utils/ffmpeg: support remux

2 files changed, 187 insertions, 7 deletions

diff --git a/src/utils/ffmpeg.c b/src/utils/ffmpeg.c
index e4d9e44..694400c 100644
--- a/src/utils/ffmpeg.c
+++ b/src/utils/ffmpeg.c
@@ -9,6 +9,25 @@
 #include "../logger.h"
 #include "ffmpeg.h"
 
+#ifdef DEBUG
+static void log_packet(const AVFormatContext *fmt_ctx, const AVPacket *pkt,
+                       const char *tag) {
+  AVRational *time_base = &fmt_ctx->streams[pkt->stream_index]->time_base;
+
+  printf("%s: pts:%s pts_time:%s dts:%s dts_time:%s duration:%s "
+         "duration_time:%s stream_index:%d\n",
+         tag, av_ts2str(pkt->pts), av_ts2timestr(pkt->pts, time_base),
+         av_ts2str(pkt->dts), av_ts2timestr(pkt->dts, time_base),
+         av_ts2str(pkt->duration), av_ts2timestr(pkt->duration, time_base),
+         pkt->stream_index);
+}
+#else
+static void log_packet(const AVFormatContext *fmt_ctx, const AVPacket *pkt,
+                       const char *tag) {
+  return;
+}
+#endif
+
 int merge_av(const char *videofn, const char *audiofn, const char *outfn) {
   AVFormatContext *input1_format_context = NULL, *input2_format_context = NULL,
                   *output_format_context = NULL;
@@ -18,6 +37,16 @@ int merge_av(const char *videofn, const char *audiofn, const char *outfn) {
   int *streams_list = NULL;
   int number_of_streams = 0;
 
+  AVDictionary *opts = NULL;
+  /* Support fragmented MP4
+   * https://developer.mozilla.org/en-US/docs/Web/API/Media_Source_Extensions_API/Transcoding_assets_for_MSE
+   */
+  av_dict_set(&opts, "movflags", "frag_keyframe+empty_moov+default_base_moof",
+              0);
+  /* Enable all protocols support */
+  av_dict_set(&opts, "protocol_whitelist",
+              "file,crypto,data,http,https,tcp,tls", 0);
+
   if ((ret = avformat_open_input(&input1_format_context, videofn, NULL, NULL)) <
       0) {
     append_log("Could not open input file '%s'\n", videofn);
@@ -112,12 +141,7 @@ int merge_av(const char *videofn, const char *audiofn, const char *outfn) {
       goto end;
     }
   }
-  AVDictionary *opts = NULL;
-  /* Support fragmented MP4
-   * https://developer.mozilla.org/en-US/docs/Web/API/Media_Source_Extensions_API/Transcoding_assets_for_MSE
-   */
-  av_dict_set(&opts, "movflags", "frag_keyframe+empty_moov+default_base_moof",
-              0);
+
   ret = avformat_write_header(output_format_context, &opts);
   if (ret < 0) {
     append_log("Error occurred when opening output file\n");
@@ -128,7 +152,7 @@ int merge_av(const char *videofn, const char *audiofn, const char *outfn) {
     ret = av_read_frame(input1_format_context, &packet);
     if (ret < 0)
       break;
-    in_stream = input1_format_context->streams[packet.stream_index];
+    in_stream = input1_format_context->streams[stream_index];
     if (packet.stream_index >= number_of_streams ||
         streams_list[packet.stream_index] < 0) {
       av_packet_unref(&packet);
@@ -137,6 +161,7 @@ int merge_av(const char *videofn, const char *audiofn, const char *outfn) {
     packet.stream_index = streams_list[packet.stream_index];
     out_stream = output_format_context->streams[packet.stream_index];
     /* copy packet */
+    log_packet(input1_format_context, &packet, "in");
     packet.pts = av_rescale_q_rnd(packet.pts, in_stream->time_base,
                                   out_stream->time_base,
                                   AV_ROUND_NEAR_INF | AV_ROUND_PASS_MINMAX);
@@ -146,6 +171,7 @@ int merge_av(const char *videofn, const char *audiofn, const char *outfn) {
     packet.duration = av_rescale_q(packet.duration, in_stream->time_base,
                                    out_stream->time_base);
     packet.pos = -1;
+    log_packet(output_format_context, &packet, "out");
 
     ret = av_interleaved_write_frame(output_format_context, &packet);
     if (ret < 0) {
@@ -170,6 +196,7 @@ int merge_av(const char *videofn, const char *audiofn, const char *outfn) {
         streams_list[packet.stream_index + input1_format_context->nb_streams];
     out_stream = output_format_context->streams[packet.stream_index];
     /* copy packet */
+    log_packet(input2_format_context, &packet, "in");
     packet.pts = av_rescale_q_rnd(packet.pts, in_stream->time_base,
                                   out_stream->time_base,
                                   AV_ROUND_NEAR_INF | AV_ROUND_PASS_MINMAX);
@@ -179,6 +206,7 @@ int merge_av(const char *videofn, const char *audiofn, const char *outfn) {
     packet.duration = av_rescale_q(packet.duration, in_stream->time_base,
                                    out_stream->time_base);
     packet.pos = -1;
+    log_packet(output_format_context, &packet, "out");
 
     ret = av_interleaved_write_frame(output_format_context, &packet);
     if (ret < 0) {
@@ -211,3 +239,153 @@ end:
   }
   return 0;
 }
+
+int remux(const char *in_filename, const char *out_filename) {
+  const AVOutputFormat *ofmt = NULL;
+  AVFormatContext *ifmt_ctx = NULL, *ofmt_ctx = NULL;
+  AVPacket *pkt = NULL;
+  int ret, i;
+  int stream_index = 0;
+  int *stream_mapping = NULL;
+  int stream_mapping_size = 0;
+
+  pkt = av_packet_alloc();
+  if (!pkt) {
+    fprintf(stderr, "Could not allocate AVPacket\n");
+    return 1;
+  }
+
+  AVDictionary *opts = NULL;
+  av_dict_set(&opts, "protocol_whitelist",
+              "concat,file,http,https,tcp,tls,crypto", 0);
+
+  if ((ret = avformat_open_input(&ifmt_ctx, in_filename, 0, &opts)) < 0) {
+    fprintf(stderr, "Could not open input file '%s'\n", in_filename);
+    goto end;
+  }
+
+  if ((ret = avformat_find_stream_info(ifmt_ctx, 0)) < 0) {
+    fprintf(stderr, "Failed to retrieve input stream information.\n");
+    goto end;
+  }
+
+  av_dump_format(ifmt_ctx, 0, in_filename, 0);
+
+  avformat_alloc_output_context2(&ofmt_ctx, NULL, NULL, out_filename);
+  if (!ofmt_ctx) {
+    fprintf(stderr, "Could not create output context.\n");
+    ret = AVERROR_UNKNOWN;
+    goto end;
+  }
+
+  stream_mapping_size = ifmt_ctx->nb_streams;
+  stream_mapping = av_calloc(stream_mapping_size, sizeof(*stream_mapping));
+  if (!stream_mapping) {
+    ret = AVERROR(ENOMEM);
+    goto end;
+  }
+
+  ofmt = ofmt_ctx->oformat;
+
+  for (i = 0; i < ifmt_ctx->nb_streams; i++) {
+    AVStream *out_stream;
+    AVStream *in_stream = ifmt_ctx->streams[i];
+    AVCodecParameters *in_codecpar = in_stream->codecpar;
+
+    if (in_codecpar->codec_type != AVMEDIA_TYPE_AUDIO &&
+        in_codecpar->codec_type != AVMEDIA_TYPE_VIDEO &&
+        in_codecpar->codec_type != AVMEDIA_TYPE_SUBTITLE) {
+      stream_mapping[i] = -1;
+      continue;
+    }
+
+    stream_mapping[i] = stream_index++;
+
+    out_stream = avformat_new_stream(ofmt_ctx, NULL);
+    if (!out_stream) {
+      fprintf(stderr, "Failed allocating output stream\n");
+      ret = AVERROR_UNKNOWN;
+      goto end;
+    }
+
+    ret = avcodec_parameters_copy(out_stream->codecpar, in_codecpar);
+    if (ret < 0) {
+      fprintf(stderr, "Failed to copy codec parameters\n");
+      goto end;
+    }
+    out_stream->codecpar->codec_tag = 0;
+  }
+  av_dump_format(ofmt_ctx, 0, out_filename, 1);
+
+  if (!(ofmt->flags & AVFMT_NOFILE)) {
+    ret = avio_open(&ofmt_ctx->pb, out_filename, AVIO_FLAG_WRITE);
+    if (ret < 0) {
+      fprintf(stderr, "Could not open output file '%s'", out_filename);
+      goto end;
+    }
+  }
+
+  ret = avformat_write_header(ofmt_ctx, &opts);
+  if (ret < 0) {
+    fprintf(stderr, "Error occurred when opening output file\n");
+    goto end;
+  }
+
+  while (1) {
+    AVStream *in_stream, *out_stream;
+
+    ret = av_read_frame(ifmt_ctx, pkt);
+    if (ret < 0)
+      break;
+
+    in_stream = ifmt_ctx->streams[pkt->stream_index];
+    if (pkt->stream_index >= stream_mapping_size ||
+        stream_mapping[pkt->stream_index] < 0) {
+      av_packet_unref(pkt);
+      continue;
+    }
+
+    pkt->stream_index = stream_mapping[pkt->stream_index];
+    out_stream = ofmt_ctx->streams[pkt->stream_index];
+    log_packet(ifmt_ctx, pkt, "in");
+
+    /* copy packet */
+    av_packet_rescale_ts(pkt, in_stream->time_base, out_stream->time_base);
+    pkt->pos = -1;
+    log_packet(ofmt_ctx, pkt, "out");
+
+    ret = av_interleaved_write_frame(ofmt_ctx, pkt);
+    /* pkt is now blank (av_interleaved_write_frame() takes ownership of
+     * its contents and resets pkt), so that no unreferencing is necessary.
+     * This would be different if one used av_write_frame(). */
+    if (ret < 0) {
+      fprintf(stderr, "Error muxing packet\n");
+      break;
+    }
+  }
+
+  av_write_trailer(ofmt_ctx);
+end:
+  av_packet_free(&pkt);
+
+  avformat_close_input(&ifmt_ctx);
+
+  /* close output */
+  if (ofmt_ctx && !(ofmt->flags & AVFMT_NOFILE))
+    avio_closep(&ofmt_ctx->pb);
+  avformat_free_context(ofmt_ctx);
+
+  av_freep(&stream_mapping);
+
+  if (ret < 0 && ret != AVERROR_EOF) {
+    fprintf(stderr, "Error occurred: %s\n", av_err2str(ret));
+    return 1;
+  }
+
+  // Delete seperate files
+  if (remove(in_filename) != 0) {
+    append_log("Error deleting partial file %s\n", in_filename);
+  }
+
+  return 0;
+}
diff --git a/src/utils/ffmpeg.h b/src/utils/ffmpeg.h
index 91d79df..1ca949d 100644
--- a/src/utils/ffmpeg.h
+++ b/src/utils/ffmpeg.h
@@ -3,4 +3,6 @@
 
 int merge_av(const char *videofn, const char *audiofn, const char *outfn);
 
+int remux(const char *inputfn, const char *outfn);
+
 #endif