[FFmpeg-devel] [PATCH 1/2] libavcodec: add support for animated WebP decoding
Josef Zlomek
josef at pex.com
Wed Jul 8 08:28:23 EEST 2020
Fixes: 4907
Adds support for decoding of animated WebP.
The WebP parser now splits the input stream into packets containing one frame.
The WebP decoder adds the animation related features according to the specs:
https://developers.google.com/speed/webp/docs/riff_container#animation
The frames of the animation may be smaller than the image canvas.
Therefore, the frame is decoded to a temporary frame,
then it is blended into the canvas, the canvas is copied to the output frame,
and finally the frame is disposed from the canvas.
The output to AV_PIX_FMT_YUVA420P/AV_PIX_FMT_YUV420P is still supported.
The background color is specified only as BGRA in the WebP file
so it is converted to YUVA if YUV formats are output.
Signed-off-by: Josef Zlomek <josef at pex.com>
---
Changelog | 1 +
libavcodec/version.h | 2 +-
libavcodec/webp.c | 548 ++++++++++++++++++++++++++++++++++++---
libavcodec/webp_parser.c | 116 ++++++---
4 files changed, 583 insertions(+), 84 deletions(-)
diff --git a/Changelog b/Changelog
index 1bb9931c0d..1e41040a8e 100644
--- a/Changelog
+++ b/Changelog
@@ -5,6 +5,7 @@ version <next>:
- AudioToolbox output device
- MacCaption demuxer
- PGX decoder
+- animated WebP parser/decoder
version 4.3:
diff --git a/libavcodec/version.h b/libavcodec/version.h
index 482cc6d6ba..e75891d463 100644
--- a/libavcodec/version.h
+++ b/libavcodec/version.h
@@ -28,7 +28,7 @@
#include "libavutil/version.h"
#define LIBAVCODEC_VERSION_MAJOR 58
-#define LIBAVCODEC_VERSION_MINOR 94
+#define LIBAVCODEC_VERSION_MINOR 95
#define LIBAVCODEC_VERSION_MICRO 100
#define LIBAVCODEC_VERSION_INT AV_VERSION_INT(LIBAVCODEC_VERSION_MAJOR, \
diff --git a/libavcodec/webp.c b/libavcodec/webp.c
index c6d0206846..e0eb076cd1 100644
--- a/libavcodec/webp.c
+++ b/libavcodec/webp.c
@@ -41,6 +41,7 @@
*/
#include "libavutil/imgutils.h"
+#include "libswscale/swscale.h"
#define BITSTREAM_READER_LE
#include "avcodec.h"
@@ -57,6 +58,9 @@
#define VP8X_FLAG_ALPHA 0x10
#define VP8X_FLAG_ICC 0x20
+#define ANMF_DISPOSAL_METHOD 0x01
+#define ANMF_BLENDING_METHOD 0x02
+
#define MAX_PALETTE_SIZE 256
#define MAX_CACHE_BITS 11
#define NUM_CODE_LENGTH_CODES 19
@@ -188,19 +192,30 @@ typedef struct ImageContext {
typedef struct WebPContext {
VP8Context v; /* VP8 Context used for lossy decoding */
GetBitContext gb; /* bitstream reader for main image chunk */
+ AVFrame *canvas_frame; /* AVFrame for canvas */
+ AVFrame *frame; /* AVFrame for decoded frame */
AVFrame *alpha_frame; /* AVFrame for alpha data decompressed from VP8L */
AVCodecContext *avctx; /* parent AVCodecContext */
int initialized; /* set once the VP8 context is initialized */
int has_alpha; /* has a separate alpha chunk */
enum AlphaCompression alpha_compression; /* compression type for alpha chunk */
enum AlphaFilter alpha_filter; /* filtering method for alpha chunk */
+ AVPacket alpha_packet; /* alpha chunk */
uint8_t *alpha_data; /* alpha chunk data */
int alpha_data_size; /* alpha chunk data size */
int has_exif; /* set after an EXIF chunk has been processed */
int has_iccp; /* set after an ICCP chunk has been processed */
- int width; /* image width */
- int height; /* image height */
+ int vp8x_flags; /* flags from VP8X chunk */
+ int anmf_flags; /* flags from ANMF chunk */
+ int canvas_width; /* canvas width */
+ int canvas_height; /* canvas height */
+ int width; /* frame width */
+ int height; /* frame height */
+ int pos_x; /* frame position X */
+ int pos_y; /* frame position Y */
int lossless; /* indicates lossless or lossy */
+ uint32_t background_argb; /* background color in ARGB format */
+ uint8_t background_yuva[4]; /* background color in YUVA format */
int nb_transforms; /* number of transforms */
enum TransformType transforms[4]; /* transformations used in the image, in order */
@@ -1100,7 +1115,7 @@ static int apply_color_indexing_transform(WebPContext *s)
return 0;
}
-static void update_canvas_size(AVCodecContext *avctx, int w, int h)
+static void update_frame_size(AVCodecContext *avctx, int w, int h)
{
WebPContext *s = avctx->priv_data;
if (s->width && s->width != w) {
@@ -1140,7 +1155,7 @@ static int vp8_lossless_decode_frame(AVCodecContext *avctx, AVFrame *p,
w = get_bits(&s->gb, 14) + 1;
h = get_bits(&s->gb, 14) + 1;
- update_canvas_size(avctx, w, h);
+ update_frame_size(avctx, w, h);
ret = ff_set_dimensions(avctx, s->width, s->height);
if (ret < 0)
@@ -1356,7 +1371,7 @@ static int vp8_lossy_decode_frame(AVCodecContext *avctx, AVFrame *p,
if (!*got_frame)
return AVERROR_INVALIDDATA;
- update_canvas_size(avctx, avctx->width, avctx->height);
+ update_frame_size(avctx, avctx->width, avctx->height);
if (s->has_alpha) {
ret = vp8_lossy_decode_alpha(avctx, p, s->alpha_data,
@@ -1367,6 +1382,392 @@ static int vp8_lossy_decode_frame(AVCodecContext *avctx, AVFrame *p,
return ret;
}
+static int convert_background_color(AVCodecContext *avctx)
+{
+ WebPContext *s = avctx->priv_data;
+ int i;
+ int ret;
+
+ uint32_t src_frame[2][2] = { {s->background_argb, s->background_argb},
+ {s->background_argb, s->background_argb} };
+ uint8_t dst_frames[4][2][2];
+
+ const uint8_t * const src_data[4] = { (const uint8_t *) &src_frame[0][0],
+ NULL,
+ NULL,
+ NULL };
+ uint8_t * const dst_data[4] = { &dst_frames[0][0][0],
+ &dst_frames[1][0][0],
+ &dst_frames[2][0][0],
+ &dst_frames[3][0][0] };
+ int src_linesize[4] = { 4, 0, 0, 0 };
+ int dst_linesize[4] = { 2, 1, 1, 2 };
+
+ struct SwsContext *ctx = sws_getContext(2, 2, AV_PIX_FMT_ARGB,
+ 2, 2, AV_PIX_FMT_YUVA420P,
+ 0, 0, 0, 0);
+ if (!ctx)
+ return AVERROR(EINVAL);
+
+ ret = sws_scale(ctx, src_data, src_linesize, 0, 2, dst_data, dst_linesize);
+
+ if (ret >= 0) {
+ for (i = 0; i < 4; i++)
+ s->background_yuva[i] = dst_frames[i][0][0];
+ }
+
+ sws_freeContext(ctx);
+ return ret;
+}
+
+static int init_canvas_frame(AVCodecContext *avctx)
+{
+ WebPContext *s = avctx->priv_data;
+ AVFrame *canvas;
+ AVFrame *frame = s->frame;
+ int x, y;
+ int width, height;
+ int ret;
+
+ canvas = av_frame_alloc();
+ if (!canvas)
+ return AVERROR(ENOMEM);
+ s->canvas_frame = canvas;
+
+ /* let canvas always have alpha */
+ canvas->format = frame->format == AV_PIX_FMT_YUV420P ? AV_PIX_FMT_YUVA420P : frame->format;
+ canvas->width = s->canvas_width;
+ canvas->height = s->canvas_height;
+
+ ret = av_frame_copy_props(canvas, frame);
+ if (ret < 0)
+ return ret;
+
+ ret = av_frame_get_buffer(canvas, 1);
+ if (ret < 0)
+ return ret;
+
+ if (canvas->format == AV_PIX_FMT_ARGB) {
+ width = canvas->width;
+ height = canvas->height;
+
+ for (y = 0; y < height; y++) {
+ uint32_t *dst = (uint32_t *) (canvas->data[0] + y * canvas->linesize[0]);
+ for (x = 0; x < width; x++)
+ dst[x] = s->background_argb;
+ }
+ } else /* if (canvas->format == AV_PIX_FMT_YUVA420P) */ {
+ const AVPixFmtDescriptor *desc = av_pix_fmt_desc_get(canvas->format);
+ int component;
+ int plane;
+
+ ret = convert_background_color(avctx);
+ if (ret < 0)
+ return ret;
+
+ for (component = 0; component < desc->nb_components; component++) {
+ plane = desc->comp[component].plane;
+ height = canvas->height;
+
+ if (component == 1 || component == 2) {
+ height = AV_CEIL_RSHIFT(height, desc->log2_chroma_h);
+ }
+
+ memset(canvas->data[plane], s->background_yuva[component],
+ height * canvas->linesize[plane]);
+ }
+ }
+
+ return 0;
+}
+
+static int blend_frame_into_canvas(AVCodecContext *avctx)
+{
+ WebPContext *s = avctx->priv_data;
+ AVFrame *canvas = s->canvas_frame;
+ AVFrame *frame = s->frame;
+ int x, y;
+ int width, height;
+ int pos_x, pos_y;
+
+ if ((s->anmf_flags & ANMF_BLENDING_METHOD) || frame->format == AV_PIX_FMT_YUV420P) {
+ /* do not blend, overwrite */
+
+ if (canvas->format == AV_PIX_FMT_ARGB) {
+ width = s->width;
+ height = s->height;
+ pos_x = s->pos_x;
+ pos_y = s->pos_y;
+
+ for (y = 0; y < height; y++) {
+ const uint32_t *src = (uint32_t *) (frame->data[0] + y * frame->linesize[0]);
+ uint32_t *dst = (uint32_t *) (canvas->data[0] + (y + pos_y) * canvas->linesize[0]) + pos_x;
+ memcpy(dst, src, width * 4);
+ }
+ } else /* if (canvas->format == AV_PIX_FMT_YUVA420P) */ {
+ const AVPixFmtDescriptor *desc = av_pix_fmt_desc_get(frame->format);
+ int component;
+ int plane;
+
+ for (component = 0; component < desc->nb_components; component++) {
+ plane = desc->comp[component].plane;
+ width = s->width;
+ height = s->height;
+ pos_x = s->pos_x;
+ pos_y = s->pos_y;
+ if (component == 1 || component == 2) {
+ width = AV_CEIL_RSHIFT(width, desc->log2_chroma_w);
+ height = AV_CEIL_RSHIFT(height, desc->log2_chroma_h);
+ pos_x = AV_CEIL_RSHIFT(pos_x, desc->log2_chroma_w);
+ pos_y = AV_CEIL_RSHIFT(pos_y, desc->log2_chroma_h);
+ }
+
+ for (y = 0; y < height; y++) {
+ const uint8_t *src = frame->data[plane] + y * frame->linesize[plane];
+ uint8_t *dst = canvas->data[plane] + (y + pos_y) * canvas->linesize[plane] + pos_x;
+ memcpy(dst, src, width);
+ }
+ }
+
+ if (desc->nb_components < 4) {
+ /* frame does not have alpha, set alpha to 255 */
+ desc = av_pix_fmt_desc_get(canvas->format);
+ plane = desc->comp[3].plane;
+ width = s->width;
+ height = s->height;
+ pos_x = s->pos_x;
+ pos_y = s->pos_y;
+
+ for (y = 0; y < height; y++) {
+ uint8_t *dst = canvas->data[plane] + (y + pos_y) * canvas->linesize[plane] + pos_x;
+ memset(dst, 255, width);
+ }
+ }
+ }
+ } else {
+ /* alpha blending */
+
+ if (canvas->format == AV_PIX_FMT_ARGB) {
+ width = s->width;
+ height = s->height;
+ pos_x = s->pos_x;
+ pos_y = s->pos_y;
+
+ for (y = 0; y < height; y++) {
+ const uint8_t *src = frame->data[0] + y * frame->linesize[0];
+ uint8_t *dst = canvas->data[0] + (y + pos_y) * canvas->linesize[0] + pos_x * 4;
+ for (x = 0; x < width; x++) {
+ int src_alpha = src[0];
+ int dst_alpha = dst[0];
+ int dst_alpha2 = dst_alpha - ROUNDED_DIV(src_alpha * dst_alpha, 255);
+ int blend_alpha = src_alpha + dst_alpha2;
+
+ if (blend_alpha == 0) {
+ dst[0] = 0;
+ dst[1] = 0;
+ dst[2] = 0;
+ dst[3] = 0;
+ } else {
+ dst[0] = blend_alpha;
+ dst[1] = ROUNDED_DIV(src[1] * src_alpha + dst[1] * dst_alpha2, blend_alpha);
+ dst[2] = ROUNDED_DIV(src[2] * src_alpha + dst[2] * dst_alpha2, blend_alpha);
+ dst[3] = ROUNDED_DIV(src[3] * src_alpha + dst[3] * dst_alpha2, blend_alpha);
+ }
+ src += 4;
+ dst += 4;
+ }
+ }
+ } else /* if (canvas->format == AV_PIX_FMT_YUVA420P) */ {
+ const AVPixFmtDescriptor *desc = av_pix_fmt_desc_get(frame->format);
+ int plane_y, plane_u, plane_v, plane_a;
+ int tile_w;
+ int tile_h;
+ int src_alpha;
+ int dst_alpha;
+ int dst_alpha2;
+ int blend_alpha;
+
+ av_assert0(desc->nb_components >= 4);
+ plane_y = desc->comp[0].plane;
+ plane_u = desc->comp[1].plane;
+ plane_v = desc->comp[2].plane;
+ plane_a = desc->comp[3].plane;
+
+ // first, blend U & V planes, because the later step modifies alpha plane
+ width = AV_CEIL_RSHIFT(s->width, desc->log2_chroma_w);
+ height = AV_CEIL_RSHIFT(s->height, desc->log2_chroma_h);
+ pos_x = AV_CEIL_RSHIFT(s->pos_x, desc->log2_chroma_w);
+ pos_y = AV_CEIL_RSHIFT(s->pos_y, desc->log2_chroma_h);
+ tile_w = 1 << desc->log2_chroma_w;
+ tile_h = 1 << desc->log2_chroma_h;
+
+ for (y = 0; y < height; y++) {
+ uint8_t *src_u = frame->data[plane_u] + y * frame->linesize[plane_u];
+ uint8_t *src_v = frame->data[plane_v] + y * frame->linesize[plane_v];
+ uint8_t *dst_u = canvas->data[plane_u] + (y + pos_y) * canvas->linesize[plane_u] + pos_x;
+ uint8_t *dst_v = canvas->data[plane_v] + (y + pos_y) * canvas->linesize[plane_v] + pos_x;
+ for (x = 0; x < width; x++) {
+ int xx, yy;
+
+ src_alpha = 0;
+ dst_alpha = 0;
+ for (yy = 0; yy < tile_h; yy++) {
+ for (xx = 0; xx < tile_w; xx++) {
+ src_alpha += frame->data[plane_a][(y * tile_h + yy) * frame->linesize[plane_a] + (x * tile_w + xx)];
+ dst_alpha += canvas->data[plane_a][((y + pos_y) * tile_h + yy) * canvas->linesize[plane_a] + ((x + pos_x) * tile_w + xx)];
+ }
+ }
+ src_alpha = RSHIFT(src_alpha, desc->log2_chroma_w + desc->log2_chroma_h);
+ dst_alpha = RSHIFT(dst_alpha, desc->log2_chroma_w + desc->log2_chroma_h);
+ dst_alpha2 = dst_alpha - ROUNDED_DIV(src_alpha * dst_alpha, 255);
+ blend_alpha = src_alpha + dst_alpha2;
+
+ if (blend_alpha == 0) {
+ *dst_u = 0;
+ *dst_v = 0;
+ } else {
+ *dst_u = ROUNDED_DIV(*src_u * src_alpha + *dst_u * dst_alpha2, blend_alpha);
+ *dst_v = ROUNDED_DIV(*src_v * src_alpha + *dst_v * dst_alpha2, blend_alpha);
+ }
+
+ src_u++;
+ src_v++;
+ dst_u++;
+ dst_v++;
+ }
+ }
+
+ // then blend Y & A planes
+ width = s->width;
+ height = s->height;
+ pos_x = s->pos_x;
+ pos_y = s->pos_y;
+
+ for (y = 0; y < height; y++) {
+ const uint8_t *src_y = frame->data[plane_y] + y * frame->linesize[plane_y];
+ const uint8_t *src_a = frame->data[plane_a] + y * frame->linesize[plane_a];
+ uint8_t *dst_y = canvas->data[plane_y] + (y + pos_y) * canvas->linesize[plane_y] + pos_x;
+ uint8_t *dst_a = canvas->data[plane_a] + (y + pos_y) * canvas->linesize[plane_a] + pos_x;
+ for (x = 0; x < width; x++) {
+ src_alpha = *src_a;
+ dst_alpha = *dst_a;
+ dst_alpha2 = dst_alpha - ROUNDED_DIV(src_alpha * dst_alpha, 255);
+ blend_alpha = src_alpha + dst_alpha2;
+
+ if (blend_alpha == 0) {
+ *dst_y = 0;
+ *dst_a = 0;
+ } else {
+ *dst_y = ROUNDED_DIV(*src_y * src_alpha + *dst_y * dst_alpha2, blend_alpha);
+ *dst_a = blend_alpha;
+ }
+
+ src_y++;
+ src_a++;
+ dst_y++;
+ dst_a++;
+ }
+ }
+ }
+ }
+
+ return 0;
+}
+
+static int copy_canvas_to_frame(AVCodecContext *avctx, AVFrame *frame)
+{
+ WebPContext *s = avctx->priv_data;
+ AVFrame *canvas = s->canvas_frame;
+ int ret;
+
+ avctx->pix_fmt = canvas->format;
+ frame->format = canvas->format;
+ frame->width = canvas->width;
+ frame->height = canvas->height;
+
+ ret = av_frame_get_buffer(frame, 1);
+ if (ret < 0)
+ return ret;
+
+ ret = av_frame_copy_props(frame, canvas);
+ if (ret < 0)
+ return ret;
+
+ ret = av_frame_copy(frame, canvas);
+ if (ret < 0)
+ return ret;
+
+ /* VP8 decoder changed the width and height in AVCodecContext.
+ * Change it back to the canvas size. */
+ ret = ff_set_dimensions(avctx, canvas->width, canvas->height);
+ if (ret < 0)
+ return ret;
+
+ return 0;
+}
+
+static int dispose_frame_in_canvas(AVCodecContext *avctx)
+{
+ WebPContext *s = avctx->priv_data;
+ AVFrame *canvas = s->canvas_frame;
+ int x, y;
+ int width, height;
+ int pos_x, pos_y;
+
+ if (s->anmf_flags & ANMF_DISPOSAL_METHOD) {
+ /* dispose to background color */
+
+ if (canvas->format == AV_PIX_FMT_ARGB) {
+ width = s->width;
+ height = s->height;
+ pos_x = s->pos_x;
+ pos_y = s->pos_y;
+
+ for (y = 0; y < height; y++) {
+ uint32_t *dst = (uint32_t *) (canvas->data[0] + (y + pos_y) * canvas->linesize[0]) + pos_x;
+ for (x = 0; x < width; x++)
+ dst[x] = s->background_argb;
+ }
+ } else /* if (canvas->format == AV_PIX_FMT_YUVA420P) */ {
+ const AVPixFmtDescriptor *desc = av_pix_fmt_desc_get(canvas->format);
+ int component;
+ int plane;
+
+ for (component = 0; component < desc->nb_components; component++) {
+ plane = desc->comp[component].plane;
+ width = s->width;
+ height = s->height;
+ pos_x = s->pos_x;
+ pos_y = s->pos_y;
+ if (component == 1 || component == 2) {
+ width = AV_CEIL_RSHIFT(width, desc->log2_chroma_w);
+ height = AV_CEIL_RSHIFT(height, desc->log2_chroma_h);
+ pos_x = AV_CEIL_RSHIFT(pos_x, desc->log2_chroma_w);
+ pos_y = AV_CEIL_RSHIFT(pos_y, desc->log2_chroma_h);
+ }
+
+ for (y = 0; y < height; y++) {
+ uint8_t *dst = canvas->data[plane] + (y + pos_y) * canvas->linesize[plane] + pos_x;
+ memset(dst, s->background_yuva[component], width);
+ }
+ }
+ }
+ }
+
+ return 0;
+}
+
+static av_cold int webp_decode_init(AVCodecContext *avctx)
+{
+ WebPContext *s = avctx->priv_data;
+
+ s->frame = av_frame_alloc();
+ if (!s->frame)
+ return AVERROR(ENOMEM);
+
+ return 0;
+}
+
static int webp_decode_frame(AVCodecContext *avctx, void *data, int *got_frame,
AVPacket *avpkt)
{
@@ -1375,33 +1776,13 @@ static int webp_decode_frame(AVCodecContext *avctx, void *data, int *got_frame,
GetByteContext gb;
int ret;
uint32_t chunk_type, chunk_size;
- int vp8x_flags = 0;
s->avctx = avctx;
- s->width = 0;
- s->height = 0;
*got_frame = 0;
- s->has_alpha = 0;
- s->has_exif = 0;
- s->has_iccp = 0;
bytestream2_init(&gb, avpkt->data, avpkt->size);
- if (bytestream2_get_bytes_left(&gb) < 12)
- return AVERROR_INVALIDDATA;
-
- if (bytestream2_get_le32(&gb) != MKTAG('R', 'I', 'F', 'F')) {
- av_log(avctx, AV_LOG_ERROR, "missing RIFF tag\n");
- return AVERROR_INVALIDDATA;
- }
-
- chunk_size = bytestream2_get_le32(&gb);
- if (bytestream2_get_bytes_left(&gb) < chunk_size)
- return AVERROR_INVALIDDATA;
-
- if (bytestream2_get_le32(&gb) != MKTAG('W', 'E', 'B', 'P')) {
- av_log(avctx, AV_LOG_ERROR, "missing WEBP tag\n");
- return AVERROR_INVALIDDATA;
- }
+ // clear the previous frame
+ av_frame_unref(s->frame);
while (bytestream2_get_bytes_left(&gb) > 8) {
char chunk_str[5] = { 0 };
@@ -1412,6 +1793,10 @@ static int webp_decode_frame(AVCodecContext *avctx, void *data, int *got_frame,
return AVERROR_INVALIDDATA;
chunk_size += chunk_size & 1;
+ /* we need to dive into RIFF chunk */
+ if (chunk_type == MKTAG('R', 'I', 'F', 'F'))
+ chunk_size = 4;
+
if (bytestream2_get_bytes_left(&gb) < chunk_size) {
/* we seem to be running out of data, but it could also be that the
bitstream has trailing junk leading to bogus chunk_size. */
@@ -1419,9 +1804,27 @@ static int webp_decode_frame(AVCodecContext *avctx, void *data, int *got_frame,
}
switch (chunk_type) {
+ case MKTAG('R', 'I', 'F', 'F'):
+ if (bytestream2_get_le32(&gb) != MKTAG('W', 'E', 'B', 'P')) {
+ av_log(avctx, AV_LOG_ERROR, "missing WEBP tag\n");
+ return AVERROR_INVALIDDATA;
+ }
+ s->vp8x_flags = 0;
+ s->anmf_flags = 0;
+ s->canvas_width = 0;
+ s->canvas_height = 0;
+ s->width = 0;
+ s->height = 0;
+ s->pos_x = 0;
+ s->pos_y = 0;
+ s->has_alpha = 0;
+ s->has_exif = 0;
+ s->has_iccp = 0;
+ av_packet_unref(&s->alpha_packet);
+ break;
case MKTAG('V', 'P', '8', ' '):
if (!*got_frame) {
- ret = vp8_lossy_decode_frame(avctx, p, got_frame,
+ ret = vp8_lossy_decode_frame(avctx, s->frame, got_frame,
avpkt->data + bytestream2_tell(&gb),
chunk_size);
if (ret < 0)
@@ -1431,7 +1834,7 @@ static int webp_decode_frame(AVCodecContext *avctx, void *data, int *got_frame,
break;
case MKTAG('V', 'P', '8', 'L'):
if (!*got_frame) {
- ret = vp8_lossless_decode_frame(avctx, p, got_frame,
+ ret = vp8_lossless_decode_frame(avctx, s->frame, got_frame,
avpkt->data + bytestream2_tell(&gb),
chunk_size, 0);
if (ret < 0)
@@ -1441,14 +1844,16 @@ static int webp_decode_frame(AVCodecContext *avctx, void *data, int *got_frame,
bytestream2_skip(&gb, chunk_size);
break;
case MKTAG('V', 'P', '8', 'X'):
- if (s->width || s->height || *got_frame) {
+ if (s->canvas_width || s->canvas_height || *got_frame) {
av_log(avctx, AV_LOG_ERROR, "Canvas dimensions are already set\n");
return AVERROR_INVALIDDATA;
}
- vp8x_flags = bytestream2_get_byte(&gb);
+ s->vp8x_flags = bytestream2_get_byte(&gb);
bytestream2_skip(&gb, 3);
s->width = bytestream2_get_le24(&gb) + 1;
s->height = bytestream2_get_le24(&gb) + 1;
+ s->canvas_width = s->width;
+ s->canvas_height = s->height;
ret = av_image_check_size(s->width, s->height, 0, avctx);
if (ret < 0)
return ret;
@@ -1456,7 +1861,7 @@ static int webp_decode_frame(AVCodecContext *avctx, void *data, int *got_frame,
case MKTAG('A', 'L', 'P', 'H'): {
int alpha_header, filter_m, compression;
- if (!(vp8x_flags & VP8X_FLAG_ALPHA)) {
+ if (!(s->vp8x_flags & VP8X_FLAG_ALPHA)) {
av_log(avctx, AV_LOG_WARNING,
"ALPHA chunk present, but alpha bit not set in the "
"VP8X header\n");
@@ -1465,8 +1870,12 @@ static int webp_decode_frame(AVCodecContext *avctx, void *data, int *got_frame,
av_log(avctx, AV_LOG_ERROR, "invalid ALPHA chunk size\n");
return AVERROR_INVALIDDATA;
}
+ av_packet_unref(&s->alpha_packet);
+ ret = av_packet_ref(&s->alpha_packet, avpkt);
+ if (ret < 0)
+ return ret;
alpha_header = bytestream2_get_byte(&gb);
- s->alpha_data = avpkt->data + bytestream2_tell(&gb);
+ s->alpha_data = s->alpha_packet.data + bytestream2_tell(&gb);
s->alpha_data_size = chunk_size - 1;
bytestream2_skip(&gb, s->alpha_data_size);
@@ -1493,7 +1902,7 @@ static int webp_decode_frame(AVCodecContext *avctx, void *data, int *got_frame,
av_log(avctx, AV_LOG_VERBOSE, "Ignoring extra EXIF chunk\n");
goto exif_end;
}
- if (!(vp8x_flags & VP8X_FLAG_EXIF_METADATA))
+ if (!(s->vp8x_flags & VP8X_FLAG_EXIF_METADATA))
av_log(avctx, AV_LOG_WARNING,
"EXIF chunk present, but Exif bit not set in the "
"VP8X header\n");
@@ -1528,13 +1937,13 @@ exif_end:
bytestream2_skip(&gb, chunk_size);
break;
}
- if (!(vp8x_flags & VP8X_FLAG_ICC))
+ if (!(s->vp8x_flags & VP8X_FLAG_ICC))
av_log(avctx, AV_LOG_WARNING,
"ICCP chunk present, but ICC Profile bit not set in the "
"VP8X header\n");
s->has_iccp = 1;
- sd = av_frame_new_side_data(p, AV_FRAME_DATA_ICC_PROFILE, chunk_size);
+ sd = av_frame_new_side_data(s->frame, AV_FRAME_DATA_ICC_PROFILE, chunk_size);
if (!sd)
return AVERROR(ENOMEM);
@@ -1542,7 +1951,39 @@ exif_end:
break;
}
case MKTAG('A', 'N', 'I', 'M'):
+ if (!(s->vp8x_flags & VP8X_FLAG_ANIMATION)) {
+ av_log(avctx, AV_LOG_WARNING,
+ "ANIM chunk present, but animation bit not set in the "
+ "VP8X header\n");
+ }
+ /* background is stored as BGRA, we need ARGB in native endian */
+ s->background_argb = av_bswap32(bytestream2_get_ne32u(&gb));
+ bytestream2_skip(&gb, 2); /* loop count is ignored */
+ break;
case MKTAG('A', 'N', 'M', 'F'):
+ av_packet_unref(&s->alpha_packet);
+ s->has_alpha = 0;
+
+ if (!(s->vp8x_flags & VP8X_FLAG_ANIMATION)) {
+ av_log(avctx, AV_LOG_WARNING,
+ "ANMF chunk present, but animation bit not set in the "
+ "VP8X header\n");
+ s->vp8x_flags |= VP8X_FLAG_ANIMATION;
+ }
+ s->pos_x = bytestream2_get_le24(&gb) * 2;
+ s->pos_y = bytestream2_get_le24(&gb) * 2;
+ s->width = bytestream2_get_le24(&gb) + 1;
+ s->height = bytestream2_get_le24(&gb) + 1;
+ bytestream2_skip(&gb, 3); /* duration */
+ s->anmf_flags = bytestream2_get_byte(&gb);
+
+ if (s->width + s->pos_x > s->canvas_width ||
+ s->height + s->pos_y > s->canvas_height) {
+ av_log(avctx, AV_LOG_ERROR,
+ "frame does not fit into canvas\n");
+ return AVERROR_INVALIDDATA;
+ }
+ break;
case MKTAG('X', 'M', 'P', ' '):
AV_WL32(chunk_str, chunk_type);
av_log(avctx, AV_LOG_WARNING, "skipping unsupported chunk: %s\n",
@@ -1558,9 +1999,31 @@ exif_end:
}
}
- if (!*got_frame) {
- av_log(avctx, AV_LOG_ERROR, "image data not found\n");
- return AVERROR_INVALIDDATA;
+ if (*got_frame) {
+ if (!(s->vp8x_flags & VP8X_FLAG_ANIMATION)) {
+ /* no animation, output the decoded frame */
+ av_frame_move_ref(p, s->frame);
+ } else {
+ if (!s->canvas_frame) {
+ ret = init_canvas_frame(avctx);
+ if (ret < 0)
+ return ret;
+ }
+
+ ret = blend_frame_into_canvas(avctx);
+ if (ret < 0)
+ return ret;
+
+ ret = copy_canvas_to_frame(avctx, p);
+ if (ret < 0)
+ return ret;
+
+ ret = dispose_frame_in_canvas(avctx);
+ if (ret < 0)
+ return ret;
+ }
+
+ p->pts = avpkt->pts;
}
return avpkt->size;
@@ -1570,6 +2033,10 @@ static av_cold int webp_decode_close(AVCodecContext *avctx)
{
WebPContext *s = avctx->priv_data;
+ av_frame_free(&s->canvas_frame);
+ av_frame_free(&s->frame);
+ av_packet_unref(&s->alpha_packet);
+
if (s->initialized)
return ff_vp8_decode_free(avctx);
@@ -1582,7 +2049,8 @@ AVCodec ff_webp_decoder = {
.type = AVMEDIA_TYPE_VIDEO,
.id = AV_CODEC_ID_WEBP,
.priv_data_size = sizeof(WebPContext),
+ .init = webp_decode_init,
.decode = webp_decode_frame,
.close = webp_decode_close,
- .capabilities = AV_CODEC_CAP_DR1 | AV_CODEC_CAP_FRAME_THREADS,
+ .capabilities = AV_CODEC_CAP_DR1,
};
diff --git a/libavcodec/webp_parser.c b/libavcodec/webp_parser.c
index fdb7c38350..f959be8520 100644
--- a/libavcodec/webp_parser.c
+++ b/libavcodec/webp_parser.c
@@ -25,13 +25,16 @@
#include "libavutil/bswap.h"
#include "libavutil/common.h"
+#include "libavutil/intreadwrite.h"
#include "parser.h"
typedef struct WebPParseContext {
ParseContext pc;
+ int frame;
uint32_t fsize;
- uint32_t remaining_size;
+ uint32_t remaining_file_size;
+ uint32_t remaining_tag_size;
} WebPParseContext;
static int webp_parse(AVCodecParserContext *s, AVCodecContext *avctx,
@@ -41,62 +44,89 @@ static int webp_parse(AVCodecParserContext *s, AVCodecContext *avctx,
WebPParseContext *ctx = s->priv_data;
uint64_t state = ctx->pc.state64;
int next = END_NOT_FOUND;
- int i = 0;
+ int i, len;
- *poutbuf = NULL;
- *poutbuf_size = 0;
-
-restart:
- if (ctx->pc.frame_start_found <= 8) {
- for (; i < buf_size; i++) {
+ for (i = 0; i < buf_size;) {
+ if (ctx->remaining_tag_size) {
+ /* consuming tag */
+ len = FFMIN(ctx->remaining_tag_size, buf_size - i);
+ i += len;
+ ctx->remaining_tag_size -= len;
+ ctx->remaining_file_size -= len;
+ } else if (ctx->frame) {
+ /* consumed tag containing frame, flush it */
+ next = i;
+ ctx->frame = 0;
+ break;
+ } else {
+ /* scan for the next tag or file */
state = (state << 8) | buf[i];
- if (ctx->pc.frame_start_found == 0) {
- if ((state >> 32) == MKBETAG('R', 'I', 'F', 'F')) {
- ctx->fsize = av_bswap32(state);
- if (ctx->fsize > 15 && ctx->fsize <= UINT32_MAX - 10) {
- ctx->pc.frame_start_found = 1;
- ctx->fsize += 8;
+ i++;
+
+ if (!ctx->remaining_file_size) {
+ /* scan for the next file */
+ if (ctx->pc.frame_start_found == 4) {
+ ctx->pc.frame_start_found = 0;
+ if ((uint32_t) state == MKBETAG('W', 'E', 'B', 'P')) {
+ if (i != 12) {
+ next = i - 12;
+ state = 0;
+ break;
+ }
+ ctx->remaining_file_size = ctx->fsize - 4;
+ continue;
}
}
- } else if (ctx->pc.frame_start_found == 8) {
- if ((state >> 32) != MKBETAG('W', 'E', 'B', 'P')) {
+ if (ctx->pc.frame_start_found == 0) {
+ if ((state >> 32) == MKBETAG('R', 'I', 'F', 'F')) {
+ ctx->fsize = av_bswap32(state);
+ if (ctx->fsize > 15 && ctx->fsize <= UINT32_MAX - 10) {
+ ctx->fsize += (ctx->fsize & 1);
+ ctx->pc.frame_start_found = 1;
+ }
+ }
+ } else
+ ctx->pc.frame_start_found++;
+ } else {
+ /* read the next tag */
+ ctx->remaining_file_size--;
+ if (ctx->remaining_file_size == 0) {
ctx->pc.frame_start_found = 0;
continue;
}
ctx->pc.frame_start_found++;
- ctx->remaining_size = ctx->fsize + i - 15;
- if (ctx->pc.index + i > 15) {
- next = i - 15;
- state = 0;
- break;
- } else {
- ctx->pc.state64 = 0;
- goto restart;
+ if (ctx->pc.frame_start_found < 8)
+ continue;
+
+ switch (state >> 32) {
+ case MKBETAG('A', 'N', 'M', 'F'):
+ case MKBETAG('V', 'P', '8', ' '):
+ case MKBETAG('V', 'P', '8', 'L'):
+ ctx->frame = 1;
+ break;
+ default:
+ ctx->frame = 0;
+ break;
}
- } else if (ctx->pc.frame_start_found)
- ctx->pc.frame_start_found++;
- }
- ctx->pc.state64 = state;
- } else {
- if (ctx->remaining_size) {
- i = FFMIN(ctx->remaining_size, buf_size);
- ctx->remaining_size -= i;
- if (ctx->remaining_size)
- goto flush;
- ctx->pc.frame_start_found = 0;
- goto restart;
+ ctx->remaining_tag_size = av_bswap32(state);
+ ctx->remaining_tag_size += ctx->remaining_tag_size & 1;
+ if (ctx->remaining_tag_size > ctx->remaining_file_size) {
+ /* this is probably trash at the end of file */
+ ctx->remaining_tag_size = ctx->remaining_file_size;
+ }
+ ctx->pc.frame_start_found = 0;
+ state = 0;
+ }
}
}
+ ctx->pc.state64 = state;
-flush:
- if (ff_combine_frame(&ctx->pc, next, &buf, &buf_size) < 0)
+ if (ff_combine_frame(&ctx->pc, next, &buf, &buf_size) < 0) {
+ *poutbuf = NULL;
+ *poutbuf_size = 0;
return buf_size;
-
- if (next != END_NOT_FOUND && next < 0)
- ctx->pc.frame_start_found = FFMAX(ctx->pc.frame_start_found - i - 1, 0);
- else
- ctx->pc.frame_start_found = 0;
+ }
*poutbuf = buf;
*poutbuf_size = buf_size;
--
2.17.1
More information about the ffmpeg-devel
mailing list