avconv: use avcodec_decode_audio4() instead of avcodec_decode_audio3()

[ffmpeg] / avconv.c

diff --git a/avconv.c b/avconv.c
index ab0d4eca20f4b640e5a2db5bcfc65d9112d86ea6..371a1183de4f74c9faac1e6898d5a730ff829070 100644 (file)
--- a/avconv.c
+++ b/avconv.c
@@ -113,7 +113,7 @@ static int video_sync_method= -1;
 static int audio_sync_method= 0;
 static float audio_drift_threshold= 0.1;
 static int copy_ts= 0;
-static int copy_tb;
+static int copy_tb = 1;
 static int opt_shortest = 0;
 static char *vstats_filename;
 static FILE *vstats_file;
@@ -137,8 +137,6 @@ static uint8_t *audio_buf;
 static uint8_t *audio_out;
 static unsigned int allocated_audio_out_size, allocated_audio_buf_size;
 
-static void *samples;
-
 #define DEFAULT_PASS_LOGFILENAME_PREFIX "av2pass"
 
 typedef struct InputStream {
@@ -541,7 +539,6 @@ void exit_program(int ret)
     av_free(audio_buf);
     av_free(audio_out);
     allocated_audio_buf_size= allocated_audio_out_size= 0;
-    av_free(samples);
 
 #if CONFIG_AVFILTER
     avfilter_uninit();
@@ -737,14 +734,11 @@ static void generate_silence(uint8_t* buf, enum AVSampleFormat sample_fmt, size_
     memset(buf, fill_char, size);
 }
 
-static void do_audio_out(AVFormatContext *s,
-                         OutputStream *ost,
-                         InputStream *ist,
-                         unsigned char *buf, int size)
+static void do_audio_out(AVFormatContext *s, OutputStream *ost,
+                         InputStream *ist, AVFrame *decoded_frame)
 {
     uint8_t *buftmp;
     int64_t audio_out_size, audio_buf_size;
-    int64_t allocated_for_size= size;
 
     int size_out, frame_bytes, ret, resample_changed;
     AVCodecContext *enc= ost->st->codec;
@@ -752,6 +746,9 @@ static void do_audio_out(AVFormatContext *s,
     int osize = av_get_bytes_per_sample(enc->sample_fmt);
     int isize = av_get_bytes_per_sample(dec->sample_fmt);
     const int coded_bps = av_get_bits_per_sample(enc->codec->id);
+    uint8_t *buf = decoded_frame->data[0];
+    int size     = decoded_frame->nb_samples * dec->channels * isize;
+    int64_t allocated_for_size = size;
 
 need_realloc:
     audio_buf_size= (allocated_for_size + isize*dec->channels - 1) / (isize*dec->channels);
@@ -1207,7 +1204,8 @@ static void do_video_out(AVFormatContext *s,
         av_init_packet(&pkt);
         pkt.stream_index= ost->index;
 
-        if (s->oformat->flags & AVFMT_RAWPICTURE) {
+        if (s->oformat->flags & AVFMT_RAWPICTURE &&
+            enc->codec->id == CODEC_ID_RAWVIDEO) {
             /* raw pictures are written as AVPicture structure to
                avoid any copies. We support temporarily the older
                method. */
@@ -1459,7 +1457,7 @@ static void flush_encoders(OutputStream *ost_table, int nb_ostreams)
 
         if (ost->st->codec->codec_type == AVMEDIA_TYPE_AUDIO && enc->frame_size <=1)
             continue;
-        if (ost->st->codec->codec_type == AVMEDIA_TYPE_VIDEO && (os->oformat->flags & AVFMT_RAWPICTURE))
+        if (ost->st->codec->codec_type == AVMEDIA_TYPE_VIDEO && (os->oformat->flags & AVFMT_RAWPICTURE) && enc->codec->id == CODEC_ID_RAWVIDEO)
             continue;
 
         for(;;) {
@@ -1619,39 +1617,40 @@ static void rate_emu_sleep(InputStream *ist)
 
 static int transcode_audio(InputStream *ist, AVPacket *pkt, int *got_output)
 {
-    static unsigned int samples_size = 0;
+    AVFrame *decoded_frame;
+    AVCodecContext *avctx = ist->st->codec;
     int bps = av_get_bytes_per_sample(ist->st->codec->sample_fmt);
-    uint8_t *decoded_data_buf  = NULL;
-    int      decoded_data_size = 0;
     int i, ret;
 
-    if (pkt && samples_size < FFMAX(pkt->size * bps, AVCODEC_MAX_AUDIO_FRAME_SIZE)) {
-        av_free(samples);
-        samples_size = FFMAX(pkt->size * bps, AVCODEC_MAX_AUDIO_FRAME_SIZE);
-        samples      = av_malloc(samples_size);
-    }
-    decoded_data_size = samples_size;
+    if (!(decoded_frame = avcodec_alloc_frame()))
+        return AVERROR(ENOMEM);
 
-    ret = avcodec_decode_audio3(ist->st->codec, samples, &decoded_data_size,
-                                pkt);
-    if (ret < 0)
+    ret = avcodec_decode_audio4(avctx, decoded_frame, got_output, pkt);
+    if (ret < 0) {
+        av_freep(&decoded_frame);
         return ret;
-    *got_output  = decoded_data_size > 0;
+    }
 
-    /* Some bug in mpeg audio decoder gives */
-    /* decoded_data_size < 0, it seems they are overflows */
     if (!*got_output) {
         /* no audio frame */
         return ret;
     }
 
-    decoded_data_buf = (uint8_t *)samples;
-    ist->next_pts   += ((int64_t)AV_TIME_BASE/bps * decoded_data_size) /
-                       (ist->st->codec->sample_rate * ist->st->codec->channels);
+    /* if the decoder provides a pts, use it instead of the last packet pts.
+       the decoder could be delaying output by a packet or more. */
+    if (decoded_frame->pts != AV_NOPTS_VALUE)
+        ist->next_pts = decoded_frame->pts;
+
+    /* increment next_pts to use for the case where the input stream does not
+       have timestamps or there are multiple frames in the packet */
+    ist->next_pts += ((int64_t)AV_TIME_BASE * decoded_frame->nb_samples) /
+                     avctx->sample_rate;
 
     // preprocess audio (volume)
     if (audio_volume != 256) {
-        switch (ist->st->codec->sample_fmt) {
+        int decoded_data_size = decoded_frame->nb_samples * avctx->channels * bps;
+        void *samples = decoded_frame->data[0];
+        switch (avctx->sample_fmt) {
         case AV_SAMPLE_FMT_U8:
         {
             uint8_t *volp = samples;
@@ -1712,8 +1711,7 @@ static int transcode_audio(InputStream *ist, AVPacket *pkt, int *got_output)
 
         if (!check_output_constraints(ist, ost) || !ost->encoding_needed)
             continue;
-        do_audio_out(output_files[ost->file_index].ctx, ost, ist,
-                     decoded_data_buf, decoded_data_size);
+        do_audio_out(output_files[ost->file_index].ctx, ost, ist, decoded_frame);
     }
     return ret;
 }
@@ -2067,9 +2065,7 @@ static int transcode_init(OutputFile *output_files,
             }
             memcpy(codec->extradata, icodec->extradata, icodec->extradata_size);
             codec->extradata_size = icodec->extradata_size;
-            if (!copy_tb &&
-                av_q2d(icodec->time_base)*icodec->ticks_per_frame > av_q2d(ist->st->time_base) &&
-                av_q2d(ist->st->time_base) < 1.0/500) {
+            if (!copy_tb) {
                 codec->time_base      = icodec->time_base;
                 codec->time_base.num *= icodec->ticks_per_frame;
                 av_reduce(&codec->time_base.num, &codec->time_base.den,