in Support/STBImage/include/stb_image.h [4478:4688]
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;
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");
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);
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");
for (j=0; j < y; ++j) {
stbi_uc *cur = a->out + stride*j;
stbi_uc *prior;
int filter = *raw++;
if (filter > 4)
return stbi__err("invalid filter","Corrupt PNG");
if (depth < 8) {
STBI_ASSERT(img_width_bytes <= x);
cur += x*out_n - img_width_bytes; // store output to the rightmost img_len bytes, so we can decode in place
filter_bytes = 1;
width = img_width_bytes;
}
prior = cur - stride; // bugfix: need to compute this after 'cur +=' computation above
// if first row, use special filter that doesn't sample previous row
if (j == 0) filter = first_row_filter[filter];
// handle first byte explicitly
for (k=0; k < filter_bytes; ++k) {
switch (filter) {
case STBI__F_none : cur[k] = raw[k]; break;
case STBI__F_sub : cur[k] = raw[k]; break;
case STBI__F_up : cur[k] = STBI__BYTECAST(raw[k] + prior[k]); break;
case STBI__F_avg : cur[k] = STBI__BYTECAST(raw[k] + (prior[k]>>1)); break;
case STBI__F_paeth : cur[k] = STBI__BYTECAST(raw[k] + stbi__paeth(0,prior[k],0)); break;
case STBI__F_avg_first : cur[k] = raw[k]; break;
case STBI__F_paeth_first: cur[k] = raw[k]; break;
}
}
if (depth == 8) {
if (img_n != out_n)
cur[img_n] = 255; // first pixel
raw += img_n;
cur += out_n;
prior += out_n;
} else if (depth == 16) {
if (img_n != out_n) {
cur[filter_bytes] = 255; // first pixel top byte
cur[filter_bytes+1] = 255; // first pixel bottom byte
}
raw += filter_bytes;
cur += output_bytes;
prior += output_bytes;
} else {
raw += 1;
cur += 1;
prior += 1;
}
// this is a little gross, so that we don't switch per-pixel or per-component
if (depth < 8 || img_n == out_n) {
int nk = (width - 1)*filter_bytes;
#define STBI__CASE(f) \
case f: \
for (k=0; k < nk; ++k)
switch (filter) {
// "none" filter turns into a memcpy here; make that explicit.
case STBI__F_none: memcpy(cur, raw, nk); break;
STBI__CASE(STBI__F_sub) { cur[k] = STBI__BYTECAST(raw[k] + cur[k-filter_bytes]); } break;
STBI__CASE(STBI__F_up) { cur[k] = STBI__BYTECAST(raw[k] + prior[k]); } break;
STBI__CASE(STBI__F_avg) { cur[k] = STBI__BYTECAST(raw[k] + ((prior[k] + cur[k-filter_bytes])>>1)); } break;
STBI__CASE(STBI__F_paeth) { cur[k] = STBI__BYTECAST(raw[k] + stbi__paeth(cur[k-filter_bytes],prior[k],prior[k-filter_bytes])); } break;
STBI__CASE(STBI__F_avg_first) { cur[k] = STBI__BYTECAST(raw[k] + (cur[k-filter_bytes] >> 1)); } break;
STBI__CASE(STBI__F_paeth_first) { cur[k] = STBI__BYTECAST(raw[k] + stbi__paeth(cur[k-filter_bytes],0,0)); } break;
}
#undef STBI__CASE
raw += nk;
} else {
STBI_ASSERT(img_n+1 == out_n);
#define STBI__CASE(f) \
case f: \
for (i=x-1; i >= 1; --i, cur[filter_bytes]=255,raw+=filter_bytes,cur+=output_bytes,prior+=output_bytes) \
for (k=0; k < filter_bytes; ++k)
switch (filter) {
STBI__CASE(STBI__F_none) { cur[k] = raw[k]; } break;
STBI__CASE(STBI__F_sub) { cur[k] = STBI__BYTECAST(raw[k] + cur[k- output_bytes]); } break;
STBI__CASE(STBI__F_up) { cur[k] = STBI__BYTECAST(raw[k] + prior[k]); } break;
STBI__CASE(STBI__F_avg) { cur[k] = STBI__BYTECAST(raw[k] + ((prior[k] + cur[k- output_bytes])>>1)); } break;
STBI__CASE(STBI__F_paeth) { cur[k] = STBI__BYTECAST(raw[k] + stbi__paeth(cur[k- output_bytes],prior[k],prior[k- output_bytes])); } break;
STBI__CASE(STBI__F_avg_first) { cur[k] = STBI__BYTECAST(raw[k] + (cur[k- output_bytes] >> 1)); } break;
STBI__CASE(STBI__F_paeth_first) { cur[k] = STBI__BYTECAST(raw[k] + stbi__paeth(cur[k- output_bytes],0,0)); } break;
}
#undef STBI__CASE
// the loop above sets the high byte of the pixels' alpha, but for
// 16 bit png files we also need the low byte set. we'll do that here.
if (depth == 16) {
cur = a->out + stride*j; // start at the beginning of the row again
for (i=0; i < x; ++i,cur+=output_bytes) {
cur[filter_bytes+1] = 255;
}
}
}
}
// we make a separate pass to expand bits to pixels; for performance,
// this could run two scanlines behind the above code, so it won't
// intefere with filtering but will still be in the cache.
if (depth < 8) {
for (j=0; j < y; ++j) {
stbi_uc *cur = a->out + stride*j;
stbi_uc *in = a->out + stride*j + x*out_n - img_width_bytes;
// unpack 1/2/4-bit into a 8-bit buffer. allows us to keep the common 8-bit path optimal at minimal cost for 1/2/4-bit
// png guarante byte alignment, if width is not multiple of 8/4/2 we'll decode dummy trailing data that will be skipped in the later loop
stbi_uc scale = (color == 0) ? stbi__depth_scale_table[depth] : 1; // scale grayscale values to 0..255 range
// note that the final byte might overshoot and write more data than desired.
// we can allocate enough data that this never writes out of memory, but it
// could also overwrite the next scanline. can it overwrite non-empty data
// on the next scanline? yes, consider 1-pixel-wide scanlines with 1-bit-per-pixel.
// so we need to explicitly clamp the final ones
if (depth == 4) {
for (k=x*img_n; k >= 2; k-=2, ++in) {
*cur++ = scale * ((*in >> 4) );
*cur++ = scale * ((*in ) & 0x0f);
}
if (k > 0) *cur++ = scale * ((*in >> 4) );
} else if (depth == 2) {
for (k=x*img_n; k >= 4; k-=4, ++in) {
*cur++ = scale * ((*in >> 6) );
*cur++ = scale * ((*in >> 4) & 0x03);
*cur++ = scale * ((*in >> 2) & 0x03);
*cur++ = scale * ((*in ) & 0x03);
}
if (k > 0) *cur++ = scale * ((*in >> 6) );
if (k > 1) *cur++ = scale * ((*in >> 4) & 0x03);
if (k > 2) *cur++ = scale * ((*in >> 2) & 0x03);
} else if (depth == 1) {
for (k=x*img_n; k >= 8; k-=8, ++in) {
*cur++ = scale * ((*in >> 7) );
*cur++ = scale * ((*in >> 6) & 0x01);
*cur++ = scale * ((*in >> 5) & 0x01);
*cur++ = scale * ((*in >> 4) & 0x01);
*cur++ = scale * ((*in >> 3) & 0x01);
*cur++ = scale * ((*in >> 2) & 0x01);
*cur++ = scale * ((*in >> 1) & 0x01);
*cur++ = scale * ((*in ) & 0x01);
}
if (k > 0) *cur++ = scale * ((*in >> 7) );
if (k > 1) *cur++ = scale * ((*in >> 6) & 0x01);
if (k > 2) *cur++ = scale * ((*in >> 5) & 0x01);
if (k > 3) *cur++ = scale * ((*in >> 4) & 0x01);
if (k > 4) *cur++ = scale * ((*in >> 3) & 0x01);
if (k > 5) *cur++ = scale * ((*in >> 2) & 0x01);
if (k > 6) *cur++ = scale * ((*in >> 1) & 0x01);
}
if (img_n != out_n) {
int q;
// insert alpha = 255
cur = a->out + stride*j;
if (img_n == 1) {
for (q=x-1; q >= 0; --q) {
cur[q*2+1] = 255;
cur[q*2+0] = cur[q];
}
} else {
STBI_ASSERT(img_n == 3);
for (q=x-1; q >= 0; --q) {
cur[q*4+3] = 255;
cur[q*4+2] = cur[q*3+2];
cur[q*4+1] = cur[q*3+1];
cur[q*4+0] = cur[q*3+0];
}
}
}
}
} else if (depth == 16) {
// force the image data from big-endian to platform-native.
// this is done in a separate pass due to the decoding relying
// on the data being untouched, but could probably be done
// per-line during decode if care is taken.
stbi_uc *cur = a->out;
stbi__uint16 *cur16 = (stbi__uint16*)cur;
for(i=0; i < x*y*out_n; ++i,cur16++,cur+=2) {
*cur16 = (cur[0] << 8) | cur[1];
}
}
return 1;
}