X-Git-Url: https://git.sesse.net/?a=blobdiff_plain;f=libavformat%2Fmov.c;h=ec57a05803301f22399c1bdaf1e4899dff25f5f8;hb=1483cfa8177176b3d5d1c611424058bb9b59cf9f;hp=cab7247cc54fddedd7c6648da915647c53b13540;hpb=318d0fcbfe5637013342d53d44bb7ea8867fb4d0;p=ffmpeg diff --git a/libavformat/mov.c b/libavformat/mov.c index cab7247cc54..3d6fef685dd 100644 --- a/libavformat/mov.c +++ b/libavformat/mov.c @@ -46,9 +46,11 @@ #include "libavutil/spherical.h" #include "libavutil/stereo3d.h" #include "libavutil/timecode.h" +#include "libavutil/dovi_meta.h" #include "libavcodec/ac3tab.h" #include "libavcodec/flac.h" #include "libavcodec/mpegaudiodecheader.h" +#include "libavcodec/mlp_parse.h" #include "avformat.h" #include "internal.h" #include "avio_internal.h" @@ -765,7 +767,8 @@ static int mov_read_hdlr(MOVContext *c, AVIOContext *pb, MOVAtom atom) title_str[title_size] = 0; if (title_str[0]) { int off = (!c->isom && title_str[0] == title_size - 1); - av_dict_set(&st->metadata, "handler_name", title_str + off, 0); + // flag added so as to not set stream handler name if already set from mdia->hdlr + av_dict_set(&st->metadata, "handler_name", title_str + off, AV_DICT_DONT_OVERWRITE); } av_freep(&title_str); } @@ -1003,6 +1006,7 @@ static int mov_read_adrm(MOVContext *c, AVIOContext *pb, MOVAtom atom) sha = av_sha_alloc(); if (!sha) return AVERROR(ENOMEM); + av_free(c->aes_decrypt); c->aes_decrypt = av_aes_alloc(); if (!c->aes_decrypt) { ret = AVERROR(ENOMEM); @@ -1127,8 +1131,8 @@ static int mov_read_ftyp(MOVContext *c, AVIOContext *pb, MOVAtom atom) return ret; } comp_brands_str[comp_brand_size] = 0; - av_dict_set(&c->fc->metadata, "compatible_brands", comp_brands_str, 0); - av_freep(&comp_brands_str); + av_dict_set(&c->fc->metadata, "compatible_brands", + comp_brands_str, AV_DICT_DONT_STRDUP_VAL); return 0; } @@ -1233,16 +1237,12 @@ static int search_frag_moof_offset(MOVFragmentIndex *frag_index, int64_t offset) static int64_t get_stream_info_time(MOVFragmentStreamInfo * frag_stream_info) { - - if (frag_stream_info) { - if (frag_stream_info->sidx_pts != AV_NOPTS_VALUE) - return frag_stream_info->sidx_pts; - if (frag_stream_info->first_tfra_pts != AV_NOPTS_VALUE) - return frag_stream_info->first_tfra_pts; - if (frag_stream_info->tfdt_dts != AV_NOPTS_VALUE) - return frag_stream_info->tfdt_dts; - } - return AV_NOPTS_VALUE; + av_assert0(frag_stream_info); + if (frag_stream_info->sidx_pts != AV_NOPTS_VALUE) + return frag_stream_info->sidx_pts; + if (frag_stream_info->first_tfra_pts != AV_NOPTS_VALUE) + return frag_stream_info->first_tfra_pts; + return frag_stream_info->tfdt_dts; } static int64_t get_frag_time(MOVFragmentIndex *frag_index, @@ -1269,7 +1269,7 @@ static int64_t get_frag_time(MOVFragmentIndex *frag_index, static int search_frag_timestamp(MOVFragmentIndex *frag_index, AVStream *st, int64_t timestamp) { - int a, b, m; + int a, b, m, m0; int64_t frag_time; int id = -1; @@ -1285,15 +1285,18 @@ static int search_frag_timestamp(MOVFragmentIndex *frag_index, b = frag_index->nb_items; while (b - a > 1) { - m = (a + b) >> 1; - frag_time = get_frag_time(frag_index, m, id); - if (frag_time != AV_NOPTS_VALUE) { - if (frag_time >= timestamp) - b = m; - if (frag_time <= timestamp) - a = m; - } + m0 = m = (a + b) >> 1; + + while (m < b && + (frag_time = get_frag_time(frag_index, m, id)) == AV_NOPTS_VALUE) + m++; + + if (m < b && frag_time <= timestamp) + a = m; + else + b = m0; } + return a; } @@ -1325,9 +1328,16 @@ static int update_frag_index(MOVContext *c, int64_t offset) return -1; for (i = 0; i < c->fc->nb_streams; i++) { + // Avoid building frag index if streams lack track id. + if (c->fc->streams[i]->id < 0) { + av_free(frag_stream_info); + return AVERROR_INVALIDDATA; + } + frag_stream_info[i].id = c->fc->streams[i]->id; frag_stream_info[i].sidx_pts = AV_NOPTS_VALUE; frag_stream_info[i].tfdt_dts = AV_NOPTS_VALUE; + frag_stream_info[i].next_trun_dts = AV_NOPTS_VALUE; frag_stream_info[i].first_tfra_pts = AV_NOPTS_VALUE; frag_stream_info[i].index_entry = -1; frag_stream_info[i].encryption_index = NULL; @@ -1365,6 +1375,9 @@ static void fix_frag_index_entries(MOVFragmentIndex *frag_index, int index, static int mov_read_moof(MOVContext *c, AVIOContext *pb, MOVAtom atom) { + // Set by mov_read_tfhd(). mov_read_trun() will reject files missing tfhd. + c->fragment.found_tfhd = 0; + if (!c->has_looked_for_mfra && c->use_mfra_for > 0) { c->has_looked_for_mfra = 1; if (pb->seekable & AVIO_SEEKABLE_NORMAL) { @@ -1386,14 +1399,14 @@ static int mov_read_moof(MOVContext *c, AVIOContext *pb, MOVAtom atom) return mov_read_default(c, pb, atom); } -static void mov_metadata_creation_time(AVDictionary **metadata, int64_t time) +static void mov_metadata_creation_time(AVDictionary **metadata, int64_t time, void *logctx) { if (time) { if(time >= 2082844800) time -= 2082844800; /* seconds between 1904-01-01 and Epoch */ if ((int64_t)(time * 1000000ULL) / 1000000 != time) { - av_log(NULL, AV_LOG_DEBUG, "creation_time is not representable\n"); + av_log(logctx, AV_LOG_DEBUG, "creation_time is not representable\n"); return; } @@ -1433,7 +1446,7 @@ static int mov_read_mdhd(MOVContext *c, AVIOContext *pb, MOVAtom atom) creation_time = avio_rb32(pb); avio_rb32(pb); /* modification time */ } - mov_metadata_creation_time(&st->metadata, creation_time); + mov_metadata_creation_time(&st->metadata, creation_time, c->fc); sc->time_scale = avio_rb32(pb); if (sc->time_scale <= 0) { @@ -1464,7 +1477,7 @@ static int mov_read_mvhd(MOVContext *c, AVIOContext *pb, MOVAtom atom) creation_time = avio_rb32(pb); avio_rb32(pb); /* modification time */ } - mov_metadata_creation_time(&c->fc->metadata, creation_time); + mov_metadata_creation_time(&c->fc->metadata, creation_time, c->fc); c->time_scale = avio_rb32(pb); /* time scale */ if (c->time_scale <= 0) { av_log(c->fc, AV_LOG_ERROR, "Invalid mvhd time scale %d, defaulting to 1\n", c->time_scale); @@ -1536,6 +1549,7 @@ static int mov_read_enda(MOVContext *c, AVIOContext *pb, MOVAtom atom) static int mov_read_colr(MOVContext *c, AVIOContext *pb, MOVAtom atom) { AVStream *st; + uint8_t *icc_profile; char color_parameter_type[5] = { 0 }; uint16_t color_primaries, color_trc, color_matrix; int ret; @@ -1548,41 +1562,51 @@ static int mov_read_colr(MOVContext *c, AVIOContext *pb, MOVAtom atom) if (ret < 0) return ret; if (strncmp(color_parameter_type, "nclx", 4) && - strncmp(color_parameter_type, "nclc", 4)) { + strncmp(color_parameter_type, "nclc", 4) && + strncmp(color_parameter_type, "prof", 4)) { av_log(c->fc, AV_LOG_WARNING, "unsupported color_parameter_type %s\n", color_parameter_type); return 0; } - color_primaries = avio_rb16(pb); - color_trc = avio_rb16(pb); - color_matrix = avio_rb16(pb); - - av_log(c->fc, AV_LOG_TRACE, - "%s: pri %d trc %d matrix %d", - color_parameter_type, color_primaries, color_trc, color_matrix); - - if (!strncmp(color_parameter_type, "nclx", 4)) { - uint8_t color_range = avio_r8(pb) >> 7; - av_log(c->fc, AV_LOG_TRACE, " full %"PRIu8"", color_range); - if (color_range) - st->codecpar->color_range = AVCOL_RANGE_JPEG; - else - st->codecpar->color_range = AVCOL_RANGE_MPEG; + if (!strncmp(color_parameter_type, "prof", 4)) { + icc_profile = av_stream_new_side_data(st, AV_PKT_DATA_ICC_PROFILE, atom.size - 4); + if (!icc_profile) + return AVERROR(ENOMEM); + ret = ffio_read_size(pb, icc_profile, atom.size - 4); + if (ret < 0) + return ret; } + else { + color_primaries = avio_rb16(pb); + color_trc = avio_rb16(pb); + color_matrix = avio_rb16(pb); - if (!av_color_primaries_name(color_primaries)) - color_primaries = AVCOL_PRI_UNSPECIFIED; - if (!av_color_transfer_name(color_trc)) - color_trc = AVCOL_TRC_UNSPECIFIED; - if (!av_color_space_name(color_matrix)) - color_matrix = AVCOL_SPC_UNSPECIFIED; + av_log(c->fc, AV_LOG_TRACE, + "%s: pri %d trc %d matrix %d", + color_parameter_type, color_primaries, color_trc, color_matrix); + + if (!strncmp(color_parameter_type, "nclx", 4)) { + uint8_t color_range = avio_r8(pb) >> 7; + av_log(c->fc, AV_LOG_TRACE, " full %"PRIu8"", color_range); + if (color_range) + st->codecpar->color_range = AVCOL_RANGE_JPEG; + else + st->codecpar->color_range = AVCOL_RANGE_MPEG; + } - st->codecpar->color_primaries = color_primaries; - st->codecpar->color_trc = color_trc; - st->codecpar->color_space = color_matrix; - av_log(c->fc, AV_LOG_TRACE, "\n"); + if (!av_color_primaries_name(color_primaries)) + color_primaries = AVCOL_PRI_UNSPECIFIED; + if (!av_color_transfer_name(color_trc)) + color_trc = AVCOL_TRC_UNSPECIFIED; + if (!av_color_space_name(color_matrix)) + color_matrix = AVCOL_SPC_UNSPECIFIED; + st->codecpar->color_primaries = color_primaries; + st->codecpar->color_trc = color_trc; + st->codecpar->color_space = color_matrix; + av_log(c->fc, AV_LOG_TRACE, "\n"); + } return 0; } @@ -1613,7 +1637,7 @@ static int mov_read_fiel(MOVContext *c, AVIOContext *pb, MOVAtom atom) } } if (decoded_field_order == AV_FIELD_UNKNOWN && mov_field_order) { - av_log(NULL, AV_LOG_ERROR, "Unknown MOV field order 0x%04x\n", mov_field_order); + av_log(c->fc, AV_LOG_ERROR, "Unknown MOV field order 0x%04x\n", mov_field_order); } st->codecpar->field_order = decoded_field_order; @@ -1790,19 +1814,19 @@ static int mov_read_aclr(MOVContext *c, AVIOContext *pb, MOVAtom atom) par->color_range = AVCOL_RANGE_JPEG; break; default: - av_log(c, AV_LOG_WARNING, "ignored unknown aclr value (%d)\n", range_value); + av_log(c->fc, AV_LOG_WARNING, "ignored unknown aclr value (%d)\n", range_value); break; } - ff_dlog(c, "color_range: %d\n", par->color_range); + ff_dlog(c->fc, "color_range: %d\n", par->color_range); } else { /* For some reason the whole atom was not added to the extradata */ - av_log(c, AV_LOG_ERROR, "aclr not decoded - incomplete atom\n"); + av_log(c->fc, AV_LOG_ERROR, "aclr not decoded - incomplete atom\n"); } } else { - av_log(c, AV_LOG_ERROR, "aclr not decoded - unable to add atom to extradata\n"); + av_log(c->fc, AV_LOG_ERROR, "aclr not decoded - unable to add atom to extradata\n"); } } else { - av_log(c, AV_LOG_WARNING, "aclr not decoded - unexpected size %"PRId64"\n", atom.size); + av_log(c->fc, AV_LOG_WARNING, "aclr not decoded - unexpected size %"PRId64"\n", atom.size); } } @@ -1830,7 +1854,6 @@ static int mov_read_wave(MOVContext *c, AVIOContext *pb, MOVAtom atom) st->codecpar->codec_id == AV_CODEC_ID_QDMC || st->codecpar->codec_id == AV_CODEC_ID_SPEEX) { // pass all frma atom to codec, needed at least for QDMC and QDM2 - av_freep(&st->codecpar->extradata); ret = ff_get_extradata(c->fc, st->codecpar, pb, atom.size); if (ret < 0) return ret; @@ -1894,13 +1917,19 @@ static int mov_read_glbl(MOVContext *c, AVIOContext *pb, MOVAtom atom) return mov_read_default(c, pb, atom); } if (st->codecpar->extradata_size > 1 && st->codecpar->extradata) { - av_log(c, AV_LOG_WARNING, "ignoring multiple glbl\n"); + av_log(c->fc, AV_LOG_WARNING, "ignoring multiple glbl\n"); return 0; } - av_freep(&st->codecpar->extradata); ret = ff_get_extradata(c->fc, st->codecpar, pb, atom.size); if (ret < 0) return ret; + if (atom.type == MKTAG('h','v','c','C') && st->codecpar->codec_tag == MKTAG('d','v','h','1')) + /* HEVC-based Dolby Vision derived from hvc1. + Happens to match with an identifier + previously utilized for DV. Thus, if we have + the hvcC extradata box available as specified, + set codec to HEVC */ + st->codecpar->codec_id = AV_CODEC_ID_HEVC; return 0; } @@ -1923,7 +1952,6 @@ static int mov_read_dvc1(MOVContext *c, AVIOContext *pb, MOVAtom atom) return 0; avio_seek(pb, 6, SEEK_CUR); - av_freep(&st->codecpar->extradata); ret = ff_get_extradata(c->fc, st->codecpar, pb, atom.size - 7); if (ret < 0) return ret; @@ -1951,7 +1979,6 @@ static int mov_read_strf(MOVContext *c, AVIOContext *pb, MOVAtom atom) return AVERROR_INVALIDDATA; avio_skip(pb, 40); - av_freep(&st->codecpar->extradata); ret = ff_get_extradata(c->fc, st->codecpar, pb, atom.size - 40); if (ret < 0) return ret; @@ -1965,6 +1992,10 @@ static int mov_read_stco(MOVContext *c, AVIOContext *pb, MOVAtom atom) MOVStreamContext *sc; unsigned int i, entries; + if (c->trak_index < 0) { + av_log(c->fc, AV_LOG_WARNING, "STCO outside TRAK\n"); + return 0; + } if (c->fc->nb_streams < 1) return 0; st = c->fc->streams[c->fc->nb_streams-1]; @@ -2031,6 +2062,8 @@ static int mov_codec_id(AVStream *st, uint32_t format) id = ff_codec_get_id(ff_codec_movsubtitle_tags, format); if (id > 0) st->codecpar->codec_type = AVMEDIA_TYPE_SUBTITLE; + else + id = ff_codec_get_id(ff_codec_movdata_tags, format); } } @@ -2117,8 +2150,8 @@ static void mov_parse_stsd_audio(MOVContext *c, AVIOContext *pb, // Read QT version 1 fields. In version 0 these do not exist. av_log(c->fc, AV_LOG_TRACE, "version =%d, isom =%d\n", version, c->isom); if (!c->isom || - (compatible_brands && strstr(compatible_brands->value, "qt "))) { - + (compatible_brands && strstr(compatible_brands->value, "qt ")) || + (sc->stsd_version == 0 && version > 0)) { if (version == 1) { sc->samples_per_frame = avio_rb32(pb); avio_rb32(pb); /* bytes per packet */ @@ -2238,7 +2271,7 @@ static int mov_rewrite_dvd_sub_extradata(AVStream *st) { char buf[256] = {0}; uint8_t *src = st->codecpar->extradata; - int i; + int i, ret; if (st->codecpar->extradata_size != 64) return 0; @@ -2258,12 +2291,9 @@ static int mov_rewrite_dvd_sub_extradata(AVStream *st) if (av_strlcat(buf, "\n", sizeof(buf)) >= sizeof(buf)) return 0; - av_freep(&st->codecpar->extradata); - st->codecpar->extradata_size = 0; - st->codecpar->extradata = av_mallocz(strlen(buf) + AV_INPUT_BUFFER_PADDING_SIZE); - if (!st->codecpar->extradata) - return AVERROR(ENOMEM); - st->codecpar->extradata_size = strlen(buf); + ret = ff_alloc_extradata(st->codecpar, strlen(buf)); + if (ret < 0) + return ret; memcpy(st->codecpar->extradata, buf, st->codecpar->extradata_size); return 0; @@ -2287,8 +2317,8 @@ static int mov_parse_stsd_data(MOVContext *c, AVIOContext *pb, int val; val = AV_RB32(st->codecpar->extradata + 4); tmcd_ctx->tmcd_flags = val; - st->avg_frame_rate.num = st->codecpar->extradata[16]; /* number of frame */ - st->avg_frame_rate.den = 1; + st->avg_frame_rate.num = AV_RB32(st->codecpar->extradata + 8); /* timescale */ + st->avg_frame_rate.den = AV_RB32(st->codecpar->extradata + 12); /* frameDuration */ #if FF_API_LAVF_AVCTX FF_DISABLE_DEPRECATION_WARNINGS st->codec->time_base = av_inv_q(st->avg_frame_rate); @@ -2489,18 +2519,16 @@ int ff_mov_read_stsd_entries(MOVContext *c, AVIOContext *pb, int entries) "size=%"PRId64" 4CC=%s codec_type=%d\n", size, av_fourcc2str(format), st->codecpar->codec_type); + st->codecpar->codec_id = id; if (st->codecpar->codec_type==AVMEDIA_TYPE_VIDEO) { - st->codecpar->codec_id = id; mov_parse_stsd_video(c, pb, st, sc); } else if (st->codecpar->codec_type==AVMEDIA_TYPE_AUDIO) { - st->codecpar->codec_id = id; mov_parse_stsd_audio(c, pb, st, sc); if (st->codecpar->sample_rate < 0) { av_log(c->fc, AV_LOG_ERROR, "Invalid sample rate %d\n", st->codecpar->sample_rate); return AVERROR_INVALIDDATA; } } else if (st->codecpar->codec_type==AVMEDIA_TYPE_SUBTITLE){ - st->codecpar->codec_id = id; mov_parse_stsd_subtitle(c, pb, st, sc, size - (avio_tell(pb) - start_pos)); } else { @@ -2551,11 +2579,12 @@ static int mov_read_stsd(MOVContext *c, AVIOContext *pb, MOVAtom atom) st = c->fc->streams[c->fc->nb_streams - 1]; sc = st->priv_data; - avio_r8(pb); /* version */ + sc->stsd_version = avio_r8(pb); avio_rb24(pb); /* flags */ entries = avio_rb32(pb); - if (entries <= 0) { + /* Each entry contains a size (4 bytes) and format (4 bytes). */ + if (entries <= 0 || entries > atom.size / 8) { av_log(c->fc, AV_LOG_ERROR, "invalid STSD entries %d\n", entries); return AVERROR_INVALIDDATA; } @@ -2650,6 +2679,10 @@ static int mov_read_stsc(MOVContext *c, AVIOContext *pb, MOVAtom atom) sc->stsc_data[i].id < 1) { av_log(c->fc, AV_LOG_WARNING, "STSC entry %d is invalid (first=%d count=%d id=%d)\n", i, sc->stsc_data[i].first, sc->stsc_data[i].count, sc->stsc_data[i].id); if (i+1 >= sc->stsc_count) { + if (sc->stsc_data[i].count == 0 && i > 0) { + sc->stsc_count --; + continue; + } sc->stsc_data[i].first = FFMAX(sc->stsc_data[i].first, first_min); if (i > 0 && sc->stsc_data[i].first <= sc->stsc_data[i-1].first) sc->stsc_data[i].first = FFMIN(sc->stsc_data[i-1].first + 1LL, INT_MAX); @@ -2685,8 +2718,11 @@ static inline int64_t mov_get_stsc_samples(MOVStreamContext *sc, unsigned int in if (mov_stsc_index_valid(index, sc->stsc_count)) chunk_count = sc->stsc_data[index + 1].first - sc->stsc_data[index].first; - else + else { + // Validation for stsc / stco happens earlier in mov_read_stsc + mov_read_trak. + av_assert0(sc->stsc_data[index].first <= sc->chunk_count); chunk_count = sc->chunk_count - (sc->stsc_data[index].first - 1); + } return sc->stsc_data[index].count * (int64_t)chunk_count; } @@ -2841,7 +2877,8 @@ static int mov_read_stsz(MOVContext *c, AVIOContext *pb, MOVAtom atom) if (ret < 0) { av_freep(&sc->sample_sizes); av_free(buf); - return ret; + av_log(c->fc, AV_LOG_WARNING, "STSZ atom truncated\n"); + return 0; } init_get_bits(&gb, buf, 8*num_bytes); @@ -2913,12 +2950,6 @@ static int mov_read_stts(MOVContext *c, AVIOContext *pb, MOVAtom atom) av_log(c->fc, AV_LOG_TRACE, "sample_count=%d, sample_duration=%d\n", sample_count, sample_duration); - if ( i+1 == entries - && i - && sample_count == 1 - && total_sample_count > 100 - && sample_duration/10 > duration / total_sample_count) - sample_duration = duration / total_sample_count; duration+=(int64_t)sample_duration*(uint64_t)sample_count; total_sample_count+=sample_count; } @@ -2927,7 +2958,7 @@ static int mov_read_stts(MOVContext *c, AVIOContext *pb, MOVAtom atom) if (duration > 0 && duration <= INT64_MAX - sc->duration_for_fps && - total_sample_count <= INT64_MAX - sc->nb_frames_for_fps + total_sample_count <= INT_MAX - sc->nb_frames_for_fps ) { sc->duration_for_fps += duration; sc->nb_frames_for_fps += total_sample_count; @@ -2945,11 +2976,45 @@ static int mov_read_stts(MOVContext *c, AVIOContext *pb, MOVAtom atom) return 0; } -static void mov_update_dts_shift(MOVStreamContext *sc, int duration) +static int mov_read_sdtp(MOVContext *c, AVIOContext *pb, MOVAtom atom) +{ + AVStream *st; + MOVStreamContext *sc; + int64_t i, entries; + + if (c->fc->nb_streams < 1) + return 0; + st = c->fc->streams[c->fc->nb_streams - 1]; + sc = st->priv_data; + + avio_r8(pb); /* version */ + avio_rb24(pb); /* flags */ + entries = atom.size - 4; + + av_log(c->fc, AV_LOG_TRACE, "track[%u].sdtp.entries = %" PRId64 "\n", + c->fc->nb_streams - 1, entries); + + if (sc->sdtp_data) + av_log(c->fc, AV_LOG_WARNING, "Duplicated SDTP atom\n"); + av_freep(&sc->sdtp_data); + sc->sdtp_count = 0; + + sc->sdtp_data = av_mallocz(entries); + if (!sc->sdtp_data) + return AVERROR(ENOMEM); + + for (i = 0; i < entries && !pb->eof_reached; i++) + sc->sdtp_data[i] = avio_r8(pb); + sc->sdtp_count = i; + + return 0; +} + +static void mov_update_dts_shift(MOVStreamContext *sc, int duration, void *logctx) { if (duration < 0) { if (duration == INT_MIN) { - av_log(NULL, AV_LOG_WARNING, "mov_update_dts_shift(): dts_shift set to %d\n", INT_MAX); + av_log(logctx, AV_LOG_WARNING, "mov_update_dts_shift(): dts_shift set to %d\n", INT_MAX); duration++; } sc->dts_shift = FFMAX(sc->dts_shift, -duration); @@ -3007,7 +3072,7 @@ static int mov_read_ctts(MOVContext *c, AVIOContext *pb, MOVAtom atom) } if (i+2fc); } sc->ctts_count = ctts_count; @@ -3300,22 +3365,21 @@ static void mov_estimate_video_delay(MOVContext *c, AVStream* st) { int ctts_sample = 0; int64_t pts_buf[MAX_REORDER_DELAY + 1]; // Circular buffer to sort pts. int buf_start = 0; - int buf_size = 0; int j, r, num_swaps; + for (j = 0; j < MAX_REORDER_DELAY + 1; j++) + pts_buf[j] = INT64_MIN; + if (st->codecpar->video_delay <= 0 && msc->ctts_data && st->codecpar->codec_id == AV_CODEC_ID_H264) { st->codecpar->video_delay = 0; for(ind = 0; ind < st->nb_index_entries && ctts_ind < msc->ctts_count; ++ind) { - if (buf_size == (MAX_REORDER_DELAY + 1)) { - // If circular buffer is full, then move the first element forward. - buf_start = (buf_start + 1) % buf_size; - } else { - ++buf_size; - } - // Point j to the last elem of the buffer and insert the current pts there. - j = (buf_start + buf_size - 1) % buf_size; + j = buf_start; + buf_start = (buf_start + 1); + if (buf_start == MAX_REORDER_DELAY + 1) + buf_start = 0; + pts_buf[j] = st->index_entries[ind].timestamp + msc->ctts_data[ctts_ind].duration; // The timestamps that are already in the sorted buffer, and are greater than the @@ -3326,10 +3390,13 @@ static void mov_estimate_video_delay(MOVContext *c, AVStream* st) { // go through, to keep this buffer in sorted order. num_swaps = 0; while (j != buf_start) { - r = (j - 1 + buf_size) % buf_size; + r = j - 1; + if (r < 0) r = MAX_REORDER_DELAY; if (pts_buf[j] < pts_buf[r]) { FFSWAP(int64_t, pts_buf[j], pts_buf[r]); ++num_swaps; + } else { + break; } j = r; } @@ -3431,6 +3498,7 @@ static void mov_fix_index(MOVContext *mov, AVStream *st) MOVIndexRange *current_index_range; int i; int found_keyframe_after_edit = 0; + int found_non_empty_edit = 0; if (!msc->elst_data || msc->elst_count <= 0 || nb_old <= 0) { return; @@ -3477,10 +3545,11 @@ static void mov_fix_index(MOVContext *mov, AVStream *st) edit_list_dts_counter = edit_list_dts_entry_end; edit_list_dts_entry_end += edit_list_duration; num_discarded_begin = 0; - if (edit_list_media_time == -1) { + if (!found_non_empty_edit && edit_list_media_time == -1) { empty_edits_sum_duration += edit_list_duration; continue; } + found_non_empty_edit = 1; // If we encounter a non-negative edit list reset the skip_samples/start_pad fields and set them // according to the edit list below. @@ -3673,12 +3742,16 @@ static void mov_fix_index(MOVContext *mov, AVStream *st) // If the minimum pts turns out to be greater than zero after fixing the index, then we subtract the // dts by that amount to make the first pts zero. - if (st->codecpar->codec_type == AVMEDIA_TYPE_VIDEO && msc->min_corrected_pts > 0) { - av_log(mov->fc, AV_LOG_DEBUG, "Offset DTS by %"PRId64" to make first pts zero.\n", msc->min_corrected_pts); - for (i = 0; i < st->nb_index_entries; ++i) { - st->index_entries[i].timestamp -= msc->min_corrected_pts; + if (st->codecpar->codec_type == AVMEDIA_TYPE_VIDEO) { + if (msc->min_corrected_pts > 0) { + av_log(mov->fc, AV_LOG_DEBUG, "Offset DTS by %"PRId64" to make first pts zero.\n", msc->min_corrected_pts); + for (i = 0; i < st->nb_index_entries; ++i) { + st->index_entries[i].timestamp -= msc->min_corrected_pts; + } } } + // Start time should be equal to zero or the duration of any empty edits. + st->start_time = empty_edits_sum_duration; // 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); @@ -4013,6 +4086,14 @@ static void mov_build_index(MOVContext *mov, AVStream *st) mov_fix_index(mov, st); } + // Update start time of the stream. + if (st->start_time == AV_NOPTS_VALUE && st->codecpar->codec_type == AVMEDIA_TYPE_VIDEO && st->nb_index_entries > 0) { + st->start_time = st->index_entries[0].timestamp + sc->dts_shift; + if (sc->ctts_data) { + st->start_time += sc->ctts_data[0].duration; + } + } + mov_estimate_video_delay(mov, st); } @@ -4135,7 +4216,7 @@ static int mov_read_trak(MOVContext *c, AVIOContext *pb, MOVAtom atom) st = avformat_new_stream(c->fc, NULL); if (!st) return AVERROR(ENOMEM); - st->id = c->fc->nb_streams; + st->id = -1; sc = av_mallocz(sizeof(MOVStreamContext)); if (!sc) return AVERROR(ENOMEM); @@ -4149,6 +4230,13 @@ static int mov_read_trak(MOVContext *c, AVIOContext *pb, MOVAtom atom) c->trak_index = -1; + // Here stsc refers to a chunk not described in stco. This is technically invalid, + // but we can overlook it (clearing stsc) whenever stts_count == 0 (indicating no samples). + if (!sc->chunk_count && !sc->stts_count && sc->stsc_count) { + sc->stsc_count = 0; + av_freep(&sc->stsc_data); + } + /* sanity checks */ if ((sc->chunk_count && (!sc->stts_count || !sc->stsc_count || (!sc->sample_size && !sc->sample_count))) || @@ -4157,7 +4245,7 @@ static int mov_read_trak(MOVContext *c, AVIOContext *pb, MOVAtom atom) st->index); return 0; } - if (sc->chunk_count && sc->stsc_count && sc->stsc_data[ sc->stsc_count - 1 ].first > sc->chunk_count) { + if (sc->stsc_count && sc->stsc_data[ sc->stsc_count - 1 ].first > sc->chunk_count) { av_log(c->fc, AV_LOG_ERROR, "stream %d, contradictionary STSC and STCO\n", st->index); return AVERROR_INVALIDDATA; @@ -4382,7 +4470,10 @@ static int mov_read_custom(MOVContext *c, AVIOContext *pb, MOVAtom atom) static int mov_read_meta(MOVContext *c, AVIOContext *pb, MOVAtom atom) { while (atom.size > 8) { - uint32_t tag = avio_rl32(pb); + uint32_t tag; + if (avio_feof(pb)) + return AVERROR_EOF; + tag = avio_rl32(pb); atom.size -= 4; if (tag == MKTAG('h','d','l','r')) { avio_seek(pb, -8, SEEK_CUR); @@ -4419,6 +4510,11 @@ static int mov_read_tkhd(MOVContext *c, AVIOContext *pb, MOVAtom atom) st = c->fc->streams[c->fc->nb_streams-1]; sc = st->priv_data; + // Each stream (trak) should have exactly 1 tkhd. This catches bad files and + // avoids corrupting AVStreams mapped to an earlier tkhd. + if (st->id != -1) + return AVERROR_INVALIDDATA; + version = avio_r8(pb); flags = avio_rb24(pb); st->disposition |= (flags & MOV_TKHD_FLAG_ENABLED) ? AV_DISPOSITION_DEFAULT : 0; @@ -4520,6 +4616,7 @@ static int mov_read_tfhd(MOVContext *c, AVIOContext *pb, MOVAtom atom) MOVFragment *frag = &c->fragment; MOVTrackExt *trex = NULL; int flags, track_id, i; + MOVFragmentStreamInfo * frag_stream_info; avio_r8(pb); /* version */ flags = avio_rb24(pb); @@ -4527,17 +4624,18 @@ static int mov_read_tfhd(MOVContext *c, AVIOContext *pb, MOVAtom atom) track_id = avio_rb32(pb); if (!track_id) return AVERROR_INVALIDDATA; - frag->track_id = track_id; - set_frag_stream(&c->frag_index, track_id); for (i = 0; i < c->trex_count; i++) - if (c->trex_data[i].track_id == frag->track_id) { + if (c->trex_data[i].track_id == track_id) { trex = &c->trex_data[i]; break; } if (!trex) { - av_log(c->fc, AV_LOG_ERROR, "could not find corresponding trex\n"); - return AVERROR_INVALIDDATA; + av_log(c->fc, AV_LOG_WARNING, "could not find corresponding trex (id %u)\n", track_id); + return 0; } + c->fragment.found_tfhd = 1; + frag->track_id = track_id; + set_frag_stream(&c->frag_index, track_id); frag->base_data_offset = flags & MOV_TFHD_BASE_DATA_OFFSET ? avio_rb64(pb) : flags & MOV_TFHD_DEFAULT_BASE_IS_MOOF ? @@ -4552,6 +4650,10 @@ static int mov_read_tfhd(MOVContext *c, AVIOContext *pb, MOVAtom atom) avio_rb32(pb) : trex->flags; av_log(c->fc, AV_LOG_TRACE, "frag flags 0x%x\n", frag->flags); + frag_stream_info = get_current_frag_stream_info(&c->frag_index); + if (frag_stream_info) + frag_stream_info->next_trun_dts = AV_NOPTS_VALUE; + return 0; } @@ -4616,8 +4718,8 @@ static int mov_read_tfdt(MOVContext *c, AVIOContext *pb, MOVAtom atom) } } if (!st) { - av_log(c->fc, AV_LOG_ERROR, "could not find corresponding track id %u\n", frag->track_id); - return AVERROR_INVALIDDATA; + av_log(c->fc, AV_LOG_WARNING, "could not find corresponding track id %u\n", frag->track_id); + return 0; } sc = st->priv_data; if (sc->pseudo_stream_id + 1 != frag->stsd_id && sc->pseudo_stream_id != -1) @@ -4656,6 +4758,11 @@ static int mov_read_trun(MOVContext *c, AVIOContext *pb, MOVAtom atom) AVIndexEntry *new_entries; MOVFragmentStreamInfo * frag_stream_info; + if (!frag->found_tfhd) { + av_log(c->fc, AV_LOG_ERROR, "trun track id unknown, no tfhd was found\n"); + return AVERROR_INVALIDDATA; + } + for (i = 0; i < c->fc->nb_streams; i++) { if (c->fc->streams[i]->id == frag->track_id) { st = c->fc->streams[i]; @@ -4663,8 +4770,8 @@ static int mov_read_trun(MOVContext *c, AVIOContext *pb, MOVAtom atom) } } if (!st) { - av_log(c->fc, AV_LOG_ERROR, "could not find corresponding track id %u\n", frag->track_id); - return AVERROR_INVALIDDATA; + av_log(c->fc, AV_LOG_WARNING, "could not find corresponding track id %u\n", frag->track_id); + return 0; } sc = st->priv_data; if (sc->pseudo_stream_id+1 != frag->stsd_id && sc->pseudo_stream_id != -1) @@ -4685,6 +4792,7 @@ static int mov_read_trun(MOVContext *c, AVIOContext *pb, MOVAtom atom) break; } } + av_assert0(index_entry_pos <= st->nb_index_entries); avio_r8(pb); /* version */ flags = avio_rb24(pb); @@ -4699,11 +4807,18 @@ static int mov_read_trun(MOVContext *c, AVIOContext *pb, MOVAtom atom) frag_stream_info = get_current_frag_stream_info(&c->frag_index); if (frag_stream_info) { - if (frag_stream_info->first_tfra_pts != AV_NOPTS_VALUE && + if (frag_stream_info->next_trun_dts != AV_NOPTS_VALUE) { + dts = frag_stream_info->next_trun_dts - sc->time_offset; + } else if (frag_stream_info->first_tfra_pts != AV_NOPTS_VALUE && c->use_mfra_for == FF_MOV_FLAG_MFRA_PTS) { pts = frag_stream_info->first_tfra_pts; av_log(c->fc, AV_LOG_DEBUG, "found mfra time %"PRId64 ", using it for pts\n", pts); + } else if (frag_stream_info->first_tfra_pts != AV_NOPTS_VALUE && + c->use_mfra_for == FF_MOV_FLAG_MFRA_DTS) { + dts = frag_stream_info->first_tfra_pts; + av_log(c->fc, AV_LOG_DEBUG, "found mfra time %"PRId64 + ", using it for dts\n", pts); } else if (frag_stream_info->sidx_pts != AV_NOPTS_VALUE) { // FIXME: sidx earliest_presentation_time is *PTS*, s.b. // pts = frag_stream_info->sidx_pts; @@ -4729,12 +4844,12 @@ static int mov_read_trun(MOVContext *c, AVIOContext *pb, MOVAtom atom) av_log(c->fc, AV_LOG_TRACE, "first sample flags 0x%x\n", first_sample_flags); // realloc space for new index entries - if((unsigned)st->nb_index_entries + entries >= UINT_MAX / sizeof(AVIndexEntry)) { + if((uint64_t)st->nb_index_entries + entries >= UINT_MAX / sizeof(AVIndexEntry)) { entries = UINT_MAX / sizeof(AVIndexEntry) - st->nb_index_entries; av_log(c->fc, AV_LOG_ERROR, "Failed to add index entry\n"); } - if (entries <= 0) - return -1; + if (entries == 0) + return 0; requested_size = (st->nb_index_entries + entries) * sizeof(AVIndexEntry); new_entries = av_fast_realloc(st->index_entries, @@ -4795,7 +4910,7 @@ static int mov_read_trun(MOVContext *c, AVIOContext *pb, MOVAtom atom) if (flags & MOV_TRUN_SAMPLE_FLAGS) sample_flags = avio_rb32(pb); if (flags & MOV_TRUN_SAMPLE_CTS) ctts_duration = avio_rb32(pb); - mov_update_dts_shift(sc, ctts_duration); + mov_update_dts_shift(sc, ctts_duration, c->fc); if (pts != AV_NOPTS_VALUE) { dts = pts - sc->dts_shift; if (flags & MOV_TRUN_SAMPLE_CTS) { @@ -4848,12 +4963,14 @@ static int mov_read_trun(MOVContext *c, AVIOContext *pb, MOVAtom atom) sc->data_size += sample_size; if (sample_duration <= INT64_MAX - sc->duration_for_fps && - 1 <= INT64_MAX - sc->nb_frames_for_fps + 1 <= INT_MAX - sc->nb_frames_for_fps ) { sc->duration_for_fps += sample_duration; sc->nb_frames_for_fps ++; } } + if (frag_stream_info) + frag_stream_info->next_trun_dts = dts + sc->time_offset; if (i < entries) { // EOF found before reading all entries. Fix the hole this would // leave in index_entries and ctts_data @@ -4968,7 +5085,7 @@ static int mov_read_sidx(MOVContext *c, AVIOContext *pb, MOVAtom atom) return AVERROR_PATCHWELCOME; } avio_rb32(pb); // sap_flags - timestamp = av_rescale_q(pts, st->time_base, timescale); + timestamp = av_rescale_q(pts, timescale, st->time_base); index = update_frag_index(c, offset); frag_stream_info = get_frag_stream_info(&c->frag_index, index, track_id); @@ -4998,7 +5115,7 @@ static int mov_read_sidx(MOVContext *c, AVIOContext *pb, MOVAtom atom) } } } - for (i = 0; i < c->fc->nb_streams; i++) { + if (ref_st) for (i = 0; i < c->fc->nb_streams; i++) { st = c->fc->streams[i]; sc = st->priv_data; if (!sc->has_sidx) { @@ -5169,6 +5286,34 @@ static int mov_read_tmcd(MOVContext *c, AVIOContext *pb, MOVAtom atom) return 0; } +static int mov_read_av1c(MOVContext *c, AVIOContext *pb, MOVAtom atom) +{ + AVStream *st; + int ret; + + if (c->fc->nb_streams < 1) + return 0; + st = c->fc->streams[c->fc->nb_streams - 1]; + + if (atom.size < 4) { + av_log(c->fc, AV_LOG_ERROR, "Empty AV1 Codec Configuration Box\n"); + return AVERROR_INVALIDDATA; + } + + /* For now, propagate only the OBUs, if any. Once libavcodec is + updated to handle isobmff style extradata this can be removed. */ + avio_skip(pb, 4); + + if (atom.size == 4) + return 0; + + ret = ff_get_extradata(c->fc, st->codecpar, pb, atom.size - 4); + if (ret < 0) + return ret; + + return 0; +} + static int mov_read_vpcc(MOVContext *c, AVIOContext *pb, MOVAtom atom) { AVStream *st; @@ -5216,9 +5361,7 @@ static int mov_read_vpcc(MOVContext *c, AVIOContext *pb, MOVAtom atom) static int mov_read_smdm(MOVContext *c, AVIOContext *pb, MOVAtom atom) { MOVStreamContext *sc; - const int chroma_den = 50000; - const int luma_den = 10000; - int i, j, version; + int i, version; if (c->fc->nb_streams < 1) return AVERROR_INVALIDDATA; @@ -5241,17 +5384,15 @@ static int mov_read_smdm(MOVContext *c, AVIOContext *pb, MOVAtom atom) if (!sc->mastering) return AVERROR(ENOMEM); - for (i = 0; i < 3; i++) - for (j = 0; j < 2; j++) - sc->mastering->display_primaries[i][j] = - av_make_q(lrint(((double)avio_rb16(pb) / (1 << 16)) * chroma_den), chroma_den); - for (i = 0; i < 2; i++) - sc->mastering->white_point[i] = - av_make_q(lrint(((double)avio_rb16(pb) / (1 << 16)) * chroma_den), chroma_den); - sc->mastering->max_luminance = - av_make_q(lrint(((double)avio_rb32(pb) / (1 << 8)) * luma_den), luma_den); - sc->mastering->min_luminance = - av_make_q(lrint(((double)avio_rb32(pb) / (1 << 14)) * luma_den), luma_den); + for (i = 0; i < 3; i++) { + sc->mastering->display_primaries[i][0] = av_make_q(avio_rb16(pb), 1 << 16); + sc->mastering->display_primaries[i][1] = av_make_q(avio_rb16(pb), 1 << 16); + } + sc->mastering->white_point[0] = av_make_q(avio_rb16(pb), 1 << 16); + sc->mastering->white_point[1] = av_make_q(avio_rb16(pb), 1 << 16); + + sc->mastering->max_luminance = av_make_q(avio_rb32(pb), 1 << 8); + sc->mastering->min_luminance = av_make_q(avio_rb32(pb), 1 << 14); sc->mastering->has_primaries = 1; sc->mastering->has_luminance = 1; @@ -5691,8 +5832,8 @@ static int mov_read_uuid(MOVContext *c, AVIOContext *pb, MOVAtom atom) return AVERROR_INVALIDDATA; } buffer[len] = '\0'; - av_dict_set(&c->fc->metadata, "xmp", buffer, 0); - av_free(buffer); + av_dict_set(&c->fc->metadata, "xmp", + buffer, AV_DICT_DONT_STRDUP_VAL); } else { // skip all uuid atom, which makes it fast for long uuid-xmp file ret = avio_skip(pb, len); @@ -5799,6 +5940,9 @@ static int get_current_encryption_info(MOVContext *c, MOVEncryptionIndex **encry *sc = st->priv_data; if (!frag_stream_info->encryption_index) { + // If this stream isn't encrypted, don't create the index. + if (!(*sc)->cenc.default_encrypted_sample) + return 0; frag_stream_info->encryption_index = av_mallocz(sizeof(*frag_stream_info->encryption_index)); if (!frag_stream_info->encryption_index) return AVERROR(ENOMEM); @@ -5814,6 +5958,9 @@ static int get_current_encryption_info(MOVContext *c, MOVEncryptionIndex **encry *sc = st->priv_data; if (!(*sc)->cenc.encryption_index) { + // If this stream isn't encrypted, don't create the index. + if (!(*sc)->cenc.default_encrypted_sample) + return 0; (*sc)->cenc.encryption_index = av_mallocz(sizeof(*frag_stream_info->encryption_index)); if (!(*sc)->cenc.encryption_index) return AVERROR(ENOMEM); @@ -5830,6 +5977,11 @@ static int mov_read_sample_encryption_info(MOVContext *c, AVIOContext *pb, MOVSt unsigned int subsample_count; AVSubsampleEncryptionInfo *subsamples; + if (!sc->cenc.default_encrypted_sample) { + av_log(c->fc, AV_LOG_ERROR, "Missing schm or tenc\n"); + return AVERROR_INVALIDDATA; + } + *sample = av_encryption_info_clone(sc->cenc.default_encrypted_sample); if (!*sample) return AVERROR(ENOMEM); @@ -6023,7 +6175,7 @@ static int mov_read_saiz(MOVContext *c, AVIOContext *pb, MOVAtom atom) MOVEncryptionIndex *encryption_index; MOVStreamContext *sc; int ret; - unsigned int sample_count; + unsigned int sample_count, aux_info_type, aux_info_param; ret = get_current_encryption_info(c, &encryption_index, &sc); if (ret != 1) @@ -6042,14 +6194,33 @@ static int mov_read_saiz(MOVContext *c, AVIOContext *pb, MOVAtom atom) avio_r8(pb); /* version */ if (avio_rb24(pb) & 0x01) { /* flags */ - if (avio_rb32(pb) != sc->cenc.default_encrypted_sample->scheme) { - av_log(c->fc, AV_LOG_DEBUG, "Ignoring saiz box with non-zero aux_info_type\n"); - return 0; - } - if (avio_rb32(pb) != 0) { - av_log(c->fc, AV_LOG_DEBUG, "Ignoring saiz box with non-zero aux_info_type_parameter\n"); - return 0; + aux_info_type = avio_rb32(pb); + aux_info_param = avio_rb32(pb); + if (sc->cenc.default_encrypted_sample) { + if (aux_info_type != sc->cenc.default_encrypted_sample->scheme) { + av_log(c->fc, AV_LOG_DEBUG, "Ignoring saiz box with non-zero aux_info_type\n"); + return 0; + } + if (aux_info_param != 0) { + av_log(c->fc, AV_LOG_DEBUG, "Ignoring saiz box with non-zero aux_info_type_parameter\n"); + return 0; + } + } else { + // Didn't see 'schm' or 'tenc', so this isn't encrypted. + if ((aux_info_type == MKBETAG('c','e','n','c') || + aux_info_type == MKBETAG('c','e','n','s') || + aux_info_type == MKBETAG('c','b','c','1') || + aux_info_type == MKBETAG('c','b','c','s')) && + aux_info_param == 0) { + av_log(c->fc, AV_LOG_ERROR, "Saw encrypted saiz without schm/tenc\n"); + return AVERROR_INVALIDDATA; + } else { + return 0; + } } + } else if (!sc->cenc.default_encrypted_sample) { + // Didn't see 'schm' or 'tenc', so this isn't encrypted. + return 0; } encryption_index->auxiliary_info_default_size = avio_r8(pb); @@ -6077,7 +6248,8 @@ static int mov_read_saio(MOVContext *c, AVIOContext *pb, MOVAtom atom) MOVEncryptionIndex *encryption_index; MOVStreamContext *sc; int i, ret; - unsigned int version, entry_count, alloc_size = 0; + unsigned int version, entry_count, aux_info_type, aux_info_param; + unsigned int alloc_size = 0; ret = get_current_encryption_info(c, &encryption_index, &sc); if (ret != 1) @@ -6096,14 +6268,33 @@ static int mov_read_saio(MOVContext *c, AVIOContext *pb, MOVAtom atom) version = avio_r8(pb); /* version */ if (avio_rb24(pb) & 0x01) { /* flags */ - if (avio_rb32(pb) != sc->cenc.default_encrypted_sample->scheme) { - av_log(c->fc, AV_LOG_DEBUG, "Ignoring saio box with non-zero aux_info_type\n"); - return 0; - } - if (avio_rb32(pb) != 0) { - av_log(c->fc, AV_LOG_DEBUG, "Ignoring saio box with non-zero aux_info_type_parameter\n"); - return 0; + aux_info_type = avio_rb32(pb); + aux_info_param = avio_rb32(pb); + if (sc->cenc.default_encrypted_sample) { + if (aux_info_type != sc->cenc.default_encrypted_sample->scheme) { + av_log(c->fc, AV_LOG_DEBUG, "Ignoring saio box with non-zero aux_info_type\n"); + return 0; + } + if (aux_info_param != 0) { + av_log(c->fc, AV_LOG_DEBUG, "Ignoring saio box with non-zero aux_info_type_parameter\n"); + return 0; + } + } else { + // Didn't see 'schm' or 'tenc', so this isn't encrypted. + if ((aux_info_type == MKBETAG('c','e','n','c') || + aux_info_type == MKBETAG('c','e','n','s') || + aux_info_type == MKBETAG('c','b','c','1') || + aux_info_type == MKBETAG('c','b','c','s')) && + aux_info_param == 0) { + av_log(c->fc, AV_LOG_ERROR, "Saw encrypted saio without schm/tenc\n"); + return AVERROR_INVALIDDATA; + } else { + return 0; + } } + } else if (!sc->cenc.default_encrypted_sample) { + // Didn't see 'schm' or 'tenc', so this isn't encrypted. + return 0; } entry_count = avio_rb32(pb); @@ -6146,6 +6337,116 @@ static int mov_read_saio(MOVContext *c, AVIOContext *pb, MOVAtom atom) return 0; } +static int mov_read_pssh(MOVContext *c, AVIOContext *pb, MOVAtom atom) +{ + AVEncryptionInitInfo *info, *old_init_info; + uint8_t **key_ids; + AVStream *st; + uint8_t *side_data, *extra_data, *old_side_data; + size_t side_data_size; + int ret = 0, old_side_data_size; + unsigned int version, kid_count, extra_data_size, alloc_size = 0; + + if (c->fc->nb_streams < 1) + return 0; + st = c->fc->streams[c->fc->nb_streams-1]; + + version = avio_r8(pb); /* version */ + avio_rb24(pb); /* flags */ + + info = av_encryption_init_info_alloc(/* system_id_size */ 16, /* num_key_ids */ 0, + /* key_id_size */ 16, /* data_size */ 0); + if (!info) + return AVERROR(ENOMEM); + + if (avio_read(pb, info->system_id, 16) != 16) { + av_log(c->fc, AV_LOG_ERROR, "Failed to read the system id\n"); + ret = AVERROR_INVALIDDATA; + goto finish; + } + + if (version > 0) { + kid_count = avio_rb32(pb); + if (kid_count >= INT_MAX / sizeof(*key_ids)) { + ret = AVERROR(ENOMEM); + goto finish; + } + + for (unsigned int i = 0; i < kid_count && !pb->eof_reached; i++) { + unsigned int min_kid_count = FFMIN(FFMAX(i + 1, 1024), kid_count); + key_ids = av_fast_realloc(info->key_ids, &alloc_size, + min_kid_count * sizeof(*key_ids)); + if (!key_ids) { + ret = AVERROR(ENOMEM); + goto finish; + } + info->key_ids = key_ids; + + info->key_ids[i] = av_mallocz(16); + if (!info->key_ids[i]) { + ret = AVERROR(ENOMEM); + goto finish; + } + info->num_key_ids = i + 1; + + if (avio_read(pb, info->key_ids[i], 16) != 16) { + av_log(c->fc, AV_LOG_ERROR, "Failed to read the key id\n"); + ret = AVERROR_INVALIDDATA; + goto finish; + } + } + + if (pb->eof_reached) { + av_log(c->fc, AV_LOG_ERROR, "Hit EOF while reading pssh\n"); + ret = AVERROR_INVALIDDATA; + goto finish; + } + } + + extra_data_size = avio_rb32(pb); + ret = mov_try_read_block(pb, extra_data_size, &extra_data); + if (ret < 0) + goto finish; + + av_freep(&info->data); // malloc(0) may still allocate something. + info->data = extra_data; + info->data_size = extra_data_size; + + // If there is existing initialization data, append to the list. + old_side_data = av_stream_get_side_data(st, AV_PKT_DATA_ENCRYPTION_INIT_INFO, &old_side_data_size); + if (old_side_data) { + old_init_info = av_encryption_init_info_get_side_data(old_side_data, old_side_data_size); + if (old_init_info) { + // Append to the end of the list. + for (AVEncryptionInitInfo *cur = old_init_info;; cur = cur->next) { + if (!cur->next) { + cur->next = info; + break; + } + } + info = old_init_info; + } else { + // Assume existing side-data will be valid, so the only error we could get is OOM. + ret = AVERROR(ENOMEM); + goto finish; + } + } + + side_data = av_encryption_init_info_add_side_data(info, &side_data_size); + if (!side_data) { + ret = AVERROR(ENOMEM); + goto finish; + } + ret = av_stream_add_side_data(st, AV_PKT_DATA_ENCRYPTION_INIT_INFO, + side_data, side_data_size); + if (ret < 0) + av_free(side_data); + +finish: + av_encryption_init_info_free(info); + return ret; +} + static int mov_read_schm(MOVContext *c, AVIOContext *pb, MOVAtom atom) { AVStream *st; @@ -6222,8 +6523,13 @@ static int mov_read_tenc(MOVContext *c, AVIOContext *pb, MOVAtom atom) return AVERROR(ENOMEM); } sc->cenc.per_sample_iv_size = avio_r8(pb); + if (sc->cenc.per_sample_iv_size != 0 && sc->cenc.per_sample_iv_size != 8 && + sc->cenc.per_sample_iv_size != 16) { + av_log(c->fc, AV_LOG_ERROR, "invalid per-sample IV size value\n"); + return AVERROR_INVALIDDATA; + } if (avio_read(pb, sc->cenc.default_encrypted_sample->key_id, 16) != 16) { - av_log(c->fc, AV_LOG_ERROR, "failed to read the default key ID"); + av_log(c->fc, AV_LOG_ERROR, "failed to read the default key ID\n"); return AVERROR_INVALIDDATA; } @@ -6235,7 +6541,7 @@ static int mov_read_tenc(MOVContext *c, AVIOContext *pb, MOVAtom atom) } if (avio_read(pb, sc->cenc.default_encrypted_sample->iv, iv_size) != iv_size) { - av_log(c->fc, AV_LOG_ERROR, "failed to read the default IV"); + av_log(c->fc, AV_LOG_ERROR, "failed to read the default IV\n"); return AVERROR_INVALIDDATA; } } @@ -6336,14 +6642,14 @@ static int cenc_decrypt(MOVContext *c, MOVStreamContext *sc, AVEncryptionInfo *s return 0; } -static int cenc_filter(MOVContext *mov, MOVStreamContext *sc, AVPacket *pkt, int current_index) +static int cenc_filter(MOVContext *mov, AVStream* st, MOVStreamContext *sc, AVPacket *pkt, int current_index) { MOVFragmentStreamInfo *frag_stream_info; MOVEncryptionIndex *encryption_index; AVEncryptionInfo *encrypted_sample; - int encrypted_index; + int encrypted_index, ret; - frag_stream_info = get_current_frag_stream_info(&mov->frag_index); + frag_stream_info = get_frag_stream_info(&mov->frag_index, mov->frag_index.current, st->id); encrypted_index = current_index; encryption_index = NULL; if (frag_stream_info) { @@ -6385,6 +6691,15 @@ static int cenc_filter(MOVContext *mov, MOVStreamContext *sc, AVPacket *pkt, int if (mov->decryption_key) { return cenc_decrypt(mov, sc, encrypted_sample, pkt->data, pkt->size); + } else { + size_t size; + uint8_t *side_data = av_encryption_info_add_side_data(encrypted_sample, &size); + if (!side_data) + return AVERROR(ENOMEM); + ret = av_packet_add_side_data(pkt, AV_PKT_DATA_ENCRYPTION_INFO, side_data, size); + if (ret < 0) + av_free(side_data); + return ret; } } @@ -6394,9 +6709,10 @@ static int cenc_filter(MOVContext *mov, MOVStreamContext *sc, AVPacket *pkt, int static int mov_read_dops(MOVContext *c, AVIOContext *pb, MOVAtom atom) { const int OPUS_SEEK_PREROLL_MS = 80; + int ret; AVStream *st; size_t size; - int16_t pre_skip; + uint16_t pre_skip; if (c->fc->nb_streams < 1) return 0; @@ -6414,8 +6730,8 @@ static int mov_read_dops(MOVContext *c, AVIOContext *pb, MOVAtom atom) /* OpusSpecificBox size plus magic for Ogg OpusHead header. */ size = atom.size + 8; - if (ff_alloc_extradata(st->codecpar, size)) - return AVERROR(ENOMEM); + if ((ret = ff_alloc_extradata(st->codecpar, size)) < 0) + return ret; AV_WL32(st->codecpar->extradata, MKTAG('O','p','u','s')); AV_WL32(st->codecpar->extradata + 4, MKTAG('H','e','a','d')); @@ -6439,12 +6755,102 @@ static int mov_read_dops(MOVContext *c, AVIOContext *pb, MOVAtom atom) return 0; } +static int mov_read_dmlp(MOVContext *c, AVIOContext *pb, MOVAtom atom) +{ + AVStream *st; + unsigned format_info; + int channel_assignment, channel_assignment1, channel_assignment2; + int ratebits; + + if (c->fc->nb_streams < 1) + return 0; + st = c->fc->streams[c->fc->nb_streams-1]; + + if (atom.size < 10) + return AVERROR_INVALIDDATA; + + format_info = avio_rb32(pb); + + ratebits = (format_info >> 28) & 0xF; + channel_assignment1 = (format_info >> 15) & 0x1F; + channel_assignment2 = format_info & 0x1FFF; + if (channel_assignment2) + channel_assignment = channel_assignment2; + else + channel_assignment = channel_assignment1; + + st->codecpar->frame_size = 40 << (ratebits & 0x7); + st->codecpar->sample_rate = mlp_samplerate(ratebits); + st->codecpar->channels = truehd_channels(channel_assignment); + st->codecpar->channel_layout = truehd_layout(channel_assignment); + + return 0; +} + +static int mov_read_dvcc_dvvc(MOVContext *c, AVIOContext *pb, MOVAtom atom) +{ + AVStream *st; + uint32_t buf; + AVDOVIDecoderConfigurationRecord *dovi; + size_t dovi_size; + int ret; + + if (c->fc->nb_streams < 1) + return 0; + st = c->fc->streams[c->fc->nb_streams-1]; + + if ((uint64_t)atom.size > (1<<30) || atom.size < 4) + return AVERROR_INVALIDDATA; + + dovi = av_dovi_alloc(&dovi_size); + if (!dovi) + return AVERROR(ENOMEM); + + dovi->dv_version_major = avio_r8(pb); + dovi->dv_version_minor = avio_r8(pb); + + buf = avio_rb16(pb); + dovi->dv_profile = (buf >> 9) & 0x7f; // 7 bits + dovi->dv_level = (buf >> 3) & 0x3f; // 6 bits + dovi->rpu_present_flag = (buf >> 2) & 0x01; // 1 bit + dovi->el_present_flag = (buf >> 1) & 0x01; // 1 bit + dovi->bl_present_flag = buf & 0x01; // 1 bit + if (atom.size >= 24) { // 4 + 4 + 4 * 4 + buf = avio_r8(pb); + dovi->dv_bl_signal_compatibility_id = (buf >> 4) & 0x0f; // 4 bits + } else { + // 0 stands for None + // Dolby Vision V1.2.93 profiles and levels + dovi->dv_bl_signal_compatibility_id = 0; + } + + ret = av_stream_add_side_data(st, AV_PKT_DATA_DOVI_CONF, + (uint8_t *)dovi, dovi_size); + if (ret < 0) { + av_freep(dovi); + return ret; + } + + av_log(c, AV_LOG_TRACE, "DOVI in dvcC/dvvC box, version: %d.%d, profile: %d, level: %d, " + "rpu flag: %d, el flag: %d, bl flag: %d, compatibility id: %d\n", + dovi->dv_version_major, dovi->dv_version_minor, + dovi->dv_profile, dovi->dv_level, + dovi->rpu_present_flag, + dovi->el_present_flag, + dovi->bl_present_flag, + dovi->dv_bl_signal_compatibility_id + ); + + return 0; +} + static const MOVParseTableEntry mov_default_parse_table[] = { { MKTAG('A','C','L','R'), mov_read_aclr }, { MKTAG('A','P','R','G'), mov_read_avid }, { MKTAG('A','A','L','P'), mov_read_avid }, { MKTAG('A','R','E','S'), mov_read_ares }, { MKTAG('a','v','s','s'), mov_read_avss }, +{ MKTAG('a','v','1','C'), mov_read_av1c }, { MKTAG('c','h','p','l'), mov_read_chpl }, { MKTAG('c','o','6','4'), mov_read_stco }, { MKTAG('c','o','l','r'), mov_read_colr }, @@ -6486,6 +6892,7 @@ static const MOVParseTableEntry mov_default_parse_table[] = { { MKTAG('s','t','s','z'), mov_read_stsz }, /* sample size */ { MKTAG('s','t','t','s'), mov_read_stts }, { MKTAG('s','t','z','2'), mov_read_stsz }, /* compact sample size */ +{ MKTAG('s','d','t','p'), mov_read_sdtp }, /* independent and disposable samples */ { MKTAG('t','k','h','d'), mov_read_tkhd }, /* track header */ { MKTAG('t','f','d','t'), mov_read_tfdt }, { MKTAG('t','f','h','d'), mov_read_tfhd }, /* track fragment header */ @@ -6518,6 +6925,7 @@ static const MOVParseTableEntry mov_default_parse_table[] = { { MKTAG('s','e','n','c'), mov_read_senc }, { MKTAG('s','a','i','z'), mov_read_saiz }, { MKTAG('s','a','i','o'), mov_read_saio }, +{ MKTAG('p','s','s','h'), mov_read_pssh }, { MKTAG('s','c','h','m'), mov_read_schm }, { MKTAG('s','c','h','i'), mov_read_default }, { MKTAG('t','e','n','c'), mov_read_tenc }, @@ -6525,11 +6933,14 @@ static const MOVParseTableEntry mov_default_parse_table[] = { { MKTAG('s','t','3','d'), mov_read_st3d }, /* stereoscopic 3D video box */ { MKTAG('s','v','3','d'), mov_read_sv3d }, /* spherical video box */ { MKTAG('d','O','p','s'), mov_read_dops }, +{ MKTAG('d','m','l','p'), mov_read_dmlp }, { MKTAG('S','m','D','m'), mov_read_smdm }, { MKTAG('C','o','L','L'), mov_read_coll }, { MKTAG('v','p','c','C'), mov_read_vpcc }, { MKTAG('m','d','c','v'), mov_read_mdcv }, { MKTAG('c','l','l','i'), mov_read_clli }, +{ MKTAG('d','v','c','C'), mov_read_dvcc_dvvc }, +{ MKTAG('d','v','v','C'), mov_read_dvcc_dvvc }, { 0, NULL } }; @@ -6554,10 +6965,10 @@ static int mov_read_default(MOVContext *c, AVIOContext *pb, MOVAtom atom) if (atom.size >= 8) { a.size = avio_rb32(pb); a.type = avio_rl32(pb); - if (a.type == MKTAG('f','r','e','e') && + if (((a.type == MKTAG('f','r','e','e') && c->moov_retry) || + a.type == MKTAG('h','o','o','v')) && a.size >= 8 && - c->fc->strict_std_compliance < FF_COMPLIANCE_STRICT && - c->moov_retry) { + c->fc->strict_std_compliance < FF_COMPLIANCE_STRICT) { uint8_t buf[8]; uint32_t *type = (uint32_t *)buf + 1; if (avio_read(pb, buf, 8) != 8) @@ -6565,7 +6976,7 @@ static int mov_read_default(MOVContext *c, AVIOContext *pb, MOVAtom atom) avio_seek(pb, -8, SEEK_CUR); if (*type == MKTAG('m','v','h','d') || *type == MKTAG('c','m','o','v')) { - av_log(c->fc, AV_LOG_ERROR, "Detected moov in a free atom.\n"); + av_log(c->fc, AV_LOG_ERROR, "Detected moov in a free or hoov atom.\n"); a.type = MKTAG('m','o','o','v'); } } @@ -6654,7 +7065,7 @@ static int mov_read_default(MOVContext *c, AVIOContext *pb, MOVAtom atom) return 0; } -static int mov_probe(AVProbeData *p) +static int mov_probe(const AVProbeData *p) { int64_t offset; uint32_t tag; @@ -6948,6 +7359,7 @@ static int mov_read_close(AVFormatContext *s) av_freep(&sc->sample_sizes); av_freep(&sc->keyframes); av_freep(&sc->stts_data); + av_freep(&sc->sdtp_data); av_freep(&sc->stps_data); av_freep(&sc->elst_data); av_freep(&sc->rap_group); @@ -7392,7 +7804,8 @@ static int mov_switch_root(AVFormatContext *s, int64_t target, int index) mov->next_root_atom = 0; if (index < 0 || index >= mov->frag_index.nb_items) index = search_frag_moof_offset(&mov->frag_index, target); - if (index < mov->frag_index.nb_items) { + if (index < mov->frag_index.nb_items && + mov->frag_index.item[index].moof_offset == target) { if (index + 1 < mov->frag_index.nb_items) mov->next_root_atom = mov->frag_index.item[index + 1].moof_offset; if (mov->frag_index.item[index].headers_read) @@ -7530,11 +7943,18 @@ static int mov_read_packet(AVFormatContext *s, AVPacket *pkt) } else { int64_t next_dts = (sc->current_sample < st->nb_index_entries) ? st->index_entries[sc->current_sample].timestamp : st->duration; - pkt->duration = next_dts - pkt->dts; + + if (next_dts >= pkt->dts) + pkt->duration = next_dts - pkt->dts; pkt->pts = pkt->dts; } if (st->discard == AVDISCARD_ALL) goto retry; + if (sc->sdtp_data && sc->current_sample <= sc->sdtp_count) { + uint8_t sample_flags = sc->sdtp_data[sc->current_sample - 1]; + uint8_t sample_is_depended_on = (sample_flags >> 2) & 0x3; + pkt->flags |= sample_is_depended_on == MOV_SAMPLE_DEPENDENCY_NO ? AV_PKT_FLAG_DISPOSABLE : 0; + } pkt->flags |= sample->flags & AVINDEX_KEYFRAME ? AV_PKT_FLAG_KEY : 0; pkt->pos = sample->pos; @@ -7560,9 +7980,10 @@ static int mov_read_packet(AVFormatContext *s, AVPacket *pkt) if (mov->aax_mode) aax_filter(pkt->data, pkt->size, mov); - ret = cenc_filter(mov, sc, pkt, current_index); - if (ret < 0) + ret = cenc_filter(mov, st, sc, pkt, current_index); + if (ret < 0) { return ret; + } return 0; } @@ -7623,6 +8044,7 @@ static int mov_seek_stream(AVFormatContext *s, AVStream *st, int64_t timestamp, } /* adjust stsd index */ + if (sc->chunk_count) { time_sample = 0; for (i = 0; i < sc->stsc_count; i++) { int64_t next = time_sample + mov_get_stsc_samples(sc, i); @@ -7634,6 +8056,7 @@ static int mov_seek_stream(AVFormatContext *s, AVStream *st, int64_t timestamp, av_assert0(next == (int)next); time_sample = next; } + } return sample; } @@ -7698,7 +8121,7 @@ static const AVOption mov_options[] = { OFFSET(use_absolute_path), AV_OPT_TYPE_BOOL, {.i64 = 0}, 0, 1, FLAGS}, {"seek_streams_individually", - "Seek each stream individually to the to the closest point", + "Seek each stream individually to the closest point", OFFSET(seek_individually), AV_OPT_TYPE_BOOL, { .i64 = 1 }, 0, 1, FLAGS}, {"ignore_editlist", "Ignore the edit list atom.", OFFSET(ignore_editlist), AV_OPT_TYPE_BOOL, {.i64 = 0}, @@ -7749,11 +8172,11 @@ AVInputFormat ff_mov_demuxer = { .long_name = NULL_IF_CONFIG_SMALL("QuickTime / MOV"), .priv_class = &mov_class, .priv_data_size = sizeof(MOVContext), - .extensions = "mov,mp4,m4a,3gp,3g2,mj2", + .extensions = "mov,mp4,m4a,3gp,3g2,mj2,psp,m4b,ism,ismv,isma,f4v", .read_probe = mov_probe, .read_header = mov_read_header, .read_packet = mov_read_packet, .read_close = mov_read_close, .read_seek = mov_read_seek, - .flags = AVFMT_NO_BYTE_SEEK, + .flags = AVFMT_NO_BYTE_SEEK | AVFMT_SEEK_TO_PTS, };