[FFmpeg-devel,v5,3/7] avcodec/webp_parser: parse each frame into one packet

diff --git a/libavcodec/webp_parser.c b/libavcodec/webp_parser.c
index bd5f94dac5..da853bb1f5 100644
--- a/libavcodec/webp_parser.c
+++ b/libavcodec/webp_parser.c
@@ -25,13 +25,17 @@ 
 
 #include "libavutil/bswap.h"
 #include "libavutil/common.h"
+#include "libavutil/intreadwrite.h"
 
 #include "parser.h"
 
 typedef struct WebPParseContext {
     ParseContext pc;
+    int frame;
+    int first_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 +45,106 @@  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 {
+            /* 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 (ctx->frame || i != 12) {
+                            ctx->frame = 0;
+                            next = i - 12;
+                            state = 0;
+                            ctx->pc.frame_start_found = 0;
+                            break;
+                        }
+                        ctx->remaining_file_size = ctx->fsize - 4;
+                        ctx->first_frame = 1;
+                        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;
+                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'):
+                    if (ctx->frame) {
+                        ctx->frame = 0;
+                        next = i - 8;
+                        state = 0;
+                        ctx->pc.frame_start_found = 0;
+                        goto flush;
+                    }
+                    ctx->frame = 1;
+                    break;
+                default:
                     break;
-                } else {
-                    ctx->pc.state64 = 0;
-                    goto restart;
                 }
-            } 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 might be truncated remains before end of file */
+                    ctx->remaining_tag_size = ctx->remaining_file_size;
+                }
+                ctx->pc.frame_start_found = 0;
+                state = 0;
+            }
         }
     }
-
 flush:
-    if (ff_combine_frame(&ctx->pc, next, &buf, &buf_size) < 0)
+    ctx->pc.state64 = state;
+
+    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;
+    // Extremely simplified key frame detection:
+    // - the first frame (containing headers) is marked as a key frame
+    // - other frames are marked as non-key frames
+    if (ctx->first_frame) {
+        ctx->first_frame = 0;
+        s->pict_type = AV_PICTURE_TYPE_I;
+        s->key_frame = 1;
+    } else {
+        s->pict_type = AV_PICTURE_TYPE_P;
+        s->key_frame = 0;
+    }
 
     *poutbuf      = buf;
     *poutbuf_size = buf_size;