SchOS/tools/ttftest.c

// Host harness for kernel/dev/ttf.c.
//
// A rasteriser is checked by looking at it. This renders a string with the real
// font and writes a PGM, which is the smallest image format that needs no
// compression -- the point is the glyphs, not the container.
//
//   build/tools/ttftest <font.ttf> <px> "text" out.pgm

#include <stdio.h>
#include <stdlib.h>
#include <string.h>

#define TTF_HOST
#include "../kernel/dev/ttf.c"

int ttf_render(struct ttf *, uint32, struct glyph *, unsigned char *, int, int *, int *);

// The console speaks UTF-8, so the harness has to as well -- otherwise the
// only glyphs it can ever ask for are ASCII, and ASCII is entirely made of
// simple glyphs. Every composite in a Latin font is an accented letter, which
// is to say: the byte-at-a-time version could not reach the code path that
// mattered.
//
// text.h declares utf8_next and kernel/dev/text.c defines it, but that file
// pulls in the kernel headers and cannot be compiled on the host. Define the
// symbol here instead: a second decoder is the cost of the harness existing
// at all, and the two agree on the only thing that matters here, which is
// always advancing.
uint32 utf8_next(const char **pp)
{
    const unsigned char *p = (const unsigned char *)*pp;
    uint32 c = *p++;
    int extra = 0;
    if      ((c & 0xe0) == 0xc0) { c &= 0x1f; extra = 1; }
    else if ((c & 0xf0) == 0xe0) { c &= 0x0f; extra = 2; }
    else if ((c & 0xf8) == 0xf0) { c &= 0x07; extra = 3; }
    while (extra-- > 0 && (*p & 0xc0) == 0x80)
        c = (c << 6) | (*p++ & 0x3f);
    *pp = (const char *)p;
    return c;
}

int main(int argc, char **argv)
{
    if (argc < 5) { fprintf(stderr, "usage: ttftest font.ttf px \"text\" out.pgm\n"); return 1; }
    const char *path = argv[1];
    int px = atoi(argv[2]);
    const char *text = argv[3];

    FILE *fp = fopen(path, "rb");
    if (!fp) { perror(path); return 1; }
    fseek(fp, 0, SEEK_END); long n = ftell(fp); fseek(fp, 0, SEEK_SET);
    unsigned char *buf = malloc(n);
    if (fread(buf, 1, n, fp) != (size_t)n) { fprintf(stderr, "short read\n"); return 1; }
    fclose(fp);

    struct ttf f;
    if (ttf_open(&f, buf, (uint32)n, px) != 0) {
        fprintf(stderr, "not a TrueType font this can read\n"); return 1;
    }
    printf("unitsPerEm %d, %d glyphs, ascent %d descent %d, %s loca\n",
           f.units_per_em, f.num_glyphs, f.ascent, f.descent,
           f.long_loca ? "long" : "short");

    struct font *fo = ttf_font(&f);
    int H = fo->ops->height(fo) + px;      // room for descenders and padding
    int base = fo->ops->baseline(fo) + px / 2;
    int W = 16;
    for (const char *p = text; *p; ) { utf8_next(&p); W += px; }   // generous

    unsigned char *img = calloc(W * H, 1);
    int pen = 8, drawn = 0, missing = 0;

    for (const char *p = text; *p; ) {
        uint32 cp = utf8_next(&p);
        struct glyph g;
        // Through the provider, not ttf_render, so the glyph cache is on the
        // path being tested rather than bypassed by the harness.
        if (fo->ops->glyph(fo, cp, &g) != 0) {
            missing++;
            pen += px / 2;
            continue;
        }
        for (int gy = 0; gy < g.h; gy++)
            for (int gx = 0; gx < g.w; gx++) {
                int X = pen + g.bearing_x + gx;
                int Y = base - g.bearing_y + gy;
                if (X < 0 || Y < 0 || X >= W || Y >= H) continue;
                int v = img[Y * W + X] + g.cov[gy * g.w + gx];
                img[Y * W + X] = v > 255 ? 255 : v;
            }
        pen += g.advance;
        drawn++;
    }

    // White on black inverted to black on white, which is how text is read.
    for (int i = 0; i < W * H; i++) img[i] = 255 - img[i];

    FILE *o = fopen(argv[4], "wb");
    fprintf(o, "P5\n%d %d\n255\n", W, H);
    fwrite(img, 1, W * H, o);
    fclose(o);

    printf("%d glyphs drawn, %d missing, %d px advance, image %dx%d -> %s\n",
           drawn, missing, pen - 8, W, H, argv[4]);
    return drawn ? 0 : 1;
}