lavf: move AVStream.{*skip_samples.*_discard_sample} to AVStreamInternal

Those are private fields, no reason to have them exposed in a public
header.

libavformat/avformat.h

@@ -1122,35 +1122,6 @@ typedef struct AVStream {
      */
     int skip_to_keyframe;
 
-    /**
-     * Number of samples to skip at the start of the frame decoded from the next packet.
-     */
-    int skip_samples;
-
-    /**
-     * If not 0, the number of samples that should be skipped from the start of
-     * the stream (the samples are removed from packets with pts==0, which also
-     * assumes negative timestamps do not happen).
-     * Intended for use with formats such as mp3 with ad-hoc gapless audio
-     * support.
-     */
-    int64_t start_skip_samples;
-
-    /**
-     * If not 0, the first audio sample that should be discarded from the stream.
-     * This is broken by design (needs global sample count), but can't be
-     * avoided for broken by design formats such as mp3 with ad-hoc gapless
-     * audio support.
-     */
-    int64_t first_discard_sample;
-
-    /**
-     * The sample after last sample that is intended to be discarded after
-     * first_discard_sample. Works on frame boundaries only. Used to prevent
-     * early EOF if the gapless info is broken (considered concatenated mp3s).
-     */
-    int64_t last_discard_sample;
-
     /**
      * An opaque field for libavformat internal usage.
      * Must not be accessed in any way by callers.

libavformat/internal.h

@@ -225,6 +225,35 @@ struct AVStreamInternal {
 
     } *info;
 
+    /**
+     * Number of samples to skip at the start of the frame decoded from the next packet.
+     */
+    int skip_samples;
+
+    /**
+     * If not 0, the number of samples that should be skipped from the start of
+     * the stream (the samples are removed from packets with pts==0, which also
+     * assumes negative timestamps do not happen).
+     * Intended for use with formats such as mp3 with ad-hoc gapless audio
+     * support.
+     */
+    int64_t start_skip_samples;
+
+    /**
+     * If not 0, the first audio sample that should be discarded from the stream.
+     * This is broken by design (needs global sample count), but can't be
+     * avoided for broken by design formats such as mp3 with ad-hoc gapless
+     * audio support.
+     */
+    int64_t first_discard_sample;
+
+    /**
+     * The sample after last sample that is intended to be discarded after
+     * first_discard_sample. Works on frame boundaries only. Used to prevent
+     * early EOF if the gapless info is broken (considered concatenated mp3s).
+     */
+    int64_t last_discard_sample;
+
     /**
      * Number of internally decoded frames, used internally in libavformat, do not access
      * its lifetime differs from info which is why it is not in that structure.

libavformat/mov.c

@@ -3550,7 +3550,7 @@ static void mov_fix_index(MOVContext *mov, AVStream *st)
             }
 
             if (first_non_zero_audio_edit > 0)
-                st->skip_samples = msc->start_pad = 0;
+                st->internal->skip_samples = msc->start_pad = 0;
         }
 
         // While reordering frame index according to edit list we must handle properly
@@ -3625,7 +3625,7 @@ static void mov_fix_index(MOVContext *mov, AVStream *st)
                     curr_cts < edit_list_media_time && curr_cts + frame_duration > edit_list_media_time &&
                     first_non_zero_audio_edit > 0) {
                     packet_skip_samples = edit_list_media_time - curr_cts;
-                    st->skip_samples += packet_skip_samples;
+                    st->internal->skip_samples += packet_skip_samples;
 
                     // Shift the index entry timestamp by packet_skip_samples to be correct.
                     edit_list_dts_counter -= packet_skip_samples;
@@ -3658,7 +3658,7 @@ static void mov_fix_index(MOVContext *mov, AVStream *st)
                         // Increment skip_samples for the first non-zero audio edit list
                         if (st->codecpar->codec_type == AVMEDIA_TYPE_AUDIO &&
                             first_non_zero_audio_edit > 0 && st->codecpar->codec_id != AV_CODEC_ID_VORBIS) {
-                            st->skip_samples += frame_duration;
+                            st->internal->skip_samples += frame_duration;
                         }
                     }
                 }
@@ -3744,7 +3744,7 @@ static void mov_fix_index(MOVContext *mov, AVStream *st)
 
     // Update av stream length, if it ends up shorter than the track's media duration
     st->duration = FFMIN(st->duration, edit_list_dts_entry_end - start_dts);
-    msc->start_pad = st->skip_samples;
+    msc->start_pad = st->internal->skip_samples;
 
     // Free the old index and the old CTTS structures
     av_free(e_old);
@@ -7616,7 +7616,7 @@ static int mov_read_header(AVFormatContext *s)
         fix_timescale(mov, sc);
         if (st->codecpar->codec_type == AVMEDIA_TYPE_AUDIO &&
             st->codecpar->codec_id   == AV_CODEC_ID_AAC) {
-            st->skip_samples = sc->start_pad;
+            st->internal->skip_samples = sc->start_pad;
         }
         if (st->codecpar->codec_type == AVMEDIA_TYPE_VIDEO && sc->nb_frames_for_fps > 0 && sc->duration_for_fps > 0)
             av_reduce(&st->avg_frame_rate.num, &st->avg_frame_rate.den,
@@ -8105,7 +8105,7 @@ static int mov_read_seek(AVFormatContext *s, int stream_index, int64_t sample_ti
             int64_t timestamp;
             MOVStreamContext *sc = s->streams[i]->priv_data;
             st = s->streams[i];
-            st->skip_samples = (sample_time <= 0) ? sc->start_pad : 0;
+            st->internal->skip_samples = (sample_time <= 0) ? sc->start_pad : 0;
 
             if (stream_index == i)
                 continue;

libavformat/mp3dec.c

@@ -255,13 +255,13 @@ static void mp3_parse_info_tag(AVFormatContext *s, AVStream *st,
 
         mp3->start_pad = v>>12;
         mp3->  end_pad = v&4095;
-        st->start_skip_samples = mp3->start_pad + 528 + 1;
+        st->internal->start_skip_samples = mp3->start_pad + 528 + 1;
         if (mp3->frames) {
-            st->first_discard_sample = -mp3->end_pad + 528 + 1 + mp3->frames * (int64_t)spf;
-            st->last_discard_sample = mp3->frames * (int64_t)spf;
+            st->internal->first_discard_sample = -mp3->end_pad + 528 + 1 + mp3->frames * (int64_t)spf;
+            st->internal->last_discard_sample = mp3->frames * (int64_t)spf;
         }
         if (!st->start_time)
-            st->start_time = av_rescale_q(st->start_skip_samples,
+            st->start_time = av_rescale_q(st->internal->start_skip_samples,
                                             (AVRational){1, c->sample_rate},
                                             st->time_base);
         av_log(s, AV_LOG_DEBUG, "pad %d %d\n", mp3->start_pad, mp3->  end_pad);

libavformat/swfdec.c

@@ -292,7 +292,7 @@ static int swf_read_packet(AVFormatContext *s, AVPacket *pkt)
                 return AVERROR(ENOMEM);
             ast->duration = avio_rl32(pb); // number of samples
             if (((v>>4) & 15) == 2) { // MP3 sound data record
-                ast->skip_samples = avio_rl16(pb);
+                ast->internal->skip_samples = avio_rl16(pb);
                 len -= 2;
             }
             len -= 7;

libavformat/utils.c

@@ -1123,7 +1123,7 @@ static void update_initial_timestamps(AVFormatContext *s, int stream_index,
         if (st->start_time == AV_NOPTS_VALUE && pktl_it->pkt.pts != AV_NOPTS_VALUE) {
             st->start_time = pktl_it->pkt.pts;
             if (st->codecpar->codec_type == AVMEDIA_TYPE_AUDIO && st->codecpar->sample_rate)
-                st->start_time = av_sat_add64(st->start_time, av_rescale_q(st->skip_samples, (AVRational){1, st->codecpar->sample_rate}, st->time_base));
+                st->start_time = av_sat_add64(st->start_time, av_rescale_q(st->internal->skip_samples, (AVRational){1, st->codecpar->sample_rate}, st->time_base));
         }
     }
 
@@ -1136,7 +1136,7 @@ static void update_initial_timestamps(AVFormatContext *s, int stream_index,
             st->start_time = pts;
         }
         if (st->codecpar->codec_type == AVMEDIA_TYPE_AUDIO && st->codecpar->sample_rate)
-            st->start_time = av_sat_add64(st->start_time, av_rescale_q(st->skip_samples, (AVRational){1, st->codecpar->sample_rate}, st->time_base));
+            st->start_time = av_sat_add64(st->start_time, av_rescale_q(st->internal->skip_samples, (AVRational){1, st->codecpar->sample_rate}, st->time_base));
     }
 }
 
@@ -1639,25 +1639,25 @@ FF_ENABLE_DEPRECATION_WARNINGS
     if (ret >= 0) {
         AVStream *st = s->streams[pkt->stream_index];
         int discard_padding = 0;
-        if (st->first_discard_sample && pkt->pts != AV_NOPTS_VALUE) {
+        if (st->internal->first_discard_sample && pkt->pts != AV_NOPTS_VALUE) {
             int64_t pts = pkt->pts - (is_relative(pkt->pts) ? RELATIVE_TS_BASE : 0);
             int64_t sample = ts_to_samples(st, pts);
             int duration = ts_to_samples(st, pkt->duration);
             int64_t end_sample = sample + duration;
-            if (duration > 0 && end_sample >= st->first_discard_sample &&
-                sample < st->last_discard_sample)
-                discard_padding = FFMIN(end_sample - st->first_discard_sample, duration);
+            if (duration > 0 && end_sample >= st->internal->first_discard_sample &&
+                sample < st->internal->last_discard_sample)
+                discard_padding = FFMIN(end_sample - st->internal->first_discard_sample, duration);
         }
-        if (st->start_skip_samples && (pkt->pts == 0 || pkt->pts == RELATIVE_TS_BASE))
-            st->skip_samples = st->start_skip_samples;
-        if (st->skip_samples || discard_padding) {
+        if (st->internal->start_skip_samples && (pkt->pts == 0 || pkt->pts == RELATIVE_TS_BASE))
+            st->internal->skip_samples = st->internal->start_skip_samples;
+        if (st->internal->skip_samples || discard_padding) {
             uint8_t *p = av_packet_new_side_data(pkt, AV_PKT_DATA_SKIP_SAMPLES, 10);
             if (p) {
-                AV_WL32(p, st->skip_samples);
+                AV_WL32(p, st->internal->skip_samples);
                 AV_WL32(p + 4, discard_padding);
-                av_log(s, AV_LOG_DEBUG, "demuxer injecting skip %d / discard %d\n", st->skip_samples, discard_padding);
+                av_log(s, AV_LOG_DEBUG, "demuxer injecting skip %d / discard %d\n", st->internal->skip_samples, discard_padding);
             }
-            st->skip_samples = 0;
+            st->internal->skip_samples = 0;
         }
 
         if (st->internal->inject_global_side_data) {
@@ -1891,7 +1891,7 @@ void ff_read_frame_flush(AVFormatContext *s)
         if (s->internal->inject_global_side_data)
             st->internal->inject_global_side_data = 1;
 
-        st->skip_samples = 0;
+        st->internal->skip_samples = 0;
     }
 }