SchOS/kernel/dev/text.c

// Text rendering. See include/text.h for what this replaces and why.

#include "types.h"
#include "defs.h"
#include "param.h"
#include "text.h"

// Included, now that this is the only file that reads it.
//
// It used to be `extern unsigned char font_data[256][16];` with a note
// explaining that include/font.h *defines* the array rather than declaring
// it, so a second includer would break the link. The second includer was
// gfx.c, which walked the bitmap itself when there was no TrueType face --
// and that was the duplicate glyph path. With it gone, the header can live
// with its one user.
#include "font.h"

// --- UTF-8 -----------------------------------------------------------------

uint32
utf8_next(const char **p)
{
  const unsigned char *s = (const unsigned char *)*p;
  uint32 c = s[0];

  if (c < 0x80) {
    *p += 1;
    return c;
  }

  int extra;
  uint32 cp;
  if      ((c & 0xE0) == 0xC0) { extra = 1; cp = c & 0x1F; }
  else if ((c & 0xF0) == 0xE0) { extra = 2; cp = c & 0x0F; }
  else if ((c & 0xF8) == 0xF0) { extra = 3; cp = c & 0x07; }
  else {
    // A continuation byte or 0xF8..0xFF where a lead byte should be. Consume
    // exactly one so a malformed string cannot stall the loop -- a decoder that
    // does not advance on bad input is a hang, not a rendering artefact.
    *p += 1;
    return 0xFFFD;
  }

  for (int i = 1; i <= extra; i++) {
    if ((s[i] & 0xC0) != 0x80) {   // truncated sequence
      *p += 1;
      return 0xFFFD;
    }
    cp = (cp << 6) | (s[i] & 0x3F);
  }
  *p += extra + 1;

  // Surrogates are not characters, and an overlong encoding is the classic way
  // to smuggle a byte past a filter that checks the decoded form.
  if (cp >= 0xD800 && cp <= 0xDFFF)
    return 0xFFFD;
  if ((extra == 1 && cp < 0x80) || (extra == 2 && cp < 0x800) ||
      (extra == 3 && cp < 0x10000))
    return 0xFFFD;
  return cp;
}

// --- the built-in bitmap font as a provider --------------------------------
//
// font_data is 256 CP437 glyphs of 8x16, one bit per pixel. Expanded here into
// 8-bit coverage so that every caller works in one representation and an
// outline rasteriser can be added without touching any of them.
//
// The expansion buffer is static and reused per glyph. That is fine because
// glyphs are consumed immediately by the blitter and nothing holds one; it
// would not be fine the moment a caller kept a struct glyph across calls, which
// is why the header says nothing about the lifetime being longer than that.

#define BUILTIN_W  8
#define BUILTIN_H  16

static unsigned char builtin_cov[BUILTIN_W * BUILTIN_H];

// Unicode to CP437, for the range where they differ and it matters.
//
// The built-in font is CP437, not Latin-1 -- a fact that has bitten this
// codebase before. Rather than pretend otherwise, map the handful of
// codepoints worth having and fall back for the rest. This table exists to be
// *deleted* when a real font arrives; it is a bridge, not a design.
static uint32
to_cp437(uint32 cp)
{
  if (cp < 0x80)
    return cp;
  switch (cp) {
  case 0x00A0: return 0x20;   // no-break space
  case 0x00B0: return 0xF8;   // degree
  case 0x00B1: return 0xF1;   // plus-minus
  case 0x00B7: return 0xFA;   // middle dot
  case 0x2022: return 0x07;   // bullet
  case 0x2190: return 0x1B;   // arrows
  case 0x2191: return 0x18;
  case 0x2192: return 0x1A;
  case 0x2193: return 0x19;
  case 0x2500: return 0xC4;   // box drawing, the part worth keeping
  case 0x2502: return 0xB3;
  case 0x250C: return 0xDA;
  case 0x2510: return 0xBF;
  case 0x2514: return 0xC0;
  case 0x2518: return 0xD9;
  case 0x251C: return 0xC3;
  case 0x2524: return 0xB4;
  case 0x252C: return 0xC2;
  case 0x2534: return 0xC1;
  case 0x253C: return 0xC5;
  case 0x2588: return 0xDB;   // full block
  case 0x2591: return 0xB0;   // shades
  case 0x2592: return 0xB1;
  case 0x2593: return 0xB2;
  default:     return 0;      // "no glyph"
  }
}

static int
builtin_glyph(struct font *f, uint32 cp, struct glyph *out)
{
  uint32 idx = to_cp437(cp);
  if (idx == 0 && cp != 0)
    return -1;                    // caller substitutes

  for (int y = 0; y < BUILTIN_H; y++) {
    unsigned char bits = font_data[idx & 0xFF][y];
    for (int x = 0; x < BUILTIN_W; x++)
      builtin_cov[y * BUILTIN_W + x] = (bits & (0x80 >> x)) ? 0xFF : 0x00;
  }

  out->cov       = builtin_cov;
  out->w         = BUILTIN_W;
  out->h         = BUILTIN_H;
  out->bearing_x = 0;
  // The whole cell sits above the baseline, less two rows of descender space.
  // The value matters only for consistency with whatever font comes next.
  out->bearing_y = BUILTIN_H - 3;
  out->advance   = BUILTIN_W;
  return 0;
}

static int builtin_height(struct font *f)   { return BUILTIN_H; }
static int builtin_baseline(struct font *f) { return BUILTIN_H - 3; }

static const struct font_ops builtin_ops = {
  .glyph    = builtin_glyph,
  .height   = builtin_height,
  .baseline = builtin_baseline,
};

static struct font builtin = { &builtin_ops, 0 };

struct font *
font_builtin(void)
{
  return &builtin;
}

// --- blitting --------------------------------------------------------------

// Blend `color` over the pixel at (x, y) by coverage a.
//
// Reads the destination, which a bitmap font never needs -- but an
// anti-aliased edge is defined as a blend with what is already there, and a
// renderer that cannot do it is a renderer that cannot draw a real typeface.
static uint32
sur_read(struct surface *s, unsigned char *at)
{
  switch (s->bpp) {
  case 24: return ((uint32)at[2] << 16) | ((uint32)at[1] << 8) | at[0];
  case 16: {
    uint16 v = *(uint16 *)at;
    return (uint32)(((v >> 11) & 0x1F) << 19) |
           (uint32)(((v >>  5) & 0x3F) << 10) |
           (uint32)((v & 0x1F) << 3);
  }
  default: return *(uint32 *)at;
  }
}

static void
sur_write(struct surface *s, unsigned char *at, uint32 color)
{
  switch (s->bpp) {
  case 24:
    at[0] = color & 0xFF; at[1] = (color >> 8) & 0xFF; at[2] = (color >> 16) & 0xFF;
    return;
  case 16:
    *(uint16 *)at = (uint16)((((color >> 19) & 0x1F) << 11) |
                             (((color >> 10) & 0x3F) <<  5) |
                             ((color >> 3) & 0x1F));
    return;
  default:
    *(uint32 *)at = color;
    return;
  }
}

static void
blend_px(struct surface *s, int x, int y, uint32 color, unsigned a)
{
  if (x < 0 || y < 0 || x >= s->width || y >= s->height)
    return;

  unsigned char *at = (unsigned char *)s->pixels + (uint64)y * s->stride +
                      (uint64)x * (s->bpp ? s->bpp / 8 : 4);
  if (a >= 255) {
    sur_write(s, at, color);
    return;
  }
  uint32 dst = sur_read(s, at);
  uint32 r = (((color >> 16) & 0xFF) * a + ((dst >> 16) & 0xFF) * (255 - a)) / 255;
  uint32 g = (((color >>  8) & 0xFF) * a + ((dst >>  8) & 0xFF) * (255 - a)) / 255;
  uint32 b = (((color      ) & 0xFF) * a + ((dst      ) & 0xFF) * (255 - a)) / 255;
  sur_write(s, at, (r << 16) | (g << 8) | b);
}

struct surface
surface_sub(const struct surface *s, int x, int y, int w, int h)
{
  struct surface out = *s;
  int bytes = s->bpp ? s->bpp / 8 : 4;

  out.pixels = (unsigned char *)s->pixels + (uint64)y * s->stride +
               (uint64)x * bytes;
  out.width  = w;
  out.height = h;
  return out;
}

int
text_draw_glyph(struct surface *s, struct font *f, int x, int y,
                uint32 cp, uint32 color)
{
  struct glyph g;

  if (f->ops->glyph(f, cp, &g) != 0) {
    // Substitute rather than skip. A missing glyph that draws nothing makes
    // text silently shorter and the fault impossible to see; a visible box
    // says exactly what happened and where.
    if (f->ops->glyph(f, 0x25A1, &g) != 0 &&      // white square
        f->ops->glyph(f, '?', &g) != 0)
      return 0;
  }

  int ox = x + g.bearing_x;
  int oy = y - g.bearing_y;      // bearing is measured up from the baseline

  for (int gy = 0; gy < g.h; gy++)
    for (int gx = 0; gx < g.w; gx++) {
      unsigned a = g.cov[gy * g.w + gx];
      if (a)
        blend_px(s, ox + gx, oy + gy, color, a);
    }

  return g.advance;
}

int
text_draw(struct surface *s, struct font *f, int x, int y,
          const char *utf8, uint32 color)
{
  int pen = x;
  const char *p = utf8;

  while (*p) {
    uint32 cp = utf8_next(&p);
    if (cp == '\n')
      break;                     // layout is the caller's business, not ours
    pen += text_draw_glyph(s, f, pen, y, cp, color);
  }
  return pen - x;
}

int
text_measure(struct font *f, const char *utf8)
{
  int w = 0;
  const char *p = utf8;
  struct glyph g;

  while (*p) {
    uint32 cp = utf8_next(&p);
    if (cp == '\n')
      break;
    if (f->ops->glyph(f, cp, &g) == 0)
      w += g.advance;
    else if (f->ops->glyph(f, '?', &g) == 0)
      w += g.advance;
  }
  return w;
}