONLY_GIF -// STBI_ONLY_HDR -// STBI_ONLY_PIC -// STBI_ONLY_PNM (.ppm and .pgm) -// -// - If you use STBI_NO_PNG (or _ONLY_ without PNG), and you still -// want the zlib decoder to be available, #define STBI_SUPPORT_ZLIB -// -// - If you define STBI_MAX_DIMENSIONS, stb_image will reject images greater -// than that size (in either width or height) without further processing. -// This is to let programs in the wild set an upper bound to prevent -// denial-of-service attacks on untrusted data, as one could generate a -// valid image of gigantic dimensions and force stb_image to allocate a -// huge block of memory and spend disproportionate time decoding it. By -// default this is set to (1 << 24), which is 16777216, but that's still -// very big. - -#ifndef STBI_NO_STDIO -#include -#endif // STBI_NO_STDIO - -#define STBI_VERSION 1 - -enum -{ - STBI_default = 0, // only used for desired_channels - - STBI_grey = 1, - STBI_grey_alpha = 2, - STBI_rgb = 3, - STBI_rgb_alpha = 4 -}; - -#include -typedef unsigned char stbi_uc; -typedef unsigned short stbi_us; - -#ifdef __cplusplus -extern "C" { -#endif - -#ifndef STBIDEF -#ifdef STB_IMAGE_STATIC -#define STBIDEF static -#else -#define STBIDEF extern -#endif -#endif - -////////////////////////////////////////////////////////////////////////////// -// -// PRIMARY API - works on images of any type -// - -// -// load image by filename, open file, or memory buffer -// - -typedef struct -{ - int (*read) (void *user,char *data,int size); // fill 'data' with 'size' bytes. return number of bytes actually read - void (*skip) (void *user,int n); // skip the next 'n' bytes, or 'unget' the last -n bytes if negative - int (*eof) (void *user); // returns nonzero if we are at end of file/data -} stbi_io_callbacks; - -//////////////////////////////////// -// -// 8-bits-per-channel interface -// - -STBIDEF stbi_uc *stbi_load_from_memory (stbi_uc const *buffer, int len , int *x, int *y, int *channels_in_file, int desired_channels); -STBIDEF stbi_uc *stbi_load_from_callbacks(stbi_io_callbacks const *clbk , void *user, int *x, int *y, int *channels_in_file, int desired_channels); - -#ifndef STBI_NO_STDIO -STBIDEF stbi_uc *stbi_load (char const *filename, int *x, int *y, int *channels_in_file, int desired_channels); -STBIDEF stbi_uc *stbi_load_from_file (FILE *f, int *x, int *y, int *channels_in_file, int desired_channels); -// for stbi_load_from_file, file pointer is left pointing immediately after image -#endif - -#ifndef STBI_NO_GIF -STBIDEF stbi_uc *stbi_load_gif_from_memory(stbi_uc const *buffer, int len, int **delays, int *x, int *y, int *z, int *comp, int req_comp); -#endif - -#ifdef STBI_WINDOWS_UTF8 -STBIDEF int stbi_convert_wchar_to_utf8(char *buffer, size_t bufferlen, const wchar_t* input); -#endif - -//////////////////////////////////// -// -// 16-bits-per-channel interface -// - -STBIDEF stbi_us *stbi_load_16_from_memory (stbi_uc const *buffer, int len, int *x, int *y, int *channels_in_file, int desired_channels); -STBIDEF stbi_us *stbi_load_16_from_callbacks(stbi_io_callbacks const *clbk, void *user, int *x, int *y, int *channels_in_file, int desired_channels); - -#ifndef STBI_NO_STDIO -STBIDEF stbi_us *stbi_load_16 (char const *filename, int *x, int *y, int *channels_in_file, int desired_channels); -STBIDEF stbi_us *stbi_load_from_file_16(FILE *f, int *x, int *y, int *channels_in_file, int desired_channels); -#endif - -//////////////////////////////////// -// -// float-per-channel interface -// -#ifndef STBI_NO_LINEAR - STBIDEF float *stbi_loadf_from_memory (stbi_uc const *buffer, int len, int *x, int *y, int *channels_in_file, int desired_channels); - STBIDEF float *stbi_loadf_from_callbacks (stbi_io_callbacks const *clbk, void *user, int *x, int *y, int *channels_in_file, int desired_channels); - - #ifndef STBI_NO_STDIO - STBIDEF float *stbi_loadf (char const *filename, int *x, int *y, int *channels_in_file, int desired_channels); - STBIDEF float *stbi_loadf_from_file (FILE *f, int *x, int *y, int *channels_in_file, int desired_channels); - #endif -#endif - -#ifndef STBI_NO_HDR - STBIDEF void stbi_hdr_to_ldr_gamma(float gamma); - STBIDEF void stbi_hdr_to_ldr_scale(float scale); -#endif // STBI_NO_HDR - -#ifndef STBI_NO_LINEAR - STBIDEF void stbi_ldr_to_hdr_gamma(float gamma); - STBIDEF void stbi_ldr_to_hdr_scale(float scale); -#endif // STBI_NO_LINEAR - -// stbi_is_hdr is always defined, but always returns false if STBI_NO_HDR -STBIDEF int stbi_is_hdr_from_callbacks(stbi_io_callbacks const *clbk, void *user); -STBIDEF int stbi_is_hdr_from_memory(stbi_uc const *buffer, int len); -#ifndef STBI_NO_STDIO -STBIDEF int stbi_is_hdr (char const *filename); -STBIDEF int stbi_is_hdr_from_file(FILE *f); -#endif // STBI_NO_STDIO - - -// get a VERY brief reason for failure -// on most compilers (and ALL modern mainstream compilers) this is threadsafe -STBIDEF const char *stbi_failure_reason (void); - -// free the loaded image -- this is just free() -STBIDEF void stbi_image_free (void *retval_from_stbi_load); - -// get image dimensions & components without fully decoding -STBIDEF int stbi_info_from_memory(stbi_uc const *buffer, int len, int *x, int *y, int *comp); -STBIDEF int stbi_info_from_callbacks(stbi_io_callbacks const *clbk, void *user, int *x, int *y, int *comp); -STBIDEF int stbi_is_16_bit_from_memory(stbi_uc const *buffer, int len); -STBIDEF int stbi_is_16_bit_from_callbacks(stbi_io_callbacks const *clbk, void *user); - -#ifndef STBI_NO_STDIO -STBIDEF int stbi_info (char const *filename, int *x, int *y, int *comp); -STBIDEF int stbi_info_from_file (FILE *f, int *x, int *y, int *comp); -STBIDEF int stbi_is_16_bit (char const *filename); -STBIDEF int stbi_is_16_bit_from_file(FILE *f); -#endif - - - -// for image formats that explicitly notate that they have premultiplied alpha, -// we just return the colors as stored in the file. set this flag to force -// unpremultiplication. results are undefined if the unpremultiply overflow. -STBIDEF void stbi_set_unpremultiply_on_load(int flag_true_if_should_unpremultiply); - -// indicate whether we should process iphone images back to canonical format, -// or just pass them through "as-is" -STBIDEF void stbi_convert_iphone_png_to_rgb(int flag_true_if_should_convert); - -// flip the image vertically, so the first pixel in the output array is the bottom left -STBIDEF void stbi_set_flip_vertically_on_load(int flag_true_if_should_flip); - -// as above, but only applies to images loaded on the thread that calls the function -// this function is only available if your compiler supports thread-local variables; -// calling it will fail to link if your compiler doesn't -STBIDEF void stbi_set_unpremultiply_on_load_thread(int flag_true_if_should_unpremultiply); -STBIDEF void stbi_convert_iphone_png_to_rgb_thread(int flag_true_if_should_convert); -STBIDEF void stbi_set_flip_vertically_on_load_thread(int flag_true_if_should_flip); - -// ZLIB client - used by PNG, available for other purposes - -STBIDEF char *stbi_zlib_decode_malloc_guesssize(const char *buffer, int len, int initial_size, int *outlen); -STBIDEF char *stbi_zlib_decode_malloc_guesssize_headerflag(const char *buffer, int len, int initial_size, int *outlen, int parse_header); -STBIDEF char *stbi_zlib_decode_malloc(const char *buffer, int len, int *outlen); -STBIDEF int stbi_zlib_decode_buffer(char *obuffer, int olen, const char *ibuffer, int ilen); - -STBIDEF char *stbi_zlib_decode_noheader_malloc(const char *buffer, int len, int *outlen); -STBIDEF int stbi_zlib_decode_noheader_buffer(char *obuffer, int olen, const char *ibuffer, int ilen); - - -#ifdef __cplusplus -} -#endif - -// -// -//// end header file ///////////////////////////////////////////////////// -#endif // STBI_INCLUDE_STB_IMAGE_H - -#ifdef STB_IMAGE_IMPLEMENTATION - -#if defined(STBI_ONLY_JPEG) || defined(STBI_ONLY_PNG) || defined(STBI_ONLY_BMP) \ - || defined(STBI_ONLY_TGA) || defined(STBI_ONLY_GIF) || defined(STBI_ONLY_PSD) \ - || defined(STBI_ONLY_HDR) || defined(STBI_ONLY_PIC) || defined(STBI_ONLY_PNM) \ - || defined(STBI_ONLY_ZLIB) - #ifndef STBI_ONLY_JPEG - #define STBI_NO_JPEG - #endif - #ifndef STBI_ONLY_PNG - #define STBI_NO_PNG - #endif - #ifndef STBI_ONLY_BMP - #define STBI_NO_BMP - #endif - #ifndef STBI_ONLY_PSD - #define STBI_NO_PSD - #endif - #ifndef STBI_ONLY_TGA - #define STBI_NO_TGA - #endif - #ifndef STBI_ONLY_GIF - #define STBI_NO_GIF - #endif - #ifndef STBI_ONLY_HDR - #define STBI_NO_HDR - #endif - #ifndef STBI_ONLY_PIC - #define STBI_NO_PIC - #endif - #ifndef STBI_ONLY_PNM - #define STBI_NO_PNM - #endif -#endif - -#if defined(STBI_NO_PNG) && !defined(STBI_SUPPORT_ZLIB) && !defined(STBI_NO_ZLIB) -#define STBI_NO_ZLIB -#endif - - -#include -#include // ptrdiff_t on osx -#include -#include -#include - -#if !defined(STBI_NO_LINEAR) || !defined(STBI_NO_HDR) -#include // ldexp, pow -#endif - -#ifndef STBI_NO_STDIO -#include -#endif - -#ifndef STBI_ASSERT -#include -#define STBI_ASSERT(x) assert(x) -#endif - -#ifdef __cplusplus -#define STBI_EXTERN extern "C" -#else -#define STBI_EXTERN extern -#endif - - -#ifndef _MSC_VER - #ifdef __cplusplus - #define stbi_inline inline - #else - #define stbi_inline - #endif -#else - #define stbi_inline __forceinline -#endif - -#ifndef STBI_NO_THREAD_LOCALS - #if defined(__cplusplus) && __cplusplus >= 201103L - #define STBI_THREAD_LOCAL thread_local - #elif defined(__GNUC__) && __GNUC__ < 5 - #define STBI_THREAD_LOCAL __thread - #elif defined(_MSC_VER) - #define STBI_THREAD_LOCAL __declspec(thread) - #elif defined (__STDC_VERSION__) && __STDC_VERSION__ >= 201112L && !defined(__STDC_NO_THREADS__) - #define STBI_THREAD_LOCAL _Thread_local - #endif - - #ifndef STBI_THREAD_LOCAL - #if defined(__GNUC__) - #define STBI_THREAD_LOCAL __thread - #endif - #endif -#endif - -#if defined(_MSC_VER) || defined(__SYMBIAN32__) -typedef unsigned short stbi__uint16; -typedef signed short stbi__int16; -typedef unsigned int stbi__uint32; -typedef signed int stbi__int32; -#else -#include -typedef uint16_t stbi__uint16; -typedef int16_t stbi__int16; -typedef uint32_t stbi__uint32; -typedef int32_t stbi__int32; -#endif - -// should produce compiler error if size is wrong -typedef unsigned char validate_uint32[sizeof(stbi__uint32)==4 ? 1 : -1]; - -#ifdef _MSC_VER -#define STBI_NOTUSED(v) (void)(v) -#else -#define STBI_NOTUSED(v) (void)sizeof(v) -#endif - -#ifdef _MSC_VER -#define STBI_HAS_LROTL -#endif - -#ifdef STBI_HAS_LROTL - #define stbi_lrot(x,y) _lrotl(x,y) -#else - #define stbi_lrot(x,y) (((x) << (y)) | ((x) >> (-(y) & 31))) -#endif - -#if defined(STBI_MALLOC) && defined(STBI_FREE) && (defined(STBI_REALLOC) || defined(STBI_REALLOC_SIZED)) -// ok -#elif !defined(STBI_MALLOC) && !defined(STBI_FREE) && !defined(STBI_REALLOC) && !defined(STBI_REALLOC_SIZED) -// ok -#else -#error "Must define all or none of STBI_MALLOC, STBI_FREE, and STBI_REALLOC (or STBI_REALLOC_SIZED)." -#endif - -#ifndef STBI_MALLOC -#define STBI_MALLOC(sz) malloc(sz) -#define STBI_REALLOC(p,newsz) realloc(p,newsz) -#define STBI_FREE(p) free(p) -#endif - -#ifndef STBI_REALLOC_SIZED -#define STBI_REALLOC_SIZED(p,oldsz,newsz) STBI_REALLOC(p,newsz) -#endif - -// x86/x64 detection -#if defined(__x86_64__) || defined(_M_X64) -#define STBI__X64_TARGET -#elif defined(__i386) || defined(_M_IX86) -#define STBI__X86_TARGET -#endif - -#if defined(__GNUC__) && defined(STBI__X86_TARGET) && !defined(__SSE2__) && !defined(STBI_NO_SIMD) -// gcc doesn't support sse2 intrinsics unless you compile with -msse2, -// which in turn means it gets to use SSE2 everywhere. This is unfortunate, -// but previous attempts to provide the SSE2 functions with runtime -// detection caused numerous issues. The way architecture extensions are -// exposed in GCC/Clang is, sadly, not really suited for one-file libs. -// New behavior: if compiled with -msse2, we use SSE2 without any -// detection; if not, we don't use it at all. -#define STBI_NO_SIMD -#endif - -#if defined(__MINGW32__) && defined(STBI__X86_TARGET) && !defined(STBI_MINGW_ENABLE_SSE2) && !defined(STBI_NO_SIMD) -// Note that __MINGW32__ doesn't actually mean 32-bit, so we have to avoid STBI__X64_TARGET -// -// 32-bit MinGW wants ESP to be 16-byte aligned, but this is not in the -// Windows ABI and VC++ as well as Windows DLLs don't maintain that invariant. -// As a result, enabling SSE2 on 32-bit MinGW is dangerous when not -// simultaneously enabling "-mstackrealign". -// -// See https://github.com/nothings/stb/issues/81 for more information. -// -// So default to no SSE2 on 32-bit MinGW. If you've read this far and added -// -mstackrealign to your build settings, feel free to #define STBI_MINGW_ENABLE_SSE2. -#define STBI_NO_SIMD -#endif - -#if !defined(STBI_NO_SIMD) && (defined(STBI__X86_TARGET) || defined(STBI__X64_TARGET)) -#define STBI_SSE2 -#include - -#ifdef _MSC_VER - -#if _MSC_VER >= 1400 // not VC6 -#include // __cpuid -static int stbi__cpuid3(void) -{ - int info[4]; - __cpuid(info,1); - return info[3]; -} -#else -static int stbi__cpuid3(void) -{ - int res; - __asm { - mov eax,1 - cpuid - mov res,edx - } - return res; -} -#endif - -#define STBI_SIMD_ALIGN(type, name) __declspec(align(16)) type name - -#if !defined(STBI_NO_JPEG) && defined(STBI_SSE2) -static int stbi__sse2_available(void) -{ - int info3 = stbi__cpuid3(); - return ((info3 >> 26) & 1) != 0; -} -#endif - -#else // assume GCC-style if not VC++ -#define STBI_SIMD_ALIGN(type, name) type name __attribute__((aligned(16))) - -#if !defined(STBI_NO_JPEG) && defined(STBI_SSE2) -static int stbi__sse2_available(void) -{ - // If we're even attempting to compile this on GCC/Clang, that means - // -msse2 is on, which means the compiler is allowed to use SSE2 - // instructions at will, and so are we. - return 1; -} -#endif - -#endif -#endif - -// ARM NEON -#if defined(STBI_NO_SIMD) && defined(STBI_NEON) -#undef STBI_NEON -#endif - -#ifdef STBI_NEON -#include -#ifdef _MSC_VER -#define STBI_SIMD_ALIGN(type, name) __declspec(align(16)) type name -#else -#define STBI_SIMD_ALIGN(type, name) type name __attribute__((aligned(16))) -#endif -#endif - -#ifndef STBI_SIMD_ALIGN -#define STBI_SIMD_ALIGN(type, name) type name -#endif - -#ifndef STBI_MAX_DIMENSIONS -#define STBI_MAX_DIMENSIONS (1 << 24) -#endif - -/////////////////////////////////////////////// -// -// stbi__context struct and start_xxx functions - -// stbi__context structure is our basic context used by all images, so it -// contains all the IO context, plus some basic image information -typedef struct -{ - stbi__uint32 img_x, img_y; - int img_n, img_out_n; - - stbi_io_callbacks io; - void *io_user_data; - - int read_from_callbacks; - int buflen; - stbi_uc buffer_start[128]; - int callback_already_read; - - stbi_uc *img_buffer, *img_buffer_end; - stbi_uc *img_buffer_original, *img_buffer_original_end; -} stbi__context; - - -static void stbi__refill_buffer(stbi__context *s); - -// initialize a memory-decode context -static void stbi__start_mem(stbi__context *s, stbi_uc const *buffer, int len) -{ - s->io.read = NULL; - s->read_from_callbacks = 0; - s->callback_already_read = 0; - s->img_buffer = s->img_buffer_original = (stbi_uc *) buffer; - s->img_buffer_end = s->img_buffer_original_end = (stbi_uc *) buffer+len; -} - -// initialize a callback-based context -static void stbi__start_callbacks(stbi__context *s, stbi_io_callbacks *c, void *user) -{ - s->io = *c; - s->io_user_data = user; - s->buflen = sizeof(s->buffer_start); - s->read_from_callbacks = 1; - s->callback_already_read = 0; - s->img_buffer = s->img_buffer_original = s->buffer_start; - stbi__refill_buffer(s); - s->img_buffer_original_end = s->img_buffer_end; -} - -#ifndef STBI_NO_STDIO - -static int stbi__stdio_read(void *user, char *data, int size) -{ - return (int) fread(data,1,size,(FILE*) user); -} - -static void stbi__stdio_skip(void *user, int n) -{ - int ch; - fseek((FILE*) user, n, SEEK_CUR); - ch = fgetc((FILE*) user); /* have to read a byte to reset feof()'s flag */ - if (ch != EOF) { - ungetc(ch, (FILE *) user); /* push byte back onto stream if valid. */ - } -} - -static int stbi__stdio_eof(void *user) -{ - return feof((FILE*) user) || ferror((FILE *) user); -} - -static stbi_io_callbacks stbi__stdio_callbacks = -{ - stbi__stdio_read, - stbi__stdio_skip, - stbi__stdio_eof, -}; - -static void stbi__start_file(stbi__context *s, FILE *f) -{ - stbi__start_callbacks(s, &stbi__stdio_callbacks, (void *) f); -} - -//static void stop_file(stbi__context *s) { } - -#endif // !STBI_NO_STDIO - -static void stbi__rewind(stbi__context *s) -{ - // conceptually rewind SHOULD rewind to the beginning of the stream, - // but we just rewind to the beginning of the initial buffer, because - // we only use it after doing 'test', which only ever looks at at most 92 bytes - s->img_buffer = s->img_buffer_original; - s->img_buffer_end = s->img_buffer_original_end; -} - -enum -{ - STBI_ORDER_RGB, - STBI_ORDER_BGR -}; - -typedef struct -{ - int bits_per_channel; - int num_channels; - int channel_order; -} stbi__result_info; - -#ifndef STBI_NO_JPEG -static int stbi__jpeg_test(stbi__context *s); -static void *stbi__jpeg_load(stbi__context *s, int *x, int *y, int *comp, int req_comp, stbi__result_info *ri); -static int stbi__jpeg_info(stbi__context *s, int *x, int *y, int *comp); -#endif - -#ifndef STBI_NO_PNG -static int stbi__png_test(stbi__context *s); -static void *stbi__png_load(stbi__context *s, int *x, int *y, int *comp, int req_comp, stbi__result_info *ri); -static int stbi__png_info(stbi__context *s, int *x, int *y, int *comp); -static int stbi__png_is16(stbi__context *s); -#endif - -#ifndef STBI_NO_BMP -static int stbi__bmp_test(stbi__context *s); -static void *stbi__bmp_load(stbi__context *s, int *x, int *y, int *comp, int req_comp, stbi__result_info *ri); -static int stbi__bmp_info(stbi__context *s, int *x, int *y, int *comp); -#endif - -#ifndef STBI_NO_TGA -static int stbi__tga_test(stbi__context *s); -static void *stbi__tga_load(stbi__context *s, int *x, int *y, int *comp, int req_comp, stbi__result_info *ri); -static int stbi__tga_info(stbi__context *s, int *x, int *y, int *comp); -#endif - -#ifndef STBI_NO_PSD -static int stbi__psd_test(stbi__context *s); -static void *stbi__psd_load(stbi__context *s, int *x, int *y, int *comp, int req_comp, stbi__result_info *ri, int bpc); -static int stbi__psd_info(stbi__context *s, int *x, int *y, int *comp); -static int stbi__psd_is16(stbi__context *s); -#endif - -#ifndef STBI_NO_HDR -static int stbi__hdr_test(stbi__context *s); -static float *stbi__hdr_load(stbi__context *s, int *x, int *y, int *comp, int req_comp, stbi__result_info *ri); -static int stbi__hdr_info(stbi__context *s, int *x, int *y, int *comp); -#endif - -#ifndef STBI_NO_PIC -static int stbi__pic_test(stbi__context *s); -static void *stbi__pic_load(stbi__context *s, int *x, int *y, int *comp, int req_comp, stbi__result_info *ri); -static int stbi__pic_info(stbi__context *s, int *x, int *y, int *comp); -#endif - -#ifndef STBI_NO_GIF -static int stbi__gif_test(stbi__context *s); -static void *stbi__gif_load(stbi__context *s, int *x, int *y, int *comp, int req_comp, stbi__result_info *ri); -static void *stbi__load_gif_main(stbi__context *s, int **delays, int *x, int *y, int *z, int *comp, int req_comp); -static int stbi__gif_info(stbi__context *s, int *x, int *y, int *comp); -#endif - -#ifndef STBI_NO_PNM -static int stbi__pnm_test(stbi__context *s); -static void *stbi__pnm_load(stbi__context *s, int *x, int *y, int *comp, int req_comp, stbi__result_info *ri); -static int stbi__pnm_info(stbi__context *s, int *x, int *y, int *comp); -static int stbi__pnm_is16(stbi__context *s); -#endif - -static -#ifdef STBI_THREAD_LOCAL -STBI_THREAD_LOCAL -#endif -const char *stbi__g_failure_reason; - -STBIDEF const char *stbi_failure_reason(void) -{ - return stbi__g_failure_reason; -} - -#ifndef STBI_NO_FAILURE_STRINGS -static int stbi__err(const char *str) -{ - stbi__g_failure_reason = str; - return 0; -} -#endif - -static void *stbi__malloc(size_t size) -{ - return STBI_MALLOC(size); -} - -// stb_image uses ints pervasively, including for offset calculations. -// therefore the largest decoded image size we can support with the -// current code, even on 64-bit targets, is INT_MAX. this is not a -// significant limitation for the intended use case. -// -// we do, however, need to make sure our size calculations don't -// overflow. hence a few helper functions for size calculations that -// multiply integers together, making sure that they're non-negative -// and no overflow occurs. - -// return 1 if the sum is valid, 0 on overflow. -// negative terms are considered invalid. -static int stbi__addsizes_valid(int a, int b) -{ - if (b < 0) return 0; - // now 0 <= b <= INT_MAX, hence also - // 0 <= INT_MAX - b <= INTMAX. - // And "a + b <= INT_MAX" (which might overflow) is the - // same as a <= INT_MAX - b (no overflow) - return a <= INT_MAX - b; -} - -// returns 1 if the product is valid, 0 on overflow. -// negative factors are considered invalid. -static int stbi__mul2sizes_valid(int a, int b) -{ - if (a < 0 || b < 0) return 0; - if (b == 0) return 1; // mul-by-0 is always safe - // portable way to check for no overflows in a*b - return a <= INT_MAX/b; -} - -#if !defined(STBI_NO_JPEG) || !defined(STBI_NO_PNG) || !defined(STBI_NO_TGA) || !defined(STBI_NO_HDR) -// returns 1 if "a*b + add" has no negative terms/factors and doesn't overflow -static int stbi__mad2sizes_valid(int a, int b, int add) -{ - return stbi__mul2sizes_valid(a, b) && stbi__addsizes_valid(a*b, add); -} -#endif - -// returns 1 if "a*b*c + add" has no negative terms/factors and doesn't overflow -static int stbi__mad3sizes_valid(int a, int b, int c, int add) -{ - return stbi__mul2sizes_valid(a, b) && stbi__mul2sizes_valid(a*b, c) && - stbi__addsizes_valid(a*b*c, add); -} - -// returns 1 if "a*b*c*d + add" has no negative terms/factors and doesn't overflow -#if !defined(STBI_NO_LINEAR) || !defined(STBI_NO_HDR) || !defined(STBI_NO_PNM) -static int stbi__mad4sizes_valid(int a, int b, int c, int d, int add) -{ - return stbi__mul2sizes_valid(a, b) && stbi__mul2sizes_valid(a*b, c) && - stbi__mul2sizes_valid(a*b*c, d) && stbi__addsizes_valid(a*b*c*d, add); -} -#endif - -#if !defined(STBI_NO_JPEG) || !defined(STBI_NO_PNG) || !defined(STBI_NO_TGA) || !defined(STBI_NO_HDR) -// mallocs with size overflow checking -static void *stbi__malloc_mad2(int a, int b, int add) -{ - if (!stbi__mad2sizes_valid(a, b, add)) return NULL; - return stbi__malloc(a*b + add); -} -#endif - -static void *stbi__malloc_mad3(int a, int b, int c, int add) -{ - if (!stbi__mad3sizes_valid(a, b, c, add)) return NULL; - return stbi__malloc(a*b*c + add); -} - -#if !defined(STBI_NO_LINEAR) || !defined(STBI_NO_HDR) || !defined(STBI_NO_PNM) -static void *stbi__malloc_mad4(int a, int b, int c, int d, int add) -{ - if (!stbi__mad4sizes_valid(a, b, c, d, add)) return NULL; - return stbi__malloc(a*b*c*d + add); -} -#endif - -// returns 1 if the sum of two signed ints is valid (between -2^31 and 2^31-1 inclusive), 0 on overflow. -static int stbi__addints_valid(int a, int b) -{ - if ((a >= 0) != (b >= 0)) return 1; // a and b have different signs, so no overflow - if (a < 0 && b < 0) return a >= INT_MIN - b; // same as a + b >= INT_MIN; INT_MIN - b cannot overflow since b < 0. - return a <= INT_MAX - b; -} - -// returns 1 if the product of two ints fits in a signed short, 0 on overflow. -static int stbi__mul2shorts_valid(int a, int b) -{ - if (b == 0 || b == -1) return 1; // multiplication by 0 is always 0; check for -1 so SHRT_MIN/b doesn't overflow - if ((a >= 0) == (b >= 0)) return a <= SHRT_MAX/b; // product is positive, so similar to mul2sizes_valid - if (b < 0) return a <= SHRT_MIN / b; // same as a * b >= SHRT_MIN - return a >= SHRT_MIN / b; -} - -// stbi__err - error -// stbi__errpf - error returning pointer to float -// stbi__errpuc - error returning pointer to unsigned char - -#ifdef STBI_NO_FAILURE_STRINGS - #define stbi__err(x,y) 0 -#elif defined(STBI_FAILURE_USERMSG) - #define stbi__err(x,y) stbi__err(y) -#else - #define stbi__err(x,y) stbi__err(x) -#endif - -#define stbi__errpf(x,y) ((float *)(size_t) (stbi__err(x,y)?NULL:NULL)) -#define stbi__errpuc(x,y) ((unsigned char *)(size_t) (stbi__err(x,y)?NULL:NULL)) - -STBIDEF void stbi_image_free(void *retval_from_stbi_load) -{ - STBI_FREE(retval_from_stbi_load); -} - -#ifndef STBI_NO_LINEAR -static float *stbi__ldr_to_hdr(stbi_uc *data, int x, int y, int comp); -#endif - -#ifndef STBI_NO_HDR -static stbi_uc *stbi__hdr_to_ldr(float *data, int x, int y, int comp); -#endif - -static int stbi__vertically_flip_on_load_global = 0; - -STBIDEF void stbi_set_flip_vertically_on_load(int flag_true_if_should_flip) -{ - stbi__vertically_flip_on_load_global = flag_true_if_should_flip; -} - -#ifndef STBI_THREAD_LOCAL -#define stbi__vertically_flip_on_load stbi__vertically_flip_on_load_global -#else -static STBI_THREAD_LOCAL int stbi__vertically_flip_on_load_local, stbi__vertically_flip_on_load_set; - -STBIDEF void stbi_set_flip_vertically_on_load_thread(int flag_true_if_should_flip) -{ - stbi__vertically_flip_on_load_local = flag_true_if_should_flip; - stbi__vertically_flip_on_load_set = 1; -} - -#define stbi__vertically_flip_on_load (stbi__vertically_flip_on_load_set \ - ? stbi__vertically_flip_on_load_local \ - : stbi__vertically_flip_on_load_global) -#endif // STBI_THREAD_LOCAL - -static void *stbi__load_main(stbi__context *s, int *x, int *y, int *comp, int req_comp, stbi__result_info *ri, int bpc) -{ - memset(ri, 0, sizeof(*ri)); // make sure it's initialized if we add new fields - ri->bits_per_channel = 8; // default is 8 so most paths don't have to be changed - ri->channel_order = STBI_ORDER_RGB; // all current input & output are this, but this is here so we can add BGR order - ri->num_channels = 0; - - // test the formats with a very explicit header first (at least a FOURCC - // or distinctive magic number first) - #ifndef STBI_NO_PNG - if (stbi__png_test(s)) return stbi__png_load(s,x,y,comp,req_comp, ri); - #endif - #ifndef STBI_NO_BMP - if (stbi__bmp_test(s)) return stbi__bmp_load(s,x,y,comp,req_comp, ri); - #endif - #ifndef STBI_NO_GIF - if (stbi__gif_test(s)) return stbi__gif_load(s,x,y,comp,req_comp, ri); - #endif - #ifndef STBI_NO_PSD - if (stbi__psd_test(s)) return stbi__psd_load(s,x,y,comp,req_comp, ri, bpc); - #else - STBI_NOTUSED(bpc); - #endif - #ifndef STBI_NO_PIC - if (stbi__pic_test(s)) return stbi__pic_load(s,x,y,comp,req_comp, ri); - #endif - - // then the formats that can end up attempting to load with just 1 or 2 - // bytes matching expectations; these are prone to false positives, so - // try them later - #ifndef STBI_NO_JPEG - if (stbi__jpeg_test(s)) return stbi__jpeg_load(s,x,y,comp,req_comp, ri); - #endif - #ifndef STBI_NO_PNM - if (stbi__pnm_test(s)) return stbi__pnm_load(s,x,y,comp,req_comp, ri); - #endif - - #ifndef STBI_NO_HDR - if (stbi__hdr_test(s)) { - float *hdr = stbi__hdr_load(s, x,y,comp,req_comp, ri); - return stbi__hdr_to_ldr(hdr, *x, *y, req_comp ? req_comp : *comp); - } - #endif - - #ifndef STBI_NO_TGA - // test tga last because it's a crappy test! - if (stbi__tga_test(s)) - return stbi__tga_load(s,x,y,comp,req_comp, ri); - #endif - - return stbi__errpuc("unknown image type", "Image not of any known type, or corrupt"); -} - -static stbi_uc *stbi__convert_16_to_8(stbi__uint16 *orig, int w, int h, int channels) -{ - int i; - int img_len = w * h * channels; - stbi_uc *reduced; - - reduced = (stbi_uc *) stbi__malloc(img_len); - if (reduced == NULL) return stbi__errpuc("outofmem", "Out of memory"); - - for (i = 0; i < img_len; ++i) - reduced[i] = (stbi_uc)((orig[i] >> 8) & 0xFF); // top half of each byte is sufficient approx of 16->8 bit scaling - - STBI_FREE(orig); - return reduced; -} - -static stbi__uint16 *stbi__convert_8_to_16(stbi_uc *orig, int w, int h, int channels) -{ - int i; - int img_len = w * h * channels; - stbi__uint16 *enlarged; - - enlarged = (stbi__uint16 *) stbi__malloc(img_len*2); - if (enlarged == NULL) return (stbi__uint16 *) stbi__errpuc("outofmem", "Out of memory"); - - for (i = 0; i < img_len; ++i) - enlarged[i] = (stbi__uint16)((orig[i] << 8) + orig[i]); // replicate to high and low byte, maps 0->0, 255->0xffff - - STBI_FREE(orig); - return enlarged; -} - -static void stbi__vertical_flip(void *image, int w, int h, int bytes_per_pixel) -{ - int row; - size_t bytes_per_row = (size_t)w * bytes_per_pixel; - stbi_uc temp[2048]; - stbi_uc *bytes = (stbi_uc *)image; - - for (row = 0; row < (h>>1); row++) { - stbi_uc *row0 = bytes + row*bytes_per_row; - stbi_uc *row1 = bytes + (h - row - 1)*bytes_per_row; - // swap row0 with row1 - size_t bytes_left = bytes_per_row; - while (bytes_left) { - size_t bytes_copy = (bytes_left < sizeof(temp)) ? bytes_left : sizeof(temp); - memcpy(temp, row0, bytes_copy); - memcpy(row0, row1, bytes_copy); - memcpy(row1, temp, bytes_copy); - row0 += bytes_copy; - row1 += bytes_copy; - bytes_left -= bytes_copy; - } - } -} - -#ifndef STBI_NO_GIF -static void stbi__vertical_flip_slices(void *image, int w, int h, int z, int bytes_per_pixel) -{ - int slice; - int slice_size = w * h * bytes_per_pixel; - - stbi_uc *bytes = (stbi_uc *)image; - for (slice = 0; slice < z; ++slice) { - stbi__vertical_flip(bytes, w, h, bytes_per_pixel); - bytes += slice_size; - } -} -#endif - -static unsigned char *stbi__load_and_postprocess_8bit(stbi__context *s, int *x, int *y, int *comp, int req_comp) -{ - stbi__result_info ri; - void *result = stbi__load_main(s, x, y, comp, req_comp, &ri, 8); - - if (result == NULL) - return NULL; - - // it is the responsibility of the loaders to make sure we get either 8 or 16 bit. - STBI_ASSERT(ri.bits_per_channel == 8 || ri.bits_per_channel == 16); - - if (ri.bits_per_channel != 8) { - result = stbi__convert_16_to_8((stbi__uint16 *) result, *x, *y, req_comp == 0 ? *comp : req_comp); - ri.bits_per_channel = 8; - } - - // @TODO: move stbi__convert_format to here - - if (stbi__vertically_flip_on_load) { - int channels = req_comp ? req_comp : *comp; - stbi__vertical_flip(result, *x, *y, channels * sizeof(stbi_uc)); - } - - return (unsigned char *) result; -} - -static stbi__uint16 *stbi__load_and_postprocess_16bit(stbi__context *s, int *x, int *y, int *comp, int req_comp) -{ - stbi__result_info ri; - void *result = stbi__load_main(s, x, y, comp, req_comp, &ri, 16); - - if (result == NULL) - return NULL; - - // it is the responsibility of the loaders to make sure we get either 8 or 16 bit. - STBI_ASSERT(ri.bits_per_channel == 8 || ri.bits_per_channel == 16); - - if (ri.bits_per_channel != 16) { - result = stbi__convert_8_to_16((stbi_uc *) result, *x, *y, req_comp == 0 ? *comp : req_comp); - ri.bits_per_channel = 16; - } - - // @TODO: move stbi__convert_format16 to here - // @TODO: special case RGB-to-Y (and RGBA-to-YA) for 8-bit-to-16-bit case to keep more precision - - if (stbi__vertically_flip_on_load) { - int channels = req_comp ? req_comp : *comp; - stbi__vertical_flip(result, *x, *y, channels * sizeof(stbi__uint16)); - } - - return (stbi__uint16 *) result; -} - -#if !defined(STBI_NO_HDR) && !defined(STBI_NO_LINEAR) -static void stbi__float_postprocess(float *result, int *x, int *y, int *comp, int req_comp) -{ - if (stbi__vertically_flip_on_load && result != NULL) { - int channels = req_comp ? req_comp : *comp; - stbi__vertical_flip(result, *x, *y, channels * sizeof(float)); - } -} -#endif - -#ifndef STBI_NO_STDIO - -#if defined(_WIN32) && defined(STBI_WINDOWS_UTF8) -STBI_EXTERN __declspec(dllimport) int __stdcall MultiByteToWideChar(unsigned int cp, unsigned long flags, const char *str, int cbmb, wchar_t *widestr, int cchwide); -STBI_EXTERN __declspec(dllimport) int __stdcall WideCharToMultiByte(unsigned int cp, unsigned long flags, const wchar_t *widestr, int cchwide, char *str, int cbmb, const char *defchar, int *used_default); -#endif - -#if defined(_WIN32) && defined(STBI_WINDOWS_UTF8) -STBIDEF int stbi_convert_wchar_to_utf8(char *buffer, size_t bufferlen, const wchar_t* input) -{ - return WideCharToMultiByte(65001 /* UTF8 */, 0, input, -1, buffer, (int) bufferlen, NULL, NULL); -} -#endif - -static FILE *stbi__fopen(char const *filename, char const *mode) -{ - FILE *f; -#if defined(_WIN32) && defined(STBI_WINDOWS_UTF8) - wchar_t wMode[64]; - wchar_t wFilename[1024]; - if (0 == MultiByteToWideChar(65001 /* UTF8 */, 0, filename, -1, wFilename, sizeof(wFilename)/sizeof(*wFilename))) - return 0; - - if (0 == MultiByteToWideChar(65001 /* UTF8 */, 0, mode, -1, wMode, sizeof(wMode)/sizeof(*wMode))) - return 0; - -#if defined(_MSC_VER) && _MSC_VER >= 1400 - if (0 != _wfopen_s(&f, wFilename, wMode)) - f = 0; -#else - f = _wfopen(wFilename, wMode); -#endif - -#elif defined(_MSC_VER) && _MSC_VER >= 1400 - if (0 != fopen_s(&f, filename, mode)) - f=0; -#else - f = fopen(filename, mode); -#endif - return f; -} - - -STBIDEF stbi_uc *stbi_load(char const *filename, int *x, int *y, int *comp, int req_comp) -{ - FILE *f = stbi__fopen(filename, "rb"); - unsigned char *result; - if (!f) return stbi__errpuc("can't fopen", "Unable to open file"); - result = stbi_load_from_file(f,x,y,comp,req_comp); - fclose(f); - return result; -} - -STBIDEF stbi_uc *stbi_load_from_file(FILE *f, int *x, int *y, int *comp, int req_comp) -{ - unsigned char *result; - stbi__context s; - stbi__start_file(&s,f); - result = stbi__load_and_postprocess_8bit(&s,x,y,comp,req_comp); - if (result) { - // need to 'unget' all the characters in the IO buffer - fseek(f, - (int) (s.img_buffer_end - s.img_buffer), SEEK_CUR); - } - return result; -} - -STBIDEF stbi__uint16 *stbi_load_from_file_16(FILE *f, int *x, int *y, int *comp, int req_comp) -{ - stbi__uint16 *result; - stbi__context s; - stbi__start_file(&s,f); - result = stbi__load_and_postprocess_16bit(&s,x,y,comp,req_comp); - if (result) { - // need to 'unget' all the characters in the IO buffer - fseek(f, - (int) (s.img_buffer_end - s.img_buffer), SEEK_CUR); - } - return result; -} - -STBIDEF stbi_us *stbi_load_16(char const *filename, int *x, int *y, int *comp, int req_comp) -{ - FILE *f = stbi__fopen(filename, "rb"); - stbi__uint16 *result; - if (!f) return (stbi_us *) stbi__errpuc("can't fopen", "Unable to open file"); - result = stbi_load_from_file_16(f,x,y,comp,req_comp); - fclose(f); - return result; -} - - -#endif //!STBI_NO_STDIO - -STBIDEF stbi_us *stbi_load_16_from_memory(stbi_uc const *buffer, int len, int *x, int *y, int *channels_in_file, int desired_channels) -{ - stbi__context s; - stbi__start_mem(&s,buffer,len); - return stbi__load_and_postprocess_16bit(&s,x,y,channels_in_file,desired_channels); -} - -STBIDEF stbi_us *stbi_load_16_from_callbacks(stbi_io_callbacks const *clbk, void *user, int *x, int *y, int *channels_in_file, int desired_channels) -{ - stbi__context s; - stbi__start_callbacks(&s, (stbi_io_callbacks *)clbk, user); - return stbi__load_and_postprocess_16bit(&s,x,y,channels_in_file,desired_channels); -} - -STBIDEF stbi_uc *stbi_load_from_memory(stbi_uc const *buffer, int len, int *x, int *y, int *comp, int req_comp) -{ - stbi__context s; - stbi__start_mem(&s,buffer,len); - return stbi__load_and_postprocess_8bit(&s,x,y,comp,req_comp); -} - -STBIDEF stbi_uc *stbi_load_from_callbacks(stbi_io_callbacks const *clbk, void *user, int *x, int *y, int *comp, int req_comp) -{ - stbi__context s; - stbi__start_callbacks(&s, (stbi_io_callbacks *) clbk, user); - return stbi__load_and_postprocess_8bit(&s,x,y,comp,req_comp); -} - -#ifndef STBI_NO_GIF -STBIDEF stbi_uc *stbi_load_gif_from_memory(stbi_uc const *buffer, int len, int **delays, int *x, int *y, int *z, int *comp, int req_comp) -{ - unsigned char *result; - stbi__context s; - stbi__start_mem(&s,buffer,len); - - result = (unsigned char*) stbi__load_gif_main(&s, delays, x, y, z, comp, req_comp); - if (stbi__vertically_flip_on_load) { - stbi__vertical_flip_slices( result, *x, *y, *z, *comp ); - } - - return result; -} -#endif - -#ifndef STBI_NO_LINEAR -static float *stbi__loadf_main(stbi__context *s, int *x, int *y, int *comp, int req_comp) -{ - unsigned char *data; - #ifndef STBI_NO_HDR - if (stbi__hdr_test(s)) { - stbi__result_info ri; - float *hdr_data = stbi__hdr_load(s,x,y,comp,req_comp, &ri); - if (hdr_data) - stbi__float_postprocess(hdr_data,x,y,comp,req_comp); - return hdr_data; - } - #endif - data = stbi__load_and_postprocess_8bit(s, x, y, comp, req_comp); - if (data) - return stbi__ldr_to_hdr(data, *x, *y, req_comp ? req_comp : *comp); - return stbi__errpf("unknown image type", "Image not of any known type, or corrupt"); -} - -STBIDEF float *stbi_loadf_from_memory(stbi_uc const *buffer, int len, int *x, int *y, int *comp, int req_comp) -{ - stbi__context s; - stbi__start_mem(&s,buffer,len); - return stbi__loadf_main(&s,x,y,comp,req_comp); -} - -STBIDEF float *stbi_loadf_from_callbacks(stbi_io_callbacks const *clbk, void *user, int *x, int *y, int *comp, int req_comp) -{ - stbi__context s; - stbi__start_callbacks(&s, (stbi_io_callbacks *) clbk, user); - return stbi__loadf_main(&s,x,y,comp,req_comp); -} - -#ifndef STBI_NO_STDIO -STBIDEF float *stbi_loadf(char const *filename, int *x, int *y, int *comp, int req_comp) -{ - float *result; - FILE *f = stbi__fopen(filename, "rb"); - if (!f) return stbi__errpf("can't fopen", "Unable to open file"); - result = stbi_loadf_from_file(f,x,y,comp,req_comp); - fclose(f); - return result; -} - -STBIDEF float *stbi_loadf_from_file(FILE *f, int *x, int *y, int *comp, int req_comp) -{ - stbi__context s; - stbi__start_file(&s,f); - return stbi__loadf_main(&s,x,y,comp,req_comp); -} -#endif // !STBI_NO_STDIO - -#endif // !STBI_NO_LINEAR - -// these is-hdr-or-not is defined independent of whether STBI_NO_LINEAR is -// defined, for API simplicity; if STBI_NO_LINEAR is defined, it always -// reports false! - -STBIDEF int stbi_is_hdr_from_memory(stbi_uc const *buffer, int len) -{ - #ifndef STBI_NO_HDR - stbi__context s; - stbi__start_mem(&s,buffer,len); - return stbi__hdr_test(&s); - #else - STBI_NOTUSED(buffer); - STBI_NOTUSED(len); - return 0; - #endif -} - -#ifndef STBI_NO_STDIO -STBIDEF int stbi_is_hdr (char const *filename) -{ - FILE *f = stbi__fopen(filename, "rb"); - int result=0; - if (f) { - result = stbi_is_hdr_from_file(f); - fclose(f); - } - return result; -} - -STBIDEF int stbi_is_hdr_from_file(FILE *f) -{ - #ifndef STBI_NO_HDR - long pos = ftell(f); - int res; - stbi__context s; - stbi__start_file(&s,f); - res = stbi__hdr_test(&s); - fseek(f, pos, SEEK_SET); - return res; - #else - STBI_NOTUSED(f); - return 0; - #endif -} -#endif // !STBI_NO_STDIO - -STBIDEF int stbi_is_hdr_from_callbacks(stbi_io_callbacks const *clbk, void *user) -{ - #ifndef STBI_NO_HDR - stbi__context s; - stbi__start_callbacks(&s, (stbi_io_callbacks *) clbk, user); - return stbi__hdr_test(&s); - #else - STBI_NOTUSED(clbk); - STBI_NOTUSED(user); - return 0; - #endif -} - -#ifndef STBI_NO_LINEAR -static float stbi__l2h_gamma=2.2f, stbi__l2h_scale=1.0f; - -STBIDEF void stbi_ldr_to_hdr_gamma(float gamma) { stbi__l2h_gamma = gamma; } -STBIDEF void stbi_ldr_to_hdr_scale(float scale) { stbi__l2h_scale = scale; } -#endif - -static float stbi__h2l_gamma_i=1.0f/2.2f, stbi__h2l_scale_i=1.0f; - -STBIDEF void stbi_hdr_to_ldr_gamma(float gamma) { stbi__h2l_gamma_i = 1/gamma; } -STBIDEF void stbi_hdr_to_ldr_scale(float scale) { stbi__h2l_scale_i = 1/scale; } - - -////////////////////////////////////////////////////////////////////////////// -// -// Common code used by all image loaders -// - -enum -{ - STBI__SCAN_load=0, - STBI__SCAN_type, - STBI__SCAN_header -}; - -static void stbi__refill_buffer(stbi__context *s) -{ - int n = (s->io.read)(s->io_user_data,(char*)s->buffer_start,s->buflen); - s->callback_already_read += (int) (s->img_buffer - s->img_buffer_original); - if (n == 0) { - // at end of file, treat same as if from memory, but need to handle case - // where s->img_buffer isn't pointing to safe memory, e.g. 0-byte file - s->read_from_callbacks = 0; - s->img_buffer = s->buffer_start; - s->img_buffer_end = s->buffer_start+1; - *s->img_buffer = 0; - } else { - s->img_buffer = s->buffer_start; - s->img_buffer_end = s->buffer_start + n; - } -} - -stbi_inline static stbi_uc stbi__get8(stbi__context *s) -{ - if (s->img_buffer < s->img_buffer_end) - return *s->img_buffer++; - if (s->read_from_callbacks) { - stbi__refill_buffer(s); - return *s->img_buffer++; - } - return 0; -} - -#if defined(STBI_NO_JPEG) && defined(STBI_NO_HDR) && defined(STBI_NO_PIC) && defined(STBI_NO_PNM) -// nothing -#else -stbi_inline static int stbi__at_eof(stbi__context *s) -{ - if (s->io.read) { - if (!(s->io.eof)(s->io_user_data)) return 0; - // if feof() is true, check if buffer = end - // special case: we've only got the special 0 character at the end - if (s->read_from_callbacks == 0) return 1; - } - - return s->img_buffer >= s->img_buffer_end; -} -#endif - -#if defined(STBI_NO_JPEG) && defined(STBI_NO_PNG) && defined(STBI_NO_BMP) && defined(STBI_NO_PSD) && defined(STBI_NO_TGA) && defined(STBI_NO_GIF) && defined(STBI_NO_PIC) -// nothing -#else -static void stbi__skip(stbi__context *s, int n) -{ - if (n == 0) return; // already there! - if (n < 0) { - s->img_buffer = s->img_buffer_end; - return; - } - if (s->io.read) { - int blen = (int) (s->img_buffer_end - s->img_buffer); - if (blen < n) { - s->img_buffer = s->img_buffer_end; - (s->io.skip)(s->io_user_data, n - blen); - return; - } - } - s->img_buffer += n; -} -#endif - -#if defined(STBI_NO_PNG) && defined(STBI_NO_TGA) && defined(STBI_NO_HDR) && defined(STBI_NO_PNM) -// nothing -#else -static int stbi__getn(stbi__context *s, stbi_uc *buffer, int n) -{ - if (s->io.read) { - int blen = (int) (s->img_buffer_end - s->img_buffer); - if (blen < n) { - int res, count; - - memcpy(buffer, s->img_buffer, blen); - - count = (s->io.read)(s->io_user_data, (char*) buffer + blen, n - blen); - res = (count == (n-blen)); - s->img_buffer = s->img_buffer_end; - return res; - } - } - - if (s->img_buffer+n <= s->img_buffer_end) { - memcpy(buffer, s->img_buffer, n); - s->img_buffer += n; - return 1; - } else - return 0; -} -#endif - -#if defined(STBI_NO_JPEG) && defined(STBI_NO_PNG) && defined(STBI_NO_PSD) && defined(STBI_NO_PIC) -// nothing -#else -static int stbi__get16be(stbi__context *s) -{ - int z = stbi__get8(s); - return (z << 8) + stbi__get8(s); -} -#endif - -#if defined(STBI_NO_PNG) && defined(STBI_NO_PSD) && defined(STBI_NO_PIC) -// nothing -#else -static stbi__uint32 stbi__get32be(stbi__context *s) -{ - stbi__uint32 z = stbi__get16be(s); - return (z << 16) + stbi__get16be(s); -} -#endif - -#if defined(STBI_NO_BMP) && defined(STBI_NO_TGA) && defined(STBI_NO_GIF) -// nothing -#else -static int stbi__get16le(stbi__context *s) -{ - int z = stbi__get8(s); - return z + (stbi__get8(s) << 8); -} -#endif - -#ifndef STBI_NO_BMP -static stbi__uint32 stbi__get32le(stbi__context *s) -{ - stbi__uint32 z = stbi__get16le(s); - z += (stbi__uint32)stbi__get16le(s) << 16; - return z; -} -#endif - -#define STBI__BYTECAST(x) ((stbi_uc) ((x) & 255)) // truncate int to byte without warnings - -#if defined(STBI_NO_JPEG) && defined(STBI_NO_PNG) && defined(STBI_NO_BMP) && defined(STBI_NO_PSD) && defined(STBI_NO_TGA) && defined(STBI_NO_GIF) && defined(STBI_NO_PIC) && defined(STBI_NO_PNM) -// nothing -#else -////////////////////////////////////////////////////////////////////////////// -// -// generic converter from built-in img_n to req_comp -// individual types do this automatically as much as possible (e.g. jpeg -// does all cases internally since it needs to colorspace convert anyway, -// and it never has alpha, so very few cases ). png can automatically -// interleave an alpha=255 channel, but falls back to this for other cases -// -// assume data buffer is malloced, so malloc a new one and free that one -// only failure mode is malloc failing - -static stbi_uc stbi__compute_y(int r, int g, int b) -{ - return (stbi_uc) (((r*77) + (g*150) + (29*b)) >> 8); -} -#endif - -#if defined(STBI_NO_PNG) && defined(STBI_NO_BMP) && defined(STBI_NO_PSD) && defined(STBI_NO_TGA) && defined(STBI_NO_GIF) && defined(STBI_NO_PIC) && defined(STBI_NO_PNM) -// nothing -#else -static unsigned char *stbi__convert_format(unsigned char *data, int img_n, int req_comp, unsigned int x, unsigned int y) -{ - int i,j; - unsigned char *good; - - if (req_comp == img_n) return data; - STBI_ASSERT(req_comp >= 1 && req_comp <= 4); - - good = (unsigned char *) stbi__malloc_mad3(req_comp, x, y, 0); - if (good == NULL) { - STBI_FREE(data); - return stbi__errpuc("outofmem", "Out of memory"); - } - - for (j=0; j < (int) y; ++j) { - unsigned char *src = data + j * x * img_n ; - unsigned char *dest = good + j * x * req_comp; - - #define STBI__COMBO(a,b) ((a)*8+(b)) - #define STBI__CASE(a,b) case STBI__COMBO(a,b): for(i=x-1; i >= 0; --i, src += a, dest += b) - // convert source image with img_n components to one with req_comp components; - // avoid switch per pixel, so use switch per scanline and massive macros - switch (STBI__COMBO(img_n, req_comp)) { - STBI__CASE(1,2) { dest[0]=src[0]; dest[1]=255; } break; - STBI__CASE(1,3) { dest[0]=dest[1]=dest[2]=src[0]; } break; - STBI__CASE(1,4) { dest[0]=dest[1]=dest[2]=src[0]; dest[3]=255; } break; - STBI__CASE(2,1) { dest[0]=src[0]; } break; - STBI__CASE(2,3) { dest[0]=dest[1]=dest[2]=src[0]; } break; - STBI__CASE(2,4) { dest[0]=dest[1]=dest[2]=src[0]; dest[3]=src[1]; } break; - STBI__CASE(3,4) { dest[0]=src[0];dest[1]=src[1];dest[2]=src[2];dest[3]=255; } break; - STBI__CASE(3,1) { dest[0]=stbi__compute_y(src[0],src[1],src[2]); } break; - STBI__CASE(3,2) { dest[0]=stbi__compute_y(src[0],src[1],src[2]); dest[1] = 255; } break; - STBI__CASE(4,1) { dest[0]=stbi__compute_y(src[0],src[1],src[2]); } break; - STBI__CASE(4,2) { dest[0]=stbi__compute_y(src[0],src[1],src[2]); dest[1] = src[3]; } break; - STBI__CASE(4,3) { dest[0]=src[0];dest[1]=src[1];dest[2]=src[2]; } break; - default: STBI_ASSERT(0); STBI_FREE(data); STBI_FREE(good); return stbi__errpuc("unsupported", "Unsupported format conversion"); - } - #undef STBI__CASE - } - - STBI_FREE(data); - return good; -} -#endif - -#if defined(STBI_NO_PNG) && defined(STBI_NO_PSD) -// nothing -#else -static stbi__uint16 stbi__compute_y_16(int r, int g, int b) -{ - return (stbi__uint16) (((r*77) + (g*150) + (29*b)) >> 8); -} -#endif - -#if defined(STBI_NO_PNG) && defined(STBI_NO_PSD) -// nothing -#else -static stbi__uint16 *stbi__convert_format16(stbi__uint16 *data, int img_n, int req_comp, unsigned int x, unsigned int y) -{ - int i,j; - stbi__uint16 *good; - - if (req_comp == img_n) return data; - STBI_ASSERT(req_comp >= 1 && req_comp <= 4); - - good = (stbi__uint16 *) stbi__malloc(req_comp * x * y * 2); - if (good == NULL) { - STBI_FREE(data); - return (stbi__uint16 *) stbi__errpuc("outofmem", "Out of memory"); - } - - for (j=0; j < (int) y; ++j) { - stbi__uint16 *src = data + j * x * img_n ; - stbi__uint16 *dest = good + j * x * req_comp; - - #define STBI__COMBO(a,b) ((a)*8+(b)) - #define STBI__CASE(a,b) case STBI__COMBO(a,b): for(i=x-1; i >= 0; --i, src += a, dest += b) - // convert source image with img_n components to one with req_comp components; - // avoid switch per pixel, so use switch per scanline and massive macros - switch (STBI__COMBO(img_n, req_comp)) { - STBI__CASE(1,2) { dest[0]=src[0]; dest[1]=0xffff; } break; - STBI__CASE(1,3) { dest[0]=dest[1]=dest[2]=src[0]; } break; - STBI__CASE(1,4) { dest[0]=dest[1]=dest[2]=src[0]; dest[3]=0xffff; } break; - STBI__CASE(2,1) { dest[0]=src[0]; } break; - STBI__CASE(2,3) { dest[0]=dest[1]=dest[2]=src[0]; } break; - STBI__CASE(2,4) { dest[0]=dest[1]=dest[2]=src[0]; dest[3]=src[1]; } break; - STBI__CASE(3,4) { dest[0]=src[0];dest[1]=src[1];dest[2]=src[2];dest[3]=0xffff; } break; - STBI__CASE(3,1) { dest[0]=stbi__compute_y_16(src[0],src[1],src[2]); } break; - STBI__CASE(3,2) { dest[0]=stbi__compute_y_16(src[0],src[1],src[2]); dest[1] = 0xffff; } break; - STBI__CASE(4,1) { dest[0]=stbi__compute_y_16(src[0],src[1],src[2]); } break; - STBI__CASE(4,2) { dest[0]=stbi__compute_y_16(src[0],src[1],src[2]); dest[1] = src[3]; } break; - STBI__CASE(4,3) { dest[0]=src[0];dest[1]=src[1];dest[2]=src[2]; } break; - default: STBI_ASSERT(0); STBI_FREE(data); STBI_FREE(good); return (stbi__uint16*) stbi__errpuc("unsupported", "Unsupported format conversion"); - } - #undef STBI__CASE - } - - STBI_FREE(data); - return good; -} -#endif - -#ifndef STBI_NO_LINEAR -static float *stbi__ldr_to_hdr(stbi_uc *data, int x, int y, int comp) -{ - int i,k,n; - float *output; - if (!data) return NULL; - output = (float *) stbi__malloc_mad4(x, y, comp, sizeof(float), 0); - if (output == NULL) { STBI_FREE(data); return stbi__errpf("outofmem", "Out of memory"); } - // compute number of non-alpha components - if (comp & 1) n = comp; else n = comp-1; - for (i=0; i < x*y; ++i) { - for (k=0; k < n; ++k) { - output[i*comp + k] = (float) (pow(data[i*comp+k]/255.0f, stbi__l2h_gamma) * stbi__l2h_scale); - } - } - if (n < comp) { - for (i=0; i < x*y; ++i) { - output[i*comp + n] = data[i*comp + n]/255.0f; - } - } - STBI_FREE(data); - return output; -} -#endif - -#ifndef STBI_NO_HDR -#define stbi__float2int(x) ((int) (x)) -static stbi_uc *stbi__hdr_to_ldr(float *data, int x, int y, int comp) -{ - int i,k,n; - stbi_uc *output; - if (!data) return NULL; - output = (stbi_uc *) stbi__malloc_mad3(x, y, comp, 0); - if (output == NULL) { STBI_FREE(data); return stbi__errpuc("outofmem", "Out of memory"); } - // compute number of non-alpha components - if (comp & 1) n = comp; else n = comp-1; - for (i=0; i < x*y; ++i) { - for (k=0; k < n; ++k) { - float z = (float) pow(data[i*comp+k]*stbi__h2l_scale_i, stbi__h2l_gamma_i) * 255 + 0.5f; - if (z < 0) z = 0; - if (z > 255) z = 255; - output[i*comp + k] = (stbi_uc) stbi__float2int(z); - } - if (k < comp) { - float z = data[i*comp+k] * 255 + 0.5f; - if (z < 0) z = 0; - if (z > 255) z = 255; - output[i*comp + k] = (stbi_uc) stbi__float2int(z); - } - } - STBI_FREE(data); - return output; -} -#endif - -////////////////////////////////////////////////////////////////////////////// -// -// "baseline" JPEG/JFIF decoder -// -// simple implementation -// - doesn't support delayed output of y-dimension -// - simple interface (only one output format: 8-bit interleaved RGB) -// - doesn't try to recover corrupt jpegs -// - doesn't allow partial loading, loading multiple at once -// - still fast on x86 (copying globals into locals doesn't help x86) -// - allocates lots of intermediate memory (full size of all components) -// - non-interleaved case requires this anyway -// - allows good upsampling (see next) -// high-quality -// - upsampled channels are bilinearly interpolated, even across blocks -// - quality integer IDCT derived from IJG's 'slow' -// performance -// - fast huffman; reasonable integer IDCT -// - some SIMD kernels for common paths on targets with SSE2/NEON -// - uses a lot of intermediate memory, could cache poorly - -#ifndef STBI_NO_JPEG - -// huffman decoding acceleration -#define FAST_BITS 9 // larger handles more cases; smaller stomps less cache - -typedef struct -{ - stbi_uc fast[1 << FAST_BITS]; - // weirdly, repacking this into AoS is a 10% speed loss, instead of a win - stbi__uint16 code[256]; - stbi_uc values[256]; - stbi_uc size[257]; - unsigned int maxcode[18]; - int delta[17]; // old 'firstsymbol' - old 'firstcode' -} stbi__huffman; - -typedef struct -{ - stbi__context *s; - stbi__huffman huff_dc[4]; - stbi__huffman huff_ac[4]; - stbi__uint16 dequant[4][64]; - stbi__int16 fast_ac[4][1 << FAST_BITS]; - -// sizes for components, interleaved MCUs - int img_h_max, img_v_max; - int img_mcu_x, img_mcu_y; - int img_mcu_w, img_mcu_h; - -// definition of jpeg image component - struct - { - int id; - int h,v; - int tq; - int hd,ha; - int dc_pred; - - int x,y,w2,h2; - stbi_uc *data; - void *raw_data, *raw_coeff; - stbi_uc *linebuf; - short *coeff; // progressive only - int coeff_w, coeff_h; // number of 8x8 coefficient blocks - } img_comp[4]; - - stbi__uint32 code_buffer; // jpeg entropy-coded buffer - int code_bits; // number of valid bits - unsigned char marker; // marker seen while filling entropy buffer - int nomore; // flag if we saw a marker so must stop - - int progressive; - int spec_start; - int spec_end; - int succ_high; - int succ_low; - int eob_run; - int jfif; - int app14_color_transform; // Adobe APP14 tag - int rgb; - - int scan_n, order[4]; - int restart_interval, todo; - -// kernels - void (*idct_block_kernel)(stbi_uc *out, int out_stride, short data[64]); - void (*YCbCr_to_RGB_kernel)(stbi_uc *out, const stbi_uc *y, const stbi_uc *pcb, const stbi_uc *pcr, int count, int step); - stbi_uc *(*resample_row_hv_2_kernel)(stbi_uc *out, stbi_uc *in_near, stbi_uc *in_far, int w, int hs); -} stbi__jpeg; - -static int stbi__build_huffman(stbi__huffman *h, int *count) -{ - int i,j,k=0; - unsigned int code; - // build size list for each symbol (from JPEG spec) - for (i=0; i < 16; ++i) { - for (j=0; j < count[i]; ++j) { - h->size[k++] = (stbi_uc) (i+1); - if(k >= 257) return stbi__err("bad size list","Corrupt JPEG"); - } - } - h->size[k] = 0; - - // compute actual symbols (from jpeg spec) - code = 0; - k = 0; - for(j=1; j <= 16; ++j) { - // compute delta to add to code to compute symbol id - h->delta[j] = k - code; - if (h->size[k] == j) { - while (h->size[k] == j) - h->code[k++] = (stbi__uint16) (code++); - if (code-1 >= (1u << j)) return stbi__err("bad code lengths","Corrupt JPEG"); - } - // compute largest code + 1 for this size, preshifted as needed later - h->maxcode[j] = code << (16-j); - code <<= 1; - } - h->maxcode[j] = 0xffffffff; - - // build non-spec acceleration table; 255 is flag for not-accelerated - memset(h->fast, 255, 1 << FAST_BITS); - for (i=0; i < k; ++i) { - int s = h->size[i]; - if (s <= FAST_BITS) { - int c = h->code[i] << (FAST_BITS-s); - int m = 1 << (FAST_BITS-s); - for (j=0; j < m; ++j) { - h->fast[c+j] = (stbi_uc) i; - } - } - } - return 1; -} - -// build a table that decodes both magnitude and value of small ACs in -// one go. -static void stbi__build_fast_ac(stbi__int16 *fast_ac, stbi__huffman *h) -{ - int i; - for (i=0; i < (1 << FAST_BITS); ++i) { - stbi_uc fast = h->fast[i]; - fast_ac[i] = 0; - if (fast < 255) { - int rs = h->values[fast]; - int run = (rs >> 4) & 15; - int magbits = rs & 15; - int len = h->size[fast]; - - if (magbits && len + magbits <= FAST_BITS) { - // magnitude code followed by receive_extend code - int k = ((i << len) & ((1 << FAST_BITS) - 1)) >> (FAST_BITS - magbits); - int m = 1 << (magbits - 1); - if (k < m) k += (~0U << magbits) + 1; - // if the result is small enough, we can fit it in fast_ac table - if (k >= -128 && k <= 127) - fast_ac[i] = (stbi__int16) ((k * 256) + (run * 16) + (len + magbits)); - } - } - } -} - -static void stbi__grow_buffer_unsafe(stbi__jpeg *j) -{ - do { - unsigned int b = j->nomore ? 0 : stbi__get8(j->s); - if (b == 0xff) { - int c = stbi__get8(j->s); - while (c == 0xff) c = stbi__get8(j->s); // consume fill bytes - if (c != 0) { - j->marker = (unsigned char) c; - j->nomore = 1; - return; - } - } - j->code_buffer |= b << (24 - j->code_bits); - j->code_bits += 8; - } while (j->code_bits <= 24); -} - -// (1 << n) - 1 -static const stbi__uint32 stbi__bmask[17]={0,1,3,7,15,31,63,127,255,511,1023,2047,4095,8191,16383,32767,65535}; - -// decode a jpeg huffman value from the bitstream -stbi_inline static int stbi__jpeg_huff_decode(stbi__jpeg *j, stbi__huffman *h) -{ - unsigned int temp; - int c,k; - - if (j->code_bits < 16) stbi__grow_buffer_unsafe(j); - - // look at the top FAST_BITS and determine what symbol ID it is, - // if the code is <= FAST_BITS - c = (j->code_buffer >> (32 - FAST_BITS)) & ((1 << FAST_BITS)-1); - k = h->fast[c]; - if (k < 255) { - int s = h->size[k]; - if (s > j->code_bits) - return -1; - j->code_buffer <<= s; - j->code_bits -= s; - return h->values[k]; - } - - // naive test is to shift the code_buffer down so k bits are - // valid, then test against maxcode. To speed this up, we've - // preshifted maxcode left so that it has (16-k) 0s at the - // end; in other words, regardless of the number of bits, it - // wants to be compared against something shifted to have 16; - // that way we don't need to shift inside the loop. - temp = j->code_buffer >> 16; - for (k=FAST_BITS+1 ; ; ++k) - if (temp < h->maxcode[k]) - break; - if (k == 17) { - // error! code not found - j->code_bits -= 16; - return -1; - } - - if (k > j->code_bits) - return -1; - - // convert the huffman code to the symbol id - c = ((j->code_buffer >> (32 - k)) & stbi__bmask[k]) + h->delta[k]; - if(c < 0 || c >= 256) // symbol id out of bounds! - return -1; - STBI_ASSERT((((j->code_buffer) >> (32 - h->size[c])) & stbi__bmask[h->size[c]]) == h->code[c]); - - // convert the id to a symbol - j->code_bits -= k; - j->code_buffer <<= k; - return h->values[c]; -} - -// bias[n] = (-1<code_bits < n) stbi__grow_buffer_unsafe(j); - if (j->code_bits < n) return 0; // ran out of bits from stream, return 0s intead of continuing - - sgn = j->code_buffer >> 31; // sign bit always in MSB; 0 if MSB clear (positive), 1 if MSB set (negative) - k = stbi_lrot(j->code_buffer, n); - j->code_buffer = k & ~stbi__bmask[n]; - k &= stbi__bmask[n]; - j->code_bits -= n; - return k + (stbi__jbias[n] & (sgn - 1)); -} - -// get some unsigned bits -stbi_inline static int stbi__jpeg_get_bits(stbi__jpeg *j, int n) -{ - unsigned int k; - if (j->code_bits < n) stbi__grow_buffer_unsafe(j); - if (j->code_bits < n) return 0; // ran out of bits from stream, return 0s intead of continuing - k = stbi_lrot(j->code_buffer, n); - j->code_buffer = k & ~stbi__bmask[n]; - k &= stbi__bmask[n]; - j->code_bits -= n; - return k; -} - -stbi_inline static int stbi__jpeg_get_bit(stbi__jpeg *j) -{ - unsigned int k; - if (j->code_bits < 1) stbi__grow_buffer_unsafe(j); - if (j->code_bits < 1) return 0; // ran out of bits from stream, return 0s intead of continuing - k = j->code_buffer; - j->code_buffer <<= 1; - --j->code_bits; - return k & 0x80000000; -} - -// given a value that's at position X in the zigzag stream, -// where does it appear in the 8x8 matrix coded as row-major? -static const stbi_uc stbi__jpeg_dezigzag[64+15] = -{ - 0, 1, 8, 16, 9, 2, 3, 10, - 17, 24, 32, 25, 18, 11, 4, 5, - 12, 19, 26, 33, 40, 48, 41, 34, - 27, 20, 13, 6, 7, 14, 21, 28, - 35, 42, 49, 56, 57, 50, 43, 36, - 29, 22, 15, 23, 30, 37, 44, 51, - 58, 59, 52, 45, 38, 31, 39, 46, - 53, 60, 61, 54, 47, 55, 62, 63, - // let corrupt input sample past end - 63, 63, 63, 63, 63, 63, 63, 63, - 63, 63, 63, 63, 63, 63, 63 -}; - -// decode one 64-entry block-- -static int stbi__jpeg_decode_block(stbi__jpeg *j, short data[64], stbi__huffman *hdc, stbi__huffman *hac, stbi__int16 *fac, int b, stbi__uint16 *dequant) -{ - int diff,dc,k; - int t; - - if (j->code_bits < 16) stbi__grow_buffer_unsafe(j); - t = stbi__jpeg_huff_decode(j, hdc); - if (t < 0 || t > 15) return stbi__err("bad huffman code","Corrupt JPEG"); - - // 0 all the ac values now so we can do it 32-bits at a time - memset(data,0,64*sizeof(data[0])); - - diff = t ? stbi__extend_receive(j, t) : 0; - if (!stbi__addints_valid(j->img_comp[b].dc_pred, diff)) return stbi__err("bad delta","Corrupt JPEG"); - dc = j->img_comp[b].dc_pred + diff; - j->img_comp[b].dc_pred = dc; - if (!stbi__mul2shorts_valid(dc, dequant[0])) return stbi__err("can't merge dc and ac", "Corrupt JPEG"); - data[0] = (short) (dc * dequant[0]); - - // decode AC components, see JPEG spec - k = 1; - do { - unsigned int zig; - int c,r,s; - if (j->code_bits < 16) stbi__grow_buffer_unsafe(j); - c = (j->code_buffer >> (32 - FAST_BITS)) & ((1 << FAST_BITS)-1); - r = fac[c]; - if (r) { // fast-AC path - k += (r >> 4) & 15; // run - s = r & 15; // combined length - if (s > j->code_bits) return stbi__err("bad huffman code", "Combined length longer than code bits available"); - j->code_buffer <<= s; - j->code_bits -= s; - // decode into unzigzag'd location - zig = stbi__jpeg_dezigzag[k++]; - data[zig] = (short) ((r >> 8) * dequant[zig]); - } else { - int rs = stbi__jpeg_huff_decode(j, hac); - if (rs < 0) return stbi__err("bad huffman code","Corrupt JPEG"); - s = rs & 15; - r = rs >> 4; - if (s == 0) { - if (rs != 0xf0) break; // end block - k += 16; - } else { - k += r; - // decode into unzigzag'd location - zig = stbi__jpeg_dezigzag[k++]; - data[zig] = (short) (stbi__extend_receive(j,s) * dequant[zig]); - } - } - } while (k < 64); - return 1; -} - -static int stbi__jpeg_decode_block_prog_dc(stbi__jpeg *j, short data[64], stbi__huffman *hdc, int b) -{ - int diff,dc; - int t; - if (j->spec_end != 0) return stbi__err("can't merge dc and ac", "Corrupt JPEG"); - - if (j->code_bits < 16) stbi__grow_buffer_unsafe(j); - - if (j->succ_high == 0) { - // first scan for DC coefficient, must be first - memset(data,0,64*sizeof(data[0])); // 0 all the ac values now - t = stbi__jpeg_huff_decode(j, hdc); - if (t < 0 || t > 15) return stbi__err("can't merge dc and ac", "Corrupt JPEG"); - diff = t ? stbi__extend_receive(j, t) : 0; - - if (!stbi__addints_valid(j->img_comp[b].dc_pred, diff)) return stbi__err("bad delta", "Corrupt JPEG"); - dc = j->img_comp[b].dc_pred + diff; - j->img_comp[b].dc_pred = dc; - if (!stbi__mul2shorts_valid(dc, 1 << j->succ_low)) return stbi__err("can't merge dc and ac", "Corrupt JPEG"); - data[0] = (short) (dc * (1 << j->succ_low)); - } else { - // refinement scan for DC coefficient - if (stbi__jpeg_get_bit(j)) - data[0] += (short) (1 << j->succ_low); - } - return 1; -} - -// @OPTIMIZE: store non-zigzagged during the decode passes, -// and only de-zigzag when dequantizing -static int stbi__jpeg_decode_block_prog_ac(stbi__jpeg *j, short data[64], stbi__huffman *hac, stbi__int16 *fac) -{ - int k; - if (j->spec_start == 0) return stbi__err("can't merge dc and ac", "Corrupt JPEG"); - - if (j->succ_high == 0) { - int shift = j->succ_low; - - if (j->eob_run) { - --j->eob_run; - return 1; - } - - k = j->spec_start; - do { - unsigned int zig; - int c,r,s; - if (j->code_bits < 16) stbi__grow_buffer_unsafe(j); - c = (j->code_buffer >> (32 - FAST_BITS)) & ((1 << FAST_BITS)-1); - r = fac[c]; - if (r) { // fast-AC path - k += (r >> 4) & 15; // run - s = r & 15; // combined length - if (s > j->code_bits) return stbi__err("bad huffman code", "Combined length longer than code bits available"); - j->code_buffer <<= s; - j->code_bits -= s; - zig = stbi__jpeg_dezigzag[k++]; - data[zig] = (short) ((r >> 8) * (1 << shift)); - } else { - int rs = stbi__jpeg_huff_decode(j, hac); - if (rs < 0) return stbi__err("bad huffman code","Corrupt JPEG"); - s = rs & 15; - r = rs >> 4; - if (s == 0) { - if (r < 15) { - j->eob_run = (1 << r); - if (r) - j->eob_run += stbi__jpeg_get_bits(j, r); - --j->eob_run; - break; - } - k += 16; - } else { - k += r; - zig = stbi__jpeg_dezigzag[k++]; - data[zig] = (short) (stbi__extend_receive(j,s) * (1 << shift)); - } - } - } while (k <= j->spec_end); - } else { - // refinement scan for these AC coefficients - - short bit = (short) (1 << j->succ_low); - - if (j->eob_run) { - --j->eob_run; - for (k = j->spec_start; k <= j->spec_end; ++k) { - short *p = &data[stbi__jpeg_dezigzag[k]]; - if (*p != 0) - if (stbi__jpeg_get_bit(j)) - if ((*p & bit)==0) { - if (*p > 0) - *p += bit; - else - *p -= bit; - } - } - } else { - k = j->spec_start; - do { - int r,s; - int rs = stbi__jpeg_huff_decode(j, hac); // @OPTIMIZE see if we can use the fast path here, advance-by-r is so slow, eh - if (rs < 0) return stbi__err("bad huffman code","Corrupt JPEG"); - s = rs & 15; - r = rs >> 4; - if (s == 0) { - if (r < 15) { - j->eob_run = (1 << r) - 1; - if (r) - j->eob_run += stbi__jpeg_get_bits(j, r); - r = 64; // force end of block - } else { - // r=15 s=0 should write 16 0s, so we just do - // a run of 15 0s and then write s (which is 0), - // so we don't have to do anything special here - } - } else { - if (s != 1) return stbi__err("bad huffman code", "Corrupt JPEG"); - // sign bit - if (stbi__jpeg_get_bit(j)) - s = bit; - else - s = -bit; - } - - // advance by r - while (k <= j->spec_end) { - short *p = &data[stbi__jpeg_dezigzag[k++]]; - if (*p != 0) { - if (stbi__jpeg_get_bit(j)) - if ((*p & bit)==0) { - if (*p > 0) - *p += bit; - else - *p -= bit; - } - } else { - if (r == 0) { - *p = (short) s; - break; - } - --r; - } - } - } while (k <= j->spec_end); - } - } - return 1; -} - -// take a -128..127 value and stbi__clamp it and convert to 0..255 -stbi_inline static stbi_uc stbi__clamp(int x) -{ - // trick to use a single test to catch both cases - if ((unsigned int) x > 255) { - if (x < 0) return 0; - if (x > 255) return 255; - } - return (stbi_uc) x; -} - -#define stbi__f2f(x) ((int) (((x) * 4096 + 0.5))) -#define stbi__fsh(x) ((x) * 4096) - -// derived from jidctint -- DCT_ISLOW -#define STBI__IDCT_1D(s0,s1,s2,s3,s4,s5,s6,s7) \ - int t0,t1,t2,t3,p1,p2,p3,p4,p5,x0,x1,x2,x3; \ - p2 = s2; \ - p3 = s6; \ - p1 = (p2+p3) * stbi__f2f(0.5411961f); \ - t2 = p1 + p3*stbi__f2f(-1.847759065f); \ - t3 = p1 + p2*stbi__f2f( 0.765366865f); \ - p2 = s0; \ - p3 = s4; \ - t0 = stbi__fsh(p2+p3); \ - t1 = stbi__fsh(p2-p3); \ - x0 = t0+t3; \ - x3 = t0-t3; \ - x1 = t1+t2; \ - x2 = t1-t2; \ - t0 = s7; \ - t1 = s5; \ - t2 = s3; \ - t3 = s1; \ - p3 = t0+t2; \ - p4 = t1+t3; \ - p1 = t0+t3; \ - p2 = t1+t2; \ - p5 = (p3+p4)*stbi__f2f( 1.175875602f); \ - t0 = t0*stbi__f2f( 0.298631336f); \ - t1 = t1*stbi__f2f( 2.053119869f); \ - t2 = t2*stbi__f2f( 3.072711026f); \ - t3 = t3*stbi__f2f( 1.501321110f); \ - p1 = p5 + p1*stbi__f2f(-0.899976223f); \ - p2 = p5 + p2*stbi__f2f(-2.562915447f); \ - p3 = p3*stbi__f2f(-1.961570560f); \ - p4 = p4*stbi__f2f(-0.390180644f); \ - t3 += p1+p4; \ - t2 += p2+p3; \ - t1 += p2+p4; \ - t0 += p1+p3; - -static void stbi__idct_block(stbi_uc *out, int out_stride, short data[64]) -{ - int i,val[64],*v=val; - stbi_uc *o; - short *d = data; - - // columns - for (i=0; i < 8; ++i,++d, ++v) { - // if all zeroes, shortcut -- this avoids dequantizing 0s and IDCTing - if (d[ 8]==0 && d[16]==0 && d[24]==0 && d[32]==0 - && d[40]==0 && d[48]==0 && d[56]==0) { - // no shortcut 0 seconds - // (1|2|3|4|5|6|7)==0 0 seconds - // all separate -0.047 seconds - // 1 && 2|3 && 4|5 && 6|7: -0.047 seconds - int dcterm = d[0]*4; - v[0] = v[8] = v[16] = v[24] = v[32] = v[40] = v[48] = v[56] = dcterm; - } else { - STBI__IDCT_1D(d[ 0],d[ 8],d[16],d[24],d[32],d[40],d[48],d[56]) - // constants scaled things up by 1<<12; let's bring them back - // down, but keep 2 extra bits of precision - x0 += 512; x1 += 512; x2 += 512; x3 += 512; - v[ 0] = (x0+t3) >> 10; - v[56] = (x0-t3) >> 10; - v[ 8] = (x1+t2) >> 10; - v[48] = (x1-t2) >> 10; - v[16] = (x2+t1) >> 10; - v[40] = (x2-t1) >> 10; - v[24] = (x3+t0) >> 10; - v[32] = (x3-t0) >> 10; - } - } - - for (i=0, v=val, o=out; i < 8; ++i,v+=8,o+=out_stride) { - // no fast case since the first 1D IDCT spread components out - STBI__IDCT_1D(v[0],v[1],v[2],v[3],v[4],v[5],v[6],v[7]) - // constants scaled things up by 1<<12, plus we had 1<<2 from first - // loop, plus horizontal and vertical each scale by sqrt(8) so together - // we've got an extra 1<<3, so 1<<17 total we need to remove. - // so we want to round that, which means adding 0.5 * 1<<17, - // aka 65536. Also, we'll end up with -128 to 127 that we want - // to encode as 0..255 by adding 128, so we'll add that before the shift - x0 += 65536 + (128<<17); - x1 += 65536 + (128<<17); - x2 += 65536 + (128<<17); - x3 += 65536 + (128<<17); - // tried computing the shifts into temps, or'ing the temps to see - // if any were out of range, but that was slower - o[0] = stbi__clamp((x0+t3) >> 17); - o[7] = stbi__clamp((x0-t3) >> 17); - o[1] = stbi__clamp((x1+t2) >> 17); - o[6] = stbi__clamp((x1-t2) >> 17); - o[2] = stbi__clamp((x2+t1) >> 17); - o[5] = stbi__clamp((x2-t1) >> 17); - o[3] = stbi__clamp((x3+t0) >> 17); - o[4] = stbi__clamp((x3-t0) >> 17); - } -} - -#ifdef STBI_SSE2 -// sse2 integer IDCT. not the fastest possible implementation but it -// produces bit-identical results to the generic C version so it's -// fully "transparent". -static void stbi__idct_simd(stbi_uc *out, int out_stride, short data[64]) -{ - // This is constructed to match our regular (generic) integer IDCT exactly. - __m128i row0, row1, row2, row3, row4, row5, row6, row7; - __m128i tmp; - - // dot product constant: even elems=x, odd elems=y - #define dct_const(x,y) _mm_setr_epi16((x),(y),(x),(y),(x),(y),(x),(y)) - - // out(0) = c0[even]*x + c0[odd]*y (c0, x, y 16-bit, out 32-bit) - // out(1) = c1[even]*x + c1[odd]*y - #define dct_rot(out0,out1, x,y,c0,c1) \ - __m128i c0##lo = _mm_unpacklo_epi16((x),(y)); \ - __m128i c0##hi = _mm_unpackhi_epi16((x),(y)); \ - __m128i out0##_l = _mm_madd_epi16(c0##lo, c0); \ - __m128i out0##_h = _mm_madd_epi16(c0##hi, c0); \ - __m128i out1##_l = _mm_madd_epi16(c0##lo, c1); \ - __m128i out1##_h = _mm_madd_epi16(c0##hi, c1) - - // out = in << 12 (in 16-bit, out 32-bit) - #define dct_widen(out, in) \ - __m128i out##_l = _mm_srai_epi32(_mm_unpacklo_epi16(_mm_setzero_si128(), (in)), 4); \ - __m128i out##_h = _mm_srai_epi32(_mm_unpackhi_epi16(_mm_setzero_si128(), (in)), 4) - - // wide add - #define dct_wadd(out, a, b) \ - __m128i out##_l = _mm_add_epi32(a##_l, b##_l); \ - __m128i out##_h = _mm_add_epi32(a##_h, b##_h) - - // wide sub - #define dct_wsub(out, a, b) \ - __m128i out##_l = _mm_sub_epi32(a##_l, b##_l); \ - __m128i out##_h = _mm_sub_epi32(a##_h, b##_h) - - // butterfly a/b, add bias, then shift by "s" and pack - #define dct_bfly32o(out0, out1, a,b,bias,s) \ - { \ - __m128i abiased_l = _mm_add_epi32(a##_l, bias); \ - __m128i abiased_h = _mm_add_epi32(a##_h, bias); \ - dct_wadd(sum, abiased, b); \ - dct_wsub(dif, abiased, b); \ - out0 = _mm_packs_epi32(_mm_srai_epi32(sum_l, s), _mm_srai_epi32(sum_h, s)); \ - out1 = _mm_packs_epi32(_mm_srai_epi32(dif_l, s), _mm_srai_epi32(dif_h, s)); \ - } - - // 8-bit interleave step (for transposes) - #define dct_interleave8(a, b) \ - tmp = a; \ - a = _mm_unpacklo_epi8(a, b); \ - b = _mm_unpackhi_epi8(tmp, b) - - // 16-bit interleave step (for transposes) - #define dct_interleave16(a, b) \ - tmp = a; \ - a = _mm_unpacklo_epi16(a, b); \ - b = _mm_unpackhi_epi16(tmp, b) - - #define dct_pass(bias,shift) \ - { \ - /* even part */ \ - dct_rot(t2e,t3e, row2,row6, rot0_0,rot0_1); \ - __m128i sum04 = _mm_add_epi16(row0, row4); \ - __m128i dif04 = _mm_sub_epi16(row0, row4); \ - dct_widen(t0e, sum04); \ - dct_widen(t1e, dif04); \ - dct_wadd(x0, t0e, t3e); \ - dct_wsub(x3, t0e, t3e); \ - dct_wadd(x1, t1e, t2e); \ - dct_wsub(x2, t1e, t2e); \ - /* odd part */ \ - dct_rot(y0o,y2o, row7,row3, rot2_0,rot2_1); \ - dct_rot(y1o,y3o, row5,row1, rot3_0,rot3_1); \ - __m128i sum17 = _mm_add_epi16(row1, row7); \ - __m128i sum35 = _mm_add_epi16(row3, row5); \ - dct_rot(y4o,y5o, sum17,sum35, rot1_0,rot1_1); \ - dct_wadd(x4, y0o, y4o); \ - dct_wadd(x5, y1o, y5o); \ - dct_wadd(x6, y2o, y5o); \ - dct_wadd(x7, y3o, y4o); \ - dct_bfly32o(row0,row7, x0,x7,bias,shift); \ - dct_bfly32o(row1,row6, x1,x6,bias,shift); \ - dct_bfly32o(row2,row5, x2,x5,bias,shift); \ - dct_bfly32o(row3,row4, x3,x4,bias,shift); \ - } - - __m128i rot0_0 = dct_const(stbi__f2f(0.5411961f), stbi__f2f(0.5411961f) + stbi__f2f(-1.847759065f)); - __m128i rot0_1 = dct_const(stbi__f2f(0.5411961f) + stbi__f2f( 0.765366865f), stbi__f2f(0.5411961f)); - __m128i rot1_0 = dct_const(stbi__f2f(1.175875602f) + stbi__f2f(-0.899976223f), stbi__f2f(1.175875602f)); - __m128i rot1_1 = dct_const(stbi__f2f(1.175875602f), stbi__f2f(1.175875602f) + stbi__f2f(-2.562915447f)); - __m128i rot2_0 = dct_const(stbi__f2f(-1.961570560f) + stbi__f2f( 0.298631336f), stbi__f2f(-1.961570560f)); - __m128i rot2_1 = dct_const(stbi__f2f(-1.961570560f), stbi__f2f(-1.961570560f) + stbi__f2f( 3.072711026f)); - __m128i rot3_0 = dct_const(stbi__f2f(-0.390180644f) + stbi__f2f( 2.053119869f), stbi__f2f(-0.390180644f)); - __m128i rot3_1 = dct_const(stbi__f2f(-0.390180644f), stbi__f2f(-0.390180644f) + stbi__f2f( 1.501321110f)); - - // rounding biases in column/row passes, see stbi__idct_block for explanation. - __m128i bias_0 = _mm_set1_epi32(512); - __m128i bias_1 = _mm_set1_epi32(65536 + (128<<17)); - - // load - row0 = _mm_load_si128((const __m128i *) (data + 0*8)); - row1 = _mm_load_si128((const __m128i *) (data + 1*8)); - row2 = _mm_load_si128((const __m128i *) (data + 2*8)); - row3 = _mm_load_si128((const __m128i *) (data + 3*8)); - row4 = _mm_load_si128((const __m128i *) (data + 4*8)); - row5 = _mm_load_si128((const __m128i *) (data + 5*8)); - row6 = _mm_load_si128((const __m128i *) (data + 6*8)); - row7 = _mm_load_si128((const __m128i *) (data + 7*8)); - - // column pass - dct_pass(bias_0, 10); - - { - // 16bit 8x8 transpose pass 1 - dct_interleave16(row0, row4); - dct_interleave16(row1, row5); - dct_interleave16(row2, row6); - dct_interleave16(row3, row7); - - // transpose pass 2 - dct_interleave16(row0, row2); - dct_interleave16(row1, row3); - dct_interleave16(row4, row6); - dct_interleave16(row5, row7); - - // transpose pass 3 - dct_interleave16(row0, row1); - dct_interleave16(row2, row3); - dct_interleave16(row4, row5); - dct_interleave16(row6, row7); - } - - // row pass - dct_pass(bias_1, 17); - - { - // pack - __m128i p0 = _mm_packus_epi16(row0, row1); // a0a1a2a3...a7b0b1b2b3...b7 - __m128i p1 = _mm_packus_epi16(row2, row3); - __m128i p2 = _mm_packus_epi16(row4, row5); - __m128i p3 = _mm_packus_epi16(row6, row7); - - // 8bit 8x8 transpose pass 1 - dct_interleave8(p0, p2); // a0e0a1e1... - dct_interleave8(p1, p3); // c0g0c1g1... - - // transpose pass 2 - dct_interleave8(p0, p1); // a0c0e0g0... - dct_interleave8(p2, p3); // b0d0f0h0... - - // transpose pass 3 - dct_interleave8(p0, p2); // a0b0c0d0... - dct_interleave8(p1, p3); // a4b4c4d4... - - // store - _mm_storel_epi64((__m128i *) out, p0); out += out_stride; - _mm_storel_epi64((__m128i *) out, _mm_shuffle_epi32(p0, 0x4e)); out += out_stride; - _mm_storel_epi64((__m128i *) out, p2); out += out_stride; - _mm_storel_epi64((__m128i *) out, _mm_shuffle_epi32(p2, 0x4e)); out += out_stride; - _mm_storel_epi64((__m128i *) out, p1); out += out_stride; - _mm_storel_epi64((__m128i *) out, _mm_shuffle_epi32(p1, 0x4e)); out += out_stride; - _mm_storel_epi64((__m128i *) out, p3); out += out_stride; - _mm_storel_epi64((__m128i *) out, _mm_shuffle_epi32(p3, 0x4e)); - } - -#undef dct_const -#undef dct_rot -#undef dct_widen -#undef dct_wadd -#undef dct_wsub -#undef dct_bfly32o -#undef dct_interleave8 -#undef dct_interleave16 -#undef dct_pass -} - -#endif // STBI_SSE2 - -#ifdef STBI_NEON - -// NEON integer IDCT. should produce bit-identical -// results to the generic C version. -static void stbi__idct_simd(stbi_uc *out, int out_stride, short data[64]) -{ - int16x8_t row0, row1, row2, row3, row4, row5, row6, row7; - - int16x4_t rot0_0 = vdup_n_s16(stbi__f2f(0.5411961f)); - int16x4_t rot0_1 = vdup_n_s16(stbi__f2f(-1.847759065f)); - int16x4_t rot0_2 = vdup_n_s16(stbi__f2f( 0.765366865f)); - int16x4_t rot1_0 = vdup_n_s16(stbi__f2f( 1.175875602f)); - int16x4_t rot1_1 = vdup_n_s16(stbi__f2f(-0.899976223f)); - int16x4_t rot1_2 = vdup_n_s16(stbi__f2f(-2.562915447f)); - int16x4_t rot2_0 = vdup_n_s16(stbi__f2f(-1.961570560f)); - int16x4_t rot2_1 = vdup_n_s16(stbi__f2f(-0.390180644f)); - int16x4_t rot3_0 = vdup_n_s16(stbi__f2f( 0.298631336f)); - int16x4_t rot3_1 = vdup_n_s16(stbi__f2f( 2.053119869f)); - int16x4_t rot3_2 = vdup_n_s16(stbi__f2f( 3.072711026f)); - int16x4_t rot3_3 = vdup_n_s16(stbi__f2f( 1.501321110f)); - -#define dct_long_mul(out, inq, coeff) \ - int32x4_t out##_l = vmull_s16(vget_low_s16(inq), coeff); \ - int32x4_t out##_h = vmull_s16(vget_high_s16(inq), coeff) - -#define dct_long_mac(out, acc, inq, coeff) \ - int32x4_t out##_l = vmlal_s16(acc##_l, vget_low_s16(inq), coeff); \ - int32x4_t out##_h = vmlal_s16(acc##_h, vget_high_s16(inq), coeff) - -#define dct_widen(out, inq) \ - int32x4_t out##_l = vshll_n_s16(vget_low_s16(inq), 12); \ - int32x4_t out##_h = vshll_n_s16(vget_high_s16(inq), 12) - -// wide add -#define dct_wadd(out, a, b) \ - int32x4_t out##_l = vaddq_s32(a##_l, b##_l); \ - int32x4_t out##_h = vaddq_s32(a##_h, b##_h) - -// wide sub -#define dct_wsub(out, a, b) \ - int32x4_t out##_l = vsubq_s32(a##_l, b##_l); \ - int32x4_t out##_h = vsubq_s32(a##_h, b##_h) - -// butterfly a/b, then shift using "shiftop" by "s" and pack -#define dct_bfly32o(out0,out1, a,b,shiftop,s) \ - { \ - dct_wadd(sum, a, b); \ - dct_wsub(dif, a, b); \ - out0 = vcombine_s16(shiftop(sum_l, s), shiftop(sum_h, s)); \ - out1 = vcombine_s16(shiftop(dif_l, s), shiftop(dif_h, s)); \ - } - -#define dct_pass(shiftop, shift) \ - { \ - /* even part */ \ - int16x8_t sum26 = vaddq_s16(row2, row6); \ - dct_long_mul(p1e, sum26, rot0_0); \ - dct_long_mac(t2e, p1e, row6, rot0_1); \ - dct_long_mac(t3e, p1e, row2, rot0_2); \ - int16x8_t sum04 = vaddq_s16(row0, row4); \ - int16x8_t dif04 = vsubq_s16(row0, row4); \ - dct_widen(t0e, sum04); \ - dct_widen(t1e, dif04); \ - dct_wadd(x0, t0e, t3e); \ - dct_wsub(x3, t0e, t3e); \ - dct_wadd(x1, t1e, t2e); \ - dct_wsub(x2, t1e, t2e); \ - /* odd part */ \ - int16x8_t sum15 = vaddq_s16(row1, row5); \ - int16x8_t sum17 = vaddq_s16(row1, row7); \ - int16x8_t sum35 = vaddq_s16(row3, row5); \ - int16x8_t sum37 = vaddq_s16(row3, row7); \ - int16x8_t sumodd = vaddq_s16(sum17, sum35); \ - dct_long_mul(p5o, sumodd, rot1_0); \ - dct_long_mac(p1o, p5o, sum17, rot1_1); \ - dct_long_mac(p2o, p5o, sum35, rot1_2); \ - dct_long_mul(p3o, sum37, rot2_0); \ - dct_long_mul(p4o, sum15, rot2_1); \ - dct_wadd(sump13o, p1o, p3o); \ - dct_wadd(sump24o, p2o, p4o); \ - dct_wadd(sump23o, p2o, p3o); \ - dct_wadd(sump14o, p1o, p4o); \ - dct_long_mac(x4, sump13o, row7, rot3_0); \ - dct_long_mac(x5, sump24o, row5, rot3_1); \ - dct_long_mac(x6, sump23o, row3, rot3_2); \ - dct_long_mac(x7, sump14o, row1, rot3_3); \ - dct_bfly32o(row0,row7, x0,x7,shiftop,shift); \ - dct_bfly32o(row1,row6, x1,x6,shiftop,shift); \ - dct_bfly32o(row2,row5, x2,x5,shiftop,shift); \ - dct_bfly32o(row3,row4, x3,x4,shiftop,shift); \ - } - - // load - row0 = vld1q_s16(data + 0*8); - row1 = vld1q_s16(data + 1*8); - row2 = vld1q_s16(data + 2*8); - row3 = vld1q_s16(data + 3*8); - row4 = vld1q_s16(data + 4*8); - row5 = vld1q_s16(data + 5*8); - row6 = vld1q_s16(data + 6*8); - row7 = vld1q_s16(data + 7*8); - - // add DC bias - row0 = vaddq_s16(row0, vsetq_lane_s16(1024, vdupq_n_s16(0), 0)); - - // column pass - dct_pass(vrshrn_n_s32, 10); - - // 16bit 8x8 transpose - { -// these three map to a single VTRN.16, VTRN.32, and VSWP, respectively. -// whether compilers actually get this is another story, sadly. -#define dct_trn16(x, y) { int16x8x2_t t = vtrnq_s16(x, y); x = t.val[0]; y = t.val[1]; } -#define dct_trn32(x, y) { int32x4x2_t t = vtrnq_s32(vreinterpretq_s32_s16(x), vreinterpretq_s32_s16(y)); x = vreinterpretq_s16_s32(t.val[0]); y = vreinterpretq_s16_s32(t.val[1]); } -#define dct_trn64(x, y) { int16x8_t x0 = x; int16x8_t y0 = y; x = vcombine_s16(vget_low_s16(x0), vget_low_s16(y0)); y = vcombine_s16(vget_high_s16(x0), vget_high_s16(y0)); } - - // pass 1 - dct_trn16(row0, row1); // a0b0a2b2a4b4a6b6 - dct_trn16(row2, row3); - dct_trn16(row4, row5); - dct_trn16(row6, row7); - - // pass 2 - dct_trn32(row0, row2); // a0b0c0d0a4b4c4d4 - dct_trn32(row1, row3); - dct_trn32(row4, row6); - dct_trn32(row5, row7); - - // pass 3 - dct_trn64(row0, row4); // a0b0c0d0e0f0g0h0 - dct_trn64(row1, row5); - dct_trn64(row2, row6); - dct_trn64(row3, row7); - -#undef dct_trn16 -#undef dct_trn32 -#undef dct_trn64 - } - - // row pass - // vrshrn_n_s32 only supports shifts up to 16, we need - // 17. so do a non-rounding shift of 16 first then follow - // up with a rounding shift by 1. - dct_pass(vshrn_n_s32, 16); - - { - // pack and round - uint8x8_t p0 = vqrshrun_n_s16(row0, 1); - uint8x8_t p1 = vqrshrun_n_s16(row1, 1); - uint8x8_t p2 = vqrshrun_n_s16(row2, 1); - uint8x8_t p3 = vqrshrun_n_s16(row3, 1); - uint8x8_t p4 = vqrshrun_n_s16(row4, 1); - uint8x8_t p5 = vqrshrun_n_s16(row5, 1); - uint8x8_t p6 = vqrshrun_n_s16(row6, 1); - uint8x8_t p7 = vqrshrun_n_s16(row7, 1); - - // again, these can translate into one instruction, but often don't. -#define dct_trn8_8(x, y) { uint8x8x2_t t = vtrn_u8(x, y); x = t.val[0]; y = t.val[1]; } -#define dct_trn8_16(x, y) { uint16x4x2_t t = vtrn_u16(vreinterpret_u16_u8(x), vreinterpret_u16_u8(y)); x = vreinterpret_u8_u16(t.val[0]); y = vreinterpret_u8_u16(t.val[1]); } -#define dct_trn8_32(x, y) { uint32x2x2_t t = vtrn_u32(vreinterpret_u32_u8(x), vreinterpret_u32_u8(y)); x = vreinterpret_u8_u32(t.val[0]); y = vreinterpret_u8_u32(t.val[1]); } - - // sadly can't use interleaved stores here since we only write - // 8 bytes to each scan line! - - // 8x8 8-bit transpose pass 1 - dct_trn8_8(p0, p1); - dct_trn8_8(p2, p3); - dct_trn8_8(p4, p5); - dct_trn8_8(p6, p7); - - // pass 2 - dct_trn8_16(p0, p2); - dct_trn8_16(p1, p3); - dct_trn8_16(p4, p6); - dct_trn8_16(p5, p7); - - // pass 3 - dct_trn8_32(p0, p4); - dct_trn8_32(p1, p5); - dct_trn8_32(p2, p6); - dct_trn8_32(p3, p7); - - // store - vst1_u8(out, p0); out += out_stride; - vst1_u8(out, p1); out += out_stride; - vst1_u8(out, p2); out += out_stride; - vst1_u8(out, p3); out += out_stride; - vst1_u8(out, p4); out += out_stride; - vst1_u8(out, p5); out += out_stride; - vst1_u8(out, p6); out += out_stride; - vst1_u8(out, p7); - -#undef dct_trn8_8 -#undef dct_trn8_16 -#undef dct_trn8_32 - } - -#undef dct_long_mul -#undef dct_long_mac -#undef dct_widen -#undef dct_wadd -#undef dct_wsub -#undef dct_bfly32o -#undef dct_pass -} - -#endif // STBI_NEON - -#define STBI__MARKER_none 0xff -// if there's a pending marker from the entropy stream, return that -// otherwise, fetch from the stream and get a marker. if there's no -// marker, return 0xff, which is never a valid marker value -static stbi_uc stbi__get_marker(stbi__jpeg *j) -{ - stbi_uc x; - if (j->marker != STBI__MARKER_none) { x = j->marker; j->marker = STBI__MARKER_none; return x; } - x = stbi__get8(j->s); - if (x != 0xff) return STBI__MARKER_none; - while (x == 0xff) - x = stbi__get8(j->s); // consume repeated 0xff fill bytes - return x; -} - -// in each scan, we'll have scan_n components, and the order -// of the components is specified by order[] -#define STBI__RESTART(x) ((x) >= 0xd0 && (x) <= 0xd7) - -// after a restart interval, stbi__jpeg_reset the entropy decoder and -// the dc prediction -static void stbi__jpeg_reset(stbi__jpeg *j) -{ - j->code_bits = 0; - j->code_buffer = 0; - j->nomore = 0; - j->img_comp[0].dc_pred = j->img_comp[1].dc_pred = j->img_comp[2].dc_pred = j->img_comp[3].dc_pred = 0; - j->marker = STBI__MARKER_none; - j->todo = j->restart_interval ? j->restart_interval : 0x7fffffff; - j->eob_run = 0; - // no more than 1<<31 MCUs if no restart_interal? that's plenty safe, - // since we don't even allow 1<<30 pixels -} - -static int stbi__parse_entropy_coded_data(stbi__jpeg *z) -{ - stbi__jpeg_reset(z); - if (!z->progressive) { - if (z->scan_n == 1) { - int i,j; - STBI_SIMD_ALIGN(short, data[64]); - int n = z->order[0]; - // non-interleaved data, we just need to process one block at a time, - // in trivial scanline order - // number of blocks to do just depends on how many actual "pixels" this - // component has, independent of interleaved MCU blocking and such - int w = (z->img_comp[n].x+7) >> 3; - int h = (z->img_comp[n].y+7) >> 3; - for (j=0; j < h; ++j) { - for (i=0; i < w; ++i) { - int ha = z->img_comp[n].ha; - if (!stbi__jpeg_decode_block(z, data, z->huff_dc+z->img_comp[n].hd, z->huff_ac+ha, z->fast_ac[ha], n, z->dequant[z->img_comp[n].tq])) return 0; - z->idct_block_kernel(z->img_comp[n].data+z->img_comp[n].w2*j*8+i*8, z->img_comp[n].w2, data); - // every data block is an MCU, so countdown the restart interval - if (--z->todo <= 0) { - if (z->code_bits < 24) stbi__grow_buffer_unsafe(z); - // if it's NOT a restart, then just bail, so we get corrupt data - // rather than no data - if (!STBI__RESTART(z->marker)) return 1; - stbi__jpeg_reset(z); - } - } - } - return 1; - } else { // interleaved - int i,j,k,x,y; - STBI_SIMD_ALIGN(short, data[64]); - for (j=0; j < z->img_mcu_y; ++j) { - for (i=0; i < z->img_mcu_x; ++i) { - // scan an interleaved mcu... process scan_n components in order - for (k=0; k < z->scan_n; ++k) { - int n = z->order[k]; - // scan out an mcu's worth of this component; that's just determined - // by the basic H and V specified for the component - for (y=0; y < z->img_comp[n].v; ++y) { - for (x=0; x < z->img_comp[n].h; ++x) { - int x2 = (i*z->img_comp[n].h + x)*8; - int y2 = (j*z->img_comp[n].v + y)*8; - int ha = z->img_comp[n].ha; - if (!stbi__jpeg_decode_block(z, data, z->huff_dc+z->img_comp[n].hd, z->huff_ac+ha, z->fast_ac[ha], n, z->dequant[z->img_comp[n].tq])) return 0; - z->idct_block_kernel(z->img_comp[n].data+z->img_comp[n].w2*y2+x2, z->img_comp[n].w2, data); - } - } - } - // after all interleaved components, that's an interleaved MCU, - // so now count down the restart interval - if (--z->todo <= 0) { - if (z->code_bits < 24) stbi__grow_buffer_unsafe(z); - if (!STBI__RESTART(z->marker)) return 1; - stbi__jpeg_reset(z); - } - } - } - return 1; - } - } else { - if (z->scan_n == 1) { - int i,j; - int n = z->order[0]; - // non-interleaved data, we just need to process one block at a time, - // in trivial scanline order - // number of blocks to do just depends on how many actual "pixels" this - // component has, independent of interleaved MCU blocking and such - int w = (z->img_comp[n].x+7) >> 3; - int h = (z->img_comp[n].y+7) >> 3; - for (j=0; j < h; ++j) { - for (i=0; i < w; ++i) { - short *data = z->img_comp[n].coeff + 64 * (i + j * z->img_comp[n].coeff_w); - if (z->spec_start == 0) { - if (!stbi__jpeg_decode_block_prog_dc(z, data, &z->huff_dc[z->img_comp[n].hd], n)) - return 0; - } else { - int ha = z->img_comp[n].ha; - if (!stbi__jpeg_decode_block_prog_ac(z, data, &z->huff_ac[ha], z->fast_ac[ha])) - return 0; - } - // every data block is an MCU, so countdown the restart interval - if (--z->todo <= 0) { - if (z->code_bits < 24) stbi__grow_buffer_unsafe(z); - if (!STBI__RESTART(z->marker)) return 1; - stbi__jpeg_reset(z); - } - } - } - return 1; - } else { // interleaved - int i,j,k,x,y; - for (j=0; j < z->img_mcu_y; ++j) { - for (i=0; i < z->img_mcu_x; ++i) { - // scan an interleaved mcu... process scan_n components in order - for (k=0; k < z->scan_n; ++k) { - int n = z->order[k]; - // scan out an mcu's worth of this component; that's just determined - // by the basic H and V specified for the component - for (y=0; y < z->img_comp[n].v; ++y) { - for (x=0; x < z->img_comp[n].h; ++x) { - int x2 = (i*z->img_comp[n].h + x); - int y2 = (j*z->img_comp[n].v + y); - short *data = z->img_comp[n].coeff + 64 * (x2 + y2 * z->img_comp[n].coeff_w); - if (!stbi__jpeg_decode_block_prog_dc(z, data, &z->huff_dc[z->img_comp[n].hd], n)) - return 0; - } - } - } - // after all interleaved components, that's an interleaved MCU, - // so now count down the restart interval - if (--z->todo <= 0) { - if (z->code_bits < 24) stbi__grow_buffer_unsafe(z); - if (!STBI__RESTART(z->marker)) return 1; - stbi__jpeg_reset(z); - } - } - } - return 1; - } - } -} - -static void stbi__jpeg_dequantize(short *data, stbi__uint16 *dequant) -{ - int i; - for (i=0; i < 64; ++i) - data[i] *= dequant[i]; -} - -static void stbi__jpeg_finish(stbi__jpeg *z) -{ - if (z->progressive) { - // dequantize and idct the data - int i,j,n; - for (n=0; n < z->s->img_n; ++n) { - int w = (z->img_comp[n].x+7) >> 3; - int h = (z->img_comp[n].y+7) >> 3; - for (j=0; j < h; ++j) { - for (i=0; i < w; ++i) { - short *data = z->img_comp[n].coeff + 64 * (i + j * z->img_comp[n].coeff_w); - stbi__jpeg_dequantize(data, z->dequant[z->img_comp[n].tq]); - z->idct_block_kernel(z->img_comp[n].data+z->img_comp[n].w2*j*8+i*8, z->img_comp[n].w2, data); - } - } - } - } -} - -static int stbi__process_marker(stbi__jpeg *z, int m) -{ - int L; - switch (m) { - case STBI__MARKER_none: // no marker found - return stbi__err("expected marker","Corrupt JPEG"); - - case 0xDD: // DRI - specify restart interval - if (stbi__get16be(z->s) != 4) return stbi__err("bad DRI len","Corrupt JPEG"); - z->restart_interval = stbi__get16be(z->s); - return 1; - - case 0xDB: // DQT - define quantization table - L = stbi__get16be(z->s)-2; - while (L > 0) { - int q = stbi__get8(z->s); - int p = q >> 4, sixteen = (p != 0); - int t = q & 15,i; - if (p != 0 && p != 1) return stbi__err("bad DQT type","Corrupt JPEG"); - if (t > 3) return stbi__err("bad DQT table","Corrupt JPEG"); - - for (i=0; i < 64; ++i) - z->dequant[t][stbi__jpeg_dezigzag[i]] = (stbi__uint16)(sixteen ? stbi__get16be(z->s) : stbi__get8(z->s)); - L -= (sixteen ? 129 : 65); - } - return L==0; - - case 0xC4: // DHT - define huffman table - L = stbi__get16be(z->s)-2; - while (L > 0) { - stbi_uc *v; - int sizes[16],i,n=0; - int q = stbi__get8(z->s); - int tc = q >> 4; - int th = q & 15; - if (tc > 1 || th > 3) return stbi__err("bad DHT header","Corrupt JPEG"); - for (i=0; i < 16; ++i) { - sizes[i] = stbi__get8(z->s); - n += sizes[i]; - } - if(n > 256) return stbi__err("bad DHT header","Corrupt JPEG"); // Loop over i < n would write past end of values! - L -= 17; - if (tc == 0) { - if (!stbi__build_huffman(z->huff_dc+th, sizes)) return 0; - v = z->huff_dc[th].values; - } else { - if (!stbi__build_huffman(z->huff_ac+th, sizes)) return 0; - v = z->huff_ac[th].values; - } - for (i=0; i < n; ++i) - v[i] = stbi__get8(z->s); - if (tc != 0) - stbi__build_fast_ac(z->fast_ac[th], z->huff_ac + th); - L -= n; - } - return L==0; - } - - // check for comment block or APP blocks - if ((m >= 0xE0 && m <= 0xEF) || m == 0xFE) { - L = stbi__get16be(z->s); - if (L < 2) { - if (m == 0xFE) - return stbi__err("bad COM len","Corrupt JPEG"); - else - return stbi__err("bad APP len","Corrupt JPEG"); - } - L -= 2; - - if (m == 0xE0 && L >= 5) { // JFIF APP0 segment - static const unsigned char tag[5] = {'J','F','I','F','\0'}; - int ok = 1; - int i; - for (i=0; i < 5; ++i) - if (stbi__get8(z->s) != tag[i]) - ok = 0; - L -= 5; - if (ok) - z->jfif = 1; - } else if (m == 0xEE && L >= 12) { // Adobe APP14 segment - static const unsigned char tag[6] = {'A','d','o','b','e','\0'}; - int ok = 1; - int i; - for (i=0; i < 6; ++i) - if (stbi__get8(z->s) != tag[i]) - ok = 0; - L -= 6; - if (ok) { - stbi__get8(z->s); // version - stbi__get16be(z->s); // flags0 - stbi__get16be(z->s); // flags1 - z->app14_color_transform = stbi__get8(z->s); // color transform - L -= 6; - } - } - - stbi__skip(z->s, L); - return 1; - } - - return stbi__err("unknown marker","Corrupt JPEG"); -} - -// after we see SOS -static int stbi__process_scan_header(stbi__jpeg *z) -{ - int i; - int Ls = stbi__get16be(z->s); - z->scan_n = stbi__get8(z->s); - if (z->scan_n < 1 || z->scan_n > 4 || z->scan_n > (int) z->s->img_n) return stbi__err("bad SOS component count","Corrupt JPEG"); - if (Ls != 6+2*z->scan_n) return stbi__err("bad SOS len","Corrupt JPEG"); - for (i=0; i < z->scan_n; ++i) { - int id = stbi__get8(z->s), which; - int q = stbi__get8(z->s); - for (which = 0; which < z->s->img_n; ++which) - if (z->img_comp[which].id == id) - break; - if (which == z->s->img_n) return 0; // no match - z->img_comp[which].hd = q >> 4; if (z->img_comp[which].hd > 3) return stbi__err("bad DC huff","Corrupt JPEG"); - z->img_comp[which].ha = q & 15; if (z->img_comp[which].ha > 3) return stbi__err("bad AC huff","Corrupt JPEG"); - z->order[i] = which; - } - - { - int aa; - z->spec_start = stbi__get8(z->s); - z->spec_end = stbi__get8(z->s); // should be 63, but might be 0 - aa = stbi__get8(z->s); - z->succ_high = (aa >> 4); - z->succ_low = (aa & 15); - if (z->progressive) { - if (z->spec_start > 63 || z->spec_end > 63 || z->spec_start > z->spec_end || z->succ_high > 13 || z->succ_low > 13) - return stbi__err("bad SOS", "Corrupt JPEG"); - } else { - if (z->spec_start != 0) return stbi__err("bad SOS","Corrupt JPEG"); - if (z->succ_high != 0 || z->succ_low != 0) return stbi__err("bad SOS","Corrupt JPEG"); - z->spec_end = 63; - } - } - - return 1; -} - -static int stbi__free_jpeg_components(stbi__jpeg *z, int ncomp, int why) -{ - int i; - for (i=0; i < ncomp; ++i) { - if (z->img_comp[i].raw_data) { - STBI_FREE(z->img_comp[i].raw_data); - z->img_comp[i].raw_data = NULL; - z->img_comp[i].data = NULL; - } - if (z->img_comp[i].raw_coeff) { - STBI_FREE(z->img_comp[i].raw_coeff); - z->img_comp[i].raw_coeff = 0; - z->img_comp[i].coeff = 0; - } - if (z->img_comp[i].linebuf) { - STBI_FREE(z->img_comp[i].linebuf); - z->img_comp[i].linebuf = NULL; - } - } - return why; -} - -static int stbi__process_frame_header(stbi__jpeg *z, int scan) -{ - stbi__context *s = z->s; - int Lf,p,i,q, h_max=1,v_max=1,c; - Lf = stbi__get16be(s); if (Lf < 11) return stbi__err("bad SOF len","Corrupt JPEG"); // JPEG - p = stbi__get8(s); if (p != 8) return stbi__err("only 8-bit","JPEG format not supported: 8-bit only"); // JPEG baseline - s->img_y = stbi__get16be(s); if (s->img_y == 0) return stbi__err("no header height", "JPEG format not supported: delayed height"); // Legal, but we don't handle it--but neither does IJG - s->img_x = stbi__get16be(s); if (s->img_x == 0) return stbi__err("0 width","Corrupt JPEG"); // JPEG requires - if (s->img_y > STBI_MAX_DIMENSIONS) return stbi__err("too large","Very large image (corrupt?)"); - if (s->img_x > STBI_MAX_DIMENSIONS) return stbi__err("too large","Very large image (corrupt?)"); - c = stbi__get8(s); - if (c != 3 && c != 1 && c != 4) return stbi__err("bad component count","Corrupt JPEG"); - s->img_n = c; - for (i=0; i < c; ++i) { - z->img_comp[i].data = NULL; - z->img_comp[i].linebuf = NULL; - } - - if (Lf != 8+3*s->img_n) return stbi__err("bad SOF len","Corrupt JPEG"); - - z->rgb = 0; - for (i=0; i < s->img_n; ++i) { - static const unsigned char rgb[3] = { 'R', 'G', 'B' }; - z->img_comp[i].id = stbi__get8(s); - if (s->img_n == 3 && z->img_comp[i].id == rgb[i]) - ++z->rgb; - q = stbi__get8(s); - z->img_comp[i].h = (q >> 4); if (!z->img_comp[i].h || z->img_comp[i].h > 4) return stbi__err("bad H","Corrupt JPEG"); - z->img_comp[i].v = q & 15; if (!z->img_comp[i].v || z->img_comp[i].v > 4) return stbi__err("bad V","Corrupt JPEG"); - z->img_comp[i].tq = stbi__get8(s); if (z->img_comp[i].tq > 3) return stbi__err("bad TQ","Corrupt JPEG"); - } - - if (scan != STBI__SCAN_load) return 1; - - if (!stbi__mad3sizes_valid(s->img_x, s->img_y, s->img_n, 0)) return stbi__err("too large", "Image too large to decode"); - - for (i=0; i < s->img_n; ++i) { - if (z->img_comp[i].h > h_max) h_max = z->img_comp[i].h; - if (z->img_comp[i].v > v_max) v_max = z->img_comp[i].v; - } - - // check that plane subsampling factors are integer ratios; our resamplers can't deal with fractional ratios - // and I've never seen a non-corrupted JPEG file actually use them - for (i=0; i < s->img_n; ++i) { - if (h_max % z->img_comp[i].h != 0) return stbi__err("bad H","Corrupt JPEG"); - if (v_max % z->img_comp[i].v != 0) return stbi__err("bad V","Corrupt JPEG"); - } - - // compute interleaved mcu info - z->img_h_max = h_max; - z->img_v_max = v_max; - z->img_mcu_w = h_max * 8; - z->img_mcu_h = v_max * 8; - // these sizes can't be more than 17 bits - z->img_mcu_x = (s->img_x + z->img_mcu_w-1) / z->img_mcu_w; - z->img_mcu_y = (s->img_y + z->img_mcu_h-1) / z->img_mcu_h; - - for (i=0; i < s->img_n; ++i) { - // number of effective pixels (e.g. for non-interleaved MCU) - z->img_comp[i].x = (s->img_x * z->img_comp[i].h + h_max-1) / h_max; - z->img_comp[i].y = (s->img_y * z->img_comp[i].v + v_max-1) / v_max; - // to simplify generation, we'll allocate enough memory to decode - // the bogus oversized data from using interleaved MCUs and their - // big blocks (e.g. a 16x16 iMCU on an image of width 33); we won't - // discard the extra data until colorspace conversion - // - // img_mcu_x, img_mcu_y: <=17 bits; comp[i].h and .v are <=4 (checked earlier) - // so these muls can't overflow with 32-bit ints (which we require) - z->img_comp[i].w2 = z->img_mcu_x * z->img_comp[i].h * 8; - z->img_comp[i].h2 = z->img_mcu_y * z->img_comp[i].v * 8; - z->img_comp[i].coeff = 0; - z->img_comp[i].raw_coeff = 0; - z->img_comp[i].linebuf = NULL; - z->img_comp[i].raw_data = stbi__malloc_mad2(z->img_comp[i].w2, z->img_comp[i].h2, 15); - if (z->img_comp[i].raw_data == NULL) - return stbi__free_jpeg_components(z, i+1, stbi__err("outofmem", "Out of memory")); - // align blocks for idct using mmx/sse - z->img_comp[i].data = (stbi_uc*) (((size_t) z->img_comp[i].raw_data + 15) & ~15); - if (z->progressive) { - // w2, h2 are multiples of 8 (see above) - z->img_comp[i].coeff_w = z->img_comp[i].w2 / 8; - z->img_comp[i].coeff_h = z->img_comp[i].h2 / 8; - z->img_comp[i].raw_coeff = stbi__malloc_mad3(z->img_comp[i].w2, z->img_comp[i].h2, sizeof(short), 15); - if (z->img_comp[i].raw_coeff == NULL) - return stbi__free_jpeg_components(z, i+1, stbi__err("outofmem", "Out of memory")); - z->img_comp[i].coeff = (short*) (((size_t) z->img_comp[i].raw_coeff + 15) & ~15); - } - } - - return 1; -} - -// use comparisons since in some cases we handle more than one case (e.g. SOF) -#define stbi__DNL(x) ((x) == 0xdc) -#define stbi__SOI(x) ((x) == 0xd8) -#define stbi__EOI(x) ((x) == 0xd9) -#define stbi__SOF(x) ((x) == 0xc0 || (x) == 0xc1 || (x) == 0xc2) -#define stbi__SOS(x) ((x) == 0xda) - -#define stbi__SOF_progressive(x) ((x) == 0xc2) - -static int stbi__decode_jpeg_header(stbi__jpeg *z, int scan) -{ - int m; - z->jfif = 0; - z->app14_color_transform = -1; // valid values are 0,1,2 - z->marker = STBI__MARKER_none; // initialize cached marker to empty - m = stbi__get_marker(z); - if (!stbi__SOI(m)) return stbi__err("no SOI","Corrupt JPEG"); - if (scan == STBI__SCAN_type) return 1; - m = stbi__get_marker(z); - while (!stbi__SOF(m)) { - if (!stbi__process_marker(z,m)) return 0; - m = stbi__get_marker(z); - while (m == STBI__MARKER_none) { - // some files have extra padding after their blocks, so ok, we'll scan - if (stbi__at_eof(z->s)) return stbi__err("no SOF", "Corrupt JPEG"); - m = stbi__get_marker(z); - } - } - z->progressive = stbi__SOF_progressive(m); - if (!stbi__process_frame_header(z, scan)) return 0; - return 1; -} - -static stbi_uc stbi__skip_jpeg_junk_at_end(stbi__jpeg *j) -{ - // some JPEGs have junk at end, skip over it but if we find what looks - // like a valid marker, resume there - while (!stbi__at_eof(j->s)) { - stbi_uc x = stbi__get8(j->s); - while (x == 0xff) { // might be a marker - if (stbi__at_eof(j->s)) return STBI__MARKER_none; - x = stbi__get8(j->s); - if (x != 0x00 && x != 0xff) { - // not a stuffed zero or lead-in to another marker, looks - // like an actual marker, return it - return x; - } - // stuffed zero has x=0 now which ends the loop, meaning we go - // back to regular scan loop. - // repeated 0xff keeps trying to read the next byte of the marker. - } - } - return STBI__MARKER_none; -} - -// decode image to YCbCr format -static int stbi__decode_jpeg_image(stbi__jpeg *j) -{ - int m; - for (m = 0; m < 4; m++) { - j->img_comp[m].raw_data = NULL; - j->img_comp[m].raw_coeff = NULL; - } - j->restart_interval = 0; - if (!stbi__decode_jpeg_header(j, STBI__SCAN_load)) return 0; - m = stbi__get_marker(j); - while (!stbi__EOI(m)) { - if (stbi__SOS(m)) { - if (!stbi__process_scan_header(j)) return 0; - if (!stbi__parse_entropy_coded_data(j)) return 0; - if (j->marker == STBI__MARKER_none ) { - j->marker = stbi__skip_jpeg_junk_at_end(j); - // if we reach eof without hitting a marker, stbi__get_marker() below will fail and we'll eventually return 0 - } - m = stbi__get_marker(j); - if (STBI__RESTART(m)) - m = stbi__get_marker(j); - } else if (stbi__DNL(m)) { - int Ld = stbi__get16be(j->s); - stbi__uint32 NL = stbi__get16be(j->s); - if (Ld != 4) return stbi__err("bad DNL len", "Corrupt JPEG"); - if (NL != j->s->img_y) return stbi__err("bad DNL height", "Corrupt JPEG"); - m = stbi__get_marker(j); - } else { - if (!stbi__process_marker(j, m)) return 1; - m = stbi__get_marker(j); - } - } - if (j->progressive) - stbi__jpeg_finish(j); - return 1; -} - -// static jfif-centered resampling (across block boundaries) - -typedef stbi_uc *(*resample_row_func)(stbi_uc *out, stbi_uc *in0, stbi_uc *in1, - int w, int hs); - -#define stbi__div4(x) ((stbi_uc) ((x) >> 2)) - -static stbi_uc *resample_row_1(stbi_uc *out, stbi_uc *in_near, stbi_uc *in_far, int w, int hs) -{ - STBI_NOTUSED(out); - STBI_NOTUSED(in_far); - STBI_NOTUSED(w); - STBI_NOTUSED(hs); - return in_near; -} - -static stbi_uc* stbi__resample_row_v_2(stbi_uc *out, stbi_uc *in_near, stbi_uc *in_far, int w, int hs) -{ - // need to generate two samples vertically for every one in input - int i; - STBI_NOTUSED(hs); - for (i=0; i < w; ++i) - out[i] = stbi__div4(3*in_near[i] + in_far[i] + 2); - return out; -} - -static stbi_uc* stbi__resample_row_h_2(stbi_uc *out, stbi_uc *in_near, stbi_uc *in_far, int w, int hs) -{ - // need to generate two samples horizontally for every one in input - int i; - stbi_uc *input = in_near; - - if (w == 1) { - // if only one sample, can't do any interpolation - out[0] = out[1] = input[0]; - return out; - } - - out[0] = input[0]; - out[1] = stbi__div4(input[0]*3 + input[1] + 2); - for (i=1; i < w-1; ++i) { - int n = 3*input[i]+2; - out[i*2+0] = stbi__div4(n+input[i-1]); - out[i*2+1] = stbi__div4(n+input[i+1]); - } - out[i*2+0] = stbi__div4(input[w-2]*3 + input[w-1] + 2); - out[i*2+1] = input[w-1]; - - STBI_NOTUSED(in_far); - STBI_NOTUSED(hs); - - return out; -} - -#define stbi__div16(x) ((stbi_uc) ((x) >> 4)) - -static stbi_uc *stbi__resample_row_hv_2(stbi_uc *out, stbi_uc *in_near, stbi_uc *in_far, int w, int hs) -{ - // need to generate 2x2 samples for every one in input - int i,t0,t1; - if (w == 1) { - out[0] = out[1] = stbi__div4(3*in_near[0] + in_far[0] + 2); - return out; - } - - t1 = 3*in_near[0] + in_far[0]; - out[0] = stbi__div4(t1+2); - for (i=1; i < w; ++i) { - t0 = t1; - t1 = 3*in_near[i]+in_far[i]; - out[i*2-1] = stbi__div16(3*t0 + t1 + 8); - out[i*2 ] = stbi__div16(3*t1 + t0 + 8); - } - out[w*2-1] = stbi__div4(t1+2); - - STBI_NOTUSED(hs); - - return out; -} - -#if defined(STBI_SSE2) || defined(STBI_NEON) -static stbi_uc *stbi__resample_row_hv_2_simd(stbi_uc *out, stbi_uc *in_near, stbi_uc *in_far, int w, int hs) -{ - // need to generate 2x2 samples for every one in input - int i=0,t0,t1; - - if (w == 1) { - out[0] = out[1] = stbi__div4(3*in_near[0] + in_far[0] + 2); - return out; - } - - t1 = 3*in_near[0] + in_far[0]; - // process groups of 8 pixels for as long as we can. - // note we can't handle the last pixel in a row in this loop - // because we need to handle the filter boundary conditions. - for (; i < ((w-1) & ~7); i += 8) { -#if defined(STBI_SSE2) - // load and perform the vertical filtering pass - // this uses 3*x + y = 4*x + (y - x) - __m128i zero = _mm_setzero_si128(); - __m128i farb = _mm_loadl_epi64((__m128i *) (in_far + i)); - __m128i nearb = _mm_loadl_epi64((__m128i *) (in_near + i)); - __m128i farw = _mm_unpacklo_epi8(farb, zero); - __m128i nearw = _mm_unpacklo_epi8(nearb, zero); - __m128i diff = _mm_sub_epi16(farw, nearw); - __m128i nears = _mm_slli_epi16(nearw, 2); - __m128i curr = _mm_add_epi16(nears, diff); // current row - - // horizontal filter works the same based on shifted vers of current - // row. "prev" is current row shifted right by 1 pixel; we need to - // insert the previous pixel value (from t1). - // "next" is current row shifted left by 1 pixel, with first pixel - // of next block of 8 pixels added in. - __m128i prv0 = _mm_slli_si128(curr, 2); - __m128i nxt0 = _mm_srli_si128(curr, 2); - __m128i prev = _mm_insert_epi16(prv0, t1, 0); - __m128i next = _mm_insert_epi16(nxt0, 3*in_near[i+8] + in_far[i+8], 7); - - // horizontal filter, polyphase implementation since it's convenient: - // even pixels = 3*cur + prev = cur*4 + (prev - cur) - // odd pixels = 3*cur + next = cur*4 + (next - cur) - // note the shared term. - __m128i bias = _mm_set1_epi16(8); - __m128i curs = _mm_slli_epi16(curr, 2); - __m128i prvd = _mm_sub_epi16(prev, curr); - __m128i nxtd = _mm_sub_epi16(next, curr); - __m128i curb = _mm_add_epi16(curs, bias); - __m128i even = _mm_add_epi16(prvd, curb); - __m128i odd = _mm_add_epi16(nxtd, curb); - - // interleave even and odd pixels, then undo scaling. - __m128i int0 = _mm_unpacklo_epi16(even, odd); - __m128i int1 = _mm_unpackhi_epi16(even, odd); - __m128i de0 = _mm_srli_epi16(int0, 4); - __m128i de1 = _mm_srli_epi16(int1, 4); - - // pack and write output - __m128i outv = _mm_packus_epi16(de0, de1); - _mm_storeu_si128((__m128i *) (out + i*2), outv); -#elif defined(STBI_NEON) - // load and perform the vertical filtering pass - // this uses 3*x + y = 4*x + (y - x) - uint8x8_t farb = vld1_u8(in_far + i); - uint8x8_t nearb = vld1_u8(in_near + i); - int16x8_t diff = vreinterpretq_s16_u16(vsubl_u8(farb, nearb)); - int16x8_t nears = vreinterpretq_s16_u16(vshll_n_u8(nearb, 2)); - int16x8_t curr = vaddq_s16(nears, diff); // current row - - // horizontal filter works the same based on shifted vers of current - // row. "prev" is current row shifted right by 1 pixel; we need to - // insert the previous pixel value (from t1). - // "next" is current row shifted left by 1 pixel, with first pixel - // of next block of 8 pixels added in. - int16x8_t prv0 = vextq_s16(curr, curr, 7); - int16x8_t nxt0 = vextq_s16(curr, curr, 1); - int16x8_t prev = vsetq_lane_s16(t1, prv0, 0); - int16x8_t next = vsetq_lane_s16(3*in_near[i+8] + in_far[i+8], nxt0, 7); - - // horizontal filter, polyphase implementation since it's convenient: - // even pixels = 3*cur + prev = cur*4 + (prev - cur) - // odd pixels = 3*cur + next = cur*4 + (next - cur) - // note the shared term. - int16x8_t curs = vshlq_n_s16(curr, 2); - int16x8_t prvd = vsubq_s16(prev, curr); - int16x8_t nxtd = vsubq_s16(next, curr); - int16x8_t even = vaddq_s16(curs, prvd); - int16x8_t odd = vaddq_s16(curs, nxtd); - - // undo scaling and round, then store with even/odd phases interleaved - uint8x8x2_t o; - o.val[0] = vqrshrun_n_s16(even, 4); - o.val[1] = vqrshrun_n_s16(odd, 4); - vst2_u8(out + i*2, o); -#endif - - // "previous" value for next iter - t1 = 3*in_near[i+7] + in_far[i+7]; - } - - t0 = t1; - t1 = 3*in_near[i] + in_far[i]; - out[i*2] = stbi__div16(3*t1 + t0 + 8); - - for (++i; i < w; ++i) { - t0 = t1; - t1 = 3*in_near[i]+in_far[i]; - out[i*2-1] = stbi__div16(3*t0 + t1 + 8); - out[i*2 ] = stbi__div16(3*t1 + t0 + 8); - } - out[w*2-1] = stbi__div4(t1+2); - - STBI_NOTUSED(hs); - - return out; -} -#endif - -static stbi_uc *stbi__resample_row_generic(stbi_uc *out, stbi_uc *in_near, stbi_uc *in_far, int w, int hs) -{ - // resample with nearest-neighbor - int i,j; - STBI_NOTUSED(in_far); - for (i=0; i < w; ++i) - for (j=0; j < hs; ++j) - out[i*hs+j] = in_near[i]; - return out; -} - -// this is a reduced-precision calculation of YCbCr-to-RGB introduced -// to make sure the code produces the same results in both SIMD and scalar -#define stbi__float2fixed(x) (((int) ((x) * 4096.0f + 0.5f)) << 8) -static void stbi__YCbCr_to_RGB_row(stbi_uc *out, const stbi_uc *y, const stbi_uc *pcb, const stbi_uc *pcr, int count, int step) -{ - int i; - for (i=0; i < count; ++i) { - int y_fixed = (y[i] << 20) + (1<<19); // rounding - int r,g,b; - int cr = pcr[i] - 128; - int cb = pcb[i] - 128; - r = y_fixed + cr* stbi__float2fixed(1.40200f); - g = y_fixed + (cr*-stbi__float2fixed(0.71414f)) + ((cb*-stbi__float2fixed(0.34414f)) & 0xffff0000); - b = y_fixed + cb* stbi__float2fixed(1.77200f); - r >>= 20; - g >>= 20; - b >>= 20; - if ((unsigned) r > 255) { if (r < 0) r = 0; else r = 255; } - if ((unsigned) g > 255) { if (g < 0) g = 0; else g = 255; } - if ((unsigned) b > 255) { if (b < 0) b = 0; else b = 255; } - out[0] = (stbi_uc)r; - out[1] = (stbi_uc)g; - out[2] = (stbi_uc)b; - out[3] = 255; - out += step; - } -} - -#if defined(STBI_SSE2) || defined(STBI_NEON) -static void stbi__YCbCr_to_RGB_simd(stbi_uc *out, stbi_uc const *y, stbi_uc const *pcb, stbi_uc const *pcr, int count, int step) -{ - int i = 0; - -#ifdef STBI_SSE2 - // step == 3 is pretty ugly on the final interleave, and i'm not convinced - // it's useful in practice (you wouldn't use it for textures, for example). - // so just accelerate step == 4 case. - if (step == 4) { - // this is a fairly straightforward implementation and not super-optimized. - __m128i signflip = _mm_set1_epi8(-0x80); - __m128i cr_const0 = _mm_set1_epi16( (short) ( 1.40200f*4096.0f+0.5f)); - __m128i cr_const1 = _mm_set1_epi16( - (short) ( 0.71414f*4096.0f+0.5f)); - __m128i cb_const0 = _mm_set1_epi16( - (short) ( 0.34414f*4096.0f+0.5f)); - __m128i cb_const1 = _mm_set1_epi16( (short) ( 1.77200f*4096.0f+0.5f)); - __m128i y_bias = _mm_set1_epi8((char) (unsigned char) 128); - __m128i xw = _mm_set1_epi16(255); // alpha channel - - for (; i+7 < count; i += 8) { - // load - __m128i y_bytes = _mm_loadl_epi64((__m128i *) (y+i)); - __m128i cr_bytes = _mm_loadl_epi64((__m128i *) (pcr+i)); - __m128i cb_bytes = _mm_loadl_epi64((__m128i *) (pcb+i)); - __m128i cr_biased = _mm_xor_si128(cr_bytes, signflip); // -128 - __m128i cb_biased = _mm_xor_si128(cb_bytes, signflip); // -128 - - // unpack to short (and left-shift cr, cb by 8) - __m128i yw = _mm_unpacklo_epi8(y_bias, y_bytes); - __m128i crw = _mm_unpacklo_epi8(_mm_setzero_si128(), cr_biased); - __m128i cbw = _mm_unpacklo_epi8(_mm_setzero_si128(), cb_biased); - - // color transform - __m128i yws = _mm_srli_epi16(yw, 4); - __m128i cr0 = _mm_mulhi_epi16(cr_const0, crw); - __m128i cb0 = _mm_mulhi_epi16(cb_const0, cbw); - __m128i cb1 = _mm_mulhi_epi16(cbw, cb_const1); - __m128i cr1 = _mm_mulhi_epi16(crw, cr_const1); - __m128i rws = _mm_add_epi16(cr0, yws); - __m128i gwt = _mm_add_epi16(cb0, yws); - __m128i bws = _mm_add_epi16(yws, cb1); - __m128i gws = _mm_add_epi16(gwt, cr1); - - // descale - __m128i rw = _mm_srai_epi16(rws, 4); - __m128i bw = _mm_srai_epi16(bws, 4); - __m128i gw = _mm_srai_epi16(gws, 4); - - // back to byte, set up for transpose - __m128i brb = _mm_packus_epi16(rw, bw); - __m128i gxb = _mm_packus_epi16(gw, xw); - - // transpose to interleave channels - __m128i t0 = _mm_unpacklo_epi8(brb, gxb); - __m128i t1 = _mm_unpackhi_epi8(brb, gxb); - __m128i o0 = _mm_unpacklo_epi16(t0, t1); - __m128i o1 = _mm_unpackhi_epi16(t0, t1); - - // store - _mm_storeu_si128((__m128i *) (out + 0), o0); - _mm_storeu_si128((__m128i *) (out + 16), o1); - out += 32; - } - } -#endif - -#ifdef STBI_NEON - // in this version, step=3 support would be easy to add. but is there demand? - if (step == 4) { - // this is a fairly straightforward implementation and not super-optimized. - uint8x8_t signflip = vdup_n_u8(0x80); - int16x8_t cr_const0 = vdupq_n_s16( (short) ( 1.40200f*4096.0f+0.5f)); - int16x8_t cr_const1 = vdupq_n_s16( - (short) ( 0.71414f*4096.0f+0.5f)); - int16x8_t cb_const0 = vdupq_n_s16( - (short) ( 0.34414f*4096.0f+0.5f)); - int16x8_t cb_const1 = vdupq_n_s16( (short) ( 1.77200f*4096.0f+0.5f)); - - for (; i+7 < count; i += 8) { - // load - uint8x8_t y_bytes = vld1_u8(y + i); - uint8x8_t cr_bytes = vld1_u8(pcr + i); - uint8x8_t cb_bytes = vld1_u8(pcb + i); - int8x8_t cr_biased = vreinterpret_s8_u8(vsub_u8(cr_bytes, signflip)); - int8x8_t cb_biased = vreinterpret_s8_u8(vsub_u8(cb_bytes, signflip)); - - // expand to s16 - int16x8_t yws = vreinterpretq_s16_u16(vshll_n_u8(y_bytes, 4)); - int16x8_t crw = vshll_n_s8(cr_biased, 7); - int16x8_t cbw = vshll_n_s8(cb_biased, 7); - - // color transform - int16x8_t cr0 = vqdmulhq_s16(crw, cr_const0); - int16x8_t cb0 = vqdmulhq_s16(cbw, cb_const0); - int16x8_t cr1 = vqdmulhq_s16(crw, cr_const1); - int16x8_t cb1 = vqdmulhq_s16(cbw, cb_const1); - int16x8_t rws = vaddq_s16(yws, cr0); - int16x8_t gws = vaddq_s16(vaddq_s16(yws, cb0), cr1); - int16x8_t bws = vaddq_s16(yws, cb1); - - // undo scaling, round, convert to byte - uint8x8x4_t o; - o.val[0] = vqrshrun_n_s16(rws, 4); - o.val[1] = vqrshrun_n_s16(gws, 4); - o.val[2] = vqrshrun_n_s16(bws, 4); - o.val[3] = vdup_n_u8(255); - - // store, interleaving r/g/b/a - vst4_u8(out, o); - out += 8*4; - } - } -#endif - - for (; i < count; ++i) { - int y_fixed = (y[i] << 20) + (1<<19); // rounding - int r,g,b; - int cr = pcr[i] - 128; - int cb = pcb[i] - 128; - r = y_fixed + cr* stbi__float2fixed(1.40200f); - g = y_fixed + cr*-stbi__float2fixed(0.71414f) + ((cb*-stbi__float2fixed(0.34414f)) & 0xffff0000); - b = y_fixed + cb* stbi__float2fixed(1.77200f); - r >>= 20; - g >>= 20; - b >>= 20; - if ((unsigned) r > 255) { if (r < 0) r = 0; else r = 255; } - if ((unsigned) g > 255) { if (g < 0) g = 0; else g = 255; } - if ((unsigned) b > 255) { if (b < 0) b = 0; else b = 255; } - out[0] = (stbi_uc)r; - out[1] = (stbi_uc)g; - out[2] = (stbi_uc)b; - out[3] = 255; - out += step; - } -} -#endif - -// set up the kernels -static void stbi__setup_jpeg(stbi__jpeg *j) -{ - j->idct_block_kernel = stbi__idct_block; - j->YCbCr_to_RGB_kernel = stbi__YCbCr_to_RGB_row; - j->resample_row_hv_2_kernel = stbi__resample_row_hv_2; - -#ifdef STBI_SSE2 - if (stbi__sse2_available()) { - j->idct_block_kernel = stbi__idct_simd; - j->YCbCr_to_RGB_kernel = stbi__YCbCr_to_RGB_simd; - j->resample_row_hv_2_kernel = stbi__resample_row_hv_2_simd; - } -#endif - -#ifdef STBI_NEON - j->idct_block_kernel = stbi__idct_simd; - j->YCbCr_to_RGB_kernel = stbi__YCbCr_to_RGB_simd; - j->resample_row_hv_2_kernel = stbi__resample_row_hv_2_simd; -#endif -} - -// clean up the temporary component buffers -static void stbi__cleanup_jpeg(stbi__jpeg *j) -{ - stbi__free_jpeg_components(j, j->s->img_n, 0); -} - -typedef struct -{ - resample_row_func resample; - stbi_uc *line0,*line1; - int hs,vs; // expansion factor in each axis - int w_lores; // horizontal pixels pre-expansion - int ystep; // how far through vertical expansion we are - int ypos; // which pre-expansion row we're on -} stbi__resample; - -// fast 0..255 * 0..255 => 0..255 rounded multiplication -static stbi_uc stbi__blinn_8x8(stbi_uc x, stbi_uc y) -{ - unsigned int t = x*y + 128; - return (stbi_uc) ((t + (t >>8)) >> 8); -} - -static stbi_uc *load_jpeg_image(stbi__jpeg *z, int *out_x, int *out_y, int *comp, int req_comp) -{ - int n, decode_n, is_rgb; - z->s->img_n = 0; // make stbi__cleanup_jpeg safe - - // validate req_comp - if (req_comp < 0 || req_comp > 4) return stbi__errpuc("bad req_comp", "Internal error"); - - // load a jpeg image from whichever source, but leave in YCbCr format - if (!stbi__decode_jpeg_image(z)) { stbi__cleanup_jpeg(z); return NULL; } - - // determine actual number of components to generate - n = req_comp ? req_comp : z->s->img_n >= 3 ? 3 : 1; - - is_rgb = z->s->img_n == 3 && (z->rgb == 3 || (z->app14_color_transform == 0 && !z->jfif)); - - if (z->s->img_n == 3 && n < 3 && !is_rgb) - decode_n = 1; - else - decode_n = z->s->img_n; - - // nothing to do if no components requested; check this now to avoid - // accessing uninitialized coutput[0] later - if (decode_n <= 0) { stbi__cleanup_jpeg(z); return NULL; } - - // resample and color-convert - { - int k; - unsigned int i,j; - stbi_uc *output; - stbi_uc *coutput[4] = { NULL, NULL, NULL, NULL }; - - stbi__resample res_comp[4]; - - for (k=0; k < decode_n; ++k) { - stbi__resample *r = &res_comp[k]; - - // allocate line buffer big enough for upsampling off the edges - // with upsample factor of 4 - z->img_comp[k].linebuf = (stbi_uc *) stbi__malloc(z->s->img_x + 3); - if (!z->img_comp[k].linebuf) { stbi__cleanup_jpeg(z); return stbi__errpuc("outofmem", "Out of memory"); } - - r->hs = z->img_h_max / z->img_comp[k].h; - r->vs = z->img_v_max / z->img_comp[k].v; - r->ystep = r->vs >> 1; - r->w_lores = (z->s->img_x + r->hs-1) / r->hs; - r->ypos = 0; - r->line0 = r->line1 = z->img_comp[k].data; - - if (r->hs == 1 && r->vs == 1) r->resample = resample_row_1; - else if (r->hs == 1 && r->vs == 2) r->resample = stbi__resample_row_v_2; - else if (r->hs == 2 && r->vs == 1) r->resample = stbi__resample_row_h_2; - else if (r->hs == 2 && r->vs == 2) r->resample = z->resample_row_hv_2_kernel; - else r->resample = stbi__resample_row_generic; - } - - // can't error after this so, this is safe - output = (stbi_uc *) stbi__malloc_mad3(n, z->s->img_x, z->s->img_y, 1); - if (!output) { stbi__cleanup_jpeg(z); return stbi__errpuc("outofmem", "Out of memory"); } - - // now go ahead and resample - for (j=0; j < z->s->img_y; ++j) { - stbi_uc *out = output + n * z->s->img_x * j; - for (k=0; k < decode_n; ++k) { - stbi__resample *r = &res_comp[k]; - int y_bot = r->ystep >= (r->vs >> 1); - coutput[k] = r->resample(z->img_comp[k].linebuf, - y_bot ? r->line1 : r->line0, - y_bot ? r->line0 : r->line1, - r->w_lores, r->hs); - if (++r->ystep >= r->vs) { - r->ystep = 0; - r->line0 = r->line1; - if (++r->ypos < z->img_comp[k].y) - r->line1 += z->img_comp[k].w2; - } - } - if (n >= 3) { - stbi_uc *y = coutput[0]; - if (z->s->img_n == 3) { - if (is_rgb) { - for (i=0; i < z->s->img_x; ++i) { - out[0] = y[i]; - out[1] = coutput[1][i]; - out[2] = coutput[2][i]; - out[3] = 255; - out += n; - } - } else { - z->YCbCr_to_RGB_kernel(out, y, coutput[1], coutput[2], z->s->img_x, n); - } - } else if (z->s->img_n == 4) { - if (z->app14_color_transform == 0) { // CMYK - for (i=0; i < z->s->img_x; ++i) { - stbi_uc m = coutput[3][i]; - out[0] = stbi__blinn_8x8(coutput[0][i], m); - out[1] = stbi__blinn_8x8(coutput[1][i], m); - out[2] = stbi__blinn_8x8(coutput[2][i], m); - out[3] = 255; - out += n; - } - } else if (z->app14_color_transform == 2) { // YCCK - z->YCbCr_to_RGB_kernel(out, y, coutput[1], coutput[2], z->s->img_x, n); - for (i=0; i < z->s->img_x; ++i) { - stbi_uc m = coutput[3][i]; - out[0] = stbi__blinn_8x8(255 - out[0], m); - out[1] = stbi__blinn_8x8(255 - out[1], m); - out[2] = stbi__blinn_8x8(255 - out[2], m); - out += n; - } - } else { // YCbCr + alpha? Ignore the fourth channel for now - z->YCbCr_to_RGB_kernel(out, y, coutput[1], coutput[2], z->s->img_x, n); - } - } else - for (i=0; i < z->s->img_x; ++i) { - out[0] = out[1] = out[2] = y[i]; - out[3] = 255; // not used if n==3 - out += n; - } - } else { - if (is_rgb) { - if (n == 1) - for (i=0; i < z->s->img_x; ++i) - *out++ = stbi__compute_y(coutput[0][i], coutput[1][i], coutput[2][i]); - else { - for (i=0; i < z->s->img_x; ++i, out += 2) { - out[0] = stbi__compute_y(coutput[0][i], coutput[1][i], coutput[2][i]); - out[1] = 255; - } - } - } else if (z->s->img_n == 4 && z->app14_color_transform == 0) { - for (i=0; i < z->s->img_x; ++i) { - stbi_uc m = coutput[3][i]; - stbi_uc r = stbi__blinn_8x8(coutput[0][i], m); - stbi_uc g = stbi__blinn_8x8(coutput[1][i], m); - stbi_uc b = stbi__blinn_8x8(coutput[2][i], m); - out[0] = stbi__compute_y(r, g, b); - out[1] = 255; - out += n; - } - } else if (z->s->img_n == 4 && z->app14_color_transform == 2) { - for (i=0; i < z->s->img_x; ++i) { - out[0] = stbi__blinn_8x8(255 - coutput[0][i], coutput[3][i]); - out[1] = 255; - out += n; - } - } else { - stbi_uc *y = coutput[0]; - if (n == 1) - for (i=0; i < z->s->img_x; ++i) out[i] = y[i]; - else - for (i=0; i < z->s->img_x; ++i) { *out++ = y[i]; *out++ = 255; } - } - } - } - stbi__cleanup_jpeg(z); - *out_x = z->s->img_x; - *out_y = z->s->img_y; - if (comp) *comp = z->s->img_n >= 3 ? 3 : 1; // report original components, not output - return output; - } -} - -static void *stbi__jpeg_load(stbi__context *s, int *x, int *y, int *comp, int req_comp, stbi__result_info *ri) -{ - unsigned char* result; - stbi__jpeg* j = (stbi__jpeg*) stbi__malloc(sizeof(stbi__jpeg)); - if (!j) return stbi__errpuc("outofmem", "Out of memory"); - memset(j, 0, sizeof(stbi__jpeg)); - STBI_NOTUSED(ri); - j->s = s; - stbi__setup_jpeg(j); - result = load_jpeg_image(j, x,y,comp,req_comp); - STBI_FREE(j); - return result; -} - -static int stbi__jpeg_test(stbi__context *s) -{ - int r; - stbi__jpeg* j = (stbi__jpeg*)stbi__malloc(sizeof(stbi__jpeg)); - if (!j) return stbi__err("outofmem", "Out of memory"); - memset(j, 0, sizeof(stbi__jpeg)); - j->s = s; - stbi__setup_jpeg(j); - r = stbi__decode_jpeg_header(j, STBI__SCAN_type); - stbi__rewind(s); - STBI_FREE(j); - return r; -} - -static int stbi__jpeg_info_raw(stbi__jpeg *j, int *x, int *y, int *comp) -{ - if (!stbi__decode_jpeg_header(j, STBI__SCAN_header)) { - stbi__rewind( j->s ); - return 0; - } - if (x) *x = j->s->img_x; - if (y) *y = j->s->img_y; - if (comp) *comp = j->s->img_n >= 3 ? 3 : 1; - return 1; -} - -static int stbi__jpeg_info(stbi__context *s, int *x, int *y, int *comp) -{ - int result; - stbi__jpeg* j = (stbi__jpeg*) (stbi__malloc(sizeof(stbi__jpeg))); - if (!j) return stbi__err("outofmem", "Out of memory"); - memset(j, 0, sizeof(stbi__jpeg)); - j->s = s; - result = stbi__jpeg_info_raw(j, x, y, comp); - STBI_FREE(j); - return result; -} -#endif - -// public domain zlib decode v0.2 Sean Barrett 2006-11-18 -// simple implementation -// - all input must be provided in an upfront buffer -// - all output is written to a single output buffer (can malloc/realloc) -// performance -// - fast huffman - -#ifndef STBI_NO_ZLIB - -// fast-way is faster to check than jpeg huffman, but slow way is slower -#define STBI__ZFAST_BITS 9 // accelerate all cases in default tables -#define STBI__ZFAST_MASK ((1 << STBI__ZFAST_BITS) - 1) -#define STBI__ZNSYMS 288 // number of symbols in literal/length alphabet - -// zlib-style huffman encoding -// (jpegs packs from left, zlib from right, so can't share code) -typedef struct -{ - stbi__uint16 fast[1 << STBI__ZFAST_BITS]; - stbi__uint16 firstcode[16]; - int maxcode[17]; - stbi__uint16 firstsymbol[16]; - stbi_uc size[STBI__ZNSYMS]; - stbi__uint16 value[STBI__ZNSYMS]; -} stbi__zhuffman; - -stbi_inline static int stbi__bitreverse16(int n) -{ - n = ((n & 0xAAAA) >> 1) | ((n & 0x5555) << 1); - n = ((n & 0xCCCC) >> 2) | ((n & 0x3333) << 2); - n = ((n & 0xF0F0) >> 4) | ((n & 0x0F0F) << 4); - n = ((n & 0xFF00) >> 8) | ((n & 0x00FF) << 8); - return n; -} - -stbi_inline static int stbi__bit_reverse(int v, int bits) -{ - STBI_ASSERT(bits <= 16); - // to bit reverse n bits, reverse 16 and shift - // e.g. 11 bits, bit reverse and shift away 5 - return stbi__bitreverse16(v) >> (16-bits); -} - -static int stbi__zbuild_huffman(stbi__zhuffman *z, const stbi_uc *sizelist, int num) -{ - int i,k=0; - int code, next_code[16], sizes[17]; - - // DEFLATE spec for generating codes - memset(sizes, 0, sizeof(sizes)); - memset(z->fast, 0, sizeof(z->fast)); - for (i=0; i < num; ++i) - ++sizes[sizelist[i]]; - sizes[0] = 0; - for (i=1; i < 16; ++i) - if (sizes[i] > (1 << i)) - return stbi__err("bad sizes", "Corrupt PNG"); - code = 0; - for (i=1; i < 16; ++i) { - next_code[i] = code; - z->firstcode[i] = (stbi__uint16) code; - z->firstsymbol[i] = (stbi__uint16) k; - code = (code + sizes[i]); - if (sizes[i]) - if (code-1 >= (1 << i)) return stbi__err("bad codelengths","Corrupt PNG"); - z->maxcode[i] = code << (16-i); // preshift for inner loop - code <<= 1; - k += sizes[i]; - } - z->maxcode[16] = 0x10000; // sentinel - for (i=0; i < num; ++i) { - int s = sizelist[i]; - if (s) { - int c = next_code[s] - z->firstcode[s] + z->firstsymbol[s]; - stbi__uint16 fastv = (stbi__uint16) ((s << 9) | i); - z->size [c] = (stbi_uc ) s; - z->value[c] = (stbi__uint16) i; - if (s <= STBI__ZFAST_BITS) { - int j = stbi__bit_reverse(next_code[s],s); - while (j < (1 << STBI__ZFAST_BITS)) { - z->fast[j] = fastv; - j += (1 << s); - } - } - ++next_code[s]; - } - } - return 1; -} - -// zlib-from-memory implementation for PNG reading -// because PNG allows splitting the zlib stream arbitrarily, -// and it's annoying structurally to have PNG call ZLIB call PNG, -// we require PNG read all the IDATs and combine them into a single -// memory buffer - -typedef struct -{ - stbi_uc *zbuffer, *zbuffer_end; - int num_bits; - int hit_zeof_once; - stbi__uint32 code_buffer; - - char *zout; - char *zout_start; - char *zout_end; - int z_expandable; - - stbi__zhuffman z_length, z_distance; -} stbi__zbuf; - -stbi_inline static int stbi__zeof(stbi__zbuf *z) -{ - return (z->zbuffer >= z->zbuffer_end); -} - -stbi_inline static stbi_uc stbi__zget8(stbi__zbuf *z) -{ - return stbi__zeof(z) ? 0 : *z->zbuffer++; -} - -static void stbi__fill_bits(stbi__zbuf *z) -{ - do { - if (z->code_buffer >= (1U << z->num_bits)) { - z->zbuffer = z->zbuffer_end; /* treat this as EOF so we fail. */ - return; - } - z->code_buffer |= (unsigned int) stbi__zget8(z) << z->num_bits; - z->num_bits += 8; - } while (z->num_bits <= 24); -} - -stbi_inline static unsigned int stbi__zreceive(stbi__zbuf *z, int n) -{ - unsigned int k; - if (z->num_bits < n) stbi__fill_bits(z); - k = z->code_buffer & ((1 << n) - 1); - z->code_buffer >>= n; - z->num_bits -= n; - return k; -} - -static int stbi__zhuffman_decode_slowpath(stbi__zbuf *a, stbi__zhuffman *z) -{ - int b,s,k; - // not resolved by fast table, so compute it the slow way - // use jpeg approach, which requires MSbits at top - k = stbi__bit_reverse(a->code_buffer, 16); - for (s=STBI__ZFAST_BITS+1; ; ++s) - if (k < z->maxcode[s]) - break; - if (s >= 16) return -1; // invalid code! - // code size is s, so: - b = (k >> (16-s)) - z->firstcode[s] + z->firstsymbol[s]; - if (b >= STBI__ZNSYMS) return -1; // some data was corrupt somewhere! - if (z->size[b] != s) return -1; // was originally an assert, but report failure instead. - a->code_buffer >>= s; - a->num_bits -= s; - return z->value[b]; -} - -stbi_inline static int stbi__zhuffman_decode(stbi__zbuf *a, stbi__zhuffman *z) -{ - int b,s; - if (a->num_bits < 16) { - if (stbi__zeof(a)) { - if (!a->hit_zeof_once) { - // This is the first time we hit eof, insert 16 extra padding btis - // to allow us to keep going; if we actually consume any of them - // though, that is invalid data. This is caught later. - a->hit_zeof_once = 1; - a->num_bits += 16; // add 16 implicit zero bits - } else { - // We already inserted our extra 16 padding bits and are again - // out, this stream is actually prematurely terminated. - return -1; - } - } else { - stbi__fill_bits(a); - } - } - b = z->fast[a->code_buffer & STBI__ZFAST_MASK]; - if (b) { - s = b >> 9; - a->code_buffer >>= s; - a->num_bits -= s; - return b & 511; - } - return stbi__zhuffman_decode_slowpath(a, z); -} - -static int stbi__zexpand(stbi__zbuf *z, char *zout, int n) // need to make room for n bytes -{ - char *q; - unsigned int cur, limit, old_limit; - z->zout = zout; - if (!z->z_expandable) return stbi__err("output buffer limit","Corrupt PNG"); - cur = (unsigned int) (z->zout - z->zout_start); - limit = old_limit = (unsigned) (z->zout_end - z->zout_start); - if (UINT_MAX - cur < (unsigned) n) return stbi__err("outofmem", "Out of memory"); - while (cur + n > limit) { - if(limit > UINT_MAX / 2) return stbi__err("outofmem", "Out of memory"); - limit *= 2; - } - q = (char *) STBI_REALLOC_SIZED(z->zout_start, old_limit, limit); - STBI_NOTUSED(old_limit); - if (q == NULL) return stbi__err("outofmem", "Out of memory"); - z->zout_start = q; - z->zout = q + cur; - z->zout_end = q + limit; - return 1; -} - -static const int stbi__zlength_base[31] = { - 3,4,5,6,7,8,9,10,11,13, - 15,17,19,23,27,31,35,43,51,59, - 67,83,99,115,131,163,195,227,258,0,0 }; - -static const int stbi__zlength_extra[31]= -{ 0,0,0,0,0,0,0,0,1,1,1,1,2,2,2,2,3,3,3,3,4,4,4,4,5,5,5,5,0,0,0 }; - -static const int stbi__zdist_base[32] = { 1,2,3,4,5,7,9,13,17,25,33,49,65,97,129,193, -257,385,513,769,1025,1537,2049,3073,4097,6145,8193,12289,16385,24577,0,0}; - -static const int stbi__zdist_extra[32] = -{ 0,0,0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7,8,8,9,9,10,10,11,11,12,12,13,13}; - -static int stbi__parse_huffman_block(stbi__zbuf *a) -{ - char *zout = a->zout; - for(;;) { - int z = stbi__zhuffman_decode(a, &a->z_length); - if (z < 256) { - if (z < 0) return stbi__err("bad huffman code","Corrupt PNG"); // error in huffman codes - if (zout >= a->zout_end) { - if (!stbi__zexpand(a, zout, 1)) return 0; - zout = a->zout; - } - *zout++ = (char) z; - } else { - stbi_uc *p; - int len,dist; - if (z == 256) { - a->zout = zout; - if (a->hit_zeof_once && a->num_bits < 16) { - // The first time we hit zeof, we inserted 16 extra zero bits into our bit - // buffer so the decoder can just do its speculative decoding. But if we - // actually consumed any of those bits (which is the case when num_bits < 16), - // the stream actually read past the end so it is malformed. - return stbi__err("unexpected end","Corrupt PNG"); - } - return 1; - } - if (z >= 286) return stbi__err("bad huffman code","Corrupt PNG"); // per DEFLATE, length codes 286 and 287 must not appear in compressed data - z -= 257; - len = stbi__zlength_base[z]; - if (stbi__zlength_extra[z]) len += stbi__zreceive(a, stbi__zlength_extra[z]); - z = stbi__zhuffman_decode(a, &a->z_distance); - if (z < 0 || z >= 30) return stbi__err("bad huffman code","Corrupt PNG"); // per DEFLATE, distance codes 30 and 31 must not appear in compressed data - dist = stbi__zdist_base[z]; - if (stbi__zdist_extra[z]) dist += stbi__zreceive(a, stbi__zdist_extra[z]); - if (zout - a->zout_start < dist) return stbi__err("bad dist","Corrupt PNG"); - if (len > a->zout_end - zout) { - if (!stbi__zexpand(a, zout, len)) return 0; - zout = a->zout; - } - p = (stbi_uc *) (zout - dist); - if (dist == 1) { // run of one byte; common in images. - stbi_uc v = *p; - if (len) { do *zout++ = v; while (--len); } - } else { - if (len) { do *zout++ = *p++; while (--len); } - } - } - } -} - -static int stbi__compute_huffman_codes(stbi__zbuf *a) -{ - static const stbi_uc length_dezigzag[19] = { 16,17,18,0,8,7,9,6,10,5,11,4,12,3,13,2,14,1,15 }; - stbi__zhuffman z_codelength; - stbi_uc lencodes[286+32+137];//padding for maximum single op - stbi_uc codelength_sizes[19]; - int i,n; - - int hlit = stbi__zreceive(a,5) + 257; - int hdist = stbi__zreceive(a,5) + 1; - int hclen = stbi__zreceive(a,4) + 4; - int ntot = hlit + hdist; - - memset(codelength_sizes, 0, sizeof(codelength_sizes)); - for (i=0; i < hclen; ++i) { - int s = stbi__zreceive(a,3); - codelength_sizes[length_dezigzag[i]] = (stbi_uc) s; - } - if (!stbi__zbuild_huffman(&z_codelength, codelength_sizes, 19)) return 0; - - n = 0; - while (n < ntot) { - int c = stbi__zhuffman_decode(a, &z_codelength); - if (c < 0 || c >= 19) return stbi__err("bad codelengths", "Corrupt PNG"); - if (c < 16) - lencodes[n++] = (stbi_uc) c; - else { - stbi_uc fill = 0; - if (c == 16) { - c = stbi__zreceive(a,2)+3; - if (n == 0) return stbi__err("bad codelengths", "Corrupt PNG"); - fill = lencodes[n-1]; - } else if (c == 17) { - c = stbi__zreceive(a,3)+3; - } else if (c == 18) { - c = stbi__zreceive(a,7)+11; - } else { - return stbi__err("bad codelengths", "Corrupt PNG"); - } - if (ntot - n < c) return stbi__err("bad codelengths", "Corrupt PNG"); - memset(lencodes+n, fill, c); - n += c; - } - } - if (n != ntot) return stbi__err("bad codelengths","Corrupt PNG"); - if (!stbi__zbuild_huffman(&a->z_length, lencodes, hlit)) return 0; - if (!stbi__zbuild_huffman(&a->z_distance, lencodes+hlit, hdist)) return 0; - return 1; -} - -static int stbi__parse_uncompressed_block(stbi__zbuf *a) -{ - stbi_uc header[4]; - int len,nlen,k; - if (a->num_bits & 7) - stbi__zreceive(a, a->num_bits & 7); // discard - // drain the bit-packed data into header - k = 0; - while (a->num_bits > 0) { - header[k++] = (stbi_uc) (a->code_buffer & 255); // suppress MSVC run-time check - a->code_buffer >>= 8; - a->num_bits -= 8; - } - if (a->num_bits < 0) return stbi__err("zlib corrupt","Corrupt PNG"); - // now fill header the normal way - while (k < 4) - header[k++] = stbi__zget8(a); - len = header[1] * 256 + header[0]; - nlen = header[3] * 256 + header[2]; - if (nlen != (len ^ 0xffff)) return stbi__err("zlib corrupt","Corrupt PNG"); - if (a->zbuffer + len > a->zbuffer_end) return stbi__err("read past buffer","Corrupt PNG"); - if (a->zout + len > a->zout_end) - if (!stbi__zexpand(a, a->zout, len)) return 0; - memcpy(a->zout, a->zbuffer, len); - a->zbuffer += len; - a->zout += len; - return 1; -} - -static int stbi__parse_zlib_header(stbi__zbuf *a) -{ - int cmf = stbi__zget8(a); - int cm = cmf & 15; - /* int cinfo = cmf >> 4; */ - int flg = stbi__zget8(a); - if (stbi__zeof(a)) return stbi__err("bad zlib header","Corrupt PNG"); // zlib spec - if ((cmf*256+flg) % 31 != 0) return stbi__err("bad zlib header","Corrupt PNG"); // zlib spec - if (flg & 32) return stbi__err("no preset dict","Corrupt PNG"); // preset dictionary not allowed in png - if (cm != 8) return stbi__err("bad compression","Corrupt PNG"); // DEFLATE required for png - // window = 1 << (8 + cinfo)... but who cares, we fully buffer output - return 1; -} - -static const stbi_uc stbi__zdefault_length[STBI__ZNSYMS] = -{ - 8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8, 8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8, - 8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8, 8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8, - 8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8, 8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8, - 8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8, 8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8, - 8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8, 9,9,9,9,9,9,9,9,9,9,9,9,9,9,9,9, - 9,9,9,9,9,9,9,9,9,9,9,9,9,9,9,9, 9,9,9,9,9,9,9,9,9,9,9,9,9,9,9,9, - 9,9,9,9,9,9,9,9,9,9,9,9,9,9,9,9, 9,9,9,9,9,9,9,9,9,9,9,9,9,9,9,9, - 9,9,9,9,9,9,9,9,9,9,9,9,9,9,9,9, 9,9,9,9,9,9,9,9,9,9,9,9,9,9,9,9, - 7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7, 7,7,7,7,7,7,7,7,8,8,8,8,8,8,8,8 -}; -static const stbi_uc stbi__zdefault_distance[32] = -{ - 5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5 -}; -/* -Init algorithm: -{ - int i; // use <= to match clearly with spec - for (i=0; i <= 143; ++i) stbi__zdefault_length[i] = 8; - for ( ; i <= 255; ++i) stbi__zdefault_length[i] = 9; - for ( ; i <= 279; ++i) stbi__zdefault_length[i] = 7; - for ( ; i <= 287; ++i) stbi__zdefault_length[i] = 8; - - for (i=0; i <= 31; ++i) stbi__zdefault_distance[i] = 5; -} -*/ - -static int stbi__parse_zlib(stbi__zbuf *a, int parse_header) -{ - int final, type; - if (parse_header) - if (!stbi__parse_zlib_header(a)) return 0; - a->num_bits = 0; - a->code_buffer = 0; - a->hit_zeof_once = 0; - do { - final = stbi__zreceive(a,1); - type = stbi__zreceive(a,2); - if (type == 0) { - if (!stbi__parse_uncompressed_block(a)) return 0; - } else if (type == 3) { - return 0; - } else { - if (type == 1) { - // use fixed code lengths - if (!stbi__zbuild_huffman(&a->z_length , stbi__zdefault_length , STBI__ZNSYMS)) return 0; - if (!stbi__zbuild_huffman(&a->z_distance, stbi__zdefault_distance, 32)) return 0; - } else { - if (!stbi__compute_huffman_codes(a)) return 0; - } - if (!stbi__parse_huffman_block(a)) return 0; - } - } while (!final); - return 1; -} - -static int stbi__do_zlib(stbi__zbuf *a, char *obuf, int olen, int exp, int parse_header) -{ - a->zout_start = obuf; - a->zout = obuf; - a->zout_end = obuf + olen; - a->z_expandable = exp; - - return stbi__parse_zlib(a, parse_header); -} - -STBIDEF char *stbi_zlib_decode_malloc_guesssize(const char *buffer, int len, int initial_size, int *outlen) -{ - stbi__zbuf a; - char *p = (char *) stbi__malloc(initial_size); - if (p == NULL) return NULL; - a.zbuffer = (stbi_uc *) buffer; - a.zbuffer_end = (stbi_uc *) buffer + len; - if (stbi__do_zlib(&a, p, initial_size, 1, 1)) { - if (outlen) *outlen = (int) (a.zout - a.zout_start); - return a.zout_start; - } else { - STBI_FREE(a.zout_start); - return NULL; - } -} - -STBIDEF char *stbi_zlib_decode_malloc(char const *buffer, int len, int *outlen) -{ - return stbi_zlib_decode_malloc_guesssize(buffer, len, 16384, outlen); -} - -STBIDEF char *stbi_zlib_decode_malloc_guesssize_headerflag(const char *buffer, int len, int initial_size, int *outlen, int parse_header) -{ - stbi__zbuf a; - char *p = (char *) stbi__malloc(initial_size); - if (p == NULL) return NULL; - a.zbuffer = (stbi_uc *) buffer; - a.zbuffer_end = (stbi_uc *) buffer + len; - if (stbi__do_zlib(&a, p, initial_size, 1, parse_header)) { - if (outlen) *outlen = (int) (a.zout - a.zout_start); - return a.zout_start; - } else { - STBI_FREE(a.zout_start); - return NULL; - } -} - -STBIDEF int stbi_zlib_decode_buffer(char *obuffer, int olen, char const *ibuffer, int ilen) -{ - stbi__zbuf a; - a.zbuffer = (stbi_uc *) ibuffer; - a.zbuffer_end = (stbi_uc *) ibuffer + ilen; - if (stbi__do_zlib(&a, obuffer, olen, 0, 1)) - return (int) (a.zout - a.zout_start); - else - return -1; -} - -STBIDEF char *stbi_zlib_decode_noheader_malloc(char const *buffer, int len, int *outlen) -{ - stbi__zbuf a; - char *p = (char *) stbi__malloc(16384); - if (p == NULL) return NULL; - a.zbuffer = (stbi_uc *) buffer; - a.zbuffer_end = (stbi_uc *) buffer+len; - if (stbi__do_zlib(&a, p, 16384, 1, 0)) { - if (outlen) *outlen = (int) (a.zout - a.zout_start); - return a.zout_start; - } else { - STBI_FREE(a.zout_start); - return NULL; - } -} - -STBIDEF int stbi_zlib_decode_noheader_buffer(char *obuffer, int olen, const char *ibuffer, int ilen) -{ - stbi__zbuf a; - a.zbuffer = (stbi_uc *) ibuffer; - a.zbuffer_end = (stbi_uc *) ibuffer + ilen; - if (stbi__do_zlib(&a, obuffer, olen, 0, 0)) - return (int) (a.zout - a.zout_start); - else - return -1; -} -#endif - -// public domain "baseline" PNG decoder v0.10 Sean Barrett 2006-11-18 -// simple implementation -// - only 8-bit samples -// - no CRC checking -// - allocates lots of intermediate memory -// - avoids problem of streaming data between subsystems -// - avoids explicit window management -// performance -// - uses stb_zlib, a PD zlib implementation with fast huffman decoding - -#ifndef STBI_NO_PNG -typedef struct -{ - stbi__uint32 length; - stbi__uint32 type; -} stbi__pngchunk; - -static stbi__pngchunk stbi__get_chunk_header(stbi__context *s) -{ - stbi__pngchunk c; - c.length = stbi__get32be(s); - c.type = stbi__get32be(s); - return c; -} - -static int stbi__check_png_header(stbi__context *s) -{ - static const stbi_uc png_sig[8] = { 137,80,78,71,13,10,26,10 }; - int i; - for (i=0; i < 8; ++i) - if (stbi__get8(s) != png_sig[i]) return stbi__err("bad png sig","Not a PNG"); - return 1; -} - -typedef struct -{ - stbi__context *s; - stbi_uc *idata, *expanded, *out; - int depth; -} stbi__png; - - -enum { - STBI__F_none=0, - STBI__F_sub=1, - STBI__F_up=2, - STBI__F_avg=3, - STBI__F_paeth=4, - // synthetic filter used for first scanline to avoid needing a dummy row of 0s - STBI__F_avg_first -}; - -static stbi_uc first_row_filter[5] = -{ - STBI__F_none, - STBI__F_sub, - STBI__F_none, - STBI__F_avg_first, - STBI__F_sub // Paeth with b=c=0 turns out to be equivalent to sub -}; - -static int stbi__paeth(int a, int b, int c) -{ - // This formulation looks very different from the reference in the PNG spec, but is - // actually equivalent and has favorable data dependencies and admits straightforward - // generation of branch-free code, which helps performance significantly. - int thresh = c*3 - (a + b); - int lo = a < b ? a : b; - int hi = a < b ? b : a; - int t0 = (hi <= thresh) ? lo : c; - int t1 = (thresh <= lo) ? hi : t0; - return t1; -} - -static const stbi_uc stbi__depth_scale_table[9] = { 0, 0xff, 0x55, 0, 0x11, 0,0,0, 0x01 }; - -// adds an extra all-255 alpha channel -// dest == src is legal -// img_n must be 1 or 3 -static void stbi__create_png_alpha_expand8(stbi_uc *dest, stbi_uc *src, stbi__uint32 x, int img_n) -{ - int i; - // must process data backwards since we allow dest==src - if (img_n == 1) { - for (i=x-1; i >= 0; --i) { - dest[i*2+1] = 255; - dest[i*2+0] = src[i]; - } - } else { - STBI_ASSERT(img_n == 3); - for (i=x-1; i >= 0; --i) { - dest[i*4+3] = 255; - dest[i*4+2] = src[i*3+2]; - dest[i*4+1] = src[i*3+1]; - dest[i*4+0] = src[i*3+0]; - } - } -} - -// create the png data from post-deflated data -static int stbi__create_png_image_raw(stbi__png *a, stbi_uc *raw, stbi__uint32 raw_len, int out_n, stbi__uint32 x, stbi__uint32 y, int depth, int color) -{ - int bytes = (depth == 16 ? 2 : 1); - stbi__context *s = a->s; - stbi__uint32 i,j,stride = x*out_n*bytes; - stbi__uint32 img_len, img_width_bytes; - stbi_uc *filter_buf; - int all_ok = 1; - int k; - int img_n = s->img_n; // copy it into a local for later - - int output_bytes = out_n*bytes; - int filter_bytes = img_n*bytes; - int width = x; - - STBI_ASSERT(out_n == s->img_n || out_n == s->img_n+1); - a->out = (stbi_uc *) stbi__malloc_mad3(x, y, output_bytes, 0); // extra bytes to write off the end into - if (!a->out) return stbi__err("outofmem", "Out of memory"); - - // note: error exits here don't need to clean up a->out individually, - // stbi__do_png always does on error. - if (!stbi__mad3sizes_valid(img_n, x, depth, 7)) return stbi__err("too large", "Corrupt PNG"); - img_width_bytes = (((img_n * x * depth) + 7) >> 3); - if (!stbi__mad2sizes_valid(img_width_bytes, y, img_width_bytes)) return stbi__err("too large", "Corrupt PNG"); - img_len = (img_width_bytes + 1) * y; - - // we used to check for exact match between raw_len and img_len on non-interlaced PNGs, - // but issue #276 reported a PNG in the wild that had extra data at the end (all zeros), - // so just check for raw_len < img_len always. - if (raw_len < img_len) return stbi__err("not enough pixels","Corrupt PNG"); - - // Allocate two scan lines worth of filter workspace buffer. - filter_buf = (stbi_uc *) stbi__malloc_mad2(img_width_bytes, 2, 0); - if (!filter_buf) return stbi__err("outofmem", "Out of memory"); - - // Filtering for low-bit-depth images - if (depth < 8) { - filter_bytes = 1; - width = img_width_bytes; - } - - for (j=0; j < y; ++j) { - // cur/prior filter buffers alternate - stbi_uc *cur = filter_buf + (j & 1)*img_width_bytes; - stbi_uc *prior = filter_buf + (~j & 1)*img_width_bytes; - stbi_uc *dest = a->out + stride*j; - int nk = width * filter_bytes; - int filter = *raw++; - - // check filter type - if (filter > 4) { - all_ok = stbi__err("invalid filter","Corrupt PNG"); - break; - } - - // if first row, use special filter that doesn't sample previous row - if (j == 0) filter = first_row_filter[filter]; - - // perform actual filtering - switch (filter) { - case STBI__F_none: - memcpy(cur, raw, nk); - break; - case STBI__F_sub: - memcpy(cur, raw, filter_bytes); - for (k = filter_bytes; k < nk; ++k) - cur[k] = STBI__BYTECAST(raw[k] + cur[k-filter_bytes]); - break; - case STBI__F_up: - for (k = 0; k < nk; ++k) - cur[k] = STBI__BYTECAST(raw[k] + prior[k]); - break; - case STBI__F_avg: - for (k = 0; k < filter_bytes; ++k) - cur[k] = STBI__BYTECAST(raw[k] + (prior[k]>>1)); - for (k = filter_bytes; k < nk; ++k) - cur[k] = STBI__BYTECAST(raw[k] + ((prior[k] + cur[k-filter_bytes])>>1)); - break; - case STBI__F_paeth: - for (k = 0; k < filter_bytes; ++k) - cur[k] = STBI__BYTECAST(raw[k] + prior[k]); // prior[k] == stbi__paeth(0,prior[k],0) - for (k = filter_bytes; k < nk; ++k) - cur[k] = STBI__BYTECAST(raw[k] + stbi__paeth(cur[k-filter_bytes], prior[k], prior[k-filter_bytes])); - break; - case STBI__F_avg_first: - memcpy(cur, raw, filter_bytes); - for (k = filter_bytes; k < nk; ++k) - cur[k] = STBI__BYTECAST(raw[k] + (cur[k-filter_bytes] >> 1)); - break; - } - - raw += nk; - - // expand decoded bits in cur to dest, also adding an extra alpha channel if desired - if (depth < 8) { - stbi_uc scale = (color == 0) ? stbi__depth_scale_table[depth] : 1; // scale grayscale values to 0..255 range - stbi_uc *in = cur; - stbi_uc *out = dest; - stbi_uc inb = 0; - stbi__uint32 nsmp = x*img_n; - - // expand bits to bytes first - if (depth == 4) { - for (i=0; i < nsmp; ++i) { - if ((i & 1) == 0) inb = *in++; - *out++ = scale * (inb >> 4); - inb <<= 4; - } - } else if (depth == 2) { - for (i=0; i < nsmp; ++i) { - if ((i & 3) == 0) inb = *in++; - *out++ = scale * (inb >> 6); - inb <<= 2; - } - } else { - STBI_ASSERT(depth == 1); - for (i=0; i < nsmp; ++i) { - if ((i & 7) == 0) inb = *in++; - *out++ = scale * (inb >> 7); - inb <<= 1; - } - } - - // insert alpha=255 values if desired - if (img_n != out_n) - stbi__create_png_alpha_expand8(dest, dest, x, img_n); - } else if (depth == 8) { - if (img_n == out_n) - memcpy(dest, cur, x*img_n); - else - stbi__create_png_alpha_expand8(dest, cur, x, img_n); - } else if (depth == 16) { - // convert the image data from big-endian to platform-native - stbi__uint16 *dest16 = (stbi__uint16*)dest; - stbi__uint32 nsmp = x*img_n; - - if (img_n == out_n) { - for (i = 0; i < nsmp; ++i, ++dest16, cur += 2) - *dest16 = (cur[0] << 8) | cur[1]; - } else { - STBI_ASSERT(img_n+1 == out_n); - if (img_n == 1) { - for (i = 0; i < x; ++i, dest16 += 2, cur += 2) { - dest16[0] = (cur[0] << 8) | cur[1]; - dest16[1] = 0xffff; - } - } else { - STBI_ASSERT(img_n == 3); - for (i = 0; i < x; ++i, dest16 += 4, cur += 6) { - dest16[0] = (cur[0] << 8) | cur[1]; - dest16[1] = (cur[2] << 8) | cur[3]; - dest16[2] = (cur[4] << 8) | cur[5]; - dest16[3] = 0xffff; - } - } - } - } - } - - STBI_FREE(filter_buf); - if (!all_ok) return 0; - - return 1; -} - -static int stbi__create_png_image(stbi__png *a, stbi_uc *image_data, stbi__uint32 image_data_len, int out_n, int depth, int color, int interlaced) -{ - int bytes = (depth == 16 ? 2 : 1); - int out_bytes = out_n * bytes; - stbi_uc *final; - int p; - if (!interlaced) - return stbi__create_png_image_raw(a, image_data, image_data_len, out_n, a->s->img_x, a->s->img_y, depth, color); - - // de-interlacing - final = (stbi_uc *) stbi__malloc_mad3(a->s->img_x, a->s->img_y, out_bytes, 0); - if (!final) return stbi__err("outofmem", "Out of memory"); - for (p=0; p < 7; ++p) { - int xorig[] = { 0,4,0,2,0,1,0 }; - int yorig[] = { 0,0,4,0,2,0,1 }; - int xspc[] = { 8,8,4,4,2,2,1 }; - int yspc[] = { 8,8,8,4,4,2,2 }; - int i,j,x,y; - // pass1_x[4] = 0, pass1_x[5] = 1, pass1_x[12] = 1 - x = (a->s->img_x - xorig[p] + xspc[p]-1) / xspc[p]; - y = (a->s->img_y - yorig[p] + yspc[p]-1) / yspc[p]; - if (x && y) { - stbi__uint32 img_len = ((((a->s->img_n * x * depth) + 7) >> 3) + 1) * y; - if (!stbi__create_png_image_raw(a, image_data, image_data_len, out_n, x, y, depth, color)) { - STBI_FREE(final); - return 0; - } - for (j=0; j < y; ++j) { - for (i=0; i < x; ++i) { - int out_y = j*yspc[p]+yorig[p]; - int out_x = i*xspc[p]+xorig[p]; - memcpy(final + out_y*a->s->img_x*out_bytes + out_x*out_bytes, - a->out + (j*x+i)*out_bytes, out_bytes); - } - } - STBI_FREE(a->out); - image_data += img_len; - image_data_len -= img_len; - } - } - a->out = final; - - return 1; -} - -static int stbi__compute_transparency(stbi__png *z, stbi_uc tc[3], int out_n) -{ - stbi__context *s = z->s; - stbi__uint32 i, pixel_count = s->img_x * s->img_y; - stbi_uc *p = z->out; - - // compute color-based transparency, assuming we've - // already got 255 as the alpha value in the output - STBI_ASSERT(out_n == 2 || out_n == 4); - - if (out_n == 2) { - for (i=0; i < pixel_count; ++i) { - p[1] = (p[0] == tc[0] ? 0 : 255); - p += 2; - } - } else { - for (i=0; i < pixel_count; ++i) { - if (p[0] == tc[0] && p[1] == tc[1] && p[2] == tc[2]) - p[3] = 0; - p += 4; - } - } - return 1; -} - -static int stbi__compute_transparency16(stbi__png *z, stbi__uint16 tc[3], int out_n) -{ - stbi__context *s = z->s; - stbi__uint32 i, pixel_count = s->img_x * s->img_y; - stbi__uint16 *p = (stbi__uint16*) z->out; - - // compute color-based transparency, assuming we've - // already got 65535 as the alpha value in the output - STBI_ASSERT(out_n == 2 || out_n == 4); - - if (out_n == 2) { - for (i = 0; i < pixel_count; ++i) { - p[1] = (p[0] == tc[0] ? 0 : 65535); - p += 2; - } - } else { - for (i = 0; i < pixel_count; ++i) { - if (p[0] == tc[0] && p[1] == tc[1] && p[2] == tc[2]) - p[3] = 0; - p += 4; - } - } - return 1; -} - -static int stbi__expand_png_palette(stbi__png *a, stbi_uc *palette, int len, int pal_img_n) -{ - stbi__uint32 i, pixel_count = a->s->img_x * a->s->img_y; - stbi_uc *p, *temp_out, *orig = a->out; - - p = (stbi_uc *) stbi__malloc_mad2(pixel_count, pal_img_n, 0); - if (p == NULL) return stbi__err("outofmem", "Out of memory"); - - // between here and free(out) below, exitting would leak - temp_out = p; - - if (pal_img_n == 3) { - for (i=0; i < pixel_count; ++i) { - int n = orig[i]*4; - p[0] = palette[n ]; - p[1] = palette[n+1]; - p[2] = palette[n+2]; - p += 3; - } - } else { - for (i=0; i < pixel_count; ++i) { - int n = orig[i]*4; - p[0] = palette[n ]; - p[1] = palette[n+1]; - p[2] = palette[n+2]; - p[3] = palette[n+3]; - p += 4; - } - } - STBI_FREE(a->out); - a->out = temp_out; - - STBI_NOTUSED(len); - - return 1; -} - -static int stbi__unpremultiply_on_load_global = 0; -static int stbi__de_iphone_flag_global = 0; - -STBIDEF void stbi_set_unpremultiply_on_load(int flag_true_if_should_unpremultiply) -{ - stbi__unpremultiply_on_load_global = flag_true_if_should_unpremultiply; -} - -STBIDEF void stbi_convert_iphone_png_to_rgb(int flag_true_if_should_convert) -{ - stbi__de_iphone_flag_global = flag_true_if_should_convert; -} - -#ifndef STBI_THREAD_LOCAL -#define stbi__unpremultiply_on_load stbi__unpremultiply_on_load_global -#define stbi__de_iphone_flag stbi__de_iphone_flag_global -#else -static STBI_THREAD_LOCAL int stbi__unpremultiply_on_load_local, stbi__unpremultiply_on_load_set; -static STBI_THREAD_LOCAL int stbi__de_iphone_flag_local, stbi__de_iphone_flag_set; - -STBIDEF void stbi_set_unpremultiply_on_load_thread(int flag_true_if_should_unpremultiply) -{ - stbi__unpremultiply_on_load_local = flag_true_if_should_unpremultiply; - stbi__unpremultiply_on_load_set = 1; -} - -STBIDEF void stbi_convert_iphone_png_to_rgb_thread(int flag_true_if_should_convert) -{ - stbi__de_iphone_flag_local = flag_true_if_should_convert; - stbi__de_iphone_flag_set = 1; -} - -#define stbi__unpremultiply_on_load (stbi__unpremultiply_on_load_set \ - ? stbi__unpremultiply_on_load_local \ - : stbi__unpremultiply_on_load_global) -#define stbi__de_iphone_flag (stbi__de_iphone_flag_set \ - ? stbi__de_iphone_flag_local \ - : stbi__de_iphone_flag_global) -#endif // STBI_THREAD_LOCAL - -static void stbi__de_iphone(stbi__png *z) -{ - stbi__context *s = z->s; - stbi__uint32 i, pixel_count = s->img_x * s->img_y; - stbi_uc *p = z->out; - - if (s->img_out_n == 3) { // convert bgr to rgb - for (i=0; i < pixel_count; ++i) { - stbi_uc t = p[0]; - p[0] = p[2]; - p[2] = t; - p += 3; - } - } else { - STBI_ASSERT(s->img_out_n == 4); - if (stbi__unpremultiply_on_load) { - // convert bgr to rgb and unpremultiply - for (i=0; i < pixel_count; ++i) { - stbi_uc a = p[3]; - stbi_uc t = p[0]; - if (a) { - stbi_uc half = a / 2; - p[0] = (p[2] * 255 + half) / a; - p[1] = (p[1] * 255 + half) / a; - p[2] = ( t * 255 + half) / a; - } else { - p[0] = p[2]; - p[2] = t; - } - p += 4; - } - } else { - // convert bgr to rgb - for (i=0; i < pixel_count; ++i) { - stbi_uc t = p[0]; - p[0] = p[2]; - p[2] = t; - p += 4; - } - } - } -} - -#define STBI__PNG_TYPE(a,b,c,d) (((unsigned) (a) << 24) + ((unsigned) (b) << 16) + ((unsigned) (c) << 8) + (unsigned) (d)) - -static int stbi__parse_png_file(stbi__png *z, int scan, int req_comp) -{ - stbi_uc palette[1024], pal_img_n=0; - stbi_uc has_trans=0, tc[3]={0}; - stbi__uint16 tc16[3]; - stbi__uint32 ioff=0, idata_limit=0, i, pal_len=0; - int first=1,k,interlace=0, color=0, is_iphone=0; - stbi__context *s = z->s; - - z->expanded = NULL; - z->idata = NULL; - z->out = NULL; - - if (!stbi__check_png_header(s)) return 0; - - if (scan == STBI__SCAN_type) return 1; - - for (;;) { - stbi__pngchunk c = stbi__get_chunk_header(s); - switch (c.type) { - case STBI__PNG_TYPE('C','g','B','I'): - is_iphone = 1; - stbi__skip(s, c.length); - break; - case STBI__PNG_TYPE('I','H','D','R'): { - int comp,filter; - if (!first) return stbi__err("multiple IHDR","Corrupt PNG"); - first = 0; - if (c.length != 13) return stbi__err("bad IHDR len","Corrupt PNG"); - s->img_x = stbi__get32be(s); - s->img_y = stbi__get32be(s); - if (s->img_y > STBI_MAX_DIMENSIONS) return stbi__err("too large","Very large image (corrupt?)"); - if (s->img_x > STBI_MAX_DIMENSIONS) return stbi__err("too large","Very large image (corrupt?)"); - z->depth = stbi__get8(s); if (z->depth != 1 && z->depth != 2 && z->depth != 4 && z->depth != 8 && z->depth != 16) return stbi__err("1/2/4/8/16-bit only","PNG not supported: 1/2/4/8/16-bit only"); - color = stbi__get8(s); if (color > 6) return stbi__err("bad ctype","Corrupt PNG"); - if (color == 3 && z->depth == 16) return stbi__err("bad ctype","Corrupt PNG"); - if (color == 3) pal_img_n = 3; else if (color & 1) return stbi__err("bad ctype","Corrupt PNG"); - comp = stbi__get8(s); if (comp) return stbi__err("bad comp method","Corrupt PNG"); - filter= stbi__get8(s); if (filter) return stbi__err("bad filter method","Corrupt PNG"); - interlace = stbi__get8(s); if (interlace>1) return stbi__err("bad interlace method","Corrupt PNG"); - if (!s->img_x || !s->img_y) return stbi__err("0-pixel image","Corrupt PNG"); - if (!pal_img_n) { - s->img_n = (color & 2 ? 3 : 1) + (color & 4 ? 1 : 0); - if ((1 << 30) / s->img_x / s->img_n < s->img_y) return stbi__err("too large", "Image too large to decode"); - } else { - // if paletted, then pal_n is our final components, and - // img_n is # components to decompress/filter. - s->img_n = 1; - if ((1 << 30) / s->img_x / 4 < s->img_y) return stbi__err("too large","Corrupt PNG"); - } - // even with SCAN_header, have to scan to see if we have a tRNS - break; - } - - case STBI__PNG_TYPE('P','L','T','E'): { - if (first) return stbi__err("first not IHDR", "Corrupt PNG"); - if (c.length > 256*3) return stbi__err("invalid PLTE","Corrupt PNG"); - pal_len = c.length / 3; - if (pal_len * 3 != c.length) return stbi__err("invalid PLTE","Corrupt PNG"); - for (i=0; i < pal_len; ++i) { - palette[i*4+0] = stbi__get8(s); - palette[i*4+1] = stbi__get8(s); - palette[i*4+2] = stbi__get8(s); - palette[i*4+3] = 255; - } - break; - } - - case STBI__PNG_TYPE('t','R','N','S'): { - if (first) return stbi__err("first not IHDR", "Corrupt PNG"); - if (z->idata) return stbi__err("tRNS after IDAT","Corrupt PNG"); - if (pal_img_n) { - if (scan == STBI__SCAN_header) { s->img_n = 4; return 1; } - if (pal_len == 0) return stbi__err("tRNS before PLTE","Corrupt PNG"); - if (c.length > pal_len) return stbi__err("bad tRNS len","Corrupt PNG"); - pal_img_n = 4; - for (i=0; i < c.length; ++i) - palette[i*4+3] = stbi__get8(s); - } else { - if (!(s->img_n & 1)) return stbi__err("tRNS with alpha","Corrupt PNG"); - if (c.length != (stbi__uint32) s->img_n*2) return stbi__err("bad tRNS len","Corrupt PNG"); - has_trans = 1; - // non-paletted with tRNS = constant alpha. if header-scanning, we can stop now. - if (scan == STBI__SCAN_header) { ++s->img_n; return 1; } - if (z->depth == 16) { - for (k = 0; k < s->img_n && k < 3; ++k) // extra loop test to suppress false GCC warning - tc16[k] = (stbi__uint16)stbi__get16be(s); // copy the values as-is - } else { - for (k = 0; k < s->img_n && k < 3; ++k) - tc[k] = (stbi_uc)(stbi__get16be(s) & 255) * stbi__depth_scale_table[z->depth]; // non 8-bit images will be larger - } - } - break; - } - - case STBI__PNG_TYPE('I','D','A','T'): { - if (first) return stbi__err("first not IHDR", "Corrupt PNG"); - if (pal_img_n && !pal_len) return stbi__err("no PLTE","Corrupt PNG"); - if (scan == STBI__SCAN_header) { - // header scan definitely stops at first IDAT - if (pal_img_n) - s->img_n = pal_img_n; - return 1; - } - if (c.length > (1u << 30)) return stbi__err("IDAT size limit", "IDAT section larger than 2^30 bytes"); - if ((int)(ioff + c.length) < (int)ioff) return 0; - if (ioff + c.length > idata_limit) { - stbi__uint32 idata_limit_old = idata_limit; - stbi_uc *p; - if (idata_limit == 0) idata_limit = c.length > 4096 ? c.length : 4096; - while (ioff + c.length > idata_limit) - idata_limit *= 2; - STBI_NOTUSED(idata_limit_old); - p = (stbi_uc *) STBI_REALLOC_SIZED(z->idata, idata_limit_old, idata_limit); if (p == NULL) return stbi__err("outofmem", "Out of memory"); - z->idata = p; - } - if (!stbi__getn(s, z->idata+ioff,c.length)) return stbi__err("outofdata","Corrupt PNG"); - ioff += c.length; - break; - } - - case STBI__PNG_TYPE('I','E','N','D'): { - stbi__uint32 raw_len, bpl; - if (first) return stbi__err("first not IHDR", "Corrupt PNG"); - if (scan != STBI__SCAN_load) return 1; - if (z->idata == NULL) return stbi__err("no IDAT","Corrupt PNG"); - // initial guess for decoded data size to avoid unnecessary reallocs - bpl = (s->img_x * z->depth + 7) / 8; // bytes per line, per component - raw_len = bpl * s->img_y * s->img_n /* pixels */ + s->img_y /* filter mode per row */; - z->expanded = (stbi_uc *) stbi_zlib_decode_malloc_guesssize_headerflag((char *) z->idata, ioff, raw_len, (int *) &raw_len, !is_iphone); - if (z->expanded == NULL) return 0; // zlib should set error - STBI_FREE(z->idata); z->idata = NULL; - if ((req_comp == s->img_n+1 && req_comp != 3 && !pal_img_n) || has_trans) - s->img_out_n = s->img_n+1; - else - s->img_out_n = s->img_n; - if (!stbi__create_png_image(z, z->expanded, raw_len, s->img_out_n, z->depth, color, interlace)) return 0; - if (has_trans) { - if (z->depth == 16) { - if (!stbi__compute_transparency16(z, tc16, s->img_out_n)) return 0; - } else { - if (!stbi__compute_transparency(z, tc, s->img_out_n)) return 0; - } - } - if (is_iphone && stbi__de_iphone_flag && s->img_out_n > 2) - stbi__de_iphone(z); - if (pal_img_n) { - // pal_img_n == 3 or 4 - s->img_n = pal_img_n; // record the actual colors we had - s->img_out_n = pal_img_n; - if (req_comp >= 3) s->img_out_n = req_comp; - if (!stbi__expand_png_palette(z, palette, pal_len, s->img_out_n)) - return 0; - } else if (has_trans) { - // non-paletted image with tRNS -> source image has (constant) alpha - ++s->img_n; - } - STBI_FREE(z->expanded); z->expanded = NULL; - // end of PNG chunk, read and skip CRC - stbi__get32be(s); - return 1; - } - - default: - // if critical, fail - if (first) return stbi__err("first not IHDR", "Corrupt PNG"); - if ((c.type & (1 << 29)) == 0) { - #ifndef STBI_NO_FAILURE_STRINGS - // not threadsafe - static char invalid_chunk[] = "XXXX PNG chunk not known"; - invalid_chunk[0] = STBI__BYTECAST(c.type >> 24); - invalid_chunk[1] = STBI__BYTECAST(c.type >> 16); - invalid_chunk[2] = STBI__BYTECAST(c.type >> 8); - invalid_chunk[3] = STBI__BYTECAST(c.type >> 0); - #endif - return stbi__err(invalid_chunk, "PNG not supported: unknown PNG chunk type"); - } - stbi__skip(s, c.length); - break; - } - // end of PNG chunk, read and skip CRC - stbi__get32be(s); - } -} - -static void *stbi__do_png(stbi__png *p, int *x, int *y, int *n, int req_comp, stbi__result_info *ri) -{ - void *result=NULL; - if (req_comp < 0 || req_comp > 4) return stbi__errpuc("bad req_comp", "Internal error"); - if (stbi__parse_png_file(p, STBI__SCAN_load, req_comp)) { - if (p->depth <= 8) - ri->bits_per_channel = 8; - else if (p->depth == 16) - ri->bits_per_channel = 16; - else - return stbi__errpuc("bad bits_per_channel", "PNG not supported: unsupported color depth"); - result = p->out; - p->out = NULL; - if (req_comp && req_comp != p->s->img_out_n) { - if (ri->bits_per_channel == 8) - result = stbi__convert_format((unsigned char *) result, p->s->img_out_n, req_comp, p->s->img_x, p->s->img_y); - else - result = stbi__convert_format16((stbi__uint16 *) result, p->s->img_out_n, req_comp, p->s->img_x, p->s->img_y); - p->s->img_out_n = req_comp; - if (result == NULL) return result; - } - *x = p->s->img_x; - *y = p->s->img_y; - if (n) *n = p->s->img_n; - } - STBI_FREE(p->out); p->out = NULL; - STBI_FREE(p->expanded); p->expanded = NULL; - STBI_FREE(p->idata); p->idata = NULL; - - return result; -} - -static void *stbi__png_load(stbi__context *s, int *x, int *y, int *comp, int req_comp, stbi__result_info *ri) -{ - stbi__png p; - p.s = s; - return stbi__do_png(&p, x,y,comp,req_comp, ri); -} - -static int stbi__png_test(stbi__context *s) -{ - int r; - r = stbi__check_png_header(s); - stbi__rewind(s); - return r; -} - -static int stbi__png_info_raw(stbi__png *p, int *x, int *y, int *comp) -{ - if (!stbi__parse_png_file(p, STBI__SCAN_header, 0)) { - stbi__rewind( p->s ); - return 0; - } - if (x) *x = p->s->img_x; - if (y) *y = p->s->img_y; - if (comp) *comp = p->s->img_n; - return 1; -} - -static int stbi__png_info(stbi__context *s, int *x, int *y, int *comp) -{ - stbi__png p; - p.s = s; - return stbi__png_info_raw(&p, x, y, comp); -} - -static int stbi__png_is16(stbi__context *s) -{ - stbi__png p; - p.s = s; - if (!stbi__png_info_raw(&p, NULL, NULL, NULL)) - return 0; - if (p.depth != 16) { - stbi__rewind(p.s); - return 0; - } - return 1; -} -#endif - -// Microsoft/Windows BMP image - -#ifndef STBI_NO_BMP -static int stbi__bmp_test_raw(stbi__context *s) -{ - int r; - int sz; - if (stbi__get8(s) != 'B') return 0; - if (stbi__get8(s) != 'M') return 0; - stbi__get32le(s); // discard filesize - stbi__get16le(s); // discard reserved - stbi__get16le(s); // discard reserved - stbi__get32le(s); // discard data offset - sz = stbi__get32le(s); - r = (sz == 12 || sz == 40 || sz == 56 || sz == 108 || sz == 124); - return r; -} - -static int stbi__bmp_test(stbi__context *s) -{ - int r = stbi__bmp_test_raw(s); - stbi__rewind(s); - return r; -} - - -// returns 0..31 for the highest set bit -static int stbi__high_bit(unsigned int z) -{ - int n=0; - if (z == 0) return -1; - if (z >= 0x10000) { n += 16; z >>= 16; } - if (z >= 0x00100) { n += 8; z >>= 8; } - if (z >= 0x00010) { n += 4; z >>= 4; } - if (z >= 0x00004) { n += 2; z >>= 2; } - if (z >= 0x00002) { n += 1;/* >>= 1;*/ } - return n; -} - -static int stbi__bitcount(unsigned int a) -{ - a = (a & 0x55555555) + ((a >> 1) & 0x55555555); // max 2 - a = (a & 0x33333333) + ((a >> 2) & 0x33333333); // max 4 - a = (a + (a >> 4)) & 0x0f0f0f0f; // max 8 per 4, now 8 bits - a = (a + (a >> 8)); // max 16 per 8 bits - a = (a + (a >> 16)); // max 32 per 8 bits - return a & 0xff; -} - -// extract an arbitrarily-aligned N-bit value (N=bits) -// from v, and then make it 8-bits long and fractionally -// extend it to full full range. -static int stbi__shiftsigned(unsigned int v, int shift, int bits) -{ - static unsigned int mul_table[9] = { - 0, - 0xff/*0b11111111*/, 0x55/*0b01010101*/, 0x49/*0b01001001*/, 0x11/*0b00010001*/, - 0x21/*0b00100001*/, 0x41/*0b01000001*/, 0x81/*0b10000001*/, 0x01/*0b00000001*/, - }; - static unsigned int shift_table[9] = { - 0, 0,0,1,0,2,4,6,0, - }; - if (shift < 0) - v <<= -shift; - else - v >>= shift; - STBI_ASSERT(v < 256); - v >>= (8-bits); - STBI_ASSERT(bits >= 0 && bits <= 8); - return (int) ((unsigned) v * mul_table[bits]) >> shift_table[bits]; -} - -typedef struct -{ - int bpp, offset, hsz; - unsigned int mr,mg,mb,ma, all_a; - int extra_read; -} stbi__bmp_data; - -static int stbi__bmp_set_mask_defaults(stbi__bmp_data *info, int compress) -{ - // BI_BITFIELDS specifies masks explicitly, don't override - if (compress == 3) - return 1; - - if (compress == 0) { - if (info->bpp == 16) { - info->mr = 31u << 10; - info->mg = 31u << 5; - info->mb = 31u << 0; - } else if (info->bpp == 32) { - info->mr = 0xffu << 16; - info->mg = 0xffu << 8; - info->mb = 0xffu << 0; - info->ma = 0xffu << 24; - info->all_a = 0; // if all_a is 0 at end, then we loaded alpha channel but it was all 0 - } else { - // otherwise, use defaults, which is all-0 - info->mr = info->mg = info->mb = info->ma = 0; - } - return 1; - } - return 0; // error -} - -static void *stbi__bmp_parse_header(stbi__context *s, stbi__bmp_data *info) -{ - int hsz; - if (stbi__get8(s) != 'B' || stbi__get8(s) != 'M') return stbi__errpuc("not BMP", "Corrupt BMP"); - stbi__get32le(s); // discard filesize - stbi__get16le(s); // discard reserved - stbi__get16le(s); // discard reserved - info->offset = stbi__get32le(s); - info->hsz = hsz = stbi__get32le(s); - info->mr = info->mg = info->mb = info->ma = 0; - info->extra_read = 14; - - if (info->offset < 0) return stbi__errpuc("bad BMP", "bad BMP"); - - if (hsz != 12 && hsz != 40 && hsz != 56 && hsz != 108 && hsz != 124) return stbi__errpuc("unknown BMP", "BMP type not supported: unknown"); - if (hsz == 12) { - s->img_x = stbi__get16le(s); - s->img_y = stbi__get16le(s); - } else { - s->img_x = stbi__get32le(s); - s->img_y = stbi__get32le(s); - } - if (stbi__get16le(s) != 1) return stbi__errpuc("bad BMP", "bad BMP"); - info->bpp = stbi__get16le(s); - if (hsz != 12) { - int compress = stbi__get32le(s); - if (compress == 1 || compress == 2) return stbi__errpuc("BMP RLE", "BMP type not supported: RLE"); - if (compress >= 4) return stbi__errpuc("BMP JPEG/PNG", "BMP type not supported: unsupported compression"); // this includes PNG/JPEG modes - if (compress == 3 && info->bpp != 16 && info->bpp != 32) return stbi__errpuc("bad BMP", "bad BMP"); // bitfields requires 16 or 32 bits/pixel - stbi__get32le(s); // discard sizeof - stbi__get32le(s); // discard hres - stbi__get32le(s); // discard vres - stbi__get32le(s); // discard colorsused - stbi__get32le(s); // discard max important - if (hsz == 40 || hsz == 56) { - if (hsz == 56) { - stbi__get32le(s); - stbi__get32le(s); - stbi__get32le(s); - stbi__get32le(s); - } - if (info->bpp == 16 || info->bpp == 32) { - if (compress == 0) { - stbi__bmp_set_mask_defaults(info, compress); - } else if (compress == 3) { - info->mr = stbi__get32le(s); - info->mg = stbi__get32le(s); - info->mb = stbi__get32le(s); - info->extra_read += 12; - // not documented, but generated by photoshop and handled by mspaint - if (info->mr == info->mg && info->mg == info->mb) { - // ?!?!? - return stbi__errpuc("bad BMP", "bad BMP"); - } - } else - return stbi__errpuc("bad BMP", "bad BMP"); - } - } else { - // V4/V5 header - int i; - if (hsz != 108 && hsz != 124) - return stbi__errpuc("bad BMP", "bad BMP"); - info->mr = stbi__get32le(s); - info->mg = stbi__get32le(s); - info->mb = stbi__get32le(s); - info->ma = stbi__get32le(s); - if (compress != 3) // override mr/mg/mb unless in BI_BITFIELDS mode, as per docs - stbi__bmp_set_mask_defaults(info, compress); - stbi__get32le(s); // discard color space - for (i=0; i < 12; ++i) - stbi__get32le(s); // discard color space parameters - if (hsz == 124) { - stbi__get32le(s); // discard rendering intent - stbi__get32le(s); // discard offset of profile data - stbi__get32le(s); // discard size of profile data - stbi__get32le(s); // discard reserved - } - } - } - return (void *) 1; -} - - -static void *stbi__bmp_load(stbi__context *s, int *x, int *y, int *comp, int req_comp, stbi__result_info *ri) -{ - stbi_uc *out; - unsigned int mr=0,mg=0,mb=0,ma=0, all_a; - stbi_uc pal[256][4]; - int psize=0,i,j,width; - int flip_vertically, pad, target; - stbi__bmp_data info; - STBI_NOTUSED(ri); - - info.all_a = 255; - if (stbi__bmp_parse_header(s, &info) == NULL) - return NULL; // error code already set - - flip_vertically = ((int) s->img_y) > 0; - s->img_y = abs((int) s->img_y); - - if (s->img_y > STBI_MAX_DIMENSIONS) return stbi__errpuc("too large","Very large image (corrupt?)"); - if (s->img_x > STBI_MAX_DIMENSIONS) return stbi__errpuc("too large","Very large image (corrupt?)"); - - mr = info.mr; - mg = info.mg; - mb = info.mb; - ma = info.ma; - all_a = info.all_a; - - if (info.hsz == 12) { - if (info.bpp < 24) - psize = (info.offset - info.extra_read - 24) / 3; - } else { - if (info.bpp < 16) - psize = (info.offset - info.extra_read - info.hsz) >> 2; - } - if (psize == 0) { - // accept some number of extra bytes after the header, but if the offset points either to before - // the header ends or implies a large amount of extra data, reject the file as malformed - int bytes_read_so_far = s->callback_already_read + (int)(s->img_buffer - s->img_buffer_original); - int header_limit = 1024; // max we actually read is below 256 bytes currently. - int extra_data_limit = 256*4; // what ordinarily goes here is a palette; 256 entries*4 bytes is its max size. - if (bytes_read_so_far <= 0 || bytes_read_so_far > header_limit) { - return stbi__errpuc("bad header", "Corrupt BMP"); - } - // we established that bytes_read_so_far is positive and sensible. - // the first half of this test rejects offsets that are either too small positives, or - // negative, and guarantees that info.offset >= bytes_read_so_far > 0. this in turn - // ensures the number computed in the second half of the test can't overflow. - if (info.offset < bytes_read_so_far || info.offset - bytes_read_so_far > extra_data_limit) { - return stbi__errpuc("bad offset", "Corrupt BMP"); - } else { - stbi__skip(s, info.offset - bytes_read_so_far); - } - } - - if (info.bpp == 24 && ma == 0xff000000) - s->img_n = 3; - else - s->img_n = ma ? 4 : 3; - if (req_comp && req_comp >= 3) // we can directly decode 3 or 4 - target = req_comp; - else - target = s->img_n; // if they want monochrome, we'll post-convert - - // sanity-check size - if (!stbi__mad3sizes_valid(target, s->img_x, s->img_y, 0)) - return stbi__errpuc("too large", "Corrupt BMP"); - - out = (stbi_uc *) stbi__malloc_mad3(target, s->img_x, s->img_y, 0); - if (!out) return stbi__errpuc("outofmem", "Out of memory"); - if (info.bpp < 16) { - int z=0; - if (psize == 0 || psize > 256) { STBI_FREE(out); return stbi__errpuc("invalid", "Corrupt BMP"); } - for (i=0; i < psize; ++i) { - pal[i][2] = stbi__get8(s); - pal[i][1] = stbi__get8(s); - pal[i][0] = stbi__get8(s); - if (info.hsz != 12) stbi__get8(s); - pal[i][3] = 255; - } - stbi__skip(s, info.offset - info.extra_read - info.hsz - psize * (info.hsz == 12 ? 3 : 4)); - if (info.bpp == 1) width = (s->img_x + 7) >> 3; - else if (info.bpp == 4) width = (s->img_x + 1) >> 1; - else if (info.bpp == 8) width = s->img_x; - else { STBI_FREE(out); return stbi__errpuc("bad bpp", "Corrupt BMP"); } - pad = (-width)&3; - if (info.bpp == 1) { - for (j=0; j < (int) s->img_y; ++j) { - int bit_offset = 7, v = stbi__get8(s); - for (i=0; i < (int) s->img_x; ++i) { - int color = (v>>bit_offset)&0x1; - out[z++] = pal[color][0]; - out[z++] = pal[color][1]; - out[z++] = pal[color][2]; - if (target == 4) out[z++] = 255; - if (i+1 == (int) s->img_x) break; - if((--bit_offset) < 0) { - bit_offset = 7; - v = stbi__get8(s); - } - } - stbi__skip(s, pad); - } - } else { - for (j=0; j < (int) s->img_y; ++j) { - for (i=0; i < (int) s->img_x; i += 2) { - int v=stbi__get8(s),v2=0; - if (info.bpp == 4) { - v2 = v & 15; - v >>= 4; - } - out[z++] = pal[v][0]; - out[z++] = pal[v][1]; - out[z++] = pal[v][2]; - if (target == 4) out[z++] = 255; - if (i+1 == (int) s->img_x) break; - v = (info.bpp == 8) ? stbi__get8(s) : v2; - out[z++] = pal[v][0]; - out[z++] = pal[v][1]; - out[z++] = pal[v][2]; - if (target == 4) out[z++] = 255; - } - stbi__skip(s, pad); - } - } - } else { - int rshift=0,gshift=0,bshift=0,ashift=0,rcount=0,gcount=0,bcount=0,acount=0; - int z = 0; - int easy=0; - stbi__skip(s, info.offset - info.extra_read - info.hsz); - if (info.bpp == 24) width = 3 * s->img_x; - else if (info.bpp == 16) width = 2*s->img_x; - else /* bpp = 32 and pad = 0 */ width=0; - pad = (-width) & 3; - if (info.bpp == 24) { - easy = 1; - } else if (info.bpp == 32) { - if (mb == 0xff && mg == 0xff00 && mr == 0x00ff0000 && ma == 0xff000000) - easy = 2; - } - if (!easy) { - if (!mr || !mg || !mb) { STBI_FREE(out); return stbi__errpuc("bad masks", "Corrupt BMP"); } - // right shift amt to put high bit in position #7 - rshift = stbi__high_bit(mr)-7; rcount = stbi__bitcount(mr); - gshift = stbi__high_bit(mg)-7; gcount = stbi__bitcount(mg); - bshift = stbi__high_bit(mb)-7; bcount = stbi__bitcount(mb); - ashift = stbi__high_bit(ma)-7; acount = stbi__bitcount(ma); - if (rcount > 8 || gcount > 8 || bcount > 8 || acount > 8) { STBI_FREE(out); return stbi__errpuc("bad masks", "Corrupt BMP"); } - } - for (j=0; j < (int) s->img_y; ++j) { - if (easy) { - for (i=0; i < (int) s->img_x; ++i) { - unsigned char a; - out[z+2] = stbi__get8(s); - out[z+1] = stbi__get8(s); - out[z+0] = stbi__get8(s); - z += 3; - a = (easy == 2 ? stbi__get8(s) : 255); - all_a |= a; - if (target == 4) out[z++] = a; - } - } else { - int bpp = info.bpp; - for (i=0; i < (int) s->img_x; ++i) { - stbi__uint32 v = (bpp == 16 ? (stbi__uint32) stbi__get16le(s) : stbi__get32le(s)); - unsigned int a; - out[z++] = STBI__BYTECAST(stbi__shiftsigned(v & mr, rshift, rcount)); - out[z++] = STBI__BYTECAST(stbi__shiftsigned(v & mg, gshift, gcount)); - out[z++] = STBI__BYTECAST(stbi__shiftsigned(v & mb, bshift, bcount)); - a = (ma ? stbi__shiftsigned(v & ma, ashift, acount) : 255); - all_a |= a; - if (target == 4) out[z++] = STBI__BYTECAST(a); - } - } - stbi__skip(s, pad); - } - } - - // if alpha channel is all 0s, replace with all 255s - if (target == 4 && all_a == 0) - for (i=4*s->img_x*s->img_y-1; i >= 0; i -= 4) - out[i] = 255; - - if (flip_vertically) { - stbi_uc t; - for (j=0; j < (int) s->img_y>>1; ++j) { - stbi_uc *p1 = out + j *s->img_x*target; - stbi_uc *p2 = out + (s->img_y-1-j)*s->img_x*target; - for (i=0; i < (int) s->img_x*target; ++i) { - t = p1[i]; p1[i] = p2[i]; p2[i] = t; - } - } - } - - if (req_comp && req_comp != target) { - out = stbi__convert_format(out, target, req_comp, s->img_x, s->img_y); - if (out == NULL) return out; // stbi__convert_format frees input on failure - } - - *x = s->img_x; - *y = s->img_y; - if (comp) *comp = s->img_n; - return out; -} -#endif - -// Targa Truevision - TGA -// by Jonathan Dummer -#ifndef STBI_NO_TGA -// returns STBI_rgb or whatever, 0 on error -static int stbi__tga_get_comp(int bits_per_pixel, int is_grey, int* is_rgb16) -{ - // only RGB or RGBA (incl. 16bit) or grey allowed - if (is_rgb16) *is_rgb16 = 0; - switch(bits_per_pixel) { - case 8: return STBI_grey; - case 16: if(is_grey) return STBI_grey_alpha; - // fallthrough - case 15: if(is_rgb16) *is_rgb16 = 1; - return STBI_rgb; - case 24: // fallthrough - case 32: return bits_per_pixel/8; - default: return 0; - } -} - -static int stbi__tga_info(stbi__context *s, int *x, int *y, int *comp) -{ - int tga_w, tga_h, tga_comp, tga_image_type, tga_bits_per_pixel, tga_colormap_bpp; - int sz, tga_colormap_type; - stbi__get8(s); // discard Offset - tga_colormap_type = stbi__get8(s); // colormap type - if( tga_colormap_type > 1 ) { - stbi__rewind(s); - return 0; // only RGB or indexed allowed - } - tga_image_type = stbi__get8(s); // image type - if ( tga_colormap_type == 1 ) { // colormapped (paletted) image - if (tga_image_type != 1 && tga_image_type != 9) { - stbi__rewind(s); - return 0; - } - stbi__skip(s,4); // skip index of first colormap entry and number of entries - sz = stbi__get8(s); // check bits per palette color entry - if ( (sz != 8) && (sz != 15) && (sz != 16) && (sz != 24) && (sz != 32) ) { - stbi__rewind(s); - return 0; - } - stbi__skip(s,4); // skip image x and y origin - tga_colormap_bpp = sz; - } else { // "normal" image w/o colormap - only RGB or grey allowed, +/- RLE - if ( (tga_image_type != 2) && (tga_image_type != 3) && (tga_image_type != 10) && (tga_image_type != 11) ) { - stbi__rewind(s); - return 0; // only RGB or grey allowed, +/- RLE - } - stbi__skip(s,9); // skip colormap specification and image x/y origin - tga_colormap_bpp = 0; - } - tga_w = stbi__get16le(s); - if( tga_w < 1 ) { - stbi__rewind(s); - return 0; // test width - } - tga_h = stbi__get16le(s); - if( tga_h < 1 ) { - stbi__rewind(s); - return 0; // test height - } - tga_bits_per_pixel = stbi__get8(s); // bits per pixel - stbi__get8(s); // ignore alpha bits - if (tga_colormap_bpp != 0) { - if((tga_bits_per_pixel != 8) && (tga_bits_per_pixel != 16)) { - // when using a colormap, tga_bits_per_pixel is the size of the indexes - // I don't think anything but 8 or 16bit indexes makes sense - stbi__rewind(s); - return 0; - } - tga_comp = stbi__tga_get_comp(tga_colormap_bpp, 0, NULL); - } else { - tga_comp = stbi__tga_get_comp(tga_bits_per_pixel, (tga_image_type == 3) || (tga_image_type == 11), NULL); - } - if(!tga_comp) { - stbi__rewind(s); - return 0; - } - if (x) *x = tga_w; - if (y) *y = tga_h; - if (comp) *comp = tga_comp; - return 1; // seems to have passed everything -} - -static int stbi__tga_test(stbi__context *s) -{ - int res = 0; - int sz, tga_color_type; - stbi__get8(s); // discard Offset - tga_color_type = stbi__get8(s); // color type - if ( tga_color_type > 1 ) goto errorEnd; // only RGB or indexed allowed - sz = stbi__get8(s); // image type - if ( tga_color_type == 1 ) { // colormapped (paletted) image - if (sz != 1 && sz != 9) goto errorEnd; // colortype 1 demands image type 1 or 9 - stbi__skip(s,4); // skip index of first colormap entry and number of entries - sz = stbi__get8(s); // check bits per palette color entry - if ( (sz != 8) && (sz != 15) && (sz != 16) && (sz != 24) && (sz != 32) ) goto errorEnd; - stbi__skip(s,4); // skip image x and y origin - } else { // "normal" image w/o colormap - if ( (sz != 2) && (sz != 3) && (sz != 10) && (sz != 11) ) goto errorEnd; // only RGB or grey allowed, +/- RLE - stbi__skip(s,9); // skip colormap specification and image x/y origin - } - if ( stbi__get16le(s) < 1 ) goto errorEnd; // test width - if ( stbi__get16le(s) < 1 ) goto errorEnd; // test height - sz = stbi__get8(s); // bits per pixel - if ( (tga_color_type == 1) && (sz != 8) && (sz != 16) ) goto errorEnd; // for colormapped images, bpp is size of an index - if ( (sz != 8) && (sz != 15) && (sz != 16) && (sz != 24) && (sz != 32) ) goto errorEnd; - - res = 1; // if we got this far, everything's good and we can return 1 instead of 0 - -errorEnd: - stbi__rewind(s); - return res; -} - -// read 16bit value and convert to 24bit RGB -static void stbi__tga_read_rgb16(stbi__context *s, stbi_uc* out) -{ - stbi__uint16 px = (stbi__uint16)stbi__get16le(s); - stbi__uint16 fiveBitMask = 31; - // we have 3 channels with 5bits each - int r = (px >> 10) & fiveBitMask; - int g = (px >> 5) & fiveBitMask; - int b = px & fiveBitMask; - // Note that this saves the data in RGB(A) order, so it doesn't need to be swapped later - out[0] = (stbi_uc)((r * 255)/31); - out[1] = (stbi_uc)((g * 255)/31); - out[2] = (stbi_uc)((b * 255)/31); - - // some people claim that the most significant bit might be used for alpha - // (possibly if an alpha-bit is set in the "image descriptor byte") - // but that only made 16bit test images completely translucent.. - // so let's treat all 15 and 16bit TGAs as RGB with no alpha. -} - -static void *stbi__tga_load(stbi__context *s, int *x, int *y, int *comp, int req_comp, stbi__result_info *ri) -{ - // read in the TGA header stuff - int tga_offset = stbi__get8(s); - int tga_indexed = stbi__get8(s); - int tga_image_type = stbi__get8(s); - int tga_is_RLE = 0; - int tga_palette_start = stbi__get16le(s); - int tga_palette_len = stbi__get16le(s); - int tga_palette_bits = stbi__get8(s); - int tga_x_origin = stbi__get16le(s); - int tga_y_origin = stbi__get16le(s); - int tga_width = stbi__get16le(s); - int tga_height = stbi__get16le(s); - int tga_bits_per_pixel = stbi__get8(s); - int tga_comp, tga_rgb16=0; - int tga_inverted = stbi__get8(s); - // int tga_alpha_bits = tga_inverted & 15; // the 4 lowest bits - unused (useless?) - // image data - unsigned char *tga_data; - unsigned char *tga_palette = NULL; - int i, j; - unsigned char raw_data[4] = {0}; - int RLE_count = 0; - int RLE_repeating = 0; - int read_next_pixel = 1; - STBI_NOTUSED(ri); - STBI_NOTUSED(tga_x_origin); // @TODO - STBI_NOTUSED(tga_y_origin); // @TODO - - if (tga_height > STBI_MAX_DIMENSIONS) return stbi__errpuc("too large","Very large image (corrupt?)"); - if (tga_width > STBI_MAX_DIMENSIONS) return stbi__errpuc("too large","Very large image (corrupt?)"); - - // do a tiny bit of precessing - if ( tga_image_type >= 8 ) - { - tga_image_type -= 8; - tga_is_RLE = 1; - } - tga_inverted = 1 - ((tga_inverted >> 5) & 1); - - // If I'm paletted, then I'll use the number of bits from the palette - if ( tga_indexed ) tga_comp = stbi__tga_get_comp(tga_palette_bits, 0, &tga_rgb16); - else tga_comp = stbi__tga_get_comp(tga_bits_per_pixel, (tga_image_type == 3), &tga_rgb16); - - if(!tga_comp) // shouldn't really happen, stbi__tga_test() should have ensured basic consistency - return stbi__errpuc("bad format", "Can't find out TGA pixelformat"); - - // tga info - *x = tga_width; - *y = tga_height; - if (comp) *comp = tga_comp; - - if (!stbi__mad3sizes_valid(tga_width, tga_height, tga_comp, 0)) - return stbi__errpuc("too large", "Corrupt TGA"); - - tga_data = (unsigned char*)stbi__malloc_mad3(tga_width, tga_height, tga_comp, 0); - if (!tga_data) return stbi__errpuc("outofmem", "Out of memory"); - - // skip to the data's starting position (offset usually = 0) - stbi__skip(s, tga_offset ); - - if ( !tga_indexed && !tga_is_RLE && !tga_rgb16 ) { - for (i=0; i < tga_height; ++i) { - int row = tga_inverted ? tga_height -i - 1 : i; - stbi_uc *tga_row = tga_data + row*tga_width*tga_comp; - stbi__getn(s, tga_row, tga_width * tga_comp); - } - } else { - // do I need to load a palette? - if ( tga_indexed) - { - if (tga_palette_len == 0) { /* you have to have at least one entry! */ - STBI_FREE(tga_data); - return stbi__errpuc("bad palette", "Corrupt TGA"); - } - - // any data to skip? (offset usually = 0) - stbi__skip(s, tga_palette_start ); - // load the palette - tga_palette = (unsigned char*)stbi__malloc_mad2(tga_palette_len, tga_comp, 0); - if (!tga_palette) { - STBI_FREE(tga_data); - return stbi__errpuc("outofmem", "Out of memory"); - } - if (tga_rgb16) { - stbi_uc *pal_entry = tga_palette; - STBI_ASSERT(tga_comp == STBI_rgb); - for (i=0; i < tga_palette_len; ++i) { - stbi__tga_read_rgb16(s, pal_entry); - pal_entry += tga_comp; - } - } else if (!stbi__getn(s, tga_palette, tga_palette_len * tga_comp)) { - STBI_FREE(tga_data); - STBI_FREE(tga_palette); - return stbi__errpuc("bad palette", "Corrupt TGA"); - } - } - // load the data - for (i=0; i < tga_width * tga_height; ++i) - { - // if I'm in RLE mode, do I need to get a RLE stbi__pngchunk? - if ( tga_is_RLE ) - { - if ( RLE_count == 0 ) - { - // yep, get the next byte as a RLE command - int RLE_cmd = stbi__get8(s); - RLE_count = 1 + (RLE_cmd & 127); - RLE_repeating = RLE_cmd >> 7; - read_next_pixel = 1; - } else if ( !RLE_repeating ) - { - read_next_pixel = 1; - } - } else - { - read_next_pixel = 1; - } - // OK, if I need to read a pixel, do it now - if ( read_next_pixel ) - { - // load however much data we did have - if ( tga_indexed ) - { - // read in index, then perform the lookup - int pal_idx = (tga_bits_per_pixel == 8) ? stbi__get8(s) : stbi__get16le(s); - if ( pal_idx >= tga_palette_len ) { - // invalid index - pal_idx = 0; - } - pal_idx *= tga_comp; - for (j = 0; j < tga_comp; ++j) { - raw_data[j] = tga_palette[pal_idx+j]; - } - } else if(tga_rgb16) { - STBI_ASSERT(tga_comp == STBI_rgb); - stbi__tga_read_rgb16(s, raw_data); - } else { - // read in the data raw - for (j = 0; j < tga_comp; ++j) { - raw_data[j] = stbi__get8(s); - } - } - // clear the reading flag for the next pixel - read_next_pixel = 0; - } // end of reading a pixel - - // copy data - for (j = 0; j < tga_comp; ++j) - tga_data[i*tga_comp+j] = raw_data[j]; - - // in case we're in RLE mode, keep counting down - --RLE_count; - } - // do I need to invert the image? - if ( tga_inverted ) - { - for (j = 0; j*2 < tga_height; ++j) - { - int index1 = j * tga_width * tga_comp; - int index2 = (tga_height - 1 - j) * tga_width * tga_comp; - for (i = tga_width * tga_comp; i > 0; --i) - { - unsigned char temp = tga_data[index1]; - tga_data[index1] = tga_data[index2]; - tga_data[index2] = temp; - ++index1; - ++index2; - } - } - } - // clear my palette, if I had one - if ( tga_palette != NULL ) - { - STBI_FREE( tga_palette ); - } - } - - // swap RGB - if the source data was RGB16, it already is in the right order - if (tga_comp >= 3 && !tga_rgb16) - { - unsigned char* tga_pixel = tga_data; - for (i=0; i < tga_width * tga_height; ++i) - { - unsigned char temp = tga_pixel[0]; - tga_pixel[0] = tga_pixel[2]; - tga_pixel[2] = temp; - tga_pixel += tga_comp; - } - } - - // convert to target component count - if (req_comp && req_comp != tga_comp) - tga_data = stbi__convert_format(tga_data, tga_comp, req_comp, tga_width, tga_height); - - // the things I do to get rid of an error message, and yet keep - // Microsoft's C compilers happy... [8^( - tga_palette_start = tga_palette_len = tga_palette_bits = - tga_x_origin = tga_y_origin = 0; - STBI_NOTUSED(tga_palette_start); - // OK, done - return tga_data; -} -#endif - -// ************************************************************************************************* -// Photoshop PSD loader -- PD by Thatcher Ulrich, integration by Nicolas Schulz, tweaked by STB - -#ifndef STBI_NO_PSD -static int stbi__psd_test(stbi__context *s) -{ - int r = (stbi__get32be(s) == 0x38425053); - stbi__rewind(s); - return r; -} - -static int stbi__psd_decode_rle(stbi__context *s, stbi_uc *p, int pixelCount) -{ - int count, nleft, len; - - count = 0; - while ((nleft = pixelCount - count) > 0) { - len = stbi__get8(s); - if (len == 128) { - // No-op. - } else if (len < 128) { - // Copy next len+1 bytes literally. - len++; - if (len > nleft) return 0; // corrupt data - count += len; - while (len) { - *p = stbi__get8(s); - p += 4; - len--; - } - } else if (len > 128) { - stbi_uc val; - // Next -len+1 bytes in the dest are replicated from next source byte. - // (Interpret len as a negative 8-bit int.) - len = 257 - len; - if (len > nleft) return 0; // corrupt data - val = stbi__get8(s); - count += len; - while (len) { - *p = val; - p += 4; - len--; - } - } - } - - return 1; -} - -static void *stbi__psd_load(stbi__context *s, int *x, int *y, int *comp, int req_comp, stbi__result_info *ri, int bpc) -{ - int pixelCount; - int channelCount, compression; - int channel, i; - int bitdepth; - int w,h; - stbi_uc *out; - STBI_NOTUSED(ri); - - // Check identifier - if (stbi__get32be(s) != 0x38425053) // "8BPS" - return stbi__errpuc("not PSD", "Corrupt PSD image"); - - // Check file type version. - if (stbi__get16be(s) != 1) - return stbi__errpuc("wrong version", "Unsupported version of PSD image"); - - // Skip 6 reserved bytes. - stbi__skip(s, 6 ); - - // Read the number of channels (R, G, B, A, etc). - channelCount = stbi__get16be(s); - if (channelCount < 0 || channelCount > 16) - return stbi__errpuc("wrong channel count", "Unsupported number of channels in PSD image"); - - // Read the rows and columns of the image. - h = stbi__get32be(s); - w = stbi__get32be(s); - - if (h > STBI_MAX_DIMENSIONS) return stbi__errpuc("too large","Very large image (corrupt?)"); - if (w > STBI_MAX_DIMENSIONS) return stbi__errpuc("too large","Very large image (corrupt?)"); - - // Make sure the depth is 8 bits. - bitdepth = stbi__get16be(s); - if (bitdepth != 8 && bitdepth != 16) - return stbi__errpuc("unsupported bit depth", "PSD bit depth is not 8 or 16 bit"); - - // Make sure the color mode is RGB. - // Valid options are: - // 0: Bitmap - // 1: Grayscale - // 2: Indexed color - // 3: RGB color - // 4: CMYK color - // 7: Multichannel - // 8: Duotone - // 9: Lab color - if (stbi__get16be(s) != 3) - return stbi__errpuc("wrong color format", "PSD is not in RGB color format"); - - // Skip the Mode Data. (It's the palette for indexed color; other info for other modes.) - stbi__skip(s,stbi__get32be(s) ); - - // Skip the image resources. (resolution, pen tool paths, etc) - stbi__skip(s, stbi__get32be(s) ); - - // Skip the reserved data. - stbi__skip(s, stbi__get32be(s) ); - - // Find out if the data is compressed. - // Known values: - // 0: no compression - // 1: RLE compressed - compression = stbi__get16be(s); - if (compression > 1) - return stbi__errpuc("bad compression", "PSD has an unknown compression format"); - - // Check size - if (!stbi__mad3sizes_valid(4, w, h, 0)) - return stbi__errpuc("too large", "Corrupt PSD"); - - // Create the destination image. - - if (!compression && bitdepth == 16 && bpc == 16) { - out = (stbi_uc *) stbi__malloc_mad3(8, w, h, 0); - ri->bits_per_channel = 16; - } else - out = (stbi_uc *) stbi__malloc(4 * w*h); - - if (!out) return stbi__errpuc("outofmem", "Out of memory"); - pixelCount = w*h; - - // Initialize the data to zero. - //memset( out, 0, pixelCount * 4 ); - - // Finally, the image data. - if (compression) { - // RLE as used by .PSD and .TIFF - // Loop until you get the number of unpacked bytes you are expecting: - // Read the next source byte into n. - // If n is between 0 and 127 inclusive, copy the next n+1 bytes literally. - // Else if n is between -127 and -1 inclusive, copy the next byte -n+1 times. - // Else if n is 128, noop. - // Endloop - - // The RLE-compressed data is preceded by a 2-byte data count for each row in the data, - // which we're going to just skip. - stbi__skip(s, h * channelCount * 2 ); - - // Read the RLE data by channel. - for (channel = 0; channel < 4; channel++) { - stbi_uc *p; - - p = out+channel; - if (channel >= channelCount) { - // Fill this channel with default data. - for (i = 0; i < pixelCount; i++, p += 4) - *p = (channel == 3 ? 255 : 0); - } else { - // Read the RLE data. - if (!stbi__psd_decode_rle(s, p, pixelCount)) { - STBI_FREE(out); - return stbi__errpuc("corrupt", "bad RLE data"); - } - } - } - - } else { - // We're at the raw image data. It's each channel in order (Red, Green, Blue, Alpha, ...) - // where each channel consists of an 8-bit (or 16-bit) value for each pixel in the image. - - // Read the data by channel. - for (channel = 0; channel < 4; channel++) { - if (channel >= channelCount) { - // Fill this channel with default data. - if (bitdepth == 16 && bpc == 16) { - stbi__uint16 *q = ((stbi__uint16 *) out) + channel; - stbi__uint16 val = channel == 3 ? 65535 : 0; - for (i = 0; i < pixelCount; i++, q += 4) - *q = val; - } else { - stbi_uc *p = out+channel; - stbi_uc val = channel == 3 ? 255 : 0; - for (i = 0; i < pixelCount; i++, p += 4) - *p = val; - } - } else { - if (ri->bits_per_channel == 16) { // output bpc - stbi__uint16 *q = ((stbi__uint16 *) out) + channel; - for (i = 0; i < pixelCount; i++, q += 4) - *q = (stbi__uint16) stbi__get16be(s); - } else { - stbi_uc *p = out+channel; - if (bitdepth == 16) { // input bpc - for (i = 0; i < pixelCount; i++, p += 4) - *p = (stbi_uc) (stbi__get16be(s) >> 8); - } else { - for (i = 0; i < pixelCount; i++, p += 4) - *p = stbi__get8(s); - } - } - } - } - } - - // remove weird white matte from PSD - if (channelCount >= 4) { - if (ri->bits_per_channel == 16) { - for (i=0; i < w*h; ++i) { - stbi__uint16 *pixel = (stbi__uint16 *) out + 4*i; - if (pixel[3] != 0 && pixel[3] != 65535) { - float a = pixel[3] / 65535.0f; - float ra = 1.0f / a; - float inv_a = 65535.0f * (1 - ra); - pixel[0] = (stbi__uint16) (pixel[0]*ra + inv_a); - pixel[1] = (stbi__uint16) (pixel[1]*ra + inv_a); - pixel[2] = (stbi__uint16) (pixel[2]*ra + inv_a); - } - } - } else { - for (i=0; i < w*h; ++i) { - unsigned char *pixel = out + 4*i; - if (pixel[3] != 0 && pixel[3] != 255) { - float a = pixel[3] / 255.0f; - float ra = 1.0f / a; - float inv_a = 255.0f * (1 - ra); - pixel[0] = (unsigned char) (pixel[0]*ra + inv_a); - pixel[1] = (unsigned char) (pixel[1]*ra + inv_a); - pixel[2] = (unsigned char) (pixel[2]*ra + inv_a); - } - } - } - } - - // convert to desired output format - if (req_comp && req_comp != 4) { - if (ri->bits_per_channel == 16) - out = (stbi_uc *) stbi__convert_format16((stbi__uint16 *) out, 4, req_comp, w, h); - else - out = stbi__convert_format(out, 4, req_comp, w, h); - if (out == NULL) return out; // stbi__convert_format frees input on failure - } - - if (comp) *comp = 4; - *y = h; - *x = w; - - return out; -} -#endif - -// ************************************************************************************************* -// Softimage PIC loader -// by Tom Seddon -// -// See http://softimage.wiki.softimage.com/index.php/INFO:_PIC_file_format -// See http://ozviz.wasp.uwa.edu.au/~pbourke/dataformats/softimagepic/ - -#ifndef STBI_NO_PIC -static int stbi__pic_is4(stbi__context *s,const char *str) -{ - int i; - for (i=0; i<4; ++i) - if (stbi__get8(s) != (stbi_uc)str[i]) - return 0; - - return 1; -} - -static int stbi__pic_test_core(stbi__context *s) -{ - int i; - - if (!stbi__pic_is4(s,"\x53\x80\xF6\x34")) - return 0; - - for(i=0;i<84;++i) - stbi__get8(s); - - if (!stbi__pic_is4(s,"PICT")) - return 0; - - return 1; -} - -typedef struct -{ - stbi_uc size,type,channel; -} stbi__pic_packet; - -static stbi_uc *stbi__readval(stbi__context *s, int channel, stbi_uc *dest) -{ - int mask=0x80, i; - - for (i=0; i<4; ++i, mask>>=1) { - if (channel & mask) { - if (stbi__at_eof(s)) return stbi__errpuc("bad file","PIC file too short"); - dest[i]=stbi__get8(s); - } - } - - return dest; -} - -static void stbi__copyval(int channel,stbi_uc *dest,const stbi_uc *src) -{ - int mask=0x80,i; - - for (i=0;i<4; ++i, mask>>=1) - if (channel&mask) - dest[i]=src[i]; -} - -static stbi_uc *stbi__pic_load_core(stbi__context *s,int width,int height,int *comp, stbi_uc *result) -{ - int act_comp=0,num_packets=0,y,chained; - stbi__pic_packet packets[10]; - - // this will (should...) cater for even some bizarre stuff like having data - // for the same channel in multiple packets. - do { - stbi__pic_packet *packet; - - if (num_packets==sizeof(packets)/sizeof(packets[0])) - return stbi__errpuc("bad format","too many packets"); - - packet = &packets[num_packets++]; - - chained = stbi__get8(s); - packet->size = stbi__get8(s); - packet->type = stbi__get8(s); - packet->channel = stbi__get8(s); - - act_comp |= packet->channel; - - if (stbi__at_eof(s)) return stbi__errpuc("bad file","file too short (reading packets)"); - if (packet->size != 8) return stbi__errpuc("bad format","packet isn't 8bpp"); - } while (chained); - - *comp = (act_comp & 0x10 ? 4 : 3); // has alpha channel? - - for(y=0; ytype) { - default: - return stbi__errpuc("bad format","packet has bad compression type"); - - case 0: {//uncompressed - int x; - - for(x=0;xchannel,dest)) - return 0; - break; - } - - case 1://Pure RLE - { - int left=width, i; - - while (left>0) { - stbi_uc count,value[4]; - - count=stbi__get8(s); - if (stbi__at_eof(s)) return stbi__errpuc("bad file","file too short (pure read count)"); - - if (count > left) - count = (stbi_uc) left; - - if (!stbi__readval(s,packet->channel,value)) return 0; - - for(i=0; ichannel,dest,value); - left -= count; - } - } - break; - - case 2: {//Mixed RLE - int left=width; - while (left>0) { - int count = stbi__get8(s), i; - if (stbi__at_eof(s)) return stbi__errpuc("bad file","file too short (mixed read count)"); - - if (count >= 128) { // Repeated - stbi_uc value[4]; - - if (count==128) - count = stbi__get16be(s); - else - count -= 127; - if (count > left) - return stbi__errpuc("bad file","scanline overrun"); - - if (!stbi__readval(s,packet->channel,value)) - return 0; - - for(i=0;ichannel,dest,value); - } else { // Raw - ++count; - if (count>left) return stbi__errpuc("bad file","scanline overrun"); - - for(i=0;ichannel,dest)) - return 0; - } - left-=count; - } - break; - } - } - } - } - - return result; -} - -static void *stbi__pic_load(stbi__context *s,int *px,int *py,int *comp,int req_comp, stbi__result_info *ri) -{ - stbi_uc *result; - int i, x,y, internal_comp; - STBI_NOTUSED(ri); - - if (!comp) comp = &internal_comp; - - for (i=0; i<92; ++i) - stbi__get8(s); - - x = stbi__get16be(s); - y = stbi__get16be(s); - - if (y > STBI_MAX_DIMENSIONS) return stbi__errpuc("too large","Very large image (corrupt?)"); - if (x > STBI_MAX_DIMENSIONS) return stbi__errpuc("too large","Very large image (corrupt?)"); - - if (stbi__at_eof(s)) return stbi__errpuc("bad file","file too short (pic header)"); - if (!stbi__mad3sizes_valid(x, y, 4, 0)) return stbi__errpuc("too large", "PIC image too large to decode"); - - stbi__get32be(s); //skip `ratio' - stbi__get16be(s); //skip `fields' - stbi__get16be(s); //skip `pad' - - // intermediate buffer is RGBA - result = (stbi_uc *) stbi__malloc_mad3(x, y, 4, 0); - if (!result) return stbi__errpuc("outofmem", "Out of memory"); - memset(result, 0xff, x*y*4); - - if (!stbi__pic_load_core(s,x,y,comp, result)) { - STBI_FREE(result); - result=0; - } - *px = x; - *py = y; - if (req_comp == 0) req_comp = *comp; - result=stbi__convert_format(result,4,req_comp,x,y); - - return result; -} - -static int stbi__pic_test(stbi__context *s) -{ - int r = stbi__pic_test_core(s); - stbi__rewind(s); - return r; -} -#endif - -// ************************************************************************************************* -// GIF loader -- public domain by Jean-Marc Lienher -- simplified/shrunk by stb - -#ifndef STBI_NO_GIF -typedef struct -{ - stbi__int16 prefix; - stbi_uc first; - stbi_uc suffix; -} stbi__gif_lzw; - -typedef struct -{ - int w,h; - stbi_uc *out; // output buffer (always 4 components) - stbi_uc *background; // The current "background" as far as a gif is concerned - stbi_uc *history; - int flags, bgindex, ratio, transparent, eflags; - stbi_uc pal[256][4]; - stbi_uc lpal[256][4]; - stbi__gif_lzw codes[8192]; - stbi_uc *color_table; - int parse, step; - int lflags; - int start_x, start_y; - int max_x, max_y; - int cur_x, cur_y; - int line_size; - int delay; -} stbi__gif; - -static int stbi__gif_test_raw(stbi__context *s) -{ - int sz; - if (stbi__get8(s) != 'G' || stbi__get8(s) != 'I' || stbi__get8(s) != 'F' || stbi__get8(s) != '8') return 0; - sz = stbi__get8(s); - if (sz != '9' && sz != '7') return 0; - if (stbi__get8(s) != 'a') return 0; - return 1; -} - -static int stbi__gif_test(stbi__context *s) -{ - int r = stbi__gif_test_raw(s); - stbi__rewind(s); - return r; -} - -static void stbi__gif_parse_colortable(stbi__context *s, stbi_uc pal[256][4], int num_entries, int transp) -{ - int i; - for (i=0; i < num_entries; ++i) { - pal[i][2] = stbi__get8(s); - pal[i][1] = stbi__get8(s); - pal[i][0] = stbi__get8(s); - pal[i][3] = transp == i ? 0 : 255; - } -} - -static int stbi__gif_header(stbi__context *s, stbi__gif *g, int *comp, int is_info) -{ - stbi_uc version; - if (stbi__get8(s) != 'G' || stbi__get8(s) != 'I' || stbi__get8(s) != 'F' || stbi__get8(s) != '8') - return stbi__err("not GIF", "Corrupt GIF"); - - version = stbi__get8(s); - if (version != '7' && version != '9') return stbi__err("not GIF", "Corrupt GIF"); - if (stbi__get8(s) != 'a') return stbi__err("not GIF", "Corrupt GIF"); - - stbi__g_failure_reason = ""; - g->w = stbi__get16le(s); - g->h = stbi__get16le(s); - g->flags = stbi__get8(s); - g->bgindex = stbi__get8(s); - g->ratio = stbi__get8(s); - g->transparent = -1; - - if (g->w > STBI_MAX_DIMENSIONS) return stbi__err("too large","Very large image (corrupt?)"); - if (g->h > STBI_MAX_DIMENSIONS) return stbi__err("too large","Very large image (corrupt?)"); - - if (comp != 0) *comp = 4; // can't actually tell whether it's 3 or 4 until we parse the comments - - if (is_info) return 1; - - if (g->flags & 0x80) - stbi__gif_parse_colortable(s,g->pal, 2 << (g->flags & 7), -1); - - return 1; -} - -static int stbi__gif_info_raw(stbi__context *s, int *x, int *y, int *comp) -{ - stbi__gif* g = (stbi__gif*) stbi__malloc(sizeof(stbi__gif)); - if (!g) return stbi__err("outofmem", "Out of memory"); - if (!stbi__gif_header(s, g, comp, 1)) { - STBI_FREE(g); - stbi__rewind( s ); - return 0; - } - if (x) *x = g->w; - if (y) *y = g->h; - STBI_FREE(g); - return 1; -} - -static void stbi__out_gif_code(stbi__gif *g, stbi__uint16 code) -{ - stbi_uc *p, *c; - int idx; - - // recurse to decode the prefixes, since the linked-list is backwards, - // and working backwards through an interleaved image would be nasty - if (g->codes[code].prefix >= 0) - stbi__out_gif_code(g, g->codes[code].prefix); - - if (g->cur_y >= g->max_y) return; - - idx = g->cur_x + g->cur_y; - p = &g->out[idx]; - g->history[idx / 4] = 1; - - c = &g->color_table[g->codes[code].suffix * 4]; - if (c[3] > 128) { // don't render transparent pixels; - p[0] = c[2]; - p[1] = c[1]; - p[2] = c[0]; - p[3] = c[3]; - } - g->cur_x += 4; - - if (g->cur_x >= g->max_x) { - g->cur_x = g->start_x; - g->cur_y += g->step; - - while (g->cur_y >= g->max_y && g->parse > 0) { - g->step = (1 << g->parse) * g->line_size; - g->cur_y = g->start_y + (g->step >> 1); - --g->parse; - } - } -} - -static stbi_uc *stbi__process_gif_raster(stbi__context *s, stbi__gif *g) -{ - stbi_uc lzw_cs; - stbi__int32 len, init_code; - stbi__uint32 first; - stbi__int32 codesize, codemask, avail, oldcode, bits, valid_bits, clear; - stbi__gif_lzw *p; - - lzw_cs = stbi__get8(s); - if (lzw_cs > 12) return NULL; - clear = 1 << lzw_cs; - first = 1; - codesize = lzw_cs + 1; - codemask = (1 << codesize) - 1; - bits = 0; - valid_bits = 0; - for (init_code = 0; init_code < clear; init_code++) { - g->codes[init_code].prefix = -1; - g->codes[init_code].first = (stbi_uc) init_code; - g->codes[init_code].suffix = (stbi_uc) init_code; - } - - // support no starting clear code - avail = clear+2; - oldcode = -1; - - len = 0; - for(;;) { - if (valid_bits < codesize) { - if (len == 0) { - len = stbi__get8(s); // start new block - if (len == 0) - return g->out; - } - --len; - bits |= (stbi__int32) stbi__get8(s) << valid_bits; - valid_bits += 8; - } else { - stbi__int32 code = bits & codemask; - bits >>= codesize; - valid_bits -= codesize; - // @OPTIMIZE: is there some way we can accelerate the non-clear path? - if (code == clear) { // clear code - codesize = lzw_cs + 1; - codemask = (1 << codesize) - 1; - avail = clear + 2; - oldcode = -1; - first = 0; - } else if (code == clear + 1) { // end of stream code - stbi__skip(s, len); - while ((len = stbi__get8(s)) > 0) - stbi__skip(s,len); - return g->out; - } else if (code <= avail) { - if (first) { - return stbi__errpuc("no clear code", "Corrupt GIF"); - } - - if (oldcode >= 0) { - p = &g->codes[avail++]; - if (avail > 8192) { - return stbi__errpuc("too many codes", "Corrupt GIF"); - } - - p->prefix = (stbi__int16) oldcode; - p->first = g->codes[oldcode].first; - p->suffix = (code == avail) ? p->first : g->codes[code].first; - } else if (code == avail) - return stbi__errpuc("illegal code in raster", "Corrupt GIF"); - - stbi__out_gif_code(g, (stbi__uint16) code); - - if ((avail & codemask) == 0 && avail <= 0x0FFF) { - codesize++; - codemask = (1 << codesize) - 1; - } - - oldcode = code; - } else { - return stbi__errpuc("illegal code in raster", "Corrupt GIF"); - } - } - } -} - -// this function is designed to support animated gifs, although stb_image doesn't support it -// two back is the image from two frames ago, used for a very specific disposal format -static stbi_uc *stbi__gif_load_next(stbi__context *s, stbi__gif *g, int *comp, int req_comp, stbi_uc *two_back) -{ - int dispose; - int first_frame; - int pi; - int pcount; - STBI_NOTUSED(req_comp); - - // on first frame, any non-written pixels get the background colour (non-transparent) - first_frame = 0; - if (g->out == 0) { - if (!stbi__gif_header(s, g, comp,0)) return 0; // stbi__g_failure_reason set by stbi__gif_header - if (!stbi__mad3sizes_valid(4, g->w, g->h, 0)) - return stbi__errpuc("too large", "GIF image is too large"); - pcount = g->w * g->h; - g->out = (stbi_uc *) stbi__malloc(4 * pcount); - g->background = (stbi_uc *) stbi__malloc(4 * pcount); - g->history = (stbi_uc *) stbi__malloc(pcount); - if (!g->out || !g->background || !g->history) - return stbi__errpuc("outofmem", "Out of memory"); - - // image is treated as "transparent" at the start - ie, nothing overwrites the current background; - // background colour is only used for pixels that are not rendered first frame, after that "background" - // color refers to the color that was there the previous frame. - memset(g->out, 0x00, 4 * pcount); - memset(g->background, 0x00, 4 * pcount); // state of the background (starts transparent) - memset(g->history, 0x00, pcount); // pixels that were affected previous frame - first_frame = 1; - } else { - // second frame - how do we dispose of the previous one? - dispose = (g->eflags & 0x1C) >> 2; - pcount = g->w * g->h; - - if ((dispose == 3) && (two_back == 0)) { - dispose = 2; // if I don't have an image to revert back to, default to the old background - } - - if (dispose == 3) { // use previous graphic - for (pi = 0; pi < pcount; ++pi) { - if (g->history[pi]) { - memcpy( &g->out[pi * 4], &two_back[pi * 4], 4 ); - } - } - } else if (dispose == 2) { - // restore what was changed last frame to background before that frame; - for (pi = 0; pi < pcount; ++pi) { - if (g->history[pi]) { - memcpy( &g->out[pi * 4], &g->background[pi * 4], 4 ); - } - } - } else { - // This is a non-disposal case eithe way, so just - // leave the pixels as is, and they will become the new background - // 1: do not dispose - // 0: not specified. - } - - // background is what out is after the undoing of the previou frame; - memcpy( g->background, g->out, 4 * g->w * g->h ); - } - - // clear my history; - memset( g->history, 0x00, g->w * g->h ); // pixels that were affected previous frame - - for (;;) { - int tag = stbi__get8(s); - switch (tag) { - case 0x2C: /* Image Descriptor */ - { - stbi__int32 x, y, w, h; - stbi_uc *o; - - x = stbi__get16le(s); - y = stbi__get16le(s); - w = stbi__get16le(s); - h = stbi__get16le(s); - if (((x + w) > (g->w)) || ((y + h) > (g->h))) - return stbi__errpuc("bad Image Descriptor", "Corrupt GIF"); - - g->line_size = g->w * 4; - g->start_x = x * 4; - g->start_y = y * g->line_size; - g->max_x = g->start_x + w * 4; - g->max_y = g->start_y + h * g->line_size; - g->cur_x = g->start_x; - g->cur_y = g->start_y; - - // if the width of the specified rectangle is 0, that means - // we may not see *any* pixels or the image is malformed; - // to make sure this is caught, move the current y down to - // max_y (which is what out_gif_code checks). - if (w == 0) - g->cur_y = g->max_y; - - g->lflags = stbi__get8(s); - - if (g->lflags & 0x40) { - g->step = 8 * g->line_size; // first interlaced spacing - g->parse = 3; - } else { - g->step = g->line_size; - g->parse = 0; - } - - if (g->lflags & 0x80) { - stbi__gif_parse_colortable(s,g->lpal, 2 << (g->lflags & 7), g->eflags & 0x01 ? g->transparent : -1); - g->color_table = (stbi_uc *) g->lpal; - } else if (g->flags & 0x80) { - g->color_table = (stbi_uc *) g->pal; - } else - return stbi__errpuc("missing color table", "Corrupt GIF"); - - o = stbi__process_gif_raster(s, g); - if (!o) return NULL; - - // if this was the first frame, - pcount = g->w * g->h; - if (first_frame && (g->bgindex > 0)) { - // if first frame, any pixel not drawn to gets the background color - for (pi = 0; pi < pcount; ++pi) { - if (g->history[pi] == 0) { - g->pal[g->bgindex][3] = 255; // just in case it was made transparent, undo that; It will be reset next frame if need be; - memcpy( &g->out[pi * 4], &g->pal[g->bgindex], 4 ); - } - } - } - - return o; - } - - case 0x21: // Comment Extension. - { - int len; - int ext = stbi__get8(s); - if (ext == 0xF9) { // Graphic Control Extension. - len = stbi__get8(s); - if (len == 4) { - g->eflags = stbi__get8(s); - g->delay = 10 * stbi__get16le(s); // delay - 1/100th of a second, saving as 1/1000ths. - - // unset old transparent - if (g->transparent >= 0) { - g->pal[g->transparent][3] = 255; - } - if (g->eflags & 0x01) { - g->transparent = stbi__get8(s); - if (g->transparent >= 0) { - g->pal[g->transparent][3] = 0; - } - } else { - // don't need transparent - stbi__skip(s, 1); - g->transparent = -1; - } - } else { - stbi__skip(s, len); - break; - } - } - while ((len = stbi__get8(s)) != 0) { - stbi__skip(s, len); - } - break; - } - - case 0x3B: // gif stream termination code - return (stbi_uc *) s; // using '1' causes warning on some compilers - - default: - return stbi__errpuc("unknown code", "Corrupt GIF"); - } - } -} - -static void *stbi__load_gif_main_outofmem(stbi__gif *g, stbi_uc *out, int **delays) -{ - STBI_FREE(g->out); - STBI_FREE(g->history); - STBI_FREE(g->background); - - if (out) STBI_FREE(out); - if (delays && *delays) STBI_FREE(*delays); - return stbi__errpuc("outofmem", "Out of memory"); -} - -static void *stbi__load_gif_main(stbi__context *s, int **delays, int *x, int *y, int *z, int *comp, int req_comp) -{ - if (stbi__gif_test(s)) { - int layers = 0; - stbi_uc *u = 0; - stbi_uc *out = 0; - stbi_uc *two_back = 0; - stbi__gif g; - int stride; - int out_size = 0; - int delays_size = 0; - - STBI_NOTUSED(out_size); - STBI_NOTUSED(delays_size); - - memset(&g, 0, sizeof(g)); - if (delays) { - *delays = 0; - } - - do { - u = stbi__gif_load_next(s, &g, comp, req_comp, two_back); - if (u == (stbi_uc *) s) u = 0; // end of animated gif marker - - if (u) { - *x = g.w; - *y = g.h; - ++layers; - stride = g.w * g.h * 4; - - if (out) { - void *tmp = (stbi_uc*) STBI_REALLOC_SIZED( out, out_size, layers * stride ); - if (!tmp) - return stbi__load_gif_main_outofmem(&g, out, delays); - else { - out = (stbi_uc*) tmp; - out_size = layers * stride; - } - - if (delays) { - int *new_delays = (int*) STBI_REALLOC_SIZED( *delays, delays_size, sizeof(int) * layers ); - if (!new_delays) - return stbi__load_gif_main_outofmem(&g, out, delays); - *delays = new_delays; - delays_size = layers * sizeof(int); - } - } else { - out = (stbi_uc*)stbi__malloc( layers * stride ); - if (!out) - return stbi__load_gif_main_outofmem(&g, out, delays); - out_size = layers * stride; - if (delays) { - *delays = (int*) stbi__malloc( layers * sizeof(int) ); - if (!*delays) - return stbi__load_gif_main_outofmem(&g, out, delays); - delays_size = layers * sizeof(int); - } - } - memcpy( out + ((layers - 1) * stride), u, stride ); - if (layers >= 2) { - two_back = out - 2 * stride; - } - - if (delays) { - (*delays)[layers - 1U] = g.delay; - } - } - } while (u != 0); - - // free temp buffer; - STBI_FREE(g.out); - STBI_FREE(g.history); - STBI_FREE(g.background); - - // do the final conversion after loading everything; - if (req_comp && req_comp != 4) - out = stbi__convert_format(out, 4, req_comp, layers * g.w, g.h); - - *z = layers; - return out; - } else { - return stbi__errpuc("not GIF", "Image was not as a gif type."); - } -} - -static void *stbi__gif_load(stbi__context *s, int *x, int *y, int *comp, int req_comp, stbi__result_info *ri) -{ - stbi_uc *u = 0; - stbi__gif g; - memset(&g, 0, sizeof(g)); - STBI_NOTUSED(ri); - - u = stbi__gif_load_next(s, &g, comp, req_comp, 0); - if (u == (stbi_uc *) s) u = 0; // end of animated gif marker - if (u) { - *x = g.w; - *y = g.h; - - // moved conversion to after successful load so that the same - // can be done for multiple frames. - if (req_comp && req_comp != 4) - u = stbi__convert_format(u, 4, req_comp, g.w, g.h); - } else if (g.out) { - // if there was an error and we allocated an image buffer, free it! - STBI_FREE(g.out); - } - - // free buffers needed for multiple frame loading; - STBI_FREE(g.history); - STBI_FREE(g.background); - - return u; -} - -static int stbi__gif_info(stbi__context *s, int *x, int *y, int *comp) -{ - return stbi__gif_info_raw(s,x,y,comp); -} -#endif - -// ************************************************************************************************* -// Radiance RGBE HDR loader -// originally by Nicolas Schulz -#ifndef STBI_NO_HDR -static int stbi__hdr_test_core(stbi__context *s, const char *signature) -{ - int i; - for (i=0; signature[i]; ++i) - if (stbi__get8(s) != signature[i]) - return 0; - stbi__rewind(s); - return 1; -} - -static int stbi__hdr_test(stbi__context* s) -{ - int r = stbi__hdr_test_core(s, "#?RADIANCE\n"); - stbi__rewind(s); - if(!r) { - r = stbi__hdr_test_core(s, "#?RGBE\n"); - stbi__rewind(s); - } - return r; -} - -#define STBI__HDR_BUFLEN 1024 -static char *stbi__hdr_gettoken(stbi__context *z, char *buffer) -{ - int len=0; - char c = '\0'; - - c = (char) stbi__get8(z); - - while (!stbi__at_eof(z) && c != '\n') { - buffer[len++] = c; - if (len == STBI__HDR_BUFLEN-1) { - // flush to end of line - while (!stbi__at_eof(z) && stbi__get8(z) != '\n') - ; - break; - } - c = (char) stbi__get8(z); - } - - buffer[len] = 0; - return buffer; -} - -static void stbi__hdr_convert(float *output, stbi_uc *input, int req_comp) -{ - if ( input[3] != 0 ) { - float f1; - // Exponent - f1 = (float) ldexp(1.0f, input[3] - (int)(128 + 8)); - if (req_comp <= 2) - output[0] = (input[0] + input[1] + input[2]) * f1 / 3; - else { - output[0] = input[0] * f1; - output[1] = input[1] * f1; - output[2] = input[2] * f1; - } - if (req_comp == 2) output[1] = 1; - if (req_comp == 4) output[3] = 1; - } else { - switch (req_comp) { - case 4: output[3] = 1; /* fallthrough */ - case 3: output[0] = output[1] = output[2] = 0; - break; - case 2: output[1] = 1; /* fallthrough */ - case 1: output[0] = 0; - break; - } - } -} - -static float *stbi__hdr_load(stbi__context *s, int *x, int *y, int *comp, int req_comp, stbi__result_info *ri) -{ - char buffer[STBI__HDR_BUFLEN]; - char *token; - int valid = 0; - int width, height; - stbi_uc *scanline; - float *hdr_data; - int len; - unsigned char count, value; - int i, j, k, c1,c2, z; - const char *headerToken; - STBI_NOTUSED(ri); - - // Check identifier - headerToken = stbi__hdr_gettoken(s,buffer); - if (strcmp(headerToken, "#?RADIANCE") != 0 && strcmp(headerToken, "#?RGBE") != 0) - return stbi__errpf("not HDR", "Corrupt HDR image"); - - // Parse header - for(;;) { - token = stbi__hdr_gettoken(s,buffer); - if (token[0] == 0) break; - if (strcmp(token, "FORMAT=32-bit_rle_rgbe") == 0) valid = 1; - } - - if (!valid) return stbi__errpf("unsupported format", "Unsupported HDR format"); - - // Parse width and height - // can't use sscanf() if we're not using stdio! - token = stbi__hdr_gettoken(s,buffer); - if (strncmp(token, "-Y ", 3)) return stbi__errpf("unsupported data layout", "Unsupported HDR format"); - token += 3; - height = (int) strtol(token, &token, 10); - while (*token == ' ') ++token; - if (strncmp(token, "+X ", 3)) return stbi__errpf("unsupported data layout", "Unsupported HDR format"); - token += 3; - width = (int) strtol(token, NULL, 10); - - if (height > STBI_MAX_DIMENSIONS) return stbi__errpf("too large","Very large image (corrupt?)"); - if (width > STBI_MAX_DIMENSIONS) return stbi__errpf("too large","Very large image (corrupt?)"); - - *x = width; - *y = height; - - if (comp) *comp = 3; - if (req_comp == 0) req_comp = 3; - - if (!stbi__mad4sizes_valid(width, height, req_comp, sizeof(float), 0)) - return stbi__errpf("too large", "HDR image is too large"); - - // Read data - hdr_data = (float *) stbi__malloc_mad4(width, height, req_comp, sizeof(float), 0); - if (!hdr_data) - return stbi__errpf("outofmem", "Out of memory"); - - // Load image data - // image data is stored as some number of sca - if ( width < 8 || width >= 32768) { - // Read flat data - for (j=0; j < height; ++j) { - for (i=0; i < width; ++i) { - stbi_uc rgbe[4]; - main_decode_loop: - stbi__getn(s, rgbe, 4); - stbi__hdr_convert(hdr_data + j * width * req_comp + i * req_comp, rgbe, req_comp); - } - } - } else { - // Read RLE-encoded data - scanline = NULL; - - for (j = 0; j < height; ++j) { - c1 = stbi__get8(s); - c2 = stbi__get8(s); - len = stbi__get8(s); - if (c1 != 2 || c2 != 2 || (len & 0x80)) { - // not run-length encoded, so we have to actually use THIS data as a decoded - // pixel (note this can't be a valid pixel--one of RGB must be >= 128) - stbi_uc rgbe[4]; - rgbe[0] = (stbi_uc) c1; - rgbe[1] = (stbi_uc) c2; - rgbe[2] = (stbi_uc) len; - rgbe[3] = (stbi_uc) stbi__get8(s); - stbi__hdr_convert(hdr_data, rgbe, req_comp); - i = 1; - j = 0; - STBI_FREE(scanline); - goto main_decode_loop; // yes, this makes no sense - } - len <<= 8; - len |= stbi__get8(s); - if (len != width) { STBI_FREE(hdr_data); STBI_FREE(scanline); return stbi__errpf("invalid decoded scanline length", "corrupt HDR"); } - if (scanline == NULL) { - scanline = (stbi_uc *) stbi__malloc_mad2(width, 4, 0); - if (!scanline) { - STBI_FREE(hdr_data); - return stbi__errpf("outofmem", "Out of memory"); - } - } - - for (k = 0; k < 4; ++k) { - int nleft; - i = 0; - while ((nleft = width - i) > 0) { - count = stbi__get8(s); - if (count > 128) { - // Run - value = stbi__get8(s); - count -= 128; - if ((count == 0) || (count > nleft)) { STBI_FREE(hdr_data); STBI_FREE(scanline); return stbi__errpf("corrupt", "bad RLE data in HDR"); } - for (z = 0; z < count; ++z) - scanline[i++ * 4 + k] = value; - } else { - // Dump - if ((count == 0) || (count > nleft)) { STBI_FREE(hdr_data); STBI_FREE(scanline); return stbi__errpf("corrupt", "bad RLE data in HDR"); } - for (z = 0; z < count; ++z) - scanline[i++ * 4 + k] = stbi__get8(s); - } - } - } - for (i=0; i < width; ++i) - stbi__hdr_convert(hdr_data+(j*width + i)*req_comp, scanline + i*4, req_comp); - } - if (scanline) - STBI_FREE(scanline); - } - - return hdr_data; -} - -static int stbi__hdr_info(stbi__context *s, int *x, int *y, int *comp) -{ - char buffer[STBI__HDR_BUFLEN]; - char *token; - int valid = 0; - int dummy; - - if (!x) x = &dummy; - if (!y) y = &dummy; - if (!comp) comp = &dummy; - - if (stbi__hdr_test(s) == 0) { - stbi__rewind( s ); - return 0; - } - - for(;;) { - token = stbi__hdr_gettoken(s,buffer); - if (token[0] == 0) break; - if (strcmp(token, "FORMAT=32-bit_rle_rgbe") == 0) valid = 1; - } - - if (!valid) { - stbi__rewind( s ); - return 0; - } - token = stbi__hdr_gettoken(s,buffer); - if (strncmp(token, "-Y ", 3)) { - stbi__rewind( s ); - return 0; - } - token += 3; - *y = (int) strtol(token, &token, 10); - while (*token == ' ') ++token; - if (strncmp(token, "+X ", 3)) { - stbi__rewind( s ); - return 0; - } - token += 3; - *x = (int) strtol(token, NULL, 10); - *comp = 3; - return 1; -} -#endif // STBI_NO_HDR - -#ifndef STBI_NO_BMP -static int stbi__bmp_info(stbi__context *s, int *x, int *y, int *comp) -{ - void *p; - stbi__bmp_data info; - - info.all_a = 255; - p = stbi__bmp_parse_header(s, &info); - if (p == NULL) { - stbi__rewind( s ); - return 0; - } - if (x) *x = s->img_x; - if (y) *y = s->img_y; - if (comp) { - if (info.bpp == 24 && info.ma == 0xff000000) - *comp = 3; - else - *comp = info.ma ? 4 : 3; - } - return 1; -} -#endif - -#ifndef STBI_NO_PSD -static int stbi__psd_info(stbi__context *s, int *x, int *y, int *comp) -{ - int channelCount, dummy, depth; - if (!x) x = &dummy; - if (!y) y = &dummy; - if (!comp) comp = &dummy; - if (stbi__get32be(s) != 0x38425053) { - stbi__rewind( s ); - return 0; - } - if (stbi__get16be(s) != 1) { - stbi__rewind( s ); - return 0; - } - stbi__skip(s, 6); - channelCount = stbi__get16be(s); - if (channelCount < 0 || channelCount > 16) { - stbi__rewind( s ); - return 0; - } - *y = stbi__get32be(s); - *x = stbi__get32be(s); - depth = stbi__get16be(s); - if (depth != 8 && depth != 16) { - stbi__rewind( s ); - return 0; - } - if (stbi__get16be(s) != 3) { - stbi__rewind( s ); - return 0; - } - *comp = 4; - return 1; -} - -static int stbi__psd_is16(stbi__context *s) -{ - int channelCount, depth; - if (stbi__get32be(s) != 0x38425053) { - stbi__rewind( s ); - return 0; - } - if (stbi__get16be(s) != 1) { - stbi__rewind( s ); - return 0; - } - stbi__skip(s, 6); - channelCount = stbi__get16be(s); - if (channelCount < 0 || channelCount > 16) { - stbi__rewind( s ); - return 0; - } - STBI_NOTUSED(stbi__get32be(s)); - STBI_NOTUSED(stbi__get32be(s)); - depth = stbi__get16be(s); - if (depth != 16) { - stbi__rewind( s ); - return 0; - } - return 1; -} -#endif - -#ifndef STBI_NO_PIC -static int stbi__pic_info(stbi__context *s, int *x, int *y, int *comp) -{ - int act_comp=0,num_packets=0,chained,dummy; - stbi__pic_packet packets[10]; - - if (!x) x = &dummy; - if (!y) y = &dummy; - if (!comp) comp = &dummy; - - if (!stbi__pic_is4(s,"\x53\x80\xF6\x34")) { - stbi__rewind(s); - return 0; - } - - stbi__skip(s, 88); - - *x = stbi__get16be(s); - *y = stbi__get16be(s); - if (stbi__at_eof(s)) { - stbi__rewind( s); - return 0; - } - if ( (*x) != 0 && (1 << 28) / (*x) < (*y)) { - stbi__rewind( s ); - return 0; - } - - stbi__skip(s, 8); - - do { - stbi__pic_packet *packet; - - if (num_packets==sizeof(packets)/sizeof(packets[0])) - return 0; - - packet = &packets[num_packets++]; - chained = stbi__get8(s); - packet->size = stbi__get8(s); - packet->type = stbi__get8(s); - packet->channel = stbi__get8(s); - act_comp |= packet->channel; - - if (stbi__at_eof(s)) { - stbi__rewind( s ); - return 0; - } - if (packet->size != 8) { - stbi__rewind( s ); - return 0; - } - } while (chained); - - *comp = (act_comp & 0x10 ? 4 : 3); - - return 1; -} -#endif - -// ************************************************************************************************* -// Portable Gray Map and Portable Pixel Map loader -// by Ken Miller -// -// PGM: http://netpbm.sourceforge.net/doc/pgm.html -// PPM: http://netpbm.sourceforge.net/doc/ppm.html -// -// Known limitations: -// Does not support comments in the header section -// Does not support ASCII image data (formats P2 and P3) - -#ifndef STBI_NO_PNM - -static int stbi__pnm_test(stbi__context *s) -{ - char p, t; - p = (char) stbi__get8(s); - t = (char) stbi__get8(s); - if (p != 'P' || (t != '5' && t != '6')) { - stbi__rewind( s ); - return 0; - } - return 1; -} - -static void *stbi__pnm_load(stbi__context *s, int *x, int *y, int *comp, int req_comp, stbi__result_info *ri) -{ - stbi_uc *out; - STBI_NOTUSED(ri); - - ri->bits_per_channel = stbi__pnm_info(s, (int *)&s->img_x, (int *)&s->img_y, (int *)&s->img_n); - if (ri->bits_per_channel == 0) - return 0; - - if (s->img_y > STBI_MAX_DIMENSIONS) return stbi__errpuc("too large","Very large image (corrupt?)"); - if (s->img_x > STBI_MAX_DIMENSIONS) return stbi__errpuc("too large","Very large image (corrupt?)"); - - *x = s->img_x; - *y = s->img_y; - if (comp) *comp = s->img_n; - - if (!stbi__mad4sizes_valid(s->img_n, s->img_x, s->img_y, ri->bits_per_channel / 8, 0)) - return stbi__errpuc("too large", "PNM too large"); - - out = (stbi_uc *) stbi__malloc_mad4(s->img_n, s->img_x, s->img_y, ri->bits_per_channel / 8, 0); - if (!out) return stbi__errpuc("outofmem", "Out of memory"); - if (!stbi__getn(s, out, s->img_n * s->img_x * s->img_y * (ri->bits_per_channel / 8))) { - STBI_FREE(out); - return stbi__errpuc("bad PNM", "PNM file truncated"); - } - - if (req_comp && req_comp != s->img_n) { - if (ri->bits_per_channel == 16) { - out = (stbi_uc *) stbi__convert_format16((stbi__uint16 *) out, s->img_n, req_comp, s->img_x, s->img_y); - } else { - out = stbi__convert_format(out, s->img_n, req_comp, s->img_x, s->img_y); - } - if (out == NULL) return out; // stbi__convert_format frees input on failure - } - return out; -} - -static int stbi__pnm_isspace(char c) -{ - return c == ' ' || c == '\t' || c == '\n' || c == '\v' || c == '\f' || c == '\r'; -} - -static void stbi__pnm_skip_whitespace(stbi__context *s, char *c) -{ - for (;;) { - while (!stbi__at_eof(s) && stbi__pnm_isspace(*c)) - *c = (char) stbi__get8(s); - - if (stbi__at_eof(s) || *c != '#') - break; - - while (!stbi__at_eof(s) && *c != '\n' && *c != '\r' ) - *c = (char) stbi__get8(s); - } -} - -static int stbi__pnm_isdigit(char c) -{ - return c >= '0' && c <= '9'; -} - -static int stbi__pnm_getinteger(stbi__context *s, char *c) -{ - int value = 0; - - while (!stbi__at_eof(s) && stbi__pnm_isdigit(*c)) { - value = value*10 + (*c - '0'); - *c = (char) stbi__get8(s); - if((value > 214748364) || (value == 214748364 && *c > '7')) - return stbi__err("integer parse overflow", "Parsing an integer in the PPM header overflowed a 32-bit int"); - } - - return value; -} - -static int stbi__pnm_info(stbi__context *s, int *x, int *y, int *comp) -{ - int maxv, dummy; - char c, p, t; - - if (!x) x = &dummy; - if (!y) y = &dummy; - if (!comp) comp = &dummy; - - stbi__rewind(s); - - // Get identifier - p = (char) stbi__get8(s); - t = (char) stbi__get8(s); - if (p != 'P' || (t != '5' && t != '6')) { - stbi__rewind(s); - return 0; - } - - *comp = (t == '6') ? 3 : 1; // '5' is 1-component .pgm; '6' is 3-component .ppm - - c = (char) stbi__get8(s); - stbi__pnm_skip_whitespace(s, &c); - - *x = stbi__pnm_getinteger(s, &c); // read width - if(*x == 0) - return stbi__err("invalid width", "PPM image header had zero or overflowing width"); - stbi__pnm_skip_whitespace(s, &c); - - *y = stbi__pnm_getinteger(s, &c); // read height - if (*y == 0) - return stbi__err("invalid width", "PPM image header had zero or overflowing width"); - stbi__pnm_skip_whitespace(s, &c); - - maxv = stbi__pnm_getinteger(s, &c); // read max value - if (maxv > 65535) - return stbi__err("max value > 65535", "PPM image supports only 8-bit and 16-bit images"); - else if (maxv > 255) - return 16; - else - return 8; -} - -static int stbi__pnm_is16(stbi__context *s) -{ - if (stbi__pnm_info(s, NULL, NULL, NULL) == 16) - return 1; - return 0; -} -#endif - -static int stbi__info_main(stbi__context *s, int *x, int *y, int *comp) -{ - #ifndef STBI_NO_JPEG - if (stbi__jpeg_info(s, x, y, comp)) return 1; - #endif - - #ifndef STBI_NO_PNG - if (stbi__png_info(s, x, y, comp)) return 1; - #endif - - #ifndef STBI_NO_GIF - if (stbi__gif_info(s, x, y, comp)) return 1; - #endif - - #ifndef STBI_NO_BMP - if (stbi__bmp_info(s, x, y, comp)) return 1; - #endif - - #ifndef STBI_NO_PSD - if (stbi__psd_info(s, x, y, comp)) return 1; - #endif - - #ifndef STBI_NO_PIC - if (stbi__pic_info(s, x, y, comp)) return 1; - #endif - - #ifndef STBI_NO_PNM - if (stbi__pnm_info(s, x, y, comp)) return 1; - #endif - - #ifndef STBI_NO_HDR - if (stbi__hdr_info(s, x, y, comp)) return 1; - #endif - - // test tga last because it's a crappy test! - #ifndef STBI_NO_TGA - if (stbi__tga_info(s, x, y, comp)) - return 1; - #endif - return stbi__err("unknown image type", "Image not of any known type, or corrupt"); -} - -static int stbi__is_16_main(stbi__context *s) -{ - #ifndef STBI_NO_PNG - if (stbi__png_is16(s)) return 1; - #endif - - #ifndef STBI_NO_PSD - if (stbi__psd_is16(s)) return 1; - #endif - - #ifndef STBI_NO_PNM - if (stbi__pnm_is16(s)) return 1; - #endif - return 0; -} - -#ifndef STBI_NO_STDIO -STBIDEF int stbi_info(char const *filename, int *x, int *y, int *comp) -{ - FILE *f = stbi__fopen(filename, "rb"); - int result; - if (!f) return stbi__err("can't fopen", "Unable to open file"); - result = stbi_info_from_file(f, x, y, comp); - fclose(f); - return result; -} - -STBIDEF int stbi_info_from_file(FILE *f, int *x, int *y, int *comp) -{ - int r; - stbi__context s; - long pos = ftell(f); - stbi__start_file(&s, f); - r = stbi__info_main(&s,x,y,comp); - fseek(f,pos,SEEK_SET); - return r; -} - -STBIDEF int stbi_is_16_bit(char const *filename) -{ - FILE *f = stbi__fopen(filename, "rb"); - int result; - if (!f) return stbi__err("can't fopen", "Unable to open file"); - result = stbi_is_16_bit_from_file(f); - fclose(f); - return result; -} - -STBIDEF int stbi_is_16_bit_from_file(FILE *f) -{ - int r; - stbi__context s; - long pos = ftell(f); - stbi__start_file(&s, f); - r = stbi__is_16_main(&s); - fseek(f,pos,SEEK_SET); - return r; -} -#endif // !STBI_NO_STDIO - -STBIDEF int stbi_info_from_memory(stbi_uc const *buffer, int len, int *x, int *y, int *comp) -{ - stbi__context s; - stbi__start_mem(&s,buffer,len); - return stbi__info_main(&s,x,y,comp); -} - -STBIDEF int stbi_info_from_callbacks(stbi_io_callbacks const *c, void *user, int *x, int *y, int *comp) -{ - stbi__context s; - stbi__start_callbacks(&s, (stbi_io_callbacks *) c, user); - return stbi__info_main(&s,x,y,comp); -} - -STBIDEF int stbi_is_16_bit_from_memory(stbi_uc const *buffer, int len) -{ - stbi__context s; - stbi__start_mem(&s,buffer,len); - return stbi__is_16_main(&s); -} - -STBIDEF int stbi_is_16_bit_from_callbacks(stbi_io_callbacks const *c, void *user) -{ - stbi__context s; - stbi__start_callbacks(&s, (stbi_io_callbacks *) c, user); - return stbi__is_16_main(&s); -} - -#endif // STB_IMAGE_IMPLEMENTATION - -/* - revision history: - 2.20 (2019-02-07) support utf8 filenames in Windows; fix warnings and platform ifdefs - 2.19 (2018-02-11) fix warning - 2.18 (2018-01-30) fix warnings - 2.17 (2018-01-29) change sbti__shiftsigned to avoid clang -O2 bug - 1-bit BMP - *_is_16_bit api - avoid warnings - 2.16 (2017-07-23) all functions have 16-bit variants; - STBI_NO_STDIO works again; - compilation fixes; - fix rounding in unpremultiply; - optimize vertical flip; - disable raw_len validation; - documentation fixes - 2.15 (2017-03-18) fix png-1,2,4 bug; now all Imagenet JPGs decode; - warning fixes; disable run-time SSE detection on gcc; - uniform handling of optional "return" values; - thread-safe initialization of zlib tables - 2.14 (2017-03-03) remove deprecated STBI_JPEG_OLD; fixes for Imagenet JPGs - 2.13 (2016-11-29) add 16-bit API, only supported for PNG right now - 2.12 (2016-04-02) fix typo in 2.11 PSD fix that caused crashes - 2.11 (2016-04-02) allocate large structures on the stack - remove white matting for transparent PSD - fix reported channel count for PNG & BMP - re-enable SSE2 in non-gcc 64-bit - support RGB-formatted JPEG - read 16-bit PNGs (only as 8-bit) - 2.10 (2016-01-22) avoid warning introduced in 2.09 by STBI_REALLOC_SIZED - 2.09 (2016-01-16) allow comments in PNM files - 16-bit-per-pixel TGA (not bit-per-component) - info() for TGA could break due to .hdr handling - info() for BMP to shares code instead of sloppy parse - can use STBI_REALLOC_SIZED if allocator doesn't support realloc - code cleanup - 2.08 (2015-09-13) fix to 2.07 cleanup, reading RGB PSD as RGBA - 2.07 (2015-09-13) fix compiler warnings - partial animated GIF support - limited 16-bpc PSD support - #ifdef unused functions - bug with < 92 byte PIC,PNM,HDR,TGA - 2.06 (2015-04-19) fix bug where PSD returns wrong '*comp' value - 2.05 (2015-04-19) fix bug in progressive JPEG handling, fix warning - 2.04 (2015-04-15) try to re-enable SIMD on MinGW 64-bit - 2.03 (2015-04-12) extra corruption checking (mmozeiko) - stbi_set_flip_vertically_on_load (nguillemot) - fix NEON support; fix mingw support - 2.02 (2015-01-19) fix incorrect assert, fix warning - 2.01 (2015-01-17) fix various warnings; suppress SIMD on gcc 32-bit without -msse2 - 2.00b (2014-12-25) fix STBI_MALLOC in progressive JPEG - 2.00 (2014-12-25) optimize JPG, including x86 SSE2 & NEON SIMD (ryg) - progressive JPEG (stb) - PGM/PPM support (Ken Miller) - STBI_MALLOC,STBI_REALLOC,STBI_FREE - GIF bugfix -- seemingly never worked - STBI_NO_*, STBI_ONLY_* - 1.48 (2014-12-14) fix incorrectly-named assert() - 1.47 (2014-12-14) 1/2/4-bit PNG support, both direct and paletted (Omar Cornut & stb) - optimize PNG (ryg) - fix bug in interlaced PNG with user-specified channel count (stb) - 1.46 (2014-08-26) - fix broken tRNS chunk (colorkey-style transparency) in non-paletted PNG - 1.45 (2014-08-16) - fix MSVC-ARM internal compiler error by wrapping malloc - 1.44 (2014-08-07) - various warning fixes from Ronny Chevalier - 1.43 (2014-07-15) - fix MSVC-only compiler problem in code changed in 1.42 - 1.42 (2014-07-09) - don't define _CRT_SECURE_NO_WARNINGS (affects user code) - fixes to stbi__cleanup_jpeg path - added STBI_ASSERT to avoid requiring assert.h - 1.41 (2014-06-25) - fix search&replace from 1.36 that messed up comments/error messages - 1.40 (2014-06-22) - fix gcc struct-initialization warning - 1.39 (2014-06-15) - fix to TGA optimization when req_comp != number of components in TGA; - fix to GIF loading because BMP wasn't rewinding (whoops, no GIFs in my test suite) - add support for BMP version 5 (more ignored fields) - 1.38 (2014-06-06) - suppress MSVC warnings on integer casts truncating values - fix accidental rename of 'skip' field of I/O - 1.37 (2014-06-04) - remove duplicate typedef - 1.36 (2014-06-03) - convert to header file single-file library - if de-iphone isn't set, load iphone images color-swapped instead of returning NULL - 1.35 (2014-05-27) - various warnings - fix broken STBI_SIMD path - fix bug where stbi_load_from_file no longer left file pointer in correct place - fix broken non-easy path for 32-bit BMP (possibly never used) - TGA optimization by Arseny Kapoulkine - 1.34 (unknown) - use STBI_NOTUSED in stbi__resample_row_generic(), fix one more leak in tga failure case - 1.33 (2011-07-14) - make stbi_is_hdr work in STBI_NO_HDR (as specified), minor compiler-friendly improvements - 1.32 (2011-07-13) - support for "info" function for all supported filetypes (SpartanJ) - 1.31 (2011-06-20) - a few more leak fixes, bug in PNG handling (SpartanJ) - 1.30 (2011-06-11) - added ability to load files via callbacks to accomidate custom input streams (Ben Wenger) - removed deprecated format-specific test/load functions - removed support for installable file formats (stbi_loader) -- would have been broken for IO callbacks anyway - error cases in bmp and tga give messages and don't leak (Raymond Barbiero, grisha) - fix inefficiency in decoding 32-bit BMP (David Woo) - 1.29 (2010-08-16) - various warning fixes from Aurelien Pocheville - 1.28 (2010-08-01) - fix bug in GIF palette transparency (SpartanJ) - 1.27 (2010-08-01) - cast-to-stbi_uc to fix warnings - 1.26 (2010-07-24) - fix bug in file buffering for PNG reported by SpartanJ - 1.25 (2010-07-17) - refix trans_data warning (Won Chun) - 1.24 (2010-07-12) - perf improvements reading from files on platforms with lock-heavy fgetc() - minor perf improvements for jpeg - deprecated type-specific functions so we'll get feedback if they're needed - attempt to fix trans_data warning (Won Chun) - 1.23 fixed bug in iPhone support - 1.22 (2010-07-10) - removed image *writing* support - stbi_info support from Jetro Lauha - GIF support from Jean-Marc Lienher - iPhone PNG-extensions from James Brown - warning-fixes from Nicolas Schulz and Janez Zemva (i.stbi__err. Janez (U+017D)emva) - 1.21 fix use of 'stbi_uc' in header (reported by jon blow) - 1.20 added support for Softimage PIC, by Tom Seddon - 1.19 bug in interlaced PNG corruption check (found by ryg) - 1.18 (2008-08-02) - fix a threading bug (local mutable static) - 1.17 support interlaced PNG - 1.16 major bugfix - stbi__convert_format converted one too many pixels - 1.15 initialize some fields for thread safety - 1.14 fix threadsafe conversion bug - header-file-only version (#define STBI_HEADER_FILE_ONLY before including) - 1.13 threadsafe - 1.12 const qualifiers in the API - 1.11 Support installable IDCT, colorspace conversion routines - 1.10 Fixes for 64-bit (don't use "unsigned long") - optimized upsampling by Fabian "ryg" Giesen - 1.09 Fix format-conversion for PSD code (bad global variables!) - 1.08 Thatcher Ulrich's PSD code integrated by Nicolas Schulz - 1.07 attempt to fix C++ warning/errors again - 1.06 attempt to fix C++ warning/errors again - 1.05 fix TGA loading to return correct *comp and use good luminance calc - 1.04 default float alpha is 1, not 255; use 'void *' for stbi_image_free - 1.03 bugfixes to STBI_NO_STDIO, STBI_NO_HDR - 1.02 support for (subset of) HDR files, float interface for preferred access to them - 1.01 fix bug: possible bug in handling right-side up bmps... not sure - fix bug: the stbi__bmp_load() and stbi__tga_load() functions didn't work at all - 1.00 interface to zlib that skips zlib header - 0.99 correct handling of alpha in palette - 0.98 TGA loader by lonesock; dynamically add loaders (untested) - 0.97 jpeg errors on too large a file; also catch another malloc failure - 0.96 fix detection of invalid v value - particleman@mollyrocket forum - 0.95 during header scan, seek to markers in case of padding - 0.94 STBI_NO_STDIO to disable stdio usage; rename all #defines the same - 0.93 handle jpegtran output; verbose errors - 0.92 read 4,8,16,24,32-bit BMP files of several formats - 0.91 output 24-bit Windows 3.0 BMP files - 0.90 fix a few more warnings; bump version number to approach 1.0 - 0.61 bugfixes due to Marc LeBlanc, Christopher Lloyd - 0.60 fix compiling as c++ - 0.59 fix warnings: merge Dave Moore's -Wall fixes - 0.58 fix bug: zlib uncompressed mode len/nlen was wrong endian - 0.57 fix bug: jpg last huffman symbol before marker was >9 bits but less than 16 available - 0.56 fix bug: zlib uncompressed mode len vs. nlen - 0.55 fix bug: restart_interval not initialized to 0 - 0.54 allow NULL for 'int *comp' - 0.53 fix bug in png 3->4; speedup png decoding - 0.52 png handles req_comp=3,4 directly; minor cleanup; jpeg comments - 0.51 obey req_comp requests, 1-component jpegs return as 1-component, - on 'test' only check type, not whether we support this variant - 0.50 (2006-11-19) - first released version -*/ - - -/* ------------------------------------------------------------------------------- -This software is available under 2 licenses -- choose whichever you prefer. ------------------------------------------------------------------------------- -ALTERNATIVE A - MIT License -Copyright (c) 2017 Sean Barrett -Permission is hereby granted, free of charge, to any person obtaining a copy of -this software and associated documentation files (the "Software"), to deal in -the Software without restriction, including without limitation the rights to -use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies -of the Software, and to permit persons to whom the Software is furnished to do -so, subject to the following conditions: -The above copyright notice and this permission notice shall be included in all -copies or substantial portions of the Software. -THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR -IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, -FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE -AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER -LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, -OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE -SOFTWARE. ------------------------------------------------------------------------------- -ALTERNATIVE B - Public Domain (www.unlicense.org) -This is free and unencumbered software released into the public domain. -Anyone is free to copy, modify, publish, use, compile, sell, or distribute this -software, either in source code form or as a compiled binary, for any purpose, -commercial or non-commercial, and by any means. -In jurisdictions that recognize copyright laws, the author or authors of this -software dedicate any and all copyright interest in the software to the public -domain. We make this dedication for the benefit of the public at large and to -the detriment of our heirs and successors. We intend this dedication to be an -overt act of relinquishment in perpetuity of all present and future rights to -this software under copyright law. -THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR -IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, -FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE -AUTHORS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN -ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION -WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. ------------------------------------------------------------------------------- -*/ diff --git a/third_party/stb_image_write.h b/third_party/stb_image_write.h deleted file mode 100644 index e4b32ed..0000000 --- a/third_party/stb_image_write.h +++ /dev/null @@ -1,1724 +0,0 @@ -/* stb_image_write - v1.16 - public domain - http://nothings.org/stb - writes out PNG/BMP/TGA/JPEG/HDR images to C stdio - Sean Barrett 2010-2015 - no warranty implied; use at your own risk - - Before #including, - - #define STB_IMAGE_WRITE_IMPLEMENTATION - - in the file that you want to have the implementation. - - Will probably not work correctly with strict-aliasing optimizations. - -ABOUT: - - This header file is a library for writing images to C stdio or a callback. - - The PNG output is not optimal; it is 20-50% larger than the file - written by a decent optimizing implementation; though providing a custom - zlib compress function (see STBIW_ZLIB_COMPRESS) can mitigate that. - This library is designed for source code compactness and simplicity, - not optimal image file size or run-time performance. - -BUILDING: - - You can #define STBIW_ASSERT(x) before the #include to avoid using assert.h. - You can #define STBIW_MALLOC(), STBIW_REALLOC(), and STBIW_FREE() to replace - malloc,realloc,free. - You can #define STBIW_MEMMOVE() to replace memmove() - You can #define STBIW_ZLIB_COMPRESS to use a custom zlib-style compress function - for PNG compression (instead of the builtin one), it must have the following signature: - unsigned char * my_compress(unsigned char *data, int data_len, int *out_len, int quality); - The returned data will be freed with STBIW_FREE() (free() by default), - so it must be heap allocated with STBIW_MALLOC() (malloc() by default), - -UNICODE: - - If compiling for Windows and you wish to use Unicode filenames, compile - with - #define STBIW_WINDOWS_UTF8 - and pass utf8-encoded filenames. Call stbiw_convert_wchar_to_utf8 to convert - Windows wchar_t filenames to utf8. - -USAGE: - - There are five functions, one for each image file format: - - int stbi_write_png(char const *filename, int w, int h, int comp, const void *data, int stride_in_bytes); - int stbi_write_bmp(char const *filename, int w, int h, int comp, const void *data); - int stbi_write_tga(char const *filename, int w, int h, int comp, const void *data); - int stbi_write_jpg(char const *filename, int w, int h, int comp, const void *data, int quality); - int stbi_write_hdr(char const *filename, int w, int h, int comp, const float *data); - - void stbi_flip_vertically_on_write(int flag); // flag is non-zero to flip data vertically - - There are also five equivalent functions that use an arbitrary write function. You are - expected to open/close your file-equivalent before and after calling these: - - int stbi_write_png_to_func(stbi_write_func *func, void *context, int w, int h, int comp, const void *data, int stride_in_bytes); - int stbi_write_bmp_to_func(stbi_write_func *func, void *context, int w, int h, int comp, const void *data); - int stbi_write_tga_to_func(stbi_write_func *func, void *context, int w, int h, int comp, const void *data); - int stbi_write_hdr_to_func(stbi_write_func *func, void *context, int w, int h, int comp, const float *data); - int stbi_write_jpg_to_func(stbi_write_func *func, void *context, int x, int y, int comp, const void *data, int quality); - - where the callback is: - void stbi_write_func(void *context, void *data, int size); - - You can configure it with these global variables: - int stbi_write_tga_with_rle; // defaults to true; set to 0 to disable RLE - int stbi_write_png_compression_level; // defaults to 8; set to higher for more compression - int stbi_write_force_png_filter; // defaults to -1; set to 0..5 to force a filter mode - - - You can define STBI_WRITE_NO_STDIO to disable the file variant of these - functions, so the library will not use stdio.h at all. However, this will - also disable HDR writing, because it requires stdio for formatted output. - - Each function returns 0 on failure and non-0 on success. - - The functions create an image file defined by the parameters. The image - is a rectangle of pixels stored from left-to-right, top-to-bottom. - Each pixel contains 'comp' channels of data stored interleaved with 8-bits - per channel, in the following order: 1=Y, 2=YA, 3=RGB, 4=RGBA. (Y is - monochrome color.) The rectangle is 'w' pixels wide and 'h' pixels tall. - The *data pointer points to the first byte of the top-left-most pixel. - For PNG, "stride_in_bytes" is the distance in bytes from the first byte of - a row of pixels to the first byte of the next row of pixels. - - PNG creates output files with the same number of components as the input. - The BMP format expands Y to RGB in the file format and does not - output alpha. - - PNG supports writing rectangles of data even when the bytes storing rows of - data are not consecutive in memory (e.g. sub-rectangles of a larger image), - by supplying the stride between the beginning of adjacent rows. The other - formats do not. (Thus you cannot write a native-format BMP through the BMP - writer, both because it is in BGR order and because it may have padding - at the end of the line.) - - PNG allows you to set the deflate compression level by setting the global - variable 'stbi_write_png_compression_level' (it defaults to 8). - - HDR expects linear float data. Since the format is always 32-bit rgb(e) - data, alpha (if provided) is discarded, and for monochrome data it is - replicated across all three channels. - - TGA supports RLE or non-RLE compressed data. To use non-RLE-compressed - data, set the global variable 'stbi_write_tga_with_rle' to 0. - - JPEG does ignore alpha channels in input data; quality is between 1 and 100. - Higher quality looks better but results in a bigger image. - JPEG baseline (no JPEG progressive). - -CREDITS: - - - Sean Barrett - PNG/BMP/TGA - Baldur Karlsson - HDR - Jean-Sebastien Guay - TGA monochrome - Tim Kelsey - misc enhancements - Alan Hickman - TGA RLE - Emmanuel Julien - initial file IO callback implementation - Jon Olick - original jo_jpeg.cpp code - Daniel Gibson - integrate JPEG, allow external zlib - Aarni Koskela - allow choosing PNG filter - - bugfixes: - github:Chribba - Guillaume Chereau - github:jry2 - github:romigrou - Sergio Gonzalez - Jonas Karlsson - Filip Wasil - Thatcher Ulrich - github:poppolopoppo - Patrick Boettcher - github:xeekworx - Cap Petschulat - Simon Rodriguez - Ivan Tikhonov - github:ignotion - Adam Schackart - Andrew Kensler - -LICENSE - - See end of file for license information. - -*/ - -#ifndef INCLUDE_STB_IMAGE_WRITE_H -#define INCLUDE_STB_IMAGE_WRITE_H - -#include - -// if STB_IMAGE_WRITE_STATIC causes problems, try defining STBIWDEF to 'inline' or 'static inline' -#ifndef STBIWDEF -#ifdef STB_IMAGE_WRITE_STATIC -#define STBIWDEF static -#else -#ifdef __cplusplus -#define STBIWDEF extern "C" -#else -#define STBIWDEF extern -#endif -#endif -#endif - -#ifndef STB_IMAGE_WRITE_STATIC // C++ forbids static forward declarations -STBIWDEF int stbi_write_tga_with_rle; -STBIWDEF int stbi_write_png_compression_level; -STBIWDEF int stbi_write_force_png_filter; -#endif - -#ifndef STBI_WRITE_NO_STDIO -STBIWDEF int stbi_write_png(char const *filename, int w, int h, int comp, const void *data, int stride_in_bytes); -STBIWDEF int stbi_write_bmp(char const *filename, int w, int h, int comp, const void *data); -STBIWDEF int stbi_write_tga(char const *filename, int w, int h, int comp, const void *data); -STBIWDEF int stbi_write_hdr(char const *filename, int w, int h, int comp, const float *data); -STBIWDEF int stbi_write_jpg(char const *filename, int x, int y, int comp, const void *data, int quality); - -#ifdef STBIW_WINDOWS_UTF8 -STBIWDEF int stbiw_convert_wchar_to_utf8(char *buffer, size_t bufferlen, const wchar_t* input); -#endif -#endif - -typedef void stbi_write_func(void *context, void *data, int size); - -STBIWDEF int stbi_write_png_to_func(stbi_write_func *func, void *context, int w, int h, int comp, const void *data, int stride_in_bytes); -STBIWDEF int stbi_write_bmp_to_func(stbi_write_func *func, void *context, int w, int h, int comp, const void *data); -STBIWDEF int stbi_write_tga_to_func(stbi_write_func *func, void *context, int w, int h, int comp, const void *data); -STBIWDEF int stbi_write_hdr_to_func(stbi_write_func *func, void *context, int w, int h, int comp, const float *data); -STBIWDEF int stbi_write_jpg_to_func(stbi_write_func *func, void *context, int x, int y, int comp, const void *data, int quality); - -STBIWDEF void stbi_flip_vertically_on_write(int flip_boolean); - -#endif//INCLUDE_STB_IMAGE_WRITE_H - -#ifdef STB_IMAGE_WRITE_IMPLEMENTATION - -#ifdef _WIN32 - #ifndef _CRT_SECURE_NO_WARNINGS - #define _CRT_SECURE_NO_WARNINGS - #endif - #ifndef _CRT_NONSTDC_NO_DEPRECATE - #define _CRT_NONSTDC_NO_DEPRECATE - #endif -#endif - -#ifndef STBI_WRITE_NO_STDIO -#include -#endif // STBI_WRITE_NO_STDIO - -#include -#include -#include -#include - -#if defined(STBIW_MALLOC) && defined(STBIW_FREE) && (defined(STBIW_REALLOC) || defined(STBIW_REALLOC_SIZED)) -// ok -#elif !defined(STBIW_MALLOC) && !defined(STBIW_FREE) && !defined(STBIW_REALLOC) && !defined(STBIW_REALLOC_SIZED) -// ok -#else -#error "Must define all or none of STBIW_MALLOC, STBIW_FREE, and STBIW_REALLOC (or STBIW_REALLOC_SIZED)." -#endif - -#ifndef STBIW_MALLOC -#define STBIW_MALLOC(sz) malloc(sz) -#define STBIW_REALLOC(p,newsz) realloc(p,newsz) -#define STBIW_FREE(p) free(p) -#endif - -#ifndef STBIW_REALLOC_SIZED -#define STBIW_REALLOC_SIZED(p,oldsz,newsz) STBIW_REALLOC(p,newsz) -#endif - - -#ifndef STBIW_MEMMOVE -#define STBIW_MEMMOVE(a,b,sz) memmove(a,b,sz) -#endif - - -#ifndef STBIW_ASSERT -#include -#define STBIW_ASSERT(x) assert(x) -#endif - -#define STBIW_UCHAR(x) (unsigned char) ((x) & 0xff) - -#ifdef STB_IMAGE_WRITE_STATIC -static int stbi_write_png_compression_level = 8; -static int stbi_write_tga_with_rle = 1; -static int stbi_write_force_png_filter = -1; -#else -int stbi_write_png_compression_level = 8; -int stbi_write_tga_with_rle = 1; -int stbi_write_force_png_filter = -1; -#endif - -static int stbi__flip_vertically_on_write = 0; - -STBIWDEF void stbi_flip_vertically_on_write(int flag) -{ - stbi__flip_vertically_on_write = flag; -} - -typedef struct -{ - stbi_write_func *func; - void *context; - unsigned char buffer[64]; - int buf_used; -} stbi__write_context; - -// initialize a callback-based context -static void stbi__start_write_callbacks(stbi__write_context *s, stbi_write_func *c, void *context) -{ - s->func = c; - s->context = context; -} - -#ifndef STBI_WRITE_NO_STDIO - -static void stbi__stdio_write(void *context, void *data, int size) -{ - fwrite(data,1,size,(FILE*) context); -} - -#if defined(_WIN32) && defined(STBIW_WINDOWS_UTF8) -#ifdef __cplusplus -#define STBIW_EXTERN extern "C" -#else -#define STBIW_EXTERN extern -#endif -STBIW_EXTERN __declspec(dllimport) int __stdcall MultiByteToWideChar(unsigned int cp, unsigned long flags, const char *str, int cbmb, wchar_t *widestr, int cchwide); -STBIW_EXTERN __declspec(dllimport) int __stdcall WideCharToMultiByte(unsigned int cp, unsigned long flags, const wchar_t *widestr, int cchwide, char *str, int cbmb, const char *defchar, int *used_default); - -STBIWDEF int stbiw_convert_wchar_to_utf8(char *buffer, size_t bufferlen, const wchar_t* input) -{ - return WideCharToMultiByte(65001 /* UTF8 */, 0, input, -1, buffer, (int) bufferlen, NULL, NULL); -} -#endif - -static FILE *stbiw__fopen(char const *filename, char const *mode) -{ - FILE *f; -#if defined(_WIN32) && defined(STBIW_WINDOWS_UTF8) - wchar_t wMode[64]; - wchar_t wFilename[1024]; - if (0 == MultiByteToWideChar(65001 /* UTF8 */, 0, filename, -1, wFilename, sizeof(wFilename)/sizeof(*wFilename))) - return 0; - - if (0 == MultiByteToWideChar(65001 /* UTF8 */, 0, mode, -1, wMode, sizeof(wMode)/sizeof(*wMode))) - return 0; - -#if defined(_MSC_VER) && _MSC_VER >= 1400 - if (0 != _wfopen_s(&f, wFilename, wMode)) - f = 0; -#else - f = _wfopen(wFilename, wMode); -#endif - -#elif defined(_MSC_VER) && _MSC_VER >= 1400 - if (0 != fopen_s(&f, filename, mode)) - f=0; -#else - f = fopen(filename, mode); -#endif - return f; -} - -static int stbi__start_write_file(stbi__write_context *s, const char *filename) -{ - FILE *f = stbiw__fopen(filename, "wb"); - stbi__start_write_callbacks(s, stbi__stdio_write, (void *) f); - return f != NULL; -} - -static void stbi__end_write_file(stbi__write_context *s) -{ - fclose((FILE *)s->context); -} - -#endif // !STBI_WRITE_NO_STDIO - -typedef unsigned int stbiw_uint32; -typedef int stb_image_write_test[sizeof(stbiw_uint32)==4 ? 1 : -1]; - -static void stbiw__writefv(stbi__write_context *s, const char *fmt, va_list v) -{ - while (*fmt) { - switch (*fmt++) { - case ' ': break; - case '1': { unsigned char x = STBIW_UCHAR(va_arg(v, int)); - s->func(s->context,&x,1); - break; } - case '2': { int x = va_arg(v,int); - unsigned char b[2]; - b[0] = STBIW_UCHAR(x); - b[1] = STBIW_UCHAR(x>>8); - s->func(s->context,b,2); - break; } - case '4': { stbiw_uint32 x = va_arg(v,int); - unsigned char b[4]; - b[0]=STBIW_UCHAR(x); - b[1]=STBIW_UCHAR(x>>8); - b[2]=STBIW_UCHAR(x>>16); - b[3]=STBIW_UCHAR(x>>24); - s->func(s->context,b,4); - break; } - default: - STBIW_ASSERT(0); - return; - } - } -} - -static void stbiw__writef(stbi__write_context *s, const char *fmt, ...) -{ - va_list v; - va_start(v, fmt); - stbiw__writefv(s, fmt, v); - va_end(v); -} - -static void stbiw__write_flush(stbi__write_context *s) -{ - if (s->buf_used) { - s->func(s->context, &s->buffer, s->buf_used); - s->buf_used = 0; - } -} - -static void stbiw__putc(stbi__write_context *s, unsigned char c) -{ - s->func(s->context, &c, 1); -} - -static void stbiw__write1(stbi__write_context *s, unsigned char a) -{ - if ((size_t)s->buf_used + 1 > sizeof(s->buffer)) - stbiw__write_flush(s); - s->buffer[s->buf_used++] = a; -} - -static void stbiw__write3(stbi__write_context *s, unsigned char a, unsigned char b, unsigned char c) -{ - int n; - if ((size_t)s->buf_used + 3 > sizeof(s->buffer)) - stbiw__write_flush(s); - n = s->buf_used; - s->buf_used = n+3; - s->buffer[n+0] = a; - s->buffer[n+1] = b; - s->buffer[n+2] = c; -} - -static void stbiw__write_pixel(stbi__write_context *s, int rgb_dir, int comp, int write_alpha, int expand_mono, unsigned char *d) -{ - unsigned char bg[3] = { 255, 0, 255}, px[3]; - int k; - - if (write_alpha < 0) - stbiw__write1(s, d[comp - 1]); - - switch (comp) { - case 2: // 2 pixels = mono + alpha, alpha is written separately, so same as 1-channel case - case 1: - if (expand_mono) - stbiw__write3(s, d[0], d[0], d[0]); // monochrome bmp - else - stbiw__write1(s, d[0]); // monochrome TGA - break; - case 4: - if (!write_alpha) { - // composite against pink background - for (k = 0; k < 3; ++k) - px[k] = bg[k] + ((d[k] - bg[k]) * d[3]) / 255; - stbiw__write3(s, px[1 - rgb_dir], px[1], px[1 + rgb_dir]); - break; - } - /* FALLTHROUGH */ - case 3: - stbiw__write3(s, d[1 - rgb_dir], d[1], d[1 + rgb_dir]); - break; - } - if (write_alpha > 0) - stbiw__write1(s, d[comp - 1]); -} - -static void stbiw__write_pixels(stbi__write_context *s, int rgb_dir, int vdir, int x, int y, int comp, void *data, int write_alpha, int scanline_pad, int expand_mono) -{ - stbiw_uint32 zero = 0; - int i,j, j_end; - - if (y <= 0) - return; - - if (stbi__flip_vertically_on_write) - vdir *= -1; - - if (vdir < 0) { - j_end = -1; j = y-1; - } else { - j_end = y; j = 0; - } - - for (; j != j_end; j += vdir) { - for (i=0; i < x; ++i) { - unsigned char *d = (unsigned char *) data + (j*x+i)*comp; - stbiw__write_pixel(s, rgb_dir, comp, write_alpha, expand_mono, d); - } - stbiw__write_flush(s); - s->func(s->context, &zero, scanline_pad); - } -} - -static int stbiw__outfile(stbi__write_context *s, int rgb_dir, int vdir, int x, int y, int comp, int expand_mono, void *data, int alpha, int pad, const char *fmt, ...) -{ - if (y < 0 || x < 0) { - return 0; - } else { - va_list v; - va_start(v, fmt); - stbiw__writefv(s, fmt, v); - va_end(v); - stbiw__write_pixels(s,rgb_dir,vdir,x,y,comp,data,alpha,pad, expand_mono); - return 1; - } -} - -static int stbi_write_bmp_core(stbi__write_context *s, int x, int y, int comp, const void *data) -{ - if (comp != 4) { - // write RGB bitmap - int pad = (-x*3) & 3; - return stbiw__outfile(s,-1,-1,x,y,comp,1,(void *) data,0,pad, - "11 4 22 4" "4 44 22 444444", - 'B', 'M', 14+40+(x*3+pad)*y, 0,0, 14+40, // file header - 40, x,y, 1,24, 0,0,0,0,0,0); // bitmap header - } else { - // RGBA bitmaps need a v4 header - // use BI_BITFIELDS mode with 32bpp and alpha mask - // (straight BI_RGB with alpha mask doesn't work in most readers) - return stbiw__outfile(s,-1,-1,x,y,comp,1,(void *)data,1,0, - "11 4 22 4" "4 44 22 444444 4444 4 444 444 444 444", - 'B', 'M', 14+108+x*y*4, 0, 0, 14+108, // file header - 108, x,y, 1,32, 3,0,0,0,0,0, 0xff0000,0xff00,0xff,0xff000000u, 0, 0,0,0, 0,0,0, 0,0,0, 0,0,0); // bitmap V4 header - } -} - -STBIWDEF int stbi_write_bmp_to_func(stbi_write_func *func, void *context, int x, int y, int comp, const void *data) -{ - stbi__write_context s = { 0 }; - stbi__start_write_callbacks(&s, func, context); - return stbi_write_bmp_core(&s, x, y, comp, data); -} - -#ifndef STBI_WRITE_NO_STDIO -STBIWDEF int stbi_write_bmp(char const *filename, int x, int y, int comp, const void *data) -{ - stbi__write_context s = { 0 }; - if (stbi__start_write_file(&s,filename)) { - int r = stbi_write_bmp_core(&s, x, y, comp, data); - stbi__end_write_file(&s); - return r; - } else - return 0; -} -#endif //!STBI_WRITE_NO_STDIO - -static int stbi_write_tga_core(stbi__write_context *s, int x, int y, int comp, void *data) -{ - int has_alpha = (comp == 2 || comp == 4); - int colorbytes = has_alpha ? comp-1 : comp; - int format = colorbytes < 2 ? 3 : 2; // 3 color channels (RGB/RGBA) = 2, 1 color channel (Y/YA) = 3 - - if (y < 0 || x < 0) - return 0; - - if (!stbi_write_tga_with_rle) { - return stbiw__outfile(s, -1, -1, x, y, comp, 0, (void *) data, has_alpha, 0, - "111 221 2222 11", 0, 0, format, 0, 0, 0, 0, 0, x, y, (colorbytes + has_alpha) * 8, has_alpha * 8); - } else { - int i,j,k; - int jend, jdir; - - stbiw__writef(s, "111 221 2222 11", 0,0,format+8, 0,0,0, 0,0,x,y, (colorbytes + has_alpha) * 8, has_alpha * 8); - - if (stbi__flip_vertically_on_write) { - j = 0; - jend = y; - jdir = 1; - } else { - j = y-1; - jend = -1; - jdir = -1; - } - for (; j != jend; j += jdir) { - unsigned char *row = (unsigned char *) data + j * x * comp; - int len; - - for (i = 0; i < x; i += len) { - unsigned char *begin = row + i * comp; - int diff = 1; - len = 1; - - if (i < x - 1) { - ++len; - diff = memcmp(begin, row + (i + 1) * comp, comp); - if (diff) { - const unsigned char *prev = begin; - for (k = i + 2; k < x && len < 128; ++k) { - if (memcmp(prev, row + k * comp, comp)) { - prev += comp; - ++len; - } else { - --len; - break; - } - } - } else { - for (k = i + 2; k < x && len < 128; ++k) { - if (!memcmp(begin, row + k * comp, comp)) { - ++len; - } else { - break; - } - } - } - } - - if (diff) { - unsigned char header = STBIW_UCHAR(len - 1); - stbiw__write1(s, header); - for (k = 0; k < len; ++k) { - stbiw__write_pixel(s, -1, comp, has_alpha, 0, begin + k * comp); - } - } else { - unsigned char header = STBIW_UCHAR(len - 129); - stbiw__write1(s, header); - stbiw__write_pixel(s, -1, comp, has_alpha, 0, begin); - } - } - } - stbiw__write_flush(s); - } - return 1; -} - -STBIWDEF int stbi_write_tga_to_func(stbi_write_func *func, void *context, int x, int y, int comp, const void *data) -{ - stbi__write_context s = { 0 }; - stbi__start_write_callbacks(&s, func, context); - return stbi_write_tga_core(&s, x, y, comp, (void *) data); -} - -#ifndef STBI_WRITE_NO_STDIO -STBIWDEF int stbi_write_tga(char const *filename, int x, int y, int comp, const void *data) -{ - stbi__write_context s = { 0 }; - if (stbi__start_write_file(&s,filename)) { - int r = stbi_write_tga_core(&s, x, y, comp, (void *) data); - stbi__end_write_file(&s); - return r; - } else - return 0; -} -#endif - -// ************************************************************************************************* -// Radiance RGBE HDR writer -// by Baldur Karlsson - -#define stbiw__max(a, b) ((a) > (b) ? (a) : (b)) - -#ifndef STBI_WRITE_NO_STDIO - -static void stbiw__linear_to_rgbe(unsigned char *rgbe, float *linear) -{ - int exponent; - float maxcomp = stbiw__max(linear[0], stbiw__max(linear[1], linear[2])); - - if (maxcomp < 1e-32f) { - rgbe[0] = rgbe[1] = rgbe[2] = rgbe[3] = 0; - } else { - float normalize = (float) frexp(maxcomp, &exponent) * 256.0f/maxcomp; - - rgbe[0] = (unsigned char)(linear[0] * normalize); - rgbe[1] = (unsigned char)(linear[1] * normalize); - rgbe[2] = (unsigned char)(linear[2] * normalize); - rgbe[3] = (unsigned char)(exponent + 128); - } -} - -static void stbiw__write_run_data(stbi__write_context *s, int length, unsigned char databyte) -{ - unsigned char lengthbyte = STBIW_UCHAR(length+128); - STBIW_ASSERT(length+128 <= 255); - s->func(s->context, &lengthbyte, 1); - s->func(s->context, &databyte, 1); -} - -static void stbiw__write_dump_data(stbi__write_context *s, int length, unsigned char *data) -{ - unsigned char lengthbyte = STBIW_UCHAR(length); - STBIW_ASSERT(length <= 128); // inconsistent with spec but consistent with official code - s->func(s->context, &lengthbyte, 1); - s->func(s->context, data, length); -} - -static void stbiw__write_hdr_scanline(stbi__write_context *s, int width, int ncomp, unsigned char *scratch, float *scanline) -{ - unsigned char scanlineheader[4] = { 2, 2, 0, 0 }; - unsigned char rgbe[4]; - float linear[3]; - int x; - - scanlineheader[2] = (width&0xff00)>>8; - scanlineheader[3] = (width&0x00ff); - - /* skip RLE for images too small or large */ - if (width < 8 || width >= 32768) { - for (x=0; x < width; x++) { - switch (ncomp) { - case 4: /* fallthrough */ - case 3: linear[2] = scanline[x*ncomp + 2]; - linear[1] = scanline[x*ncomp + 1]; - linear[0] = scanline[x*ncomp + 0]; - break; - default: - linear[0] = linear[1] = linear[2] = scanline[x*ncomp + 0]; - break; - } - stbiw__linear_to_rgbe(rgbe, linear); - s->func(s->context, rgbe, 4); - } - } else { - int c,r; - /* encode into scratch buffer */ - for (x=0; x < width; x++) { - switch(ncomp) { - case 4: /* fallthrough */ - case 3: linear[2] = scanline[x*ncomp + 2]; - linear[1] = scanline[x*ncomp + 1]; - linear[0] = scanline[x*ncomp + 0]; - break; - default: - linear[0] = linear[1] = linear[2] = scanline[x*ncomp + 0]; - break; - } - stbiw__linear_to_rgbe(rgbe, linear); - scratch[x + width*0] = rgbe[0]; - scratch[x + width*1] = rgbe[1]; - scratch[x + width*2] = rgbe[2]; - scratch[x + width*3] = rgbe[3]; - } - - s->func(s->context, scanlineheader, 4); - - /* RLE each component separately */ - for (c=0; c < 4; c++) { - unsigned char *comp = &scratch[width*c]; - - x = 0; - while (x < width) { - // find first run - r = x; - while (r+2 < width) { - if (comp[r] == comp[r+1] && comp[r] == comp[r+2]) - break; - ++r; - } - if (r+2 >= width) - r = width; - // dump up to first run - while (x < r) { - int len = r-x; - if (len > 128) len = 128; - stbiw__write_dump_data(s, len, &comp[x]); - x += len; - } - // if there's a run, output it - if (r+2 < width) { // same test as what we break out of in search loop, so only true if we break'd - // find next byte after run - while (r < width && comp[r] == comp[x]) - ++r; - // output run up to r - while (x < r) { - int len = r-x; - if (len > 127) len = 127; - stbiw__write_run_data(s, len, comp[x]); - x += len; - } - } - } - } - } -} - -static int stbi_write_hdr_core(stbi__write_context *s, int x, int y, int comp, float *data) -{ - if (y <= 0 || x <= 0 || data == NULL) - return 0; - else { - // Each component is stored separately. Allocate scratch space for full output scanline. - unsigned char *scratch = (unsigned char *) STBIW_MALLOC(x*4); - int i, len; - char buffer[128]; - char header[] = "#?RADIANCE\n# Written by stb_image_write.h\nFORMAT=32-bit_rle_rgbe\n"; - s->func(s->context, header, sizeof(header)-1); - -#ifdef __STDC_LIB_EXT1__ - len = sprintf_s(buffer, sizeof(buffer), "EXPOSURE= 1.0000000000000\n\n-Y %d +X %d\n", y, x); -#else - len = sprintf(buffer, "EXPOSURE= 1.0000000000000\n\n-Y %d +X %d\n", y, x); -#endif - s->func(s->context, buffer, len); - - for(i=0; i < y; i++) - stbiw__write_hdr_scanline(s, x, comp, scratch, data + comp*x*(stbi__flip_vertically_on_write ? y-1-i : i)); - STBIW_FREE(scratch); - return 1; - } -} - -STBIWDEF int stbi_write_hdr_to_func(stbi_write_func *func, void *context, int x, int y, int comp, const float *data) -{ - stbi__write_context s = { 0 }; - stbi__start_write_callbacks(&s, func, context); - return stbi_write_hdr_core(&s, x, y, comp, (float *) data); -} - -STBIWDEF int stbi_write_hdr(char const *filename, int x, int y, int comp, const float *data) -{ - stbi__write_context s = { 0 }; - if (stbi__start_write_file(&s,filename)) { - int r = stbi_write_hdr_core(&s, x, y, comp, (float *) data); - stbi__end_write_file(&s); - return r; - } else - return 0; -} -#endif // STBI_WRITE_NO_STDIO - - -////////////////////////////////////////////////////////////////////////////// -// -// PNG writer -// - -#ifndef STBIW_ZLIB_COMPRESS -// stretchy buffer; stbiw__sbpush() == vector<>::push_back() -- stbiw__sbcount() == vector<>::size() -#define stbiw__sbraw(a) ((int *) (void *) (a) - 2) -#define stbiw__sbm(a) stbiw__sbraw(a)[0] -#define stbiw__sbn(a) stbiw__sbraw(a)[1] - -#define stbiw__sbneedgrow(a,n) ((a)==0 || stbiw__sbn(a)+n >= stbiw__sbm(a)) -#define stbiw__sbmaybegrow(a,n) (stbiw__sbneedgrow(a,(n)) ? stbiw__sbgrow(a,n) : 0) -#define stbiw__sbgrow(a,n) stbiw__sbgrowf((void **) &(a), (n), sizeof(*(a))) - -#define stbiw__sbpush(a, v) (stbiw__sbmaybegrow(a,1), (a)[stbiw__sbn(a)++] = (v)) -#define stbiw__sbcount(a) ((a) ? stbiw__sbn(a) : 0) -#define stbiw__sbfree(a) ((a) ? STBIW_FREE(stbiw__sbraw(a)),0 : 0) - -static void *stbiw__sbgrowf(void **arr, int increment, int itemsize) -{ - int m = *arr ? 2*stbiw__sbm(*arr)+increment : increment+1; - void *p = STBIW_REALLOC_SIZED(*arr ? stbiw__sbraw(*arr) : 0, *arr ? (stbiw__sbm(*arr)*itemsize + sizeof(int)*2) : 0, itemsize * m + sizeof(int)*2); - STBIW_ASSERT(p); - if (p) { - if (!*arr) ((int *) p)[1] = 0; - *arr = (void *) ((int *) p + 2); - stbiw__sbm(*arr) = m; - } - return *arr; -} - -static unsigned char *stbiw__zlib_flushf(unsigned char *data, unsigned int *bitbuffer, int *bitcount) -{ - while (*bitcount >= 8) { - stbiw__sbpush(data, STBIW_UCHAR(*bitbuffer)); - *bitbuffer >>= 8; - *bitcount -= 8; - } - return data; -} - -static int stbiw__zlib_bitrev(int code, int codebits) -{ - int res=0; - while (codebits--) { - res = (res << 1) | (code & 1); - code >>= 1; - } - return res; -} - -static unsigned int stbiw__zlib_countm(unsigned char *a, unsigned char *b, int limit) -{ - int i; - for (i=0; i < limit && i < 258; ++i) - if (a[i] != b[i]) break; - return i; -} - -static unsigned int stbiw__zhash(unsigned char *data) -{ - stbiw_uint32 hash = data[0] + (data[1] << 8) + (data[2] << 16); - hash ^= hash << 3; - hash += hash >> 5; - hash ^= hash << 4; - hash += hash >> 17; - hash ^= hash << 25; - hash += hash >> 6; - return hash; -} - -#define stbiw__zlib_flush() (out = stbiw__zlib_flushf(out, &bitbuf, &bitcount)) -#define stbiw__zlib_add(code,codebits) \ - (bitbuf |= (code) << bitcount, bitcount += (codebits), stbiw__zlib_flush()) -#define stbiw__zlib_huffa(b,c) stbiw__zlib_add(stbiw__zlib_bitrev(b,c),c) -// default huffman tables -#define stbiw__zlib_huff1(n) stbiw__zlib_huffa(0x30 + (n), 8) -#define stbiw__zlib_huff2(n) stbiw__zlib_huffa(0x190 + (n)-144, 9) -#define stbiw__zlib_huff3(n) stbiw__zlib_huffa(0 + (n)-256,7) -#define stbiw__zlib_huff4(n) stbiw__zlib_huffa(0xc0 + (n)-280,8) -#define stbiw__zlib_huff(n) ((n) <= 143 ? stbiw__zlib_huff1(n) : (n) <= 255 ? stbiw__zlib_huff2(n) : (n) <= 279 ? stbiw__zlib_huff3(n) : stbiw__zlib_huff4(n)) -#define stbiw__zlib_huffb(n) ((n) <= 143 ? stbiw__zlib_huff1(n) : stbiw__zlib_huff2(n)) - -#define stbiw__ZHASH 16384 - -#endif // STBIW_ZLIB_COMPRESS - -STBIWDEF unsigned char * stbi_zlib_compress(unsigned char *data, int data_len, int *out_len, int quality) -{ -#ifdef STBIW_ZLIB_COMPRESS - // user provided a zlib compress implementation, use that - return STBIW_ZLIB_COMPRESS(data, data_len, out_len, quality); -#else // use builtin - static unsigned short lengthc[] = { 3,4,5,6,7,8,9,10,11,13,15,17,19,23,27,31,35,43,51,59,67,83,99,115,131,163,195,227,258, 259 }; - static unsigned char lengtheb[]= { 0,0,0,0,0,0,0, 0, 1, 1, 1, 1, 2, 2, 2, 2, 3, 3, 3, 3, 4, 4, 4, 4, 5, 5, 5, 5, 0 }; - static unsigned short distc[] = { 1,2,3,4,5,7,9,13,17,25,33,49,65,97,129,193,257,385,513,769,1025,1537,2049,3073,4097,6145,8193,12289,16385,24577, 32768 }; - static unsigned char disteb[] = { 0,0,0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7,8,8,9,9,10,10,11,11,12,12,13,13 }; - unsigned int bitbuf=0; - int i,j, bitcount=0; - unsigned char *out = NULL; - unsigned char ***hash_table = (unsigned char***) STBIW_MALLOC(stbiw__ZHASH * sizeof(unsigned char**)); - if (hash_table == NULL) - return NULL; - if (quality < 5) quality = 5; - - stbiw__sbpush(out, 0x78); // DEFLATE 32K window - stbiw__sbpush(out, 0x5e); // FLEVEL = 1 - stbiw__zlib_add(1,1); // BFINAL = 1 - stbiw__zlib_add(1,2); // BTYPE = 1 -- fixed huffman - - for (i=0; i < stbiw__ZHASH; ++i) - hash_table[i] = NULL; - - i=0; - while (i < data_len-3) { - // hash next 3 bytes of data to be compressed - int h = stbiw__zhash(data+i)&(stbiw__ZHASH-1), best=3; - unsigned char *bestloc = 0; - unsigned char **hlist = hash_table[h]; - int n = stbiw__sbcount(hlist); - for (j=0; j < n; ++j) { - if (hlist[j]-data > i-32768) { // if entry lies within window - int d = stbiw__zlib_countm(hlist[j], data+i, data_len-i); - if (d >= best) { best=d; bestloc=hlist[j]; } - } - } - // when hash table entry is too long, delete half the entries - if (hash_table[h] && stbiw__sbn(hash_table[h]) == 2*quality) { - STBIW_MEMMOVE(hash_table[h], hash_table[h]+quality, sizeof(hash_table[h][0])*quality); - stbiw__sbn(hash_table[h]) = quality; - } - stbiw__sbpush(hash_table[h],data+i); - - if (bestloc) { - // "lazy matching" - check match at *next* byte, and if it's better, do cur byte as literal - h = stbiw__zhash(data+i+1)&(stbiw__ZHASH-1); - hlist = hash_table[h]; - n = stbiw__sbcount(hlist); - for (j=0; j < n; ++j) { - if (hlist[j]-data > i-32767) { - int e = stbiw__zlib_countm(hlist[j], data+i+1, data_len-i-1); - if (e > best) { // if next match is better, bail on current match - bestloc = NULL; - break; - } - } - } - } - - if (bestloc) { - int d = (int) (data+i - bestloc); // distance back - STBIW_ASSERT(d <= 32767 && best <= 258); - for (j=0; best > lengthc[j+1]-1; ++j); - stbiw__zlib_huff(j+257); - if (lengtheb[j]) stbiw__zlib_add(best - lengthc[j], lengtheb[j]); - for (j=0; d > distc[j+1]-1; ++j); - stbiw__zlib_add(stbiw__zlib_bitrev(j,5),5); - if (disteb[j]) stbiw__zlib_add(d - distc[j], disteb[j]); - i += best; - } else { - stbiw__zlib_huffb(data[i]); - ++i; - } - } - // write out final bytes - for (;i < data_len; ++i) - stbiw__zlib_huffb(data[i]); - stbiw__zlib_huff(256); // end of block - // pad with 0 bits to byte boundary - while (bitcount) - stbiw__zlib_add(0,1); - - for (i=0; i < stbiw__ZHASH; ++i) - (void) stbiw__sbfree(hash_table[i]); - STBIW_FREE(hash_table); - - // store uncompressed instead if compression was worse - if (stbiw__sbn(out) > data_len + 2 + ((data_len+32766)/32767)*5) { - stbiw__sbn(out) = 2; // truncate to DEFLATE 32K window and FLEVEL = 1 - for (j = 0; j < data_len;) { - int blocklen = data_len - j; - if (blocklen > 32767) blocklen = 32767; - stbiw__sbpush(out, data_len - j == blocklen); // BFINAL = ?, BTYPE = 0 -- no compression - stbiw__sbpush(out, STBIW_UCHAR(blocklen)); // LEN - stbiw__sbpush(out, STBIW_UCHAR(blocklen >> 8)); - stbiw__sbpush(out, STBIW_UCHAR(~blocklen)); // NLEN - stbiw__sbpush(out, STBIW_UCHAR(~blocklen >> 8)); - memcpy(out+stbiw__sbn(out), data+j, blocklen); - stbiw__sbn(out) += blocklen; - j += blocklen; - } - } - - { - // compute adler32 on input - unsigned int s1=1, s2=0; - int blocklen = (int) (data_len % 5552); - j=0; - while (j < data_len) { - for (i=0; i < blocklen; ++i) { s1 += data[j+i]; s2 += s1; } - s1 %= 65521; s2 %= 65521; - j += blocklen; - blocklen = 5552; - } - stbiw__sbpush(out, STBIW_UCHAR(s2 >> 8)); - stbiw__sbpush(out, STBIW_UCHAR(s2)); - stbiw__sbpush(out, STBIW_UCHAR(s1 >> 8)); - stbiw__sbpush(out, STBIW_UCHAR(s1)); - } - *out_len = stbiw__sbn(out); - // make returned pointer freeable - STBIW_MEMMOVE(stbiw__sbraw(out), out, *out_len); - return (unsigned char *) stbiw__sbraw(out); -#endif // STBIW_ZLIB_COMPRESS -} - -static unsigned int stbiw__crc32(unsigned char *buffer, int len) -{ -#ifdef STBIW_CRC32 - return STBIW_CRC32(buffer, len); -#else - static unsigned int crc_table[256] = - { - 0x00000000, 0x77073096, 0xEE0E612C, 0x990951BA, 0x076DC419, 0x706AF48F, 0xE963A535, 0x9E6495A3, - 0x0eDB8832, 0x79DCB8A4, 0xE0D5E91E, 0x97D2D988, 0x09B64C2B, 0x7EB17CBD, 0xE7B82D07, 0x90BF1D91, - 0x1DB71064, 0x6AB020F2, 0xF3B97148, 0x84BE41DE, 0x1ADAD47D, 0x6DDDE4EB, 0xF4D4B551, 0x83D385C7, - 0x136C9856, 0x646BA8C0, 0xFD62F97A, 0x8A65C9EC, 0x14015C4F, 0x63066CD9, 0xFA0F3D63, 0x8D080DF5, - 0x3B6E20C8, 0x4C69105E, 0xD56041E4, 0xA2677172, 0x3C03E4D1, 0x4B04D447, 0xD20D85FD, 0xA50AB56B, - 0x35B5A8FA, 0x42B2986C, 0xDBBBC9D6, 0xACBCF940, 0x32D86CE3, 0x45DF5C75, 0xDCD60DCF, 0xABD13D59, - 0x26D930AC, 0x51DE003A, 0xC8D75180, 0xBFD06116, 0x21B4F4B5, 0x56B3C423, 0xCFBA9599, 0xB8BDA50F, - 0x2802B89E, 0x5F058808, 0xC60CD9B2, 0xB10BE924, 0x2F6F7C87, 0x58684C11, 0xC1611DAB, 0xB6662D3D, - 0x76DC4190, 0x01DB7106, 0x98D220BC, 0xEFD5102A, 0x71B18589, 0x06B6B51F, 0x9FBFE4A5, 0xE8B8D433, - 0x7807C9A2, 0x0F00F934, 0x9609A88E, 0xE10E9818, 0x7F6A0DBB, 0x086D3D2D, 0x91646C97, 0xE6635C01, - 0x6B6B51F4, 0x1C6C6162, 0x856530D8, 0xF262004E, 0x6C0695ED, 0x1B01A57B, 0x8208F4C1, 0xF50FC457, - 0x65B0D9C6, 0x12B7E950, 0x8BBEB8EA, 0xFCB9887C, 0x62DD1DDF, 0x15DA2D49, 0x8CD37CF3, 0xFBD44C65, - 0x4DB26158, 0x3AB551CE, 0xA3BC0074, 0xD4BB30E2, 0x4ADFA541, 0x3DD895D7, 0xA4D1C46D, 0xD3D6F4FB, - 0x4369E96A, 0x346ED9FC, 0xAD678846, 0xDA60B8D0, 0x44042D73, 0x33031DE5, 0xAA0A4C5F, 0xDD0D7CC9, - 0x5005713C, 0x270241AA, 0xBE0B1010, 0xC90C2086, 0x5768B525, 0x206F85B3, 0xB966D409, 0xCE61E49F, - 0x5EDEF90E, 0x29D9C998, 0xB0D09822, 0xC7D7A8B4, 0x59B33D17, 0x2EB40D81, 0xB7BD5C3B, 0xC0BA6CAD, - 0xEDB88320, 0x9ABFB3B6, 0x03B6E20C, 0x74B1D29A, 0xEAD54739, 0x9DD277AF, 0x04DB2615, 0x73DC1683, - 0xE3630B12, 0x94643B84, 0x0D6D6A3E, 0x7A6A5AA8, 0xE40ECF0B, 0x9309FF9D, 0x0A00AE27, 0x7D079EB1, - 0xF00F9344, 0x8708A3D2, 0x1E01F268, 0x6906C2FE, 0xF762575D, 0x806567CB, 0x196C3671, 0x6E6B06E7, - 0xFED41B76, 0x89D32BE0, 0x10DA7A5A, 0x67DD4ACC, 0xF9B9DF6F, 0x8EBEEFF9, 0x17B7BE43, 0x60B08ED5, - 0xD6D6A3E8, 0xA1D1937E, 0x38D8C2C4, 0x4FDFF252, 0xD1BB67F1, 0xA6BC5767, 0x3FB506DD, 0x48B2364B, - 0xD80D2BDA, 0xAF0A1B4C, 0x36034AF6, 0x41047A60, 0xDF60EFC3, 0xA867DF55, 0x316E8EEF, 0x4669BE79, - 0xCB61B38C, 0xBC66831A, 0x256FD2A0, 0x5268E236, 0xCC0C7795, 0xBB0B4703, 0x220216B9, 0x5505262F, - 0xC5BA3BBE, 0xB2BD0B28, 0x2BB45A92, 0x5CB36A04, 0xC2D7FFA7, 0xB5D0CF31, 0x2CD99E8B, 0x5BDEAE1D, - 0x9B64C2B0, 0xEC63F226, 0x756AA39C, 0x026D930A, 0x9C0906A9, 0xEB0E363F, 0x72076785, 0x05005713, - 0x95BF4A82, 0xE2B87A14, 0x7BB12BAE, 0x0CB61B38, 0x92D28E9B, 0xE5D5BE0D, 0x7CDCEFB7, 0x0BDBDF21, - 0x86D3D2D4, 0xF1D4E242, 0x68DDB3F8, 0x1FDA836E, 0x81BE16CD, 0xF6B9265B, 0x6FB077E1, 0x18B74777, - 0x88085AE6, 0xFF0F6A70, 0x66063BCA, 0x11010B5C, 0x8F659EFF, 0xF862AE69, 0x616BFFD3, 0x166CCF45, - 0xA00AE278, 0xD70DD2EE, 0x4E048354, 0x3903B3C2, 0xA7672661, 0xD06016F7, 0x4969474D, 0x3E6E77DB, - 0xAED16A4A, 0xD9D65ADC, 0x40DF0B66, 0x37D83BF0, 0xA9BCAE53, 0xDEBB9EC5, 0x47B2CF7F, 0x30B5FFE9, - 0xBDBDF21C, 0xCABAC28A, 0x53B39330, 0x24B4A3A6, 0xBAD03605, 0xCDD70693, 0x54DE5729, 0x23D967BF, - 0xB3667A2E, 0xC4614AB8, 0x5D681B02, 0x2A6F2B94, 0xB40BBE37, 0xC30C8EA1, 0x5A05DF1B, 0x2D02EF8D - }; - - unsigned int crc = ~0u; - int i; - for (i=0; i < len; ++i) - crc = (crc >> 8) ^ crc_table[buffer[i] ^ (crc & 0xff)]; - return ~crc; -#endif -} - -#define stbiw__wpng4(o,a,b,c,d) ((o)[0]=STBIW_UCHAR(a),(o)[1]=STBIW_UCHAR(b),(o)[2]=STBIW_UCHAR(c),(o)[3]=STBIW_UCHAR(d),(o)+=4) -#define stbiw__wp32(data,v) stbiw__wpng4(data, (v)>>24,(v)>>16,(v)>>8,(v)); -#define stbiw__wptag(data,s) stbiw__wpng4(data, s[0],s[1],s[2],s[3]) - -static void stbiw__wpcrc(unsigned char **data, int len) -{ - unsigned int crc = stbiw__crc32(*data - len - 4, len+4); - stbiw__wp32(*data, crc); -} - -static unsigned char stbiw__paeth(int a, int b, int c) -{ - int p = a + b - c, pa = abs(p-a), pb = abs(p-b), pc = abs(p-c); - if (pa <= pb && pa <= pc) return STBIW_UCHAR(a); - if (pb <= pc) return STBIW_UCHAR(b); - return STBIW_UCHAR(c); -} - -// @OPTIMIZE: provide an option that always forces left-predict or paeth predict -static void stbiw__encode_png_line(unsigned char *pixels, int stride_bytes, int width, int height, int y, int n, int filter_type, signed char *line_buffer) -{ - static int mapping[] = { 0,1,2,3,4 }; - static int firstmap[] = { 0,1,0,5,6 }; - int *mymap = (y != 0) ? mapping : firstmap; - int i; - int type = mymap[filter_type]; - unsigned char *z = pixels + stride_bytes * (stbi__flip_vertically_on_write ? height-1-y : y); - int signed_stride = stbi__flip_vertically_on_write ? -stride_bytes : stride_bytes; - - if (type==0) { - memcpy(line_buffer, z, width*n); - return; - } - - // first loop isn't optimized since it's just one pixel - for (i = 0; i < n; ++i) { - switch (type) { - case 1: line_buffer[i] = z[i]; break; - case 2: line_buffer[i] = z[i] - z[i-signed_stride]; break; - case 3: line_buffer[i] = z[i] - (z[i-signed_stride]>>1); break; - case 4: line_buffer[i] = (signed char) (z[i] - stbiw__paeth(0,z[i-signed_stride],0)); break; - case 5: line_buffer[i] = z[i]; break; - case 6: line_buffer[i] = z[i]; break; - } - } - switch (type) { - case 1: for (i=n; i < width*n; ++i) line_buffer[i] = z[i] - z[i-n]; break; - case 2: for (i=n; i < width*n; ++i) line_buffer[i] = z[i] - z[i-signed_stride]; break; - case 3: for (i=n; i < width*n; ++i) line_buffer[i] = z[i] - ((z[i-n] + z[i-signed_stride])>>1); break; - case 4: for (i=n; i < width*n; ++i) line_buffer[i] = z[i] - stbiw__paeth(z[i-n], z[i-signed_stride], z[i-signed_stride-n]); break; - case 5: for (i=n; i < width*n; ++i) line_buffer[i] = z[i] - (z[i-n]>>1); break; - case 6: for (i=n; i < width*n; ++i) line_buffer[i] = z[i] - stbiw__paeth(z[i-n], 0,0); break; - } -} - -STBIWDEF unsigned char *stbi_write_png_to_mem(const unsigned char *pixels, int stride_bytes, int x, int y, int n, int *out_len) -{ - int force_filter = stbi_write_force_png_filter; - int ctype[5] = { -1, 0, 4, 2, 6 }; - unsigned char sig[8] = { 137,80,78,71,13,10,26,10 }; - unsigned char *out,*o, *filt, *zlib; - signed char *line_buffer; - int j,zlen; - - if (stride_bytes == 0) - stride_bytes = x * n; - - if (force_filter >= 5) { - force_filter = -1; - } - - filt = (unsigned char *) STBIW_MALLOC((x*n+1) * y); if (!filt) return 0; - line_buffer = (signed char *) STBIW_MALLOC(x * n); if (!line_buffer) { STBIW_FREE(filt); return 0; } - for (j=0; j < y; ++j) { - int filter_type; - if (force_filter > -1) { - filter_type = force_filter; - stbiw__encode_png_line((unsigned char*)(pixels), stride_bytes, x, y, j, n, force_filter, line_buffer); - } else { // Estimate the best filter by running through all of them: - int best_filter = 0, best_filter_val = 0x7fffffff, est, i; - for (filter_type = 0; filter_type < 5; filter_type++) { - stbiw__encode_png_line((unsigned char*)(pixels), stride_bytes, x, y, j, n, filter_type, line_buffer); - - // Estimate the entropy of the line using this filter; the less, the better. - est = 0; - for (i = 0; i < x*n; ++i) { - est += abs((signed char) line_buffer[i]); - } - if (est < best_filter_val) { - best_filter_val = est; - best_filter = filter_type; - } - } - if (filter_type != best_filter) { // If the last iteration already got us the best filter, don't redo it - stbiw__encode_png_line((unsigned char*)(pixels), stride_bytes, x, y, j, n, best_filter, line_buffer); - filter_type = best_filter; - } - } - // when we get here, filter_type contains the filter type, and line_buffer contains the data - filt[j*(x*n+1)] = (unsigned char) filter_type; - STBIW_MEMMOVE(filt+j*(x*n+1)+1, line_buffer, x*n); - } - STBIW_FREE(line_buffer); - zlib = stbi_zlib_compress(filt, y*( x*n+1), &zlen, stbi_write_png_compression_level); - STBIW_FREE(filt); - if (!zlib) return 0; - - // each tag requires 12 bytes of overhead - out = (unsigned char *) STBIW_MALLOC(8 + 12+13 + 12+zlen + 12); - if (!out) return 0; - *out_len = 8 + 12+13 + 12+zlen + 12; - - o=out; - STBIW_MEMMOVE(o,sig,8); o+= 8; - stbiw__wp32(o, 13); // header length - stbiw__wptag(o, "IHDR"); - stbiw__wp32(o, x); - stbiw__wp32(o, y); - *o++ = 8; - *o++ = STBIW_UCHAR(ctype[n]); - *o++ = 0; - *o++ = 0; - *o++ = 0; - stbiw__wpcrc(&o,13); - - stbiw__wp32(o, zlen); - stbiw__wptag(o, "IDAT"); - STBIW_MEMMOVE(o, zlib, zlen); - o += zlen; - STBIW_FREE(zlib); - stbiw__wpcrc(&o, zlen); - - stbiw__wp32(o,0); - stbiw__wptag(o, "IEND"); - stbiw__wpcrc(&o,0); - - STBIW_ASSERT(o == out + *out_len); - - return out; -} - -#ifndef STBI_WRITE_NO_STDIO -STBIWDEF int stbi_write_png(char const *filename, int x, int y, int comp, const void *data, int stride_bytes) -{ - FILE *f; - int len; - unsigned char *png = stbi_write_png_to_mem((const unsigned char *) data, stride_bytes, x, y, comp, &len); - if (png == NULL) return 0; - - f = stbiw__fopen(filename, "wb"); - if (!f) { STBIW_FREE(png); return 0; } - fwrite(png, 1, len, f); - fclose(f); - STBIW_FREE(png); - return 1; -} -#endif - -STBIWDEF int stbi_write_png_to_func(stbi_write_func *func, void *context, int x, int y, int comp, const void *data, int stride_bytes) -{ - int len; - unsigned char *png = stbi_write_png_to_mem((const unsigned char *) data, stride_bytes, x, y, comp, &len); - if (png == NULL) return 0; - func(context, png, len); - STBIW_FREE(png); - return 1; -} - - -/* *************************************************************************** - * - * JPEG writer - * - * This is based on Jon Olick's jo_jpeg.cpp: - * public domain Simple, Minimalistic JPEG writer - http://www.jonolick.com/code.html - */ - -static const unsigned char stbiw__jpg_ZigZag[] = { 0,1,5,6,14,15,27,28,2,4,7,13,16,26,29,42,3,8,12,17,25,30,41,43,9,11,18, - 24,31,40,44,53,10,19,23,32,39,45,52,54,20,22,33,38,46,51,55,60,21,34,37,47,50,56,59,61,35,36,48,49,57,58,62,63 }; - -static void stbiw__jpg_writeBits(stbi__write_context *s, int *bitBufP, int *bitCntP, const unsigned short *bs) { - int bitBuf = *bitBufP, bitCnt = *bitCntP; - bitCnt += bs[1]; - bitBuf |= bs[0] << (24 - bitCnt); - while(bitCnt >= 8) { - unsigned char c = (bitBuf >> 16) & 255; - stbiw__putc(s, c); - if(c == 255) { - stbiw__putc(s, 0); - } - bitBuf <<= 8; - bitCnt -= 8; - } - *bitBufP = bitBuf; - *bitCntP = bitCnt; -} - -static void stbiw__jpg_DCT(float *d0p, float *d1p, float *d2p, float *d3p, float *d4p, float *d5p, float *d6p, float *d7p) { - float d0 = *d0p, d1 = *d1p, d2 = *d2p, d3 = *d3p, d4 = *d4p, d5 = *d5p, d6 = *d6p, d7 = *d7p; - float z1, z2, z3, z4, z5, z11, z13; - - float tmp0 = d0 + d7; - float tmp7 = d0 - d7; - float tmp1 = d1 + d6; - float tmp6 = d1 - d6; - float tmp2 = d2 + d5; - float tmp5 = d2 - d5; - float tmp3 = d3 + d4; - float tmp4 = d3 - d4; - - // Even part - float tmp10 = tmp0 + tmp3; // phase 2 - float tmp13 = tmp0 - tmp3; - float tmp11 = tmp1 + tmp2; - float tmp12 = tmp1 - tmp2; - - d0 = tmp10 + tmp11; // phase 3 - d4 = tmp10 - tmp11; - - z1 = (tmp12 + tmp13) * 0.707106781f; // c4 - d2 = tmp13 + z1; // phase 5 - d6 = tmp13 - z1; - - // Odd part - tmp10 = tmp4 + tmp5; // phase 2 - tmp11 = tmp5 + tmp6; - tmp12 = tmp6 + tmp7; - - // The rotator is modified from fig 4-8 to avoid extra negations. - z5 = (tmp10 - tmp12) * 0.382683433f; // c6 - z2 = tmp10 * 0.541196100f + z5; // c2-c6 - z4 = tmp12 * 1.306562965f + z5; // c2+c6 - z3 = tmp11 * 0.707106781f; // c4 - - z11 = tmp7 + z3; // phase 5 - z13 = tmp7 - z3; - - *d5p = z13 + z2; // phase 6 - *d3p = z13 - z2; - *d1p = z11 + z4; - *d7p = z11 - z4; - - *d0p = d0; *d2p = d2; *d4p = d4; *d6p = d6; -} - -static void stbiw__jpg_calcBits(int val, unsigned short bits[2]) { - int tmp1 = val < 0 ? -val : val; - val = val < 0 ? val-1 : val; - bits[1] = 1; - while(tmp1 >>= 1) { - ++bits[1]; - } - bits[0] = val & ((1<0)&&(DU[end0pos]==0); --end0pos) { - } - // end0pos = first element in reverse order !=0 - if(end0pos == 0) { - stbiw__jpg_writeBits(s, bitBuf, bitCnt, EOB); - return DU[0]; - } - for(i = 1; i <= end0pos; ++i) { - int startpos = i; - int nrzeroes; - unsigned short bits[2]; - for (; DU[i]==0 && i<=end0pos; ++i) { - } - nrzeroes = i-startpos; - if ( nrzeroes >= 16 ) { - int lng = nrzeroes>>4; - int nrmarker; - for (nrmarker=1; nrmarker <= lng; ++nrmarker) - stbiw__jpg_writeBits(s, bitBuf, bitCnt, M16zeroes); - nrzeroes &= 15; - } - stbiw__jpg_calcBits(DU[i], bits); - stbiw__jpg_writeBits(s, bitBuf, bitCnt, HTAC[(nrzeroes<<4)+bits[1]]); - stbiw__jpg_writeBits(s, bitBuf, bitCnt, bits); - } - if(end0pos != 63) { - stbiw__jpg_writeBits(s, bitBuf, bitCnt, EOB); - } - return DU[0]; -} - -static int stbi_write_jpg_core(stbi__write_context *s, int width, int height, int comp, const void* data, int quality) { - // Constants that don't pollute global namespace - static const unsigned char std_dc_luminance_nrcodes[] = {0,0,1,5,1,1,1,1,1,1,0,0,0,0,0,0,0}; - static const unsigned char std_dc_luminance_values[] = {0,1,2,3,4,5,6,7,8,9,10,11}; - static const unsigned char std_ac_luminance_nrcodes[] = {0,0,2,1,3,3,2,4,3,5,5,4,4,0,0,1,0x7d}; - static const unsigned char std_ac_luminance_values[] = { - 0x01,0x02,0x03,0x00,0x04,0x11,0x05,0x12,0x21,0x31,0x41,0x06,0x13,0x51,0x61,0x07,0x22,0x71,0x14,0x32,0x81,0x91,0xa1,0x08, - 0x23,0x42,0xb1,0xc1,0x15,0x52,0xd1,0xf0,0x24,0x33,0x62,0x72,0x82,0x09,0x0a,0x16,0x17,0x18,0x19,0x1a,0x25,0x26,0x27,0x28, - 0x29,0x2a,0x34,0x35,0x36,0x37,0x38,0x39,0x3a,0x43,0x44,0x45,0x46,0x47,0x48,0x49,0x4a,0x53,0x54,0x55,0x56,0x57,0x58,0x59, - 0x5a,0x63,0x64,0x65,0x66,0x67,0x68,0x69,0x6a,0x73,0x74,0x75,0x76,0x77,0x78,0x79,0x7a,0x83,0x84,0x85,0x86,0x87,0x88,0x89, - 0x8a,0x92,0x93,0x94,0x95,0x96,0x97,0x98,0x99,0x9a,0xa2,0xa3,0xa4,0xa5,0xa6,0xa7,0xa8,0xa9,0xaa,0xb2,0xb3,0xb4,0xb5,0xb6, - 0xb7,0xb8,0xb9,0xba,0xc2,0xc3,0xc4,0xc5,0xc6,0xc7,0xc8,0xc9,0xca,0xd2,0xd3,0xd4,0xd5,0xd6,0xd7,0xd8,0xd9,0xda,0xe1,0xe2, - 0xe3,0xe4,0xe5,0xe6,0xe7,0xe8,0xe9,0xea,0xf1,0xf2,0xf3,0xf4,0xf5,0xf6,0xf7,0xf8,0xf9,0xfa - }; - static const unsigned char std_dc_chrominance_nrcodes[] = {0,0,3,1,1,1,1,1,1,1,1,1,0,0,0,0,0}; - static const unsigned char std_dc_chrominance_values[] = {0,1,2,3,4,5,6,7,8,9,10,11}; - static const unsigned char std_ac_chrominance_nrcodes[] = {0,0,2,1,2,4,4,3,4,7,5,4,4,0,1,2,0x77}; - static const unsigned char std_ac_chrominance_values[] = { - 0x00,0x01,0x02,0x03,0x11,0x04,0x05,0x21,0x31,0x06,0x12,0x41,0x51,0x07,0x61,0x71,0x13,0x22,0x32,0x81,0x08,0x14,0x42,0x91, - 0xa1,0xb1,0xc1,0x09,0x23,0x33,0x52,0xf0,0x15,0x62,0x72,0xd1,0x0a,0x16,0x24,0x34,0xe1,0x25,0xf1,0x17,0x18,0x19,0x1a,0x26, - 0x27,0x28,0x29,0x2a,0x35,0x36,0x37,0x38,0x39,0x3a,0x43,0x44,0x45,0x46,0x47,0x48,0x49,0x4a,0x53,0x54,0x55,0x56,0x57,0x58, - 0x59,0x5a,0x63,0x64,0x65,0x66,0x67,0x68,0x69,0x6a,0x73,0x74,0x75,0x76,0x77,0x78,0x79,0x7a,0x82,0x83,0x84,0x85,0x86,0x87, - 0x88,0x89,0x8a,0x92,0x93,0x94,0x95,0x96,0x97,0x98,0x99,0x9a,0xa2,0xa3,0xa4,0xa5,0xa6,0xa7,0xa8,0xa9,0xaa,0xb2,0xb3,0xb4, - 0xb5,0xb6,0xb7,0xb8,0xb9,0xba,0xc2,0xc3,0xc4,0xc5,0xc6,0xc7,0xc8,0xc9,0xca,0xd2,0xd3,0xd4,0xd5,0xd6,0xd7,0xd8,0xd9,0xda, - 0xe2,0xe3,0xe4,0xe5,0xe6,0xe7,0xe8,0xe9,0xea,0xf2,0xf3,0xf4,0xf5,0xf6,0xf7,0xf8,0xf9,0xfa - }; - // Huffman tables - static const unsigned short YDC_HT[256][2] = { {0,2},{2,3},{3,3},{4,3},{5,3},{6,3},{14,4},{30,5},{62,6},{126,7},{254,8},{510,9}}; - static const unsigned short UVDC_HT[256][2] = { {0,2},{1,2},{2,2},{6,3},{14,4},{30,5},{62,6},{126,7},{254,8},{510,9},{1022,10},{2046,11}}; - static const unsigned short YAC_HT[256][2] = { - {10,4},{0,2},{1,2},{4,3},{11,4},{26,5},{120,7},{248,8},{1014,10},{65410,16},{65411,16},{0,0},{0,0},{0,0},{0,0},{0,0},{0,0}, - {12,4},{27,5},{121,7},{502,9},{2038,11},{65412,16},{65413,16},{65414,16},{65415,16},{65416,16},{0,0},{0,0},{0,0},{0,0},{0,0},{0,0}, - {28,5},{249,8},{1015,10},{4084,12},{65417,16},{65418,16},{65419,16},{65420,16},{65421,16},{65422,16},{0,0},{0,0},{0,0},{0,0},{0,0},{0,0}, - {58,6},{503,9},{4085,12},{65423,16},{65424,16},{65425,16},{65426,16},{65427,16},{65428,16},{65429,16},{0,0},{0,0},{0,0},{0,0},{0,0},{0,0}, - {59,6},{1016,10},{65430,16},{65431,16},{65432,16},{65433,16},{65434,16},{65435,16},{65436,16},{65437,16},{0,0},{0,0},{0,0},{0,0},{0,0},{0,0}, - {122,7},{2039,11},{65438,16},{65439,16},{65440,16},{65441,16},{65442,16},{65443,16},{65444,16},{65445,16},{0,0},{0,0},{0,0},{0,0},{0,0},{0,0}, - {123,7},{4086,12},{65446,16},{65447,16},{65448,16},{65449,16},{65450,16},{65451,16},{65452,16},{65453,16},{0,0},{0,0},{0,0},{0,0},{0,0},{0,0}, - {250,8},{4087,12},{65454,16},{65455,16},{65456,16},{65457,16},{65458,16},{65459,16},{65460,16},{65461,16},{0,0},{0,0},{0,0},{0,0},{0,0},{0,0}, - {504,9},{32704,15},{65462,16},{65463,16},{65464,16},{65465,16},{65466,16},{65467,16},{65468,16},{65469,16},{0,0},{0,0},{0,0},{0,0},{0,0},{0,0}, - {505,9},{65470,16},{65471,16},{65472,16},{65473,16},{65474,16},{65475,16},{65476,16},{65477,16},{65478,16},{0,0},{0,0},{0,0},{0,0},{0,0},{0,0}, - {506,9},{65479,16},{65480,16},{65481,16},{65482,16},{65483,16},{65484,16},{65485,16},{65486,16},{65487,16},{0,0},{0,0},{0,0},{0,0},{0,0},{0,0}, - {1017,10},{65488,16},{65489,16},{65490,16},{65491,16},{65492,16},{65493,16},{65494,16},{65495,16},{65496,16},{0,0},{0,0},{0,0},{0,0},{0,0},{0,0}, - {1018,10},{65497,16},{65498,16},{65499,16},{65500,16},{65501,16},{65502,16},{65503,16},{65504,16},{65505,16},{0,0},{0,0},{0,0},{0,0},{0,0},{0,0}, - {2040,11},{65506,16},{65507,16},{65508,16},{65509,16},{65510,16},{65511,16},{65512,16},{65513,16},{65514,16},{0,0},{0,0},{0,0},{0,0},{0,0},{0,0}, - {65515,16},{65516,16},{65517,16},{65518,16},{65519,16},{65520,16},{65521,16},{65522,16},{65523,16},{65524,16},{0,0},{0,0},{0,0},{0,0},{0,0}, - {2041,11},{65525,16},{65526,16},{65527,16},{65528,16},{65529,16},{65530,16},{65531,16},{65532,16},{65533,16},{65534,16},{0,0},{0,0},{0,0},{0,0},{0,0} - }; - static const unsigned short UVAC_HT[256][2] = { - {0,2},{1,2},{4,3},{10,4},{24,5},{25,5},{56,6},{120,7},{500,9},{1014,10},{4084,12},{0,0},{0,0},{0,0},{0,0},{0,0},{0,0}, - {11,4},{57,6},{246,8},{501,9},{2038,11},{4085,12},{65416,16},{65417,16},{65418,16},{65419,16},{0,0},{0,0},{0,0},{0,0},{0,0},{0,0}, - {26,5},{247,8},{1015,10},{4086,12},{32706,15},{65420,16},{65421,16},{65422,16},{65423,16},{65424,16},{0,0},{0,0},{0,0},{0,0},{0,0},{0,0}, - {27,5},{248,8},{1016,10},{4087,12},{65425,16},{65426,16},{65427,16},{65428,16},{65429,16},{65430,16},{0,0},{0,0},{0,0},{0,0},{0,0},{0,0}, - {58,6},{502,9},{65431,16},{65432,16},{65433,16},{65434,16},{65435,16},{65436,16},{65437,16},{65438,16},{0,0},{0,0},{0,0},{0,0},{0,0},{0,0}, - {59,6},{1017,10},{65439,16},{65440,16},{65441,16},{65442,16},{65443,16},{65444,16},{65445,16},{65446,16},{0,0},{0,0},{0,0},{0,0},{0,0},{0,0}, - {121,7},{2039,11},{65447,16},{65448,16},{65449,16},{65450,16},{65451,16},{65452,16},{65453,16},{65454,16},{0,0},{0,0},{0,0},{0,0},{0,0},{0,0}, - {122,7},{2040,11},{65455,16},{65456,16},{65457,16},{65458,16},{65459,16},{65460,16},{65461,16},{65462,16},{0,0},{0,0},{0,0},{0,0},{0,0},{0,0}, - {249,8},{65463,16},{65464,16},{65465,16},{65466,16},{65467,16},{65468,16},{65469,16},{65470,16},{65471,16},{0,0},{0,0},{0,0},{0,0},{0,0},{0,0}, - {503,9},{65472,16},{65473,16},{65474,16},{65475,16},{65476,16},{65477,16},{65478,16},{65479,16},{65480,16},{0,0},{0,0},{0,0},{0,0},{0,0},{0,0}, - {504,9},{65481,16},{65482,16},{65483,16},{65484,16},{65485,16},{65486,16},{65487,16},{65488,16},{65489,16},{0,0},{0,0},{0,0},{0,0},{0,0},{0,0}, - {505,9},{65490,16},{65491,16},{65492,16},{65493,16},{65494,16},{65495,16},{65496,16},{65497,16},{65498,16},{0,0},{0,0},{0,0},{0,0},{0,0},{0,0}, - {506,9},{65499,16},{65500,16},{65501,16},{65502,16},{65503,16},{65504,16},{65505,16},{65506,16},{65507,16},{0,0},{0,0},{0,0},{0,0},{0,0},{0,0}, - {2041,11},{65508,16},{65509,16},{65510,16},{65511,16},{65512,16},{65513,16},{65514,16},{65515,16},{65516,16},{0,0},{0,0},{0,0},{0,0},{0,0},{0,0}, - {16352,14},{65517,16},{65518,16},{65519,16},{65520,16},{65521,16},{65522,16},{65523,16},{65524,16},{65525,16},{0,0},{0,0},{0,0},{0,0},{0,0}, - {1018,10},{32707,15},{65526,16},{65527,16},{65528,16},{65529,16},{65530,16},{65531,16},{65532,16},{65533,16},{65534,16},{0,0},{0,0},{0,0},{0,0},{0,0} - }; - static const int YQT[] = {16,11,10,16,24,40,51,61,12,12,14,19,26,58,60,55,14,13,16,24,40,57,69,56,14,17,22,29,51,87,80,62,18,22, - 37,56,68,109,103,77,24,35,55,64,81,104,113,92,49,64,78,87,103,121,120,101,72,92,95,98,112,100,103,99}; - static const int UVQT[] = {17,18,24,47,99,99,99,99,18,21,26,66,99,99,99,99,24,26,56,99,99,99,99,99,47,66,99,99,99,99,99,99, - 99,99,99,99,99,99,99,99,99,99,99,99,99,99,99,99,99,99,99,99,99,99,99,99,99,99,99,99,99,99,99,99}; - static const float aasf[] = { 1.0f * 2.828427125f, 1.387039845f * 2.828427125f, 1.306562965f * 2.828427125f, 1.175875602f * 2.828427125f, - 1.0f * 2.828427125f, 0.785694958f * 2.828427125f, 0.541196100f * 2.828427125f, 0.275899379f * 2.828427125f }; - - int row, col, i, k, subsample; - float fdtbl_Y[64], fdtbl_UV[64]; - unsigned char YTable[64], UVTable[64]; - - if(!data || !width || !height || comp > 4 || comp < 1) { - return 0; - } - - quality = quality ? quality : 90; - subsample = quality <= 90 ? 1 : 0; - quality = quality < 1 ? 1 : quality > 100 ? 100 : quality; - quality = quality < 50 ? 5000 / quality : 200 - quality * 2; - - for(i = 0; i < 64; ++i) { - int uvti, yti = (YQT[i]*quality+50)/100; - YTable[stbiw__jpg_ZigZag[i]] = (unsigned char) (yti < 1 ? 1 : yti > 255 ? 255 : yti); - uvti = (UVQT[i]*quality+50)/100; - UVTable[stbiw__jpg_ZigZag[i]] = (unsigned char) (uvti < 1 ? 1 : uvti > 255 ? 255 : uvti); - } - - for(row = 0, k = 0; row < 8; ++row) { - for(col = 0; col < 8; ++col, ++k) { - fdtbl_Y[k] = 1 / (YTable [stbiw__jpg_ZigZag[k]] * aasf[row] * aasf[col]); - fdtbl_UV[k] = 1 / (UVTable[stbiw__jpg_ZigZag[k]] * aasf[row] * aasf[col]); - } - } - - // Write Headers - { - static const unsigned char head0[] = { 0xFF,0xD8,0xFF,0xE0,0,0x10,'J','F','I','F',0,1,1,0,0,1,0,1,0,0,0xFF,0xDB,0,0x84,0 }; - static const unsigned char head2[] = { 0xFF,0xDA,0,0xC,3,1,0,2,0x11,3,0x11,0,0x3F,0 }; - const unsigned char head1[] = { 0xFF,0xC0,0,0x11,8,(unsigned char)(height>>8),STBIW_UCHAR(height),(unsigned char)(width>>8),STBIW_UCHAR(width), - 3,1,(unsigned char)(subsample?0x22:0x11),0,2,0x11,1,3,0x11,1,0xFF,0xC4,0x01,0xA2,0 }; - s->func(s->context, (void*)head0, sizeof(head0)); - s->func(s->context, (void*)YTable, sizeof(YTable)); - stbiw__putc(s, 1); - s->func(s->context, UVTable, sizeof(UVTable)); - s->func(s->context, (void*)head1, sizeof(head1)); - s->func(s->context, (void*)(std_dc_luminance_nrcodes+1), sizeof(std_dc_luminance_nrcodes)-1); - s->func(s->context, (void*)std_dc_luminance_values, sizeof(std_dc_luminance_values)); - stbiw__putc(s, 0x10); // HTYACinfo - s->func(s->context, (void*)(std_ac_luminance_nrcodes+1), sizeof(std_ac_luminance_nrcodes)-1); - s->func(s->context, (void*)std_ac_luminance_values, sizeof(std_ac_luminance_values)); - stbiw__putc(s, 1); // HTUDCinfo - s->func(s->context, (void*)(std_dc_chrominance_nrcodes+1), sizeof(std_dc_chrominance_nrcodes)-1); - s->func(s->context, (void*)std_dc_chrominance_values, sizeof(std_dc_chrominance_values)); - stbiw__putc(s, 0x11); // HTUACinfo - s->func(s->context, (void*)(std_ac_chrominance_nrcodes+1), sizeof(std_ac_chrominance_nrcodes)-1); - s->func(s->context, (void*)std_ac_chrominance_values, sizeof(std_ac_chrominance_values)); - s->func(s->context, (void*)head2, sizeof(head2)); - } - - // Encode 8x8 macroblocks - { - static const unsigned short fillBits[] = {0x7F, 7}; - int DCY=0, DCU=0, DCV=0; - int bitBuf=0, bitCnt=0; - // comp == 2 is grey+alpha (alpha is ignored) - int ofsG = comp > 2 ? 1 : 0, ofsB = comp > 2 ? 2 : 0; - const unsigned char *dataR = (const unsigned char *)data; - const unsigned char *dataG = dataR + ofsG; - const unsigned char *dataB = dataR + ofsB; - int x, y, pos; - if(subsample) { - for(y = 0; y < height; y += 16) { - for(x = 0; x < width; x += 16) { - float Y[256], U[256], V[256]; - for(row = y, pos = 0; row < y+16; ++row) { - // row >= height => use last input row - int clamped_row = (row < height) ? row : height - 1; - int base_p = (stbi__flip_vertically_on_write ? (height-1-clamped_row) : clamped_row)*width*comp; - for(col = x; col < x+16; ++col, ++pos) { - // if col >= width => use pixel from last input column - int p = base_p + ((col < width) ? col : (width-1))*comp; - float r = dataR[p], g = dataG[p], b = dataB[p]; - Y[pos]= +0.29900f*r + 0.58700f*g + 0.11400f*b - 128; - U[pos]= -0.16874f*r - 0.33126f*g + 0.50000f*b; - V[pos]= +0.50000f*r - 0.41869f*g - 0.08131f*b; - } - } - DCY = stbiw__jpg_processDU(s, &bitBuf, &bitCnt, Y+0, 16, fdtbl_Y, DCY, YDC_HT, YAC_HT); - DCY = stbiw__jpg_processDU(s, &bitBuf, &bitCnt, Y+8, 16, fdtbl_Y, DCY, YDC_HT, YAC_HT); - DCY = stbiw__jpg_processDU(s, &bitBuf, &bitCnt, Y+128, 16, fdtbl_Y, DCY, YDC_HT, YAC_HT); - DCY = stbiw__jpg_processDU(s, &bitBuf, &bitCnt, Y+136, 16, fdtbl_Y, DCY, YDC_HT, YAC_HT); - - // subsample U,V - { - float subU[64], subV[64]; - int yy, xx; - for(yy = 0, pos = 0; yy < 8; ++yy) { - for(xx = 0; xx < 8; ++xx, ++pos) { - int j = yy*32+xx*2; - subU[pos] = (U[j+0] + U[j+1] + U[j+16] + U[j+17]) * 0.25f; - subV[pos] = (V[j+0] + V[j+1] + V[j+16] + V[j+17]) * 0.25f; - } - } - DCU = stbiw__jpg_processDU(s, &bitBuf, &bitCnt, subU, 8, fdtbl_UV, DCU, UVDC_HT, UVAC_HT); - DCV = stbiw__jpg_processDU(s, &bitBuf, &bitCnt, subV, 8, fdtbl_UV, DCV, UVDC_HT, UVAC_HT); - } - } - } - } else { - for(y = 0; y < height; y += 8) { - for(x = 0; x < width; x += 8) { - float Y[64], U[64], V[64]; - for(row = y, pos = 0; row < y+8; ++row) { - // row >= height => use last input row - int clamped_row = (row < height) ? row : height - 1; - int base_p = (stbi__flip_vertically_on_write ? (height-1-clamped_row) : clamped_row)*width*comp; - for(col = x; col < x+8; ++col, ++pos) { - // if col >= width => use pixel from last input column - int p = base_p + ((col < width) ? col : (width-1))*comp; - float r = dataR[p], g = dataG[p], b = dataB[p]; - Y[pos]= +0.29900f*r + 0.58700f*g + 0.11400f*b - 128; - U[pos]= -0.16874f*r - 0.33126f*g + 0.50000f*b; - V[pos]= +0.50000f*r - 0.41869f*g - 0.08131f*b; - } - } - - DCY = stbiw__jpg_processDU(s, &bitBuf, &bitCnt, Y, 8, fdtbl_Y, DCY, YDC_HT, YAC_HT); - DCU = stbiw__jpg_processDU(s, &bitBuf, &bitCnt, U, 8, fdtbl_UV, DCU, UVDC_HT, UVAC_HT); - DCV = stbiw__jpg_processDU(s, &bitBuf, &bitCnt, V, 8, fdtbl_UV, DCV, UVDC_HT, UVAC_HT); - } - } - } - - // Do the bit alignment of the EOI marker - stbiw__jpg_writeBits(s, &bitBuf, &bitCnt, fillBits); - } - - // EOI - stbiw__putc(s, 0xFF); - stbiw__putc(s, 0xD9); - - return 1; -} - -STBIWDEF int stbi_write_jpg_to_func(stbi_write_func *func, void *context, int x, int y, int comp, const void *data, int quality) -{ - stbi__write_context s = { 0 }; - stbi__start_write_callbacks(&s, func, context); - return stbi_write_jpg_core(&s, x, y, comp, (void *) data, quality); -} - - -#ifndef STBI_WRITE_NO_STDIO -STBIWDEF int stbi_write_jpg(char const *filename, int x, int y, int comp, const void *data, int quality) -{ - stbi__write_context s = { 0 }; - if (stbi__start_write_file(&s,filename)) { - int r = stbi_write_jpg_core(&s, x, y, comp, data, quality); - stbi__end_write_file(&s); - return r; - } else - return 0; -} -#endif - -#endif // STB_IMAGE_WRITE_IMPLEMENTATION - -/* Revision history - 1.16 (2021-07-11) - make Deflate code emit uncompressed blocks when it would otherwise expand - support writing BMPs with alpha channel - 1.15 (2020-07-13) unknown - 1.14 (2020-02-02) updated JPEG writer to downsample chroma channels - 1.13 - 1.12 - 1.11 (2019-08-11) - - 1.10 (2019-02-07) - support utf8 filenames in Windows; fix warnings and platform ifdefs - 1.09 (2018-02-11) - fix typo in zlib quality API, improve STB_I_W_STATIC in C++ - 1.08 (2018-01-29) - add stbi__flip_vertically_on_write, external zlib, zlib quality, choose PNG filter - 1.07 (2017-07-24) - doc fix - 1.06 (2017-07-23) - writing JPEG (using Jon Olick's code) - 1.05 ??? - 1.04 (2017-03-03) - monochrome BMP expansion - 1.03 ??? - 1.02 (2016-04-02) - avoid allocating large structures on the stack - 1.01 (2016-01-16) - STBIW_REALLOC_SIZED: support allocators with no realloc support - avoid race-condition in crc initialization - minor compile issues - 1.00 (2015-09-14) - installable file IO function - 0.99 (2015-09-13) - warning fixes; TGA rle support - 0.98 (2015-04-08) - added STBIW_MALLOC, STBIW_ASSERT etc - 0.97 (2015-01-18) - fixed HDR asserts, rewrote HDR rle logic - 0.96 (2015-01-17) - add HDR output - fix monochrome BMP - 0.95 (2014-08-17) - add monochrome TGA output - 0.94 (2014-05-31) - rename private functions to avoid conflicts with stb_image.h - 0.93 (2014-05-27) - warning fixes - 0.92 (2010-08-01) - casts to unsigned char to fix warnings - 0.91 (2010-07-17) - first public release - 0.90 first internal release -*/ - -/* ------------------------------------------------------------------------------- -This software is available under 2 licenses -- choose whichever you prefer. ------------------------------------------------------------------------------- -ALTERNATIVE A - MIT License -Copyright (c) 2017 Sean Barrett -Permission is hereby granted, free of charge, to any person obtaining a copy of -this software and associated documentation files (the "Software"), to deal in -the Software without restriction, including without limitation the rights to -use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies -of the Software, and to permit persons to whom the Software is furnished to do -so, subject to the following conditions: -The above copyright notice and this permission notice shall be included in all -copies or substantial portions of the Software. -THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR -IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, -FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE -AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER -LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, -OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE -SOFTWARE. ------------------------------------------------------------------------------- -ALTERNATIVE B - Public Domain (www.unlicense.org) -This is free and unencumbered software released into the public domain. -Anyone is free to copy, modify, publish, use, compile, sell, or distribute this -software, either in source code form or as a compiled binary, for any purpose, -commercial or non-commercial, and by any means. -In jurisdictions that recognize copyright laws, the author or authors of this -software dedicate any and all copyright interest in the software to the public -domain. We make this dedication for the benefit of the public at large and to -the detriment of our heirs and successors. We intend this dedication to be an -overt act of relinquishment in perpetuity of all present and future rights to -this software under copyright law. -THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR -IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, -FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE -AUTHORS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN -ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION -WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. ------------------------------------------------------------------------------- -*/ diff --git a/tools/build_release.sh b/tools/build_release.sh deleted file mode 100755 index 540c332..0000000 --- a/tools/build_release.sh +++ /dev/null @@ -1,60 +0,0 @@ -#!/usr/bin/env bash -# Builds every release download into dist/release/ — for maintainers. -# -# tools/build_release.sh -# -# Needs: zig (cross-compiles all six platforms from one machine), python3, -# and node + npx for the VS Code package. Outputs: -# yapf-.zip command-line tool + shared/static library + header -# yapf_image-blender.zip Blender extension with libraries for all platforms -# yapf-preview.vsix VS Code extension -# yapf-figma.zip Figma plugin (import via manifest.json) -# yapf-photoshop.zip Photoshop scripts -# yapf-gimp-source.zip GIMP plugin source (build with gimptool) -# yapf-kde-source.zip Dolphin thumbnail plugin source (build with CMake) -set -euo pipefail -cd "$(dirname "$0")/.." -OUT=dist/release -LIBS=dist/libs -rm -rf "$OUT" "$LIBS" -mkdir -p "$OUT" "$LIBS" - -command -v zig >/dev/null || { echo "zig not found: https://ziglang.org/download/" >&2; exit 1; } -export ZIG_GLOBAL_CACHE_DIR=${ZIG_GLOBAL_CACHE_DIR:-$PWD/dist/.zig-cache} - -# zig target folder library tool -targets="x86_64-linux-gnu.2.17 linux-x64 libyapf.so yapf - aarch64-linux-gnu.2.17 linux-arm64 libyapf.so yapf - x86_64-windows-gnu windows-x64 yapf.dll yapf.exe - aarch64-windows-gnu windows-arm64 yapf.dll yapf.exe - x86_64-macos macos-x64 libyapf.dylib yapf - aarch64-macos macos-arm64 libyapf.dylib yapf" - -echo "$targets" | while read -r tgt dir lib tool; do - pkg=dist/pkg/yapf-$dir - rm -rf "$pkg" && mkdir -p "$pkg" "$LIBS/$dir" - zig cc -target "$tgt" -O2 -std=c99 -shared -fPIC -s yapf.c -o "$LIBS/$dir/$lib" - zig cc -target "$tgt" -O2 -std=c99 -s tools/yapf_cli.c yapf.c -o "$pkg/$tool" -lm - zig cc -target "$tgt" -O2 -std=c99 -c yapf.c -o "$pkg/yapf.o" - zig ar rcs "$pkg/libyapf.a" "$pkg/yapf.o" && rm "$pkg/yapf.o" - cp "$LIBS/$dir/$lib" yapf.h LICENSE "$pkg/" - rm -f "$pkg"/*.lib "$pkg"/*.pdb "$LIBS/$dir"/*.lib "$LIBS/$dir"/*.pdb - (cd dist/pkg && python3 -m zipfile -c "../../$OUT/yapf-$dir.zip" "yapf-$dir") - echo "built yapf-$dir.zip" -done - -python3 extensions/blender/build.py "$LIBS" -mv dist/yapf_image-blender.zip "$OUT/" - -if command -v npx >/dev/null; then - (cd extensions/vscode && npm run --silent package && mv yapf-preview-*.vsix "../../$OUT/yapf-preview.vsix") -else - echo "node/npx not found: skipped the VS Code package" >&2 -fi - -(cd extensions/figma && node build.js 2>/dev/null || true) -python3 -m zipfile -c "$OUT/yapf-figma.zip" extensions/figma/manifest.json extensions/figma/code.js extensions/figma/ui.html -python3 -m zipfile -c "$OUT/yapf-photoshop.zip" extensions/photoshop -python3 -m zipfile -c "$OUT/yapf-gimp-source.zip" extensions/gimp yapf.c yapf.h -python3 -m zipfile -c "$OUT/yapf-kde-source.zip" extensions/kde extensions/linux/yapf-mime.xml yapf.c yapf.h -ls -la "$OUT" diff --git a/tools/yapf_cli.c b/tools/yapf_cli.c deleted file mode 100644 index b18330b..0000000 --- a/tools/yapf_cli.c +++ /dev/null @@ -1,990 +0,0 @@ -/* - * yapf_cli.c — the `yapf` command-line tool. - * - * Copyright 2026 Nexoniarz - * - * Licensed under the Apache License, Version 2.0 (the "License"); - * you may not use this file except in compliance with the License. - * You may obtain a copy of the License at - * - * http://www.apache.org/licenses/LICENSE-2.0 - * - * Unless required by applicable law or agreed to in writing, software - * distributed under the License is distributed on an "AS IS" BASIS, - * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. - * See the License for the specific language governing permissions and - * limitations under the License. - * - * ------------------------------------------------------------------------- - * - * yapf [options] convert; formats chosen by extension - * yapf pack [options] - * yapf info print header, tables and notes - * yapf verify check every checksum and decode - * yapf bench time decoding - * yapf thumbnail [size] small preview (default 256) - * yapf compare [more…] size and decode speed: original vs YAPF - * - * Reads PNG (8 / 16-bit), JPEG, BMP, TGA, GIF (first frame), PSD, PNM, - * HDR (float) and YAPF. Writes YAPF, PNG, BMP, TGA, JPEG and HDR. - * Plain 8-bit 2D images are written as YAPF version 1; anything that - * needs version 2 (see `yapf` without arguments) is written as version 2. - * - * Build: cc -O2 -std=c99 -Ithird_party tools/yapf_cli.c yapf.c -o yapf -lm -pthread - */ - -#if !defined(_WIN32) && !defined(_POSIX_C_SOURCE) -# define _POSIX_C_SOURCE 200809L -#endif - -#include "../yapf.h" - -/* Third-party, public domain; keep their warnings out of our build. */ -#if defined(__GNUC__) || defined(__clang__) -# pragma GCC diagnostic push -# pragma GCC diagnostic ignored "-Wunused-function" -# pragma GCC diagnostic ignored "-Wunused-but-set-variable" -# pragma GCC diagnostic ignored "-Wsign-compare" -#endif -#define STB_IMAGE_IMPLEMENTATION -#define STBI_FAILURE_USERMSG -#include "../third_party/stb_image.h" -#define STB_IMAGE_WRITE_IMPLEMENTATION -#include "../third_party/stb_image_write.h" -#if defined(__GNUC__) || defined(__clang__) -# pragma GCC diagnostic pop -#endif - -#include -#include -#include -#include -#include - -static int ends_with(const char *s, const char *ext) { - size_t n = strlen(s), m = strlen(ext); - if (n < m) return 0; - for (size_t i = 0; i < m; i++) - if (tolower((unsigned char)s[n - m + i]) != ext[i]) return 0; - return 1; -} - -static int is_yapf(const char *path) { return ends_with(path, ".yapf"); } - -static double now_s(void) { -#if defined(_WIN32) - return (double)clock() / CLOCKS_PER_SEC; -#else - struct timespec t; - clock_gettime(CLOCK_MONOTONIC, &t); - return (double)t.tv_sec + (double)t.tv_nsec * 1e-9; -#endif -} - - -/* ── Options ─────────────────────────────────────────────────────────── */ - -typedef struct { - int mips, srgb, premult, v2, entropy, eight_bit, float32; - int coverage; /* alpha_ref, 0 = off */ - int format; /* block format, -1 = none */ - int normal; /* YAPF_NORMAL_* */ - int linear_alpha; - int primaries, transfer; - int have_map; - uint8_t map[4]; - double frame_ms; - int loops; - /* export selection */ - int mip, layer, face, frame, slice; - const char *author, *license, *source; - const char *notes[16]; - int nnotes; -} opts_t; - -static const struct { const char *name; uint8_t v; } ch_names[] = { - { "r", YAPF_CH_RED }, { "g", YAPF_CH_GREEN }, { "b", YAPF_CH_BLUE }, { "a", YAPF_CH_ALPHA }, - { "luma", YAPF_CH_LUMA }, { "nx", YAPF_CH_NORMAL_X }, { "ny", YAPF_CH_NORMAL_Y }, - { "nz", YAPF_CH_NORMAL_Z }, { "rough", YAPF_CH_ROUGHNESS }, { "gloss", YAPF_CH_GLOSS }, - { "metal", YAPF_CH_METALNESS }, { "ao", YAPF_CH_OCCLUSION }, { "height", YAPF_CH_HEIGHT }, - { "spec", YAPF_CH_SPECULAR }, { "emissive", YAPF_CH_EMISSIVE }, { "opacity", YAPF_CH_OPACITY }, - { "mask", YAPF_CH_MASK }, { "cavity", YAPF_CH_CAVITY }, { "thickness", YAPF_CH_THICKNESS }, - { "id", YAPF_CH_ID }, { "-", YAPF_CH_UNUSED }, { "default", YAPF_CH_DEFAULT } -}; - -static const char *ch_name(uint8_t v) { - for (size_t i = 0; i < sizeof(ch_names) / sizeof(ch_names[0]); i++) - if (ch_names[i].v == v) return ch_names[i].name; - return "?"; -} - -static const struct { const char *name; uint8_t v; } fmt_names[] = { - { "bc1", YAPF_GPU_BC1 }, { "bc3", YAPF_GPU_BC3 }, { "bc4", YAPF_GPU_BC4 }, - { "bc5", YAPF_GPU_BC5 }, { "bc6h", YAPF_GPU_BC6H }, { "bc7", YAPF_GPU_BC7 } -}; - -static const char *gpu_name(int g) { - static const char *px[] = { "RGBA8", "RGB8", "RG8", "R8", "SRGB8_A8", "SRGB8", - "RGBA16", "RGB16", "RG16", "R16", "RGBA16F", "RGB16F", "RG16F", "R16F", - "RGBA32F", "RGB32F", "RG32F", "R32F" }; - static const char *bc[] = { "BC1", "BC2", "BC3", "BC4", "BC4_SNORM", "BC5", "BC5_SNORM", - "BC6H", "BC6H_SF", "BC7" }; - static const char *etc[] = { "ETC2_RGB8", "ETC2_RGB8A1", "ETC2_RGBA8", "EAC_R11", - "EAC_R11_SNORM", "EAC_RG11", "EAC_RG11_SNORM" }; - static const char *astc[] = { "ASTC_4x4", "ASTC_5x4", "ASTC_5x5", "ASTC_6x5", "ASTC_6x6", - "ASTC_8x5", "ASTC_8x6", "ASTC_8x8", "ASTC_10x5", "ASTC_10x6", "ASTC_10x8", - "ASTC_10x10", "ASTC_12x10", "ASTC_12x12" }; - if (g >= 0 && g < 18) return px[g]; - if (g >= 0x40 && g < 0x4A) return bc[g - 0x40]; - if (g >= 0x50 && g < 0x57) return etc[g - 0x50]; - if (g >= 0x60 && g < 0x6E) return astc[g - 0x60]; - return "unknown"; -} - -static uint8_t gpu_hint(int ch, int srgb, int sample) { - static const uint8_t u8[2][4] = { { YAPF_GPU_R8, YAPF_GPU_RG8, YAPF_GPU_RGB8, YAPF_GPU_RGBA8 }, - { YAPF_GPU_R8, YAPF_GPU_RG8, YAPF_GPU_SRGB8, YAPF_GPU_SRGB8_A8 } }; - static const uint8_t wide[3][4] = { - { YAPF_GPU_R16, YAPF_GPU_RG16, YAPF_GPU_RGB16, YAPF_GPU_RGBA16 }, - { YAPF_GPU_R16F, YAPF_GPU_RG16F, YAPF_GPU_RGB16F, YAPF_GPU_RGBA16F }, - { YAPF_GPU_R32F, YAPF_GPU_RG32F, YAPF_GPU_RGB32F, YAPF_GPU_RGBA32F } }; - if (sample == YAPF_SAMPLE_U8) return u8[srgb ? 1 : 0][ch - 1]; - return wide[sample - 1][ch - 1]; -} - -static int parse_map(const char *s, uint8_t *map) { - memset(map, 0, 4); - for (int c = 0; c < 4 && *s; c++) { - const char *e = strchr(s, ','); - size_t n = e ? (size_t)(e - s) : strlen(s); - size_t i; - for (i = 0; i < sizeof(ch_names) / sizeof(ch_names[0]); i++) - if (strlen(ch_names[i].name) == n && strncmp(ch_names[i].name, s, n) == 0) break; - if (i == sizeof(ch_names) / sizeof(ch_names[0])) return 0; - map[c] = ch_names[i].v; - s += n + (e ? 1 : 0); - } - return 1; -} - -static const char *err_name(int e); - -/* ── Reading any input into a texture ────────────────────────────────── */ - -static yapf_texture_t *new_tex(uint32_t w, uint32_t h, int ch, int sample) { - yapf_texture_t d; - memset(&d, 0, sizeof(d)); - d.width = w; d.height = h; d.depth = 1; d.layers = 1; d.frames = 1; d.mip_levels = 1; - d.channels = (uint8_t)ch; d.sample = (uint8_t)sample; - return yapf_tex_create(&d); -} - -static yapf_texture_t *read_input(const char *path, const opts_t *o, int *from_yapf) { - *from_yapf = 0; - if (is_yapf(path)) { - int err = 0; - yapf_texture_t *t = yapf_tex_load(path, 0, 0, &err); - if (!t) fprintf(stderr, "yapf: cannot read %s: %s\n", path, err_name(err)); - *from_yapf = 1; - return t; - } - int w, h, ch; - yapf_texture_t *t = NULL; - if (stbi_is_hdr(path)) { - float *f = stbi_loadf(path, &w, &h, &ch, 0); - if (!f) { fprintf(stderr, "yapf: cannot read %s: %s\n", path, stbi_failure_reason()); return NULL; } - int sample = o->float32 ? YAPF_SAMPLE_F32 : YAPF_SAMPLE_F16; - t = new_tex((uint32_t)w, (uint32_t)h, ch, sample); - if (t) { - size_t n = (size_t)w * h * ch; - if (sample == YAPF_SAMPLE_F32) memcpy(t->data[0], f, n * 4); - else for (size_t i = 0; i < n; i++) ((uint16_t *)t->data[0])[i] = yapf_float_to_half(f[i]); - t->transfer = YAPF_TRANSFER_LINEAR; - } - stbi_image_free(f); - } else if (stbi_is_16_bit(path) && !o->eight_bit) { - stbi_us *p = stbi_load_16(path, &w, &h, &ch, 0); - if (!p) { fprintf(stderr, "yapf: cannot read %s: %s\n", path, stbi_failure_reason()); return NULL; } - t = new_tex((uint32_t)w, (uint32_t)h, ch, YAPF_SAMPLE_U16); - if (t) memcpy(t->data[0], p, (size_t)w * h * ch * 2); - stbi_image_free(p); - } else { - stbi_uc *p = stbi_load(path, &w, &h, &ch, 0); - if (!p) { fprintf(stderr, "yapf: cannot read %s: %s\n", path, stbi_failure_reason()); return NULL; } - t = new_tex((uint32_t)w, (uint32_t)h, ch, YAPF_SAMPLE_U8); - if (t) memcpy(t->data[0], p, (size_t)w * h * ch); - stbi_image_free(p); - } - if (!t) fprintf(stderr, "yapf: %s: unsupported size or out of memory\n", path); - return t; -} - -/* Several same-sized inputs into one cube / array / volume / animation. */ -static yapf_texture_t *assemble(const char *kind, int n, char **paths, const opts_t *o) { - yapf_texture_t *first = NULL, *t = NULL; - for (int i = 0; i < n; i++) { - int y; - yapf_texture_t *in = read_input(paths[i], o, &y); - if (!in) { yapf_tex_free(t); yapf_tex_free(first); return NULL; } - if (!t) { - yapf_texture_t d = *in; - d.mip_levels = 1; - if (strcmp(kind, "cube") == 0) { - if (n % 6) { fprintf(stderr, "yapf: a cube needs 6 faces per layer (+X -X +Y -Y +Z -Z)\n"); yapf_tex_free(in); return NULL; } - d.shape = YAPF_SHAPE_CUBE; d.layers = (uint16_t)(n / 6); - } else if (strcmp(kind, "array") == 0) { - d.layers = (uint16_t)n; - } else if (strcmp(kind, "volume") == 0) { - d.shape = YAPF_SHAPE_VOLUME; d.depth = (uint32_t)n; - } else if (strcmp(kind, "anim") == 0) { - d.frames = (uint16_t)n; - } else { - fprintf(stderr, "yapf: pack kind must be cube, array, volume or anim\n"); - yapf_tex_free(in); - return NULL; - } - t = yapf_tex_create(&d); - if (!t) { fprintf(stderr, "yapf: invalid %s (cube faces must be square)\n", kind); yapf_tex_free(in); return NULL; } - first = in; - } else if (in->width != t->width || in->height != t->height || - in->channels != t->channels || in->sample != t->sample) { - fprintf(stderr, "yapf: %s does not match the size and channels of %s\n", paths[i], paths[0]); - yapf_tex_free(in); yapf_tex_free(t); yapf_tex_free(first); - return NULL; - } - size_t bytes = yapf_tex_surface_bytes(in, 0); - if (t->shape == YAPF_SHAPE_VOLUME) memcpy((uint8_t *)t->data[0] + bytes * i, in->data[0], bytes); - else if (t->frames > 1) memcpy(t->data[yapf_tex_surface(t, (uint32_t)i, 0, 0, 0)], in->data[0], bytes); - else if (t->shape == YAPF_SHAPE_CUBE) memcpy(t->data[yapf_tex_surface(t, 0, (uint32_t)i / 6, (uint32_t)i % 6, 0)], in->data[0], bytes); - else memcpy(t->data[yapf_tex_surface(t, 0, (uint32_t)i, 0, 0)], in->data[0], bytes); - if (in != first) yapf_tex_free(in); - } - if (t && t->frames > 1) - for (int f = 0; f < t->frames; f++) t->frame_us[f] = (uint32_t)(o->frame_ms * 1000.0 + 0.5); - yapf_tex_free(first); - return t; -} - -/* ── Writing .yapf ───────────────────────────────────────────────────── */ - -static int needs_v2(const yapf_texture_t *t, const opts_t *o) { - return o->v2 || o->entropy || o->format >= 0 || o->coverage || o->normal || o->have_map || - o->linear_alpha || o->primaries || o->transfer || o->author || o->license || - o->source || o->nnotes || t->sample != YAPF_SAMPLE_U8 || t->shape != YAPF_SHAPE_2D || - t->layers > 1 || t->frames > 1 || t->payload != YAPF_PAYLOAD_PIXELS || t->note_count; -} - -static int write_yapf(yapf_texture_t *t, const char *out, const opts_t *o, int from_yapf) { - if (!from_yapf) { - t->flags = (uint8_t)((o->srgb && t->sample == YAPF_SAMPLE_U8 && !o->normal ? YAPF_FLAG_SRGB : 0) | - (o->premult ? YAPF_FLAG_PREMULT_ALPHA : 0)); - t->format = gpu_hint(t->channels, t->flags & YAPF_FLAG_SRGB, t->sample); - } - if (o->normal) { - t->normal = (uint8_t)o->normal; - t->channel_map[0] = YAPF_CH_NORMAL_X; - t->channel_map[1] = YAPF_CH_NORMAL_Y; - if (t->channels >= 3) t->channel_map[2] = YAPF_CH_NORMAL_Z; - else t->normal |= YAPF_NORMAL_XY; - t->flags &= (uint8_t)~YAPF_FLAG_SRGB; - } - if (o->have_map) memcpy(t->channel_map, o->map, 4); - if (o->linear_alpha && (t->channels == 2 || t->channels == 4)) - t->linear_mask |= (uint8_t)(1u << (t->channels - 1)); - if (o->primaries) t->primaries = (uint8_t)o->primaries; - if (o->transfer) t->transfer = (uint8_t)o->transfer; - if (o->frame_ms > 0 && t->frames > 1) - for (int f = 0; f < t->frames; f++) t->frame_us[f] = (uint32_t)(o->frame_ms * 1000.0 + 0.5); - if (o->loops >= 0) t->loop_count = (uint16_t)o->loops; - - if (o->mips && t->payload == YAPF_PAYLOAD_PIXELS) { - int rc = yapf_tex_build_mips(t, 0, (uint8_t)o->coverage); - if (rc != YAPF_OK) { - fprintf(stderr, "yapf: cannot build mips%s\n", o->coverage ? " (--coverage needs an alpha channel)" : ""); - return 1; - } - } - int v2 = needs_v2(t, o); - if (o->format >= 0) { - yapf_texture_t *c = NULL; - int rc = yapf_tex_compress(t, (uint8_t)o->format, &c); - if (rc != YAPF_OK) { - fprintf(stderr, "yapf: cannot compress to %s: %s\n", gpu_name(o->format), - o->format == YAPF_GPU_BC6H ? "BC6H needs a 16-bit or HDR (float) image" - : "LDR block formats need an 8-bit image"); - return 1; - } - opts_t rest = *o; /* the blocks are made: write them */ - rest.format = -1; - rest.mips = 0; - rest.v2 = 1; - int r2 = write_yapf(c, out, &rest, 1); - yapf_tex_free(c); - return r2; - } - if (!v2) { - /* 8-bit 2D: version 1, readable by every YAPF decoder */ - yapf_image_t img; - memset(&img, 0, sizeof(img)); - img.width = t->width; img.height = t->height; img.channels = t->channels; - img.gpu_format = t->format; img.flags = t->flags; img.mip_levels = t->mip_levels; - img.mips = (uint8_t **)t->data; - img.pixels = (uint8_t *)t->data[0]; - if (yapf_save(out, &img) != YAPF_OK) { fprintf(stderr, "yapf: cannot write %s\n", out); return 1; } - return 0; - } - if (!yapf_tex_find_note(t, "TOOL")) yapf_tex_add_note(t, "TOOL", "yapf command-line tool", 22); - if (o->author) yapf_tex_add_note(t, "AUTH", o->author, (uint32_t)strlen(o->author)); - if (o->license) yapf_tex_add_note(t, "LICN", o->license, (uint32_t)strlen(o->license)); - if (o->source) yapf_tex_add_note(t, "SRCE", o->source, (uint32_t)strlen(o->source)); - for (int i = 0; i < o->nnotes; i++) { - const char *eq = strchr(o->notes[i], '='); - if (!eq || eq - o->notes[i] != 4) { fprintf(stderr, "yapf: --note wants TAG=text with a 4-letter tag\n"); return 1; } - yapf_tex_add_note(t, o->notes[i], eq + 1, (uint32_t)strlen(eq + 1)); - } - if (yapf_tex_save(out, t, o->entropy ? YAPF_ENC_ENTROPY : 0) != YAPF_OK) { - fprintf(stderr, "yapf: cannot write %s\n", out); - return 1; - } - return 0; -} - -/* ── Exporting a surface to a common format ──────────────────────────── */ - -/* One surface slice as 8-bit pixels (*hdr = 0) or float RGB(A) (*hdr = 1). */ -static void *surface_view(const yapf_texture_t *t, uint32_t s, uint32_t slice, - uint32_t *w, uint32_t *h, int *ch, int *hdr) -{ - uint32_t m = s % t->mip_levels, d; - yapf_tex_mip_size(t, m, w, h, &d); - if (slice >= d) return NULL; - size_t n = (size_t)*w * *h, slice_bytes = yapf_tex_surface_bytes(t, m) / d; - const uint8_t *src = (const uint8_t *)t->data[s] + slice_bytes * slice; - *hdr = 0; - if (t->payload == YAPF_PAYLOAD_BLOCKS) { - int is6 = t->format == YAPF_GPU_BC6H || t->format == YAPF_GPU_BC6H_SF; - void *out = malloc(n * (is6 ? 6 : 4)); - if (!out) return NULL; - if (yapf_blocks_decode(t->format, src, *w, *h, out) != YAPF_OK) { free(out); return NULL; } - if (!is6) { *ch = 4; return out; } - float *f = (float *)malloc(n * 3 * sizeof(float)); - for (size_t i = 0; f && i < n * 3; i++) f[i] = yapf_half_to_float(((uint16_t *)out)[i]); - free(out); - *ch = 3; *hdr = 1; - return f; - } - *ch = t->channels; - if (t->sample == YAPF_SAMPLE_U8) { - uint8_t *o = (uint8_t *)malloc(n * *ch); - if (o) memcpy(o, src, n * *ch); - return o; - } - if (t->sample == YAPF_SAMPLE_U16) { - uint8_t *o = (uint8_t *)malloc(n * *ch); - for (size_t i = 0; o && i < n * *ch; i++) o[i] = (uint8_t)((((const uint16_t *)src)[i] + 128) / 257); - return o; - } - float *f = (float *)malloc(n * *ch * sizeof(float)); - for (size_t i = 0; f && i < n * *ch; i++) - f[i] = t->sample == YAPF_SAMPLE_F16 ? yapf_half_to_float(((const uint16_t *)src)[i]) - : ((const float *)src)[i]; - *hdr = 1; - return f; -} - -static uint8_t *to8(const float *f, size_t n) { - uint8_t *o = (uint8_t *)malloc(n); - for (size_t i = 0; o && i < n; i++) { - float v = f[i] < 0 ? 0 : f[i] > 1 ? 1 : f[i]; - o[i] = (uint8_t)(v * 255.0f + 0.5f); - } - return o; -} - -/* 16-bit PNG (stb_image_write only writes 8 bits): rows of big-endian - * samples, filter 0, compressed with stb's zlib. */ -static uint32_t png_crc(const uint8_t *p, size_t n, uint32_t c) { - c = ~c; - for (size_t i = 0; i < n; i++) { - c ^= p[i]; - for (int k = 0; k < 8; k++) c = (c >> 1) ^ (0xEDB88320u & (0u - (c & 1))); - } - return ~c; -} - -static void png_chunk(FILE *f, const char *type, const uint8_t *d, uint32_t n) { - uint8_t b[4] = { (uint8_t)(n >> 24), (uint8_t)(n >> 16), (uint8_t)(n >> 8), (uint8_t)n }; - fwrite(b, 1, 4, f); - fwrite(type, 1, 4, f); - if (n) fwrite(d, 1, n, f); - uint32_t c = png_crc(d, n, png_crc((const uint8_t *)type, 4, 0)); - uint8_t cb[4] = { (uint8_t)(c >> 24), (uint8_t)(c >> 16), (uint8_t)(c >> 8), (uint8_t)c }; - fwrite(cb, 1, 4, f); -} - -static int write_png16(const char *path, const uint16_t *px, int w, int h, int ch) { - size_t row = (size_t)w * ch * 2 + 1; - uint8_t *raw = (uint8_t *)malloc(row * h); - if (!raw) return 0; - for (int y = 0; y < h; y++) { - uint8_t *r = raw + row * y; - r[0] = 0; - for (int i = 0; i < w * ch; i++) { - uint16_t v = px[(size_t)y * w * ch + i]; - r[1 + 2 * i] = (uint8_t)(v >> 8); - r[2 + 2 * i] = (uint8_t)v; - } - } - int zlen = 0; - uint8_t *z = stbi_zlib_compress(raw, (int)(row * h), &zlen, 8); - free(raw); - FILE *f = z ? fopen(path, "wb") : NULL; - if (!f) { STBIW_FREE(z); return 0; } - static const uint8_t sig[8] = { 0x89, 'P', 'N', 'G', 13, 10, 26, 10 }; - static const uint8_t ctype[5] = { 0, 0, 4, 2, 6 }; - uint8_t ihdr[13] = { (uint8_t)(w >> 24), (uint8_t)(w >> 16), (uint8_t)(w >> 8), (uint8_t)w, - (uint8_t)(h >> 24), (uint8_t)(h >> 16), (uint8_t)(h >> 8), (uint8_t)h, - 16, ctype[ch], 0, 0, 0 }; - fwrite(sig, 1, 8, f); - png_chunk(f, "IHDR", ihdr, 13); - png_chunk(f, "IDAT", z, (uint32_t)zlen); - png_chunk(f, "IEND", NULL, 0); - STBIW_FREE(z); - return fclose(f) == 0; -} - -static int write_image(const char *path, const void *px, int w, int h, int ch, int hdr) { - if (ends_with(path, ".hdr")) { - if (!hdr) { - float *f = (float *)malloc((size_t)w * h * ch * sizeof(float)); - for (size_t i = 0; f && i < (size_t)w * h * ch; i++) f[i] = ((const uint8_t *)px)[i] / 255.0f; - int ok = f && stbi_write_hdr(path, w, h, ch, f); - free(f); - return ok; - } - return stbi_write_hdr(path, w, h, ch, (const float *)px); - } - uint8_t *tmp = NULL; - if (hdr) { - tmp = to8((const float *)px, (size_t)w * h * ch); - if (!tmp) return 0; - fprintf(stderr, "yapf: note: float pixels clamped to 0..1 for %s (use .hdr to keep them)\n", path); - px = tmp; - } - int ok = 0; - if (ends_with(path, ".png")) ok = stbi_write_png(path, w, h, ch, px, w * ch); - else if (ends_with(path, ".bmp")) ok = stbi_write_bmp(path, w, h, ch, px); - else if (ends_with(path, ".tga")) ok = stbi_write_tga(path, w, h, ch, px); - else if (ends_with(path, ".jpg") || ends_with(path, ".jpeg")) ok = stbi_write_jpg(path, w, h, ch, px, 95); - else fprintf(stderr, "yapf: unsupported output format: %s (use .yapf .png .bmp .tga .jpg .hdr)\n", path); - free(tmp); - return ok; -} - -static int export_image(const yapf_texture_t *t, const char *in, const char *out, const opts_t *o) { - uint32_t faces = yapf_tex_faces(t); - if ((uint32_t)o->mip >= t->mip_levels || (uint32_t)o->layer >= t->layers || - (uint32_t)o->face >= faces || (uint32_t)o->frame >= t->frames) { - fprintf(stderr, "yapf: %s has %u mip(s), %u layer(s), %u face(s), %u frame(s)\n", - in, t->mip_levels, t->layers, faces, t->frames); - return 1; - } - uint32_t s = yapf_tex_surface(t, (uint32_t)o->frame, (uint32_t)o->layer, (uint32_t)o->face, (uint32_t)o->mip); - uint32_t w, h; - int ch, hdr; - void *px = surface_view(t, s, (uint32_t)o->slice, &w, &h, &ch, &hdr); - if (!px) { - fprintf(stderr, "yapf: cannot export %s: %s\n", in, - t->payload == YAPF_PAYLOAD_BLOCKS ? "no built-in decoder for this block format (ETC2 / ASTC)" - : "no such slice, or out of memory"); - return 1; - } - int ok; - if (t->payload == YAPF_PAYLOAD_PIXELS && t->sample == YAPF_SAMPLE_U16 && ends_with(out, ".png")) { - /* keep all 16 bits */ - uint32_t m = s % t->mip_levels, d; - yapf_tex_mip_size(t, m, NULL, NULL, &d); - const uint16_t *src = (const uint16_t *)((const uint8_t *)t->data[s] + - yapf_tex_surface_bytes(t, m) / d * (uint32_t)o->slice); - ok = write_png16(out, src, (int)w, (int)h, t->channels); - } else { - if (t->sample == YAPF_SAMPLE_U16 && !ends_with(out, ".hdr")) - fprintf(stderr, "yapf: note: 16-bit samples written as 8-bit (use .png to keep them)\n"); - ok = write_image(out, px, (int)w, (int)h, ch, hdr); - } - free(px); - if (!ok) { fprintf(stderr, "yapf: cannot write %s\n", out); return 1; } - return 0; -} - -/* ── info / verify / bench / thumbnail ───────────────────────────────── */ - -static uint8_t *read_all(const char *path, size_t *n) { - FILE *f = fopen(path, "rb"); - if (!f) return NULL; - fseek(f, 0, SEEK_END); - long sz = ftell(f); - rewind(f); - uint8_t *buf = sz >= 0 ? (uint8_t *)malloc((size_t)sz + 1) : NULL; - if (buf && fread(buf, 1, (size_t)sz, f) != (size_t)sz) { free(buf); buf = NULL; } - fclose(f); - *n = buf ? (size_t)sz : 0; - return buf; -} - -static const char *err_name(int e) { - switch (e) { - case YAPF_ERR_INVALID: return "invalid argument"; - case YAPF_ERR_IO: return "cannot read the file"; - case YAPF_ERR_OOM: return "out of memory"; - case YAPF_ERR_CORRUPT: return "corrupt or not a YAPF file"; - case YAPF_ERR_UNSUPPORTED: return "needs a feature this decoder does not have"; - case YAPF_ERR_CHECKSUM: return "checksum mismatch (damaged file)"; - case YAPF_ERR_TRUNCATED: return "file is truncated"; - default: return "error"; - } -} - -static int cmd_info(const char *path) { - size_t n; - uint8_t *buf = read_all(path, &n); - int err = 0; - yapf_texture_t *t = buf ? yapf_tex_open(buf, n, 0, &err) : NULL; - if (!t) { - fprintf(stderr, "yapf: %s: %s\n", path, buf ? err_name(err) : "cannot open"); - free(buf); - return 1; - } - static const char *shape[] = { "2D", "cube", "volume" }; - static const char *sample[] = { "8-bit", "16-bit", "half float", "float" }; - static const char *prim[] = { "unspecified", "BT.709 / sRGB", "Display P3", "BT.2020", - "ACES AP0", "ACEScg", "Adobe RGB" }; - static const char *tf[] = { "unspecified", "sRGB", "linear", "gamma 2.2", "PQ", "HLG", "BT.1886" }; - static const char *mf[] = { "unknown", "box", "tent", "Kaiser", "Lanczos", "Mitchell", "authored" }; - uint32_t w, h, d; - yapf_tex_mip_size(t, 0, &w, &h, &d); - printf("%s\n", path); - printf(" format version : %u\n", buf[4]); - printf(" size : %u x %u%s", w, h, t->shape == YAPF_SHAPE_VOLUME ? "" : "\n"); - if (t->shape == YAPF_SHAPE_VOLUME) printf(" x %u\n", d); - printf(" shape : %s, %u layer(s), %u frame(s)\n", shape[t->shape], t->layers, t->frames); - printf(" mip levels : %u\n", t->mip_levels); - if (t->payload == YAPF_PAYLOAD_BLOCKS) - printf(" payload : GPU blocks, %s (%u channel(s))\n", gpu_name(t->format), t->channels); - else - printf(" payload : lossless pixels, %u channel(s), %s, GPU hint %s\n", - t->channels, sample[t->sample], gpu_name(t->format)); - printf(" flags : %s%s%s\n", t->flags & YAPF_FLAG_SRGB ? "sRGB" : "linear", - t->flags & YAPF_FLAG_PREMULT_ALPHA ? ", premultiplied alpha" : "", - t->flags & YAPF_FLAG_COVERAGE ? ", coverage-preserving mips" : ""); - if (buf[4] == 2) { - uint32_t needs = (uint32_t)buf[0x1C] | (uint32_t)buf[0x1D] << 8; - printf(" needs : %s%s%s%s%s%s\n", needs ? "" : "nothing beyond 8-bit 2D", - needs & YAPF_NEED_WIDE ? "wide " : "", needs & YAPF_NEED_BLOCKS ? "blocks " : "", - needs & YAPF_NEED_ENTROPY ? "entropy " : "", needs & YAPF_NEED_LAYOUT ? "layout " : "", - needs & YAPF_NEED_FRAMES ? "frames" : ""); - printf(" channels :"); - for (int c = 0; c < t->channels; c++) - printf(" %s%s", ch_name(t->channel_map[c]), t->linear_mask & (1u << c) ? "(linear)" : ""); - printf("\n"); - if (t->normal) - printf(" normal map : %s, %s\n", - (t->normal & 3) == YAPF_NORMAL_GL ? "OpenGL (+Y)" : (t->normal & 3) == YAPF_NORMAL_DX ? "DirectX (-Y)" : "no convention", - t->normal & YAPF_NORMAL_XY ? "XY (Z reconstructed)" : t->normal & YAPF_NORMAL_OCT ? "octahedral" : "XYZ"); - printf(" colour : primaries %s, transfer %s\n", - t->primaries < 7 ? prim[t->primaries] : "?", t->transfer < 7 ? tf[t->transfer] : "?"); - if (t->mip_levels > 1) - printf(" mip filter : %s%s%s\n", (t->mip_filter & 0x7F) < 7 ? mf[t->mip_filter & 0x7F] : "?", - t->mip_filter & YAPF_MIP_LINEAR_LIGHT ? ", linear light" : "", - t->flags & YAPF_FLAG_COVERAGE ? "" : ""); - if (t->flags & YAPF_FLAG_COVERAGE) printf(" alpha ref : %u\n", t->alpha_ref); - if (t->frames > 1) - printf(" animation : %u frames, first %.1f ms, loops %s\n", t->frames, - t->frame_us ? t->frame_us[0] / 1000.0 : 0.0, t->loop_count ? "" : "forever"); - for (uint32_t i = 0; i < t->note_count; i++) { - const yapf_note_t *nt = &t->notes[i]; - int text = 1; - for (uint32_t k = 0; k < nt->size; k++) if (nt->data[k] < 9) text = 0; - if (text && nt->size < 200) printf(" note %.4s : %.*s\n", nt->tag, (int)nt->size, nt->data); - else printf(" note %.4s : %u bytes\n", nt->tag, nt->size); - } - printf(" stream prefix :"); - for (uint32_t m = t->mip_levels; m-- > 0; ) { - uint32_t mw; - yapf_tex_mip_size(t, m, &mw, NULL, NULL); - printf(" %u px: %llu B%s", mw, (unsigned long long)yapf_tex_stream_bytes(t, m), m ? "," : "\n"); - } - } - size_t raw = 0; - for (uint32_t s = 0; s < yapf_tex_surface_count(t); s++) { - uint32_t mw, mh, md; - yapf_tex_mip_size(t, s % t->mip_levels, &mw, &mh, &md); - raw += (size_t)mw * mh * md * t->channels * (t->payload ? 1 : yapf_sample_bytes(t->sample)); - } - printf(" file size : %zu bytes (%.1f%% of raw)\n", n, 100.0 * (double)n / (double)raw); - yapf_tex_free(t); - t = yapf_tex_load_memory(buf, n, 0, 0, &err); - printf(" decodes : %s\n", t ? "ok (checksums verified)" : err_name(err)); - yapf_tex_free(t); - free(buf); - return t ? 0 : 1; -} - -static int cmd_verify(const char *path) { - size_t n; - uint8_t *buf = read_all(path, &n); - int err = YAPF_ERR_IO; - yapf_texture_t *t = buf ? yapf_tex_load_memory(buf, n, 0, 0, &err) : NULL; - if (t) printf("%s: ok%s\n", path, buf[4] == 2 ? " (header, tables and every tile checksum match)" - : " (version 1: decodes; no checksums in v1)"); - else printf("%s: FAILED — %s\n", path, err_name(err)); - yapf_tex_free(t); - free(buf); - return t ? 0 : 1; -} - -static int cmd_bench(const char *path) { - size_t n; - uint8_t *buf = read_all(path, &n); - if (!buf) { fprintf(stderr, "yapf: cannot open %s\n", path); return 1; } - int err; - yapf_texture_t *t = yapf_tex_load_memory(buf, n, 0, 1, &err); - if (!t) { fprintf(stderr, "yapf: %s: %s\n", path, err_name(err)); free(buf); return 1; } - double raw = 0; - for (uint32_t s = 0; s < yapf_tex_surface_count(t); s++) raw += (double)yapf_tex_surface_bytes(t, s % t->mip_levels); - yapf_tex_free(t); - for (int mode = 0; mode < 3; mode++) { - int threads = mode == 1 ? 0 : 1, flags = mode == 2 ? YAPF_LOAD_TRUST : 0; - if (mode == 2 && buf[4] != 2) break; - /* Best of 15 rounds; each round repeats enough decodes to last - * ~20 ms, so short images are measured warm and not timer-bound. */ - double one = now_s(); - yapf_tex_free(yapf_tex_load_memory(buf, n, flags, threads, NULL)); - one = now_s() - one; - int reps = (int)(0.02 / (one > 1e-6 ? one : 1e-6)) + 1; - double best = 1e9; - for (int r = 0; r < 15; r++) { - double tt = now_s(); - for (int k = 0; k < reps; k++) yapf_tex_free(yapf_tex_load_memory(buf, n, flags, threads, NULL)); - tt = (now_s() - tt) / reps; - if (tt < best) best = tt; - } - static const char *nm[] = { "1 thread", "all cores", "no checks" }; - printf(" %-12s %8.3f ms %6.2f GB/s\n", nm[mode], best * 1e3, raw / best / 1e9); - } - free(buf); - return 0; -} - -/* Preview no larger than size×size: start from the smallest mip that is - * still big enough, then average boxes of source pixels. */ -static int cmd_thumbnail(const char *in, const char *out, int size) { - int err; - yapf_texture_t *t = yapf_tex_load(in, 0, 0, &err); - if (!t) { fprintf(stderr, "yapf: cannot read %s: %s\n", in, err_name(err)); return 1; } - if (size < 1) size = 256; - int m = 0; - while (m + 1 < t->mip_levels && - (int)(t->width >> (m + 1)) >= size && (int)(t->height >> (m + 1)) >= size) - m++; - uint32_t sw, sh; - int ch, hdr; - uint8_t *src = (uint8_t *)surface_view(t, (uint32_t)m, 0, &sw, &sh, &ch, &hdr); - yapf_tex_free(t); - if (!src) { fprintf(stderr, "yapf: cannot preview %s\n", in); return 1; } - if (hdr) { - uint8_t *b = to8((const float *)src, (size_t)sw * sh * ch); - free(src); - if (!(src = b)) return 1; - } - double k = (double)size / (double)(sw > sh ? sw : sh); - if (k > 1.0) k = 1.0; - uint32_t dw = (uint32_t)(sw * k + 0.5), dh = (uint32_t)(sh * k + 0.5); - if (dw < 1) dw = 1; - if (dh < 1) dh = 1; - uint8_t *dst = (uint8_t *)malloc((size_t)dw * dh * ch); - if (!dst) { free(src); return 1; } - for (uint32_t y = 0; y < dh; y++) { - uint32_t y0 = (uint32_t)((uint64_t)y * sh / dh), y1 = (uint32_t)((uint64_t)(y + 1) * sh / dh); - if (y1 <= y0) y1 = y0 + 1; - for (uint32_t x = 0; x < dw; x++) { - uint32_t x0 = (uint32_t)((uint64_t)x * sw / dw), x1 = (uint32_t)((uint64_t)(x + 1) * sw / dw); - if (x1 <= x0) x1 = x0 + 1; - for (int c = 0; c < ch; c++) { - uint64_t sum = 0; - for (uint32_t yy = y0; yy < y1; yy++) - for (uint32_t xx = x0; xx < x1; xx++) - sum += src[((size_t)yy * sw + xx) * ch + c]; - uint64_t nn = (uint64_t)(y1 - y0) * (x1 - x0); - dst[((size_t)y * dw + x) * ch + c] = (uint8_t)((sum + nn / 2) / nn); - } - } - } - int ok = stbi_write_png(out, (int)dw, (int)dh, ch, dst, (int)dw * ch); - free(dst); - free(src); - if (!ok) fprintf(stderr, "yapf: cannot write %s\n", out); - return ok ? 0 : 1; -} - -/* Best time over several rounds of a decode call, for fair small-image timing. */ -#define YAPF_TIME_BEST(result, expr) \ - do { \ - double one_ = now_s(); { expr; } one_ = now_s() - one_; \ - int reps_ = (int)(0.02 / (one_ > 1e-6 ? one_ : 1e-6)) + 1; \ - double best_ = 1e9; \ - for (int r_ = 0; r_ < 9; r_++) { \ - double t_ = now_s(); \ - for (int k_ = 0; k_ < reps_; k_++) { expr; } \ - t_ = (now_s() - t_) / reps_; \ - if (t_ < best_) best_ = t_; \ - } \ - (result) = best_; \ - } while (0) - -static const char *fmt_kb(double bytes, char *buf) { - if (bytes >= 1024.0 * 1024.0) sprintf(buf, "%.2f MB", bytes / (1024.0 * 1024.0)); - else sprintf(buf, "%.1f KB", bytes / 1024.0); - return buf; -} - -static const char *ext_name(const char *path) { - const char *dot = strrchr(path, '.'); - static char name[8]; - size_t i = 0; - if (!dot) return "file"; - for (dot++; *dot && i < sizeof(name) - 1; dot++) name[i++] = (char)toupper((unsigned char)*dot); - name[i] = 0; - return name; -} - -/* Original format vs YAPF: size, decode time (1 thread / all cores), - * and a lossless check. */ -static int cmd_compare(int n, char **paths) { - int rc = 0; - double tot_src = 0, tot_yapf = 0, tot_src_t = 0, tot_yapf_t = 0, tot_ent = 0; - for (int i = 0; i < n; i++) { - const char *path = paths[i]; - if (is_yapf(path)) { - fprintf(stderr, "yapf: compare takes the original image (PNG, JPG, ...), not %s\n", path); - rc = 1; - continue; - } - FILE *f = fopen(path, "rb"); - if (!f) { fprintf(stderr, "yapf: cannot open %s\n", path); rc = 1; continue; } - fseek(f, 0, SEEK_END); - long fsz = ftell(f); - rewind(f); - uint8_t *src = (uint8_t *)malloc((size_t)fsz); - if (!src || fread(src, 1, (size_t)fsz, f) != (size_t)fsz) { fclose(f); free(src); rc = 1; continue; } - fclose(f); - - int w, h, ch; - uint8_t *px = stbi_load_from_memory(src, (int)fsz, &w, &h, &ch, 0); - if (!px) { fprintf(stderr, "yapf: cannot read %s: %s\n", path, stbi_failure_reason()); free(src); rc = 1; continue; } - - yapf_image_t img; - memset(&img, 0, sizeof(img)); - img.width = (uint32_t)w; img.height = (uint32_t)h; img.channels = (uint8_t)ch; - img.mip_levels = 1; img.pixels = px; img.flags = YAPF_FLAG_SRGB; - img.gpu_format = gpu_hint(ch, 1, YAPF_SAMPLE_U8); - - void *enc = NULL; - size_t esz = 0; - double t_enc = now_s(); - int erc = yapf_encode(&img, &enc, &esz); - t_enc = now_s() - t_enc; - if (erc != YAPF_OK) { fprintf(stderr, "yapf: cannot encode %s\n", path); stbi_image_free(px); free(src); rc = 1; continue; } - - yapf_image_t *chk = yapf_load_memory(enc, esz); - int lossless = chk && memcmp(chk->pixels, px, (size_t)w * h * ch) == 0; - yapf_free(chk); - - double t_src, t_one, t_all; - int dw, dh, dc; - YAPF_TIME_BEST(t_src, stbi_image_free(stbi_load_from_memory(src, (int)fsz, &dw, &dh, &dc, 0))); - YAPF_TIME_BEST(t_one, yapf_free(yapf_load_memory(enc, esz))); - YAPF_TIME_BEST(t_all, yapf_free(yapf_load_memory_mt(enc, esz, 0))); - - double raw = (double)w * h * ch; - char a[32], b[32], c[32]; - static const char *chn[] = { "", "gray", "gray+alpha", "RGB", "RGBA" }; - printf("%s (%d x %d, %s)\n", path, w, h, chn[ch]); - printf(" %-5s %10s\n", "raw", fmt_kb(raw, c)); - printf(" %-5s %10s %5.1f%% of raw decode %8.3f ms\n", ext_name(path), fmt_kb((double)fsz, a), - 100.0 * fsz / raw, t_src * 1e3); - printf(" %-5s %10s %5.1f%% of raw decode %8.3f ms %.1fx faster, %.0f%% of the %s size\n", - "YAPF", fmt_kb((double)esz, b), 100.0 * esz / raw, t_one * 1e3, - t_src / t_one, 100.0 * esz / fsz, ext_name(path)); - /* version 2 with the optional Huffman planes */ - { - yapf_texture_t v; - void *data[1] = { px }; - size_t esz2 = 0; - void *enc2 = NULL; - double t_e; - memset(&v, 0, sizeof(v)); - v.width = (uint32_t)w; v.height = (uint32_t)h; v.depth = 1; v.layers = 1; v.frames = 1; - v.mip_levels = 1; v.channels = (uint8_t)ch; v.flags = YAPF_FLAG_SRGB; v.data = data; - if (yapf_tex_encode(&v, YAPF_ENC_ENTROPY, &enc2, &esz2) == YAPF_OK) { - yapf_texture_t *c2 = yapf_tex_load_memory(enc2, esz2, 0, 1, NULL); - if (!c2 || memcmp(c2->data[0], px, (size_t)w * h * ch) != 0) lossless = 0; - yapf_tex_free(c2); - YAPF_TIME_BEST(t_e, yapf_tex_free(yapf_tex_load_memory(enc2, esz2, 0, 1, NULL))); - printf(" %-5s %10s %5.1f%% of raw decode %8.3f ms %.1fx faster, %.0f%% of the %s size\n", - "YAPF+E", fmt_kb((double)esz2, c), 100.0 * esz2 / raw, t_e * 1e3, - t_src / t_e, 100.0 * esz2 / fsz, ext_name(path)); - tot_ent += (double)esz2; - yapf_free_buffer(enc2); - } - } - printf(" YAPF on all cores: decode %.3f ms (%.1f GB/s), encode %.0f ms, %s\n\n", - t_all * 1e3, raw / t_all / 1e9, t_enc * 1e3, - lossless ? "lossless: yes" : "LOSSLESS CHECK FAILED"); - if (!lossless) rc = 1; - tot_src += (double)fsz; tot_yapf += (double)esz; tot_src_t += t_src; tot_yapf_t += t_one; - yapf_free_buffer(enc); - stbi_image_free(px); - free(src); - } - if (n > 1 && tot_yapf_t > 0) { - char a[32], b[32]; - char e[32]; - printf("Total: originals %s, YAPF %s (%.0f%%), YAPF+E %s (%.0f%%); decoding %.1fx faster on one core\n", - fmt_kb(tot_src, a), fmt_kb(tot_yapf, b), 100.0 * tot_yapf / tot_src, - fmt_kb(tot_ent, e), 100.0 * tot_ent / tot_src, tot_src_t / tot_yapf_t); - } - return rc; -} - -static void usage(void) { - fprintf(stderr, - "usage: yapf [options] convert (formats by extension)\n" - " yapf pack [options]\n" - " yapf info header, tables and notes\n" - " yapf verify check every checksum\n" - " yapf bench time decoding\n" - " yapf thumbnail [size] preview, default 256 px\n" - " yapf compare [more...] size and speed vs the original format\n" - "\n" - "reads: .yapf .png (8/16-bit) .jpg .bmp .tga .gif .psd .pnm .hdr\n" - "writes: .yapf .png .jpg .bmp .tga .hdr\n" - "\n" - "options when writing .yapf:\n" - " --mips store a full mip chain (sRGB averaged in linear light)\n" - " --coverage REF mips keep alpha-test coverage at alpha REF (0-255)\n" - " --format F GPU blocks: bc1 bc3 bc4 bc5 bc6h bc7\n" - " --entropy Huffman-coded planes: smaller, slower to decode\n" - " --linear pixels are linear, not sRGB\n" - " --premult alpha is premultiplied\n" - " --linear-alpha alpha is linear even in an sRGB image\n" - " --normal gl|dx normal map (OpenGL +Y / DirectX -Y); implies linear\n" - " --map a,b,c,d channel meanings: r g b a luma nx ny nz rough gloss metal\n" - " ao height spec emissive opacity mask cavity thickness id -\n" - " --primaries P bt709 p3 bt2020 aces acescg adobe\n" - " --transfer T srgb linear gamma22 pq hlg bt1886\n" - " --8bit read 16-bit images as 8-bit\n" - " --float32 keep .hdr input as 32-bit float (default half)\n" - " --frame-ms N animation frame time (pack anim), --loops N\n" - " --author S --license S --source S --note TAG=text\n" - " --v2 write version 2 even for a plain 8-bit image\n" - "options when reading .yapf:\n" - " --mip N --layer N --face N --frame N --slice N which image to export\n"); -} - -static int parse_opts(int argc, char **argv, int start, opts_t *o) { - static const char *prim[] = { "", "bt709", "p3", "bt2020", "aces", "acescg", "adobe" }; - static const char *tf[] = { "", "srgb", "linear", "gamma22", "pq", "hlg", "bt1886" }; - memset(o, 0, sizeof(*o)); - o->srgb = 1; - o->format = -1; - o->loops = -1; - for (int i = start; i < argc; i++) { - const char *a = argv[i], *v = i + 1 < argc ? argv[i + 1] : NULL; - if (strcmp(a, "--mips") == 0) o->mips = 1; - else if (strcmp(a, "--linear") == 0) o->srgb = 0; - else if (strcmp(a, "--premult") == 0) o->premult = 1; - else if (strcmp(a, "--entropy") == 0) o->entropy = 1; - else if (strcmp(a, "--v2") == 0) o->v2 = 1; - else if (strcmp(a, "--8bit") == 0) o->eight_bit = 1; - else if (strcmp(a, "--float32") == 0) o->float32 = 1; - else if (strcmp(a, "--linear-alpha") == 0) o->linear_alpha = 1; - else if (!v) return 0; - else if (strcmp(a, "--coverage") == 0) { o->coverage = atoi(v); o->mips = 1; i++; - if (o->coverage < 1 || o->coverage > 255) return 0; } - else if (strcmp(a, "--format") == 0) { - size_t k; - for (k = 0; k < sizeof(fmt_names) / sizeof(fmt_names[0]); k++) - if (strcmp(v, fmt_names[k].name) == 0) o->format = fmt_names[k].v; - if (o->format < 0) return 0; - i++; - } - else if (strcmp(a, "--normal") == 0) { - o->normal = strcmp(v, "gl") == 0 ? YAPF_NORMAL_GL : strcmp(v, "dx") == 0 ? YAPF_NORMAL_DX : 0; - if (!o->normal) return 0; - i++; - } - else if (strcmp(a, "--map") == 0) { if (!parse_map(v, o->map)) return 0; o->have_map = 1; i++; } - else if (strcmp(a, "--primaries") == 0 || strcmp(a, "--transfer") == 0) { - const char **names = a[2] == 'p' ? prim : tf; - int found = 0; - for (int k = 1; k < 7; k++) if (strcmp(v, names[k]) == 0) found = k; - if (!found) return 0; - if (a[2] == 'p') o->primaries = found; else o->transfer = found; - i++; - } - else if (strcmp(a, "--frame-ms") == 0) { o->frame_ms = atof(v); i++; } - else if (strcmp(a, "--loops") == 0) { o->loops = atoi(v); i++; } - else if (strcmp(a, "--author") == 0) { o->author = v; i++; } - else if (strcmp(a, "--license") == 0) { o->license = v; i++; } - else if (strcmp(a, "--source") == 0) { o->source = v; i++; } - else if (strcmp(a, "--note") == 0) { if (o->nnotes == 16) return 0; o->notes[o->nnotes++] = v; i++; } - else if (strcmp(a, "--mip") == 0) { o->mip = atoi(v); i++; } - else if (strcmp(a, "--layer") == 0) { o->layer = atoi(v); i++; } - else if (strcmp(a, "--face") == 0) { o->face = atoi(v); i++; } - else if (strcmp(a, "--frame") == 0) { o->frame = atoi(v); i++; } - else if (strcmp(a, "--slice") == 0) { o->slice = atoi(v); i++; } - else return 0; - } - if (o->mip < 0 || o->layer < 0 || o->face < 0 || o->frame < 0 || o->slice < 0) return 0; - return 1; -} - -int main(int argc, char **argv) { - if (argc == 3 && strcmp(argv[1], "info") == 0) return cmd_info(argv[2]); - if (argc == 3 && strcmp(argv[1], "verify") == 0) return cmd_verify(argv[2]); - if (argc == 3 && strcmp(argv[1], "bench") == 0) return cmd_bench(argv[2]); - if (argc >= 3 && strcmp(argv[1], "compare") == 0) return cmd_compare(argc - 2, argv + 2); - if ((argc == 4 || argc == 5) && strcmp(argv[1], "thumbnail") == 0) - return cmd_thumbnail(argv[2], argv[3], argc == 5 ? atoi(argv[4]) : 256); - - opts_t o; - if (argc >= 5 && strcmp(argv[1], "pack") == 0) { - int first_opt = 3; - while (first_opt < argc && strncmp(argv[first_opt], "--", 2) != 0) first_opt++; - int n = first_opt - 3 - 1; /* inputs, then the output */ - if (n < 1 || !parse_opts(argc, argv, first_opt, &o)) { usage(); return 2; } - const char *out = argv[first_opt - 1]; - if (!is_yapf(out)) { fprintf(stderr, "yapf: pack writes a .yapf file\n"); return 2; } - if (o.frame_ms <= 0) o.frame_ms = 100; - yapf_texture_t *t = assemble(argv[2], n, argv + 3, &o); - if (!t) return 1; - int rc = write_yapf(t, out, &o, 0); - yapf_tex_free(t); - return rc; - } - if (argc < 3 || !parse_opts(argc, argv, 3, &o)) { usage(); return 2; } - - const char *in = argv[1], *out = argv[2]; - int from_yapf; - yapf_texture_t *t = read_input(in, &o, &from_yapf); - if (!t) return 1; - int rc; - if (is_yapf(out)) { - rc = write_yapf(t, out, &o, from_yapf); - } else { - rc = export_image(t, in, out, &o); - } - yapf_tex_free(t); - return rc; -} diff --git a/yapf.c b/yapf.c deleted file mode 100644 index 281977e..0000000 --- a/yapf.c +++ /dev/null @@ -1,4747 +0,0 @@ -/* - * yapf.c — Yet Another Picture Format - * Encoder and decoder implementation. - * - * Copyright 2026 Nexoniarz - * - * Licensed under the Apache License, Version 2.0 (the "License"); - * you may not use this file except in compliance with the License. - * You may obtain a copy of the License at - * - * http://www.apache.org/licenses/LICENSE-2.0 - * - * Unless required by applicable law or agreed to in writing, software - * distributed under the License is distributed on an "AS IS" BASIS, - * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. - * See the License for the specific language governing permissions and - * limitations under the License. - */ - -#if !defined(_WIN32) && !defined(_POSIX_C_SOURCE) -# define _POSIX_C_SOURCE 200809L -#endif -#if defined(__APPLE__) && !defined(_DARWIN_C_SOURCE) -# define _DARWIN_C_SOURCE /* sysconf(_SC_NPROCESSORS_ONLN) on macOS */ -#endif - -#include "yapf.h" - -#include -#include -#include - -/* ── Constants ───────────────────────────────────────────────────────── */ - -#define YAPF__MAGIC "YAPF" -#define YAPF__VERSION 1 -#define YAPF__HDR_LEN 20 -#define YAPF__MIP_ENTRY 8 -#define YAPF__TILE_PX (YAPF_TILE_SIZE * YAPF_TILE_SIZE) - -#define YAPF__GROUP 8 /* residuals per group: w bits each = w bytes */ -#define YAPF__MAX_GROUPS (YAPF__TILE_PX / YAPF__GROUP) -#define YAPF__BAND 8 /* rows sharing one filter byte */ -#define YAPF__STORED 0x80 /* tile header: raw pixels follow */ - -/* Control nibble → number of groups it covers. - * 0..8: one group of that width; 9..15: that many groups repeating the - * width of the last 0..8 nibble (0 at the start of a plane). */ -static const uint8_t yapf__nib_groups[16] = { - 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 3, 4, 8, 16, 32, 64 -}; -#define YAPF__NIB_REPEAT 9 - -/* Row filters (one byte per band of 8 rows, per plane). L / A / D / AR - * are the left, above, above-left and above-right samples. Every filter - * depends on the previous sample through at most one add; MED and - * average-with-left predictors were measured and dropped (~1 % smaller, - * half the decode speed). */ -enum { - YAPF__F_LEFT = 0, /* L */ - YAPF__F_GRAD = 1, /* L + A - D */ - YAPF__F_UPRIGHT = 2, /* AR */ - YAPF__F_UPAVG = 3, /* (A + AR) >> 1 */ - YAPF__F_UP = 16 /* 16 + k - 1: the sample k rows above, */ - /* k = 1..8 (repeating textures, dither) */ -}; -#define YAPF__UP_MAX 8 -#define YAPF__RING 16 /* decoder row ring, >= UP_MAX + 1, power of 2 */ - -static int yapf__filter_valid(uint8_t f) { - return f <= YAPF__F_UPAVG || (f >= YAPF__F_UP && f < YAPF__F_UP + YAPF__UP_MAX); -} - -/* Filters the encoder tries, cheapest to decode first: the up-row filters - * vectorise, Left and Gradient carry a serial dependency. On equal cost - * the earlier one wins. */ -static const uint8_t yapf__filters[] = { - YAPF__F_UP + 0, YAPF__F_UP + 1, YAPF__F_UP + 2, YAPF__F_UP + 3, - YAPF__F_UP + 4, YAPF__F_UP + 5, YAPF__F_UP + 6, YAPF__F_UP + 7, - YAPF__F_UPRIGHT, YAPF__F_UPAVG, YAPF__F_LEFT, YAPF__F_GRAD -}; - -static uint32_t yapf__r32le(const uint8_t *p) { - return (uint32_t)p[0] - | ((uint32_t)p[1] << 8) - | ((uint32_t)p[2] << 16) - | ((uint32_t)p[3] << 24); -} - -static void yapf__w32le(uint8_t *p, uint32_t v) { - p[0] = (uint8_t)(v); - p[1] = (uint8_t)(v >> 8); - p[2] = (uint8_t)(v >> 16); - p[3] = (uint8_t)(v >> 24); -} - -/* Little-endian 64-bit load; compilers turn this into a single load. */ -static uint64_t yapf__r64le(const uint8_t *p) { - return (uint64_t)p[0] - | ((uint64_t)p[1] << 8) - | ((uint64_t)p[2] << 16) - | ((uint64_t)p[3] << 24) - | ((uint64_t)p[4] << 32) - | ((uint64_t)p[5] << 40) - | ((uint64_t)p[6] << 48) - | ((uint64_t)p[7] << 56); -} - -/* ── Growable output buffer (encoder) ────────────────────────────────── */ - -typedef struct { - uint8_t *buf; - size_t len; - size_t cap; -} yapf__out; - -static int yapf__reserve(yapf__out *o, size_t n) { - if (o->len + n <= o->cap) return 0; - size_t nc = o->cap ? o->cap : 4096; - while (nc < o->len + n) nc *= 2; - uint8_t *nb = (uint8_t *)realloc(o->buf, nc); - if (!nb) return -1; - o->buf = nb; - o->cap = nc; - return 0; -} - -/* ── YCoCg-R, 8-bit modular form ─────────────────────────────────────── */ -/* - * The usual YCoCg-R lifting steps, computed mod 256, with Co and Cg biased - * by 128 so neutral colours sit mid-range. Every lifting step adds a - * function of the other channel, so the transform stays exactly - * reversible while every plane remains one byte per sample. - */ -static void yapf__forward(uint8_t *y, uint8_t *co, uint8_t *cg, - uint8_t r, uint8_t g, uint8_t b) { - uint8_t o = (uint8_t)(r - b); - uint8_t t = (uint8_t)(b + ((int8_t)o >> 1)); - uint8_t q = (uint8_t)(g - t); - *y = (uint8_t)(t + ((int8_t)q >> 1)); - *co = (uint8_t)(o + 128); - *cg = (uint8_t)(q + 128); -} - -/* ── Prediction ──────────────────────────────────────────────────────── */ -/* Samples outside the tile (left of column 0, above row 0) read as 0. */ - - -/* Residuals are folded so small magnitudes become small codes: - * 0, -1, 1, -2, 2, ... → 0, 1, 2, 3, 4, ... */ -static uint8_t yapf__zz(uint8_t r) { - return (uint8_t)((r << 1) ^ (uint8_t)((int8_t)r >> 7)); -} - -static uint8_t yapf__unzz(uint8_t z) { - return (uint8_t)((z >> 1) ^ (uint8_t)-(z & 1)); -} - -/* Prediction for one row: R = the row, U = the row above, K = the row k - * rows above for YAPF__F_UP + k - 1 (rows outside the tile are all 0). - * Writes pred[0..tw). The encoder knows every sample, so this has no - * serial dependency. */ -static void yapf__predict_row(uint8_t f, const uint8_t *R, const uint8_t *U, - const uint8_t *K, uint8_t *pred, uint32_t tw) -{ - uint32_t x; - switch (f) { - case YAPF__F_LEFT: - pred[0] = 0; - for (x = 1; x < tw; x++) pred[x] = R[x - 1]; - break; - case YAPF__F_GRAD: - pred[0] = U[0]; - for (x = 1; x < tw; x++) pred[x] = (uint8_t)(R[x - 1] + U[x] - U[x - 1]); - break; - case YAPF__F_UPRIGHT: - for (x = 0; x + 1 < tw; x++) pred[x] = U[x + 1]; - pred[tw - 1] = U[tw - 1]; - break; - case YAPF__F_UPAVG: - for (x = 0; x + 1 < tw; x++) pred[x] = (uint8_t)((U[x] + U[x + 1]) >> 1); - pred[tw - 1] = U[tw - 1]; - break; - default: - memcpy(pred, K, tw); - break; - } -} - -static int yapf__width(uint8_t z) { - int w = 0; - while (z) { z >>= 1; w++; } - return w; -} - -static const uint8_t yapf__zero_row[YAPF_TILE_SIZE + 1] = { 0 }; - -/* ── SIMD ────────────────────────────────────────────────────────────── */ -/* - * On by default; define YAPF_NO_SIMD for plain C everywhere. - * x86 / x64 (GCC, Clang, MSVC, MinGW): SSSE3 kernels, chosen at run time - * with CPUID, so the same binary still runs on CPUs without SSSE3. - * ARM64 (GCC, Clang, MSVC): NEON kernels; NEON is always present. - * Every kernel produces exactly the same bytes as the scalar code. Row - * kernels work in whole 16-sample chunks: they may read and write up to - * the end of the 64 (+1) sample row buffers, never past them, and pixels - * of narrow edge tiles go through a scratch row before being copied out. - * - * Group unpack, both ISAs: lane i of 16 bits gathers the two bytes holding - * value i (table yapf__simd_shuf), shifts right by that value's bit offset - * and masks to w bits. SSSE3 has no per-lane shift, so it multiplies: - * (2u * 2^(15 - s)) >> 16 = u >> s; overflow of 2u only touches bits >= 8. - */ -#if !defined(YAPF_NO_SIMD) && \ - (defined(__x86_64__) || defined(__i386__) || defined(_M_X64) || defined(_M_IX86)) -# define YAPF__SIMD_X86 1 -#elif !defined(YAPF_NO_SIMD) && (defined(__aarch64__) || defined(_M_ARM64)) -# define YAPF__SIMD_NEON 1 -#endif - -#if defined(YAPF__SIMD_X86) || defined(YAPF__SIMD_NEON) -# define YAPF__SIMD 1 -static const uint8_t yapf__simd_shuf[9][16] = { - { 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80 }, - { 0x00, 0x01, 0x00, 0x01, 0x00, 0x01, 0x00, 0x01, 0x00, 0x01, 0x00, 0x01, 0x00, 0x01, 0x00, 0x01 }, - { 0x00, 0x01, 0x00, 0x01, 0x00, 0x01, 0x00, 0x01, 0x01, 0x02, 0x01, 0x02, 0x01, 0x02, 0x01, 0x02 }, - { 0x00, 0x01, 0x00, 0x01, 0x00, 0x01, 0x01, 0x02, 0x01, 0x02, 0x01, 0x02, 0x02, 0x03, 0x02, 0x03 }, - { 0x00, 0x01, 0x00, 0x01, 0x01, 0x02, 0x01, 0x02, 0x02, 0x03, 0x02, 0x03, 0x03, 0x04, 0x03, 0x04 }, - { 0x00, 0x01, 0x00, 0x01, 0x01, 0x02, 0x01, 0x02, 0x02, 0x03, 0x03, 0x04, 0x03, 0x04, 0x04, 0x05 }, - { 0x00, 0x01, 0x00, 0x01, 0x01, 0x02, 0x02, 0x03, 0x03, 0x04, 0x03, 0x04, 0x04, 0x05, 0x05, 0x06 }, - { 0x00, 0x01, 0x00, 0x01, 0x01, 0x02, 0x02, 0x03, 0x03, 0x04, 0x04, 0x05, 0x05, 0x06, 0x06, 0x07 }, - { 0x00, 0x01, 0x01, 0x02, 0x02, 0x03, 0x03, 0x04, 0x04, 0x05, 0x05, 0x06, 0x06, 0x07, 0x07, 0x80 } -}; -#else -# define YAPF__SIMD 0 -#endif - -#if defined(YAPF__SIMD_X86) -# if defined(_MSC_VER) -# include -# else -# include -# endif -# include -# if defined(__GNUC__) || defined(__clang__) -# define YAPF__SIMD_FN static __attribute__((target("ssse3"))) -# else -# define YAPF__SIMD_FN static /* MSVC allows intrinsics anywhere */ -# endif - -static const uint16_t yapf__simd_mul[9][8] = { - { 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000 }, - { 0x8000, 0x4000, 0x2000, 0x1000, 0x0800, 0x0400, 0x0200, 0x0100 }, - { 0x8000, 0x2000, 0x0800, 0x0200, 0x8000, 0x2000, 0x0800, 0x0200 }, - { 0x8000, 0x1000, 0x0200, 0x4000, 0x0800, 0x0100, 0x2000, 0x0400 }, - { 0x8000, 0x0800, 0x8000, 0x0800, 0x8000, 0x0800, 0x8000, 0x0800 }, - { 0x8000, 0x0400, 0x2000, 0x0100, 0x0800, 0x4000, 0x0200, 0x1000 }, - { 0x8000, 0x0200, 0x0800, 0x2000, 0x8000, 0x0200, 0x0800, 0x2000 }, - { 0x8000, 0x0100, 0x0200, 0x0400, 0x0800, 0x1000, 0x2000, 0x4000 }, - { 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000 } -}; - -/* Shuffle masks: R, G, B rows of 16 → 48 interleaved bytes. */ -static const uint8_t yapf__simd_rgb[3][3][16] = { - { - { 0x00, 0x80, 0x80, 0x01, 0x80, 0x80, 0x02, 0x80, 0x80, 0x03, 0x80, 0x80, 0x04, 0x80, 0x80, 0x05 }, - { 0x80, 0x00, 0x80, 0x80, 0x01, 0x80, 0x80, 0x02, 0x80, 0x80, 0x03, 0x80, 0x80, 0x04, 0x80, 0x80 }, - { 0x80, 0x80, 0x00, 0x80, 0x80, 0x01, 0x80, 0x80, 0x02, 0x80, 0x80, 0x03, 0x80, 0x80, 0x04, 0x80 } - }, - { - { 0x80, 0x80, 0x06, 0x80, 0x80, 0x07, 0x80, 0x80, 0x08, 0x80, 0x80, 0x09, 0x80, 0x80, 0x0A, 0x80 }, - { 0x05, 0x80, 0x80, 0x06, 0x80, 0x80, 0x07, 0x80, 0x80, 0x08, 0x80, 0x80, 0x09, 0x80, 0x80, 0x0A }, - { 0x80, 0x05, 0x80, 0x80, 0x06, 0x80, 0x80, 0x07, 0x80, 0x80, 0x08, 0x80, 0x80, 0x09, 0x80, 0x80 } - }, - { - { 0x80, 0x0B, 0x80, 0x80, 0x0C, 0x80, 0x80, 0x0D, 0x80, 0x80, 0x0E, 0x80, 0x80, 0x0F, 0x80, 0x80 }, - { 0x80, 0x80, 0x0B, 0x80, 0x80, 0x0C, 0x80, 0x80, 0x0D, 0x80, 0x80, 0x0E, 0x80, 0x80, 0x0F, 0x80 }, - { 0x0A, 0x80, 0x80, 0x0B, 0x80, 0x80, 0x0C, 0x80, 0x80, 0x0D, 0x80, 0x80, 0x0E, 0x80, 0x80, 0x0F } - } -}; - -/* CPUID leaf 1, ECX bit 9 = SSSE3. Called once per load. */ -static int yapf__simd_available(void) { -# if defined(_MSC_VER) - int r[4]; - __cpuid(r, 1); - return (r[2] >> 9) & 1; -# else - unsigned a, b, c, d; - if (!__get_cpuid(1, &a, &b, &c, &d)) return 0; - return (int)((c >> 9) & 1u); -# endif -} - -YAPF__SIMD_FN const uint8_t *yapf__simd_unpack(const uint8_t *p, - const uint8_t *end, - const uint8_t *gw, uint32_t ng, - uint8_t *z) -{ - for (uint32_t g = 0; g < ng; g++) { - int w = gw[g]; - __m128i x; - if ((size_t)(end - p) >= 8) { - x = _mm_loadl_epi64((const __m128i *)(const void *)p); - } else { - uint8_t tmp[8] = {0}; - memcpy(tmp, p, (size_t)w); - x = _mm_loadl_epi64((const __m128i *)(const void *)tmp); - } - __m128i u = _mm_shuffle_epi8(x, _mm_loadu_si128( - (const __m128i *)(const void *)yapf__simd_shuf[w])); - u = _mm_add_epi16(u, u); - __m128i v = _mm_mulhi_epu16(u, _mm_loadu_si128( - (const __m128i *)(const void *)yapf__simd_mul[w])); - v = _mm_and_si128(v, _mm_set1_epi16((short)((1 << w) - 1))); - _mm_storel_epi64((__m128i *)(void *)(z + g * YAPF__GROUP), - _mm_packus_epi16(v, v)); - p += w; - } - return p; -} - -/* Left / Gradient for a full 64-sample row: the per-sample increments are - * independent (r, or r + A - D), so compute them 16 at a time and turn the - * serial chain into a prefix sum. */ -YAPF__SIMD_FN void yapf__simd_serial_row(uint8_t f, uint8_t *R, - const uint8_t *U, const uint8_t *Z, - uint32_t tw) -{ - const __m128i zero = _mm_setzero_si128(); - __m128i carry = zero, uprev = zero; - for (uint32_t k = 0; k < tw; k += 16) { - __m128i zz = _mm_loadu_si128((const __m128i *)(const void *)(Z + k)); - __m128i t = _mm_xor_si128( - _mm_and_si128(_mm_srli_epi16(zz, 1), _mm_set1_epi8(0x7F)), - _mm_sub_epi8(zero, _mm_and_si128(zz, _mm_set1_epi8(1)))); - if (f == YAPF__F_GRAD) { - __m128i u = _mm_loadu_si128((const __m128i *)(const void *)(U + k)); - t = _mm_add_epi8(t, _mm_sub_epi8(u, _mm_alignr_epi8(u, uprev, 15))); - uprev = u; - } - t = _mm_add_epi8(t, _mm_slli_si128(t, 1)); - t = _mm_add_epi8(t, _mm_slli_si128(t, 2)); - t = _mm_add_epi8(t, _mm_slli_si128(t, 4)); - t = _mm_add_epi8(t, _mm_slli_si128(t, 8)); - t = _mm_add_epi8(t, carry); - _mm_storeu_si128((__m128i *)(void *)(R + k), t); - carry = _mm_shuffle_epi8(t, _mm_set1_epi8(15)); - } -} - -/* Bytes as int8, arithmetic shift right by one: ((v ^ 0x80) >> 1) - 64. */ -YAPF__SIMD_FN __m128i yapf__sse_half_s8(__m128i v) { - __m128i x = _mm_xor_si128(v, _mm_set1_epi8((char)0x80)); - x = _mm_and_si128(_mm_srli_epi16(x, 1), _mm_set1_epi8(0x7F)); - return _mm_sub_epi8(x, _mm_set1_epi8(64)); -} - -YAPF__SIMD_FN __m128i yapf__sse_unzz(__m128i z) { - return _mm_xor_si128(_mm_and_si128(_mm_srli_epi16(z, 1), _mm_set1_epi8(0x7F)), - _mm_sub_epi8(_mm_setzero_si128(), _mm_and_si128(z, _mm_set1_epi8(1)))); -} - -/* Vertical filters for a full 64-sample row: R = ((a + b) >> 1) + r. */ -YAPF__SIMD_FN void yapf__simd_vertical_row(uint8_t *R, const uint8_t *A, - const uint8_t *B, const uint8_t *Z, - uint32_t tw) -{ - for (uint32_t k = 0; k < tw; k += 16) { - __m128i a = _mm_loadu_si128((const __m128i *)(const void *)(A + k)); - __m128i b = _mm_loadu_si128((const __m128i *)(const void *)(B + k)); - __m128i avg = _mm_sub_epi8(_mm_avg_epu8(a, b), /* avg rounds up */ - _mm_and_si128(_mm_xor_si128(a, b), _mm_set1_epi8(1))); - __m128i z = _mm_loadu_si128((const __m128i *)(const void *)(Z + k)); - _mm_storeu_si128((__m128i *)(void *)(R + k), _mm_add_epi8(avg, yapf__sse_unzz(z))); - } -} - -/* Planes of one 64-pixel row → interleaved output pixels. */ -YAPF__SIMD_FN void yapf__simd_inverse_row(uint8_t *d, const uint8_t *P0, - const uint8_t *P1, const uint8_t *P2, - const uint8_t *P3, int ch, int xf) -{ - const __m128i bias = _mm_set1_epi8((char)0x80); - for (int k = 0; k < 64; k += 16) { - __m128i p0 = _mm_loadu_si128((const __m128i *)(const void *)(P0 + k)); - if (ch == 1) { - _mm_storeu_si128((__m128i *)(void *)(d + k), p0); - continue; - } - __m128i p1 = _mm_loadu_si128((const __m128i *)(const void *)(P1 + k)); - if (ch == 2) { - _mm_storeu_si128((__m128i *)(void *)(d + 2 * k), _mm_unpacklo_epi8(p0, p1)); - _mm_storeu_si128((__m128i *)(void *)(d + 2 * k + 16), _mm_unpackhi_epi8(p0, p1)); - continue; - } - __m128i p2 = _mm_loadu_si128((const __m128i *)(const void *)(P2 + k)); - __m128i r, g, b; - if (xf == 2) { /* none (v2) */ - r = p0; g = p1; b = p2; - } else if (xf) { /* subtract-green */ - g = p0; - r = _mm_add_epi8(_mm_sub_epi8(p1, bias), g); - b = _mm_add_epi8(_mm_sub_epi8(p2, bias), g); - } else { /* YCoCg-R */ - __m128i co = _mm_sub_epi8(p1, bias), cg = _mm_sub_epi8(p2, bias); - __m128i t = _mm_sub_epi8(p0, yapf__sse_half_s8(cg)); - b = _mm_sub_epi8(t, yapf__sse_half_s8(co)); - r = _mm_add_epi8(b, co); - g = _mm_add_epi8(cg, t); - } - if (ch == 3) { - uint8_t *o = d + 3 * k; - for (int j = 0; j < 3; j++) { - const __m128i *m = (const __m128i *)(const void *)yapf__simd_rgb[j]; - __m128i v = _mm_or_si128( - _mm_or_si128(_mm_shuffle_epi8(r, _mm_loadu_si128(m)), - _mm_shuffle_epi8(g, _mm_loadu_si128(m + 1))), - _mm_shuffle_epi8(b, _mm_loadu_si128(m + 2))); - _mm_storeu_si128((__m128i *)(void *)(o + 16 * j), v); - } - } else { - __m128i a = _mm_loadu_si128((const __m128i *)(const void *)(P3 + k)); - __m128i rg0 = _mm_unpacklo_epi8(r, g), rg1 = _mm_unpackhi_epi8(r, g); - __m128i ba0 = _mm_unpacklo_epi8(b, a), ba1 = _mm_unpackhi_epi8(b, a); - uint8_t *o = d + 4 * k; - _mm_storeu_si128((__m128i *)(void *)(o), _mm_unpacklo_epi16(rg0, ba0)); - _mm_storeu_si128((__m128i *)(void *)(o + 16), _mm_unpackhi_epi16(rg0, ba0)); - _mm_storeu_si128((__m128i *)(void *)(o + 32), _mm_unpacklo_epi16(rg1, ba1)); - _mm_storeu_si128((__m128i *)(void *)(o + 48), _mm_unpackhi_epi16(rg1, ba1)); - } - } -} - -#elif defined(YAPF__SIMD_NEON) -# include -# define YAPF__SIMD_FN static - -static const int16_t yapf__simd_nshift[9][8] = { - { 0, 0, 0, 0, 0, 0, 0, 0 }, - { 0, -1, -2, -3, -4, -5, -6, -7 }, - { 0, -2, -4, -6, 0, -2, -4, -6 }, - { 0, -3, -6, -1, -4, -7, -2, -5 }, - { 0, -4, 0, -4, 0, -4, 0, -4 }, - { 0, -5, -2, -7, -4, -1, -6, -3 }, - { 0, -6, -4, -2, 0, -6, -4, -2 }, - { 0, -7, -6, -5, -4, -3, -2, -1 }, - { 0, 0, 0, 0, 0, 0, 0, 0 } -}; - -static int yapf__simd_available(void) { return 1; } - -YAPF__SIMD_FN const uint8_t *yapf__simd_unpack(const uint8_t *p, - const uint8_t *end, - const uint8_t *gw, uint32_t ng, - uint8_t *z) -{ - for (uint32_t g = 0; g < ng; g++) { - int w = gw[g]; - uint8_t tmp[8] = {0}; - const uint8_t *src = p; - if ((size_t)(end - p) < 8) { memcpy(tmp, p, (size_t)w); src = tmp; } - uint8x16_t x = vcombine_u8(vld1_u8(src), vdup_n_u8(0)); - uint16x8_t u = vreinterpretq_u16_u8(vqtbl1q_u8(x, vld1q_u8(yapf__simd_shuf[w]))); - uint16x8_t v = vandq_u16(vshlq_u16(u, vld1q_s16(yapf__simd_nshift[w])), - vdupq_n_u16((uint16_t)((1u << w) - 1))); - vst1_u8(z + g * YAPF__GROUP, vmovn_u16(v)); - p += w; - } - return p; -} - -YAPF__SIMD_FN void yapf__simd_serial_row(uint8_t f, uint8_t *R, - const uint8_t *U, const uint8_t *Z, - uint32_t tw) -{ - const uint8x16_t zero = vdupq_n_u8(0); - uint8x16_t carry = zero, uprev = zero; - for (uint32_t k = 0; k < tw; k += 16) { - uint8x16_t zz = vld1q_u8(Z + k); - uint8x16_t t = veorq_u8(vshrq_n_u8(zz, 1), - vsubq_u8(zero, vandq_u8(zz, vdupq_n_u8(1)))); - if (f == YAPF__F_GRAD) { - uint8x16_t u = vld1q_u8(U + k); - t = vaddq_u8(t, vsubq_u8(u, vextq_u8(uprev, u, 15))); - uprev = u; - } - t = vaddq_u8(t, vextq_u8(zero, t, 15)); - t = vaddq_u8(t, vextq_u8(zero, t, 14)); - t = vaddq_u8(t, vextq_u8(zero, t, 12)); - t = vaddq_u8(t, vextq_u8(zero, t, 8)); - t = vaddq_u8(t, carry); - vst1q_u8(R + k, t); - carry = vdupq_laneq_u8(t, 15); - } -} - -YAPF__SIMD_FN void yapf__simd_vertical_row(uint8_t *R, const uint8_t *A, - const uint8_t *B, const uint8_t *Z, - uint32_t tw) -{ - for (uint32_t k = 0; k < tw; k += 16) { - uint8x16_t z = vld1q_u8(Z + k); - uint8x16_t r = veorq_u8(vshrq_n_u8(z, 1), - vsubq_u8(vdupq_n_u8(0), vandq_u8(z, vdupq_n_u8(1)))); - vst1q_u8(R + k, vaddq_u8(vhaddq_u8(vld1q_u8(A + k), vld1q_u8(B + k)), r)); - } -} - -YAPF__SIMD_FN void yapf__simd_inverse_row(uint8_t *d, const uint8_t *P0, - const uint8_t *P1, const uint8_t *P2, - const uint8_t *P3, int ch, int xf) -{ - const uint8x16_t bias = vdupq_n_u8(0x80); - for (int k = 0; k < 64; k += 16) { - uint8x16_t p0 = vld1q_u8(P0 + k); - if (ch == 1) { vst1q_u8(d + k, p0); continue; } - uint8x16_t p1 = vld1q_u8(P1 + k); - if (ch == 2) { - uint8x16x2_t v; v.val[0] = p0; v.val[1] = p1; - vst2q_u8(d + 2 * k, v); - continue; - } - uint8x16_t p2 = vld1q_u8(P2 + k), r, g, b; - if (xf == 2) { - r = p0; g = p1; b = p2; - } else if (xf) { - g = p0; - r = vaddq_u8(vsubq_u8(p1, bias), g); - b = vaddq_u8(vsubq_u8(p2, bias), g); - } else { - uint8x16_t co = vsubq_u8(p1, bias), cg = vsubq_u8(p2, bias); - uint8x16_t t = vsubq_u8(p0, vreinterpretq_u8_s8(vshrq_n_s8(vreinterpretq_s8_u8(cg), 1))); - b = vsubq_u8(t, vreinterpretq_u8_s8(vshrq_n_s8(vreinterpretq_s8_u8(co), 1))); - r = vaddq_u8(b, co); - g = vaddq_u8(cg, t); - } - if (ch == 3) { - uint8x16x3_t v; v.val[0] = r; v.val[1] = g; v.val[2] = b; - vst3q_u8(d + 3 * k, v); - } else { - uint8x16x4_t v; v.val[0] = r; v.val[1] = g; v.val[2] = b; v.val[3] = vld1q_u8(P3 + k); - vst4q_u8(d + 4 * k, v); - } - } -} -#endif - - -/* ── Plane coding ────────────────────────────────────────────────────── */ -/* - * Plane payload (all byte aligned): - * filter[ceil(th / 8)] one YAPF__F_* byte per band of 8 rows - * control nibbles low nibble first; one per group of 8 folded - * residuals, in raster order: - * 0..8 width w of this group - * 9..15 2, 3, 4, 8, 16, 32 or 64 groups repeating - * the last 0..8 width (0 at plane start) - * an odd count is padded with a zero nibble - * group data w bytes per group: the 8 values packed - * little-endian, value i at bit i*w - * The last group of a plane is padded with zeros. - */ - -/* Chooses a filter per band and writes the folded residuals to z (zero - * padded to a whole group) and the filters to filt. Returns the estimated - * coded size in 1/16 byte units. */ -static uint32_t yapf__choose_filters(const uint8_t *P, uint32_t tw, uint32_t th, - uint8_t *z, uint8_t *filt) -{ - uint32_t total = tw * th; - uint32_t nb = (th + YAPF__BAND - 1) / YAPF__BAND; - uint32_t sum = 0; - - /* Per band, pick the filter whose residuals code smallest: group - * widths plus control nibbles, in 1/16 byte units (zero groups mostly - * end up in runs, so they are counted as cheap). Left and Gradient - * decode serially, so they must win by more than 4 %. The previous - * band's winner is tried first and the others stop as soon as they - * cannot win; ties go to the earlier filter in yapf__filters. */ - size_t prev_fi = 0; - for (uint32_t b = 0; b < nb; b++) { - uint32_t y0 = b * YAPF__BAND; - uint32_t y1 = y0 + YAPF__BAND < th ? y0 + YAPF__BAND : th; - uint32_t n = (y1 - y0) * tw; - uint8_t *Z = z + y0 * tw; - uint8_t tmp[YAPF__BAND * YAPF_TILE_SIZE + YAPF__GROUP]; - uint32_t best_cost = UINT32_MAX; - size_t best_fi = 0; - - for (size_t t = 0; t < sizeof(yapf__filters); t++) { - size_t fi = t == 0 ? prev_fi : (t <= prev_fi ? t - 1 : t); - uint8_t f = yapf__filters[fi]; - uint32_t k = f >= YAPF__F_UP ? (uint32_t)(f - YAPF__F_UP + 1) : 1; - int serial = f == YAPF__F_LEFT || f == YAPF__F_GRAD; - uint32_t cost = 0, done = 0; - int lost = 0; - - for (uint32_t y = y0; y < y1 && !lost; y++) { - const uint8_t *R = P + y * tw; - const uint8_t *U = y ? R - tw : yapf__zero_row; - const uint8_t *K = y >= k ? R - k * tw : yapf__zero_row; - uint8_t *T = tmp + (y - y0) * tw; - uint8_t pred[YAPF_TILE_SIZE]; - yapf__predict_row(f, R, U, K, pred, tw); - for (uint32_t x = 0; x < tw; x++) - T[x] = yapf__zz((uint8_t)(R[x] - pred[x])); - - /* cost of the groups completed so far */ - uint32_t end = y + 1 == y1 ? n : (y + 1 - y0) * tw; - if (y + 1 == y1) memset(tmp + n, 0, YAPF__GROUP); - for (; done + YAPF__GROUP <= end || (y + 1 == y1 && done < end); - done += YAPF__GROUP) { - uint8_t m = 0; - for (int i = 0; i < YAPF__GROUP; i++) m |= tmp[done + i]; - int w = yapf__width(m); - cost += w ? (uint32_t)(16 * w + 8) : 2; - } - uint32_t c = serial ? cost + cost / 25 : cost; - if (c > best_cost || (c == best_cost && fi > best_fi)) lost = 1; - } - if (lost) continue; - if (serial) cost += cost / 25; - if (cost < best_cost || (cost == best_cost && fi < best_fi)) { - best_cost = cost; - best_fi = fi; - memcpy(Z, tmp, n); - } - } - prev_fi = best_fi; - filt[b] = yapf__filters[best_fi]; - sum += best_cost; - } - memset(z + total, 0, YAPF__GROUP); - return sum; -} - -/* Writes a plane payload from residuals and filters made by - * yapf__choose_filters. */ -static int yapf__emit_plane(yapf__out *o, const uint8_t *z, const uint8_t *filt, - uint32_t tw, uint32_t th) -{ - uint32_t total = tw * th; - uint32_t ng = (total + YAPF__GROUP - 1) / YAPF__GROUP; - uint32_t nb = (th + YAPF__BAND - 1) / YAPF__BAND; - uint8_t gw[YAPF__MAX_GROUPS]; - uint8_t nib[YAPF__MAX_GROUPS]; - uint32_t nn = 0; - - /* worst case: filters + a nibble and 8 bytes per group */ - if (yapf__reserve(o, nb + ng + (size_t)ng * 8) != 0) return -1; - memcpy(o->buf + o->len, filt, nb); - o->len += nb; - - /* Group widths → control nibbles. A group may be stored wider than - * it needs if that lets a repeat code cover it; a small dynamic - * program over (group, current width) finds the cheapest sequence, - * counted in nibbles (1 per code, 2 per data byte). */ - uint8_t need[YAPF__MAX_GROUPS]; - for (uint32_t g = 0; g < ng; g++) { - uint8_t m = 0; - for (int i = 0; i < YAPF__GROUP; i++) m |= z[g * YAPF__GROUP + i]; - need[g] = (uint8_t)yapf__width(m); - } - { - static const uint8_t lens[7] = { 2, 3, 4, 8, 16, 32, 64 }; - uint32_t cost[YAPF__MAX_GROUPS + 1][9]; - uint8_t pick[YAPF__MAX_GROUPS][9]; /* nibble code */ - - /* span[j][g] = widest need in groups [g, g + 2^j) */ - static const int levels = 7; - uint8_t span[7][YAPF__MAX_GROUPS]; - memcpy(span[0], need, ng); - for (int j = 1; j < levels; j++) - for (uint32_t g = 0; g + (1u << j) <= ng; g++) { - uint8_t a = span[j - 1][g], c = span[j - 1][g + (1u << (j - 1))]; - span[j][g] = a > c ? a : c; - } - - for (int pw = 0; pw <= 8; pw++) cost[ng][pw] = 0; - for (uint32_t g = ng; g-- > 0; ) { - /* Best literal: independent of the current width. */ - uint32_t lc = UINT32_MAX; - uint8_t lk = 0; - for (int w = need[g]; w <= 8; w++) { - uint32_t c = 1 + 2u * (uint32_t)w + cost[g + 1][w]; - if (c < lc) { lc = c; lk = (uint8_t)w; } - } - /* Widest need over each repeat length that fits, from the - * power-of-two max table (length 3 = 2 + one more). */ - uint8_t mx[7]; - int nl = 0; - for (; nl < 7 && g + lens[nl] <= ng; nl++) { - uint32_t L = lens[nl]; - if (L == 3) { - uint8_t a = span[1][g], c = need[g + 2]; - mx[nl] = a > c ? a : c; - } else { - int j = 0; - while ((1u << j) < L) j++; - mx[nl] = span[j][g]; - } - } - for (int pw = 0; pw <= 8; pw++) { - uint32_t bc = lc; - uint8_t bk = lk; - for (int li = 0; li < nl && mx[li] <= pw; li++) { - uint32_t c = 1 + 2u * (uint32_t)pw * lens[li] + cost[g + lens[li]][pw]; - if (c < bc) { bc = c; bk = (uint8_t)(YAPF__NIB_REPEAT + li); } - } - cost[g][pw] = bc; - pick[g][pw] = bk; - } - } - uint8_t pw = 0; - for (uint32_t g = 0; g < ng; ) { - uint8_t k = pick[g][pw]; - nib[nn++] = k; - if (k < YAPF__NIB_REPEAT) { - pw = k; - gw[g++] = k; - } else { - for (uint32_t n = 0; n < yapf__nib_groups[k]; n++) gw[g++] = pw; - } - } - } - for (uint32_t k = 0; k < nn; k += 2) - o->buf[o->len++] = (uint8_t)(nib[k] | (k + 1 < nn ? nib[k + 1] << 4 : 0)); - - /* Packed group data: 8 values of w bits = w bytes */ - for (uint32_t g = 0; g < ng; g++) { - int w = gw[g]; - uint64_t acc = 0; - for (int i = 0; i < YAPF__GROUP; i++) - acc |= (uint64_t)z[g * YAPF__GROUP + i] << (i * w); - for (int k = 0; k < w; k++) o->buf[o->len++] = (uint8_t)(acc >> (8 * k)); - } - return 0; -} - -/* Parses one plane payload from [p, end) and unpacks its folded residuals - * into z; *filt receives the band filters. Returns the end of the payload - * or NULL on corrupt input. All sizes are validated before the unpack. */ -static const uint8_t *yapf__unpack_plane(const uint8_t *p, const uint8_t *end, - uint8_t *z, const uint8_t **filt_out, - uint32_t tw, uint32_t th, int simd) -{ - uint32_t total = tw * th; - uint32_t ng = (total + YAPF__GROUP - 1) / YAPF__GROUP; - uint32_t nb = (th + YAPF__BAND - 1) / YAPF__BAND; - uint8_t gw[YAPF__MAX_GROUPS + 64]; /* a final run may overshoot */ - - if ((size_t)(end - p) < nb) return NULL; - const uint8_t *filt = p; - *filt_out = filt; - p += nb; - for (uint32_t b = 0; b < nb; b++) - if (!yapf__filter_valid(filt[b])) return NULL; - - /* Control nibbles → group widths, and the total data size. Every - * nibble stores its width into the next 8 entries with one 64-bit - * write (the array has room); only runs longer than 8 groups, which - * are rare, take a branch to fill the rest. */ - size_t data = 0; - uint32_t g = 0; - int hi = 0; - uint8_t w = 0; - while (g < ng) { - if (p >= end) return NULL; - uint8_t c = (uint8_t)((*p >> (hi * 4)) & 15); - uint32_t n = yapf__nib_groups[c]; - p += hi; - hi ^= 1; - w = c < YAPF__NIB_REPEAT ? c : w; - { - uint64_t w8 = (uint64_t)w * 0x0101010101010101ull; - memcpy(gw + g, &w8, 8); - if (n > 8) memset(gw + g + 8, w, 56); - } - data += (size_t)w * n; - g += n; - } - if (g != ng) return NULL; /* run past the last group */ - if (hi) { /* padding nibble must be 0 */ - if (*p >> 4) return NULL; - p++; - } - if ((size_t)(end - p) < data) return NULL; - -#if YAPF__SIMD - if (simd) return yapf__simd_unpack(p, end, gw, ng, z); -#else - (void)simd; -#endif - - /* Unpack. Branch-free per group: one 64-bit load, 8 shifts. */ - for (g = 0; g < ng; g++) { - int w = gw[g]; - uint64_t x; - if ((size_t)(end - p) >= 8) { - x = yapf__r64le(p); - } else { - uint8_t tmp[8] = {0}; - memcpy(tmp, p, (size_t)w); - x = yapf__r64le(tmp); - } - uint64_t m = (1u << w) - 1; - uint8_t *o = z + g * YAPF__GROUP; - for (int i = 0; i < YAPF__GROUP; i++) - o[i] = (uint8_t)((x >> (i * w)) & m); - p += w; - } - - return p; -} - -/* Undo filter f for one row. R = reconstructed row, U = row above, - * K = row k above (for YAPF__F_UP + k - 1), Z = folded residuals. Rows - * carry one extra sample, R[tw] = R[tw - 1], so "above-right" needs no - * edge case. All vertical filters share one loop, pred = (a + b) >> 1: - * Up k: a = b = K Up-right: a = b = U + 1 - * Up-avg: a = U, b = U + 1 - * which keeps the per-row dispatch down to three targets. */ -static void yapf__unfilter_row(uint8_t f, uint8_t *R, const uint8_t *U, - const uint8_t *K, const uint8_t *Z, uint32_t tw) -{ - uint32_t x; - if (f == YAPF__F_LEFT) { - uint8_t L = 0; - for (x = 0; x < tw; x++) R[x] = L = (uint8_t)(L + yapf__unzz(Z[x])); - } else if (f == YAPF__F_GRAD) { - /* L + (A - D + r): only one add depends on the previous sample. */ - uint8_t L = (uint8_t)(U[0] + yapf__unzz(Z[0])); - R[0] = L; - for (x = 1; x < tw; x++) { - uint8_t t = (uint8_t)(U[x] - U[x - 1] + yapf__unzz(Z[x])); - R[x] = L = (uint8_t)(L + t); - } - } else { - const uint8_t *a = f >= YAPF__F_UP ? K : f == YAPF__F_UPAVG ? U : U + 1; - const uint8_t *b = f >= YAPF__F_UP ? K : U + 1; - for (x = 0; x < tw; x++) - R[x] = (uint8_t)(((a[x] + b[x]) >> 1) + yapf__unzz(Z[x])); - } - R[tw] = R[tw - 1]; -} - -/* ── Tile encode / decode ────────────────────────────────────────────── */ -/* - * Tile layout (byte aligned): - * header byte: 0x80 stored: tw*th*ch raw interleaved bytes follow - * bits 0..3 coded: bit c set = plane c is constant - * bit 4 coded RGB(A): planes are G, R-G, B-G (+ A) - * instead of Y, Co, Cg (+ A) - * coded: one value byte per constant plane, in plane order, - * then a plane payload per non-constant plane, in plane order - * The encoder tries both colour transforms and keeps the smaller tile, and - * stores the tile raw whenever coding would not make it smaller. - */ -#define YAPF__SUBGREEN 0x10 -#define YAPF__ENTROPY 0x20 /* v2: entropy plane mask follows */ -#define YAPF__NOXFORM 0x40 /* v2: planes are R, G, B (+ A) as stored */ - -/* ── yapf-sum ────────────────────────────────────────────────────────── */ -/* - * The version 2 checksum. Four independent 64-bit lanes take the 8-byte - * little-endian words of the input in turn (word j goes to lane j mod 4; - * the last word is zero padded): - * a = (a ^ w) * K; a ^= a >> 32; K = 0x9E3779B97F4A7C15 - * Lane i starts at (i + 1) * K ^ n, n = byte length. The result is - * h = a0 ^ rotl(a1, 16) ^ rotl(a2, 32) ^ rotl(a3, 48); - * h *= K; h ^= h >> 32; low 32 bits of h. - * The lanes keep four multiplies in flight, so it runs well above the - * decoder's own speed. - */ -#define YAPF__K 0x9E3779B97F4A7C15ull - -static uint64_t yapf__rotl(uint64_t v, int r) { return (v << r) | (v >> (64 - r)); } - -uint32_t yapf_checksum(const void *data, size_t size) { - const uint8_t *p = (const uint8_t *)data; - uint64_t n = (uint64_t)size; - uint64_t a[4]; - for (int i = 0; i < 4; i++) a[i] = ((uint64_t)(i + 1) * YAPF__K) ^ n; - size_t j = 0, words = size / 8; - for (; j + 4 <= words; j += 4) { - for (int i = 0; i < 4; i++) { - uint64_t v = (a[i] ^ yapf__r64le(p + (j + i) * 8)) * YAPF__K; - a[i] = v ^ (v >> 32); - } - } - for (; j < words; j++) { - uint64_t v = (a[j & 3] ^ yapf__r64le(p + j * 8)) * YAPF__K; - a[j & 3] = v ^ (v >> 32); - } - if (size & 7) { - uint8_t tail[8] = {0}; - memcpy(tail, p + words * 8, size & 7); - uint64_t v = (a[j & 3] ^ yapf__r64le(tail)) * YAPF__K; - a[j & 3] = v ^ (v >> 32); - } - uint64_t h = a[0] ^ yapf__rotl(a[1], 16) ^ yapf__rotl(a[2], 32) ^ yapf__rotl(a[3], 48); - h *= YAPF__K; - h ^= h >> 32; - return (uint32_t)h; -} - -static uint16_t yapf__r16le(const uint8_t *p) { - return (uint16_t)(p[0] | (p[1] << 8)); -} - -static void yapf__w16le(uint8_t *p, uint32_t v) { - p[0] = (uint8_t)v; - p[1] = (uint8_t)(v >> 8); -} - -static void yapf__w64le(uint8_t *p, uint64_t v) { - yapf__w32le(p, (uint32_t)v); - yapf__w32le(p + 4, (uint32_t)(v >> 32)); -} - -/* ── Entropy stage (version 2, optional) ─────────────────────────────── */ -/* - * A surface that uses it starts with a code book: Huffman tables keyed by - * (slot, context). Pixel planes: slot = transform · 16 + plane (transform - * 0 YCoCg-R, 1 subtract-green, 2 none), context = how busy the neighbours - * are (folded residuals left + above, in 7 classes). Block tiles: slot = - * byte lane of the block, context 0. Sharing the tables per surface - * keeps tiles independent and their headers tiny. - * - * Code table: 1 byte n − 1 (n = symbols 0..n−1 described), then n 4-bit - * code lengths (0 = unused, 1..11), low nibble first; an odd - * count is padded with a zero nibble. Kraft sum <= 1. - * Codes are canonical (shorter first, then by symbol, as in deflate) and - * written least significant bit first, so a decoder reads them with one - * 2048-entry table lookup. - */ -#define YAPF__HUFF_BITS 11 -#define YAPF__HUFF_SIZE (1u << YAPF__HUFF_BITS) - -static uint32_t yapf__bitrev(uint32_t c, int n) { - uint32_t r = 0; - for (int i = 0; i < n; i++) { r = (r << 1) | (c & 1); c >>= 1; } - return r; -} - -/* Parses a code table into lut (entry = length << 8 | symbol, 0 = no - * code). Returns the byte after the table, or NULL. */ -static const uint8_t *yapf__huff_table(const uint8_t *p, const uint8_t *end, - uint16_t *lut) -{ - if (p >= end) return NULL; - uint32_t n = (uint32_t)*p++ + 1, nbytes = (n + 1) / 2; - if ((size_t)(end - p) < nbytes) return NULL; - uint8_t len[256]; - uint32_t count[YAPF__HUFF_BITS + 1] = {0}, kraft = 0; - for (uint32_t i = 0; i < n; i++) { - uint8_t l = (uint8_t)((p[i >> 1] >> ((i & 1) * 4)) & 15); - if (l > YAPF__HUFF_BITS) return NULL; - len[i] = l; - count[l]++; - if (l) kraft += YAPF__HUFF_SIZE >> l; - } - if ((n & 1) && (p[n >> 1] >> 4)) return NULL; - if (kraft == 0 || kraft > YAPF__HUFF_SIZE) return NULL; - p += nbytes; - - uint32_t next[YAPF__HUFF_BITS + 2], code = 0; - count[0] = 0; - for (int l = 1; l <= YAPF__HUFF_BITS; l++) { - code = (code + count[l - 1]) << 1; - next[l] = code; - } - memset(lut, 0, YAPF__HUFF_SIZE * sizeof(uint16_t)); - for (uint32_t s = 0; s < n; s++) { - int l = len[s]; - if (!l) continue; - uint32_t r = yapf__bitrev(next[l]++, l); - for (uint32_t k = r; k < YAPF__HUFF_SIZE; k += 1u << l) - lut[k] = (uint16_t)((l << 8) | s); - } - return p; -} - -/* Bit reader for code streams; reading past the end yields zeros and is - * caught by yapf__br_done. */ -typedef struct { - const uint8_t *p; - size_t L, pos; - uint64_t buf, used; - int bits; -} yapf__br; - -static void yapf__br_init(yapf__br *b, const uint8_t *p, size_t L) { - b->p = p; b->L = L; b->pos = 0; b->buf = 0; b->used = 0; b->bits = 0; -} - -static int yapf__br_sym(yapf__br *b, const uint16_t *lut) { - if (b->bits < (int)YAPF__HUFF_BITS) { - if (b->pos + 8 <= b->L) { - b->buf |= yapf__r64le(b->p + b->pos) << b->bits; - b->pos += (size_t)((63 - b->bits) >> 3); - b->bits |= 56; - } else { - while (b->bits <= 56) { - b->buf |= (uint64_t)(b->pos < b->L ? b->p[b->pos] : 0) << b->bits; - b->pos++; - b->bits += 8; - } - } - } - uint16_t e = lut[b->buf & (YAPF__HUFF_SIZE - 1)]; - if (!e) return -1; - int l = e >> 8; - b->buf >>= l; - b->bits -= l; - b->used += (uint64_t)l; - return e & 0xFF; -} - -/* The stream must end in its last byte. */ -static int yapf__br_done(const yapf__br *b) { - return (b->used + 7) / 8 == b->L; -} - -#define YAPF__SLOTS 48 -#define YAPF__CTX 7 - -/* Context of a residual from its left and upper neighbours' folded - * residuals s = l + u: 0, 1–2, 3–6, 7–14, 15–30, 31–62, 63 and up - * (= min(6, floor(log2(s + 1)))). Branch free: the decoder computes it - * on the critical path of every sample. */ -static int yapf__ctx(uint32_t s) { - return (s > 0) + (s > 2) + (s > 6) + (s > 14) + (s > 30) + (s > 62); -} - -/* The same as table offsets for the decoder: ctx(min(s, 63)) << 11. */ -#define YAPF__C(c) (uint16_t)((c) << 11) -static const uint16_t yapf__ctx_off[64] = { /* index min(s, 63) */ - YAPF__C(0), YAPF__C(1), YAPF__C(1), YAPF__C(2), YAPF__C(2), YAPF__C(2), YAPF__C(2), - YAPF__C(3), YAPF__C(3), YAPF__C(3), YAPF__C(3), YAPF__C(3), YAPF__C(3), YAPF__C(3), YAPF__C(3), - YAPF__C(4), YAPF__C(4), YAPF__C(4), YAPF__C(4), YAPF__C(4), YAPF__C(4), YAPF__C(4), YAPF__C(4), - YAPF__C(4), YAPF__C(4), YAPF__C(4), YAPF__C(4), YAPF__C(4), YAPF__C(4), YAPF__C(4), YAPF__C(4), - YAPF__C(5), YAPF__C(5), YAPF__C(5), YAPF__C(5), YAPF__C(5), YAPF__C(5), YAPF__C(5), YAPF__C(5), - YAPF__C(5), YAPF__C(5), YAPF__C(5), YAPF__C(5), YAPF__C(5), YAPF__C(5), YAPF__C(5), YAPF__C(5), - YAPF__C(5), YAPF__C(5), YAPF__C(5), YAPF__C(5), YAPF__C(5), YAPF__C(5), YAPF__C(5), YAPF__C(5), - YAPF__C(5), YAPF__C(5), YAPF__C(5), YAPF__C(5), YAPF__C(5), YAPF__C(5), YAPF__C(5), YAPF__C(5), - YAPF__C(6) -}; -#undef YAPF__C - -/* Decoder side of a code book: per slot one array of 7 × 2048 lookup - * entries (contexts without a table stay 0 = invalid), so context and - * bits form a single index. */ -typedef struct { - uint16_t *slot[YAPF__SLOTS]; - uint16_t *mem; -} yapf__dbook; - -/* Book: u16 table count, then per table: slot, context, code table. */ -static int yapf__book_read(const uint8_t *p, size_t len, yapf__dbook *bk) { - const uint8_t *end = p + len, *q; - uint8_t seen[YAPF__SLOTS][YAPF__CTX]; - uint32_t slots = 0; - memset(bk, 0, sizeof(*bk)); - memset(seen, 0, sizeof(seen)); - if (len < 2) return -1; - uint32_t n = yapf__r16le(p); - p += 2; - if (n == 0 || n > YAPF__SLOTS * YAPF__CTX) return -1; - /* first pass: validate the layout and count the slots in use */ - for (uint32_t i = 0, k; i < n; i++) { - if (end - p < 3) return -1; - uint8_t slot = p[0], ctx = p[1]; - if (slot >= YAPF__SLOTS || ctx >= YAPF__CTX || seen[slot][ctx]) return -1; - seen[slot][ctx] = 1; - for (k = 0; k < YAPF__CTX && (k == ctx || !seen[slot][k]); k++) {} - if (k == YAPF__CTX) slots++; /* first table of this slot */ - uint32_t ns = (uint32_t)p[2] + 1; - p += 3 + (ns + 1) / 2; - if (p > end) return -1; - } - if (p != end) return -1; - bk->mem = (uint16_t *)calloc((size_t)slots * YAPF__CTX * YAPF__HUFF_SIZE, sizeof(uint16_t)); - if (!bk->mem) return -1; - uint32_t used = 0; - for (q = end - len + 2; q < end; ) { - uint8_t slot = q[0], ctx = q[1]; - if (!bk->slot[slot]) bk->slot[slot] = bk->mem + (size_t)used++ * YAPF__CTX * YAPF__HUFF_SIZE; - q = yapf__huff_table(q + 2, end, bk->slot[slot] + (size_t)ctx * YAPF__HUFF_SIZE); - if (!q) return -1; - } - return 0; -} - -/* Entropy plane payload: filters, u16 stream length, the folded - * residuals in raster order, each with the table of its context. - * - * Every residual's context needs the one decoded just before it, so one - * stream is a chain of dependent steps. The planes of a tile are - * independent streams, though: the decoder runs up to four of them in - * the same loop and the CPU overlaps their chains. */ -typedef struct { - const uint8_t *p; - size_t L; - const uint16_t *lut; - uint8_t *z; -} yapf__hstream; - -/* Parses the header of an entropy plane into *s; returns the end of the - * payload or NULL. */ -static const uint8_t *yapf__huff_head(const uint8_t *p, const uint8_t *end, - const uint8_t **filt_out, uint32_t th, - const yapf__dbook *bk, int slot, - uint8_t *z, yapf__hstream *s) -{ - uint32_t nb = (th + YAPF__BAND - 1) / YAPF__BAND; - if (!bk || !bk->slot[slot] || (size_t)(end - p) < nb + 2) return NULL; - *filt_out = p; - for (uint32_t b = 0; b < nb; b++) - if (!yapf__filter_valid(p[b])) return NULL; - p += nb; - s->L = yapf__r16le(p); - p += 2; - if ((size_t)(end - p) < s->L) return NULL; - s->p = p; - s->lut = bk->slot[slot]; - s->z = z; - return p + s->L; -} - -#define YAPF__HSTATE(k) \ - uint64_t buf##k = 0; \ - int bits##k = 0; \ - size_t pos##k = 0; \ - uint32_t l##k = 0; \ - const uint8_t *P##k = s[k].p, *U##k = yapf__zero_row; \ - const size_t L##k = s[k].L; \ - const uint16_t *T##k = s[k].lut; \ - uint8_t *Z##k = s[k].z; - -#define YAPF__HROW(k) \ - U##k = y ? Z##k + i - tw : yapf__zero_row; \ - l##k = 0; - -#define YAPF__HSTEP(k) \ - { \ - if (pos##k + 8 <= L##k) { /* branch free while not near the end */ \ - buf##k |= yapf__r64le(P##k + pos##k) << bits##k; \ - pos##k += (size_t)((63 - bits##k) >> 3); \ - bits##k |= 56; \ - } else if (bits##k < (int)YAPF__HUFF_BITS) { \ - while (bits##k <= 56) { \ - buf##k |= (uint64_t)(pos##k < L##k ? P##k[pos##k] : 0) << bits##k; \ - pos##k++; \ - bits##k += 8; \ - } \ - } \ - uint32_t s_ = l##k + U##k[x]; \ - uint32_t e_ = T##k[yapf__ctx_off[s_ < 63 ? s_ : 63] | \ - (uint32_t)(buf##k & (YAPF__HUFF_SIZE - 1))]; \ - int n_ = (int)(e_ >> 8); \ - if (!e_) return -1; \ - buf##k >>= n_; \ - bits##k -= n_; \ - l##k = e_ & 0xFF; \ - Z##k[i] = (uint8_t)l##k; \ - } - -/* bits consumed = 8·pos − bits still buffered; the stream must end in - * its last byte */ -#define YAPF__HEND(k) if ((8 * (uint64_t)pos##k - (uint64_t)bits##k + 7) / 8 != L##k) return -1; - -static int yapf__hdec1(const yapf__hstream *s, uint32_t tw, uint32_t th) { - YAPF__HSTATE(0) - for (uint32_t y = 0, i = 0; y < th; y++) { - YAPF__HROW(0) - for (uint32_t x = 0; x < tw; x++, i++) YAPF__HSTEP(0) - } - YAPF__HEND(0) - return 0; -} - -static int yapf__hdec2(const yapf__hstream *s, uint32_t tw, uint32_t th) { - YAPF__HSTATE(0) YAPF__HSTATE(1) - for (uint32_t y = 0, i = 0; y < th; y++) { - YAPF__HROW(0) YAPF__HROW(1) - for (uint32_t x = 0; x < tw; x++, i++) { YAPF__HSTEP(0) YAPF__HSTEP(1) } - } - YAPF__HEND(0) YAPF__HEND(1) - return 0; -} - -static int yapf__hdec3(const yapf__hstream *s, uint32_t tw, uint32_t th) { - YAPF__HSTATE(0) YAPF__HSTATE(1) YAPF__HSTATE(2) - for (uint32_t y = 0, i = 0; y < th; y++) { - YAPF__HROW(0) YAPF__HROW(1) YAPF__HROW(2) - for (uint32_t x = 0; x < tw; x++, i++) { YAPF__HSTEP(0) YAPF__HSTEP(1) YAPF__HSTEP(2) } - } - YAPF__HEND(0) YAPF__HEND(1) YAPF__HEND(2) - return 0; -} - -static int yapf__hdec4(const yapf__hstream *s, uint32_t tw, uint32_t th) { - YAPF__HSTATE(0) YAPF__HSTATE(1) YAPF__HSTATE(2) YAPF__HSTATE(3) - for (uint32_t y = 0, i = 0; y < th; y++) { - YAPF__HROW(0) YAPF__HROW(1) YAPF__HROW(2) YAPF__HROW(3) - for (uint32_t x = 0; x < tw; x++, i++) { - YAPF__HSTEP(0) YAPF__HSTEP(1) YAPF__HSTEP(2) YAPF__HSTEP(3) - } - } - YAPF__HEND(0) YAPF__HEND(1) YAPF__HEND(2) YAPF__HEND(3) - return 0; -} - -/* Decodes n (1..) streams, four at a time; zeroes each tail group. */ -static int yapf__huff_run(const yapf__hstream *s, int n, uint32_t tw, uint32_t th) { - for (int k = 0; k < n; k += 4) { - int m = n - k < 4 ? n - k : 4, rc; - rc = m == 4 ? yapf__hdec4(s + k, tw, th) : m == 3 ? yapf__hdec3(s + k, tw, th) - : m == 2 ? yapf__hdec2(s + k, tw, th) : yapf__hdec1(s + k, tw, th); - if (rc != 0) return -1; - } - for (int k = 0; k < n; k++) memset(s[k].z + (size_t)tw * th, 0, YAPF__GROUP); - return 0; -} - -/* One entropy plane on its own. */ -static const uint8_t *yapf__huff_plane(const uint8_t *p, const uint8_t *end, - uint8_t *z, const uint8_t **filt_out, - uint32_t tw, uint32_t th, - const yapf__dbook *bk, int slot) -{ - yapf__hstream s; - p = yapf__huff_head(p, end, filt_out, th, bk, slot, z, &s); - if (!p || yapf__huff_run(&s, 1, tw, th) != 0) return NULL; - return p; -} - -/* Code lengths (<= 11 bits) for freq[0..n). Plain Huffman by the - * two-queue method; if a code comes out too long the counts are halved - * and it is built again. */ -static void yapf__huff_lengths(const uint32_t *freq_in, uint32_t n, uint8_t *len) { - uint32_t freq[256], sym[256], m = 0; - memcpy(freq, freq_in, n * sizeof(uint32_t)); - for (;;) { - m = 0; - for (uint32_t s = 0; s < n; s++) { len[s] = 0; if (freq[s]) sym[m++] = s; } - if (m == 0) return; - if (m == 1) { len[sym[0]] = 1; return; } - /* insertion sort by frequency (m <= 256) */ - for (uint32_t i = 1; i < m; i++) { - uint32_t v = sym[i], j = i; - while (j > 0 && freq[sym[j - 1]] > freq[v]) { sym[j] = sym[j - 1]; j--; } - sym[j] = v; - } - /* nodes 0..m-1 leaves (sorted), m..2m-2 internal in creation order */ - uint64_t w[512]; - uint32_t parent[512], li = 0, ii = m, nn = m; - for (uint32_t i = 0; i < m; i++) w[i] = freq[sym[i]]; - for (uint32_t k = 0; k + 1 < m; k++) { - uint32_t pick[2]; - for (int t = 0; t < 2; t++) { - if (li < m && (ii >= nn || w[li] <= w[ii])) pick[t] = li++; - else pick[t] = ii++; - } - w[nn] = w[pick[0]] + w[pick[1]]; - parent[pick[0]] = parent[pick[1]] = nn; - nn++; - } - uint8_t depth[512]; - depth[nn - 1] = 0; - int maxl = 0; - for (uint32_t k = nn - 1; k-- > 0; ) { - depth[k] = (uint8_t)(depth[parent[k]] + 1); - if (k < m && depth[k] > maxl) maxl = depth[k]; - } - if (maxl <= (int)YAPF__HUFF_BITS) { - for (uint32_t i = 0; i < m; i++) len[sym[i]] = depth[i]; - return; - } - for (uint32_t s = 0; s < n; s++) if (freq[s]) freq[s] = (freq[s] >> 1) | 1; - } -} - -typedef struct { - uint64_t acc; - int bits; - yapf__out *o; -} yapf__bitw; - -static void yapf__bitw_put(yapf__bitw *b, uint32_t code, int len) { - b->acc |= (uint64_t)code << b->bits; - b->bits += len; - while (b->bits >= 8) { - b->o->buf[b->o->len++] = (uint8_t)b->acc; - b->acc >>= 8; - b->bits -= 8; - } -} - -static void yapf__bitw_flush(yapf__bitw *b) { - if (b->bits > 0) b->o->buf[b->o->len++] = (uint8_t)b->acc; - b->acc = 0; - b->bits = 0; -} - -/* Canonical codes for lengths len[0..ns). */ -static void yapf__huff_codes(const uint8_t *len, uint32_t ns, uint16_t *code) { - uint32_t count[YAPF__HUFF_BITS + 1] = {0}, next[YAPF__HUFF_BITS + 2], c = 0; - for (uint32_t s = 0; s < ns; s++) if (len[s]) count[len[s]]++; - for (int l = 1; l <= (int)YAPF__HUFF_BITS; l++) { - c = (c + count[l - 1]) << 1; - next[l] = c; - } - for (uint32_t s = 0; s < ns; s++) - code[s] = len[s] ? (uint16_t)yapf__bitrev(next[len[s]]++, len[s]) : 0; -} - -typedef struct { /* encoder side of a code book */ - uint32_t freq[YAPF__SLOTS][YAPF__CTX][256]; - uint8_t len[YAPF__SLOTS][YAPF__CTX][256]; - uint16_t code[YAPF__SLOTS][YAPF__CTX][256]; -} yapf__ebook; - -/* Encoder modes for the tile writers. */ -#define YAPF__ENC_PLAIN 0 /* groups only */ -#define YAPF__ENC_STATS 1 /* groups, and count symbols for a book */ -#define YAPF__ENC_BOOK 2 /* entropy planes / packed blocks */ - -/* Builds every table that has symbols and writes the book. */ -static int yapf__book_write(yapf__ebook *eb, yapf__out *o) { - uint32_t n = 0; - if (yapf__reserve(o, 2) != 0) return -1; - size_t at = o->len; - o->len += 2; - memset(eb->len, 0, sizeof(eb->len)); - for (int s = 0; s < YAPF__SLOTS; s++) - for (int c = 0; c < YAPF__CTX; c++) { - const uint32_t *f = eb->freq[s][c]; - uint32_t ns = 256; - while (ns > 0 && !f[ns - 1]) ns--; - if (ns == 0) continue; - yapf__huff_lengths(f, ns, eb->len[s][c]); - yapf__huff_codes(eb->len[s][c], ns, eb->code[s][c]); - if (yapf__reserve(o, 3 + 128) != 0) return -1; - o->buf[o->len++] = (uint8_t)s; - o->buf[o->len++] = (uint8_t)c; - o->buf[o->len++] = (uint8_t)(ns - 1); - for (uint32_t k = 0; k < ns; k += 2) - o->buf[o->len++] = (uint8_t)(eb->len[s][c][k] | (k + 1 < ns ? eb->len[s][c][k + 1] << 4 : 0)); - n++; - } - yapf__w16le(o->buf + at, n); - return n ? 0 : 1; /* 1: nothing to code */ -} - -static void yapf__plane_stats(yapf__ebook *eb, int slot, const uint8_t *z, uint32_t tw, uint32_t th) { - for (uint32_t y = 0, i = 0; y < th; y++) - for (uint32_t x = 0; x < tw; x++, i++) { - uint32_t s = (x ? z[i - 1] : 0u) + (y ? z[i - tw] : 0u); - eb->freq[slot][yapf__ctx(s)][z[i]]++; - } -} - -/* Entropy plane payload (see yapf__huff_plane). Returns 1 when some - * symbol has no code in the book (the caller keeps the group form). */ -static int yapf__huff_emit_plane(yapf__out *o, const uint8_t *z, const uint8_t *filt, - uint32_t tw, uint32_t th, const yapf__ebook *eb, int slot) -{ - uint32_t nb = (th + YAPF__BAND - 1) / YAPF__BAND; - uint64_t bits = 0; - for (uint32_t y = 0, i = 0; y < th; y++) - for (uint32_t x = 0; x < tw; x++, i++) { - uint32_t s = (x ? z[i - 1] : 0u) + (y ? z[i - tw] : 0u); - uint8_t l = eb->len[slot][yapf__ctx(s)][z[i]]; - if (!l) return 1; - bits += l; - } - size_t L = (size_t)((bits + 7) / 8); - if (L > 0xFFFF) return 1; - if (yapf__reserve(o, nb + 2 + L + 8) != 0) return -1; - memcpy(o->buf + o->len, filt, nb); - o->len += nb; - yapf__w16le(o->buf + o->len, (uint32_t)L); - o->len += 2; - yapf__bitw bw = { 0, 0, o }; - for (uint32_t y = 0, i = 0; y < th; y++) - for (uint32_t x = 0; x < tw; x++, i++) { - uint32_t s = (x ? z[i - 1] : 0u) + (y ? z[i - tw] : 0u); - int c = yapf__ctx(s); - yapf__bitw_put(&bw, eb->code[slot][c][z[i]], eb->len[slot][c][z[i]]); - } - yapf__bitw_flush(&bw); - return 0; -} - -/* ── Plane set emission (version 2) ──────────────────────────────────── */ -/* - * Writes a coded v2 tile: header byte, (wide) u16 constant mask, entropy - * mask if any plane is entropy coded, constant values, payloads. With a - * book (mode BOOK) each plane is coded both ways and the entropy form is - * kept only if it is at least 1/32 smaller; mode STATS feeds the book. - */ -typedef struct { - int np; /* planes */ - int wide; /* masks are u16 (wide samples) */ - uint32_t cmask; /* constant planes */ - const uint8_t *cval; /* constant value per plane */ - const uint8_t *z[16]; /* folded residuals per plane */ - const uint8_t *filt[16]; -} yapf__planeset; - -static int yapf__emit_planeset(yapf__out *o, yapf__out *tmp, uint8_t hdr, - const yapf__planeset *ps, uint32_t tw, uint32_t th, - int mode, yapf__ebook *eb) -{ - size_t off[17]; - uint32_t emask = 0; - int tsel = (hdr & YAPF__SUBGREEN) ? 1 : (hdr & YAPF__NOXFORM) ? 2 : 0; - tmp->len = 0; - for (int c = 0; c < ps->np; c++) { - off[c] = tmp->len; - if (ps->cmask & (1u << c)) continue; - if (yapf__emit_plane(tmp, ps->z[c], ps->filt[c], tw, th) != 0) return -1; - if (mode == YAPF__ENC_STATS) yapf__plane_stats(eb, tsel * 16 + c, ps->z[c], tw, th); - if (mode != YAPF__ENC_BOOK) continue; - size_t gsz = tmp->len - off[c]; - int r = yapf__huff_emit_plane(tmp, ps->z[c], ps->filt[c], tw, th, eb, tsel * 16 + c); - if (r < 0) return -1; - size_t hsz = r ? (size_t)-1 : tmp->len - off[c] - gsz; - if (!r && hsz + gsz / 32 < gsz) { - memmove(tmp->buf + off[c], tmp->buf + off[c] + gsz, hsz); - tmp->len = off[c] + hsz; - emask |= 1u << c; - } else { - tmp->len = off[c] + gsz; - } - } - if (yapf__reserve(o, 5 + (size_t)ps->np + tmp->len) != 0) return -1; - o->buf[o->len++] = (uint8_t)(hdr | (emask ? YAPF__ENTROPY : 0)); - if (ps->wide) { yapf__w16le(o->buf + o->len, ps->cmask); o->len += 2; } - if (emask) { - if (ps->wide) { yapf__w16le(o->buf + o->len, emask); o->len += 2; } - else o->buf[o->len++] = (uint8_t)emask; - } - for (int c = 0; c < ps->np; c++) - if (ps->cmask & (1u << c)) o->buf[o->len++] = ps->cval[c]; - if (tmp->len) memcpy(o->buf + o->len, tmp->buf, tmp->len); - o->len += tmp->len; - return 0; -} - -/* ── Wide samples (version 2) ────────────────────────────────────────── */ -/* - * 16- and 32-bit samples are coded as byte planes with the 8-bit - * machinery. Floats first become order-preserving integers (sign set: - * all bits flipped; else the sign bit set), so nearby values stay nearby. - * The colour transforms are the 8-bit ones at the sample width (mod 2^16 - * or 2^32); a third choice keeps R, G, B as they are. Channel c gives - * planes c·B .. c·B + B − 1, most significant byte first, so the smooth - * high bytes and the noisy low bytes each get their own filters. - */ -#define YAPF__MAX_PLANES 16 -#define YAPF__ROW (YAPF_TILE_SIZE + 1) - -static size_t yapf__sbytes(int sample) { - return sample == YAPF_SAMPLE_U8 ? 1 : sample == YAPF_SAMPLE_F32 ? 4 : 2; -} - -static uint32_t yapf__vmask(int bits) { - return bits == 32 ? 0xFFFFFFFFu : (1u << bits) - 1; -} - -static uint32_t yapf__fmap(uint32_t v, int bits) { - uint32_t s = 1u << (bits - 1); - return (v & s) ? (~v & yapf__vmask(bits)) : (v | s); -} - -static uint32_t yapf__funmap(uint32_t v, int bits) { - uint32_t s = 1u << (bits - 1); - return (v & s) ? (v ^ s) : (~v & yapf__vmask(bits)); -} - -/* Arithmetic shift right by one of a bits-wide two's complement value. */ -static uint32_t yapf__sar1(uint32_t v, int bits) { - return ((v >> 1) | (v & (1u << (bits - 1)))) & yapf__vmask(bits); -} - -static uint32_t yapf__get_sample(const uint8_t *p, int sample) { - if (sample == YAPF_SAMPLE_U8) return *p; - if (sample == YAPF_SAMPLE_F32) { uint32_t v; memcpy(&v, p, 4); return v; } - uint16_t v; memcpy(&v, p, 2); return v; -} - -static void yapf__put_sample(uint8_t *p, int sample, uint32_t v) { - if (sample == YAPF_SAMPLE_U8) { *p = (uint8_t)v; return; } - if (sample == YAPF_SAMPLE_F32) { memcpy(p, &v, 4); return; } - uint16_t h = (uint16_t)v; - memcpy(p, &h, 2); -} - -typedef struct { - uint8_t plane[2][YAPF__MAX_PLANES][YAPF__TILE_PX]; - uint8_t z[2][YAPF__MAX_PLANES][YAPF__TILE_PX + YAPF__GROUP]; - uint8_t filt[2][YAPF__MAX_PLANES][YAPF_TILE_SIZE / YAPF__BAND]; - uint32_t val[4][YAPF__TILE_PX]; -} yapf__wscratch; - -static int yapf__encode_tile_wide( - yapf__out *o, yapf__out *tmp, yapf__wscratch *sc, - const uint8_t *pixels, uint32_t img_w, - uint32_t tx, uint32_t ty, uint32_t tw, uint32_t th, - int ch, int sample, int mode, yapf__ebook *eb) -{ - int sb = (int)yapf__sbytes(sample), bits = 8 * sb; - int isf = sample == YAPF_SAMPLE_F16 || sample == YAPF_SAMPLE_F32; - int np = ch * sb; - uint32_t total = tw * th, half = 1u << (bits - 1), m = yapf__vmask(bits); - size_t start = o->len, raw = (size_t)total * ch * sb; - int tries = ch >= 3 ? 3 : 1, cur = 0; - uint32_t best_est = UINT32_MAX, cmask[2] = { 0, 0 }; - uint8_t cval[2][YAPF__MAX_PLANES]; - uint8_t xfs[2] = { 0, 0 }; - - /* t = 0: YCoCg-R, 1: subtract-green, 2: none (only with 3+ channels; - * with 1–2 channels the planes are the channels). */ - for (int t = 0; t < tries; t++) { - for (uint32_t y = 0; y < th; y++) { - const uint8_t *row = pixels + ((size_t)(ty + y) * img_w + tx) * (size_t)ch * sb; - for (uint32_t x = 0; x < tw; x++) { - uint32_t v[4], i = y * tw + x; - for (int c = 0; c < ch; c++) { - v[c] = yapf__get_sample(row + ((size_t)x * ch + c) * sb, sample); - if (isf) v[c] = yapf__fmap(v[c], bits); - } - if (ch >= 3 && t == 0) { - uint32_t r = v[0], g = v[1], b = v[2]; - uint32_t o_ = (r - b) & m, t_ = (b + yapf__sar1(o_, bits)) & m; - uint32_t q = (g - t_) & m; - v[0] = (t_ + yapf__sar1(q, bits)) & m; - v[1] = (o_ + half) & m; - v[2] = (q + half) & m; - } else if (ch >= 3 && t == 1) { - uint32_t r = v[0], g = v[1], b = v[2]; - v[0] = g; - v[1] = (r - g + half) & m; - v[2] = (b - g + half) & m; - } - for (int c = 0; c < ch; c++) sc->val[c][i] = v[c]; - } - } - /* planes, constant mask, filters, size estimate */ - uint8_t (*plane)[YAPF__TILE_PX] = sc->plane[cur]; - uint32_t est = 0, cm = 0; - for (int c = 0; c < ch; c++) - for (int k = 0; k < sb; k++) { - int pl = c * sb + k, sh = 8 * (sb - 1 - k); - uint8_t *P = plane[pl]; - for (uint32_t i = 0; i < total; i++) P[i] = (uint8_t)(sc->val[c][i] >> sh); - uint32_t i = 1; - while (i < total && P[i] == P[0]) i++; - if (i == total) { cm |= 1u << pl; cval[cur][pl] = P[0]; est += 16; continue; } - est += yapf__choose_filters(P, tw, th, sc->z[cur][pl], sc->filt[cur][pl]); - } - if (est < best_est) { - best_est = est; - cmask[cur] = cm; - xfs[cur] = (uint8_t)t; - cur ^= 1; /* keep this set, work in the other one */ - } - } - int keep = cur ^ 1; - uint8_t hdr = ch < 3 ? 0 : xfs[keep] == 1 ? YAPF__SUBGREEN : xfs[keep] == 2 ? YAPF__NOXFORM : 0; - - yapf__planeset ps; - memset(&ps, 0, sizeof(ps)); - ps.np = np; - ps.wide = 1; - ps.cmask = cmask[keep]; - ps.cval = cval[keep]; - for (int c = 0; c < np; c++) { ps.z[c] = sc->z[keep][c]; ps.filt[c] = sc->filt[keep][c]; } - if (yapf__emit_planeset(o, tmp, hdr, &ps, tw, th, mode, eb) != 0) return -1; - - if (o->len - start > raw + 1) { /* stored: raw LE samples */ - o->len = start; - if (yapf__reserve(o, raw + 1) != 0) return -1; - o->buf[o->len++] = YAPF__STORED; - for (uint32_t y = 0; y < th; y++) { - const uint8_t *row = pixels + ((size_t)(ty + y) * img_w + tx) * (size_t)ch * sb; - for (uint32_t i = 0; i < tw * (uint32_t)ch; i++) { - uint32_t v = yapf__get_sample(row + (size_t)i * sb, sample); - for (int k = 0; k < sb; k++) o->buf[o->len++] = (uint8_t)(v >> (8 * k)); - } - } - } - return 0; -} - -typedef struct { - uint8_t plane[YAPF__MAX_PLANES][YAPF_TILE_SIZE * YAPF__ROW]; - uint8_t z[YAPF__TILE_PX + YAPF_TILE_SIZE]; -} yapf__wdec; - -static int yapf__decode_tile_wide( - const uint8_t *data, size_t len, - uint8_t *pixels, uint32_t img_w, - uint32_t tx, uint32_t ty, uint32_t tw, uint32_t th, - int ch, int sample, int simd, const yapf__dbook *bk, yapf__wdec *sc) -{ - int sb = (int)yapf__sbytes(sample), bits = 8 * sb, np = ch * sb; - int isf = sample == YAPF_SAMPLE_F16 || sample == YAPF_SAMPLE_F32; - uint32_t half = 1u << (bits - 1), m = yapf__vmask(bits); - const uint8_t *p = data, *end = data + len; - size_t rowb = (size_t)tw * ch * sb; - - if (len == 0) return -1; - uint8_t hdr = *p++; - if (hdr == YAPF__STORED) { - if (len != 1 + rowb * th) return -1; - for (uint32_t y = 0; y < th; y++) { - uint8_t *d = pixels + ((size_t)(ty + y) * img_w + tx) * (size_t)ch * sb; - for (uint32_t i = 0; i < tw * (uint32_t)ch; i++, p += sb) { - uint32_t v = 0; - for (int k = sb; k-- > 0; ) v = (v << 8) | p[k]; - yapf__put_sample(d + (size_t)i * sb, sample, v); - } - } - return 0; - } - if (hdr & 0x8F) return -1; - if ((hdr & YAPF__NOXFORM) && (hdr & YAPF__SUBGREEN)) return -1; - if (ch < 3 && (hdr & (YAPF__NOXFORM | YAPF__SUBGREEN))) return -1; - int xf = (hdr & YAPF__NOXFORM) ? 2 : (hdr & YAPF__SUBGREEN) ? 1 : 0; - if (ch < 3) xf = 2; - - if (end - p < 2) return -1; - uint32_t cmask = yapf__r16le(p), emask = 0; - p += 2; - if (cmask >> np) return -1; - if (hdr & YAPF__ENTROPY) { - if (end - p < 2 || !bk) return -1; - emask = yapf__r16le(p); - p += 2; - if ((emask >> np) || (emask & cmask)) return -1; - } - for (int pl = 0; pl < np; pl++) { - if (!(cmask & (1u << pl))) continue; - if (p >= end) return -1; - memset(sc->plane[pl], *p++, sizeof(sc->plane[pl])); - } - for (int pl = 0; pl < np; pl++) { - if (cmask & (1u << pl)) continue; - const uint8_t *filt = NULL; - memset(sc->z + (size_t)tw * th, 0, sizeof(sc->z) - (size_t)tw * th); - p = (emask & (1u << pl)) - ? yapf__huff_plane(p, end, sc->z, &filt, tw, th, bk, (ch < 3 ? 0 : xf) * 16 + pl) - : yapf__unpack_plane(p, end, sc->z, &filt, tw, th, simd); - if (!p) return -1; - if (tw != YAPF_TILE_SIZE) { - size_t used = ((size_t)tw * th + YAPF__GROUP - 1) / YAPF__GROUP * YAPF__GROUP; - memset(sc->z + used, 0, sizeof(sc->z) - used); - } - uint8_t *P = sc->plane[pl]; - for (uint32_t y = 0; y < th; y++) { - uint8_t f = filt[y / YAPF__BAND]; - uint32_t k = f >= YAPF__F_UP ? (uint32_t)(f - YAPF__F_UP + 1) : 1; - uint8_t *R = P + (size_t)y * YAPF__ROW; - const uint8_t *U = y ? R - YAPF__ROW : yapf__zero_row; - const uint8_t *K = y >= k ? R - (size_t)k * YAPF__ROW : yapf__zero_row; - const uint8_t *Z = sc->z + (size_t)y * tw; -#if YAPF__SIMD - if (simd) { - if (f == YAPF__F_LEFT || f == YAPF__F_GRAD) - yapf__simd_serial_row(f, R, U, Z, tw); - else if (f >= YAPF__F_UP) - yapf__simd_vertical_row(R, K, K, Z, tw); - else if (f == YAPF__F_UPAVG) - yapf__simd_vertical_row(R, U, U + 1, Z, tw); - else - yapf__simd_vertical_row(R, U + 1, U + 1, Z, tw); - R[tw] = R[tw - 1]; - continue; - } -#endif - yapf__unfilter_row(f, R, U, K, Z, tw); - } - } - if (p != end) return -1; - - for (uint32_t y = 0; y < th; y++) { - uint8_t *d = pixels + ((size_t)(ty + y) * img_w + tx) * (size_t)ch * sb; - size_t r = (size_t)y * YAPF__ROW; - for (uint32_t x = 0; x < tw; x++) { - uint32_t v[4]; - for (int c = 0; c < ch; c++) { - uint32_t a = 0; - for (int k = 0; k < sb; k++) a = (a << 8) | sc->plane[c * sb + k][r + x]; - v[c] = a; - } - if (xf == 0) { - uint32_t o_ = (v[1] - half) & m, q = (v[2] - half) & m; - uint32_t t_ = (v[0] - yapf__sar1(q, bits)) & m; - uint32_t g = (q + t_) & m; - uint32_t b = (t_ - yapf__sar1(o_, bits)) & m; - v[0] = (b + o_) & m; - v[1] = g; - v[2] = b; - } else if (xf == 1) { - uint32_t g = v[0]; - v[0] = (v[1] + g - half) & m; - v[2] = (v[2] + g - half) & m; - v[1] = g; - } - for (int c = 0; c < ch; c++) - yapf__put_sample(d + ((size_t)x * ch + c) * sb, sample, - isf ? yapf__funmap(v[c], bits) : v[c]); - } - } - return 0; -} - -/* ── GPU block tiles (version 2) ─────────────────────────────────────── */ -/* - * A block tile holds up to 16 × 16 blocks, rows of blocks top to bottom, - * exactly as the GPU takes them. Packed tiles (bit 31 of the tile size) - * code the bytes lane by lane — byte 0 of every block, then byte 1, … — - * each lane with its own table of the surface's code book (slot = lane): - * endpoint bytes and index bytes have very different statistics. The - * bit stream fills the tile exactly. - */ -static int yapf__decode_block_tile(const uint8_t *src, size_t len, int packed, - uint8_t *dst, size_t dst_row, - uint32_t tbw, uint32_t tbh, uint32_t S, - const yapf__dbook *bk) -{ - size_t n = (size_t)tbw * tbh, raw = n * S; - if (!packed) { - if (len != raw) return -1; - for (uint32_t r = 0; r < tbh; r++) - memcpy(dst + r * dst_row, src + (size_t)r * tbw * S, (size_t)tbw * S); - return 0; - } - if (!bk) return -1; - yapf__br br; - yapf__br_init(&br, src, len); - for (uint32_t k = 0; k < S; k++) { - const uint16_t *lut = bk->slot[k]; - if (!lut) return -1; - for (size_t i = 0; i < n; i++) { - int v = yapf__br_sym(&br, lut); - if (v < 0) return -1; - dst[(i / tbw) * dst_row + (i % tbw) * S + k] = (uint8_t)v; - } - } - return yapf__br_done(&br) ? 0 : -1; -} - -/* Writes one block tile; *packed is set when the packed form is used. */ -static int yapf__encode_block_tile(yapf__out *o, const uint8_t *src, size_t src_row, - uint32_t tbw, uint32_t tbh, uint32_t S, - int mode, yapf__ebook *eb, int *packed) -{ - size_t n = (size_t)tbw * tbh, raw = n * S; - *packed = 0; - if (mode == YAPF__ENC_STATS) - for (uint32_t r = 0; r < tbh; r++) - for (size_t i = 0; i < (size_t)tbw * S; i++) - eb->freq[i % S][0][src[r * src_row + i]]++; - if (mode == YAPF__ENC_BOOK) { - uint64_t bits = 0; - for (uint32_t r = 0; r < tbh && bits != UINT64_MAX; r++) - for (size_t i = 0; i < (size_t)tbw * S; i++) { - uint8_t l = eb->len[i % S][0][src[r * src_row + i]]; - if (!l) { bits = UINT64_MAX; break; } - bits += l; - } - if (bits != UINT64_MAX && (bits + 7) / 8 < raw) { - if (yapf__reserve(o, (size_t)(bits + 7) / 8 + 8) != 0) return -1; - yapf__bitw bw = { 0, 0, o }; - for (uint32_t k = 0; k < S; k++) /* lane by lane */ - for (size_t i = 0; i < n; i++) { - uint8_t v = src[(i / tbw) * src_row + (i % tbw) * S + k]; - yapf__bitw_put(&bw, eb->code[k][0][v], eb->len[k][0][v]); - } - yapf__bitw_flush(&bw); - *packed = 1; - return 0; - } - } - if (yapf__reserve(o, raw) != 0) return -1; - for (uint32_t r = 0; r < tbh; r++) { - memcpy(o->buf + o->len, src + r * src_row, (size_t)tbw * S); - o->len += (size_t)tbw * S; - } - return 0; -} - -/* Encoder scratch, heap allocated once per level (too big for small - * thread stacks). */ -typedef struct { - uint8_t plane[2][4][YAPF__TILE_PX]; - uint8_t z[2][4][YAPF__TILE_PX + YAPF__GROUP]; - uint8_t filt[2][4][YAPF_TILE_SIZE / YAPF__BAND]; -} yapf__scratch; - -static int yapf__encode_tile( - yapf__out *o, yapf__scratch *sc, - const uint8_t *pixels, uint32_t img_w, - uint32_t tx, uint32_t ty, uint32_t tw, uint32_t th, - int ch, int mode, yapf__ebook *eb, yapf__out *tmp) -{ - uint32_t total = tw * th; - size_t start = o->len; - size_t raw = (size_t)total * ch; - int tries = ch >= 3 ? 2 : 1; - uint8_t mask[2] = { 0, 0 }; - uint32_t est[2] = { 0, 0 }; - - /* For each colour transform: planes, constant mask, filters, and an - * estimate of the coded size. Only the cheaper one is written. */ - for (int t = 0; t < tries; t++) { - uint8_t (*plane)[YAPF__TILE_PX] = sc->plane[t]; - for (uint32_t y = 0; y < th; y++) { - const uint8_t *row = pixels + ((size_t)(ty + y) * img_w + tx) * (size_t)ch; - for (uint32_t x = 0; x < tw; x++) { - const uint8_t *s = row + (size_t)x * ch; - uint32_t i = y * tw + x; - if (ch < 3) { - for (int c = 0; c < ch; c++) plane[c][i] = s[c]; - continue; - } - if (t == 0) { - yapf__forward(&plane[0][i], &plane[1][i], &plane[2][i], - s[0], s[1], s[2]); - } else { - plane[0][i] = s[1]; - plane[1][i] = (uint8_t)(s[0] - s[1] + 128); - plane[2][i] = (uint8_t)(s[2] - s[1] + 128); - } - if (ch == 4) plane[3][i] = s[3]; - } - } - for (int c = 0; c < ch; c++) { - uint32_t i = 1; - while (i < total && plane[c][i] == plane[c][0]) i++; - if (i == total) { mask[t] |= (uint8_t)(1u << c); est[t] += 16; continue; } - est[t] += yapf__choose_filters(plane[c], tw, th, sc->z[t][c], sc->filt[t][c]); - } - } - int t = (tries == 2 && est[1] < est[0]) ? 1 : 0; - - if (mode != YAPF__ENC_PLAIN) { /* v2: statistics / entropy planes */ - yapf__planeset ps; - uint8_t cval[4]; - memset(&ps, 0, sizeof(ps)); - ps.np = ch; - ps.cmask = mask[t]; - ps.cval = cval; - for (int c = 0; c < ch; c++) { - cval[c] = sc->plane[t][c][0]; - ps.z[c] = sc->z[t][c]; - ps.filt[c] = sc->filt[t][c]; - } - if (yapf__emit_planeset(o, tmp, (uint8_t)(mask[t] | (t ? YAPF__SUBGREEN : 0)), - &ps, tw, th, mode, eb) != 0) return -1; - } else { - if (yapf__reserve(o, 1 + 4) != 0) return -1; - o->buf[o->len++] = (uint8_t)(mask[t] | (t ? YAPF__SUBGREEN : 0)); - for (int c = 0; c < ch; c++) - if (mask[t] & (1u << c)) o->buf[o->len++] = sc->plane[t][c][0]; - for (int c = 0; c < ch; c++) - if (!(mask[t] & (1u << c)) && - yapf__emit_plane(o, sc->z[t][c], sc->filt[t][c], tw, th) != 0) return -1; - } - - /* Fall back to a stored tile if coding did not pay off. */ - if (o->len - start > raw + 1) { - o->len = start; - if (yapf__reserve(o, raw + 1) != 0) return -1; - o->buf[o->len++] = YAPF__STORED; - for (uint32_t y = 0; y < th; y++) { - const uint8_t *row = pixels + ((size_t)(ty + y) * img_w + tx) * (size_t)ch; - memcpy(o->buf + o->len, row, (size_t)tw * ch); - o->len += (size_t)tw * ch; - } - } - return 0; -} - -/* v2 (version 2 files) additionally allows bit 5 (a mask byte follows: - * bit c = plane c is entropy coded with book bk) and bit 6 (no colour - * transform). */ -static int yapf__decode_tile( - const uint8_t *data, size_t len, - uint8_t *pixels, uint32_t img_w, - uint32_t tx, uint32_t ty, uint32_t tw, uint32_t th, - int ch, int simd, int v2, const yapf__dbook *bk) -{ - uint8_t rows[4][YAPF__RING][YAPF_TILE_SIZE + 1]; /* last rows, ring */ - uint8_t z[4][YAPF__TILE_PX + YAPF__GROUP]; - const uint8_t *filt[4] = { NULL, NULL, NULL, NULL }; - size_t rowb = (size_t)tw * ch; - const uint8_t *p = data, *end = data + len; - - if (len == 0) return -1; - uint8_t hdr = *p++; - - if (hdr == YAPF__STORED) { - if (len != 1 + rowb * th) return -1; - for (uint32_t y = 0; y < th; y++) - memcpy(pixels + ((size_t)(ty + y) * img_w + tx) * (size_t)ch, - p + rowb * y, rowb); - return 0; - } - if (hdr & (v2 ? 0x80 : 0xE0)) return -1; /* reserved bits set */ - if ((hdr & YAPF__NOXFORM) && (hdr & YAPF__SUBGREEN)) return -1; - uint8_t xf = (hdr & YAPF__NOXFORM) ? 2 : (hdr & YAPF__SUBGREEN) ? 1 : 0; - uint8_t emask = 0; - int ent = hdr & YAPF__ENTROPY; - hdr &= 0x0F; - if ((hdr >> ch) || (xf && ch < 3)) return -1; /* unknown bits set */ - if (ent) { - if (p >= end || !bk) return -1; /* entropy needs the surface book */ - emask = *p++; - if ((emask >> ch) || (emask & hdr)) return -1; - } - - for (int c = 0; c < ch; c++) { - if (!(hdr & (1u << c))) continue; - if (p >= end) return -1; - memset(rows[c], *p++, sizeof(rows[c])); - } - yapf__hstream hs[4]; - int nh = 0; - for (int c = 0; c < ch; c++) { - if (hdr & (1u << c)) continue; - p = (emask & (1u << c)) - ? yapf__huff_head(p, end, &filt[c], th, bk, xf * 16 + c, z[c], &hs[nh++]) - : yapf__unpack_plane(p, end, z[c], &filt[c], tw, th, simd); - if (!p) return -1; - /* SIMD row kernels read whole 16-sample chunks; keep the unused - * tail of narrow tiles defined. */ - if (tw != YAPF_TILE_SIZE) { - size_t used = ((size_t)tw * th + YAPF__GROUP - 1) / YAPF__GROUP * YAPF__GROUP; - memset(z[c] + used, 0, sizeof(z[c]) - used); - } - } - if (p != end) return -1; - if (nh && yapf__huff_run(hs, nh, tw, th) != 0) return -1; - - /* Row by row: undo the filters of every plane (independent dependency - * chains the CPU can overlap), then the colour transform while the - * row is still in L1. */ - for (uint32_t y = 0; y < th; y++) { - for (int c = 0; c < ch; c++) { - if (!filt[c]) continue; - uint8_t f = filt[c][y / YAPF__BAND]; - uint32_t k = f >= YAPF__F_UP ? (uint32_t)(f - YAPF__F_UP + 1) : 1; - uint8_t *R = rows[c][y % YAPF__RING]; - const uint8_t *U = y ? rows[c][(y - 1) % YAPF__RING] : yapf__zero_row; - const uint8_t *K = y >= k ? rows[c][(y - k) % YAPF__RING] : yapf__zero_row; - const uint8_t *Z = z[c] + y * tw; -#if YAPF__SIMD - if (simd) { - if (f == YAPF__F_LEFT || f == YAPF__F_GRAD) - yapf__simd_serial_row(f, R, U, Z, tw); - else if (f >= YAPF__F_UP) - yapf__simd_vertical_row(R, K, K, Z, tw); - else if (f == YAPF__F_UPAVG) - yapf__simd_vertical_row(R, U, U + 1, Z, tw); - else - yapf__simd_vertical_row(R, U + 1, U + 1, Z, tw); - R[tw] = R[tw - 1]; - continue; - } -#endif - yapf__unfilter_row(f, R, U, K, Z, tw); - } - - uint8_t *d = pixels + ((size_t)(ty + y) * img_w + tx) * (size_t)ch; - const uint8_t *P0 = rows[0][y % YAPF__RING], *P1 = rows[1][y % YAPF__RING]; - const uint8_t *P2 = rows[2][y % YAPF__RING], *P3 = rows[3][y % YAPF__RING]; -#if YAPF__SIMD - if (simd) { - if (tw == YAPF_TILE_SIZE) { - yapf__simd_inverse_row(d, P0, P1, P2, P3, ch, xf); - } else { - uint8_t tmp[YAPF_TILE_SIZE * 4]; - yapf__simd_inverse_row(tmp, P0, P1, P2, P3, ch, xf); - memcpy(d, tmp, (size_t)tw * ch); - } - continue; - } -#endif - -#define YAPF__INVERSE(N, ALPHA) \ - for (uint32_t x = 0; x < tw; x++, d += N) { \ - uint8_t co = (uint8_t)(P1[x] - 128), cg = (uint8_t)(P2[x] - 128); \ - uint8_t t = (uint8_t)(P0[x] - ((int8_t)cg >> 1)); \ - uint8_t b = (uint8_t)(t - ((int8_t)co >> 1)); \ - d[0] = (uint8_t)(b + co); \ - d[1] = (uint8_t)(cg + t); \ - d[2] = b; \ - ALPHA; \ - } -#define YAPF__INVERSE_SG(N, ALPHA) \ - for (uint32_t x = 0; x < tw; x++, d += N) { \ - uint8_t g = P0[x]; \ - d[0] = (uint8_t)(P1[x] + g - 128); \ - d[1] = g; \ - d[2] = (uint8_t)(P2[x] + g - 128); \ - ALPHA; \ - } - if (ch == 3) { - /* Planes → separate R, G, B rows (vectorises), then interleave. */ - uint8_t rgb[3][YAPF_TILE_SIZE]; - if (xf == 2) { - memcpy(rgb[0], P0, tw); memcpy(rgb[1], P1, tw); memcpy(rgb[2], P2, tw); - } else if (xf) { - for (uint32_t x = 0; x < tw; x++) { - uint8_t g = P0[x]; - rgb[0][x] = (uint8_t)(P1[x] + g - 128); - rgb[1][x] = g; - rgb[2][x] = (uint8_t)(P2[x] + g - 128); - } - } else { - for (uint32_t x = 0; x < tw; x++) { - uint8_t co = (uint8_t)(P1[x] - 128), cg = (uint8_t)(P2[x] - 128); - uint8_t t = (uint8_t)(P0[x] - ((int8_t)cg >> 1)); - uint8_t b = (uint8_t)(t - ((int8_t)co >> 1)); - rgb[0][x] = (uint8_t)(b + co); - rgb[1][x] = (uint8_t)(cg + t); - rgb[2][x] = b; - } - } - d = pixels + ((size_t)(ty + y) * img_w + tx) * 3; - for (uint32_t x = 0; x < tw; x++, d += 3) { - d[0] = rgb[0][x]; d[1] = rgb[1][x]; d[2] = rgb[2][x]; - } - } else if (xf == 2) { - for (uint32_t x = 0; x < tw; x++, d += 4) { - d[0] = P0[x]; d[1] = P1[x]; d[2] = P2[x]; d[3] = P3[x]; - } - } else if (xf) { - YAPF__INVERSE_SG(4, d[3] = P3[x]) - } else if (ch == 4) { - YAPF__INVERSE(4, d[3] = P3[x]) - } else if (ch == 2) { - for (uint32_t x = 0; x < tw; x++, d += 2) { d[0] = P0[x]; d[1] = P1[x]; } - } else { - memcpy(d, P0, tw); - } -#undef YAPF__INVERSE -#undef YAPF__INVERSE_SG - } - return 0; -} - -/* ── Level encode / decode ───────────────────────────────────────────── */ -/* - * Level layout: - * uint32 tile_size[tile_count] byte size of each tile, row-major order - * tile data, back to back - * Tiles are independent, so they can be decoded in any order or in - * parallel, and a sub-rectangle can be decoded without the rest. - */ - -static uint32_t yapf__tiles(uint32_t n) { - return (n + YAPF_TILE_SIZE - 1) / YAPF_TILE_SIZE; -} - -static int yapf__encode_level( - yapf__out *o, const uint8_t *pixels, uint32_t mw, uint32_t mh, int ch) -{ - uint32_t tcx = yapf__tiles(mw), tcy = yapf__tiles(mh); - size_t tcount = (size_t)tcx * tcy; - - /* Each level has its own buffer, so the table starts at offset 0. - * Reserve the size table, fill it after each tile is written. */ - if (yapf__reserve(o, tcount * 4) != 0) return -1; - memset(o->buf, 0, tcount * 4); - o->len = tcount * 4; - - yapf__scratch *sc = (yapf__scratch *)malloc(sizeof(yapf__scratch)); - if (!sc) return -1; - - size_t t = 0; - int rc = 0; - for (uint32_t ty = 0; ty < tcy && rc == 0; ty++) { - for (uint32_t tx = 0; tx < tcx && rc == 0; tx++, t++) { - uint32_t x0 = tx * YAPF_TILE_SIZE, y0 = ty * YAPF_TILE_SIZE; - uint32_t tw = mw - x0 < YAPF_TILE_SIZE ? mw - x0 : YAPF_TILE_SIZE; - uint32_t th = mh - y0 < YAPF_TILE_SIZE ? mh - y0 : YAPF_TILE_SIZE; - size_t start = o->len; - rc = yapf__encode_tile(o, sc, pixels, mw, x0, y0, tw, th, ch, YAPF__ENC_PLAIN, NULL, NULL); - if (rc == 0) yapf__w32le(o->buf + t * 4, (uint32_t)(o->len - start)); - } - } - free(sc); - return rc; -} - -/* A level (surface) whose tile table has been validated; tiles can then - * be decoded in any order, from any thread. Version 1 levels are one - * 8-bit slice with 4-byte table entries; version 2 adds slices, wide - * samples, block tiles and 8-byte entries (size, yapf-sum). */ -typedef struct { - const uint8_t *data; - size_t *offs; /* tcount + 1 byte offsets into data */ - uint8_t *pixels; - uint32_t mw, mh, md, tcx, tcy; /* tcy: tile rows per slice */ - int ch; - int sample; /* YAPF_SAMPLE_* (pixel payload) */ - int simd; /* SIMD kernels usable on this CPU */ - int v2; - int verify; /* check tile yapf-sums */ - uint32_t blk; /* bytes per GPU block, 0 = pixel payload */ - uint32_t nbx, nby; /* blocks across / down */ - yapf__dbook *book; /* the surface's code book, or NULL */ -} yapf__level; - -static void yapf__level_free(yapf__level *lv) { - free(lv->offs); - lv->offs = NULL; - if (lv->book) { free(lv->book->mem); free(lv->book); lv->book = NULL; } -} - -/* Parses the tile table; lv must have data, the grid and v2 set. */ -static int yapf__level_table(yapf__level *lv, size_t len) { - uint64_t tc64 = (uint64_t)lv->tcx * lv->tcy * lv->md; - size_t ent = lv->v2 ? 8 : 4; - if ((uint64_t)(len / ent) < tc64) return -1; - size_t tcount = (size_t)tc64; - lv->offs = (size_t *)malloc((tcount + 1) * sizeof(size_t)); - if (!lv->offs) return -1; - - size_t pos = tcount * ent; - for (size_t t = 0; t < tcount; t++) { - uint32_t sz = yapf__r32le(lv->data + t * ent); - if (lv->v2) { - if ((sz >> 31) && (!lv->blk || !lv->book)) return -1; /* packed: blocks + book */ - sz &= 0x7FFFFFFFu; - } - if (sz > len - pos) return -1; - lv->offs[t] = pos; - pos += sz; - } - lv->offs[tcount] = pos; - if (lv->v2 && pos != len) return -1; - return 0; -} - -static int yapf__level_init(yapf__level *lv, const uint8_t *data, size_t len, - uint8_t *pixels, uint32_t mw, uint32_t mh, int ch) -{ - lv->data = data; - lv->pixels = pixels; - lv->mw = mw; - lv->mh = mh; - lv->md = 1; - lv->tcx = yapf__tiles(mw); - lv->tcy = yapf__tiles(mh); - lv->ch = ch; - lv->sample = YAPF_SAMPLE_U8; - return yapf__level_table(lv, len); -} - -/* Decodes tile (tx, row) of a level, row counting across all slices. - * dst == NULL writes into the level's pixels; otherwise into dst with - * dst_w texels (or blocks) per row, the tile at its top-left corner. - * Returns 0, -1 (corrupt) or YAPF_ERR_CHECKSUM. */ -static int yapf__level_tile(const yapf__level *lv, uint32_t tx, uint32_t row, - yapf__wdec *wsc, uint8_t *dst, size_t dst_w) -{ - size_t t = (size_t)row * lv->tcx + tx; - uint32_t z = row / lv->tcy, ty = row % lv->tcy; - const uint8_t *src = lv->data + lv->offs[t]; - size_t len = lv->offs[t + 1] - lv->offs[t]; - - if (lv->v2 && lv->verify && yapf_checksum(src, len) != yapf__r32le(lv->data + t * 8 + 4)) - return YAPF_ERR_CHECKSUM; - - if (lv->blk) { - uint32_t bx0 = tx * YAPF_BLOCK_TILE, by0 = ty * YAPF_BLOCK_TILE; - uint32_t tbw = lv->nbx - bx0 < YAPF_BLOCK_TILE ? lv->nbx - bx0 : YAPF_BLOCK_TILE; - uint32_t tbh = lv->nby - by0 < YAPF_BLOCK_TILE ? lv->nby - by0 : YAPF_BLOCK_TILE; - int packed = (int)(yapf__r32le(lv->data + t * 8) >> 31); - size_t rowb; - if (!dst) { - rowb = (size_t)lv->nbx * lv->blk; - dst = lv->pixels + (size_t)z * lv->nby * rowb + (size_t)by0 * rowb + (size_t)bx0 * lv->blk; - } else { - rowb = dst_w * lv->blk; - } - return yapf__decode_block_tile(src, len, packed, dst, rowb, tbw, tbh, lv->blk, lv->book); - } - - uint32_t x0 = tx * YAPF_TILE_SIZE, y0 = ty * YAPF_TILE_SIZE; - uint32_t tw = lv->mw - x0 < YAPF_TILE_SIZE ? lv->mw - x0 : YAPF_TILE_SIZE; - uint32_t th = lv->mh - y0 < YAPF_TILE_SIZE ? lv->mh - y0 : YAPF_TILE_SIZE; - size_t px = yapf__sbytes(lv->sample) * (size_t)lv->ch; - uint8_t *base; - uint32_t img_w; - if (!dst) { - base = lv->pixels + (size_t)z * lv->mw * lv->mh * px; - img_w = lv->mw; - } else { - base = dst; - img_w = (uint32_t)dst_w; - x0 = y0 = 0; - } - if (lv->sample == YAPF_SAMPLE_U8) - return yapf__decode_tile(src, len, base, img_w, x0, y0, tw, th, lv->ch, lv->simd, lv->v2, lv->book); - return yapf__decode_tile_wide(src, len, base, img_w, x0, y0, tw, th, lv->ch, - lv->sample, lv->simd, lv->book, wsc); -} - -/* Decode tile rows first_row, first_row + step, ... (over all slices) */ -static int yapf__level_decode_rows(const yapf__level *lv, - uint32_t first_row, uint32_t step) -{ - uint32_t rows = lv->tcy * lv->md; - yapf__wdec *wsc = NULL; - int rc = 0; - if (!lv->blk && lv->sample != YAPF_SAMPLE_U8 && first_row < rows) { - wsc = (yapf__wdec *)malloc(sizeof(yapf__wdec)); - if (!wsc) return YAPF_ERR_OOM; - } - for (uint32_t ty = first_row; ty < rows && rc == 0; ty += step) - for (uint32_t tx = 0; tx < lv->tcx && rc == 0; tx++) - rc = yapf__level_tile(lv, tx, ty, wsc, NULL, 0); - free(wsc); - return rc; -} - -/* ── Threads ─────────────────────────────────────────────────────────── */ -/* - * Worker t of n decodes tile rows t, t + n, t + 2n, ... of every level. - * Define YAPF_NO_THREADS to build without any threading support. - */ - -typedef struct { - const yapf__level *levels; - int nlevels; - uint32_t index, count; - int rc; -} yapf__job; - -static void yapf__job_run(yapf__job *j) { - j->rc = 0; - for (int m = 0; m < j->nlevels && j->rc == 0; m++) - j->rc = yapf__level_decode_rows(&j->levels[m], j->index, j->count); -} - -#if !defined(YAPF_NO_THREADS) && defined(_WIN32) -# include -# define YAPF__THREADS 1 -typedef HANDLE yapf__thread; -static DWORD WINAPI yapf__thread_main(LPVOID arg) { - yapf__job_run((yapf__job *)arg); - return 0; -} -static int yapf__thread_start(yapf__thread *t, yapf__job *j) { - *t = CreateThread(NULL, 0, yapf__thread_main, j, 0, NULL); - return *t ? 0 : -1; -} -static void yapf__thread_join(yapf__thread t) { - WaitForSingleObject(t, INFINITE); - CloseHandle(t); -} -static int yapf__cpu_count(void) { - SYSTEM_INFO si; - GetSystemInfo(&si); - return (int)si.dwNumberOfProcessors; -} -#elif !defined(YAPF_NO_THREADS) && (defined(__unix__) || defined(__APPLE__)) -# include -# include -# define YAPF__THREADS 1 -typedef pthread_t yapf__thread; -static void *yapf__thread_main(void *arg) { - yapf__job_run((yapf__job *)arg); - return NULL; -} -static int yapf__thread_start(yapf__thread *t, yapf__job *j) { - return pthread_create(t, NULL, yapf__thread_main, j) == 0 ? 0 : -1; -} -static void yapf__thread_join(yapf__thread t) { - pthread_join(t, NULL); -} -static int yapf__cpu_count(void) { - long n = sysconf(_SC_NPROCESSORS_ONLN); - return n > 0 ? (int)n : 1; -} -#else -# define YAPF__THREADS 0 -#endif - -#define YAPF__MAX_THREADS 64 -#define YAPF__TILES_PER_THREAD 32 - -/* Decode all levels with up to `threads` threads (0 = one per core). */ -static int yapf__decode_levels(const yapf__level *levels, int nlevels, - int threads) -{ - yapf__job jobs[YAPF__MAX_THREADS]; - int n = 1; - -#if YAPF__THREADS - yapf__thread th[YAPF__MAX_THREADS]; - n = threads > 0 ? threads : yapf__cpu_count(); - if (n > YAPF__MAX_THREADS) n = YAPF__MAX_THREADS; - { - uint32_t rows = 0; - for (int m = 0; m < nlevels; m++) - if (levels[m].tcy * levels[m].md > rows) rows = levels[m].tcy * levels[m].md; - if ((uint32_t)n > rows) n = (int)rows; - } - /* Starting a thread costs about as much as decoding a few tiles, so - * give each one at least YAPF__TILES_PER_THREAD tiles of work. */ - { - size_t tiles = 0; - for (int m = 0; m < nlevels; m++) tiles += (size_t)levels[m].tcx * levels[m].tcy; - if ((size_t)n > tiles / YAPF__TILES_PER_THREAD) - n = (int)(tiles / YAPF__TILES_PER_THREAD); - } - if (n < 1) n = 1; -#else - (void)threads; -#endif - - for (int i = 0; i < n; i++) { - jobs[i].levels = levels; - jobs[i].nlevels = nlevels; - jobs[i].index = (uint32_t)i; - jobs[i].count = (uint32_t)n; - } - -#if YAPF__THREADS - int started = 1; - for (; started < n; started++) - if (yapf__thread_start(&th[started], &jobs[started]) != 0) break; - /* If a thread failed to start, the calling thread takes its rows. */ - yapf__job_run(&jobs[0]); - for (int i = started; i < n; i++) yapf__job_run(&jobs[i]); - for (int i = 1; i < started; i++) yapf__thread_join(th[i]); -#else - yapf__job_run(&jobs[0]); -#endif - - for (int i = 0; i < n; i++) - if (jobs[i].rc != 0) return jobs[i].rc; - return 0; -} - -/* ======================================================================== - * yapf_load_memory / yapf_load - * ======================================================================== */ - -static yapf_image_t *yapf__load_v2_image(const uint8_t *buf, size_t size, int threads); - -static yapf_image_t *yapf__load(const uint8_t *buf, size_t size, int threads) { - if (!buf || size < YAPF__HDR_LEN) return NULL; - if (memcmp(buf, YAPF__MAGIC, 4) != 0) return NULL; - if (buf[4] == 2) return yapf__load_v2_image(buf, size, threads); - - uint8_t version = buf[4]; - uint8_t channels = buf[5]; - uint8_t mip_levels = buf[7]; - uint32_t base_w = yapf__r32le(buf + 12); - uint32_t base_h = yapf__r32le(buf + 16); - - if (version != YAPF__VERSION) return NULL; - if (channels < 1 || channels > 4) return NULL; - if (mip_levels < 1 || mip_levels > YAPF_MAX_MIPS) return NULL; - if (base_w == 0 || base_w > YAPF_MAX_DIM) return NULL; - if (base_h == 0 || base_h > YAPF_MAX_DIM) return NULL; - - size_t idx_end = YAPF__HDR_LEN + (size_t)mip_levels * YAPF__MIP_ENTRY; - if (size < idx_end) return NULL; - - yapf__level levels[YAPF_MAX_MIPS]; - memset(levels, 0, sizeof(levels)); - int ok = 0; - - yapf_image_t *img = (yapf_image_t *)calloc(1, sizeof(yapf_image_t)); - if (!img) return NULL; - img->width = base_w; - img->height = base_h; - img->channels = channels; - img->gpu_format = buf[6]; - img->flags = buf[8]; - img->mip_levels = mip_levels; - img->mips = (uint8_t **)calloc(mip_levels, sizeof(uint8_t *)); - if (!img->mips) goto done; - - for (uint8_t m = 0; m < mip_levels; m++) { - const uint8_t *e = buf + YAPF__HDR_LEN + (size_t)m * YAPF__MIP_ENTRY; - uint32_t off = yapf__r32le(e); - uint32_t len = yapf__r32le(e + 4); - uint32_t mw = base_w >> m; if (mw < 1) mw = 1; - uint32_t mh = base_h >> m; if (mh < 1) mh = 1; - - if (off < idx_end || off > size || len > size - off) goto done; - - img->mips[m] = (uint8_t *)malloc((size_t)mw * mh * channels); - if (!img->mips[m]) goto done; - - if (yapf__level_init(&levels[m], buf + off, len, - img->mips[m], mw, mh, channels) != 0) - goto done; - } - -#if YAPF__SIMD - { - int simd = yapf__simd_available(); - for (uint8_t m = 0; m < mip_levels; m++) levels[m].simd = simd; - } -#endif - ok = yapf__decode_levels(levels, mip_levels, threads) == 0; - -done: - for (unsigned m = 0; m < YAPF_MAX_MIPS; m++) free(levels[m].offs); - if (!ok) { yapf_free(img); return NULL; } - img->pixels = img->mips[0]; - return img; -} - -yapf_image_t *yapf_load_memory(const void *buffer, size_t size) { - return yapf__load((const uint8_t *)buffer, size, 1); -} - -yapf_image_t *yapf_load_memory_mt(const void *buffer, size_t size, int threads) { - return yapf__load((const uint8_t *)buffer, size, threads); -} - -static uint8_t *yapf__read_file(const char *filename, size_t *out_len) { - if (!filename) return NULL; - FILE *f = fopen(filename, "rb"); - if (!f) return NULL; - - /* Read the whole file in chunks; avoids ftell() limits on 32-bit long. */ - size_t cap = 1 << 16, len = 0; - uint8_t *buf = (uint8_t *)malloc(cap); - while (buf) { - size_t n = fread(buf + len, 1, cap - len, f); - len += n; - if (len < cap) break; - uint8_t *nb = (uint8_t *)realloc(buf, cap * 2); - if (!nb) { free(buf); buf = NULL; break; } - buf = nb; - cap *= 2; - } - int err = ferror(f); - fclose(f); - if (!buf) return NULL; - if (err) { free(buf); return NULL; } - *out_len = len; - return buf; -} - -static yapf_image_t *yapf__load_file(const char *filename, int threads) { - size_t len = 0; - uint8_t *buf = yapf__read_file(filename, &len); - if (!buf) return NULL; - yapf_image_t *img = yapf__load(buf, len, threads); - free(buf); - return img; -} - -yapf_image_t *yapf_load(const char *filename) { - return yapf__load_file(filename, 1); -} - -yapf_image_t *yapf_load_mt(const char *filename, int threads) { - return yapf__load_file(filename, threads); -} - -/* ======================================================================== - * yapf_encode / yapf_save - * ======================================================================== */ - -int yapf_encode(const yapf_image_t *img, void **out_data, size_t *out_size) { - if (!out_data || !out_size) return YAPF_ERR_INVALID; - *out_data = NULL; - *out_size = 0; - if (!img || !img->pixels) return YAPF_ERR_INVALID; - if (img->width == 0 || img->width > YAPF_MAX_DIM) return YAPF_ERR_INVALID; - if (img->height == 0 || img->height > YAPF_MAX_DIM) return YAPF_ERR_INVALID; - if (img->channels < 1 || img->channels > 4) return YAPF_ERR_INVALID; - if (img->mip_levels < 1 || img->mip_levels > YAPF_MAX_MIPS) return YAPF_ERR_INVALID; - - int ch = (int)img->channels; - uint8_t mip_levels = img->mip_levels; - int err = YAPF_OK; - - yapf__out bws[YAPF_MAX_MIPS]; - memset(bws, 0, sizeof(bws)); - - for (uint8_t m = 0; m < mip_levels && err == YAPF_OK; m++) { - uint32_t mw = img->width >> m; if (mw < 1) mw = 1; - uint32_t mh = img->height >> m; if (mh < 1) mh = 1; - - const uint8_t *src = (m == 0) ? img->pixels - : (img->mips ? img->mips[m] : NULL); - if (!src) { err = YAPF_ERR_INVALID; break; } - - if (yapf__reserve(&bws[m], (size_t)mw * mh * (size_t)ch / 2 + 1024) != 0 || - yapf__encode_level(&bws[m], src, mw, mh, ch) != 0) - err = YAPF_ERR_OOM; - } - - /* Offsets are 32-bit: refuse files that would not fit. */ - uint64_t total = YAPF__HDR_LEN + (uint64_t)mip_levels * YAPF__MIP_ENTRY; - for (uint8_t m = 0; m < mip_levels && err == YAPF_OK; m++) { - total += bws[m].len; - if (total > 0xFFFFFFFFull) err = YAPF_ERR_INVALID; - } - - uint8_t *file = NULL; - if (err == YAPF_OK && !(file = (uint8_t *)malloc((size_t)total))) err = YAPF_ERR_OOM; - - if (err == YAPF_OK) { - memset(file, 0, YAPF__HDR_LEN); - memcpy(file, YAPF__MAGIC, 4); - file[4] = YAPF__VERSION; - file[5] = img->channels; - file[6] = img->gpu_format; - file[7] = mip_levels; - file[8] = img->flags; - yapf__w32le(file + 12, img->width); - yapf__w32le(file + 16, img->height); - - size_t pos = YAPF__HDR_LEN + (size_t)mip_levels * YAPF__MIP_ENTRY; - for (uint8_t m = 0; m < mip_levels; m++) { - uint8_t *entry = file + YAPF__HDR_LEN + (size_t)m * YAPF__MIP_ENTRY; - yapf__w32le(entry + 0, (uint32_t)pos); - yapf__w32le(entry + 4, (uint32_t)bws[m].len); - memcpy(file + pos, bws[m].buf, bws[m].len); - pos += bws[m].len; - } - *out_data = file; - *out_size = (size_t)total; - } - - for (uint8_t m = 0; m < mip_levels; m++) free(bws[m].buf); - return err; -} - -void yapf_free_buffer(void *data) { - free(data); -} - -int yapf_save(const char *filename, const yapf_image_t *img) { - if (!filename) return YAPF_ERR_INVALID; - void *data = NULL; - size_t size = 0; - int err = yapf_encode(img, &data, &size); - if (err != YAPF_OK) return err; - - FILE *f = fopen(filename, "wb"); - if (!f) err = YAPF_ERR_IO; - else { - if (fwrite(data, 1, size, f) != size) err = YAPF_ERR_IO; - if (fclose(f) != 0 && err == YAPF_OK) err = YAPF_ERR_IO; - } - yapf_free_buffer(data); - return err; -} - -/* ======================================================================== - * yapf_free - * ======================================================================== */ - -void yapf_free(yapf_image_t *img) { - if (!img) return; - if (img->mips) { - for (uint8_t m = 0; m < img->mip_levels; m++) - free(img->mips[m]); - free(img->mips); - } - free(img); -} - -/* ======================================================================== - * Version 2: textures - * ======================================================================== */ - -#define YAPF__V2_HDR 64 -#define YAPF__V2_SURFACE 16 -#define YAPF__MAX_SURFACES (1u << 24) - -static const struct { uint8_t fmt, bw, bh, bytes; } yapf__block_formats[] = { - { YAPF_GPU_BC1, 4, 4, 8 }, { YAPF_GPU_BC2, 4, 4, 16 }, - { YAPF_GPU_BC3, 4, 4, 16 }, { YAPF_GPU_BC4, 4, 4, 8 }, - { YAPF_GPU_BC4_SNORM, 4, 4, 8 }, { YAPF_GPU_BC5, 4, 4, 16 }, - { YAPF_GPU_BC5_SNORM, 4, 4, 16 }, { YAPF_GPU_BC6H, 4, 4, 16 }, - { YAPF_GPU_BC6H_SF, 4, 4, 16 }, { YAPF_GPU_BC7, 4, 4, 16 }, - { YAPF_GPU_ETC2_RGB8, 4, 4, 8 }, { YAPF_GPU_ETC2_RGB8A1, 4, 4, 8 }, - { YAPF_GPU_ETC2_RGBA8, 4, 4, 16 }, { YAPF_GPU_EAC_R11, 4, 4, 8 }, - { YAPF_GPU_EAC_R11_SNORM, 4, 4, 8 }, { YAPF_GPU_EAC_RG11, 4, 4, 16 }, - { YAPF_GPU_EAC_RG11_SNORM, 4, 4, 16 }, - { YAPF_GPU_ASTC_4x4, 4, 4, 16 }, { YAPF_GPU_ASTC_5x4, 5, 4, 16 }, - { YAPF_GPU_ASTC_5x5, 5, 5, 16 }, { YAPF_GPU_ASTC_6x5, 6, 5, 16 }, - { YAPF_GPU_ASTC_6x6, 6, 6, 16 }, { YAPF_GPU_ASTC_8x5, 8, 5, 16 }, - { YAPF_GPU_ASTC_8x6, 8, 6, 16 }, { YAPF_GPU_ASTC_8x8, 8, 8, 16 }, - { YAPF_GPU_ASTC_10x5, 10, 5, 16 }, { YAPF_GPU_ASTC_10x6, 10, 6, 16 }, - { YAPF_GPU_ASTC_10x8, 10, 8, 16 }, { YAPF_GPU_ASTC_10x10, 10, 10, 16 }, - { YAPF_GPU_ASTC_12x10, 12, 10, 16 }, { YAPF_GPU_ASTC_12x12, 12, 12, 16 } -}; - -int yapf_block_info(uint8_t format, uint32_t *bw, uint32_t *bh, uint32_t *bytes) { - for (size_t i = 0; i < sizeof(yapf__block_formats) / sizeof(yapf__block_formats[0]); i++) - if (yapf__block_formats[i].fmt == format) { - if (bw) *bw = yapf__block_formats[i].bw; - if (bh) *bh = yapf__block_formats[i].bh; - if (bytes) *bytes = yapf__block_formats[i].bytes; - return 1; - } - return 0; -} - -size_t yapf_sample_bytes(uint8_t sample) { - return sample <= YAPF_SAMPLE_F32 ? yapf__sbytes(sample) : 0; -} - -/* Library-side state of a texture: the file tables of an opened file, - * and the marker that the library owns data, notes and frame times. */ -typedef struct { - int version; /* 1 or 2 (0: made by yapf_tex_create) */ - int flags; /* YAPF_LOAD_* */ - uint32_t needs; - uint64_t file_size, front; - uint64_t *off; - uint32_t *size, *tcheck; -} yapf__texi; - -static uint32_t yapf__faces(const yapf_texture_t *t) { - return t->shape == YAPF_SHAPE_CUBE ? 6u : 1u; -} - -uint32_t yapf_tex_faces(const yapf_texture_t *tex) { - return tex ? yapf__faces(tex) : 0; -} - -/* Checks a description; *count receives the number of surfaces. */ -static int yapf__tex_check(const yapf_texture_t *t, uint32_t *count) { - if (!t) return -1; - if (t->channels < 1 || t->channels > 4) return -1; - if (t->sample > YAPF_SAMPLE_F32 || t->payload > YAPF_PAYLOAD_BLOCKS) return -1; - if (t->shape > YAPF_SHAPE_VOLUME) return -1; - if (t->width == 0 || t->width > YAPF_MAX_DIM) return -1; - if (t->height == 0 || t->height > YAPF_MAX_DIM) return -1; - if (t->layers == 0 || t->frames == 0) return -1; - if (t->mip_levels < 1 || t->mip_levels > YAPF_MAX_MIPS) return -1; - if (t->shape == YAPF_SHAPE_VOLUME) { - if (t->depth == 0 || t->depth > YAPF_MAX_DIM || t->layers != 1) return -1; - } else if (t->depth > 1) { - return -1; - } - if (t->shape == YAPF_SHAPE_CUBE && t->width != t->height) return -1; - if (t->payload == YAPF_PAYLOAD_BLOCKS && !yapf_block_info(t->format, NULL, NULL, NULL)) - return -1; - uint64_t n = (uint64_t)t->frames * t->layers * yapf__faces(t) * t->mip_levels; - if (n > YAPF__MAX_SURFACES) return -1; - /* the largest surface must be addressable (32-bit builds) */ - uint64_t texels = (uint64_t)t->width * t->height * (t->shape == YAPF_SHAPE_VOLUME ? t->depth : 1); - if (texels * 4 * 4 > (uint64_t)(SIZE_MAX / 2)) return -1; - if (count) *count = (uint32_t)n; - return 0; -} - -uint32_t yapf_tex_surface_count(const yapf_texture_t *tex) { - uint32_t n = 0; - return yapf__tex_check(tex, &n) == 0 ? n : 0; -} - -uint32_t yapf_tex_surface(const yapf_texture_t *tex, uint32_t frame, - uint32_t layer, uint32_t face, uint32_t mip) -{ - return ((frame * tex->layers + layer) * yapf__faces(tex) + face) * tex->mip_levels + mip; -} - -void yapf_tex_mip_size(const yapf_texture_t *tex, uint32_t mip, - uint32_t *w, uint32_t *h, uint32_t *d) -{ - uint32_t a = tex->width >> mip, b = tex->height >> mip; - uint32_t c = tex->shape == YAPF_SHAPE_VOLUME ? tex->depth >> mip : 1; - if (w) *w = a ? a : 1; - if (h) *h = b ? b : 1; - if (d) *d = c ? c : 1; -} - -/* Blocks across and down for a mip of a block texture. */ -static void yapf__mip_blocks(const yapf_texture_t *t, uint32_t mip, - uint32_t *nbx, uint32_t *nby, uint32_t *S) -{ - uint32_t w, h, bw = 4, bh = 4, bytes = 16; - yapf_tex_mip_size(t, mip, &w, &h, NULL); - yapf_block_info(t->format, &bw, &bh, &bytes); - *nbx = (w + bw - 1) / bw; - *nby = (h + bh - 1) / bh; - *S = bytes; -} - -size_t yapf_tex_surface_bytes(const yapf_texture_t *tex, uint32_t mip) { - uint32_t w, h, d; - yapf_tex_mip_size(tex, mip, &w, &h, &d); - if (tex->payload == YAPF_PAYLOAD_BLOCKS) { - uint32_t nbx, nby, S; - yapf__mip_blocks(tex, mip, &nbx, &nby, &S); - return (size_t)nbx * nby * d * S; - } - return (size_t)w * h * d * tex->channels * yapf__sbytes(tex->sample); -} - -void yapf_tex_tile_grid(const yapf_texture_t *tex, uint32_t mip, - uint32_t *tiles_x, uint32_t *tiles_y) -{ - uint32_t tx, ty; - if (tex->payload == YAPF_PAYLOAD_BLOCKS) { - uint32_t nbx, nby, S; - yapf__mip_blocks(tex, mip, &nbx, &nby, &S); - tx = (nbx + YAPF_BLOCK_TILE - 1) / YAPF_BLOCK_TILE; - ty = (nby + YAPF_BLOCK_TILE - 1) / YAPF_BLOCK_TILE; - } else { - uint32_t w, h; - yapf_tex_mip_size(tex, mip, &w, &h, NULL); - tx = yapf__tiles(w); - ty = yapf__tiles(h); - } - if (tiles_x) *tiles_x = tx; - if (tiles_y) *tiles_y = ty; -} - -static yapf_texture_t *yapf__tex_new(void) { - yapf_texture_t *t = (yapf_texture_t *)calloc(1, sizeof(yapf_texture_t)); - if (!t) return NULL; - t->internal_ = calloc(1, sizeof(yapf__texi)); - if (!t->internal_) { free(t); return NULL; } - return t; -} - -void yapf_tex_free(yapf_texture_t *tex) { - if (!tex) return; - yapf__texi *ti = (yapf__texi *)tex->internal_; - uint32_t n = 0; - if (tex->data) { - n = (uint32_t)((uint64_t)tex->frames * tex->layers * yapf__faces(tex) * tex->mip_levels); - for (uint32_t s = 0; s < n; s++) free(tex->data[s]); - free(tex->data); - } - for (uint32_t i = 0; i < tex->note_count; i++) free(tex->notes[i].data); - free(tex->notes); - free(tex->frame_us); - if (ti) { free(ti->off); free(ti->size); free(ti->tcheck); free(ti); } - free(tex); -} - -/* Copies the description fields (everything up to loop_count). */ -static void yapf__tex_copy_desc(yapf_texture_t *d, const yapf_texture_t *s) { - d->width = s->width; d->height = s->height; - d->depth = s->shape == YAPF_SHAPE_VOLUME ? s->depth : 1; - d->layers = s->layers; d->frames = s->frames; d->shape = s->shape; - d->mip_levels = s->mip_levels; d->payload = s->payload; d->format = s->format; - d->sample = s->sample; d->channels = s->channels; d->flags = s->flags; - memcpy(d->channel_map, s->channel_map, 4); - d->linear_mask = s->linear_mask; d->normal = s->normal; - d->primaries = s->primaries; d->transfer = s->transfer; - d->mip_filter = s->mip_filter; d->alpha_ref = s->alpha_ref; - d->loop_count = s->loop_count; -} - -yapf_texture_t *yapf_tex_create(const yapf_texture_t *desc) { - yapf_texture_t probe; - uint32_t n; - if (!desc) return NULL; - probe = *desc; - if (probe.shape != YAPF_SHAPE_VOLUME && probe.depth == 0) probe.depth = 1; - if (yapf__tex_check(&probe, &n) != 0) return NULL; - yapf_texture_t *t = yapf__tex_new(); - if (!t) return NULL; - yapf__tex_copy_desc(t, &probe); - t->data = (void **)calloc(n, sizeof(void *)); - if (!t->data) { yapf_tex_free(t); return NULL; } - if (t->frames > 1) { - t->frame_us = (uint32_t *)calloc(t->frames, sizeof(uint32_t)); - if (!t->frame_us) { yapf_tex_free(t); return NULL; } - } - for (uint32_t s = 0; s < n; s++) { - t->data[s] = calloc(1, yapf_tex_surface_bytes(t, s % t->mip_levels)); - if (!t->data[s]) { yapf_tex_free(t); return NULL; } - } - return t; -} - -int yapf_tex_add_note(yapf_texture_t *tex, const char tag[4], - const void *data, uint32_t size) -{ - if (!tex || !tex->internal_ || !tag || (size && !data)) return YAPF_ERR_INVALID; - yapf_note_t *n = (yapf_note_t *)realloc(tex->notes, (tex->note_count + 1) * sizeof(yapf_note_t)); - if (!n) return YAPF_ERR_OOM; - tex->notes = n; - n += tex->note_count; - memcpy(n->tag, tag, 4); - n->size = size; - n->data = (uint8_t *)malloc(size ? size : 1); - if (!n->data) return YAPF_ERR_OOM; - if (size) memcpy(n->data, data, size); - tex->note_count++; - return YAPF_OK; -} - -const yapf_note_t *yapf_tex_find_note(const yapf_texture_t *tex, const char tag[4]) { - if (!tex || !tag) return NULL; - for (uint32_t i = 0; i < tex->note_count; i++) - if (memcmp(tex->notes[i].tag, tag, 4) == 0) return &tex->notes[i]; - return NULL; -} - -/* ── Writing ─────────────────────────────────────────────────────────── */ - -typedef struct { - yapf__scratch *sc; - yapf__wscratch *wsc; - yapf__ebook *eb; - yapf__out tmp; -} yapf__enc; - -/* u32 book size, the book, the tile table and the tiles of one surface. - * *checked receives the length the tile-table check covers. */ -static int yapf__encode_tiles(yapf__out *o, yapf__enc *e, const yapf_texture_t *t, - uint32_t mip, const uint8_t *src, int mode, - const yapf__out *book, size_t *checked) -{ - uint32_t w, h, d, tcx, tcy, nbx = 0, nby = 0, S = 0; - int blocks = t->payload == YAPF_PAYLOAD_BLOCKS; - int ch = t->channels, sb = (int)yapf__sbytes(t->sample); - yapf_tex_mip_size(t, mip, &w, &h, &d); - yapf_tex_tile_grid(t, mip, &tcx, &tcy); - if (blocks) yapf__mip_blocks(t, mip, &nbx, &nby, &S); - size_t n = (size_t)tcx * tcy * d, bl = book ? book->len : 0; - size_t slice = blocks ? (size_t)nbx * nby * S : (size_t)w * h * ch * sb; - - o->len = 0; - if (yapf__reserve(o, 4 + bl + n * 8) != 0) return -1; - yapf__w32le(o->buf, (uint32_t)bl); - if (bl) memcpy(o->buf + 4, book->buf, bl); - size_t table = 4 + bl; - memset(o->buf + table, 0, n * 8); - o->len = table + n * 8; - *checked = o->len; - - size_t t_i = 0; - for (uint32_t z = 0; z < d; z++) - for (uint32_t ty = 0; ty < tcy; ty++) - for (uint32_t tx = 0; tx < tcx; tx++, t_i++) { - size_t start = o->len; - int packed = 0, rc; - const uint8_t *sl = src + (size_t)z * slice; - if (blocks) { - uint32_t bx0 = tx * YAPF_BLOCK_TILE, by0 = ty * YAPF_BLOCK_TILE; - uint32_t tbw = nbx - bx0 < YAPF_BLOCK_TILE ? nbx - bx0 : YAPF_BLOCK_TILE; - uint32_t tbh = nby - by0 < YAPF_BLOCK_TILE ? nby - by0 : YAPF_BLOCK_TILE; - rc = yapf__encode_block_tile(o, sl + ((size_t)by0 * nbx + bx0) * S, - (size_t)nbx * S, tbw, tbh, S, mode, e->eb, &packed); - } else { - uint32_t x0 = tx * YAPF_TILE_SIZE, y0 = ty * YAPF_TILE_SIZE; - uint32_t tw = w - x0 < YAPF_TILE_SIZE ? w - x0 : YAPF_TILE_SIZE; - uint32_t th = h - y0 < YAPF_TILE_SIZE ? h - y0 : YAPF_TILE_SIZE; - rc = sb == 1 - ? yapf__encode_tile(o, e->sc, sl, w, x0, y0, tw, th, ch, mode, e->eb, &e->tmp) - : yapf__encode_tile_wide(o, &e->tmp, e->wsc, sl, w, x0, y0, tw, th, ch, - t->sample, mode, e->eb); - } - if (rc != 0) return -1; - size_t sz = o->len - start; - yapf__w32le(o->buf + table + t_i * 8, (uint32_t)sz | ((uint32_t)packed << 31)); - yapf__w32le(o->buf + table + t_i * 8 + 4, yapf_checksum(o->buf + start, sz)); - } - return 0; -} - -/* One surface; with entropy: a counting pass, the book, a coding pass, - * and the book version is kept only if it comes out smaller. */ -static int yapf__encode_surface(yapf__out *o, yapf__enc *e, const yapf_texture_t *t, - uint32_t mip, const uint8_t *src, int entropy, - size_t *checked, int *used_entropy) -{ - if (!entropy || !e->eb) - return yapf__encode_tiles(o, e, t, mip, src, YAPF__ENC_PLAIN, NULL, checked); - memset(e->eb->freq, 0, sizeof(e->eb->freq)); - if (yapf__encode_tiles(o, e, t, mip, src, YAPF__ENC_STATS, NULL, checked) != 0) return -1; - yapf__out book = { NULL, 0, 0 }, alt = { NULL, 0, 0 }; - size_t alt_checked = 0; - int rc = yapf__book_write(e->eb, &book); - if (rc == 0) rc = yapf__encode_tiles(&alt, e, t, mip, src, YAPF__ENC_BOOK, &book, &alt_checked); - if (rc == 0 && alt.len < o->len) { - yapf__out tmp = *o; - *o = alt; - alt = tmp; - *checked = alt_checked; - *used_entropy = 1; - } - free(book.buf); - free(alt.buf); - return rc < 0 ? -1 : 0; -} - -int yapf_tex_encode(const yapf_texture_t *tex, int flags, void **out_data, size_t *out_size) { - if (!out_data || !out_size) return YAPF_ERR_INVALID; - *out_data = NULL; - *out_size = 0; - uint32_t S; - yapf_texture_t t; - if (!tex) return YAPF_ERR_INVALID; - t = *tex; - if (t.shape != YAPF_SHAPE_VOLUME && t.depth == 0) t.depth = 1; - if (yapf__tex_check(&t, &S) != 0 || !t.data) return YAPF_ERR_INVALID; - for (uint32_t s = 0; s < S; s++) if (!t.data[s]) return YAPF_ERR_INVALID; - if (t.frames > 1 && !t.frame_us) return YAPF_ERR_INVALID; - uint64_t notes = 0; - for (uint32_t i = 0; i < t.note_count; i++) { - if (t.notes[i].size && !t.notes[i].data) return YAPF_ERR_INVALID; - notes += 8 + (uint64_t)t.notes[i].size; - } - if (notes > 0xFFFFFFFFull) return YAPF_ERR_INVALID; - - int err = YAPF_OK, used_ent = 0; - int entropy = (flags & YAPF_ENC_ENTROPY) != 0; - yapf__out *bufs = (yapf__out *)calloc(S, sizeof(yapf__out)); - uint32_t *tchk = (uint32_t *)calloc(S, sizeof(uint32_t)); - yapf__enc e; - memset(&e, 0, sizeof(e)); - if (!bufs || !tchk) err = YAPF_ERR_OOM; - if (err == YAPF_OK && t.payload == YAPF_PAYLOAD_PIXELS) { - if (t.sample == YAPF_SAMPLE_U8) e.sc = (yapf__scratch *)malloc(sizeof(yapf__scratch)); - else e.wsc = (yapf__wscratch *)malloc(sizeof(yapf__wscratch)); - if (!e.sc && !e.wsc) err = YAPF_ERR_OOM; - } - if (err == YAPF_OK && entropy && !(e.eb = (yapf__ebook *)malloc(sizeof(yapf__ebook)))) - err = YAPF_ERR_OOM; - for (uint32_t s = 0; s < S && err == YAPF_OK; s++) { - size_t n = 0; - if (yapf__encode_surface(&bufs[s], &e, &t, s % t.mip_levels, - (const uint8_t *)t.data[s], entropy, &n, &used_ent) != 0) - err = YAPF_ERR_OOM; - else - tchk[s] = yapf_checksum(bufs[s].buf, n); - } - - uint64_t front = YAPF__V2_HDR + (uint64_t)S * YAPF__V2_SURFACE - + (t.frames > 1 ? 4ull * t.frames : 0) + notes; - uint64_t total = front; - for (uint32_t s = 0; s < S && err == YAPF_OK; s++) total += bufs[s].len; - if (err == YAPF_OK && total > (uint64_t)SIZE_MAX) err = YAPF_ERR_INVALID; - - uint8_t *file = NULL; - if (err == YAPF_OK && !(file = (uint8_t *)malloc((size_t)total))) err = YAPF_ERR_OOM; - if (err == YAPF_OK) { - uint32_t needs = 0; - if (t.payload == YAPF_PAYLOAD_PIXELS && t.sample != YAPF_SAMPLE_U8) needs |= YAPF_NEED_WIDE; - if (t.payload == YAPF_PAYLOAD_BLOCKS) needs |= YAPF_NEED_BLOCKS; - if (used_ent) needs |= YAPF_NEED_ENTROPY; - if (t.shape != YAPF_SHAPE_2D || t.layers > 1) needs |= YAPF_NEED_LAYOUT; - if (t.frames > 1) needs |= YAPF_NEED_FRAMES; - - uint8_t *h = file; - memset(h, 0, YAPF__V2_HDR); - memcpy(h, YAPF__MAGIC, 4); - h[4] = 2; - h[5] = t.channels; h[6] = t.format; h[7] = t.mip_levels; - h[8] = t.flags; h[9] = t.payload; h[10] = t.sample; h[11] = t.shape; - yapf__w32le(h + 0x0C, t.width); - yapf__w32le(h + 0x10, t.height); - yapf__w32le(h + 0x14, t.depth); - yapf__w16le(h + 0x18, t.layers); - yapf__w16le(h + 0x1A, t.frames); - yapf__w32le(h + 0x1C, needs); - memcpy(h + 0x20, t.channel_map, 4); - h[0x24] = t.linear_mask; h[0x25] = t.normal; - h[0x26] = t.primaries; h[0x27] = t.transfer; - h[0x28] = t.mip_filter; h[0x29] = t.alpha_ref; - yapf__w16le(h + 0x2A, t.loop_count); - yapf__w32le(h + 0x2C, (uint32_t)notes); - yapf__w64le(h + 0x30, total); - - /* surface data, smallest mips first */ - uint64_t pos = front; - for (uint32_t m = t.mip_levels; m-- > 0; ) - for (uint32_t s = m; s < S; s += t.mip_levels) { - uint8_t *ent = file + YAPF__V2_HDR + (size_t)s * YAPF__V2_SURFACE; - yapf__w64le(ent, pos); - yapf__w32le(ent + 8, (uint32_t)bufs[s].len); - yapf__w32le(ent + 12, tchk[s]); - memcpy(file + pos, bufs[s].buf, bufs[s].len); - pos += bufs[s].len; - } - uint8_t *q = file + YAPF__V2_HDR + (size_t)S * YAPF__V2_SURFACE; - if (t.frames > 1) - for (uint32_t f = 0; f < t.frames; f++, q += 4) yapf__w32le(q, t.frame_us[f]); - for (uint32_t i = 0; i < t.note_count; i++) { - memcpy(q, t.notes[i].tag, 4); - yapf__w32le(q + 4, t.notes[i].size); - if (t.notes[i].size) memcpy(q + 8, t.notes[i].data, t.notes[i].size); - q += 8 + t.notes[i].size; - } - yapf__w32le(h + 0x38, yapf_checksum(file + YAPF__V2_HDR, (size_t)(front - YAPF__V2_HDR))); - yapf__w32le(h + 0x3C, yapf_checksum(file, 0x3C)); - *out_data = file; - *out_size = (size_t)total; - } - - if (bufs) for (uint32_t s = 0; s < S; s++) free(bufs[s].buf); - free(bufs); - free(tchk); - free(e.sc); - free(e.wsc); - free(e.eb); - free(e.tmp.buf); - return err; -} - -int yapf_tex_save(const char *filename, const yapf_texture_t *tex, int flags) { - if (!filename) return YAPF_ERR_INVALID; - void *data = NULL; - size_t size = 0; - int err = yapf_tex_encode(tex, flags, &data, &size); - if (err != YAPF_OK) return err; - FILE *f = fopen(filename, "wb"); - if (!f) err = YAPF_ERR_IO; - else { - if (fwrite(data, 1, size, f) != size) err = YAPF_ERR_IO; - if (fclose(f) != 0 && err == YAPF_OK) err = YAPF_ERR_IO; - } - yapf_free_buffer(data); - return err; -} - -/* ── Reading ─────────────────────────────────────────────────────────── */ - -static yapf_texture_t *yapf__open_fail(yapf_texture_t *t, int *err, int code) { - if (err) *err = code; - yapf_tex_free(t); - return NULL; -} - -/* Tiles in surface s (all slices). */ -static uint64_t yapf__surface_tiles(const yapf_texture_t *t, uint32_t mip) { - uint32_t tcx, tcy, d; - yapf_tex_tile_grid(t, mip, &tcx, &tcy); - yapf_tex_mip_size(t, mip, NULL, NULL, &d); - return (uint64_t)tcx * tcy * d; -} - -yapf_texture_t *yapf_tex_open(const void *buffer, size_t avail, int flags, int *err) { - const uint8_t *b = (const uint8_t *)buffer; - if (err) *err = YAPF_OK; - if (!b) return yapf__open_fail(NULL, err, YAPF_ERR_INVALID); - if (avail < 5) return yapf__open_fail(NULL, err, YAPF_ERR_TRUNCATED); - if (memcmp(b, YAPF__MAGIC, 4) != 0) return yapf__open_fail(NULL, err, YAPF_ERR_CORRUPT); - if (b[4] != 1 && b[4] != 2) return yapf__open_fail(NULL, err, YAPF_ERR_UNSUPPORTED); - - yapf_texture_t *t = yapf__tex_new(); - if (!t) return yapf__open_fail(NULL, err, YAPF_ERR_OOM); - yapf__texi *ti = (yapf__texi *)t->internal_; - ti->flags = flags; - uint32_t S; - - if (b[4] == 1) { - if (avail < YAPF__HDR_LEN) return yapf__open_fail(t, err, YAPF_ERR_TRUNCATED); - t->channels = b[5]; t->format = b[6]; t->mip_levels = b[7]; t->flags = b[8]; - t->width = yapf__r32le(b + 12); t->height = yapf__r32le(b + 16); - t->depth = 1; t->layers = 1; t->frames = 1; - ti->version = 1; - if (yapf__tex_check(t, &S) != 0) return yapf__open_fail(t, err, YAPF_ERR_CORRUPT); - ti->front = YAPF__HDR_LEN + (uint64_t)S * YAPF__MIP_ENTRY; - ti->file_size = avail; - if (avail < ti->front) return yapf__open_fail(t, err, YAPF_ERR_TRUNCATED); - } else { - if (avail < YAPF__V2_HDR) return yapf__open_fail(t, err, YAPF_ERR_TRUNCATED); - if (!(flags & YAPF_LOAD_TRUST) && yapf_checksum(b, 0x3C) != yapf__r32le(b + 0x3C)) - return yapf__open_fail(t, err, YAPF_ERR_CHECKSUM); - t->channels = b[5]; t->format = b[6]; t->mip_levels = b[7]; t->flags = b[8]; - t->payload = b[9]; t->sample = b[10]; t->shape = b[11]; - t->width = yapf__r32le(b + 0x0C); - t->height = yapf__r32le(b + 0x10); - t->depth = yapf__r32le(b + 0x14); - t->layers = yapf__r16le(b + 0x18); - t->frames = yapf__r16le(b + 0x1A); - ti->needs = yapf__r32le(b + 0x1C); - memcpy(t->channel_map, b + 0x20, 4); - t->linear_mask = b[0x24]; t->normal = b[0x25]; - t->primaries = b[0x26]; t->transfer = b[0x27]; - t->mip_filter = b[0x28]; t->alpha_ref = b[0x29]; - t->loop_count = yapf__r16le(b + 0x2A); - uint32_t notes = yapf__r32le(b + 0x2C); - ti->file_size = yapf__r64le(b + 0x30); - ti->version = 2; - - if (ti->needs & ~(uint32_t)YAPF_NEED_ALL) return yapf__open_fail(t, err, YAPF_ERR_UNSUPPORTED); - if (yapf__tex_check(t, &S) != 0) return yapf__open_fail(t, err, YAPF_ERR_CORRUPT); - /* every feature in use must be announced */ - if ((t->payload == YAPF_PAYLOAD_PIXELS && t->sample != YAPF_SAMPLE_U8 && !(ti->needs & YAPF_NEED_WIDE)) || - (t->payload == YAPF_PAYLOAD_BLOCKS && !(ti->needs & YAPF_NEED_BLOCKS)) || - ((t->shape != YAPF_SHAPE_2D || t->layers > 1) && !(ti->needs & YAPF_NEED_LAYOUT)) || - (t->frames > 1 && !(ti->needs & YAPF_NEED_FRAMES))) - return yapf__open_fail(t, err, YAPF_ERR_CORRUPT); - - ti->front = YAPF__V2_HDR + (uint64_t)S * YAPF__V2_SURFACE - + (t->frames > 1 ? 4ull * t->frames : 0) + notes; - if (ti->front > ti->file_size) return yapf__open_fail(t, err, YAPF_ERR_CORRUPT); - if (avail < ti->front) return yapf__open_fail(t, err, YAPF_ERR_TRUNCATED); - if (!(flags & YAPF_LOAD_TRUST) && - yapf_checksum(b + YAPF__V2_HDR, (size_t)(ti->front - YAPF__V2_HDR)) != yapf__r32le(b + 0x38)) - return yapf__open_fail(t, err, YAPF_ERR_CHECKSUM); - - const uint8_t *q = b + YAPF__V2_HDR + (size_t)S * YAPF__V2_SURFACE; - if (t->frames > 1) { - t->frame_us = (uint32_t *)malloc(t->frames * sizeof(uint32_t)); - if (!t->frame_us) return yapf__open_fail(t, err, YAPF_ERR_OOM); - for (uint32_t f = 0; f < t->frames; f++, q += 4) t->frame_us[f] = yapf__r32le(q); - } - const uint8_t *qe = q + notes; - while (q < qe) { - if (qe - q < 8) return yapf__open_fail(t, err, YAPF_ERR_CORRUPT); - uint32_t sz = yapf__r32le(q + 4); - if ((size_t)(qe - q - 8) < sz) return yapf__open_fail(t, err, YAPF_ERR_CORRUPT); - if (yapf_tex_add_note(t, (const char *)q, q + 8, sz) != YAPF_OK) - return yapf__open_fail(t, err, YAPF_ERR_OOM); - q += 8 + sz; - } - } - - t->data = (void **)calloc(S, sizeof(void *)); - ti->off = (uint64_t *)calloc(S, sizeof(uint64_t)); - ti->size = (uint32_t *)calloc(S, sizeof(uint32_t)); - ti->tcheck = (uint32_t *)calloc(S, sizeof(uint32_t)); - if (!t->data || !ti->off || !ti->size || !ti->tcheck) - return yapf__open_fail(t, err, YAPF_ERR_OOM); - for (uint32_t s = 0; s < S; s++) { - uint32_t mip = s % t->mip_levels; - if (ti->version == 1) { - const uint8_t *e = b + YAPF__HDR_LEN + (size_t)s * YAPF__MIP_ENTRY; - ti->off[s] = yapf__r32le(e); - ti->size[s] = yapf__r32le(e + 4); - } else { - const uint8_t *e = b + YAPF__V2_HDR + (size_t)s * YAPF__V2_SURFACE; - ti->off[s] = yapf__r64le(e); - ti->size[s] = yapf__r32le(e + 8); - ti->tcheck[s] = yapf__r32le(e + 12); - if (ti->off[s] > ti->file_size || ti->size[s] > ti->file_size - ti->off[s]) - return yapf__open_fail(t, err, YAPF_ERR_CORRUPT); - if (ti->size[s] < 4 || (ti->size[s] - 4) / 8 < yapf__surface_tiles(t, mip)) - return yapf__open_fail(t, err, YAPF_ERR_CORRUPT); - } - if (ti->off[s] < ti->front) return yapf__open_fail(t, err, YAPF_ERR_CORRUPT); - } - return t; -} - -uint64_t yapf_tex_stream_bytes(const yapf_texture_t *tex, uint32_t first_mip) { - if (!tex || !tex->internal_) return 0; - const yapf__texi *ti = (const yapf__texi *)tex->internal_; - if (!ti->off) return 0; - uint32_t S = yapf_tex_surface_count(tex); - uint64_t end = ti->front; - for (uint32_t s = 0; s < S; s++) - if (s % tex->mip_levels >= first_mip && ti->off[s] + ti->size[s] > end) - end = ti->off[s] + ti->size[s]; - return end; -} - -/* Prepares the level for surface s; alloc: allocate tex->data[s]. */ -static int yapf__surface_level(yapf_texture_t *t, const uint8_t *buf, size_t avail, - uint32_t s, yapf__level *lv, int alloc) -{ - const yapf__texi *ti = (const yapf__texi *)t->internal_; - uint32_t mip = s % t->mip_levels, w, h, d; - memset(lv, 0, sizeof(*lv)); - if (ti->off[s] + ti->size[s] > avail) return YAPF_ERR_TRUNCATED; - uint64_t tiles = yapf__surface_tiles(t, mip); - const uint8_t *sd = buf + ti->off[s]; - size_t ssz = ti->size[s], pre = 0; - if (ti->version == 2) { - /* u32 book size, book, tile table: covered by the tile-table check */ - uint32_t bl = yapf__r32le(sd); - if (ssz < 4 || bl > ssz - 4 || (ssz - 4 - bl) / 8 < tiles) return YAPF_ERR_CORRUPT; - pre = 4 + (size_t)bl; - if (!(ti->flags & YAPF_LOAD_TRUST) && yapf_checksum(sd, pre + (size_t)tiles * 8) != ti->tcheck[s]) - return YAPF_ERR_CHECKSUM; - if (bl) { - if (!(ti->needs & YAPF_NEED_ENTROPY)) return YAPF_ERR_CORRUPT; - lv->book = (yapf__dbook *)malloc(sizeof(yapf__dbook)); - if (!lv->book) return YAPF_ERR_OOM; - if (yapf__book_read(sd + 4, bl, lv->book) != 0) return YAPF_ERR_CORRUPT; - } - } - if (alloc && !t->data[s]) { - t->data[s] = malloc(yapf_tex_surface_bytes(t, mip)); - if (!t->data[s]) return YAPF_ERR_OOM; - } - yapf_tex_mip_size(t, mip, &w, &h, &d); - lv->data = sd + pre; - lv->pixels = (uint8_t *)t->data[s]; - lv->mw = w; lv->mh = h; lv->md = d; - lv->ch = t->channels; - lv->sample = t->sample; - lv->v2 = ti->version == 2; - lv->verify = !(ti->flags & YAPF_LOAD_TRUST); -#if YAPF__SIMD - lv->simd = yapf__simd_available(); -#endif - yapf_tex_tile_grid(t, mip, &lv->tcx, &lv->tcy); - if (t->payload == YAPF_PAYLOAD_BLOCKS) { - uint32_t S; - yapf__mip_blocks(t, mip, &lv->nbx, &lv->nby, &S); - lv->blk = S; - } - if (yapf__level_table(lv, ssz - pre) != 0) return YAPF_ERR_CORRUPT; - return YAPF_OK; -} - -static int yapf__map_rc(int rc) { - return rc == 0 ? YAPF_OK : rc == YAPF_ERR_CHECKSUM || rc == YAPF_ERR_OOM ? rc : YAPF_ERR_CORRUPT; -} - -int yapf_tex_decode_surface(yapf_texture_t *tex, const void *buffer, size_t avail, - uint32_t surface, int threads) -{ - if (!tex || !tex->internal_ || !buffer) return YAPF_ERR_INVALID; - if (!((yapf__texi *)tex->internal_)->off) return YAPF_ERR_INVALID; - if (surface >= yapf_tex_surface_count(tex)) return YAPF_ERR_INVALID; - yapf__level lv; - int rc = yapf__surface_level(tex, (const uint8_t *)buffer, avail, surface, &lv, 1); - if (rc == YAPF_OK) rc = yapf__map_rc(yapf__decode_levels(&lv, 1, threads)); - yapf__level_free(&lv); - return rc; -} - -int yapf_tex_decode_tile(const yapf_texture_t *tex, const void *buffer, size_t avail, - uint32_t surface, uint32_t tx, uint32_t ty, uint32_t slice, - void *out, size_t stride, - uint32_t *x, uint32_t *y, uint32_t *w, uint32_t *h) -{ - if (!tex || !tex->internal_ || !buffer || !out) return YAPF_ERR_INVALID; - if (!((const yapf__texi *)tex->internal_)->off) return YAPF_ERR_INVALID; - if (surface >= yapf_tex_surface_count(tex)) return YAPF_ERR_INVALID; - uint32_t mip = surface % tex->mip_levels, mw, mh, md, tcx, tcy; - yapf_tex_mip_size(tex, mip, &mw, &mh, &md); - yapf_tex_tile_grid(tex, mip, &tcx, &tcy); - if (tx >= tcx || ty >= tcy || slice >= md) return YAPF_ERR_INVALID; - - /* unit: bytes per texel (or block); the row must hold the tile */ - size_t unit; - uint32_t span, bw = 1, bh = 1, across; - if (tex->payload == YAPF_PAYLOAD_BLOCKS) { - uint32_t bytes = 16, nbx, nby, S; - yapf_block_info(tex->format, &bw, &bh, &bytes); - yapf__mip_blocks(tex, mip, &nbx, &nby, &S); - unit = bytes; - span = YAPF_BLOCK_TILE; - across = nbx; - } else { - unit = (size_t)tex->channels * yapf__sbytes(tex->sample); - span = YAPF_TILE_SIZE; - across = mw; - } - { - uint32_t need = across - tx * span < span ? across - tx * span : span; - if (stride % unit != 0 || stride / unit < need) return YAPF_ERR_INVALID; - } - yapf__level lv; - int rc = yapf__surface_level((yapf_texture_t *)tex, (const uint8_t *)buffer, avail, - surface, &lv, 0); - if (rc == YAPF_OK) { - yapf__wdec *wsc = NULL; - if (!lv.blk && lv.sample != YAPF_SAMPLE_U8) { - wsc = (yapf__wdec *)malloc(sizeof(yapf__wdec)); - if (!wsc) rc = YAPF_ERR_OOM; - } - if (rc == YAPF_OK) - rc = yapf__map_rc(yapf__level_tile(&lv, tx, slice * lv.tcy + ty, wsc, - (uint8_t *)out, stride / unit)); - free(wsc); - } - yapf__level_free(&lv); - if (rc == YAPF_OK) { - uint32_t px = tx * span * bw, py = ty * span * bh; - uint32_t pw = span * bw, ph = span * bh; - if (x) *x = px; - if (y) *y = py; - if (w) *w = mw - px < pw ? mw - px : pw; - if (h) *h = mh - py < ph ? mh - py : ph; - } - return rc; -} - -yapf_texture_t *yapf_tex_load_memory(const void *buffer, size_t size, - int flags, int threads, int *err) -{ - yapf_texture_t *t = yapf_tex_open(buffer, size, flags, err); - if (!t) return NULL; - yapf__texi *ti = (yapf__texi *)t->internal_; - if (ti->version == 2 && size < ti->file_size) - return yapf__open_fail(t, err, YAPF_ERR_TRUNCATED); - uint32_t S = yapf_tex_surface_count(t); - yapf__level *lv = (yapf__level *)calloc(S, sizeof(yapf__level)); - int rc = lv ? YAPF_OK : YAPF_ERR_OOM; - for (uint32_t s = 0; s < S && rc == YAPF_OK; s++) - rc = yapf__surface_level(t, (const uint8_t *)buffer, size, s, &lv[s], 1); - if (rc == YAPF_ERR_TRUNCATED) rc = YAPF_ERR_CORRUPT; - if (rc == YAPF_OK) rc = yapf__map_rc(yapf__decode_levels(lv, (int)S, threads)); - if (lv) for (uint32_t s = 0; s < S; s++) yapf__level_free(&lv[s]); - free(lv); - if (rc != YAPF_OK) return yapf__open_fail(t, err, rc); - return t; -} - -yapf_texture_t *yapf_tex_load(const char *filename, int flags, int threads, int *err) { - size_t len = 0; - uint8_t *buf = yapf__read_file(filename, &len); - if (!buf) { if (err) *err = YAPF_ERR_IO; return NULL; } - yapf_texture_t *t = yapf_tex_load_memory(buf, len, flags, threads, err); - free(buf); - return t; -} - -/* v1 API on a version 2 file: frame 0, layer 0, face 0 of an 8-bit - * pixel texture (not volumes), with its mips. */ -static yapf_image_t *yapf__load_v2_image(const uint8_t *buf, size_t size, int threads) { - yapf_texture_t *t = yapf_tex_open(buf, size, 0, NULL); - if (!t) return NULL; - yapf__texi *ti = (yapf__texi *)t->internal_; - if (t->payload != YAPF_PAYLOAD_PIXELS || t->sample != YAPF_SAMPLE_U8 || - t->shape == YAPF_SHAPE_VOLUME || size < ti->file_size) { - yapf_tex_free(t); - return NULL; - } - yapf__level lv[YAPF_MAX_MIPS]; - int rc = YAPF_OK; - memset(lv, 0, sizeof(lv)); - for (uint32_t m = 0; m < t->mip_levels && rc == YAPF_OK; m++) - rc = yapf__surface_level(t, buf, size, m, &lv[m], 1); - if (rc == YAPF_OK) rc = yapf__decode_levels(lv, t->mip_levels, threads); - for (uint32_t m = 0; m < YAPF_MAX_MIPS; m++) yapf__level_free(&lv[m]); - - yapf_image_t *img = NULL; - if (rc == 0) img = (yapf_image_t *)calloc(1, sizeof(yapf_image_t)); - if (img) img->mips = (uint8_t **)calloc(t->mip_levels, sizeof(uint8_t *)); - if (img && img->mips) { - img->width = t->width; img->height = t->height; img->channels = t->channels; - img->gpu_format = t->format; img->flags = t->flags; img->mip_levels = t->mip_levels; - for (uint32_t m = 0; m < t->mip_levels; m++) { - img->mips[m] = (uint8_t *)t->data[m]; /* surface m: frame 0, layer 0, face 0 */ - t->data[m] = NULL; - } - img->pixels = img->mips[0]; - } else if (img) { - free(img); - img = NULL; - } - yapf_tex_free(t); - return img; -} - -/* ======================================================================== - * Half floats - * ======================================================================== */ - -uint16_t yapf_float_to_half(float f) { - uint32_t x; - memcpy(&x, &f, 4); - uint32_t sign = (x >> 16) & 0x8000u, e = (x >> 23) & 0xFFu, m = x & 0x7FFFFFu; - if (e == 255) return (uint16_t)(sign | 0x7C00u | (m ? 0x200u | (m >> 13) : 0)); - int32_t ee = (int32_t)e - 127 + 15; - if (ee >= 31) return (uint16_t)(sign | 0x7C00u); - if (ee <= 0) { /* subnormal or zero */ - if (ee < -10) return (uint16_t)sign; - m |= 0x800000u; - int shift = 14 - ee; - uint32_t hm = m >> shift, rem = m & ((1u << shift) - 1), halfway = 1u << (shift - 1); - if (rem > halfway || (rem == halfway && (hm & 1))) hm++; - return (uint16_t)(sign | hm); - } - uint32_t h = sign | ((uint32_t)ee << 10) | (m >> 13), rem = m & 0x1FFFu; - if (rem > 0x1000u || (rem == 0x1000u && (h & 1))) h++; /* carries into the exponent */ - return (uint16_t)h; -} - -float yapf_half_to_float(uint16_t h) { - uint32_t s = (uint32_t)(h & 0x8000u) << 16, e = (h >> 10) & 31u, m = h & 0x3FFu, x; - if (e == 0) { - if (!m) x = s; - else { - e = 113; - while (!(m & 0x400u)) { m <<= 1; e--; } - x = s | (e << 23) | ((m & 0x3FFu) << 13); - } - } else if (e == 31) { - x = s | 0x7F800000u | (m << 13); - } else { - x = s | ((e + 112) << 23) | (m << 13); - } - float f; - memcpy(&f, &x, 4); - return f; -} - -/* ======================================================================== - * GPU block codecs (BC1–BC7) - * ======================================================================== */ - -/* BC6H / BC7 partitions. 2 subsets: bit i set = pixel i in subset 1. - * 3 subsets: 2 bits per pixel. Anchors: the pixel of each extra subset - * whose index drops its top bit. */ -static const uint16_t yapf__part2[64] = { - 0xCCCC, 0x8888, 0xEEEE, 0xECC8, 0xC880, 0xFEEC, 0xFEC8, 0xEC80, - 0xC800, 0xFFEC, 0xFE80, 0xE800, 0xFFE8, 0xFF00, 0xFFF0, 0xF000, - 0xF710, 0x008E, 0x7100, 0x08CE, 0x008C, 0x7310, 0x3100, 0x8CCE, - 0x088C, 0x3110, 0x6666, 0x366C, 0x17E8, 0x0FF0, 0x718E, 0x399C, - 0xAAAA, 0xF0F0, 0x5A5A, 0x33CC, 0x3C3C, 0x55AA, 0x9696, 0xA55A, - 0x73CE, 0x13C8, 0x324C, 0x3BDC, 0x6996, 0xC33C, 0x9966, 0x0660, - 0x0272, 0x04E4, 0x4E40, 0x2720, 0xC936, 0x936C, 0x39C6, 0x639C, - 0x9336, 0x9CC6, 0x817E, 0xE718, 0xCCF0, 0x0FCC, 0x7744, 0xEE22 -}; - -static const uint32_t yapf__part3[64] = { - 0xAA685050, 0x6A5A5040, 0x5A5A4200, 0x5450A0A8, 0xA5A50000, 0xA0A05050, 0x5555A0A0, 0x5A5A5050, - 0xAA550000, 0xAA555500, 0xAAAA5500, 0x90909090, 0x94949494, 0xA4A4A4A4, 0xA9A59450, 0x2A0A4250, - 0xA5945040, 0x0A425054, 0xA5A5A500, 0x55A0A0A0, 0xA8A85454, 0x6A6A4040, 0xA4A45000, 0x1A1A0500, - 0x0050A4A4, 0xAAA59090, 0x14696914, 0x69691400, 0xA08585A0, 0xAA821414, 0x50A4A450, 0x6A5A0200, - 0xA9A58000, 0x5090A0A8, 0xA8A09050, 0x24242424, 0x00AA5500, 0x24924924, 0x24499224, 0x50A50A50, - 0x500AA550, 0xAAAA4444, 0x66660000, 0xA5A0A5A0, 0x50A050A0, 0x69286928, 0x44AAAA44, 0x66666600, - 0xAA444444, 0x54A854A8, 0x95809580, 0x96969600, 0xA85454A8, 0x80959580, 0xAA141414, 0x96960000, - 0xAAAA1414, 0xA05050A0, 0xA0A5A5A0, 0x96000000, 0x40804080, 0xA9A8A9A8, 0xAAAAAA44, 0x2A4A5254 -}; - -static const uint8_t yapf__anchor2[64] = { - 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, - 15, 2, 8, 2, 2, 8, 8, 15, 2, 8, 2, 2, 8, 8, 2, 2, - 15, 15, 6, 8, 2, 8, 15, 15, 2, 8, 2, 2, 2, 15, 15, 6, - 6, 2, 6, 8, 15, 15, 2, 2, 15, 15, 15, 15, 15, 2, 2, 15 -}; -static const uint8_t yapf__anchor3a[64] = { - 3, 3, 15, 15, 8, 3, 15, 15, 8, 8, 6, 6, 6, 5, 3, 3, - 3, 3, 8, 15, 3, 3, 6, 10, 5, 8, 8, 6, 8, 5, 15, 15, - 8, 15, 3, 5, 6, 10, 8, 15, 15, 3, 15, 5, 15, 15, 15, 15, - 3, 15, 5, 5, 5, 8, 5, 10, 5, 10, 8, 13, 15, 12, 3, 3 -}; -static const uint8_t yapf__anchor3b[64] = { - 15, 8, 8, 3, 15, 15, 3, 8, 15, 15, 15, 15, 15, 15, 15, 8, - 15, 8, 15, 3, 15, 8, 15, 8, 3, 15, 6, 10, 15, 15, 10, 8, - 15, 3, 15, 10, 10, 8, 9, 10, 6, 15, 8, 15, 3, 6, 6, 8, - 15, 3, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 3, 15, 15, 8 -}; - -static const uint8_t yapf__w2[4] = { 0, 21, 43, 64 }; -static const uint8_t yapf__w3[8] = { 0, 9, 18, 27, 37, 46, 55, 64 }; -static const uint8_t yapf__w4[16] = { 0, 4, 9, 13, 17, 21, 26, 30, 34, 38, 43, 47, 51, 55, 60, 64 }; - -static const uint8_t *yapf__weights(int bits) { - return bits == 2 ? yapf__w2 : bits == 3 ? yapf__w3 : yapf__w4; -} - -static int yapf__bc_interp(int a, int b, int w) { - return (a * (64 - w) + b * w + 32) >> 6; -} - -/* 128-bit little-endian bit reader / writer */ -static uint32_t yapf__getbits(const uint8_t *b, unsigned *pos, unsigned n) { - uint32_t v = 0; - for (unsigned i = 0; i < n; i++, (*pos)++) - v |= (uint32_t)((b[*pos >> 3] >> (*pos & 7)) & 1u) << i; - return v; -} - -static void yapf__putbits(uint8_t *b, unsigned *pos, uint32_t v, unsigned n) { - for (unsigned i = 0; i < n; i++, (*pos)++) - if ((v >> i) & 1u) b[*pos >> 3] |= (uint8_t)(1u << (*pos & 7)); -} - -/* ── BC1–BC5 ─────────────────────────────────────────────────────────── */ - -static void yapf__565(uint16_t c, int *rgb) { - int r = (c >> 11) & 31, g = (c >> 5) & 63, b = c & 31; - rgb[0] = (r << 3) | (r >> 2); - rgb[1] = (g << 2) | (g >> 4); - rgb[2] = (b << 3) | (b >> 2); -} - -/* BC1 colour block; four_only: BC2 / BC3 always use four colours. */ -static void yapf__bc1_block(const uint8_t *s, uint8_t out[16][4], int four_only) { - uint16_t c0 = yapf__r16le(s), c1 = yapf__r16le(s + 2); - uint32_t idx = yapf__r32le(s + 4); - int pal[4][4]; - yapf__565(c0, pal[0]); - yapf__565(c1, pal[1]); - pal[0][3] = pal[1][3] = pal[2][3] = pal[3][3] = 255; - for (int k = 0; k < 3; k++) { - if (c0 > c1 || four_only) { - pal[2][k] = (2 * pal[0][k] + pal[1][k] + 1) / 3; - pal[3][k] = (pal[0][k] + 2 * pal[1][k] + 1) / 3; - } else { - pal[2][k] = (pal[0][k] + pal[1][k] + 1) / 2; - pal[3][k] = 0; - } - } - if (!(c0 > c1 || four_only)) pal[3][3] = 0; - for (int i = 0; i < 16; i++) - for (int k = 0; k < 4; k++) out[i][k] = (uint8_t)pal[(idx >> (2 * i)) & 3][k]; -} - -/* BC4 channel block into out[i][ch]; snorm values are shifted by +128. */ -static void yapf__bc4_block(const uint8_t *s, uint8_t out[16][4], int ch, int snorm) { - int pal[8]; - uint64_t idx = 0; - for (int k = 0; k < 6; k++) idx |= (uint64_t)s[2 + k] << (8 * k); - if (!snorm) { - int r0 = s[0], r1 = s[1]; - pal[0] = r0; pal[1] = r1; - if (r0 > r1) for (int i = 2; i < 8; i++) pal[i] = ((8 - i) * r0 + (i - 1) * r1 + 3) / 7; - else { - for (int i = 2; i < 6; i++) pal[i] = ((6 - i) * r0 + (i - 1) * r1 + 2) / 5; - pal[6] = 0; pal[7] = 255; - } - } else { - int r0 = (int8_t)s[0], r1 = (int8_t)s[1]; - if (r0 < -127) r0 = -127; - if (r1 < -127) r1 = -127; - pal[0] = r0; pal[1] = r1; - if (r0 > r1) { - for (int i = 2; i < 8; i++) { - int v = (8 - i) * r0 + (i - 1) * r1; - pal[i] = v >= 0 ? (v + 3) / 7 : -((-v + 3) / 7); - } - } else { - for (int i = 2; i < 6; i++) { - int v = (6 - i) * r0 + (i - 1) * r1; - pal[i] = v >= 0 ? (v + 2) / 5 : -((-v + 2) / 5); - } - pal[6] = -127; pal[7] = 127; - } - for (int i = 0; i < 8; i++) pal[i] += 128; - } - for (int i = 0; i < 16; i++) out[i][ch] = (uint8_t)pal[(idx >> (3 * i)) & 7]; -} - -/* ── BC7 ─────────────────────────────────────────────────────────────── */ - -static const struct { - uint8_t ns, pb, rb, isb, cb, ab, epb, spb, ib, ib2; -} yapf__bc7_modes[8] = { - { 3, 4, 0, 0, 4, 0, 1, 0, 3, 0 }, { 2, 6, 0, 0, 6, 0, 0, 1, 3, 0 }, - { 3, 6, 0, 0, 5, 0, 0, 0, 2, 0 }, { 2, 6, 0, 0, 7, 0, 1, 0, 2, 0 }, - { 1, 0, 2, 1, 5, 6, 0, 0, 2, 3 }, { 1, 0, 2, 0, 7, 8, 0, 0, 2, 2 }, - { 1, 0, 0, 0, 7, 7, 1, 0, 4, 0 }, { 2, 6, 0, 0, 5, 5, 1, 0, 2, 0 } -}; - -static int yapf__subset(int ns, int part, int i) { - if (ns == 2) return (yapf__part2[part] >> i) & 1; - if (ns == 3) return (int)((yapf__part3[part] >> (2 * i)) & 3); - return 0; -} - -static int yapf__is_anchor(int ns, int part, int i) { - if (i == 0) return 1; - if (ns == 2) return i == yapf__anchor2[part]; - if (ns == 3) return i == yapf__anchor3a[part] || i == yapf__anchor3b[part]; - return 0; -} - -static void yapf__bc7_block(const uint8_t *s, uint8_t out[16][4]) { - unsigned pos = 0; - int mode = 0; - while (mode < 8 && !yapf__getbits(s, &pos, 1)) mode++; - if (mode == 8) { memset(out, 0, 64); return; } - int ns = yapf__bc7_modes[mode].ns, cb = yapf__bc7_modes[mode].cb, ab = yapf__bc7_modes[mode].ab; - int part = (int)yapf__getbits(s, &pos, yapf__bc7_modes[mode].pb); - int rot = (int)yapf__getbits(s, &pos, yapf__bc7_modes[mode].rb); - int isb = (int)yapf__getbits(s, &pos, yapf__bc7_modes[mode].isb); - int ne = ns * 2, ep[6][4]; - for (int c = 0; c < 3; c++) - for (int e = 0; e < ne; e++) ep[e][c] = (int)yapf__getbits(s, &pos, cb); - for (int e = 0; e < ne; e++) ep[e][3] = ab ? (int)yapf__getbits(s, &pos, ab) : 255; - int pbit = yapf__bc7_modes[mode].epb | yapf__bc7_modes[mode].spb; - if (yapf__bc7_modes[mode].epb) { - for (int e = 0; e < ne; e++) { - int p = (int)yapf__getbits(s, &pos, 1); - for (int c = 0; c < 4; c++) if (c < 3 || ab) ep[e][c] = (ep[e][c] << 1) | p; - } - } else if (yapf__bc7_modes[mode].spb) { - for (int k = 0; k < ns; k++) { - int p = (int)yapf__getbits(s, &pos, 1); - for (int c = 0; c < 3; c++) { - ep[2 * k][c] = (ep[2 * k][c] << 1) | p; - ep[2 * k + 1][c] = (ep[2 * k + 1][c] << 1) | p; - } - } - } - for (int e = 0; e < ne; e++) - for (int c = 0; c < 4; c++) { - int bits = (c < 3 ? cb : ab) + pbit; - if (c == 3 && !ab) continue; - int v = ep[e][c] << (8 - bits); - ep[e][c] = v | (v >> bits); - } - int ib = yapf__bc7_modes[mode].ib, ib2 = yapf__bc7_modes[mode].ib2; - int idx[16], idx2[16]; - for (int i = 0; i < 16; i++) - idx[i] = (int)yapf__getbits(s, &pos, ib - yapf__is_anchor(ns, part, i)); - for (int i = 0; i < 16; i++) - idx2[i] = ib2 ? (int)yapf__getbits(s, &pos, ib2 - (i == 0)) : 0; - const uint8_t *w1 = yapf__weights(ib), *w2 = yapf__weights(ib2 ? ib2 : 2); - for (int i = 0; i < 16; i++) { - int k = yapf__subset(ns, part, i), px[4]; - const int *a = ep[2 * k], *b = ep[2 * k + 1]; - int cw, aw; - if (!ib2) { cw = w1[idx[i]]; aw = w1[idx[i]]; } - else if (!isb) { cw = w1[idx[i]]; aw = w2[idx2[i]]; } - else { cw = w2[idx2[i]]; aw = w1[idx[i]]; } - for (int c = 0; c < 3; c++) px[c] = yapf__bc_interp(a[c], b[c], cw); - px[3] = yapf__bc_interp(a[3], b[3], aw); - if (rot) { int t = px[3]; px[3] = px[rot - 1]; px[rot - 1] = t; } - for (int c = 0; c < 4; c++) out[i][c] = (uint8_t)px[c]; - } -} - -/* ── BC6H ────────────────────────────────────────────────────────────── */ -/* - * Header layouts as sequences of (field, first bit, bit count), in the - * order they appear after the mode bits. Fields: 0–3 red w, x, y, z; - * 4–7 green; 8–11 blue; 12 partition. The same table drives the reader - * and the encoder's writer. - */ -#define YAPF__F(f, lo, n) { f, lo, n } -typedef struct { uint8_t f, lo, n; } yapf__seg; -enum { RW, RX, RY, RZ, GW, GX, GY, GZ, BW, BX, BY, BZ, PD }; - -static const yapf__seg yapf__bc6_m0[] = { - {GY,4,1},{BY,4,1},{BZ,4,1},{RW,0,10},{GW,0,10},{BW,0,10},{RX,0,5},{GZ,4,1},{GY,0,4}, - {GX,0,5},{BZ,0,1},{GZ,0,4},{BX,0,5},{BZ,1,1},{BY,0,4},{RY,0,5},{BZ,2,1},{RZ,0,5},{BZ,3,1},{PD,0,5},{0,0,0} }; -static const yapf__seg yapf__bc6_m1[] = { - {GY,5,1},{GZ,4,1},{GZ,5,1},{RW,0,7},{BZ,0,1},{BZ,1,1},{BY,4,1},{GW,0,7},{BY,5,1},{BZ,2,1}, - {GY,4,1},{BW,0,7},{BZ,3,1},{BZ,5,1},{BZ,4,1},{RX,0,6},{GY,0,4},{GX,0,6},{GZ,0,4},{BX,0,6}, - {BY,0,4},{RY,0,6},{RZ,0,6},{PD,0,5},{0,0,0} }; -static const yapf__seg yapf__bc6_m2[] = { - {RW,0,10},{GW,0,10},{BW,0,10},{RX,0,5},{RW,10,1},{GY,0,4},{GX,0,4},{GW,10,1},{BZ,0,1},{GZ,0,4}, - {BX,0,4},{BW,10,1},{BZ,1,1},{BY,0,4},{RY,0,5},{BZ,2,1},{RZ,0,5},{BZ,3,1},{PD,0,5},{0,0,0} }; -static const yapf__seg yapf__bc6_m3[] = { - {RW,0,10},{GW,0,10},{BW,0,10},{RX,0,4},{RW,10,1},{GZ,4,1},{GY,0,4},{GX,0,5},{GW,10,1},{GZ,0,4}, - {BX,0,4},{BW,10,1},{BZ,1,1},{BY,0,4},{RY,0,4},{BZ,0,1},{BZ,2,1},{RZ,0,4},{GY,4,1},{BZ,3,1},{PD,0,5},{0,0,0} }; -static const yapf__seg yapf__bc6_m4[] = { - {RW,0,10},{GW,0,10},{BW,0,10},{RX,0,4},{RW,10,1},{BY,4,1},{GY,0,4},{GX,0,4},{GW,10,1},{BZ,0,1}, - {GZ,0,4},{BX,0,5},{BW,10,1},{BY,0,4},{RY,0,4},{BZ,1,1},{BZ,2,1},{RZ,0,4},{BZ,4,1},{BZ,3,1},{PD,0,5},{0,0,0} }; -static const yapf__seg yapf__bc6_m5[] = { - {RW,0,9},{BY,4,1},{GW,0,9},{GY,4,1},{BW,0,9},{BZ,4,1},{RX,0,5},{GZ,4,1},{GY,0,4},{GX,0,5}, - {BZ,0,1},{GZ,0,4},{BX,0,5},{BZ,1,1},{BY,0,4},{RY,0,5},{BZ,2,1},{RZ,0,5},{BZ,3,1},{PD,0,5},{0,0,0} }; -static const yapf__seg yapf__bc6_m6[] = { - {RW,0,8},{GZ,4,1},{BY,4,1},{GW,0,8},{BZ,2,1},{GY,4,1},{BW,0,8},{BZ,3,1},{BZ,4,1},{RX,0,6}, - {GY,0,4},{GX,0,5},{BZ,0,1},{GZ,0,4},{BX,0,5},{BZ,1,1},{BY,0,4},{RY,0,6},{RZ,0,6},{PD,0,5},{0,0,0} }; -static const yapf__seg yapf__bc6_m7[] = { - {RW,0,8},{BZ,0,1},{BY,4,1},{GW,0,8},{GY,5,1},{GY,4,1},{BW,0,8},{GZ,5,1},{BZ,4,1},{RX,0,5}, - {GZ,4,1},{GY,0,4},{GX,0,6},{GZ,0,4},{BX,0,5},{BZ,1,1},{BY,0,4},{RY,0,5},{BZ,2,1},{RZ,0,5},{BZ,3,1},{PD,0,5},{0,0,0} }; -static const yapf__seg yapf__bc6_m8[] = { - {RW,0,8},{BZ,1,1},{BY,4,1},{GW,0,8},{BY,5,1},{GY,4,1},{BW,0,8},{BZ,5,1},{BZ,4,1},{RX,0,5}, - {GZ,4,1},{GY,0,4},{GX,0,5},{BZ,0,1},{GZ,0,4},{BX,0,6},{BY,0,4},{RY,0,5},{BZ,2,1},{RZ,0,5},{BZ,3,1},{PD,0,5},{0,0,0} }; -static const yapf__seg yapf__bc6_m9[] = { - {RW,0,6},{GZ,4,1},{BZ,0,1},{BZ,1,1},{BY,4,1},{GW,0,6},{GY,5,1},{BY,5,1},{BZ,2,1},{GY,4,1}, - {BW,0,6},{GZ,5,1},{BZ,3,1},{BZ,5,1},{BZ,4,1},{RX,0,6},{GY,0,4},{GX,0,6},{GZ,0,4},{BX,0,6}, - {BY,0,4},{RY,0,6},{RZ,0,6},{PD,0,5},{0,0,0} }; -static const yapf__seg yapf__bc6_m10[] = { - {RW,0,10},{GW,0,10},{BW,0,10},{RX,0,10},{GX,0,10},{BX,0,10},{0,0,0} }; -static const yapf__seg yapf__bc6_m11[] = { - {RW,0,10},{GW,0,10},{BW,0,10},{RX,0,9},{RW,10,1},{GX,0,9},{GW,10,1},{BX,0,9},{BW,10,1},{0,0,0} }; -static const yapf__seg yapf__bc6_m12[] = { - {RW,0,10},{GW,0,10},{BW,0,10},{RX,0,8},{RW,11,1},{RW,10,1},{GX,0,8},{GW,11,1},{GW,10,1}, - {BX,0,8},{BW,11,1},{BW,10,1},{0,0,0} }; -static const yapf__seg yapf__bc6_m13[] = { - {RW,0,10},{GW,0,10},{BW,0,10},{RX,0,4},{RW,15,1},{RW,14,1},{RW,13,1},{RW,12,1},{RW,11,1},{RW,10,1}, - {GX,0,4},{GW,15,1},{GW,14,1},{GW,13,1},{GW,12,1},{GW,11,1},{GW,10,1}, - {BX,0,4},{BW,15,1},{BW,14,1},{BW,13,1},{BW,12,1},{BW,11,1},{BW,10,1},{0,0,0} }; - -static const struct { - uint8_t code, codebits, w, dr, dg, db; - const yapf__seg *seg; -} yapf__bc6_modes[14] = { - { 0x00, 2, 10, 5, 5, 5, yapf__bc6_m0 }, { 0x01, 2, 7, 6, 6, 6, yapf__bc6_m1 }, - { 0x02, 5, 11, 5, 4, 4, yapf__bc6_m2 }, { 0x06, 5, 11, 4, 5, 4, yapf__bc6_m3 }, - { 0x0A, 5, 11, 4, 4, 5, yapf__bc6_m4 }, { 0x0E, 5, 9, 5, 5, 5, yapf__bc6_m5 }, - { 0x12, 5, 8, 6, 5, 5, yapf__bc6_m6 }, { 0x16, 5, 8, 5, 6, 5, yapf__bc6_m7 }, - { 0x1A, 5, 8, 5, 5, 6, yapf__bc6_m8 }, { 0x1E, 5, 6, 6, 6, 6, yapf__bc6_m9 }, - { 0x03, 5, 10, 10, 10, 10, yapf__bc6_m10 }, { 0x07, 5, 11, 9, 9, 9, yapf__bc6_m11 }, - { 0x0B, 5, 12, 8, 8, 8, yapf__bc6_m12 }, { 0x0F, 5, 16, 4, 4, 4, yapf__bc6_m13 } -}; - -static int yapf__sext(int v, int bits) { - int m = 1 << (bits - 1); - v &= (1 << bits) - 1; - return (v ^ m) - m; -} - -static int yapf__bc6_unq(int v, int bits, int sgn) { - if (!sgn) { - if (bits >= 15) return v; - if (v == 0) return 0; - if (v == (1 << bits) - 1) return 0xFFFF; - return ((v << 16) + 0x8000) >> bits; - } - if (bits >= 16) return v; - int s = v < 0; - if (s) v = -v; - int u; - if (v == 0) u = 0; - else if (v >= (1 << (bits - 1)) - 1) u = 0x7FFF; - else u = ((v << 15) + 0x4000) >> (bits - 1); - return s ? -u : u; -} - -static uint16_t yapf__bc6_finish(int v, int sgn) { - if (!sgn) return (uint16_t)((v * 31) >> 6); - v = v < 0 ? -(((-v) * 31) >> 5) : (v * 31) >> 5; - return (uint16_t)(v < 0 ? 0x8000 | -v : v); -} - -static void yapf__bc6_block(const uint8_t *s, uint16_t out[16][3], int sgn) { - unsigned pos = 0; - int code = (int)yapf__getbits(s, &pos, 2), m = -1; - if (code > 1) code |= (int)yapf__getbits(s, &pos, 3) << 2; - for (int i = 0; i < 14; i++) - if (yapf__bc6_modes[i].code == code) { m = i; break; } - if (m < 0) { memset(out, 0, 96); return; } /* reserved modes */ - - int f[13] = {0}; - for (const yapf__seg *g = yapf__bc6_modes[m].seg; g->n; g++) - f[g->f] |= (int)yapf__getbits(s, &pos, g->n) << g->lo; - int W = yapf__bc6_modes[m].w, regions = m < 10 ? 2 : 1, ne = regions * 2; - int db[3] = { yapf__bc6_modes[m].dr, yapf__bc6_modes[m].dg, yapf__bc6_modes[m].db }; - int ep[4][3]; - for (int c = 0; c < 3; c++) { - for (int e = 0; e < ne; e++) ep[e][c] = f[c * 4 + e]; - if (sgn) ep[0][c] = yapf__sext(ep[0][c], W); - int delta = m != 9 && m != 10; - for (int e = 1; e < ne; e++) { - if (delta || sgn) ep[e][c] = yapf__sext(ep[e][c], db[c]); - if (delta) { - ep[e][c] = (ep[e][c] + ep[0][c]) & ((1 << W) - 1); - if (sgn) ep[e][c] = yapf__sext(ep[e][c], W); - } - } - for (int e = 0; e < ne; e++) ep[e][c] = yapf__bc6_unq(ep[e][c], W, sgn); - } - int part = f[PD], ib = regions == 2 ? 3 : 4; - const uint8_t *wt = yapf__weights(ib); - for (int i = 0; i < 16; i++) { - int k = regions == 2 ? (yapf__part2[part] >> i) & 1 : 0; - int anchor = i == 0 || (regions == 2 && i == yapf__anchor2[part]); - int idx = (int)yapf__getbits(s, &pos, ib - anchor); - for (int c = 0; c < 3; c++) - out[i][c] = yapf__bc6_finish(yapf__bc_interp(ep[2 * k][c], ep[2 * k + 1][c], wt[idx]), sgn); - } -} - -int yapf_blocks_decode(uint8_t format, const void *blocks, uint32_t w, uint32_t h, void *out) { - uint32_t bw, bh, S; - if (!blocks || !out || !w || !h) return YAPF_ERR_INVALID; - if (!yapf_block_info(format, &bw, &bh, &S)) return YAPF_ERR_INVALID; - if (format >= YAPF_GPU_ETC2_RGB8) return YAPF_ERR_UNSUPPORTED; - const uint8_t *b = (const uint8_t *)blocks; - uint32_t nbx = (w + 3) / 4, nby = (h + 3) / 4; - int hdr = format == YAPF_GPU_BC6H || format == YAPF_GPU_BC6H_SF; - for (uint32_t by = 0; by < nby; by++) - for (uint32_t bx = 0; bx < nbx; bx++, b += S) { - uint8_t px[16][4]; - uint16_t hx[16][3]; - switch (format) { - case YAPF_GPU_BC1: yapf__bc1_block(b, px, 0); break; - case YAPF_GPU_BC2: - yapf__bc1_block(b + 8, px, 1); - for (int i = 0; i < 16; i++) px[i][3] = (uint8_t)(((b[i / 2] >> (4 * (i & 1))) & 15) * 17); - break; - case YAPF_GPU_BC3: - yapf__bc1_block(b + 8, px, 1); - yapf__bc4_block(b, px, 3, 0); - break; - case YAPF_GPU_BC4: case YAPF_GPU_BC4_SNORM: - memset(px, 0, sizeof(px)); - yapf__bc4_block(b, px, 0, format == YAPF_GPU_BC4_SNORM); - for (int i = 0; i < 16; i++) px[i][3] = 255; - break; - case YAPF_GPU_BC5: case YAPF_GPU_BC5_SNORM: - memset(px, 0, sizeof(px)); - yapf__bc4_block(b, px, 0, format == YAPF_GPU_BC5_SNORM); - yapf__bc4_block(b + 8, px, 1, format == YAPF_GPU_BC5_SNORM); - for (int i = 0; i < 16; i++) px[i][3] = 255; - break; - case YAPF_GPU_BC7: yapf__bc7_block(b, px); break; - default: yapf__bc6_block(b, hx, format == YAPF_GPU_BC6H_SF); break; - } - for (uint32_t y = 0; y < 4 && by * 4 + y < h; y++) - for (uint32_t x = 0; x < 4 && bx * 4 + x < w; x++) { - size_t o = (size_t)(by * 4 + y) * w + bx * 4 + x; - if (hdr) memcpy((uint16_t *)out + o * 3, hx[y * 4 + x], 6); - else memcpy((uint8_t *)out + o * 4, px[y * 4 + x], 4); - } - } - return YAPF_OK; -} - -/* ── Encoders ────────────────────────────────────────────────────────── */ -/* - * Straightforward, decent-quality encoders so YAPF can make GPU textures - * on its own: principal axis endpoints with least-squares refinement. - * For the best BC7 / ASTC quality use a dedicated encoder and store its - * blocks (payload = BLOCKS). - */ - -/* Principal axis of n points of dim k (power iteration). */ -static void yapf__pca(const float (*p)[4], int n, int k, float *mean, float *axis) { - for (int c = 0; c < k; c++) { - mean[c] = 0; - for (int i = 0; i < n; i++) mean[c] += p[i][c]; - mean[c] /= (float)n; - } - float cov[4][4] = {{0}}; - for (int i = 0; i < n; i++) - for (int a = 0; a < k; a++) - for (int b = 0; b < k; b++) - cov[a][b] += (p[i][a] - mean[a]) * (p[i][b] - mean[b]); - float v[4] = { 1.0f, 0.7f, 0.4f, 0.2f }; - for (int it = 0; it < 12; it++) { - float nv[4] = {0}, len = 0; - for (int a = 0; a < k; a++) { - for (int b = 0; b < k; b++) nv[a] += cov[a][b] * v[b]; - len += nv[a] * nv[a]; - } - if (len < 1e-12f) break; - float mx = 0; /* scale by the largest component */ - for (int a = 0; a < k; a++) mx = nv[a] > mx ? nv[a] : -nv[a] > mx ? -nv[a] : mx; - for (int a = 0; a < k; a++) v[a] = nv[a] / mx; - } - for (int a = 0; a < k; a++) axis[a] = v[a]; -} - -/* Endpoints at the extremes of the projections onto the principal axis. */ -static void yapf__extents(const float (*p)[4], int n, int k, float *e0, float *e1) { - float mean[4], axis[4], lo = 1e30f, hi = -1e30f, len2 = 0; - yapf__pca(p, n, k, mean, axis); - for (int c = 0; c < k; c++) len2 += axis[c] * axis[c]; - if (len2 < 1e-20f) len2 = 1.0f; - for (int i = 0; i < n; i++) { - float t = 0; - for (int c = 0; c < k; c++) t += (p[i][c] - mean[c]) * axis[c]; - if (t < lo) lo = t; - if (t > hi) hi = t; - } - lo /= len2; /* the axis need not be unit length */ - hi /= len2; - for (int c = 0; c < k; c++) { e0[c] = mean[c] + axis[c] * lo; e1[c] = mean[c] + axis[c] * hi; } -} - -/* Least squares endpoints for given interpolation weights (0..1). */ -static int yapf__lsq(const float (*p)[4], const float *wt, int n, int k, float *e0, float *e1) { - float aa = 0, ab = 0, bb = 0, ax[4] = {0}, bx[4] = {0}; - for (int i = 0; i < n; i++) { - float b = wt[i], a = 1.0f - b; - aa += a * a; ab += a * b; bb += b * b; - for (int c = 0; c < k; c++) { ax[c] += a * p[i][c]; bx[c] += b * p[i][c]; } - } - float det = aa * bb - ab * ab; - if (det < 1e-8f && det > -1e-8f) return -1; - for (int c = 0; c < k; c++) { - e0[c] = (ax[c] * bb - bx[c] * ab) / det; - e1[c] = (bx[c] * aa - ax[c] * ab) / det; - } - return 0; -} - -static int yapf__clampi(float v, int lo, int hi) { - int i = (int)(v + 0.5f); - if (v < 0) i = (int)(v - 0.5f); - return i < lo ? lo : i > hi ? hi : i; -} - -static uint16_t yapf__to565(const float *c) { - return (uint16_t)((yapf__clampi(c[0] * 31.0f / 255.0f, 0, 31) << 11) | - (yapf__clampi(c[1] * 63.0f / 255.0f, 0, 63) << 5) | - yapf__clampi(c[2] * 31.0f / 255.0f, 0, 31)); -} - -/* BC1 colour block from 16 RGBA pixels. four: force 4-colour mode - * (BC2 / BC3); otherwise pixels with alpha < 128 become transparent. */ -static void yapf__bc1_encode(const uint8_t px[16][4], uint8_t *out, int four) { - float p[16][4]; - int transparent = 0, n = 0, map[16]; - for (int i = 0; i < 16; i++) { - if (!four && px[i][3] < 128) { transparent = 1; map[i] = -1; continue; } - map[i] = n; - for (int c = 0; c < 3; c++) p[n][c] = px[i][c]; - n++; - } - if (n == 0) { /* all transparent */ - yapf__w16le(out, 0); yapf__w16le(out + 2, 0); yapf__w32le(out + 4, 0xFFFFFFFFu); - return; - } - float e0[4], e1[4]; - uint32_t best_idx = 0, best_err = UINT32_MAX; - uint16_t best_c0 = 0, best_c1 = 0; - yapf__extents((const float (*)[4])p, n, 3, e0, e1); - for (int it = 0; it < 3; it++) { - uint16_t c0 = yapf__to565(e1), c1 = yapf__to565(e0); - int three = transparent; - if (three ? c0 > c1 : c0 < c1) { uint16_t t = c0; c0 = c1; c1 = t; } - if (!three && c0 == c1) { /* single colour */ - if (c1 > 0) c1--; else c0++; - if (c0 < c1) { uint16_t t = c0; c0 = c1; c1 = t; } - } - uint8_t blk[8], full[16][4]; - /* decode a block with indices 0, 1, 2, 3 to get the palette */ - yapf__w16le(blk, c0); yapf__w16le(blk + 2, c1); yapf__w32le(blk + 4, 0xE4u); - yapf__bc1_block(blk, full, four); - int nc = three ? 3 : 4; - uint32_t idx = 0, err = 0; - float wt[16]; - static const float wv4[4] = { 0.0f, 1.0f, 1.0f / 3, 2.0f / 3 }; - static const float wv3[3] = { 0.0f, 1.0f, 0.5f }; - for (int i = 0; i < 16; i++) { - if (map[i] < 0) { idx |= 3u << (2 * i); continue; } - uint32_t be = UINT32_MAX; - int bi = 0; - for (int j = 0; j < nc; j++) { - uint32_t e = 0; - for (int c = 0; c < 3; c++) { int d = (int)full[j][c] - px[i][c]; e += (uint32_t)(d * d); } - if (e < be) { be = e; bi = j; } - } - idx |= (uint32_t)bi << (2 * i); - err += be; - wt[map[i]] = three ? wv3[bi] : wv4[bi]; - } - if (err < best_err) { best_err = err; best_idx = idx; best_c0 = c0; best_c1 = c1; } - if (err == 0) break; - /* refine: endpoints in palette order (index 0 = c0) */ - float n0[4], n1[4]; - if (yapf__lsq((const float (*)[4])p, wt, n, 3, n0, n1) != 0) break; - for (int c = 0; c < 3; c++) { e1[c] = n0[c]; e0[c] = n1[c]; } - } - yapf__w16le(out, best_c0); - yapf__w16le(out + 2, best_c1); - yapf__w32le(out + 4, best_idx); -} - -/* BC4 block from 16 values. */ -static void yapf__bc4_encode(const uint8_t *v, uint8_t *out) { - int lo = 255, hi = 0; - for (int i = 0; i < 16; i++) { if (v[i] < lo) lo = v[i]; if (v[i] > hi) hi = v[i]; } - uint64_t best_bits = 0; - uint32_t best_err = UINT32_MAX; - int best0 = hi, best1 = lo; - for (int d0 = 0; d0 < 3; d0++) - for (int d1 = 0; d1 < 3; d1++) { - int r0 = hi - d0, r1 = lo + d1; - if (r0 < r1) continue; - if (r0 == r1) { if (d0 || d1) continue; } - uint8_t blk[8] = { (uint8_t)r0, (uint8_t)r1, 0, 0, 0, 0, 0, 0 }; - uint8_t pal[16][4]; - int palv[8]; - for (int j = 0; j < 8; j++) { - uint64_t ix = 0; - for (int i = 0; i < 16; i++) ix |= (uint64_t)j << (3 * i); - for (int k = 0; k < 6; k++) blk[2 + k] = (uint8_t)(ix >> (8 * k)); - yapf__bc4_block(blk, pal, 0, 0); - palv[j] = pal[0][0]; - } - uint64_t bits = 0; - uint32_t err = 0; - for (int i = 0; i < 16; i++) { - int bj = 0, be = 1 << 30; - for (int j = 0; j < 8; j++) { - int d = palv[j] - v[i]; - if (d * d < be) { be = d * d; bj = j; } - } - bits |= (uint64_t)bj << (3 * i); - err += (uint32_t)be; - } - if (err < best_err) { best_err = err; best_bits = bits; best0 = r0; best1 = r1; } - } - out[0] = (uint8_t)best0; - out[1] = (uint8_t)best1; - for (int k = 0; k < 6; k++) out[2 + k] = (uint8_t)(best_bits >> (8 * k)); -} - -/* BC7 mode 6 (one subset, RGBA 7.7.7.7 + p-bit per endpoint, 4-bit - * indices). Opaque blocks keep the p-bits at 1 so alpha stays 255. - * Returns the squared error. */ -static uint32_t yapf__bc7_mode6(const uint8_t px[16][4], uint8_t *out) { - float p[16][4], e0[4], e1[4]; - int opaque = 1; - for (int i = 0; i < 16; i++) { - for (int c = 0; c < 4; c++) p[i][c] = px[i][c]; - if (px[i][3] != 255) opaque = 0; - } - yapf__extents((const float (*)[4])p, 16, opaque ? 3 : 4, e0, e1); - if (opaque) e0[3] = e1[3] = 255; - - uint8_t best[16]; - uint32_t best_err = UINT32_MAX; - for (int it = 0; it < 3; it++) { - int q[2][4], pb[2]; - const float *e[2] = { e0, e1 }; - for (int k = 0; k < 2; k++) { - uint32_t bestp = UINT32_MAX; - for (int pbit = opaque ? 1 : 0; pbit < 2; pbit++) { - uint32_t er = 0; - int qq[4]; - for (int c = 0; c < 4; c++) { - qq[c] = yapf__clampi((e[k][c] - (float)pbit) / 2.0f, 0, 127); - int d = (2 * qq[c] + pbit) - (int)(e[k][c] + 0.5f); - er += (uint32_t)(d * d); - } - if (er < bestp) { bestp = er; pb[k] = pbit; memcpy(q[k], qq, sizeof(qq)); } - } - } - int v[2][4]; - for (int k = 0; k < 2; k++) for (int c = 0; c < 4; c++) v[k][c] = 2 * q[k][c] + pb[k]; - int idx[16]; - uint32_t err = 0; - float wt[16]; - for (int i = 0; i < 16; i++) { - uint32_t be = UINT32_MAX; - int bi = 0; - for (int j = 0; j < 16; j++) { - uint32_t er = 0; - for (int c = 0; c < 4; c++) { - int d = yapf__bc_interp(v[0][c], v[1][c], yapf__w4[j]) - px[i][c]; - er += (uint32_t)(d * d); - } - if (er < be) { be = er; bi = j; } - } - idx[i] = bi; - err += be; - wt[i] = yapf__w4[bi] / 64.0f; - } - if (err < best_err) { - best_err = err; - int swap = idx[0] >= 8; - int a = swap ? 1 : 0, b = swap ? 0 : 1; - memset(best, 0, 16); - unsigned pos = 0; - yapf__putbits(best, &pos, 1u << 6, 7); - for (int c = 0; c < 4; c++) { - yapf__putbits(best, &pos, (uint32_t)q[a][c], 7); - yapf__putbits(best, &pos, (uint32_t)q[b][c], 7); - } - yapf__putbits(best, &pos, (uint32_t)pb[a], 1); - yapf__putbits(best, &pos, (uint32_t)pb[b], 1); - for (int i = 0; i < 16; i++) { - int ix = swap ? 15 - idx[i] : idx[i]; - yapf__putbits(best, &pos, (uint32_t)ix, i == 0 ? 3 : 4); - } - } - if (err == 0) break; - float n0[4], n1[4]; - if (yapf__lsq((const float (*)[4])p, wt, 16, 4, n0, n1) != 0) break; - memcpy(e0, n0, sizeof(n0)); - memcpy(e1, n1, sizeof(n1)); - if (opaque) e0[3] = e1[3] = 255; - } - memcpy(out, best, 16); - return best_err; -} - -/* Fits indices of `bits` bits for the points of one subset against - * endpoints v0, v1 (k channels); returns the error, fills idx / wt. */ -static uint32_t yapf__bc7_fit(const uint8_t px[16][4], const int *sel, int n, - const int *v0, const int *v1, int c0, int k, int bits, - int *idx, float *wt) -{ - const uint8_t *w = yapf__weights(bits); - uint32_t err = 0; - for (int i = 0; i < n; i++) { - uint32_t be = UINT32_MAX; - int bi = 0; - for (int j = 0; j < (1 << bits); j++) { - uint32_t e = 0; - for (int c = c0; c < c0 + k; c++) { - int d = yapf__bc_interp(v0[c], v1[c], w[j]) - px[sel[i]][c]; - e += (uint32_t)(d * d); - } - if (e < be) { be = e; bi = j; } - } - idx[i] = bi; - wt[i] = w[bi] / 64.0f; - err += be; - } - return err; -} - -/* BC7 mode 5: RGB 7 bits and alpha 8 bits on separate 2-bit indices, so - * colour and alpha need not move together (cut-outs, decals). */ -static uint32_t yapf__bc7_mode5(const uint8_t px[16][4], uint8_t *out) { - int sel[16]; - float p[16][4], e0[4], e1[4]; - for (int i = 0; i < 16; i++) { sel[i] = i; for (int c = 0; c < 4; c++) p[i][c] = px[i][c]; } - yapf__extents((const float (*)[4])p, 16, 3, e0, e1); - - int bq[2][3] = {{0}}, bidx[16] = {0}; - uint32_t cerr = UINT32_MAX; - for (int it = 0; it < 3; it++) { - int q[2][3], v[2][4] = {{0}}, idx[16]; - float wt[16]; - for (int c = 0; c < 3; c++) { - q[0][c] = yapf__clampi(e0[c] * 127.0f / 255.0f, 0, 127); - q[1][c] = yapf__clampi(e1[c] * 127.0f / 255.0f, 0, 127); - v[0][c] = (q[0][c] << 1) | (q[0][c] >> 6); - v[1][c] = (q[1][c] << 1) | (q[1][c] >> 6); - } - uint32_t e = yapf__bc7_fit(px, sel, 16, v[0], v[1], 0, 3, 2, idx, wt); - if (e < cerr) { cerr = e; memcpy(bq, q, sizeof(q)); memcpy(bidx, idx, sizeof(idx)); } - float n0[4], n1[4]; - if (e == 0 || yapf__lsq((const float (*)[4])p, wt, 16, 3, n0, n1) != 0) break; - memcpy(e0, n0, sizeof(n0)); - memcpy(e1, n1, sizeof(n1)); - } - int lo = 255, hi = 0; - for (int i = 0; i < 16; i++) { if (px[i][3] < lo) lo = px[i][3]; if (px[i][3] > hi) hi = px[i][3]; } - int ba[2] = { lo, hi }, aidx[16] = {0}; - uint32_t aerr = UINT32_MAX; - for (int d0 = 0; d0 < 4; d0++) - for (int d1 = 0; d1 < 4; d1++) { - int a0 = lo + d0, a1 = hi - d1, v0[4], v1[4], idx[16]; - float wt[16]; - if (a0 > a1) continue; - v0[3] = a0; v1[3] = a1; - uint32_t e = yapf__bc7_fit(px, sel, 16, v0, v1, 3, 1, 2, idx, wt); - if (e < aerr) { aerr = e; ba[0] = a0; ba[1] = a1; memcpy(aidx, idx, sizeof(idx)); } - } - /* anchors: the first index of each set keeps its top bit clear */ - if (bidx[0] >= 2) { - for (int c = 0; c < 3; c++) { int t = bq[0][c]; bq[0][c] = bq[1][c]; bq[1][c] = t; } - for (int i = 0; i < 16; i++) bidx[i] = 3 - bidx[i]; - } - if (aidx[0] >= 2) { - int t = ba[0]; ba[0] = ba[1]; ba[1] = t; - for (int i = 0; i < 16; i++) aidx[i] = 3 - aidx[i]; - } - unsigned pos = 0; - memset(out, 0, 16); - yapf__putbits(out, &pos, 1u << 5, 6); - yapf__putbits(out, &pos, 0, 2); /* no rotation */ - for (int c = 0; c < 3; c++) { - yapf__putbits(out, &pos, (uint32_t)bq[0][c], 7); - yapf__putbits(out, &pos, (uint32_t)bq[1][c], 7); - } - yapf__putbits(out, &pos, (uint32_t)ba[0], 8); - yapf__putbits(out, &pos, (uint32_t)ba[1], 8); - for (int i = 0; i < 16; i++) yapf__putbits(out, &pos, (uint32_t)bidx[i], i ? 2 : 1); - for (int i = 0; i < 16; i++) yapf__putbits(out, &pos, (uint32_t)aidx[i], i ? 2 : 1); - return cerr + aerr; -} - -/* BC7 mode 1: two subsets, RGB 6 bits + a shared p-bit per subset, 3-bit - * indices; for opaque blocks with two colour regions. */ -static uint32_t yapf__bc7_mode1(const uint8_t px[16][4], int part, uint8_t *out) { - int q[2][2][3], pb[2], idx16[16]; - uint32_t total = 0; - for (int k = 0; k < 2; k++) { - int sel[16], n = 0; - float p[16][4], e0[4], e1[4]; - for (int i = 0; i < 16; i++) - if (yapf__subset(2, part, i) == k) { - sel[n] = i; - for (int c = 0; c < 3; c++) p[n][c] = px[i][c]; - n++; - } - yapf__extents((const float (*)[4])p, n, 3, e0, e1); - uint32_t best = UINT32_MAX; - for (int it = 0; it < 2; it++) { - for (int pbit = 0; pbit < 2; pbit++) { - int qq[2][3], v[2][4] = {{0}}, idx[16]; - float wt[16]; - for (int c = 0; c < 3; c++) { - const float *e[2] = { e0, e1 }; - for (int j = 0; j < 2; j++) { - qq[j][c] = yapf__clampi((e[j][c] * 127.0f / 255.0f - (float)pbit) / 2.0f, 0, 63); - int x = (qq[j][c] << 1) | pbit; - v[j][c] = (x << 1) | (x >> 6); - } - } - uint32_t er = yapf__bc7_fit(px, sel, n, v[0], v[1], 0, 3, 3, idx, wt); - if (er < best) { - best = er; - pb[k] = pbit; - memcpy(q[k], qq, sizeof(qq)); - for (int i = 0; i < n; i++) idx16[sel[i]] = idx[i]; - } - if (it == 0 && pbit == 1) { - float n0[4], n1[4]; - if (yapf__lsq((const float (*)[4])p, wt, n, 3, n0, n1) == 0) { - memcpy(e0, n0, sizeof(n0)); - memcpy(e1, n1, sizeof(n1)); - } - } - } - } - total += best; - int anchor = k == 0 ? 0 : yapf__anchor2[part]; - if (idx16[anchor] >= 4) { - for (int c = 0; c < 3; c++) { int t = q[k][0][c]; q[k][0][c] = q[k][1][c]; q[k][1][c] = t; } - for (int i = 0; i < 16; i++) if (yapf__subset(2, part, i) == k) idx16[i] = 7 - idx16[i]; - } - } - unsigned pos = 0; - memset(out, 0, 16); - yapf__putbits(out, &pos, 2, 2); - yapf__putbits(out, &pos, (uint32_t)part, 6); - for (int c = 0; c < 3; c++) - for (int k = 0; k < 2; k++) { - yapf__putbits(out, &pos, (uint32_t)q[k][0][c], 6); - yapf__putbits(out, &pos, (uint32_t)q[k][1][c], 6); - } - yapf__putbits(out, &pos, (uint32_t)pb[0], 1); - yapf__putbits(out, &pos, (uint32_t)pb[1], 1); - for (int i = 0; i < 16; i++) - yapf__putbits(out, &pos, (uint32_t)idx16[i], 3 - yapf__is_anchor(2, part, i)); - return total; -} - -/* BC7: mode 6, plus mode 5 when there is alpha, plus mode 1 on the two - * most promising partitions (least summed per-subset variance) for - * opaque blocks. The block with the smallest error wins. */ -static void yapf__bc7_encode(const uint8_t px[16][4], uint8_t *out) { - uint8_t cand[16]; - uint32_t best = yapf__bc7_mode6(px, out), e; - int opaque = 1; - for (int i = 0; i < 16; i++) if (px[i][3] != 255) opaque = 0; - if (best == 0) return; - if (!opaque) { - if ((e = yapf__bc7_mode5(px, cand)) < best) { best = e; memcpy(out, cand, 16); } - return; - } - float score[64]; - for (int part = 0; part < 64; part++) { - float s = 0; - for (int k = 0; k < 2; k++) { - float sum[3] = {0}, sq[3] = {0}; - int n = 0; - for (int i = 0; i < 16; i++) - if (yapf__subset(2, part, i) == k) { - n++; - for (int c = 0; c < 3; c++) { sum[c] += px[i][c]; sq[c] += (float)px[i][c] * px[i][c]; } - } - for (int c = 0; c < 3; c++) s += sq[c] - sum[c] * sum[c] / (float)n; - } - score[part] = s; - } - for (int t = 0; t < 2; t++) { - int bp = 0; - for (int part = 1; part < 64; part++) if (score[part] < score[bp]) bp = part; - score[bp] = 1e30f; - if ((e = yapf__bc7_mode1(px, bp, cand)) < best) { best = e; memcpy(out, cand, 16); } - } -} - -/* BC6H unsigned, one region: tries modes 11–14 (10.10, 11.9, 12.8, 16.4) - * and keeps the one with the smallest error in half-float bits. */ -static void yapf__bc6_encode(const uint16_t px[16][3], uint8_t *out) { - float p[16][4], e0[4], e1[4]; - int hv[16][3]; - for (int i = 0; i < 16; i++) - for (int c = 0; c < 3; c++) { - int h = px[i][c]; - if (h & 0x8000) h = 0; /* negative: unsigned format */ - if (h > 0x7BFF) h = 0x7BFF; /* inf / nan: largest finite */ - hv[i][c] = h; - p[i][c] = (float)h * 64.0f / 31.0f; /* interpolation domain */ - } - yapf__extents((const float (*)[4])p, 16, 3, e0, e1); - - uint8_t best[16]; - uint64_t best_err = UINT64_MAX; - memset(best, 0, 16); - for (int m = 10; m < 14; m++) { - int W = yapf__bc6_modes[m].w, d = yapf__bc6_modes[m].dr; - float f0[4], f1[4]; - memcpy(f0, e0, sizeof(f0)); - memcpy(f1, e1, sizeof(f1)); - for (int it = 0; it < 2; it++) { - int q[2][3], ok = 1; - for (int c = 0; c < 3; c++) { - const float *e[2] = { f0, f1 }; - for (int k = 0; k < 2; k++) { - float u = e[k][c]; - int v = W >= 15 ? yapf__clampi(u, 0, (1 << W) - 1) - : yapf__clampi((u - (float)(1 << (15 - W))) / (float)(1 << (16 - W)), - 0, (1 << W) - 1); - q[k][c] = v; - } - if (m != 10) { - int delta = q[1][c] - q[0][c]; - if (delta < -(1 << (d - 1)) || delta > (1 << (d - 1)) - 1) ok = 0; - } - } - if (!ok) break; - int u[2][3]; - for (int k = 0; k < 2; k++) for (int c = 0; c < 3; c++) u[k][c] = yapf__bc6_unq(q[k][c], W, 0); - int idx[16]; - uint64_t err = 0; - float wt[16]; - for (int i = 0; i < 16; i++) { - uint64_t be = UINT64_MAX; - int bi = 0; - for (int j = 0; j < 16; j++) { - uint64_t er = 0; - for (int c = 0; c < 3; c++) { - int64_t dd = (int64_t)yapf__bc6_finish(yapf__bc_interp(u[0][c], u[1][c], yapf__w4[j]), 0) - hv[i][c]; - er += (uint64_t)(dd * dd); - } - if (er < be) { be = er; bi = j; } - } - idx[i] = bi; - err += be; - wt[i] = yapf__w4[bi] / 64.0f; - } - if (err < best_err) { - best_err = err; - int swap = idx[0] >= 8, a = swap ? 1 : 0, b = swap ? 0 : 1; - int f[13] = {0}; - for (int c = 0; c < 3; c++) { - f[c * 4] = q[a][c]; - f[c * 4 + 1] = m == 10 ? q[b][c] : (q[b][c] - q[a][c]) & ((1 << d) - 1); - } - /* with swapped endpoints the delta must still fit */ - int fits = 1; - if (m != 10) - for (int c = 0; c < 3; c++) { - int delta = q[b][c] - q[a][c]; - if (delta < -(1 << (d - 1)) || delta > (1 << (d - 1)) - 1) fits = 0; - } - if (fits) { - memset(best, 0, 16); - unsigned pos = 0; - yapf__putbits(best, &pos, yapf__bc6_modes[m].code, 5); - for (const yapf__seg *g = yapf__bc6_modes[m].seg; g->n; g++) - yapf__putbits(best, &pos, (uint32_t)(f[g->f] >> g->lo), g->n); - for (int i = 0; i < 16; i++) { - int ix = swap ? 15 - idx[i] : idx[i]; - yapf__putbits(best, &pos, (uint32_t)ix, i == 0 ? 3 : 4); - } - } else { - best_err = UINT64_MAX; - } - } - float n0[4], n1[4]; - if (yapf__lsq((const float (*)[4])p, wt, 16, 3, n0, n1) != 0) break; - memcpy(f0, n0, sizeof(n0)); - memcpy(f1, n1, sizeof(n1)); - } - } - memcpy(out, best, 16); -} - -/* Reads texel (x, y) of a pixel surface slice as RGBA8 / RGB half. */ -static void yapf__texel_rgba8(const yapf_texture_t *t, const uint8_t *src, uint32_t w, - uint32_t h, uint32_t x, uint32_t y, uint8_t *o) -{ - if (x >= w) x = w - 1; /* edge blocks repeat the last texel */ - if (y >= h) y = h - 1; - const uint8_t *s = src + ((size_t)y * w + x) * t->channels; - switch (t->channels) { - case 1: o[0] = o[1] = o[2] = s[0]; o[3] = 255; break; - case 2: o[0] = o[1] = o[2] = s[0]; o[3] = s[1]; break; - case 3: o[0] = s[0]; o[1] = s[1]; o[2] = s[2]; o[3] = 255; break; - default: memcpy(o, s, 4); break; - } -} - -static void yapf__texel_half(const yapf_texture_t *t, const uint8_t *src, uint32_t w, - uint32_t h, uint32_t x, uint32_t y, uint16_t *o) -{ - if (x >= w) x = w - 1; - if (y >= h) y = h - 1; - size_t sb = yapf__sbytes(t->sample); - const uint8_t *s = src + ((size_t)y * w + x) * t->channels * sb; - for (int c = 0; c < 3; c++) { - int k = t->channels >= 3 ? c : 0; - uint32_t v = yapf__get_sample(s + (size_t)k * sb, t->sample); - if (t->sample == YAPF_SAMPLE_F16) { o[c] = (uint16_t)v; continue; } - float f; - if (t->sample == YAPF_SAMPLE_F32) memcpy(&f, &v, 4); - else f = t->sample == YAPF_SAMPLE_U16 ? (float)v / 65535.0f : (float)v / 255.0f; - o[c] = yapf_float_to_half(f); - } -} - -int yapf_tex_compress(const yapf_texture_t *src, uint8_t format, yapf_texture_t **out) { - uint32_t S; - if (!out) return YAPF_ERR_INVALID; - *out = NULL; - if (yapf__tex_check(src, &S) != 0 || src->payload != YAPF_PAYLOAD_PIXELS || !src->data) - return YAPF_ERR_INVALID; - int hdr = format == YAPF_GPU_BC6H; - if (format != YAPF_GPU_BC1 && format != YAPF_GPU_BC3 && format != YAPF_GPU_BC4 && - format != YAPF_GPU_BC5 && format != YAPF_GPU_BC7 && !hdr) - return YAPF_ERR_UNSUPPORTED; - if (hdr == (src->sample == YAPF_SAMPLE_U8)) return YAPF_ERR_INVALID; - - yapf_texture_t d = *src; - d.payload = YAPF_PAYLOAD_BLOCKS; - d.format = format; - d.sample = hdr ? YAPF_SAMPLE_F16 : YAPF_SAMPLE_U8; - d.channels = format == YAPF_GPU_BC4 ? 1 : format == YAPF_GPU_BC5 ? 2 : hdr ? 3 - : format == YAPF_GPU_BC3 ? 4 : (src->channels == 4 || src->channels == 2) ? 4 : 3; - for (int c = d.channels; c < 4; c++) d.channel_map[c] = YAPF_CH_DEFAULT; - d.linear_mask &= (uint8_t)((1u << d.channels) - 1); - if (d.normal && d.channels == 2) d.normal = (uint8_t)((d.normal & 3) | YAPF_NORMAL_XY); - yapf_texture_t *t = yapf_tex_create(&d); - if (!t) return YAPF_ERR_OOM; - for (uint32_t i = 0; i < src->note_count; i++) - if (yapf_tex_add_note(t, src->notes[i].tag, src->notes[i].data, src->notes[i].size) != YAPF_OK) { - yapf_tex_free(t); - return YAPF_ERR_OOM; - } - if (t->frames > 1 && src->frame_us) memcpy(t->frame_us, src->frame_us, t->frames * sizeof(uint32_t)); - - for (uint32_t s = 0; s < S; s++) { - uint32_t m = s % src->mip_levels, w, h, dd, nbx, nby, B; - yapf_tex_mip_size(src, m, &w, &h, &dd); - yapf__mip_blocks(t, m, &nbx, &nby, &B); - size_t slice = (size_t)w * h * src->channels * yapf__sbytes(src->sample); - uint8_t *o = (uint8_t *)t->data[s]; - for (uint32_t z = 0; z < dd; z++) { - const uint8_t *sl = (const uint8_t *)src->data[s] + z * slice; - for (uint32_t by = 0; by < nby; by++) - for (uint32_t bx = 0; bx < nbx; bx++, o += B) { - uint8_t px[16][4]; - uint16_t hx[16][3]; - for (int i = 0; i < 16; i++) { - uint32_t x = bx * 4 + (uint32_t)(i & 3), y = by * 4 + (uint32_t)(i >> 2); - if (hdr) yapf__texel_half(src, sl, w, h, x, y, hx[i]); - else yapf__texel_rgba8(src, sl, w, h, x, y, px[i]); - } - if (format == YAPF_GPU_BC4 || format == YAPF_GPU_BC5) { - /* raw channels, not the gray expansion */ - for (int k = 0; k < (format == YAPF_GPU_BC5 ? 2 : 1); k++) { - uint8_t v[16]; - for (int i = 0; i < 16; i++) { - uint32_t x = bx * 4 + (uint32_t)(i & 3), y = by * 4 + (uint32_t)(i >> 2); - if (x >= w) x = w - 1; - if (y >= h) y = h - 1; - int c = k < src->channels ? k : 0; - v[i] = sl[((size_t)y * w + x) * src->channels + c]; - } - yapf__bc4_encode(v, o + 8 * k); - } - } else if (format == YAPF_GPU_BC1) { - yapf__bc1_encode((const uint8_t (*)[4])px, o, 0); - } else if (format == YAPF_GPU_BC3) { - uint8_t a[16]; - for (int i = 0; i < 16; i++) a[i] = px[i][3]; - yapf__bc4_encode(a, o); - yapf__bc1_encode((const uint8_t (*)[4])px, o + 8, 1); - } else if (format == YAPF_GPU_BC7) { - yapf__bc7_encode((const uint8_t (*)[4])px, o); - } else { - yapf__bc6_encode((const uint16_t (*)[3])hx, o); - } - } - } - } - *out = t; - return YAPF_OK; -} - -/* ======================================================================== - * Mip generation - * ======================================================================== */ - -/* x^2.4 for x in [0, 1] without libm: x² · x^0.4, x^0.4 by Newton on - * y^5 = x². */ -static double yapf__pow24(double x) { - if (x <= 0) return 0; - double a = x * x, y = 1.0; - for (int i = 0; i < 60; i++) { - double y4 = y * y * y * y, ny = y - (y4 * y - a) / (5.0 * y4); - if (ny == y) break; - y = ny; - } - return x * x * y; -} - -static double yapf__srgb_to_lin(double v) { - return v <= 0.04045 ? v / 12.92 : yapf__pow24((v + 0.055) / 1.055); -} - -/* 8-bit sRGB: code → linear, and the linear thresholds halfway between - * codes, so linear → code rounds exactly as in sRGB space. */ -typedef struct { float lin[256], mid[255]; } yapf__srgb_tab; - -static void yapf__srgb_init(yapf__srgb_tab *t) { - for (int i = 0; i < 256; i++) t->lin[i] = (float)yapf__srgb_to_lin(i / 255.0); - for (int i = 0; i < 255; i++) t->mid[i] = (float)yapf__srgb_to_lin((i + 0.5) / 255.0); -} - -static float yapf__lin_to_srgb(const yapf__srgb_tab *t, float v) { - int lo = 0, hi = 255; /* first code whose mid >= v */ - while (lo < hi) { - int m = (lo + hi) / 2; - if (t->mid[m] < v) lo = m + 1; else hi = m; - } - return (float)lo / 255.0f; -} - -/* Index of the alpha channel, or -1. */ -static int yapf__alpha_channel(const yapf_texture_t *t) { - for (int c = 0; c < t->channels; c++) - if (t->channel_map[c] == YAPF_CH_ALPHA || t->channel_map[c] == YAPF_CH_OPACITY) return c; - if (t->channel_map[t->channels - 1] == YAPF_CH_DEFAULT && (t->channels == 2 || t->channels == 4)) - return t->channels - 1; - return -1; -} - -static float yapf__load_f(const yapf_texture_t *t, const uint8_t *p) { - uint32_t v = yapf__get_sample(p, t->sample); - switch (t->sample) { - case YAPF_SAMPLE_U8: return (float)v / 255.0f; - case YAPF_SAMPLE_U16: return (float)v / 65535.0f; - case YAPF_SAMPLE_F16: return yapf_half_to_float((uint16_t)v); - default: { float f; memcpy(&f, &v, 4); return f; } - } -} - -static void yapf__store_f(const yapf_texture_t *t, uint8_t *p, float f) { - uint32_t v; - switch (t->sample) { - case YAPF_SAMPLE_U8: v = (uint32_t)yapf__clampi(f * 255.0f, 0, 255); break; - case YAPF_SAMPLE_U16: v = (uint32_t)yapf__clampi(f * 65535.0f, 0, 65535); break; - case YAPF_SAMPLE_F16: v = yapf_float_to_half(f); break; - default: memcpy(&v, &f, 4); break; - } - yapf__put_sample(p, t->sample, v); -} - -/* Share of alpha values above ref after scaling by k, measured on the - * values as they will be stored (q = 255 or 65535; 0 for floats). */ -static double yapf__coverage(const float *a, size_t n, float ref, float k, float q) { - size_t c = 0; - for (size_t i = 0; i < n; i++) { - float v = a[i] * k; - if (q > 0) { - v = v > 1.0f ? q : (float)(int)(v * q + 0.5f); - if (v > ref * q) c++; - } else if (v > ref) { - c++; - } - } - return n ? (double)c / (double)n : 0.0; -} - -int yapf_tex_build_mips(yapf_texture_t *tex, uint32_t levels, uint8_t alpha_ref) { - uint32_t S; - if (!tex || !tex->internal_ || yapf__tex_check(tex, &S) != 0) return YAPF_ERR_INVALID; - if (tex->payload != YAPF_PAYLOAD_PIXELS) return YAPF_ERR_INVALID; - uint32_t full = 1; - while (full < YAPF_MAX_MIPS && - ((tex->width >> full) || (tex->height >> full) || - (tex->shape == YAPF_SHAPE_VOLUME && (tex->depth >> full)))) - full++; - if (levels == 0 || levels > full) levels = full; - - int ach = yapf__alpha_channel(tex); - if (alpha_ref && ach < 0) return YAPF_ERR_INVALID; - int srgb[4]; - for (int c = 0; c < tex->channels; c++) - srgb[c] = (tex->flags & YAPF_FLAG_SRGB) && tex->sample == YAPF_SAMPLE_U8 && c != ach && - !(tex->linear_mask & (1u << c)) && - (tex->transfer == YAPF_TRANSFER_UNSPECIFIED || tex->transfer == YAPF_TRANSFER_SRGB); - - yapf__srgb_tab *st = (yapf__srgb_tab *)malloc(sizeof(yapf__srgb_tab)); - if (!st) return YAPF_ERR_OOM; - yapf__srgb_init(st); - - yapf_texture_t d = *tex; - d.mip_levels = (uint8_t)levels; - uint32_t NS = yapf_tex_surface_count(&d); - void **data = (void **)calloc(NS, sizeof(void *)); - if (!data) { free(st); return YAPF_ERR_OOM; } - int rc = YAPF_OK; - size_t sb = yapf__sbytes(tex->sample), ch = tex->channels; - float qs = tex->sample == YAPF_SAMPLE_U8 ? 255.0f : tex->sample == YAPF_SAMPLE_U16 ? 65535.0f : 0.0f; - - for (uint32_t base = 0; base < NS && rc == YAPF_OK; base += levels) { - uint32_t old = base / levels * tex->mip_levels; /* mip 0 of this face in tex */ - data[base] = tex->data[old]; - tex->data[old] = NULL; - float *alpha0 = NULL; - double target = 0; - for (uint32_t m = 1; m < levels && rc == YAPF_OK; m++) { - uint32_t pw, ph, pd, w, h, dd; - yapf_tex_mip_size(&d, m - 1, &pw, &ph, &pd); - yapf_tex_mip_size(&d, m, &w, &h, &dd); - const uint8_t *src = (const uint8_t *)data[base + m - 1]; - uint8_t *dst = (uint8_t *)malloc(yapf_tex_surface_bytes(&d, m)); - float *alpha = alpha_ref ? (float *)malloc((size_t)w * h * dd * sizeof(float)) : NULL; - if (!dst || (alpha_ref && !alpha)) { free(dst); free(alpha); rc = YAPF_ERR_OOM; break; } - data[base + m] = dst; - if (alpha_ref && m == 1) { - size_t n0 = (size_t)pw * ph * pd; - alpha0 = (float *)malloc(n0 * sizeof(float)); - if (!alpha0) { free(alpha); rc = YAPF_ERR_OOM; break; } - for (size_t i = 0; i < n0; i++) alpha0[i] = yapf__load_f(tex, src + (i * ch + ach) * sb); - target = yapf__coverage(alpha0, n0, alpha_ref / 255.0f, 1.0f, qs); - } - for (uint32_t z = 0; z < dd; z++) - for (uint32_t y = 0; y < h; y++) - for (uint32_t x = 0; x < w; x++) { - uint32_t xs[2] = { 2 * x < pw ? 2 * x : pw - 1, 2 * x + 1 < pw ? 2 * x + 1 : pw - 1 }; - uint32_t ys[2] = { 2 * y < ph ? 2 * y : ph - 1, 2 * y + 1 < ph ? 2 * y + 1 : ph - 1 }; - uint32_t zs[2] = { 2 * z < pd ? 2 * z : pd - 1, 2 * z + 1 < pd ? 2 * z + 1 : pd - 1 }; - int nz = d.shape == YAPF_SHAPE_VOLUME ? 2 : 1; - size_t o = (((size_t)z * h + y) * w + x) * ch; - for (size_t c = 0; c < ch; c++) { - float sum = 0; - for (int k = 0; k < nz; k++) - for (int j = 0; j < 2; j++) - for (int i = 0; i < 2; i++) { - size_t q = (((size_t)zs[k] * ph + ys[j]) * pw + xs[i]) * ch + c; - sum += srgb[c] ? st->lin[src[q]] : yapf__load_f(tex, src + q * sb); - } - float v = sum / (float)(4 * nz); - if (srgb[c]) v = yapf__lin_to_srgb(st, v); - if (alpha && (int)c == ach) alpha[o / ch] = v; - yapf__store_f(tex, dst + (o + c) * sb, v); - } - } - if (alpha) { - /* scale alpha so coverage at alpha_ref matches mip 0 */ - size_t n = (size_t)w * h * dd; - float lo = 0.0f, hi = 8.0f, ref = alpha_ref / 255.0f; - for (int it = 0; it < 20; it++) { - float mid = 0.5f * (lo + hi); - if (yapf__coverage(alpha, n, ref, mid, qs) < target) lo = mid; else hi = mid; - } - double clo = yapf__coverage(alpha, n, ref, lo, qs), chi = yapf__coverage(alpha, n, ref, hi, qs); - float k = (target - clo <= chi - target) ? lo : hi; /* nearer bound */ - for (size_t i = 0; i < n; i++) { - float v = alpha[i] * k; - if (tex->sample != YAPF_SAMPLE_F16 && tex->sample != YAPF_SAMPLE_F32 && v > 1.0f) v = 1.0f; - yapf__store_f(tex, dst + (i * ch + ach) * sb, v); - } - free(alpha); - } - } - free(alpha0); - } - if (rc != YAPF_OK) { - for (uint32_t s = 0; s < NS; s++) { - if (s % levels == 0) { /* give mip 0 back */ - if (data[s]) tex->data[s / levels * tex->mip_levels] = data[s]; - } else { - free(data[s]); - } - } - free(data); - free(st); - return rc; - } - free(st); - for (uint32_t s = 0; s < S; s++) free(tex->data[s]); /* old mips (mip 0 moved) */ - free(tex->data); - tex->data = data; - tex->mip_levels = (uint8_t)levels; - int any_srgb = 0; - for (int c = 0; c < tex->channels; c++) any_srgb |= srgb[c]; - tex->mip_filter = (uint8_t)(YAPF_MIP_BOX | (any_srgb ? YAPF_MIP_LINEAR_LIGHT : 0)); - if (alpha_ref) { tex->flags |= YAPF_FLAG_COVERAGE; tex->alpha_ref = alpha_ref; } - else tex->flags &= (uint8_t)~YAPF_FLAG_COVERAGE; - return YAPF_OK; -} - -/* ======================================================================== - * Previews - * ======================================================================== */ - -/* Linear 0..1 → sRGB code, exact to the 8-bit rounding (thresholds). */ -static uint8_t yapf__lin_to_code(const yapf__srgb_tab *t, float v) { - if (!(v > 0.0f)) return 0; /* also NaN */ - if (v >= 1.0f) return 255; - return (uint8_t)(yapf__lin_to_srgb(t, v) * 255.0f + 0.5f); -} - -int yapf_tex_to_rgba8(const yapf_texture_t *tex, uint32_t surface, uint32_t slice, uint8_t *out) { - uint32_t S; - if (!out || yapf__tex_check(tex, &S) != 0 || surface >= S || !tex->data || !tex->data[surface]) - return YAPF_ERR_INVALID; - uint32_t m = surface % tex->mip_levels, w, h, d; - yapf_tex_mip_size(tex, m, &w, &h, &d); - if (slice >= d) return YAPF_ERR_INVALID; - size_t n = (size_t)w * h; - const uint8_t *src = (const uint8_t *)tex->data[surface] + yapf_tex_surface_bytes(tex, m) / d * slice; - - int ch = tex->channels, sample = tex->sample; - uint16_t *half = NULL; - if (tex->payload == YAPF_PAYLOAD_BLOCKS) { - if (tex->format != YAPF_GPU_BC6H && tex->format != YAPF_GPU_BC6H_SF) { - int rc = yapf_blocks_decode(tex->format, src, w, h, out); - if (rc == YAPF_OK && tex->channels == 3) /* BC1 / BC7 without alpha */ - for (size_t i = 0; i < n; i++) out[i * 4 + 3] = 255; - return rc; - } - half = (uint16_t *)malloc(n * 3 * sizeof(uint16_t)); - if (!half) return YAPF_ERR_OOM; - yapf_blocks_decode(tex->format, src, w, h, half); - src = (const uint8_t *)half; - ch = 3; - sample = YAPF_SAMPLE_F16; - } - yapf__srgb_tab *st = NULL; - if (sample == YAPF_SAMPLE_F16 || sample == YAPF_SAMPLE_F32) { - st = (yapf__srgb_tab *)malloc(sizeof(yapf__srgb_tab)); - if (!st) { free(half); return YAPF_ERR_OOM; } - yapf__srgb_init(st); - } - size_t sb = yapf__sbytes(sample); - for (size_t i = 0; i < n; i++) { - uint8_t v[4] = { 0, 0, 0, 255 }; - for (int c = 0; c < ch; c++) { - uint32_t x = yapf__get_sample(src + (i * ch + c) * sb, sample); - int alpha = (ch == 2 && c == 1) || (ch == 4 && c == 3); - uint8_t b; - if (sample == YAPF_SAMPLE_U8) b = (uint8_t)x; - else if (sample == YAPF_SAMPLE_U16) b = (uint8_t)((x + 128) / 257); - else { - float f; - if (sample == YAPF_SAMPLE_F16) f = yapf_half_to_float((uint16_t)x); - else memcpy(&f, &x, 4); - b = alpha ? (uint8_t)yapf__clampi(f * 255.0f, 0, 255) : yapf__lin_to_code(st, f); - } - v[ch <= 2 ? (c == 0 ? 0 : 3) : c] = b; - } - if (ch <= 2) v[1] = v[2] = v[0]; - memcpy(out + i * 4, v, 4); - } - free(st); - free(half); - return YAPF_OK; -} diff --git a/yapf.h b/yapf.h deleted file mode 100644 index fdca43b..0000000 --- a/yapf.h +++ /dev/null @@ -1,625 +0,0 @@ -/* - * yapf.h — Yet Another Picture Format - * Public API and format specification. - * - * Copyright 2026 Nexoniarz - * - * Licensed under the Apache License, Version 2.0 (the "License"); - * you may not use this file except in compliance with the License. - * You may obtain a copy of the License at - * - * http://www.apache.org/licenses/LICENSE-2.0 - * - * Unless required by applicable law or agreed to in writing, software - * distributed under the License is distributed on an "AS IS" BASIS, - * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. - * See the License for the specific language governing permissions and - * limitations under the License. - * - * ------------------------------------------------------------------------- - * - * YAPF — lossless, GPU-ready image format. - * - * Designed for single-core decode speed. Everything is byte aligned: - * no bit reader, no entropy coder, no context model. Per row the decoder - * dispatches one filter; per 8 samples it reads a 4-bit control code and - * exactly w bytes of payload, unpacked with one 64-bit load and shifts. - * The encoder does the hard work (filter search, colour transform choice, - * optimal control codes); the decoder only follows instructions. - * - * 1. Per tile: YCoCg-R or subtract-green colour transform, 8-bit modular - * 2. Per band of 8 rows: one of 12 row filters - * 3. Residuals in groups of 8, each group at its bit width (0–8); - * 4-bit control codes, with codes that repeat the previous width - * 4. Independent 64×64 tiles with a size table → random access and - * optional parallel decode - * - * The file carries GPU metadata (format hint, mip levels, flags) so a - * loader can upload the decoded buffer straight to a texture without any - * additional transcoding step. - * - * Two versions exist. Version 1 (below) is a single 8-bit 2D image with - * optional mips. Version 2 is the texture container: GPU block payloads - * (BCn / ETC2 / ASTC), 16-bit and float samples, cubemaps, arrays and - * volumes, channel meanings, per-tile checksums, optional entropy-coded - * planes, notes (metadata) and animation frames. Its complete - * specification is docs/FORMAT.md; a summary follows the v1 spec. - * - * ========================================================================= - * FILE FORMAT (version 1) - * ========================================================================= - * - * All multi-byte integers are little-endian. All arithmetic on samples - * is mod 256. - * - * ┌─────────────────────────────────────────────────────────────────────┐ - * │ HEADER — 20 bytes │ - * ├────────┬──────┬────────────────────────────────────────────────────┤ - * │ Offset │ Size │ Field │ - * ├────────┼──────┼────────────────────────────────────────────────────┤ - * │ 0x00 │ 4 │ Magic: "YAPF" │ - * │ 0x04 │ 1 │ Version: 1 │ - * │ 0x05 │ 1 │ Channels: 1 gray / 2 gray+A / 3 RGB / 4 RGBA │ - * │ 0x06 │ 1 │ GPU format hint (YAPF_GPU_* constant) │ - * │ 0x07 │ 1 │ Mip levels (1 = base only, max 16) │ - * │ 0x08 │ 1 │ Flags (see YAPF_FLAG_* bitmask) │ - * │ 0x09 │ 3 │ Reserved (write 0, ignore on read) │ - * │ 0x0C │ 4 │ Base width (uint32, pixels) │ - * │ 0x10 │ 4 │ Base height (uint32, pixels) │ - * └────────┴──────┴────────────────────────────────────────────────────┘ - * - * ┌─────────────────────────────────────────────────────────────────────┐ - * │ MIP INDEX — 8 bytes × mip_levels, immediately after header │ - * ├────────┬──────┬────────────────────────────────────────────────────┤ - * │ +0 │ 4 │ Byte offset of mip data from start of file (uint32) │ - * │ +4 │ 4 │ Byte size of mip data (uint32) │ - * └────────┴──────┴────────────────────────────────────────────────────┘ - * Mip m has size max(1, width >> m) × max(1, height >> m). - * - * ┌─────────────────────────────────────────────────────────────────────┐ - * │ MIP LEVEL DATA │ - * ├─────────────────────────────────────────────────────────────────────┤ - * │ Pixels are divided into 64×64 tiles in row-major order; the last │ - * │ column / row of tiles may be smaller (no padding). │ - * │ │ - * │ uint32 tile_size[tile_count] byte size of each tile │ - * │ tile data, back to back │ - * │ │ - * │ TILE │ - * │ 1 byte header │ - * │ 0x80 stored: tile_w × tile_h × channels raw bytes │ - * │ follow, interleaved, in the original channel order │ - * │ otherwise coded: │ - * │ bits 0–3 bit c set = plane c is constant (only bits below │ - * │ the channel count may be set) │ - * │ bit 4 colour transform: 0 = YCoCg-R, 1 = subtract-green │ - * │ (RGB / RGBA only; must be 0 for gray) │ - * │ bits 5–7 must be 0 │ - * │ coded tiles then hold one value byte per constant plane, and a │ - * │ plane payload per other plane, both in plane order. The tile │ - * │ must end exactly where its last payload ends. │ - * │ │ - * │ PLANES │ - * │ gray / gray+A: the channels as stored. │ - * │ RGB(A), YCoCg-R (>> is an arithmetic shift of the value as int8):│ - * │ planes Y, Co, Cg (+ A) │ - * │ forward: o = R − B; t = B + (o >> 1); q = G − t; │ - * │ Y = t + (q >> 1); Co = o + 128; Cg = q + 128 │ - * │ inverse: o = Co − 128; q = Cg − 128; t = Y − (q >> 1); │ - * │ G = q + t; B = t − (o >> 1); R = B + o │ - * │ RGB(A), subtract-green: │ - * │ planes G, R − G + 128, B − G + 128 (+ A) │ - * │ │ - * │ PLANE PAYLOAD │ - * │ filter[ceil(tile_h / 8)] one byte per band of 8 rows. │ - * │ L / A / D / AR = left, above, above-left, above-right sample; │ - * │ samples outside the tile read as 0, except that AR in the │ - * │ last column reads as A. │ - * │ 0 Left pred = L │ - * │ 1 Gradient pred = L + A − D │ - * │ 2 Up-right pred = AR │ - * │ 3 Up-average pred = (A + AR) >> 1 (not mod 256) │ - * │ 16 + k−1 Up k pred = sample k rows above, k = 1..8 │ - * │ control nibbles, low nibble of each byte first, covering │ - * │ exactly ceil(tile_w × tile_h / 8) groups of 8 consecutive │ - * │ residuals in raster order: │ - * │ 0–8 one group of width w │ - * │ 9–15 2, 3, 4, 8, 16, 32 or 64 groups at the width of │ - * │ the last 0–8 code in this plane (0 if none yet) │ - * │ an odd nibble count is padded with a zero high nibble │ - * │ group data: w bytes per group, the 8 values packed little- │ - * │ endian, value i in bits [i·w, i·w + w) │ - * │ Residual r = (sample − pred) mod 256 is stored folded: │ - * │ v = (r << 1) ^ (r >> 7) (0, −1, 1, −2, … → 0, 1, 2, 3, …) │ - * │ The last group is padded with zero values. │ - * └─────────────────────────────────────────────────────────────────────┘ - * - * GPU FORMAT HINTS (YAPF_GPU_* values for the gpu_format field) - * ────────────────────────────────────────────────────────────── - * 0x00 RGBA8 GL_RGBA8 / VK_FORMAT_R8G8B8A8_UNORM - * 0x01 RGB8 GL_RGB8 / VK_FORMAT_R8G8B8_UNORM - * 0x02 RG8 GL_RG8 / VK_FORMAT_R8G8_UNORM - * 0x03 R8 GL_R8 / VK_FORMAT_R8_UNORM - * 0x04 SRGB8_A8 GL_SRGB8_ALPHA8 - * 0x05 SRGB8 GL_SRGB8 - * - * FLAGS (YAPF_FLAG_* bitmask for the flags field) - * ───────────────────────────────────────────────── - * bit 0 PREMULT_ALPHA alpha is premultiplied into RGB - * bit 1 SRGB pixels are in sRGB gamma (informational only) - * bit 2 COVERAGE (v2) mips keep alpha-test coverage at alpha_ref - * - * ========================================================================= - * FILE FORMAT (version 2) — summary; the full text is docs/FORMAT.md - * ========================================================================= - * - * HEADER (64 bytes) - * 0x00 "YAPF" 0x04 version 2 0x05 channels 0x06 format - * 0x07 mips 0x08 flags 0x09 payload 0x0A sample 0x0B shape - * 0x0C width u32 0x10 height u32 0x14 depth u32 - * 0x18 layers u16 0x1A frames u16 0x1C needs u32 - * 0x20 channel map[4] 0x24 linear mask 0x25 normal 0x26 primaries - * 0x27 transfer 0x28 mip filter 0x29 alpha ref 0x2A loop count u16 - * 0x2C notes size u32 0x30 file size u64 - * 0x38 tables check u32 (yapf-sum of bytes [0x40, data start)) - * 0x3C header check u32 (yapf-sum of bytes [0, 0x3C)) - * SURFACE TABLE 16 bytes per surface: offset u64, size u32, - * tile-table check u32. Surface s of (frame, layer, - * face, mip) is ((frame·layers + layer)·faces + face)·mips + mip - * FRAME TABLE u32 duration in µs per frame (only when frames > 1) - * NOTES tag[4], length u32, bytes — repeated - * SURFACE DATA smallest mips first, so a file prefix is a complete - * low-resolution texture. Per surface: u32 book size, - * code book (Huffman tables by slot and context, only - * with entropy coding), tile table (size u32 with bit 31 = - * packed, yapf-sum u32 per tile), then the tiles. Pixel - * tiles are the v1 tiles plus byte planes for wide samples - * and entropy-coded planes; block tiles hold 16 × 16 GPU - * blocks, raw or packed lane by lane. - * NEEDS a decoder must refuse a file with a needs bit it does - * not implement; everything else may be ignored safely. - */ - -#ifndef YAPF_H -#define YAPF_H - -#include -#include - -/* ── GPU format hints ────────────────────────────────────────────────── */ - -#define YAPF_GPU_RGBA8 0x00 -#define YAPF_GPU_RGB8 0x01 -#define YAPF_GPU_RG8 0x02 -#define YAPF_GPU_R8 0x03 -#define YAPF_GPU_SRGB8_A8 0x04 -#define YAPF_GPU_SRGB8 0x05 -/* v2 pixel hints for wide samples */ -#define YAPF_GPU_RGBA16 0x06 -#define YAPF_GPU_RGB16 0x07 -#define YAPF_GPU_RG16 0x08 -#define YAPF_GPU_R16 0x09 -#define YAPF_GPU_RGBA16F 0x0A -#define YAPF_GPU_RGB16F 0x0B -#define YAPF_GPU_RG16F 0x0C -#define YAPF_GPU_R16F 0x0D -#define YAPF_GPU_RGBA32F 0x0E -#define YAPF_GPU_RGB32F 0x0F -#define YAPF_GPU_RG32F 0x10 -#define YAPF_GPU_R32F 0x11 -/* v2 GPU block formats (payload = YAPF_PAYLOAD_BLOCKS). The sRGB flag - * selects the _SRGB variant where the API has one. */ -#define YAPF_GPU_BC1 0x40 /* RGB(A1), 8 bytes per 4×4 */ -#define YAPF_GPU_BC2 0x41 /* RGBA, explicit 4-bit alpha */ -#define YAPF_GPU_BC3 0x42 /* RGBA */ -#define YAPF_GPU_BC4 0x43 /* R */ -#define YAPF_GPU_BC4_SNORM 0x44 -#define YAPF_GPU_BC5 0x45 /* RG (normal maps) */ -#define YAPF_GPU_BC5_SNORM 0x46 -#define YAPF_GPU_BC6H 0x47 /* RGB half float, unsigned */ -#define YAPF_GPU_BC6H_SF 0x48 /* RGB half float, signed */ -#define YAPF_GPU_BC7 0x49 /* RGB(A) */ -#define YAPF_GPU_ETC2_RGB8 0x50 -#define YAPF_GPU_ETC2_RGB8A1 0x51 -#define YAPF_GPU_ETC2_RGBA8 0x52 -#define YAPF_GPU_EAC_R11 0x53 -#define YAPF_GPU_EAC_R11_SNORM 0x54 -#define YAPF_GPU_EAC_RG11 0x55 -#define YAPF_GPU_EAC_RG11_SNORM 0x56 -#define YAPF_GPU_ASTC_4x4 0x60 /* ASTC: 0x60 + footprint index */ -#define YAPF_GPU_ASTC_5x4 0x61 -#define YAPF_GPU_ASTC_5x5 0x62 -#define YAPF_GPU_ASTC_6x5 0x63 -#define YAPF_GPU_ASTC_6x6 0x64 -#define YAPF_GPU_ASTC_8x5 0x65 -#define YAPF_GPU_ASTC_8x6 0x66 -#define YAPF_GPU_ASTC_8x8 0x67 -#define YAPF_GPU_ASTC_10x5 0x68 -#define YAPF_GPU_ASTC_10x6 0x69 -#define YAPF_GPU_ASTC_10x8 0x6A -#define YAPF_GPU_ASTC_10x10 0x6B -#define YAPF_GPU_ASTC_12x10 0x6C -#define YAPF_GPU_ASTC_12x12 0x6D - -/* ── Flags ───────────────────────────────────────────────────────────── */ - -#define YAPF_FLAG_PREMULT_ALPHA 0x01 -#define YAPF_FLAG_SRGB 0x02 -#define YAPF_FLAG_COVERAGE 0x04 /* v2: mips preserve alpha-test coverage */ - -/* ── Channel constants ───────────────────────────────────────────────── */ - -#define YAPF_CHANNELS_GRAY 1 -#define YAPF_CHANNELS_GRAY_ALPHA 2 -#define YAPF_CHANNELS_RGB 3 -#define YAPF_CHANNELS_RGBA 4 - -/* ── Return codes ────────────────────────────────────────────────────── */ - -#define YAPF_OK 0 -#define YAPF_ERR_INVALID -1 -#define YAPF_ERR_IO -2 -#define YAPF_ERR_OOM -3 -#define YAPF_ERR_CORRUPT -4 -#define YAPF_ERR_UNSUPPORTED -5 /* valid file, feature this decoder lacks */ -#define YAPF_ERR_CHECKSUM -6 /* a yapf-sum does not match */ -#define YAPF_ERR_TRUNCATED -7 /* data lies beyond the bytes available yet */ - -/* ── Limits ──────────────────────────────────────────────────────────── */ - -#define YAPF_MAX_DIM 65535u -#define YAPF_MAX_MIPS 16u -#define YAPF_TILE_SIZE 64u -#define YAPF_BLOCK_TILE 16u /* v2 block tiles: 16 × 16 GPU blocks */ - -/* ── Image descriptor ────────────────────────────────────────────────── */ - -typedef struct { - uint32_t width; - uint32_t height; - uint8_t channels; /* 1–4 */ - uint8_t gpu_format; /* YAPF_GPU_* */ - uint8_t flags; /* YAPF_FLAG_* bitmask */ - uint8_t mip_levels; /* number of mip levels stored (1 = base only) */ - uint8_t *pixels; /* base-level pixels, malloc-owned */ - uint8_t **mips; /* mips[0]=base alias, mips[1..mip_levels-1] owned */ -} yapf_image_t; - -/* ── Version 2: texture description ──────────────────────────────────── */ - -/* payload */ -#define YAPF_PAYLOAD_PIXELS 0 /* lossless YAPF tiles */ -#define YAPF_PAYLOAD_BLOCKS 1 /* GPU blocks, uploaded as they are */ - -/* sample: how one channel value is stored (pixel payload); for block - * payloads, the type of the decoded texels (U8, or F16 for BC6H) */ -#define YAPF_SAMPLE_U8 0 -#define YAPF_SAMPLE_U16 1 -#define YAPF_SAMPLE_F16 2 /* IEEE half, as uint16_t bits */ -#define YAPF_SAMPLE_F32 3 - -/* shape */ -#define YAPF_SHAPE_2D 0 -#define YAPF_SHAPE_CUBE 1 /* 6 faces: +X −X +Y −Y +Z −Z; with layers - > 1 a cube array */ -#define YAPF_SHAPE_VOLUME 2 /* depth slices; mips halve depth too */ - -/* needs: features a decoder must implement to read the file */ -#define YAPF_NEED_WIDE 0x01 /* sample other than U8 (pixel payload) */ -#define YAPF_NEED_BLOCKS 0x02 /* GPU block payload */ -#define YAPF_NEED_ENTROPY 0x04 /* code books: entropy planes, packed blocks */ -#define YAPF_NEED_LAYOUT 0x08 /* cube, volume or layers > 1 */ -#define YAPF_NEED_FRAMES 0x10 /* frames > 1 */ -#define YAPF_NEED_ALL 0x1F /* everything this library implements */ - -/* channel meanings (channel_map[c]); 0 = default for the channel count */ -#define YAPF_CH_DEFAULT 0 -#define YAPF_CH_RED 1 -#define YAPF_CH_GREEN 2 -#define YAPF_CH_BLUE 3 -#define YAPF_CH_ALPHA 4 -#define YAPF_CH_LUMA 5 -#define YAPF_CH_NORMAL_X 6 -#define YAPF_CH_NORMAL_Y 7 -#define YAPF_CH_NORMAL_Z 8 -#define YAPF_CH_ROUGHNESS 9 -#define YAPF_CH_GLOSS 10 /* smoothness = 1 − roughness */ -#define YAPF_CH_METALNESS 11 -#define YAPF_CH_OCCLUSION 12 /* ambient occlusion */ -#define YAPF_CH_HEIGHT 13 -#define YAPF_CH_SPECULAR 14 -#define YAPF_CH_EMISSIVE 15 -#define YAPF_CH_OPACITY 16 /* alpha-test / cut-out mask */ -#define YAPF_CH_MASK 17 /* generic mask */ -#define YAPF_CH_CAVITY 18 -#define YAPF_CH_THICKNESS 19 -#define YAPF_CH_ID 20 /* material or object id */ -#define YAPF_CH_UNUSED 255 - -/* normal: bits 0–1 convention, bits 2–3 encoding */ -#define YAPF_NORMAL_NONE 0x00 -#define YAPF_NORMAL_GL 0x01 /* +Y up (OpenGL, Blender, Unity) */ -#define YAPF_NORMAL_DX 0x02 /* −Y (DirectX, Unreal) */ -#define YAPF_NORMAL_XYZ 0x00 -#define YAPF_NORMAL_XY 0x04 /* Z = sqrt(1 − x² − y²) is reconstructed */ -#define YAPF_NORMAL_OCT 0x08 /* octahedral */ - -/* primaries / transfer (0 = unspecified: the sRGB flag decides) */ -#define YAPF_PRIMARIES_UNSPECIFIED 0 -#define YAPF_PRIMARIES_BT709 1 /* = sRGB */ -#define YAPF_PRIMARIES_DISPLAY_P3 2 -#define YAPF_PRIMARIES_BT2020 3 -#define YAPF_PRIMARIES_ACES_AP0 4 -#define YAPF_PRIMARIES_ACES_AP1 5 /* ACEScg */ -#define YAPF_PRIMARIES_ADOBE_RGB 6 - -#define YAPF_TRANSFER_UNSPECIFIED 0 -#define YAPF_TRANSFER_SRGB 1 -#define YAPF_TRANSFER_LINEAR 2 -#define YAPF_TRANSFER_GAMMA22 3 -#define YAPF_TRANSFER_PQ 4 /* SMPTE ST 2084 */ -#define YAPF_TRANSFER_HLG 5 -#define YAPF_TRANSFER_BT1886 6 /* gamma 2.4 */ - -/* mip filter (bits 0–6) | YAPF_MIP_LINEAR_LIGHT */ -#define YAPF_MIP_UNKNOWN 0 -#define YAPF_MIP_BOX 1 -#define YAPF_MIP_TENT 2 -#define YAPF_MIP_KAISER 3 -#define YAPF_MIP_LANCZOS 4 -#define YAPF_MIP_MITCHELL 5 -#define YAPF_MIP_AUTHORED 6 /* made by hand / by an external tool */ -#define YAPF_MIP_LINEAR_LIGHT 0x80 /* sRGB channels were filtered in linear light */ - -/* load flags */ -#define YAPF_LOAD_TRUST 0x01 /* skip checksum verification */ - -/* encode flags */ -#define YAPF_ENC_ENTROPY 0x01 /* allow entropy-coded planes and packed - blocks where they are smaller: ~10 % - smaller photos, ~3× smaller GPU blocks - on disk; slower to decode */ - -/* A note (metadata entry). Well-known tags: "AUTH" author, "LICN" - * licence, "SRCE" source, "TOOL" creating tool, "TITL" title, "DESC" - * description, "DATE" ISO 8601 date (all UTF-8 text); "ICCP" ICC profile; - * "ORNT" orientation (1 byte); "DPI " 2 × u32 milli-dots per inch; - * "CLL " 2 × u16 max content / max frame-average light level (cd/m²). - * Tags that start with a lowercase letter belong to applications. */ -typedef struct { - char tag[4]; - uint32_t size; - uint8_t *data; -} yapf_note_t; - -/* - * A version 2 texture. Surfaces are numbered - * s = ((frame × layers + layer) × faces + face) × mip_levels + mip - * (faces = 6 for cubes, else 1) and data[s] holds the whole surface: - * pixels: width_m × height_m × depth_m × channels samples, rows top to - * bottom, slices in order; samples in the native byte order - * (uint8_t, uint16_t, half bits as uint16_t, float); - * blocks: ceil(width_m / bw) × ceil(height_m / bh) blocks per slice, - * row-major — exactly what glCompressedTexImage / Vulkan take. - * width_m = max(1, width >> m), likewise height and (volumes) depth. - */ -typedef struct { - uint32_t width, height, depth; /* depth: volumes only, else 1 */ - uint16_t layers; /* array layers, >= 1 */ - uint16_t frames; /* animation frames, >= 1 */ - uint8_t shape; /* YAPF_SHAPE_* */ - uint8_t mip_levels; /* 1–16 */ - uint8_t payload; /* YAPF_PAYLOAD_* */ - uint8_t format; /* YAPF_GPU_*: block format, or hint */ - uint8_t sample; /* YAPF_SAMPLE_* */ - uint8_t channels; /* 1–4 */ - uint8_t flags; /* YAPF_FLAG_* */ - uint8_t channel_map[4]; /* YAPF_CH_* per channel */ - uint8_t linear_mask; /* bit c: channel c is linear even in - an sRGB image (e.g. alpha, masks) */ - uint8_t normal; /* YAPF_NORMAL_* */ - uint8_t primaries, transfer; /* YAPF_PRIMARIES_*, YAPF_TRANSFER_* */ - uint8_t mip_filter; /* YAPF_MIP_* */ - uint8_t alpha_ref; /* coverage reference (with COVERAGE) */ - uint16_t loop_count; /* animation loops, 0 = forever */ - uint32_t *frame_us; /* frames durations in µs, or NULL */ - uint32_t note_count; - yapf_note_t *notes; - void **data; /* one pointer per surface */ - void *internal_; /* library use: file tables, ownership */ -} yapf_texture_t; - -/* ── Public API ──────────────────────────────────────────────────────── */ - -#ifdef __cplusplus -extern "C" { -#endif - -/* - * yapf_load — decode a .yapf file. - * Returns NULL on any failure (bad magic, truncated data, OOM, I/O error). - * The returned image must be released with yapf_free(). - */ -yapf_image_t *yapf_load(const char *filename); - -/* - * yapf_load_memory — decode a .yapf file already in memory (e.g. from a - * game archive). Same ownership and failure rules as yapf_load(). - */ -yapf_image_t *yapf_load_memory(const void *buffer, size_t size); - -/* - * yapf_load_mt / yapf_load_memory_mt — same as above, but decode tiles on - * up to `threads` threads (0 = one per CPU core). Output is identical. - * Without thread support (YAPF_NO_THREADS, or an unknown platform) these - * decode on the calling thread. - */ -yapf_image_t *yapf_load_mt(const char *filename, int threads); -yapf_image_t *yapf_load_memory_mt(const void *buffer, size_t size, int threads); - -/* - * yapf_save — encode an image to disk. - * img->mip_levels controls how many levels are written; set to 1 to write - * only the base level. img->mips may be NULL when mip_levels == 1. - * Returns YAPF_OK or a negative YAPF_ERR_* code. - */ -int yapf_save(const char *filename, const yapf_image_t *img); - -/* - * yapf_encode — encode an image into memory. - * On success *out_data points to *out_size bytes of a complete .yapf file; - * release it with yapf_free_buffer(). Same rules and return codes as - * yapf_save() (no YAPF_ERR_IO). - */ -int yapf_encode(const yapf_image_t *img, void **out_data, size_t *out_size); - -/* yapf_free_buffer — release memory returned by yapf_encode(). NULL-safe. */ -void yapf_free_buffer(void *data); - -/* - * yapf_free — release all memory owned by an image returned by yapf_load(). - * NULL-safe. - */ -void yapf_free(yapf_image_t *img); - -/* - * The v1 functions above also read version 2 files that hold 8-bit pixels - * of a 2D, cube or array texture: they return frame 0, layer 0, face 0 - * with all its mips. yapf_save / yapf_encode always write version 1. - */ - -/* ── Version 2: textures ─────────────────────────────────────────────── */ - -/* - * yapf_tex_create — a library-owned texture with the description of - * `desc` (every field up to loop_count; notes, frame times and data are - * not copied) and zeroed storage for every surface. frame_us is - * allocated (zeroed) when frames > 1. NULL on invalid description / OOM. - */ -yapf_texture_t *yapf_tex_create(const yapf_texture_t *desc); - -/* yapf_tex_free — release a texture made by the library. NULL-safe. */ -void yapf_tex_free(yapf_texture_t *tex); - -/* Surface helpers. */ -uint32_t yapf_tex_faces(const yapf_texture_t *tex); /* 6 or 1 */ -uint32_t yapf_tex_surface_count(const yapf_texture_t *tex); -uint32_t yapf_tex_surface(const yapf_texture_t *tex, uint32_t frame, - uint32_t layer, uint32_t face, uint32_t mip); -void yapf_tex_mip_size(const yapf_texture_t *tex, uint32_t mip, - uint32_t *w, uint32_t *h, uint32_t *d); -size_t yapf_tex_surface_bytes(const yapf_texture_t *tex, uint32_t mip); -size_t yapf_sample_bytes(uint8_t sample); /* 1, 2 or 4 */ - -/* Notes: add (library-owned textures only; data is copied) and find. */ -int yapf_tex_add_note(yapf_texture_t *tex, const char tag[4], - const void *data, uint32_t size); -const yapf_note_t *yapf_tex_find_note(const yapf_texture_t *tex, const char tag[4]); - -/* - * yapf_tex_encode / yapf_tex_save — write a version 2 file. `flags` is - * YAPF_ENC_*. Works on library-owned and caller-built textures alike - * (nothing is taken over). Returns YAPF_OK or a YAPF_ERR_* code. - */ -int yapf_tex_encode(const yapf_texture_t *tex, int flags, - void **out_data, size_t *out_size); -int yapf_tex_save(const char *filename, const yapf_texture_t *tex, int flags); - -/* - * yapf_tex_load / yapf_tex_load_memory — read a version 1 or 2 file and - * decode every surface on up to `threads` threads (0 = one per core). - * `flags` is YAPF_LOAD_*. On failure NULL is returned and *err (if not - * NULL) receives the YAPF_ERR_* reason. - */ -yapf_texture_t *yapf_tex_load(const char *filename, int flags, int threads, int *err); -yapf_texture_t *yapf_tex_load_memory(const void *buffer, size_t size, - int flags, int threads, int *err); - -/* - * Streaming and partial decoding. - * - * yapf_tex_open — read only the header, tables and notes. `avail` may be - * less than the whole file (a download in progress): it must cover the - * front matter, else YAPF_ERR_TRUNCATED. All data[] pointers are NULL. - * - * yapf_tex_stream_bytes — how many leading bytes of the file hold every - * surface of mip `first_mip` and smaller (the file stores small mips - * first, so these are a usable texture on their own). - * - * yapf_tex_decode_surface — decode surface s into tex->data[s] - * (allocated). `buffer`/`avail` is the file or a prefix of it; returns - * YAPF_ERR_TRUNCATED when the surface is not in it yet. - * - * yapf_tex_tile_grid / yapf_tex_decode_tile — virtual texturing: the - * surfaces of mip m are cut into tiles (64 × 64 pixels, or 16 × 16 - * blocks), tx across, ty down, per slice. decode_tile writes one tile - * into `out`, rows `stride` bytes apart, and reports its pixel rectangle. - */ -yapf_texture_t *yapf_tex_open(const void *buffer, size_t avail, int flags, int *err); -uint64_t yapf_tex_stream_bytes(const yapf_texture_t *tex, uint32_t first_mip); -int yapf_tex_decode_surface(yapf_texture_t *tex, const void *buffer, size_t avail, - uint32_t surface, int threads); -void yapf_tex_tile_grid(const yapf_texture_t *tex, uint32_t mip, - uint32_t *tiles_x, uint32_t *tiles_y); -int yapf_tex_decode_tile(const yapf_texture_t *tex, const void *buffer, size_t avail, - uint32_t surface, uint32_t tx, uint32_t ty, uint32_t slice, - void *out, size_t stride, - uint32_t *x, uint32_t *y, uint32_t *w, uint32_t *h); - -/* - * yapf_tex_build_mips — replace the mips of a library-owned pixel texture - * with a chain made from mip 0: `levels` levels (0 = down to 1 × 1). - * 2 × 2 (× 2 for volumes) box filter; sRGB channels are averaged in - * linear light. alpha_ref > 0 rescales alpha on every mip so the share - * of texels above alpha_ref stays that of mip 0 (fences and foliage do - * not thin out); it sets YAPF_FLAG_COVERAGE. Records the filter used. - */ -int yapf_tex_build_mips(yapf_texture_t *tex, uint32_t levels, uint8_t alpha_ref); - -/* ── GPU blocks ──────────────────────────────────────────────────────── */ - -/* Block footprint and size of a YAPF_GPU_* block format; 0 if not one. */ -int yapf_block_info(uint8_t format, uint32_t *block_w, uint32_t *block_h, - uint32_t *block_bytes); - -/* - * yapf_tex_compress — a new library-owned texture holding `src` (pixel - * payload) as GPU blocks. Built-in encoders: BC1, BC3, BC4, BC5, BC7 and - * BC6H (unsigned). LDR formats take 8-bit pixels; BC6H takes 16-bit, - * half or float pixels. For other formats bring blocks from your own - * encoder: a payload = BLOCKS texture with data[] filled. - */ -int yapf_tex_compress(const yapf_texture_t *src, uint8_t format, - yapf_texture_t **out); - -/* - * yapf_blocks_decode — decode a w × h image of BC1–BC7 blocks (previews, - * tools). LDR formats write RGBA8 (BC4 / BC5: R / RG, then 0, 255; - * snorm values shifted by +128); BC6H writes RGB half floats. Returns - * YAPF_ERR_UNSUPPORTED for ETC2 / EAC / ASTC. - */ -int yapf_blocks_decode(uint8_t format, const void *blocks, uint32_t w, uint32_t h, - void *out); - -/* - * yapf_tex_to_rgba8 — one slice of a decoded surface as 8-bit RGBA for - * display (thumbnails, previews): gray is expanded, 16-bit is rounded to - * 8 bits, float and half are clamped to 0..1 and sRGB encoded (they are - * linear), GPU blocks are decoded. out holds w × h × 4 bytes of that - * mip. Returns YAPF_ERR_UNSUPPORTED for ETC2 / EAC / ASTC blocks. - */ -int yapf_tex_to_rgba8(const yapf_texture_t *tex, uint32_t surface, uint32_t slice, - uint8_t *out); - -/* yapf-sum, the checksum used by version 2 files. */ -uint32_t yapf_checksum(const void *data, size_t size); - -/* Half float conversion helpers. */ -uint16_t yapf_float_to_half(float f); -float yapf_half_to_float(uint16_t h); - -#ifdef __cplusplus -} -#endif - -#endif /* YAPF_H */