diff options
Diffstat (limited to 'libavformat/mov.c')
-rw-r--r-- | libavformat/mov.c | 835 |
1 files changed, 678 insertions, 157 deletions
diff --git a/libavformat/mov.c b/libavformat/mov.c index e3dc67b..ff85a1f 100644 --- a/libavformat/mov.c +++ b/libavformat/mov.c @@ -6,20 +6,20 @@ * first version by Francois Revol <revol@free.fr> * seek function by Gael Chardon <gael.dev@4now.net> * - * This file is part of Libav. + * This file is part of FFmpeg. * - * Libav is free software; you can redistribute it and/or + * FFmpeg is free software; you can redistribute it and/or * modify it under the terms of the GNU Lesser General Public * License as published by the Free Software Foundation; either * version 2.1 of the License, or (at your option) any later version. * - * Libav is distributed in the hope that it will be useful, + * FFmpeg is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU * Lesser General Public License for more details. * * You should have received a copy of the GNU Lesser General Public - * License along with Libav; if not, write to the Free Software + * License along with FFmpeg; if not, write to the Free Software * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA */ @@ -36,6 +36,8 @@ #include "libavutil/mathematics.h" #include "libavutil/avstring.h" #include "libavutil/dict.h" +#include "libavutil/opt.h" +#include "libavutil/timecode.h" #include "libavcodec/ac3tab.h" #include "avformat.h" #include "internal.h" @@ -159,7 +161,7 @@ static int mov_read_mac_string(MOVContext *c, AVIOContext *pb, int len, uint8_t t, c = avio_r8(pb); if (c < 0x80 && p < end) *p++ = c; - else + else if (p < end) PUT_UTF8(mac_to_unicode[c-0x80], t, if (p < end) *p++ = t;); } *p = 0; @@ -208,6 +210,17 @@ static int mov_read_covr(MOVContext *c, AVIOContext *pb, int type, int len) return 0; } +static int mov_metadata_raw(MOVContext *c, AVIOContext *pb, + unsigned len, const char *key) +{ + char *value = av_malloc(len + 1); + if (!value) + return AVERROR(ENOMEM); + avio_read(pb, value, len); + value[len] = 0; + return av_dict_set(&c->fc->metadata, key, value, AV_DICT_DONT_STRDUP_VAL); +} + static int mov_read_udta_string(MOVContext *c, AVIOContext *pb, MOVAtom atom) { #ifdef MOV_EXPORT_ALL_METADATA @@ -225,8 +238,12 @@ static int mov_read_udta_string(MOVContext *c, AVIOContext *pb, MOVAtom atom) case MKTAG(0xa9,'A','R','T'): key = "artist"; break; case MKTAG( 'a','A','R','T'): key = "album_artist"; break; case MKTAG(0xa9,'w','r','t'): key = "composer"; break; + case MKTAG( 'c','p','i','l'): key = "compilation"; + parse = mov_metadata_int8_no_padding; break; case MKTAG( 'c','p','r','t'): case MKTAG(0xa9,'c','p','y'): key = "copyright"; break; + case MKTAG(0xa9,'g','r','p'): key = "grouping"; break; + case MKTAG(0xa9,'l','y','r'): key = "lyrics"; break; case MKTAG(0xa9,'c','m','t'): case MKTAG(0xa9,'i','n','f'): key = "comment"; break; case MKTAG(0xa9,'a','l','b'): key = "album"; break; @@ -237,6 +254,9 @@ static int mov_read_udta_string(MOVContext *c, AVIOContext *pb, MOVAtom atom) case MKTAG(0xa9,'t','o','o'): case MKTAG(0xa9,'s','w','r'): key = "encoder"; break; case MKTAG(0xa9,'e','n','c'): key = "encoder"; break; + case MKTAG(0xa9,'m','a','k'): key = "make"; break; + case MKTAG(0xa9,'m','o','d'): key = "model"; break; + case MKTAG(0xa9,'x','y','z'): key = "location"; break; case MKTAG( 'd','e','s','c'): key = "description";break; case MKTAG( 'l','d','e','s'): key = "synopsis"; break; case MKTAG( 't','v','s','h'): key = "show"; break; @@ -256,6 +276,10 @@ static int mov_read_udta_string(MOVContext *c, AVIOContext *pb, MOVAtom atom) parse = mov_metadata_int8_no_padding; break; case MKTAG( 'p','g','a','p'): key = "gapless_playback"; parse = mov_metadata_int8_no_padding; break; + case MKTAG( '@','P','R','M'): + return mov_metadata_raw(c, pb, atom.size, "premiere_version"); + case MKTAG( '@','P','R','Q'): + return mov_metadata_raw(c, pb, atom.size, "quicktime_version"); } if (c->itunes_metadata && atom.size > 8) { @@ -303,7 +327,9 @@ static int mov_read_udta_string(MOVContext *c, AVIOContext *pb, MOVAtom atom) if (data_type == 3 || (data_type == 0 && (langcode < 0x400 || langcode == 0x7fff))) { // MAC Encoded mov_read_mac_string(c, pb, str_size, str, sizeof(str)); } else { - avio_read(pb, str, str_size); + int ret = avio_read(pb, str, str_size); + if (ret != str_size) + return ret < 0 ? ret : AVERROR_INVALIDDATA; str[str_size] = 0; } av_dict_set(&c->fc->metadata, key, str, 0); @@ -369,6 +395,7 @@ static int mov_read_dref(MOVContext *c, AVIOContext *pb, MOVAtom atom) entries >= UINT_MAX / sizeof(*sc->drefs)) return AVERROR_INVALIDDATA; av_free(sc->drefs); + sc->drefs_count = 0; sc->drefs = av_mallocz(entries * sizeof(*sc->drefs)); if (!sc->drefs) return AVERROR(ENOMEM); @@ -418,7 +445,7 @@ static int mov_read_dref(MOVContext *c, AVIOContext *pb, MOVAtom atom) avio_skip(pb, 16); for (type = 0; type != -1 && avio_tell(pb) < next; ) { - if (pb->eof_reached) + if(url_feof(pb)) return AVERROR_EOF; type = avio_rb16(pb); len = avio_rb16(pb); @@ -445,7 +472,8 @@ static int mov_read_dref(MOVContext *c, AVIOContext *pb, MOVAtom atom) dref->dir = av_malloc(len+1); if (!dref->dir) return AVERROR(ENOMEM); - avio_read(pb, dref->dir, len); + if (avio_read(pb, dref->dir, len) != len) + return AVERROR_INVALIDDATA; dref->dir[len] = 0; for (j = 0; j < len; j++) if (dref->dir[j] == ':') @@ -465,6 +493,8 @@ static int mov_read_hdlr(MOVContext *c, AVIOContext *pb, MOVAtom atom) AVStream *st; uint32_t type; uint32_t av_unused ctype; + int title_size; + char *title_str; if (c->fc->nb_streams < 1) // meta before first trak return 0; @@ -494,6 +524,19 @@ static int mov_read_hdlr(MOVContext *c, AVIOContext *pb, MOVAtom atom) avio_rb32(pb); /* component flags */ avio_rb32(pb); /* component flags mask */ + title_size = atom.size - 24; + if (title_size > 0) { + title_str = av_malloc(title_size + 1); /* Add null terminator */ + if (!title_str) + return AVERROR(ENOMEM); + avio_read(pb, title_str, title_size); + title_str[title_size] = 0; + if (title_str[0]) + av_dict_set(&st->metadata, "handler_name", title_str + + (!c->isom && title_str[0] == title_size - 1), 0); + av_freep(&title_str); + } + return 0; } @@ -587,6 +630,9 @@ static int mov_read_chan(MOVContext *c, AVIOContext *pb, MOVAtom atom) if (atom.size < 16) return 0; + /* skip version and flags */ + avio_skip(pb, 4); + ff_mov_read_chan(c->fc, pb, st, atom.size - 4); return 0; @@ -600,7 +646,9 @@ static int mov_read_wfex(MOVContext *c, AVIOContext *pb, MOVAtom atom) return 0; st = c->fc->streams[c->fc->nb_streams-1]; - ff_get_wav_header(pb, st->codec, atom.size); + if (ff_get_wav_header(pb, st->codec, atom.size) < 0) { + av_log(c->fc, AV_LOG_WARNING, "get_wav_header failed\n"); + } return 0; } @@ -674,6 +722,12 @@ static int mov_read_moov(MOVContext *c, AVIOContext *pb, MOVAtom atom) { int ret; + if (c->found_moov) { + av_log(c->fc, AV_LOG_WARNING, "Found duplicated MOOV Atom. Skipped it\n"); + avio_skip(pb, atom.size); + return 0; + } + if ((ret = mov_read_default(c, pb, atom)) < 0) return ret; /* we parsed the 'moov' atom, we can terminate the parsing as soon as we find the 'mdat' */ @@ -689,13 +743,16 @@ 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, time_t time) +static void mov_metadata_creation_time(AVDictionary **metadata, int64_t time) { char buffer[32]; if (time) { struct tm *ptm; - time -= 2082844800; /* seconds between 1904-01-01 and Epoch */ - ptm = gmtime(&time); + time_t timet; + if(time >= 2082844800) + time -= 2082844800; /* seconds between 1904-01-01 and Epoch */ + timet = time; + ptm = gmtime(&timet); if (!ptm) return; strftime(buffer, sizeof(buffer), "%Y-%m-%d %H:%M:%S", ptm); av_dict_set(metadata, "creation_time", buffer, 0); @@ -709,7 +766,7 @@ static int mov_read_mdhd(MOVContext *c, AVIOContext *pb, MOVAtom atom) int version; char language[4] = {0}; unsigned lang; - time_t creation_time; + int64_t creation_time; if (c->fc->nb_streams < 1) return 0; @@ -749,7 +806,7 @@ static int mov_read_mdhd(MOVContext *c, AVIOContext *pb, MOVAtom atom) static int mov_read_mvhd(MOVContext *c, AVIOContext *pb, MOVAtom atom) { - time_t creation_time; + int64_t creation_time; int version = avio_r8(pb); /* version */ avio_rb24(pb); /* flags */ @@ -766,6 +823,10 @@ static int mov_read_mvhd(MOVContext *c, AVIOContext *pb, MOVAtom atom) av_dlog(c->fc, "time scale = %i\n", c->time_scale); c->duration = (version == 1) ? avio_rb64(pb) : avio_rb32(pb); /* duration */ + // set the AVCodecContext duration because the duration of individual tracks + // may be inaccurate + if (c->time_scale > 0 && !c->trex_data) + c->fc->duration = av_rescale(c->duration, AV_TIME_BASE, c->time_scale); avio_rb32(pb); /* preferred scale */ avio_rb16(pb); /* preferred volume */ @@ -781,31 +842,6 @@ static int mov_read_mvhd(MOVContext *c, AVIOContext *pb, MOVAtom atom) avio_rb32(pb); /* selection duration */ avio_rb32(pb); /* current time */ avio_rb32(pb); /* next track ID */ - - return 0; -} - -static int mov_read_smi(MOVContext *c, AVIOContext *pb, MOVAtom atom) -{ - AVStream *st; - - if (c->fc->nb_streams < 1) - return 0; - st = c->fc->streams[c->fc->nb_streams-1]; - - if ((uint64_t)atom.size > (1<<30)) - return AVERROR_INVALIDDATA; - - // currently SVQ3 decoder expect full STSD header - so let's fake it - // this should be fixed and just SMI header should be passed - av_free(st->codec->extradata); - st->codec->extradata = av_mallocz(atom.size + 0x5a + FF_INPUT_BUFFER_PADDING_SIZE); - if (!st->codec->extradata) - return AVERROR(ENOMEM); - st->codec->extradata_size = 0x5a + atom.size; - memcpy(st->codec->extradata, "SVQ3", 4); // fake - avio_read(pb, st->codec->extradata + 0x5a, atom.size); - av_dlog(c->fc, "Reading SMI %"PRId64" %s\n", atom.size, st->codec->extradata + 0x5a); return 0; } @@ -818,7 +854,7 @@ static int mov_read_enda(MOVContext *c, AVIOContext *pb, MOVAtom atom) return 0; st = c->fc->streams[c->fc->nb_streams-1]; - little_endian = avio_rb16(pb); + little_endian = avio_rb16(pb) & 0xFF; av_dlog(c->fc, "enda %d\n", little_endian); if (little_endian == 1) { switch (st->codec->codec_id) { @@ -876,7 +912,8 @@ static int mov_read_fiel(MOVContext *c, AVIOContext *pb, MOVAtom atom) } /* FIXME modify qdm2/svq3/h264 decoders to take full atom as extradata */ -static int mov_read_extradata(MOVContext *c, AVIOContext *pb, MOVAtom atom) +static int mov_read_extradata(MOVContext *c, AVIOContext *pb, MOVAtom atom, + enum AVCodecID codec_id) { AVStream *st; uint64_t size; @@ -886,6 +923,10 @@ static int mov_read_extradata(MOVContext *c, AVIOContext *pb, MOVAtom atom) if (c->fc->nb_streams < 1) // will happen with jp2 files return 0; st= c->fc->streams[c->fc->nb_streams-1]; + + if (st->codec->codec_id != codec_id) + return 0; /* unexpected codec_id - don't mess with extradata */ + size= (uint64_t)st->codec->extradata_size + atom.size + 8 + FF_INPUT_BUFFER_PADDING_SIZE; if (size > INT_MAX || (uint64_t)atom.size > INT_MAX) return AVERROR_INVALIDDATA; @@ -897,10 +938,75 @@ static int mov_read_extradata(MOVContext *c, AVIOContext *pb, MOVAtom atom) st->codec->extradata_size= size - FF_INPUT_BUFFER_PADDING_SIZE; AV_WB32( buf , atom.size + 8); AV_WL32( buf + 4, atom.type); - avio_read(pb, buf + 8, atom.size); + err = avio_read(pb, buf + 8, atom.size); + if (err < 0) { + return err; + } else if (err < atom.size) { + av_log(c->fc, AV_LOG_WARNING, "truncated extradata\n"); + st->codec->extradata_size -= atom.size - err; + } + memset(buf + 8 + err, 0, FF_INPUT_BUFFER_PADDING_SIZE); return 0; } +/* wrapper functions for reading ALAC/AVS/MJPEG/MJPEG2000 extradata atoms only for those codecs */ +static int mov_read_alac(MOVContext *c, AVIOContext *pb, MOVAtom atom) +{ + return mov_read_extradata(c, pb, atom, AV_CODEC_ID_ALAC); +} + +static int mov_read_avss(MOVContext *c, AVIOContext *pb, MOVAtom atom) +{ + return mov_read_extradata(c, pb, atom, AV_CODEC_ID_AVS); +} + +static int mov_read_jp2h(MOVContext *c, AVIOContext *pb, MOVAtom atom) +{ + return mov_read_extradata(c, pb, atom, AV_CODEC_ID_JPEG2000); +} + +static int mov_read_avid(MOVContext *c, AVIOContext *pb, MOVAtom atom) +{ + return mov_read_extradata(c, pb, atom, AV_CODEC_ID_AVUI); +} + +static int mov_read_targa_y216(MOVContext *c, AVIOContext *pb, MOVAtom atom) +{ + int ret = mov_read_extradata(c, pb, atom, AV_CODEC_ID_TARGA_Y216); + + if (!ret && c->fc->nb_streams >= 1) { + AVCodecContext *avctx = c->fc->streams[c->fc->nb_streams-1]->codec; + if (avctx->extradata_size >= 40) { + avctx->height = AV_RB16(&avctx->extradata[36]); + avctx->width = AV_RB16(&avctx->extradata[38]); + } + } + return ret; +} + +static int mov_read_ares(MOVContext *c, AVIOContext *pb, MOVAtom atom) +{ + if (c->fc->nb_streams >= 1) { + AVCodecContext *codec = c->fc->streams[c->fc->nb_streams-1]->codec; + if (codec->codec_tag == MKTAG('A', 'V', 'i', 'n') && + codec->codec_id == AV_CODEC_ID_H264 && + atom.size > 11) { + avio_skip(pb, 10); + /* For AVID AVCI50, force width of 1440 to be able to select the correct SPS and PPS */ + if (avio_rb16(pb) == 0xd4d) + codec->width = 1440; + return 0; + } + } + + return mov_read_avid(c, pb, atom); +} + +static int mov_read_svq3(MOVContext *c, AVIOContext *pb, MOVAtom atom) +{ + return mov_read_extradata(c, pb, atom, AV_CODEC_ID_SVQ3); +} + static int mov_read_wave(MOVContext *c, AVIOContext *pb, MOVAtom atom) { AVStream *st; @@ -912,14 +1018,13 @@ static int mov_read_wave(MOVContext *c, AVIOContext *pb, MOVAtom atom) if ((uint64_t)atom.size > (1<<30)) return AVERROR_INVALIDDATA; - if (st->codec->codec_id == AV_CODEC_ID_QDM2 || st->codec->codec_id == AV_CODEC_ID_QDMC) { + if (st->codec->codec_id == AV_CODEC_ID_QDM2 || + st->codec->codec_id == AV_CODEC_ID_QDMC || + st->codec->codec_id == AV_CODEC_ID_SPEEX) { // pass all frma atom to codec, needed at least for QDMC and QDM2 av_free(st->codec->extradata); - st->codec->extradata = av_mallocz(atom.size + FF_INPUT_BUFFER_PADDING_SIZE); - if (!st->codec->extradata) + if (ff_get_extradata(st->codec, pb, atom.size) < 0) return AVERROR(ENOMEM); - st->codec->extradata_size = atom.size; - avio_read(pb, st->codec->extradata, atom.size); } else if (atom.size > 8) { /* to read frma, esds atoms */ int ret; if ((ret = mov_read_default(c, pb, atom)) < 0) @@ -954,11 +1059,9 @@ static int mov_read_glbl(MOVContext *c, AVIOContext *pb, MOVAtom atom) return mov_read_default(c, pb, atom); } av_free(st->codec->extradata); - st->codec->extradata = av_mallocz(atom.size + FF_INPUT_BUFFER_PADDING_SIZE); - if (!st->codec->extradata) + if (ff_get_extradata(st->codec, pb, atom.size) < 0) return AVERROR(ENOMEM); - st->codec->extradata_size = atom.size; - avio_read(pb, st->codec->extradata, atom.size); + return 0; } @@ -966,6 +1069,7 @@ static int mov_read_dvc1(MOVContext *c, AVIOContext *pb, MOVAtom atom) { AVStream *st; uint8_t profile_level; + int ret; if (c->fc->nb_streams < 1) return 0; @@ -978,13 +1082,11 @@ static int mov_read_dvc1(MOVContext *c, AVIOContext *pb, MOVAtom atom) if ((profile_level & 0xf0) != 0xc0) return 0; - av_free(st->codec->extradata); - st->codec->extradata = av_mallocz(atom.size - 7 + FF_INPUT_BUFFER_PADDING_SIZE); - if (!st->codec->extradata) - return AVERROR(ENOMEM); - st->codec->extradata_size = atom.size - 7; avio_seek(pb, 6, SEEK_CUR); - avio_read(pb, st->codec->extradata, st->codec->extradata_size); + av_free(st->codec->extradata); + if ((ret = ff_get_extradata(st->codec, pb, atom.size - 7)) < 0) + return ret; + return 0; } @@ -1006,13 +1108,10 @@ static int mov_read_strf(MOVContext *c, AVIOContext *pb, MOVAtom atom) if ((uint64_t)atom.size > (1<<30)) return AVERROR_INVALIDDATA; + avio_skip(pb, 40); av_free(st->codec->extradata); - st->codec->extradata = av_mallocz(atom.size - 40 + FF_INPUT_BUFFER_PADDING_SIZE); - if (!st->codec->extradata) + if (ff_get_extradata(st->codec, pb, atom.size - 40) < 0) return AVERROR(ENOMEM); - st->codec->extradata_size = atom.size - 40; - avio_skip(pb, 40); - avio_read(pb, st->codec->extradata, atom.size - 40); return 0; } @@ -1092,7 +1191,9 @@ static int mov_codec_id(AVStream *st, uint32_t format) id = ff_codec_get_id(ff_codec_bmp_tags, format); if (id > 0) st->codec->codec_type = AVMEDIA_TYPE_VIDEO; - else if (st->codec->codec_type == AVMEDIA_TYPE_DATA) { + else if (st->codec->codec_type == AVMEDIA_TYPE_DATA || + (st->codec->codec_type == AVMEDIA_TYPE_SUBTITLE && + st->codec->codec_id == AV_CODEC_ID_NONE)) { id = ff_codec_get_id(ff_codec_movsubtitle_tags, format); if (id > 0) st->codec->codec_type = AVMEDIA_TYPE_SUBTITLE; @@ -1137,8 +1238,11 @@ static void mov_parse_stsd_video(MOVContext *c, AVIOContext *pb, av_dict_set(&st->metadata, "encoder", codec_name, 0); /* codec_tag YV12 triggers an UV swap in rawdec.c */ - if (!memcmp(codec_name, "Planar Y'CbCr 8-bit 4:2:0", 25)) + if (!memcmp(codec_name, "Planar Y'CbCr 8-bit 4:2:0", 25)) { st->codec->codec_tag = MKTAG('I', '4', '2', '0'); + st->codec->width &= ~1; + st->codec->height &= ~1; + } /* Flash Media Server uses tag H263 with Sorenson Spark */ if (st->codec->codec_tag == MKTAG('H','2','6','3') && !memcmp(codec_name, "Sorenson H263", 13)) @@ -1151,12 +1255,15 @@ static void mov_parse_stsd_video(MOVContext *c, AVIOContext *pb, /* figure out the palette situation */ color_depth = st->codec->bits_per_coded_sample & 0x1F; color_greyscale = st->codec->bits_per_coded_sample & 0x20; + /* Do not create a greyscale palette for cinepak */ + if (color_greyscale && st->codec->codec_id == AV_CODEC_ID_CINEPAK) + return; /* if the depth is 2, 4, or 8 bpp, file is palettized */ if ((color_depth == 2) || (color_depth == 4) || (color_depth == 8)) { /* for palette traversal */ unsigned int color_start, color_count, color_end; - unsigned char r, g, b; + unsigned char a, r, g, b; if (color_greyscale) { int color_index, color_dec; @@ -1167,7 +1274,7 @@ static void mov_parse_stsd_video(MOVContext *c, AVIOContext *pb, color_dec = 256 / (color_count - 1); for (j = 0; j < color_count; j++) { r = g = b = color_index; - sc->palette[j] = (r << 16) | (g << 8) | (b); + sc->palette[j] = (0xFFU << 24) | (r << 16) | (g << 8) | (b); color_index -= color_dec; if (color_index < 0) color_index = 0; @@ -1187,7 +1294,7 @@ static void mov_parse_stsd_video(MOVContext *c, AVIOContext *pb, r = color_table[j * 3 + 0]; g = color_table[j * 3 + 1]; b = color_table[j * 3 + 2]; - sc->palette[j] = (r << 16) | (g << 8) | (b); + sc->palette[j] = (0xFFU << 24) | (r << 16) | (g << 8) | (b); } } else { /* load the palette from the file */ @@ -1196,10 +1303,9 @@ static void mov_parse_stsd_video(MOVContext *c, AVIOContext *pb, color_end = avio_rb16(pb); if ((color_start <= 255) && (color_end <= 255)) { for (j = color_start; j <= color_end; j++) { - /* each R, G, or B component is 16 bits; - * only use the top 8 bits; skip alpha bytes - * up front */ - avio_r8(pb); + /* each A, R, G, or B component is 16 bits; + * only use the top 8 bits */ + a = avio_r8(pb); avio_r8(pb); r = avio_r8(pb); avio_r8(pb); @@ -1207,7 +1313,7 @@ static void mov_parse_stsd_video(MOVContext *c, AVIOContext *pb, avio_r8(pb); b = avio_r8(pb); avio_r8(pb); - sc->palette[j] = (r << 16) | (g << 8) | (b); + sc->palette[j] = (a << 24 ) | (r << 16) | (g << 8) | (b); } } } @@ -1220,6 +1326,7 @@ static void mov_parse_stsd_audio(MOVContext *c, AVIOContext *pb, { int bits_per_sample, flags; uint16_t version = avio_rb16(pb); + AVDictionaryEntry *compatible_brands = av_dict_get(c->fc->metadata, "compatible_brands", NULL, AV_DICT_MATCH_CASE); avio_rb16(pb); /* revision level */ avio_rb32(pb); /* vendor */ @@ -1235,7 +1342,9 @@ static void mov_parse_stsd_audio(MOVContext *c, AVIOContext *pb, // Read QT version 1 fields. In version 0 these do not exist. av_dlog(c->fc, "version =%d, isom =%d\n", version, c->isom); - if (!c->isom) { + if (!c->isom || + (compatible_brands && strstr(compatible_brands->value, "qt "))) { + if (version == 1) { sc->samples_per_frame = avio_rb32(pb); avio_rb32(pb); /* bytes per packet */ @@ -1371,11 +1480,18 @@ static int mov_parse_stsd_data(MOVContext *c, AVIOContext *pb, int size) { if (st->codec->codec_tag == MKTAG('t','m','c','d')) { - st->codec->extradata_size = size; - st->codec->extradata = av_malloc(size + FF_INPUT_BUFFER_PADDING_SIZE); - if (!st->codec->extradata) + if (ff_get_extradata(st->codec, pb, size) < 0) return AVERROR(ENOMEM); - avio_read(pb, st->codec->extradata, size); + if (size > 16) { + MOVStreamContext *tmcd_ctx = st->priv_data; + int val; + val = AV_RB32(st->codec->extradata + 4); + tmcd_ctx->tmcd_flags = val; + if (val & 1) + st->codec->flags2 |= CODEC_FLAG2_DROP_FRAME_TIMECODE; + st->codec->time_base.den = st->codec->extradata[16]; /* number of frame */ + st->codec->time_base.num = 1; + } } else { /* other codec type, just skip (rtp, mp4s ...) */ avio_skip(pb, size); @@ -1410,6 +1526,10 @@ static int mov_finalize_stsd_codec(MOVContext *c, AVIOContext *pb, // force sample rate for qcelp when not stored in mov if (st->codec->codec_tag != MKTAG('Q','c','l','p')) st->codec->sample_rate = 8000; + // FIXME: Why is the following needed for some files? + sc->samples_per_frame = 160; + if (!sc->bytes_per_frame) + sc->bytes_per_frame = 35; break; case AV_CODEC_ID_AMR_NB: st->codec->channels = 1; @@ -1430,6 +1550,9 @@ static int mov_finalize_stsd_codec(MOVContext *c, AVIOContext *pb, case AV_CODEC_ID_ADPCM_MS: case AV_CODEC_ID_ADPCM_IMA_WAV: case AV_CODEC_ID_ILBC: + case AV_CODEC_ID_MACE3: + case AV_CODEC_ID_MACE6: + case AV_CODEC_ID_QDM2: st->codec->block_align = sc->bytes_per_frame; break; case AV_CODEC_ID_ALAC: @@ -1438,6 +1561,8 @@ static int mov_finalize_stsd_codec(MOVContext *c, AVIOContext *pb, st->codec->sample_rate = AV_RB32(st->codec->extradata + 32); } break; + case AV_CODEC_ID_AC3: + case AV_CODEC_ID_MPEG1VIDEO: case AV_CODEC_ID_VC1: st->need_parsing = AVSTREAM_PARSE_FULL; break; @@ -1454,12 +1579,9 @@ static int mov_skip_multiple_stsd(MOVContext *c, AVIOContext *pb, int video_codec_id = ff_codec_get_id(ff_codec_movvideo_tags, format); if (codec_tag && - (codec_tag == AV_RL32("avc1") || - codec_tag == AV_RL32("hvc1") || - codec_tag == AV_RL32("hev1") || (codec_tag != format && (c->fc->video_codec_id ? video_codec_id != c->fc->video_codec_id - : codec_tag != MKTAG('j','p','e','g'))))) { + : codec_tag != MKTAG('j','p','e','g')))) { /* Multiple fourcc, we skip JPEG. This is not correct, we should * export it as a separate AVStream but this needs a few changes * in the MOV demuxer, patch welcome. */ @@ -1468,6 +1590,11 @@ static int mov_skip_multiple_stsd(MOVContext *c, AVIOContext *pb, avio_skip(pb, size); return 1; } + if ( codec_tag == AV_RL32("avc1") || + codec_tag == AV_RL32("hvc1") || + codec_tag == AV_RL32("hev1") + ) + av_log(c->fc, AV_LOG_WARNING, "Concatenated H.264 or H.265 might not play correctly.\n"); return 0; } @@ -1491,15 +1618,15 @@ int ff_mov_read_stsd_entries(MOVContext *c, AVIOContext *pb, int entries) int ret, dref_id = 1; MOVAtom a = { AV_RL32("stsd") }; int64_t start_pos = avio_tell(pb); - uint32_t size = avio_rb32(pb); /* size */ + int64_t size = avio_rb32(pb); /* size */ uint32_t format = avio_rl32(pb); /* data format */ if (size >= 16) { avio_rb32(pb); /* reserved */ avio_rb16(pb); /* reserved */ dref_id = avio_rb16(pb); - } else { - av_log(c->fc, AV_LOG_ERROR, "invalid size %"PRIu32" in stsd\n", size); + }else if (size <= 7){ + av_log(c->fc, AV_LOG_ERROR, "invalid size %"PRId64" in stsd\n", size); return AVERROR_INVALIDDATA; } @@ -1512,7 +1639,7 @@ int ff_mov_read_stsd_entries(MOVContext *c, AVIOContext *pb, int entries) id = mov_codec_id(st, format); - av_dlog(c->fc, "size=%"PRIu32" 4CC= %"PRIu8"%"PRIu8"%"PRIu8"%"PRIu8" codec_type=%d\n", size, + av_dlog(c->fc, "size=%"PRId64" 4CC= %c%c%c%c codec_type=%d\n", size, (format >> 0) & 0xff, (format >> 8) & 0xff, (format >> 16) & 0xff, (format >> 24) & 0xff, st->codec->codec_type); @@ -1652,6 +1779,8 @@ static int mov_read_stss(MOVContext *c, AVIOContext *pb, MOVAtom atom) if (!entries) { sc->keyframe_absent = 1; + if (!st->need_parsing && st->codec->codec_type == AVMEDIA_TYPE_VIDEO) + st->need_parsing = AVSTREAM_PARSE_HEADERS; return 0; } if (entries >= UINT_MAX / sizeof(int)) @@ -1693,6 +1822,7 @@ static int mov_read_stsz(MOVContext *c, AVIOContext *pb, MOVAtom atom) sample_size = avio_rb32(pb); if (!sc->sample_size) /* do not overwrite value computed in stsd */ sc->sample_size = sample_size; + sc->stsz_sample_size = sample_size; field_size = 32; } else { sample_size = 0; @@ -1770,10 +1900,8 @@ static int mov_read_stts(MOVContext *c, AVIOContext *pb, MOVAtom atom) av_dlog(c->fc, "track[%i].stts.entries = %i\n", c->fc->nb_streams-1, entries); - if (!entries) - return 0; if (entries >= UINT_MAX / sizeof(*sc->stts_data)) - return AVERROR(EINVAL); + return -1; av_free(sc->stts_data); sc->stts_data = av_malloc(entries * sizeof(*sc->stts_data)); @@ -1786,6 +1914,13 @@ static int mov_read_stts(MOVContext *c, AVIOContext *pb, MOVAtom atom) sample_count=avio_rb32(pb); sample_duration = avio_rb32(pb); + + /* sample_duration < 0 is invalid based on the spec */ + if (sample_duration < 0) { + av_log(c->fc, AV_LOG_ERROR, "Invalid SampleDelta %d in STTS, at %d st:%d\n", + sample_duration, i, c->fc->nb_streams-1); + sample_duration = 1; + } if (sample_count < 0) { av_log(c->fc, AV_LOG_ERROR, "Invalid sample_count=%d\n", sample_count); return AVERROR_INVALIDDATA; @@ -1796,12 +1931,21 @@ static int mov_read_stts(MOVContext *c, AVIOContext *pb, MOVAtom atom) av_dlog(c->fc, "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*sample_count; total_sample_count+=sample_count; } sc->stts_count = i; + sc->duration_for_fps += duration; + sc->nb_frames_for_fps += total_sample_count; + if (pb->eof_reached) return AVERROR_EOF; @@ -1812,6 +1956,13 @@ static int mov_read_stts(MOVContext *c, AVIOContext *pb, MOVAtom atom) return 0; } +static void mov_update_dts_shift(MOVStreamContext *sc, int duration) +{ + if (duration < 0) { + sc->dts_shift = FFMAX(sc->dts_shift, -duration); + } +} + static int mov_read_ctts(MOVContext *c, AVIOContext *pb, MOVAtom atom) { AVStream *st; @@ -1843,8 +1994,19 @@ static int mov_read_ctts(MOVContext *c, AVIOContext *pb, MOVAtom atom) sc->ctts_data[i].count = count; sc->ctts_data[i].duration= duration; - if (duration < 0) - sc->dts_shift = FFMAX(sc->dts_shift, -duration); + + av_dlog(c->fc, "count=%d, duration=%d\n", + count, duration); + + if (FFABS(duration) > (1<<28) && i+2<entries) { + av_log(c->fc, AV_LOG_WARNING, "CTTS invalid\n"); + av_freep(&sc->ctts_data); + sc->ctts_count = 0; + return 0; + } + + if (i+2<entries) + mov_update_dts_shift(sc, duration); } sc->ctts_count = i; @@ -1910,12 +2072,13 @@ static void mov_build_index(MOVContext *mov, AVStream *st) uint64_t stream_size = 0; /* adjust first dts according to edit list */ - if (sc->time_offset && mov->time_scale > 0) { - if (sc->time_offset < 0) - sc->time_offset = av_rescale(sc->time_offset, sc->time_scale, mov->time_scale); + if ((sc->empty_duration || sc->start_time) && mov->time_scale > 0) { + if (sc->empty_duration) + sc->empty_duration = av_rescale(sc->empty_duration, sc->time_scale, mov->time_scale); + sc->time_offset = sc->start_time - sc->empty_duration; current_dts = -sc->time_offset; - if (sc->ctts_data && sc->stts_data && sc->stts_data[0].duration && - sc->ctts_data[0].duration / sc->stts_data[0].duration > 16) { + if (sc->ctts_count>0 && sc->stts_count>0 && + sc->ctts_data[0].duration / FFMAX(sc->stts_data[0].duration, 1) > 16) { /* more than 16 frames delay, dts are likely wrong this happens with files created by iMovie */ sc->wrong_dts = 1; @@ -1933,11 +2096,11 @@ static void mov_build_index(MOVContext *mov, AVStream *st) unsigned int rap_group_index = 0; unsigned int rap_group_sample = 0; int rap_group_present = sc->rap_group_count && sc->rap_group; - int key_off = (sc->keyframes && sc->keyframes[0] > 0) || (sc->stps_data && sc->stps_data[0] > 0); + int key_off = (sc->keyframe_count && sc->keyframes[0] > 0) || (sc->stps_count && sc->stps_data[0] > 0); current_dts -= sc->dts_shift; - if (!sc->sample_count) + if (!sc->sample_count || st->nb_index_entries) return; if (sc->sample_count >= UINT_MAX / sizeof(*st->index_entries) - st->nb_index_entries) return; @@ -1950,10 +2113,22 @@ static void mov_build_index(MOVContext *mov, AVStream *st) st->index_entries_allocated_size = (st->nb_index_entries + sc->sample_count) * sizeof(*st->index_entries); for (i = 0; i < sc->chunk_count; i++) { + int64_t next_offset = i+1 < sc->chunk_count ? sc->chunk_offsets[i+1] : INT64_MAX; current_offset = sc->chunk_offsets[i]; while (stsc_index + 1 < sc->stsc_count && i + 1 == sc->stsc_data[stsc_index + 1].first) stsc_index++; + + if (next_offset > current_offset && sc->sample_size>0 && sc->sample_size < sc->stsz_sample_size && + sc->stsc_data[stsc_index].count * (int64_t)sc->stsz_sample_size > next_offset - current_offset) { + av_log(mov->fc, AV_LOG_WARNING, "STSZ sample size %d invalid (too large), ignoring\n", sc->stsz_sample_size); + sc->stsz_sample_size = sc->sample_size; + } + if (sc->stsz_sample_size>0 && sc->stsz_sample_size < sc->sample_size) { + av_log(mov->fc, AV_LOG_WARNING, "STSZ sample size %d invalid (too small), ignoring\n", sc->stsz_sample_size); + sc->stsz_sample_size = sc->sample_size; + } + for (j = 0; j < sc->stsc_data[stsc_index].count; j++) { int keyframe = 0; if (current_sample >= sc->sample_count) { @@ -1978,9 +2153,14 @@ static void mov_build_index(MOVContext *mov, AVStream *st) rap_group_index++; } } + if (sc->keyframe_absent + && !sc->stps_count + && !rap_group_present + && st->codec->codec_type == AVMEDIA_TYPE_AUDIO) + keyframe = 1; if (keyframe) distance = 0; - sample_size = sc->sample_size > 0 ? sc->sample_size : sc->sample_sizes[current_sample]; + sample_size = sc->stsz_sample_size > 0 ? sc->stsz_sample_size : sc->sample_sizes[current_sample]; if (sc->pseudo_stream_id == -1 || sc->stsc_data[stsc_index].id - 1 == sc->pseudo_stream_id) { AVIndexEntry *e = &st->index_entries[st->nb_index_entries++]; @@ -1992,6 +2172,8 @@ static void mov_build_index(MOVContext *mov, AVStream *st) av_dlog(mov->fc, "AVIndex stream %d, sample %d, offset %"PRIx64", dts %"PRId64", " "size %d, distance %d, keyframe %d\n", st->index, current_sample, current_offset, current_dts, sample_size, distance, keyframe); + if (st->codec->codec_type == AVMEDIA_TYPE_VIDEO && st->nb_index_entries < 100) + ff_rfps_add_frame(mov->fc, st, current_dts); } current_offset += sample_size; @@ -2097,14 +2279,14 @@ static void mov_build_index(MOVContext *mov, AVStream *st) } } -static int mov_open_dref(AVIOContext **pb, char *src, MOVDref *ref, - AVIOInterruptCB *int_cb) +static int mov_open_dref(AVIOContext **pb, const char *src, MOVDref *ref, + AVIOInterruptCB *int_cb, int use_absolute_path, AVFormatContext *fc) { /* try relative path, we do not try the absolute because it can leak information about our system to an attacker */ if (ref->nlvl_to > 0 && ref->nlvl_from > 0) { char filename[1024]; - char *src_path; + const char *src_path; int i, l; /* find a source dir */ @@ -2136,11 +2318,26 @@ static int mov_open_dref(AVIOContext **pb, char *src, MOVDref *ref, if (!avio_open2(pb, filename, AVIO_FLAG_READ, int_cb, NULL)) return 0; } + } else if (use_absolute_path) { + av_log(fc, AV_LOG_WARNING, "Using absolute path on user request, " + "this is a possible security issue\n"); + if (!avio_open2(pb, ref->path, AVIO_FLAG_READ, int_cb, NULL)) + return 0; } return AVERROR(ENOENT); } +static void fix_timescale(MOVContext *c, MOVStreamContext *sc) +{ + if (sc->time_scale <= 0) { + av_log(c->fc, AV_LOG_WARNING, "stream %d, timescale not set\n", sc->ffindex); + sc->time_scale = c->time_scale; + if (sc->time_scale <= 0) + sc->time_scale = 1; + } +} + static int mov_read_trak(MOVContext *c, AVIOContext *pb, MOVAtom atom) { AVStream *st; @@ -2168,12 +2365,7 @@ static int mov_read_trak(MOVContext *c, AVIOContext *pb, MOVAtom atom) return 0; } - if (sc->time_scale <= 0) { - av_log(c->fc, AV_LOG_WARNING, "stream %d, timescale not set\n", st->index); - sc->time_scale = c->time_scale; - if (sc->time_scale <= 0) - sc->time_scale = 1; - } + fix_timescale(c, sc); avpriv_set_pts_info(st, 64, 1, sc->time_scale); @@ -2181,14 +2373,17 @@ static int mov_read_trak(MOVContext *c, AVIOContext *pb, MOVAtom atom) if (sc->dref_id-1 < sc->drefs_count && sc->drefs[sc->dref_id-1].path) { MOVDref *dref = &sc->drefs[sc->dref_id - 1]; - if (mov_open_dref(&sc->pb, c->fc->filename, dref, &c->fc->interrupt_callback) < 0) + if (mov_open_dref(&sc->pb, c->fc->filename, dref, &c->fc->interrupt_callback, + c->use_absolute_path, c->fc) < 0) av_log(c->fc, AV_LOG_ERROR, "stream %d, error opening alias: path='%s', dir='%s', " "filename='%s', volume='%s', nlvl_from=%d, nlvl_to=%d\n", st->index, dref->path, dref->dir, dref->filename, dref->volume, dref->nlvl_from, dref->nlvl_to); - } else + } else { sc->pb = c->fc->pb; + sc->pb_is_copied = 1; + } if (st->codec->codec_type == AVMEDIA_TYPE_VIDEO) { if (!st->sample_aspect_ratio.num && @@ -2196,6 +2391,12 @@ static int mov_read_trak(MOVContext *c, AVIOContext *pb, MOVAtom atom) st->sample_aspect_ratio = av_d2q(((double)st->codec->height * sc->width) / ((double)st->codec->width * sc->height), INT_MAX); } + +#if FF_API_R_FRAME_RATE + if (sc->stts_count == 1 || (sc->stts_count == 2 && sc->stts_data[1].count == 1)) + av_reduce(&st->r_frame_rate.num, &st->r_frame_rate.den, + sc->time_scale, sc->stts_data[0].duration, INT_MAX); +#endif } // done for ai5q, ai52, ai55, ai1q, ai12 and ai15. @@ -2242,11 +2443,18 @@ static int mov_read_ilst(MOVContext *c, AVIOContext *pb, MOVAtom atom) return ret; } -static int mov_read_replaygain(MOVContext *c, AVIOContext *pb, int size) +static int mov_read_custom_2plus(MOVContext *c, AVIOContext *pb, int size) { int64_t end = avio_tell(pb) + size; uint8_t *key = NULL, *val = NULL; int i; + AVStream *st; + MOVStreamContext *sc; + + if (c->fc->nb_streams < 1) + return 0; + st = c->fc->streams[c->fc->nb_streams-1]; + sc = st->priv_data; for (i = 0; i < 2; i++) { uint8_t **p; @@ -2280,9 +2488,18 @@ static int mov_read_replaygain(MOVContext *c, AVIOContext *pb, int size) } if (key && val) { - av_dict_set(&c->fc->metadata, key, val, - AV_DICT_DONT_STRDUP_KEY | AV_DICT_DONT_STRDUP_VAL); - key = val = NULL; + if (strcmp(key, "iTunSMPB") == 0) { + int priming, remainder, samples; + if(sscanf(val, "%*X %X %X %X", &priming, &remainder, &samples) == 3){ + if(priming>0 && priming<16384) + sc->start_pad = priming; + } + } else if (strcmp(key, "cdec") == 0) { + } else { + av_dict_set(&c->fc->metadata, key, val, + AV_DICT_DONT_STRDUP_KEY | AV_DICT_DONT_STRDUP_VAL); + key = val = NULL; + } } avio_seek(pb, end, SEEK_SET); @@ -2314,8 +2531,7 @@ static int mov_read_custom(MOVContext *c, AVIOContext *pb, MOVAtom atom) domain_len = avio_get_str(pb, len, domain, sizeof(domain)); avio_skip(pb, len - domain_len); - if (!strcmp(domain, "org.hydrogenaudio.replaygain")) - return mov_read_replaygain(c, pb, end - avio_tell(pb)); + return mov_read_custom_2plus(c, pb, end - avio_tell(pb)); } fail: @@ -2393,6 +2609,21 @@ static int mov_read_tkhd(MOVContext *c, AVIOContext *pb, MOVAtom atom) sc->width = width >> 16; sc->height = height >> 16; + //Assign clockwise rotate values based on transform matrix so that + //we can compensate for iPhone orientation during capture. + + if (display_matrix[1][0] == -65536 && display_matrix[0][1] == 65536) { + av_dict_set(&st->metadata, "rotate", "90", 0); + } + + if (display_matrix[0][0] == -65536 && display_matrix[1][1] == -65536) { + av_dict_set(&st->metadata, "rotate", "180", 0); + } + + if (display_matrix[1][0] == 65536 && display_matrix[0][1] == -65536) { + av_dict_set(&st->metadata, "rotate", "270", 0); + } + // transform the display width/height according to the matrix // skip this if the display matrix is the default identity matrix // or if it is rotating the picture, ex iPhone 3GS @@ -2472,6 +2703,9 @@ static int mov_read_trex(MOVContext *c, AVIOContext *pb, MOVAtom atom) c->trex_count = 0; return err; } + + c->fc->duration = AV_NOPTS_VALUE; // the duration from mvhd is not representing the whole file when fragments are used. + trex = &c->trex_data[c->trex_count++]; avio_r8(pb); /* version */ avio_rb24(pb); /* flags */ @@ -2506,7 +2740,7 @@ static int mov_read_trun(MOVContext *c, AVIOContext *pb, MOVAtom atom) return AVERROR_INVALIDDATA; } sc = st->priv_data; - if (sc->pseudo_stream_id+1 != frag->stsd_id) + if (sc->pseudo_stream_id+1 != frag->stsd_id && sc->pseudo_stream_id != -1) return 0; avio_r8(pb); /* version */ flags = avio_rb24(pb); @@ -2554,6 +2788,7 @@ static int mov_read_trun(MOVContext *c, AVIOContext *pb, MOVAtom atom) sc->ctts_data[sc->ctts_count].count = 1; sc->ctts_data[sc->ctts_count].duration = (flags & MOV_TRUN_SAMPLE_CTS) ? avio_rb32(pb) : 0; + mov_update_dts_shift(sc, sc->ctts_data[sc->ctts_count].duration); sc->ctts_count++; if (st->codec->codec_type == AVMEDIA_TYPE_AUDIO) keyframe = 1; @@ -2572,6 +2807,8 @@ static int mov_read_trun(MOVContext *c, AVIOContext *pb, MOVAtom atom) dts += sample_duration; offset += sample_size; sc->data_size += sample_size; + sc->duration_for_fps += sample_duration; + sc->nb_frames_for_fps ++; } if (pb->eof_reached) @@ -2618,7 +2855,7 @@ static int mov_read_cmov(MOVContext *c, AVIOContext *pb, MOVAtom atom) if (avio_rl32(pb) != MKTAG('d','c','o','m')) return AVERROR_INVALIDDATA; if (avio_rl32(pb) != MKTAG('z','l','i','b')) { - av_log(c->fc, AV_LOG_ERROR, "unknown compression for cmov atom !"); + av_log(c->fc, AV_LOG_ERROR, "unknown compression for cmov atom !\n"); return AVERROR_INVALIDDATA; } avio_rb32(pb); /* cmvd atom */ @@ -2657,9 +2894,10 @@ free_and_return: static int mov_read_elst(MOVContext *c, AVIOContext *pb, MOVAtom atom) { MOVStreamContext *sc; - int i, edit_count, version; + int i, edit_count, version, edit_start_index = 0; + int unsupported = 0; - if (c->fc->nb_streams < 1) + if (c->fc->nb_streams < 1 || c->ignore_editlist) return 0; sc = c->fc->streams[c->fc->nb_streams-1]->priv_data; @@ -2670,9 +2908,11 @@ static int mov_read_elst(MOVContext *c, AVIOContext *pb, MOVAtom atom) if ((uint64_t)edit_count*12+8 > atom.size) return AVERROR_INVALIDDATA; + av_dlog(c->fc, "track[%i].edit_count = %i\n", c->fc->nb_streams-1, edit_count); for (i=0; i<edit_count; i++){ int64_t time; int64_t duration; + int rate; if (version == 1) { duration = avio_rb64(pb); time = avio_rb64(pb); @@ -2680,22 +2920,109 @@ static int mov_read_elst(MOVContext *c, AVIOContext *pb, MOVAtom atom) duration = avio_rb32(pb); /* segment duration */ time = (int32_t)avio_rb32(pb); /* media time */ } - avio_rb32(pb); /* Media rate */ - if (i == 0 && time >= -1) { - sc->time_offset = time != -1 ? time : -duration; - } + rate = avio_rb32(pb); + if (i == 0 && time == -1) { + sc->empty_duration = duration; + edit_start_index = 1; + } else if (i == edit_start_index && time >= 0) + sc->start_time = time; + else + unsupported = 1; + + av_dlog(c->fc, "duration=%"PRId64" time=%"PRId64" rate=%f\n", + duration, time, rate / 65536.0); } - if (edit_count > 1) + if (unsupported) av_log(c->fc, AV_LOG_WARNING, "multiple edit list entries, " "a/v desync might occur, patch welcome\n"); - av_dlog(c->fc, "track[%i].edit_count = %i\n", c->fc->nb_streams-1, edit_count); + return 0; +} + +static int mov_read_tmcd(MOVContext *c, AVIOContext *pb, MOVAtom atom) +{ + MOVStreamContext *sc; + + if (c->fc->nb_streams < 1) + return AVERROR_INVALIDDATA; + sc = c->fc->streams[c->fc->nb_streams - 1]->priv_data; + sc->timecode_track = avio_rb32(pb); + return 0; +} + +static int mov_read_uuid(MOVContext *c, AVIOContext *pb, MOVAtom atom) +{ + int ret; + uint8_t uuid[16]; + static const uint8_t uuid_isml_manifest[] = { + 0xa5, 0xd4, 0x0b, 0x30, 0xe8, 0x14, 0x11, 0xdd, + 0xba, 0x2f, 0x08, 0x00, 0x20, 0x0c, 0x9a, 0x66 + }; + + if (atom.size < sizeof(uuid) || atom.size == INT64_MAX) + return AVERROR_INVALIDDATA; + + ret = avio_read(pb, uuid, sizeof(uuid)); + if (ret < 0) { + return ret; + } else if (ret != sizeof(uuid)) { + return AVERROR_INVALIDDATA; + } + if (!memcmp(uuid, uuid_isml_manifest, sizeof(uuid))) { + uint8_t *buffer, *ptr; + char *endptr; + size_t len = atom.size - sizeof(uuid); + + if (len < 4) { + return AVERROR_INVALIDDATA; + } + ret = avio_skip(pb, 4); // zeroes + len -= 4; + + buffer = av_mallocz(len + 1); + if (!buffer) { + return AVERROR(ENOMEM); + } + ret = avio_read(pb, buffer, len); + if (ret < 0) { + av_free(buffer); + return ret; + } else if (ret != len) { + av_free(buffer); + return AVERROR_INVALIDDATA; + } + + ptr = buffer; + while ((ptr = av_stristr(ptr, "systemBitrate=\"")) != NULL) { + ptr += sizeof("systemBitrate=\"") - 1; + c->bitrates_count++; + c->bitrates = av_realloc_f(c->bitrates, c->bitrates_count, sizeof(*c->bitrates)); + if (!c->bitrates) { + c->bitrates_count = 0; + av_free(buffer); + return AVERROR(ENOMEM); + } + errno = 0; + ret = strtol(ptr, &endptr, 10); + if (ret < 0 || errno || *endptr != '"') { + c->bitrates[c->bitrates_count - 1] = 0; + } else { + c->bitrates[c->bitrates_count - 1] = ret; + } + } + + av_free(buffer); + } return 0; } static const MOVParseTableEntry mov_default_parse_table[] = { -{ MKTAG('a','v','s','s'), mov_read_extradata }, +{ MKTAG('A','C','L','R'), mov_read_avid }, +{ 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('c','h','p','l'), mov_read_chpl }, { MKTAG('c','o','6','4'), mov_read_stco }, { MKTAG('c','t','t','s'), mov_read_ctts }, /* composition time to sample */ @@ -2709,7 +3036,7 @@ static const MOVParseTableEntry mov_default_parse_table[] = { { MKTAG('g','l','b','l'), mov_read_glbl }, { MKTAG('h','d','l','r'), mov_read_hdlr }, { MKTAG('i','l','s','t'), mov_read_ilst }, -{ MKTAG('j','p','2','h'), mov_read_extradata }, +{ MKTAG('j','p','2','h'), mov_read_jp2h }, { MKTAG('m','d','a','t'), mov_read_mdat }, { MKTAG('m','d','h','d'), mov_read_mdhd }, { MKTAG('m','d','i','a'), mov_read_default }, @@ -2719,8 +3046,8 @@ static const MOVParseTableEntry mov_default_parse_table[] = { { MKTAG('m','o','o','v'), mov_read_moov }, { MKTAG('m','v','e','x'), mov_read_default }, { MKTAG('m','v','h','d'), mov_read_mvhd }, -{ MKTAG('S','M','I',' '), mov_read_smi }, /* Sorenson extension ??? */ -{ MKTAG('a','l','a','c'), mov_read_extradata }, /* alac specific atom */ +{ MKTAG('S','M','I',' '), mov_read_svq3 }, +{ MKTAG('a','l','a','c'), mov_read_alac }, /* alac specific atom */ { MKTAG('a','v','c','C'), mov_read_glbl }, { MKTAG('p','a','s','p'), mov_read_pasp }, { MKTAG('s','t','b','l'), mov_read_default }, @@ -2738,6 +3065,7 @@ static const MOVParseTableEntry mov_default_parse_table[] = { { MKTAG('t','r','a','k'), mov_read_trak }, { MKTAG('t','r','a','f'), mov_read_default }, { MKTAG('t','r','e','f'), mov_read_default }, +{ MKTAG('t','m','c','d'), mov_read_tmcd }, { MKTAG('c','h','a','p'), mov_read_chap }, { MKTAG('t','r','e','x'), mov_read_trex }, { MKTAG('t','r','u','n'), mov_read_trun }, @@ -2753,6 +3081,8 @@ static const MOVParseTableEntry mov_default_parse_table[] = { { MKTAG('d','v','c','1'), mov_read_dvc1 }, { MKTAG('s','b','g','p'), mov_read_sbgp }, { MKTAG('h','v','c','C'), mov_read_glbl }, +{ MKTAG('u','u','i','d'), mov_read_uuid }, +{ MKTAG('C','i','n', 0x8e), mov_read_targa_y216 }, { MKTAG('-','-','-','-'), mov_read_custom }, { 0, NULL } }; @@ -2765,25 +3095,33 @@ static int mov_read_default(MOVContext *c, AVIOContext *pb, MOVAtom atom) if (atom.size < 0) atom.size = INT64_MAX; - while (total_size + 8 < atom.size && !pb->eof_reached) { + while (total_size + 8 <= atom.size && !url_feof(pb)) { int (*parse)(MOVContext*, AVIOContext*, MOVAtom) = NULL; a.size = atom.size; a.type=0; if (atom.size >= 8) { a.size = avio_rb32(pb); a.type = avio_rl32(pb); + if (atom.type != MKTAG('r','o','o','t') && + atom.type != MKTAG('m','o','o','v')) + { + if (a.type == MKTAG('t','r','a','k') || a.type == MKTAG('m','d','a','t')) + { + av_log(c->fc, AV_LOG_ERROR, "Broken file, trak/mdat not at top-level\n"); + avio_skip(pb, -8); + return 0; + } + } + total_size += 8; + if (a.size == 1) { /* 64 bit extended size */ + a.size = avio_rb64(pb) - 8; + total_size += 8; + } } av_dlog(c->fc, "type: %08x '%.4s' parent:'%.4s' sz: %"PRId64" %"PRId64" %"PRId64"\n", a.type, (char*)&a.type, (char*)&atom.type, a.size, total_size, atom.size); - total_size += 8; - if (a.size == 1) { /* 64 bit extended size */ - a.size = avio_rb64(pb) - 8; - total_size += 8; - } if (a.size == 0) { - a.size = atom.size - total_size; - if (a.size <= 8) - break; + a.size = atom.size - total_size + 8; } a.size -= 8; if (a.size < 0) @@ -2838,46 +3176,81 @@ static int mov_read_default(MOVContext *c, AVIOContext *pb, MOVAtom atom) static int mov_probe(AVProbeData *p) { - unsigned int offset; + int64_t offset; uint32_t tag; int score = 0; + int moov_offset = -1; /* check file header */ offset = 0; for (;;) { /* ignore invalid offset */ if ((offset + 8) > (unsigned int)p->buf_size) - return score; + break; tag = AV_RL32(p->buf + offset + 4); switch(tag) { /* check for obvious tags */ - case MKTAG('j','P',' ',' '): /* jpeg 2000 signature */ case MKTAG('m','o','o','v'): + moov_offset = offset + 4; + case MKTAG('j','P',' ',' '): /* jpeg 2000 signature */ case MKTAG('m','d','a','t'): case MKTAG('p','n','o','t'): /* detect movs with preview pics like ew.mov and april.mov */ case MKTAG('u','d','t','a'): /* Packet Video PVAuthor adds this and a lot of more junk */ case MKTAG('f','t','y','p'): - return AVPROBE_SCORE_MAX; + if (AV_RB32(p->buf+offset) < 8 && + (AV_RB32(p->buf+offset) != 1 || + offset + 12 > (unsigned int)p->buf_size || + AV_RB64(p->buf+offset + 8) == 0)) { + score = FFMAX(score, AVPROBE_SCORE_EXTENSION); + } else { + score = AVPROBE_SCORE_MAX; + } + offset = FFMAX(4, AV_RB32(p->buf+offset)) + offset; + break; /* those are more common words, so rate then a bit less */ case MKTAG('e','d','i','w'): /* xdcam files have reverted first tags */ case MKTAG('w','i','d','e'): case MKTAG('f','r','e','e'): case MKTAG('j','u','n','k'): case MKTAG('p','i','c','t'): - return AVPROBE_SCORE_MAX - 5; + score = FFMAX(score, AVPROBE_SCORE_MAX - 5); + offset = FFMAX(4, AV_RB32(p->buf+offset)) + offset; + break; case MKTAG(0x82,0x82,0x7f,0x7d): case MKTAG('s','k','i','p'): case MKTAG('u','u','i','d'): case MKTAG('p','r','f','l'): - offset = AV_RB32(p->buf+offset) + offset; /* if we only find those cause probedata is too small at least rate them */ - score = AVPROBE_SCORE_EXTENSION; + score = FFMAX(score, AVPROBE_SCORE_EXTENSION); + offset = FFMAX(4, AV_RB32(p->buf+offset)) + offset; break; default: - /* unrecognized tag */ - return score; + offset = FFMAX(4, AV_RB32(p->buf+offset)) + offset; + } + } + if(score > AVPROBE_SCORE_MAX - 50 && moov_offset != -1) { + /* moov atom in the header - we should make sure that this is not a + * MOV-packed MPEG-PS */ + offset = moov_offset; + + while(offset < (p->buf_size - 16)){ /* Sufficient space */ + /* We found an actual hdlr atom */ + if(AV_RL32(p->buf + offset ) == MKTAG('h','d','l','r') && + AV_RL32(p->buf + offset + 8) == MKTAG('m','h','l','r') && + AV_RL32(p->buf + offset + 12) == MKTAG('M','P','E','G')){ + av_log(NULL, AV_LOG_WARNING, "Found media data tag MPEG indicating this is a MOV-packed MPEG-PS.\n"); + /* We found a media handler reference atom describing an + * MPEG-PS-in-MOV, return a + * low score to force expanding the probe window until + * mpegps_probe finds what it needs */ + return 5; + }else + /* Keep looking */ + offset+=2; } } + + return score; } // must be done after parsing all trak because there's no order requirement @@ -2939,7 +3312,7 @@ static void mov_read_chapters(AVFormatContext *s) if (len == 1 || len == 2) title[len] = 0; else - avio_get_str(sc->pb, len - 2, title + 2, title_len - 2); + avio_get_str(sc->pb, INT_MAX, title + 2, len - 1); } } @@ -2950,6 +3323,49 @@ finish: avio_seek(sc->pb, cur_pos, SEEK_SET); } +static int parse_timecode_in_framenum_format(AVFormatContext *s, AVStream *st, + uint32_t value, int flags) +{ + AVTimecode tc; + char buf[AV_TIMECODE_STR_SIZE]; + AVRational rate = {st->codec->time_base.den, + st->codec->time_base.num}; + int ret = av_timecode_init(&tc, rate, flags, 0, s); + if (ret < 0) + return ret; + av_dict_set(&st->metadata, "timecode", + av_timecode_make_string(&tc, buf, value), 0); + return 0; +} + +static int mov_read_timecode_track(AVFormatContext *s, AVStream *st) +{ + MOVStreamContext *sc = st->priv_data; + int flags = 0; + int64_t cur_pos = avio_tell(sc->pb); + uint32_t value; + + if (!st->nb_index_entries) + return -1; + + avio_seek(sc->pb, st->index_entries->pos, SEEK_SET); + value = avio_rb32(s->pb); + + if (sc->tmcd_flags & 0x0001) flags |= AV_TIMECODE_FLAG_DROPFRAME; + if (sc->tmcd_flags & 0x0002) flags |= AV_TIMECODE_FLAG_24HOURSMAX; + if (sc->tmcd_flags & 0x0004) flags |= AV_TIMECODE_FLAG_ALLOWNEGATIVE; + + /* Assume Counter flag is set to 1 in tmcd track (even though it is likely + * not the case) and thus assume "frame number format" instead of QT one. + * No sample with tmcd track can be found with a QT timecode at the moment, + * despite what the tmcd track "suggests" (Counter flag set to 0 means QT + * format). */ + parse_timecode_in_framenum_format(s, st, value, flags); + + avio_seek(sc->pb, cur_pos, SEEK_SET); + return 0; +} + static int mov_read_close(AVFormatContext *s) { MOVContext *mov = s->priv_data; @@ -2965,9 +3381,13 @@ static int mov_read_close(AVFormatContext *s) av_freep(&sc->drefs[j].dir); } av_freep(&sc->drefs); - if (sc->pb && sc->pb != s->pb) + + sc->drefs_count = 0; + + if (!sc->pb_is_copied) avio_close(sc->pb); + sc->pb = NULL; av_freep(&sc->chunk_offsets); av_freep(&sc->stsc_data); av_freep(&sc->sample_sizes); @@ -2987,15 +3407,50 @@ static int mov_read_close(AVFormatContext *s) } av_freep(&mov->trex_data); + av_freep(&mov->bitrates); + + return 0; +} + +static int tmcd_is_referenced(AVFormatContext *s, int tmcd_id) +{ + int i; + + for (i = 0; i < s->nb_streams; i++) { + AVStream *st = s->streams[i]; + MOVStreamContext *sc = st->priv_data; + if (st->codec->codec_type == AVMEDIA_TYPE_VIDEO && + sc->timecode_track == tmcd_id) + return 1; + } return 0; } +/* look for a tmcd track not referenced by any video track, and export it globally */ +static void export_orphan_timecode(AVFormatContext *s) +{ + int i; + + for (i = 0; i < s->nb_streams; i++) { + AVStream *st = s->streams[i]; + + if (st->codec->codec_tag == MKTAG('t','m','c','d') && + !tmcd_is_referenced(s, i + 1)) { + AVDictionaryEntry *tcr = av_dict_get(st->metadata, "timecode", NULL, 0); + if (tcr) { + av_dict_set(&s->metadata, "timecode", tcr->value, 0); + break; + } + } + } +} + static int mov_read_header(AVFormatContext *s) { MOVContext *mov = s->priv_data; AVIOContext *pb = s->pb; - int err; + int j, err; MOVAtom atom = { AV_RL32("root") }; int i; @@ -3019,15 +3474,47 @@ static int mov_read_header(AVFormatContext *s) } av_dlog(mov->fc, "on_parse_exit_offset=%"PRId64"\n", avio_tell(pb)); - if (pb->seekable && mov->chapter_track > 0) - mov_read_chapters(s); + if (pb->seekable) { + if (mov->chapter_track > 0) + mov_read_chapters(s); + for (i = 0; i < s->nb_streams; i++) + if (s->streams[i]->codec->codec_tag == AV_RL32("tmcd")) + mov_read_timecode_track(s, s->streams[i]); + } + /* copy timecode metadata from tmcd tracks to the related video streams */ for (i = 0; i < s->nb_streams; i++) { AVStream *st = s->streams[i]; MOVStreamContext *sc = st->priv_data; + if (sc->timecode_track > 0) { + AVDictionaryEntry *tcr; + int tmcd_st_id = -1; + + for (j = 0; j < s->nb_streams; j++) + if (s->streams[j]->id == sc->timecode_track) + tmcd_st_id = j; + + if (tmcd_st_id < 0 || tmcd_st_id == i) + continue; + tcr = av_dict_get(s->streams[tmcd_st_id]->metadata, "timecode", NULL, 0); + if (tcr) + av_dict_set(&st->metadata, "timecode", tcr->value, 0); + } + } + export_orphan_timecode(s); + for (i = 0; i < s->nb_streams; i++) { + AVStream *st = s->streams[i]; + MOVStreamContext *sc = st->priv_data; + fix_timescale(mov, sc); + if(st->codec->codec_type == AVMEDIA_TYPE_AUDIO && st->codec->codec_id == AV_CODEC_ID_AAC) { + st->skip_samples = sc->start_pad; + } + if (st->codec->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, + sc->time_scale*(int64_t)sc->nb_frames_for_fps, sc->duration_for_fps, INT_MAX); if (st->codec->codec_type == AVMEDIA_TYPE_SUBTITLE) { - if (st->codec->width <= 0 && st->codec->width <= 0) { + if (st->codec->width <= 0 && st->codec->height <= 0) { st->codec->width = sc->width; st->codec->height = sc->height; } @@ -3047,6 +3534,14 @@ static int mov_read_header(AVFormatContext *s) } } + for (i = 0; i < mov->bitrates_count && i < s->nb_streams; i++) { + if (mov->bitrates[i]) { + s->streams[i]->codec->bit_rate = mov->bitrates[i]; + } + } + + ff_rfps_calculate(s); + for (i = 0; i < s->nb_streams; i++) { AVStream *st = s->streams[i]; @@ -3096,6 +3591,7 @@ static int mov_read_packet(AVFormatContext *s, AVPacket *pkt) AVIndexEntry *sample; AVStream *st = NULL; int ret; + mov->fc = s; retry: sample = mov_find_next_sample(s, &st); if (!sample) { @@ -3105,7 +3601,7 @@ static int mov_read_packet(AVFormatContext *s, AVPacket *pkt) avio_seek(s->pb, mov->next_root_atom, SEEK_SET); mov->next_root_atom = 0; if (mov_read_default(mov, s->pb, (MOVAtom){ AV_RL32("root"), INT64_MAX }) < 0 || - s->pb->eof_reached) + url_feof(s->pb)) return AVERROR_EOF; av_dlog(s, "read fragments, offset 0x%"PRIx64"\n", avio_tell(s->pb)); goto retry; @@ -3114,6 +3610,11 @@ static int mov_read_packet(AVFormatContext *s, AVPacket *pkt) /* must be done just before reading, to avoid infinite loop on sample */ sc->current_sample++; + if (mov->next_root_atom) { + sample->pos = FFMIN(sample->pos, mov->next_root_atom); + sample->size = FFMIN(sample->size, (mov->next_root_atom - sample->pos)); + } + if (st->discard != AVDISCARD_ALL) { if (avio_seek(sc->pb, sample->pos, SEEK_SET) != sample->pos) { av_log(mov->fc, AV_LOG_ERROR, "stream %d, offset 0x%"PRIx64": partial file\n", @@ -3136,7 +3637,7 @@ static int mov_read_packet(AVFormatContext *s, AVPacket *pkt) } #if CONFIG_DV_DEMUXER if (mov->dv_demux && sc->dv_audio_container) { - avpriv_dv_produce_packet(mov->dv_demux, pkt, pkt->data, pkt->size); + avpriv_dv_produce_packet(mov->dv_demux, pkt, pkt->data, pkt->size, pkt->pos); av_free(pkt->data); pkt->size = 0; ret = avpriv_dv_get_packet(mov->dv_demux, pkt); @@ -3213,8 +3714,6 @@ static int mov_read_seek(AVFormatContext *s, int stream_index, int64_t sample_ti if (stream_index >= s->nb_streams) return AVERROR_INVALIDDATA; - if (sample_time < 0) - sample_time = 0; st = s->streams[stream_index]; sample = mov_seek_stream(s, st, sample_time, flags); @@ -3225,7 +3724,10 @@ static int mov_read_seek(AVFormatContext *s, int stream_index, int64_t sample_ti seek_timestamp = st->index_entries[sample].timestamp; for (i = 0; i < s->nb_streams; i++) { + MOVStreamContext *sc = s->streams[i]->priv_data; st = s->streams[i]; + st->skip_samples = (sample_time <= 0) ? sc->start_pad : 0; + if (stream_index == i) continue; @@ -3235,6 +3737,23 @@ static int mov_read_seek(AVFormatContext *s, int stream_index, int64_t sample_ti return 0; } +static const AVOption options[] = { + {"use_absolute_path", + "allow using absolute path when opening alias, this is a possible security issue", + offsetof(MOVContext, use_absolute_path), FF_OPT_TYPE_INT, {.i64 = 0}, + 0, 1, AV_OPT_FLAG_VIDEO_PARAM|AV_OPT_FLAG_DECODING_PARAM}, + {"ignore_editlist", "", offsetof(MOVContext, ignore_editlist), FF_OPT_TYPE_INT, {.i64 = 0}, + 0, 1, AV_OPT_FLAG_VIDEO_PARAM|AV_OPT_FLAG_DECODING_PARAM}, + {NULL} +}; + +static const AVClass mov_class = { + .class_name = "mov,mp4,m4a,3gp,3g2,mj2", + .item_name = av_default_item_name, + .option = options, + .version = LIBAVUTIL_VERSION_INT, +}; + AVInputFormat ff_mov_demuxer = { .name = "mov,mp4,m4a,3gp,3g2,mj2", .long_name = NULL_IF_CONFIG_SMALL("QuickTime / MOV"), @@ -3245,4 +3764,6 @@ AVInputFormat ff_mov_demuxer = { .read_packet = mov_read_packet, .read_close = mov_read_close, .read_seek = mov_read_seek, + .priv_class = &mov_class, + .flags = AVFMT_NO_BYTE_SEEK, }; |