From e924a4ba715da13260ed83262469a8a56aad427b Mon Sep 17 00:00:00 2001 From: Justin Ruggles Date: Fri, 20 Jan 2012 13:56:51 -0500 Subject: [PATCH 01/16] westwood: split the AUD and VQA demuxers into separate files. They have no code in common. --- libavformat/Makefile | 4 +- libavformat/westwood_aud.c | 173 +++++++++++++++++++++ libavformat/{westwood.c => westwood_vqa.c} | 147 +---------------- 3 files changed, 177 insertions(+), 147 deletions(-) create mode 100644 libavformat/westwood_aud.c rename libavformat/{westwood.c => westwood_vqa.c} (63%) diff --git a/libavformat/Makefile b/libavformat/Makefile index 2a2a946104..a19ff3c48b 100644 --- a/libavformat/Makefile +++ b/libavformat/Makefile @@ -308,8 +308,8 @@ OBJS-$(CONFIG_WC3_DEMUXER) += wc3movie.o OBJS-$(CONFIG_WEBM_MUXER) += matroskaenc.o matroska.o \ riff.o isom.o avc.o \ flacenc_header.o avlanguage.o -OBJS-$(CONFIG_WSAUD_DEMUXER) += westwood.o -OBJS-$(CONFIG_WSVQA_DEMUXER) += westwood.o +OBJS-$(CONFIG_WSAUD_DEMUXER) += westwood_aud.o +OBJS-$(CONFIG_WSVQA_DEMUXER) += westwood_vqa.o OBJS-$(CONFIG_WTV_DEMUXER) += wtv.o asfdec.o asf.o asfcrypt.o \ avlanguage.o mpegts.o isom.o riff.o OBJS-$(CONFIG_WV_DEMUXER) += wv.o apetag.o diff --git a/libavformat/westwood_aud.c b/libavformat/westwood_aud.c new file mode 100644 index 0000000000..b1eb768016 --- /dev/null +++ b/libavformat/westwood_aud.c @@ -0,0 +1,173 @@ +/* + * Westwood Studios AUD Format Demuxer + * Copyright (c) 2003 The ffmpeg Project + * + * This file is part of Libav. + * + * Libav 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, + * 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 + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA + */ + +/** + * @file + * Westwood Studios AUD file demuxer + * by Mike Melanson (melanson@pcisys.net) + * for more information on the Westwood file formats, visit: + * http://www.pcisys.net/~melanson/codecs/ + * http://www.geocities.com/SiliconValley/8682/aud3.txt + * + * Implementation note: There is no definite file signature for AUD files. + * The demuxer uses a probabilistic strategy for content detection. This + * entails performing sanity checks on certain header values in order to + * qualify a file. Refer to wsaud_probe() for the precise parameters. + */ + +#include "libavutil/intreadwrite.h" +#include "avformat.h" +#include "internal.h" + +#define AUD_HEADER_SIZE 12 +#define AUD_CHUNK_PREAMBLE_SIZE 8 +#define AUD_CHUNK_SIGNATURE 0x0000DEAF + +typedef struct WsAudDemuxContext { + int audio_samplerate; + int audio_channels; + int audio_bits; + enum CodecID audio_type; + int audio_stream_index; + int64_t audio_frame_counter; +} WsAudDemuxContext; + +static int wsaud_probe(AVProbeData *p) +{ + int field; + + /* Probabilistic content detection strategy: There is no file signature + * so perform sanity checks on various header parameters: + * 8000 <= sample rate (16 bits) <= 48000 ==> 40001 acceptable numbers + * flags <= 0x03 (2 LSBs are used) ==> 4 acceptable numbers + * compression type (8 bits) = 1 or 99 ==> 2 acceptable numbers + * first audio chunk signature (32 bits) ==> 1 acceptable number + * The number space contains 2^64 numbers. There are 40001 * 4 * 2 * 1 = + * 320008 acceptable number combinations. + */ + + if (p->buf_size < AUD_HEADER_SIZE + AUD_CHUNK_PREAMBLE_SIZE) + return 0; + + /* check sample rate */ + field = AV_RL16(&p->buf[0]); + if ((field < 8000) || (field > 48000)) + return 0; + + /* enforce the rule that the top 6 bits of this flags field are reserved (0); + * this might not be true, but enforce it until deemed unnecessary */ + if (p->buf[10] & 0xFC) + return 0; + + /* note: only check for WS IMA (type 99) right now since there is no + * support for type 1 */ + if (p->buf[11] != 99) + return 0; + + /* read ahead to the first audio chunk and validate the first header signature */ + if (AV_RL32(&p->buf[16]) != AUD_CHUNK_SIGNATURE) + return 0; + + /* return 1/2 certainty since this file check is a little sketchy */ + return AVPROBE_SCORE_MAX / 2; +} + +static int wsaud_read_header(AVFormatContext *s, + AVFormatParameters *ap) +{ + WsAudDemuxContext *wsaud = s->priv_data; + AVIOContext *pb = s->pb; + AVStream *st; + unsigned char header[AUD_HEADER_SIZE]; + + if (avio_read(pb, header, AUD_HEADER_SIZE) != AUD_HEADER_SIZE) + return AVERROR(EIO); + wsaud->audio_samplerate = AV_RL16(&header[0]); + if (header[11] == 99) + wsaud->audio_type = CODEC_ID_ADPCM_IMA_WS; + else + return AVERROR_INVALIDDATA; + + /* flag 0 indicates stereo */ + wsaud->audio_channels = (header[10] & 0x1) + 1; + /* flag 1 indicates 16 bit audio */ + wsaud->audio_bits = (((header[10] & 0x2) >> 1) + 1) * 8; + + /* initialize the audio decoder stream */ + st = avformat_new_stream(s, NULL); + if (!st) + return AVERROR(ENOMEM); + avpriv_set_pts_info(st, 33, 1, wsaud->audio_samplerate); + st->codec->codec_type = AVMEDIA_TYPE_AUDIO; + st->codec->codec_id = wsaud->audio_type; + st->codec->codec_tag = 0; /* no tag */ + st->codec->channels = wsaud->audio_channels; + st->codec->sample_rate = wsaud->audio_samplerate; + st->codec->bits_per_coded_sample = wsaud->audio_bits; + st->codec->bit_rate = st->codec->channels * st->codec->sample_rate * + st->codec->bits_per_coded_sample / 4; + st->codec->block_align = st->codec->channels * st->codec->bits_per_coded_sample; + + wsaud->audio_stream_index = st->index; + wsaud->audio_frame_counter = 0; + + return 0; +} + +static int wsaud_read_packet(AVFormatContext *s, + AVPacket *pkt) +{ + WsAudDemuxContext *wsaud = s->priv_data; + AVIOContext *pb = s->pb; + unsigned char preamble[AUD_CHUNK_PREAMBLE_SIZE]; + unsigned int chunk_size; + int ret = 0; + + if (avio_read(pb, preamble, AUD_CHUNK_PREAMBLE_SIZE) != + AUD_CHUNK_PREAMBLE_SIZE) + return AVERROR(EIO); + + /* validate the chunk */ + if (AV_RL32(&preamble[4]) != AUD_CHUNK_SIGNATURE) + return AVERROR_INVALIDDATA; + + chunk_size = AV_RL16(&preamble[0]); + ret= av_get_packet(pb, pkt, chunk_size); + if (ret != chunk_size) + return AVERROR(EIO); + pkt->stream_index = wsaud->audio_stream_index; + pkt->pts = wsaud->audio_frame_counter; + pkt->pts /= wsaud->audio_samplerate; + + /* 2 samples/byte, 1 or 2 samples per frame depending on stereo */ + wsaud->audio_frame_counter += (chunk_size * 2) / wsaud->audio_channels; + + return ret; +} + +AVInputFormat ff_wsaud_demuxer = { + .name = "wsaud", + .long_name = NULL_IF_CONFIG_SMALL("Westwood Studios audio format"), + .priv_data_size = sizeof(WsAudDemuxContext), + .read_probe = wsaud_probe, + .read_header = wsaud_read_header, + .read_packet = wsaud_read_packet, +}; diff --git a/libavformat/westwood.c b/libavformat/westwood_vqa.c similarity index 63% rename from libavformat/westwood.c rename to libavformat/westwood_vqa.c index 82b7e94840..2eff4cc0a5 100644 --- a/libavformat/westwood.c +++ b/libavformat/westwood_vqa.c @@ -1,5 +1,5 @@ /* - * Westwood Studios Multimedia Formats Demuxer (VQA, AUD) + * Westwood Studios VQA Format Demuxer * Copyright (c) 2003 The ffmpeg Project * * This file is part of Libav. @@ -21,26 +21,17 @@ /** * @file - * Westwood Studios VQA & AUD file demuxers + * Westwood Studios VQA file demuxer * by Mike Melanson (melanson@pcisys.net) * for more information on the Westwood file formats, visit: * http://www.pcisys.net/~melanson/codecs/ * http://www.geocities.com/SiliconValley/8682/aud3.txt - * - * Implementation note: There is no definite file signature for AUD files. - * The demuxer uses a probabilistic strategy for content detection. This - * entails performing sanity checks on certain header values in order to - * qualify a file. Refer to wsaud_probe() for the precise parameters. */ #include "libavutil/intreadwrite.h" #include "avformat.h" #include "internal.h" -#define AUD_HEADER_SIZE 12 -#define AUD_CHUNK_PREAMBLE_SIZE 8 -#define AUD_CHUNK_SIGNATURE 0x0000DEAF - #define FORM_TAG MKBETAG('F', 'O', 'R', 'M') #define WVQA_TAG MKBETAG('W', 'V', 'Q', 'A') #define VQHD_TAG MKBETAG('V', 'Q', 'H', 'D') @@ -63,15 +54,6 @@ #define VQA_FRAMERATE 15 #define VQA_PREAMBLE_SIZE 8 -typedef struct WsAudDemuxContext { - int audio_samplerate; - int audio_channels; - int audio_bits; - enum CodecID audio_type; - int audio_stream_index; - int64_t audio_frame_counter; -} WsAudDemuxContext; - typedef struct WsVqaDemuxContext { int audio_samplerate; int audio_channels; @@ -83,119 +65,6 @@ typedef struct WsVqaDemuxContext { int64_t audio_frame_counter; } WsVqaDemuxContext; -static int wsaud_probe(AVProbeData *p) -{ - int field; - - /* Probabilistic content detection strategy: There is no file signature - * so perform sanity checks on various header parameters: - * 8000 <= sample rate (16 bits) <= 48000 ==> 40001 acceptable numbers - * flags <= 0x03 (2 LSBs are used) ==> 4 acceptable numbers - * compression type (8 bits) = 1 or 99 ==> 2 acceptable numbers - * first audio chunk signature (32 bits) ==> 1 acceptable number - * The number space contains 2^64 numbers. There are 40001 * 4 * 2 * 1 = - * 320008 acceptable number combinations. - */ - - if (p->buf_size < AUD_HEADER_SIZE + AUD_CHUNK_PREAMBLE_SIZE) - return 0; - - /* check sample rate */ - field = AV_RL16(&p->buf[0]); - if ((field < 8000) || (field > 48000)) - return 0; - - /* enforce the rule that the top 6 bits of this flags field are reserved (0); - * this might not be true, but enforce it until deemed unnecessary */ - if (p->buf[10] & 0xFC) - return 0; - - /* note: only check for WS IMA (type 99) right now since there is no - * support for type 1 */ - if (p->buf[11] != 99) - return 0; - - /* read ahead to the first audio chunk and validate the first header signature */ - if (AV_RL32(&p->buf[16]) != AUD_CHUNK_SIGNATURE) - return 0; - - /* return 1/2 certainty since this file check is a little sketchy */ - return AVPROBE_SCORE_MAX / 2; -} - -static int wsaud_read_header(AVFormatContext *s, - AVFormatParameters *ap) -{ - WsAudDemuxContext *wsaud = s->priv_data; - AVIOContext *pb = s->pb; - AVStream *st; - unsigned char header[AUD_HEADER_SIZE]; - - if (avio_read(pb, header, AUD_HEADER_SIZE) != AUD_HEADER_SIZE) - return AVERROR(EIO); - wsaud->audio_samplerate = AV_RL16(&header[0]); - if (header[11] == 99) - wsaud->audio_type = CODEC_ID_ADPCM_IMA_WS; - else - return AVERROR_INVALIDDATA; - - /* flag 0 indicates stereo */ - wsaud->audio_channels = (header[10] & 0x1) + 1; - /* flag 1 indicates 16 bit audio */ - wsaud->audio_bits = (((header[10] & 0x2) >> 1) + 1) * 8; - - /* initialize the audio decoder stream */ - st = avformat_new_stream(s, NULL); - if (!st) - return AVERROR(ENOMEM); - avpriv_set_pts_info(st, 33, 1, wsaud->audio_samplerate); - st->codec->codec_type = AVMEDIA_TYPE_AUDIO; - st->codec->codec_id = wsaud->audio_type; - st->codec->codec_tag = 0; /* no tag */ - st->codec->channels = wsaud->audio_channels; - st->codec->sample_rate = wsaud->audio_samplerate; - st->codec->bits_per_coded_sample = wsaud->audio_bits; - st->codec->bit_rate = st->codec->channels * st->codec->sample_rate * - st->codec->bits_per_coded_sample / 4; - st->codec->block_align = st->codec->channels * st->codec->bits_per_coded_sample; - - wsaud->audio_stream_index = st->index; - wsaud->audio_frame_counter = 0; - - return 0; -} - -static int wsaud_read_packet(AVFormatContext *s, - AVPacket *pkt) -{ - WsAudDemuxContext *wsaud = s->priv_data; - AVIOContext *pb = s->pb; - unsigned char preamble[AUD_CHUNK_PREAMBLE_SIZE]; - unsigned int chunk_size; - int ret = 0; - - if (avio_read(pb, preamble, AUD_CHUNK_PREAMBLE_SIZE) != - AUD_CHUNK_PREAMBLE_SIZE) - return AVERROR(EIO); - - /* validate the chunk */ - if (AV_RL32(&preamble[4]) != AUD_CHUNK_SIGNATURE) - return AVERROR_INVALIDDATA; - - chunk_size = AV_RL16(&preamble[0]); - ret= av_get_packet(pb, pkt, chunk_size); - if (ret != chunk_size) - return AVERROR(EIO); - pkt->stream_index = wsaud->audio_stream_index; - pkt->pts = wsaud->audio_frame_counter; - pkt->pts /= wsaud->audio_samplerate; - - /* 2 samples/byte, 1 or 2 samples per frame depending on stereo */ - wsaud->audio_frame_counter += (chunk_size * 2) / wsaud->audio_channels; - - return ret; -} - static int wsvqa_probe(AVProbeData *p) { /* need 12 bytes to qualify */ @@ -372,17 +241,6 @@ static int wsvqa_read_packet(AVFormatContext *s, return ret; } -#if CONFIG_WSAUD_DEMUXER -AVInputFormat ff_wsaud_demuxer = { - .name = "wsaud", - .long_name = NULL_IF_CONFIG_SMALL("Westwood Studios audio format"), - .priv_data_size = sizeof(WsAudDemuxContext), - .read_probe = wsaud_probe, - .read_header = wsaud_read_header, - .read_packet = wsaud_read_packet, -}; -#endif -#if CONFIG_WSVQA_DEMUXER AVInputFormat ff_wsvqa_demuxer = { .name = "wsvqa", .long_name = NULL_IF_CONFIG_SMALL("Westwood Studios VQA format"), @@ -391,4 +249,3 @@ AVInputFormat ff_wsvqa_demuxer = { .read_header = wsvqa_read_header, .read_packet = wsvqa_read_packet, }; -#endif From 50a3f9a4bd7498d3cb2b12bac0ca6f562cbb8a73 Mon Sep 17 00:00:00 2001 From: Janne Grunau Date: Sun, 22 Jan 2012 19:57:13 +0100 Subject: [PATCH 02/16] mxfdec: fix memleak on mxf_read_close() --- libavformat/mxfdec.c | 1 + 1 file changed, 1 insertion(+) diff --git a/libavformat/mxfdec.c b/libavformat/mxfdec.c index 4b63b277ff..0b514dbb24 100644 --- a/libavformat/mxfdec.c +++ b/libavformat/mxfdec.c @@ -1915,6 +1915,7 @@ static int mxf_read_close(AVFormatContext *s) for (i = 0; i < mxf->nb_index_tables; i++) { av_freep(&mxf->index_tables[i].segments); + av_freep(&mxf->index_tables[i].ptses); av_freep(&mxf->index_tables[i].fake_index); } av_freep(&mxf->index_tables); From 7662a532fbb83d5b3e559a7da58254e56cae3157 Mon Sep 17 00:00:00 2001 From: Hendrik Leppkes Date: Fri, 13 Jan 2012 18:41:21 +0100 Subject: [PATCH 03/16] vc1: don't read the interpfrm and bfraction elements for interlaced frames This matches the spec as well as the reference decoder, and fixes a bug with interlaced frame decoding. Signed-off-by: Kostya Shishkov --- libavcodec/vc1.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/libavcodec/vc1.c b/libavcodec/vc1.c index d728f9beb4..0a70062893 100644 --- a/libavcodec/vc1.c +++ b/libavcodec/vc1.c @@ -911,13 +911,15 @@ int vc1_parse_frame_header_adv(VC1Context *v, GetBitContext* gb) } goto parse_common_info; } - if (v->finterpflag) - v->interpfrm = get_bits1(gb); - if (v->s.pict_type == AV_PICTURE_TYPE_B) { - v->bfraction_lut_index = get_vlc2(gb, ff_vc1_bfraction_vlc.table, VC1_BFRACTION_VLC_BITS, 1); - v->bfraction = ff_vc1_bfraction_lut[v->bfraction_lut_index]; - if (v->bfraction == 0) { - v->s.pict_type = AV_PICTURE_TYPE_BI; /* XXX: should not happen here */ + if (v->fcm == PROGRESSIVE) { + if (v->finterpflag) + v->interpfrm = get_bits1(gb); + if (v->s.pict_type == AV_PICTURE_TYPE_B) { + v->bfraction_lut_index = get_vlc2(gb, ff_vc1_bfraction_vlc.table, VC1_BFRACTION_VLC_BITS, 1); + v->bfraction = ff_vc1_bfraction_lut[v->bfraction_lut_index]; + if (v->bfraction == 0) { + v->s.pict_type = AV_PICTURE_TYPE_BI; /* XXX: should not happen here */ + } } } From 27ed027bcdcb7445ab62d4870a8be3615ffc1e31 Mon Sep 17 00:00:00 2001 From: Paul B Mahol Date: Sat, 21 Jan 2012 17:45:52 +0000 Subject: [PATCH 04/16] XWD encoder and decoder Signed-off-by: Kostya Shishkov --- Changelog | 1 + doc/general.texi | 2 + libavcodec/Makefile | 2 + libavcodec/allcodecs.c | 1 + libavcodec/avcodec.h | 1 + libavcodec/version.h | 2 +- libavcodec/xwd.h | 41 +++++++ libavcodec/xwddec.c | 267 +++++++++++++++++++++++++++++++++++++++++ libavcodec/xwdenc.c | 246 +++++++++++++++++++++++++++++++++++++ libavformat/img2.c | 3 +- 10 files changed, 564 insertions(+), 2 deletions(-) create mode 100644 libavcodec/xwd.h create mode 100644 libavcodec/xwddec.c create mode 100644 libavcodec/xwdenc.c diff --git a/Changelog b/Changelog index f1530749de..ae092b1f50 100644 --- a/Changelog +++ b/Changelog @@ -6,6 +6,7 @@ version 0.8: - GSM audio parser - SMJPEG muxer +- XWD encoder and decoder version 0.8_beta2: diff --git a/doc/general.texi b/doc/general.texi index 79af887570..cda79c07b4 100644 --- a/doc/general.texi +++ b/doc/general.texi @@ -379,6 +379,8 @@ following image formats are supported: @tab YUV, JPEG and some extension is not supported yet. @item Truevision Targa @tab X @tab X @tab Targa (.TGA) image format +@item XWD @tab X @tab X + @tab X Window Dump image format @end multitable @code{X} means that encoding (resp. decoding) is supported. diff --git a/libavcodec/Makefile b/libavcodec/Makefile index 1e8d09b956..3468f66863 100644 --- a/libavcodec/Makefile +++ b/libavcodec/Makefile @@ -435,6 +435,8 @@ OBJS-$(CONFIG_XAN_WC4_DECODER) += xxan.o OBJS-$(CONFIG_XL_DECODER) += xl.o OBJS-$(CONFIG_XSUB_DECODER) += xsubdec.o OBJS-$(CONFIG_XSUB_ENCODER) += xsubenc.o +OBJS-$(CONFIG_XWD_DECODER) += xwddec.o +OBJS-$(CONFIG_XWD_ENCODER) += xwdenc.o OBJS-$(CONFIG_YOP_DECODER) += yop.o OBJS-$(CONFIG_ZLIB_DECODER) += lcldec.o OBJS-$(CONFIG_ZLIB_ENCODER) += lclenc.o diff --git a/libavcodec/allcodecs.c b/libavcodec/allcodecs.c index 528969214e..d00bd0b79c 100644 --- a/libavcodec/allcodecs.c +++ b/libavcodec/allcodecs.c @@ -230,6 +230,7 @@ void avcodec_register_all(void) REGISTER_DECODER (XAN_WC3, xan_wc3); REGISTER_DECODER (XAN_WC4, xan_wc4); REGISTER_DECODER (XL, xl); + REGISTER_ENCDEC (XWD, xwd); REGISTER_DECODER (YOP, yop); REGISTER_ENCDEC (ZLIB, zlib); REGISTER_ENCDEC (ZMBV, zmbv); diff --git a/libavcodec/avcodec.h b/libavcodec/avcodec.h index be1b2021bd..967a134bdd 100644 --- a/libavcodec/avcodec.h +++ b/libavcodec/avcodec.h @@ -254,6 +254,7 @@ enum CodecID { CODEC_ID_VBLE, CODEC_ID_DXTORY, CODEC_ID_V410, + CODEC_ID_XWD, /* various PCM "codecs" */ CODEC_ID_FIRST_AUDIO = 0x10000, ///< A dummy id pointing at the start of audio codecs diff --git a/libavcodec/version.h b/libavcodec/version.h index c7b4c15b7a..77e16823f9 100644 --- a/libavcodec/version.h +++ b/libavcodec/version.h @@ -21,7 +21,7 @@ #define AVCODEC_VERSION_H #define LIBAVCODEC_VERSION_MAJOR 53 -#define LIBAVCODEC_VERSION_MINOR 34 +#define LIBAVCODEC_VERSION_MINOR 35 #define LIBAVCODEC_VERSION_MICRO 0 #define LIBAVCODEC_VERSION_INT AV_VERSION_INT(LIBAVCODEC_VERSION_MAJOR, \ diff --git a/libavcodec/xwd.h b/libavcodec/xwd.h new file mode 100644 index 0000000000..f41e2cd651 --- /dev/null +++ b/libavcodec/xwd.h @@ -0,0 +1,41 @@ +/* + * XWD image format + * + * Copyright (c) 2012 Paul B Mahol + * + * This file is part of Libav. + * + * Libav 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, + * 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 + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA + */ + +#ifndef AVCODEC_XWD_H +#define AVCODEC_XWD_H + +#define XWD_VERSION 7 +#define XWD_HEADER_SIZE 100 +#define XWD_CMAP_SIZE 12 + +#define XWD_XY_BITMAP 0 +#define XWD_XY_PIXMAP 1 +#define XWD_Z_PIXMAP 2 + +#define XWD_STATIC_GRAY 0 +#define XWD_GRAY_SCALE 1 +#define XWD_STATIC_COLOR 2 +#define XWD_PSEUDO_COLOR 3 +#define XWD_TRUE_COLOR 4 +#define XWD_DIRECT_COLOR 5 + +#endif /* AVCODEC_XWD_H */ diff --git a/libavcodec/xwddec.c b/libavcodec/xwddec.c new file mode 100644 index 0000000000..97f3a6a979 --- /dev/null +++ b/libavcodec/xwddec.c @@ -0,0 +1,267 @@ +/* + * XWD image format + * + * Copyright (c) 2012 Paul B Mahol + * + * This file is part of Libav. + * + * Libav 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, + * 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 + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA + */ + +#include "libavutil/imgutils.h" +#include "avcodec.h" +#include "bytestream.h" +#include "xwd.h" + +static av_cold int xwd_decode_init(AVCodecContext *avctx) +{ + avctx->coded_frame = avcodec_alloc_frame(); + if (!avctx->coded_frame) + return AVERROR(ENOMEM); + + return 0; +} + +static int xwd_decode_frame(AVCodecContext *avctx, void *data, + int *data_size, AVPacket *avpkt) +{ + AVFrame *p = avctx->coded_frame; + const uint8_t *buf = avpkt->data; + int i, ret, buf_size = avpkt->size; + uint32_t version, header_size, vclass, ncolors; + uint32_t xoffset, be, bpp, lsize, rsize; + uint32_t pixformat, pixdepth, bunit, bitorder, bpad; + uint32_t rgb[3]; + uint8_t *ptr; + + if (buf_size < XWD_HEADER_SIZE) + return AVERROR_INVALIDDATA; + + header_size = bytestream_get_be32(&buf); + if (buf_size < header_size) + return AVERROR_INVALIDDATA; + + version = bytestream_get_be32(&buf); + if (version != XWD_VERSION) { + av_log(avctx, AV_LOG_ERROR, "unsupported version\n"); + return AVERROR_INVALIDDATA; + } + + if (header_size < XWD_HEADER_SIZE) { + av_log(avctx, AV_LOG_ERROR, "invalid header size\n"); + return AVERROR_INVALIDDATA; + } + + pixformat = bytestream_get_be32(&buf); + pixdepth = bytestream_get_be32(&buf); + avctx->width = bytestream_get_be32(&buf); + avctx->height = bytestream_get_be32(&buf); + xoffset = bytestream_get_be32(&buf); + be = bytestream_get_be32(&buf); + bunit = bytestream_get_be32(&buf); + bitorder = bytestream_get_be32(&buf); + bpad = bytestream_get_be32(&buf); + bpp = bytestream_get_be32(&buf); + lsize = bytestream_get_be32(&buf); + vclass = bytestream_get_be32(&buf); + rgb[0] = bytestream_get_be32(&buf); + rgb[1] = bytestream_get_be32(&buf); + rgb[2] = bytestream_get_be32(&buf); + buf += 8; + ncolors = bytestream_get_be32(&buf); + buf += header_size - (XWD_HEADER_SIZE - 20); + + av_log(avctx, AV_LOG_DEBUG, "pixformat %d, pixdepth %d, bunit %d, bitorder %d, bpad %d\n", + pixformat, pixdepth, bunit, bitorder, bpad); + av_log(avctx, AV_LOG_DEBUG, "vclass %d, ncolors %d, bpp %d, be %d, lsize %d, xoffset %d\n", + vclass, ncolors, bpp, be, lsize, xoffset); + av_log(avctx, AV_LOG_DEBUG, "red %0x, green %0x, blue %0x\n", rgb[0], rgb[1], rgb[2]); + + if (pixformat > XWD_Z_PIXMAP) { + av_log(avctx, AV_LOG_ERROR, "invalid pixmap format\n"); + return AVERROR_INVALIDDATA; + } + + if (pixdepth == 0 || pixdepth > 32) { + av_log(avctx, AV_LOG_ERROR, "invalid pixmap depth\n"); + return AVERROR_INVALIDDATA; + } + + if (xoffset) { + av_log_ask_for_sample(avctx, "unsupported xoffset %d\n", xoffset); + return AVERROR_PATCHWELCOME; + } + + if (be > 1) { + av_log(avctx, AV_LOG_ERROR, "invalid byte order\n"); + return AVERROR_INVALIDDATA; + } + + if (bitorder > 1) { + av_log(avctx, AV_LOG_ERROR, "invalid bitmap bit order\n"); + return AVERROR_INVALIDDATA; + } + + if (bunit != 8 && bunit != 16 && bunit != 32) { + av_log(avctx, AV_LOG_ERROR, "invalid bitmap unit\n"); + return AVERROR_INVALIDDATA; + } + + if (bpad != 8 && bpad != 16 && bpad != 32) { + av_log(avctx, AV_LOG_ERROR, "invalid bitmap scan-line pad\n"); + return AVERROR_INVALIDDATA; + } + + if (bpp == 0 || bpp > 32) { + av_log(avctx, AV_LOG_ERROR, "invalid bits per pixel\n"); + return AVERROR_INVALIDDATA; + } + + if (ncolors > 256) { + av_log(avctx, AV_LOG_ERROR, "invalid number of entries in colormap\n"); + return AVERROR_INVALIDDATA; + } + + if ((ret = av_image_check_size(avctx->width, avctx->height, 0, NULL)) < 0) + return ret; + + rsize = FFALIGN(avctx->width * bpp, bpad) / 8; + if (lsize < rsize) { + av_log(avctx, AV_LOG_ERROR, "invalid bytes per scan-line\n"); + return AVERROR_INVALIDDATA; + } + + if (buf_size < header_size + ncolors * XWD_CMAP_SIZE + avctx->height * lsize) { + av_log(avctx, AV_LOG_ERROR, "input buffer too small\n"); + return AVERROR_INVALIDDATA; + } + + if (pixformat != XWD_Z_PIXMAP) { + av_log(avctx, AV_LOG_ERROR, "pixmap format %d unsupported\n", pixformat); + return AVERROR_PATCHWELCOME; + } + + avctx->pix_fmt = PIX_FMT_NONE; + switch (vclass) { + case XWD_STATIC_GRAY: + case XWD_GRAY_SCALE: + if (bpp != 1) + return AVERROR_INVALIDDATA; + if (pixdepth == 1) + avctx->pix_fmt = PIX_FMT_MONOWHITE; + break; + case XWD_STATIC_COLOR: + case XWD_PSEUDO_COLOR: + if (bpp == 8) + avctx->pix_fmt = PIX_FMT_PAL8; + break; + case XWD_TRUE_COLOR: + case XWD_DIRECT_COLOR: + if (bpp != 16 && bpp != 24 && bpp != 32) + return AVERROR_INVALIDDATA; + if (bpp == 16 && pixdepth == 15) { + if (rgb[0] == 0x7C00 && rgb[1] == 0x3E0 && rgb[2] == 0x1F) + avctx->pix_fmt = be ? PIX_FMT_RGB555BE : PIX_FMT_RGB555LE; + else if (rgb[0] == 0x1F && rgb[1] == 0x3E0 && rgb[2] == 0x7C00) + avctx->pix_fmt = be ? PIX_FMT_BGR555BE : PIX_FMT_BGR555LE; + } else if (bpp == 16 && pixdepth == 16) { + if (rgb[0] == 0xF800 && rgb[1] == 0x7E0 && rgb[2] == 0x1F) + avctx->pix_fmt = be ? PIX_FMT_RGB565BE : PIX_FMT_RGB565LE; + else if (rgb[0] == 0x1F && rgb[1] == 0x7E0 && rgb[2] == 0xF800) + avctx->pix_fmt = be ? PIX_FMT_BGR565BE : PIX_FMT_BGR565LE; + } else if (bpp == 24) { + if (rgb[0] == 0xFF0000 && rgb[1] == 0xFF00 && rgb[2] == 0xFF) + avctx->pix_fmt = be ? PIX_FMT_RGB24 : PIX_FMT_BGR24; + else if (rgb[0] == 0xFF && rgb[1] == 0xFF00 && rgb[2] == 0xFF0000) + avctx->pix_fmt = be ? PIX_FMT_BGR24 : PIX_FMT_RGB24; + } else if (bpp == 32) { + if (rgb[0] == 0xFF0000 && rgb[1] == 0xFF00 && rgb[2] == 0xFF) + avctx->pix_fmt = be ? PIX_FMT_ARGB : PIX_FMT_BGRA; + else if (rgb[0] == 0xFF && rgb[1] == 0xFF00 && rgb[2] == 0xFF0000) + avctx->pix_fmt = be ? PIX_FMT_ABGR : PIX_FMT_RGBA; + } + buf += ncolors * XWD_CMAP_SIZE; + break; + default: + av_log(avctx, AV_LOG_ERROR, "invalid visual class\n"); + return AVERROR_INVALIDDATA; + } + + if (avctx->pix_fmt == PIX_FMT_NONE) { + av_log_ask_for_sample(avctx, "unknown file: bpp %d, pixdepth %d, vclass %d\n", bpp, pixdepth, vclass); + return AVERROR_PATCHWELCOME; + } + + if (p->data[0]) + avctx->release_buffer(avctx, p); + + p->reference = 0; + if ((ret = avctx->get_buffer(avctx, p)) < 0) { + av_log(avctx, AV_LOG_ERROR, "get_buffer() failed\n"); + return ret; + } + + p->key_frame = 1; + p->pict_type = AV_PICTURE_TYPE_I; + + if (avctx->pix_fmt == PIX_FMT_PAL8) { + uint32_t *dst = (uint32_t *)p->data[1]; + uint8_t red, green, blue; + + for (i = 0; i < ncolors; i++) { + + buf += 4; // skip colormap entry number + red = *buf; buf += 2; + green = *buf; buf += 2; + blue = *buf; buf += 2; + buf += 2; // skip bitmask flag and padding + + dst[i] = red << 16 | green << 8 | blue; + } + } + + ptr = p->data[0]; + for (i = 0; i < avctx->height; i++) { + bytestream_get_buffer(&buf, ptr, rsize); + buf += lsize - rsize; + ptr += p->linesize[0]; + } + + *data_size = sizeof(AVFrame); + *(AVFrame *)data = *p; + + return buf_size; +} + +static av_cold int xwd_decode_close(AVCodecContext *avctx) +{ + if (avctx->coded_frame->data[0]) + avctx->release_buffer(avctx, avctx->coded_frame); + + av_freep(&avctx->coded_frame); + + return 0; +} + +AVCodec ff_xwd_decoder = { + .name = "xwd", + .type = AVMEDIA_TYPE_VIDEO, + .id = CODEC_ID_XWD, + .init = xwd_decode_init, + .close = xwd_decode_close, + .decode = xwd_decode_frame, + .capabilities = CODEC_CAP_DR1, + .long_name = NULL_IF_CONFIG_SMALL("XWD (X Window Dump) image"), +}; diff --git a/libavcodec/xwdenc.c b/libavcodec/xwdenc.c new file mode 100644 index 0000000000..5bfdaf780a --- /dev/null +++ b/libavcodec/xwdenc.c @@ -0,0 +1,246 @@ +/* + * XWD image format + * + * Copyright (c) 2012 Paul B Mahol + * + * This file is part of Libav. + * + * Libav 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, + * 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 + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA + */ + +#include "libavutil/intreadwrite.h" +#include "libavutil/pixdesc.h" +#include "avcodec.h" +#include "bytestream.h" +#include "xwd.h" + +#define WINDOW_NAME "lavcxwdenc" +#define WINDOW_NAME_SIZE 11 + +static av_cold int xwd_encode_init(AVCodecContext *avctx) +{ + avctx->coded_frame = avcodec_alloc_frame(); + if (!avctx->coded_frame) + return AVERROR(ENOMEM); + + return 0; +} + +static int xwd_encode_frame(AVCodecContext *avctx, uint8_t *buf, + int buf_size, void *data) +{ + AVFrame *p = data; + enum PixelFormat pix_fmt = avctx->pix_fmt; + uint32_t pixdepth, bpp, bpad, ncolors = 0, lsize, vclass, be = 0; + uint32_t rgb[3] = { 0 }; + uint32_t header_size; + int i, out_size; + uint8_t *ptr; + + pixdepth = av_get_bits_per_pixel(&av_pix_fmt_descriptors[pix_fmt]); + if (av_pix_fmt_descriptors[pix_fmt].flags & PIX_FMT_BE) + be = 1; + switch (pix_fmt) { + case PIX_FMT_ARGB: + case PIX_FMT_BGRA: + case PIX_FMT_RGBA: + case PIX_FMT_ABGR: + if (pix_fmt == PIX_FMT_ARGB || + pix_fmt == PIX_FMT_ABGR) + be = 1; + if (pix_fmt == PIX_FMT_ABGR || + pix_fmt == PIX_FMT_RGBA) { + rgb[0] = 0xFF; + rgb[1] = 0xFF00; + rgb[2] = 0xFF0000; + } else { + rgb[0] = 0xFF0000; + rgb[1] = 0xFF00; + rgb[2] = 0xFF; + } + bpp = 32; + pixdepth = 24; + vclass = XWD_TRUE_COLOR; + bpad = 32; + break; + case PIX_FMT_BGR24: + case PIX_FMT_RGB24: + if (pix_fmt == PIX_FMT_RGB24) + be = 1; + bpp = 24; + vclass = XWD_TRUE_COLOR; + bpad = 32; + rgb[0] = 0xFF0000; + rgb[1] = 0xFF00; + rgb[2] = 0xFF; + break; + case PIX_FMT_RGB565LE: + case PIX_FMT_RGB565BE: + case PIX_FMT_BGR565LE: + case PIX_FMT_BGR565BE: + if (pix_fmt == PIX_FMT_BGR565LE || + pix_fmt == PIX_FMT_BGR565BE) { + rgb[0] = 0x1F; + rgb[1] = 0x7E0; + rgb[2] = 0xF800; + } else { + rgb[0] = 0xF800; + rgb[1] = 0x7E0; + rgb[2] = 0x1F; + } + bpp = 16; + vclass = XWD_TRUE_COLOR; + bpad = 16; + break; + case PIX_FMT_RGB555LE: + case PIX_FMT_RGB555BE: + case PIX_FMT_BGR555LE: + case PIX_FMT_BGR555BE: + if (pix_fmt == PIX_FMT_BGR555LE || + pix_fmt == PIX_FMT_BGR555BE) { + rgb[0] = 0x1F; + rgb[1] = 0x3E0; + rgb[2] = 0x7C00; + } else { + rgb[0] = 0x7C00; + rgb[1] = 0x3E0; + rgb[2] = 0x1F; + } + bpp = 16; + vclass = XWD_TRUE_COLOR; + bpad = 16; + break; + case PIX_FMT_RGB8: + case PIX_FMT_BGR8: + case PIX_FMT_RGB4_BYTE: + case PIX_FMT_BGR4_BYTE: + case PIX_FMT_PAL8: + bpp = 8; + vclass = XWD_PSEUDO_COLOR; + bpad = 8; + ncolors = 256; + break; + case PIX_FMT_MONOWHITE: + bpp = 1; + bpad = 8; + vclass = XWD_STATIC_GRAY; + break; + default: + av_log(avctx, AV_LOG_INFO, "unsupported pixel format\n"); + return AVERROR(EINVAL); + } + + lsize = FFALIGN(bpp * avctx->width, bpad) / 8; + header_size = XWD_HEADER_SIZE + WINDOW_NAME_SIZE; + out_size = header_size + ncolors * XWD_CMAP_SIZE + avctx->height * lsize; + + if (buf_size < out_size) { + av_log(avctx, AV_LOG_ERROR, "output buffer too small\n"); + return AVERROR(ENOMEM); + } + + avctx->coded_frame->key_frame = 1; + avctx->coded_frame->pict_type = AV_PICTURE_TYPE_I; + + bytestream_put_be32(&buf, header_size); + bytestream_put_be32(&buf, XWD_VERSION); // file version + bytestream_put_be32(&buf, XWD_Z_PIXMAP); // pixmap format + bytestream_put_be32(&buf, pixdepth); // pixmap depth in pixels + bytestream_put_be32(&buf, avctx->width); // pixmap width in pixels + bytestream_put_be32(&buf, avctx->height); // pixmap height in pixels + bytestream_put_be32(&buf, 0); // bitmap x offset + bytestream_put_be32(&buf, be); // byte order + bytestream_put_be32(&buf, 32); // bitmap unit + bytestream_put_be32(&buf, be); // bit-order of image data + bytestream_put_be32(&buf, bpad); // bitmap scan-line pad in bits + bytestream_put_be32(&buf, bpp); // bits per pixel + bytestream_put_be32(&buf, lsize); // bytes per scan-line + bytestream_put_be32(&buf, vclass); // visual class + bytestream_put_be32(&buf, rgb[0]); // red mask + bytestream_put_be32(&buf, rgb[1]); // green mask + bytestream_put_be32(&buf, rgb[2]); // blue mask + bytestream_put_be32(&buf, 8); // size of each bitmask in bits + bytestream_put_be32(&buf, ncolors); // number of colors + bytestream_put_be32(&buf, ncolors); // number of entries in color map + bytestream_put_be32(&buf, avctx->width); // window width + bytestream_put_be32(&buf, avctx->height); // window height + bytestream_put_be32(&buf, 0); // window upper left X coordinate + bytestream_put_be32(&buf, 0); // window upper left Y coordinate + bytestream_put_be32(&buf, 0); // window border width + bytestream_put_buffer(&buf, WINDOW_NAME, WINDOW_NAME_SIZE); + + for (i = 0; i < ncolors; i++) { + uint32_t val; + uint8_t red, green, blue; + + val = AV_RN32A(p->data[1] + i * 4); + red = (val >> 16) & 0xFF; + green = (val >> 8) & 0xFF; + blue = val & 0xFF; + + bytestream_put_be32(&buf, i); // colormap entry number + bytestream_put_be16(&buf, red << 8); + bytestream_put_be16(&buf, green << 8); + bytestream_put_be16(&buf, blue << 8); + bytestream_put_byte(&buf, 0x7); // bitmask flag + bytestream_put_byte(&buf, 0); // padding + } + + ptr = p->data[0]; + for (i = 0; i < avctx->height; i++) { + bytestream_put_buffer(&buf, ptr, lsize); + ptr += p->linesize[0]; + } + + return out_size; +} + +static av_cold int xwd_encode_close(AVCodecContext *avctx) +{ + av_freep(&avctx->coded_frame); + + return 0; +} + +AVCodec ff_xwd_encoder = { + .name = "xwd", + .type = AVMEDIA_TYPE_VIDEO, + .id = CODEC_ID_XWD, + .init = xwd_encode_init, + .encode = xwd_encode_frame, + .close = xwd_encode_close, + .pix_fmts = (const enum PixelFormat[]) { PIX_FMT_BGRA, + PIX_FMT_RGBA, + PIX_FMT_ARGB, + PIX_FMT_ABGR, + PIX_FMT_RGB24, + PIX_FMT_BGR24, + PIX_FMT_RGB565BE, + PIX_FMT_RGB565LE, + PIX_FMT_BGR565BE, + PIX_FMT_BGR565LE, + PIX_FMT_RGB555BE, + PIX_FMT_RGB555LE, + PIX_FMT_BGR555BE, + PIX_FMT_BGR555LE, + PIX_FMT_RGB8, + PIX_FMT_BGR8, + PIX_FMT_RGB4_BYTE, + PIX_FMT_BGR4_BYTE, + PIX_FMT_PAL8, + PIX_FMT_MONOWHITE, + PIX_FMT_NONE }, + .long_name = NULL_IF_CONFIG_SMALL("XWD (X Window Dump) image"), +}; diff --git a/libavformat/img2.c b/libavformat/img2.c index 2af561c2ce..e3e7d11e43 100644 --- a/libavformat/img2.c +++ b/libavformat/img2.c @@ -85,6 +85,7 @@ static const IdStrMap img_tags[] = { { CODEC_ID_JPEG2000 , "jpc"}, { CODEC_ID_DPX , "dpx"}, { CODEC_ID_PICTOR , "pic"}, + { CODEC_ID_XWD , "xwd"}, { CODEC_ID_NONE , NULL} }; @@ -501,7 +502,7 @@ AVOutputFormat ff_image2_muxer = { .name = "image2", .long_name = NULL_IF_CONFIG_SMALL("image2 sequence"), .extensions = "bmp,dpx,jpeg,jpg,ljpg,pam,pbm,pcx,pgm,pgmyuv,png," - "ppm,sgi,tga,tif,tiff,jp2", + "ppm,sgi,tga,tif,tiff,jp2,xwd", .priv_data_size = sizeof(VideoData), .video_codec = CODEC_ID_MJPEG, .write_header = write_header, From 17ae608127324cabd083202a32a8dc210d30c3a1 Mon Sep 17 00:00:00 2001 From: Nathan Caldwell Date: Fri, 2 Dec 2011 15:08:55 -0700 Subject: [PATCH 05/16] aacenc: aac_encode_init() cleanup Macroify sanity checks and check return values of allocs and other functions. Signed-off-by: Alex Converse --- libavcodec/aacenc.c | 117 ++++++++++++++++++++++++++++---------------- 1 file changed, 74 insertions(+), 43 deletions(-) diff --git a/libavcodec/aacenc.c b/libavcodec/aacenc.c index b112fa8555..cfee931993 100644 --- a/libavcodec/aacenc.c +++ b/libavcodec/aacenc.c @@ -46,6 +46,12 @@ #define AAC_MAX_CHANNELS 6 +#define ERROR_IF(cond, ...) \ + if (cond) { \ + av_log(avctx, AV_LOG_ERROR, __VA_ARGS__); \ + return AVERROR(EINVAL); \ + } + static const uint8_t swb_size_1024_96[] = { 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 8, 8, 8, 8, 8, 12, 12, 12, 12, 12, 16, 16, 24, 28, 36, 44, @@ -160,10 +166,55 @@ static void put_audio_specific_config(AVCodecContext *avctx) flush_put_bits(&pb); } +static av_cold int aac_encode_end(AVCodecContext *avctx) +{ + AACEncContext *s = avctx->priv_data; + + ff_mdct_end(&s->mdct1024); + ff_mdct_end(&s->mdct128); + ff_psy_end(&s->psy); + if (s->psypp) + ff_psy_preprocess_end(s->psypp); + av_freep(&s->samples); + av_freep(&s->cpe); + return 0; +} + +static av_cold int dsp_init(AVCodecContext *avctx, AACEncContext *s) +{ + int ret = 0; + + dsputil_init(&s->dsp, avctx); + + // window init + ff_kbd_window_init(ff_aac_kbd_long_1024, 4.0, 1024); + ff_kbd_window_init(ff_aac_kbd_short_128, 6.0, 128); + ff_init_ff_sine_windows(10); + ff_init_ff_sine_windows(7); + + if (ret = ff_mdct_init(&s->mdct1024, 11, 0, 1.0)) + return ret; + if (ret = ff_mdct_init(&s->mdct128, 8, 0, 1.0)) + return ret; + + return 0; +} + +static av_cold int alloc_buffers(AVCodecContext *avctx, AACEncContext *s) +{ + FF_ALLOC_OR_GOTO (avctx, s->samples, 2 * 1024 * avctx->channels * sizeof(s->samples[0]), alloc_fail); + FF_ALLOCZ_OR_GOTO(avctx, s->cpe, sizeof(ChannelElement) * s->chan_map[0], alloc_fail); + FF_ALLOCZ_OR_GOTO(avctx, avctx->extradata, 5 + FF_INPUT_BUFFER_PADDING_SIZE, alloc_fail); + + return 0; +alloc_fail: + return AVERROR(ENOMEM); +} + static av_cold int aac_encode_init(AVCodecContext *avctx) { AACEncContext *s = avctx->priv_data; - int i; + int i, ret = 0; const uint8_t *sizes[2]; uint8_t grouping[AAC_MAX_CHANNELS]; int lengths[2]; @@ -173,37 +224,26 @@ static av_cold int aac_encode_init(AVCodecContext *avctx) for (i = 0; i < 16; i++) if (avctx->sample_rate == avpriv_mpeg4audio_sample_rates[i]) break; - if (i == 16) { - av_log(avctx, AV_LOG_ERROR, "Unsupported sample rate %d\n", avctx->sample_rate); - return -1; - } - if (avctx->channels > AAC_MAX_CHANNELS) { - av_log(avctx, AV_LOG_ERROR, "Unsupported number of channels: %d\n", avctx->channels); - return -1; - } - if (avctx->profile != FF_PROFILE_UNKNOWN && avctx->profile != FF_PROFILE_AAC_LOW) { - av_log(avctx, AV_LOG_ERROR, "Unsupported profile %d\n", avctx->profile); - return -1; - } - if (1024.0 * avctx->bit_rate / avctx->sample_rate > 6144 * avctx->channels) { - av_log(avctx, AV_LOG_ERROR, "Too many bits per frame requested\n"); - return -1; - } + + ERROR_IF(i == 16, + "Unsupported sample rate %d\n", avctx->sample_rate); + ERROR_IF(avctx->channels > AAC_MAX_CHANNELS, + "Unsupported number of channels: %d\n", avctx->channels); + ERROR_IF(avctx->profile != FF_PROFILE_UNKNOWN && avctx->profile != FF_PROFILE_AAC_LOW, + "Unsupported profile %d\n", avctx->profile); + ERROR_IF(1024.0 * avctx->bit_rate / avctx->sample_rate > 6144 * avctx->channels, + "Too many bits per frame requested\n"); + s->samplerate_index = i; - dsputil_init(&s->dsp, avctx); - ff_mdct_init(&s->mdct1024, 11, 0, 1.0); - ff_mdct_init(&s->mdct128, 8, 0, 1.0); - // window init - ff_kbd_window_init(ff_aac_kbd_long_1024, 4.0, 1024); - ff_kbd_window_init(ff_aac_kbd_short_128, 6.0, 128); - ff_init_ff_sine_windows(10); - ff_init_ff_sine_windows(7); + s->chan_map = aac_chan_configs[avctx->channels-1]; + + if (ret = dsp_init(avctx, s)) + goto fail; + + if (ret = alloc_buffers(avctx, s)) + goto fail; - s->chan_map = aac_chan_configs[avctx->channels-1]; - s->samples = av_malloc(2 * 1024 * avctx->channels * sizeof(s->samples[0])); - s->cpe = av_mallocz(sizeof(ChannelElement) * s->chan_map[0]); - avctx->extradata = av_mallocz(5 + FF_INPUT_BUFFER_PADDING_SIZE); avctx->extradata_size = 5; put_audio_specific_config(avctx); @@ -213,7 +253,8 @@ static av_cold int aac_encode_init(AVCodecContext *avctx) lengths[1] = ff_aac_num_swb_128[i]; for (i = 0; i < s->chan_map[0]; i++) grouping[i] = s->chan_map[i + 1] == TYPE_CPE; - ff_psy_init(&s->psy, avctx, 2, sizes, lengths, s->chan_map[0], grouping); + if (ret = ff_psy_init(&s->psy, avctx, 2, sizes, lengths, s->chan_map[0], grouping)) + goto fail; s->psypp = ff_psy_preprocess_init(avctx); s->coder = &ff_aac_coders[2]; @@ -222,6 +263,9 @@ static av_cold int aac_encode_init(AVCodecContext *avctx) ff_aac_tableinit(); return 0; +fail: + aac_encode_end(avctx); + return ret; } static void apply_window_and_mdct(AVCodecContext *avctx, AACEncContext *s, @@ -653,19 +697,6 @@ static int aac_encode_frame(AVCodecContext *avctx, return put_bits_count(&s->pb)>>3; } -static av_cold int aac_encode_end(AVCodecContext *avctx) -{ - AACEncContext *s = avctx->priv_data; - - ff_mdct_end(&s->mdct1024); - ff_mdct_end(&s->mdct128); - ff_psy_end(&s->psy); - ff_psy_preprocess_end(s->psypp); - av_freep(&s->samples); - av_freep(&s->cpe); - return 0; -} - #define AACENC_FLAGS AV_OPT_FLAG_ENCODING_PARAM | AV_OPT_FLAG_AUDIO_PARAM static const AVOption aacenc_options[] = { {"stereo_mode", "Stereo coding method", offsetof(AACEncContext, options.stereo_mode), AV_OPT_TYPE_INT, {.dbl = 0}, -1, 1, AACENC_FLAGS, "stereo_mode"}, From 53107041907f482ee941122d3bbe44683b74cb23 Mon Sep 17 00:00:00 2001 From: Nathan Caldwell Date: Wed, 14 Dec 2011 19:50:23 -0700 Subject: [PATCH 06/16] aacenc: cosmetics: move init() and end() to the bottom of the file. Signed-off-by: Alex Converse --- libavcodec/aacenc.c | 204 ++++++++++++++++++++++---------------------- 1 file changed, 102 insertions(+), 102 deletions(-) diff --git a/libavcodec/aacenc.c b/libavcodec/aacenc.c index cfee931993..33396b2e83 100644 --- a/libavcodec/aacenc.c +++ b/libavcodec/aacenc.c @@ -166,108 +166,6 @@ static void put_audio_specific_config(AVCodecContext *avctx) flush_put_bits(&pb); } -static av_cold int aac_encode_end(AVCodecContext *avctx) -{ - AACEncContext *s = avctx->priv_data; - - ff_mdct_end(&s->mdct1024); - ff_mdct_end(&s->mdct128); - ff_psy_end(&s->psy); - if (s->psypp) - ff_psy_preprocess_end(s->psypp); - av_freep(&s->samples); - av_freep(&s->cpe); - return 0; -} - -static av_cold int dsp_init(AVCodecContext *avctx, AACEncContext *s) -{ - int ret = 0; - - dsputil_init(&s->dsp, avctx); - - // window init - ff_kbd_window_init(ff_aac_kbd_long_1024, 4.0, 1024); - ff_kbd_window_init(ff_aac_kbd_short_128, 6.0, 128); - ff_init_ff_sine_windows(10); - ff_init_ff_sine_windows(7); - - if (ret = ff_mdct_init(&s->mdct1024, 11, 0, 1.0)) - return ret; - if (ret = ff_mdct_init(&s->mdct128, 8, 0, 1.0)) - return ret; - - return 0; -} - -static av_cold int alloc_buffers(AVCodecContext *avctx, AACEncContext *s) -{ - FF_ALLOC_OR_GOTO (avctx, s->samples, 2 * 1024 * avctx->channels * sizeof(s->samples[0]), alloc_fail); - FF_ALLOCZ_OR_GOTO(avctx, s->cpe, sizeof(ChannelElement) * s->chan_map[0], alloc_fail); - FF_ALLOCZ_OR_GOTO(avctx, avctx->extradata, 5 + FF_INPUT_BUFFER_PADDING_SIZE, alloc_fail); - - return 0; -alloc_fail: - return AVERROR(ENOMEM); -} - -static av_cold int aac_encode_init(AVCodecContext *avctx) -{ - AACEncContext *s = avctx->priv_data; - int i, ret = 0; - const uint8_t *sizes[2]; - uint8_t grouping[AAC_MAX_CHANNELS]; - int lengths[2]; - - avctx->frame_size = 1024; - - for (i = 0; i < 16; i++) - if (avctx->sample_rate == avpriv_mpeg4audio_sample_rates[i]) - break; - - ERROR_IF(i == 16, - "Unsupported sample rate %d\n", avctx->sample_rate); - ERROR_IF(avctx->channels > AAC_MAX_CHANNELS, - "Unsupported number of channels: %d\n", avctx->channels); - ERROR_IF(avctx->profile != FF_PROFILE_UNKNOWN && avctx->profile != FF_PROFILE_AAC_LOW, - "Unsupported profile %d\n", avctx->profile); - ERROR_IF(1024.0 * avctx->bit_rate / avctx->sample_rate > 6144 * avctx->channels, - "Too many bits per frame requested\n"); - - s->samplerate_index = i; - - s->chan_map = aac_chan_configs[avctx->channels-1]; - - if (ret = dsp_init(avctx, s)) - goto fail; - - if (ret = alloc_buffers(avctx, s)) - goto fail; - - avctx->extradata_size = 5; - put_audio_specific_config(avctx); - - sizes[0] = swb_size_1024[i]; - sizes[1] = swb_size_128[i]; - lengths[0] = ff_aac_num_swb_1024[i]; - lengths[1] = ff_aac_num_swb_128[i]; - for (i = 0; i < s->chan_map[0]; i++) - grouping[i] = s->chan_map[i + 1] == TYPE_CPE; - if (ret = ff_psy_init(&s->psy, avctx, 2, sizes, lengths, s->chan_map[0], grouping)) - goto fail; - s->psypp = ff_psy_preprocess_init(avctx); - s->coder = &ff_aac_coders[2]; - - s->lambda = avctx->global_quality ? avctx->global_quality : 120; - - ff_aac_tableinit(); - - return 0; -fail: - aac_encode_end(avctx); - return ret; -} - static void apply_window_and_mdct(AVCodecContext *avctx, AACEncContext *s, SingleChannelElement *sce, short *audio) { @@ -697,6 +595,108 @@ static int aac_encode_frame(AVCodecContext *avctx, return put_bits_count(&s->pb)>>3; } +static av_cold int aac_encode_end(AVCodecContext *avctx) +{ + AACEncContext *s = avctx->priv_data; + + ff_mdct_end(&s->mdct1024); + ff_mdct_end(&s->mdct128); + ff_psy_end(&s->psy); + if (s->psypp) + ff_psy_preprocess_end(s->psypp); + av_freep(&s->samples); + av_freep(&s->cpe); + return 0; +} + +static av_cold int dsp_init(AVCodecContext *avctx, AACEncContext *s) +{ + int ret = 0; + + dsputil_init(&s->dsp, avctx); + + // window init + ff_kbd_window_init(ff_aac_kbd_long_1024, 4.0, 1024); + ff_kbd_window_init(ff_aac_kbd_short_128, 6.0, 128); + ff_init_ff_sine_windows(10); + ff_init_ff_sine_windows(7); + + if (ret = ff_mdct_init(&s->mdct1024, 11, 0, 1.0)) + return ret; + if (ret = ff_mdct_init(&s->mdct128, 8, 0, 1.0)) + return ret; + + return 0; +} + +static av_cold int alloc_buffers(AVCodecContext *avctx, AACEncContext *s) +{ + FF_ALLOC_OR_GOTO (avctx, s->samples, 2 * 1024 * avctx->channels * sizeof(s->samples[0]), alloc_fail); + FF_ALLOCZ_OR_GOTO(avctx, s->cpe, sizeof(ChannelElement) * s->chan_map[0], alloc_fail); + FF_ALLOCZ_OR_GOTO(avctx, avctx->extradata, 5 + FF_INPUT_BUFFER_PADDING_SIZE, alloc_fail); + + return 0; +alloc_fail: + return AVERROR(ENOMEM); +} + +static av_cold int aac_encode_init(AVCodecContext *avctx) +{ + AACEncContext *s = avctx->priv_data; + int i, ret = 0; + const uint8_t *sizes[2]; + uint8_t grouping[AAC_MAX_CHANNELS]; + int lengths[2]; + + avctx->frame_size = 1024; + + for (i = 0; i < 16; i++) + if (avctx->sample_rate == avpriv_mpeg4audio_sample_rates[i]) + break; + + ERROR_IF(i == 16, + "Unsupported sample rate %d\n", avctx->sample_rate); + ERROR_IF(avctx->channels > AAC_MAX_CHANNELS, + "Unsupported number of channels: %d\n", avctx->channels); + ERROR_IF(avctx->profile != FF_PROFILE_UNKNOWN && avctx->profile != FF_PROFILE_AAC_LOW, + "Unsupported profile %d\n", avctx->profile); + ERROR_IF(1024.0 * avctx->bit_rate / avctx->sample_rate > 6144 * avctx->channels, + "Too many bits per frame requested\n"); + + s->samplerate_index = i; + + s->chan_map = aac_chan_configs[avctx->channels-1]; + + if (ret = dsp_init(avctx, s)) + goto fail; + + if (ret = alloc_buffers(avctx, s)) + goto fail; + + avctx->extradata_size = 5; + put_audio_specific_config(avctx); + + sizes[0] = swb_size_1024[i]; + sizes[1] = swb_size_128[i]; + lengths[0] = ff_aac_num_swb_1024[i]; + lengths[1] = ff_aac_num_swb_128[i]; + for (i = 0; i < s->chan_map[0]; i++) + grouping[i] = s->chan_map[i + 1] == TYPE_CPE; + if (ret = ff_psy_init(&s->psy, avctx, 2, sizes, lengths, s->chan_map[0], grouping)) + goto fail; + s->psypp = ff_psy_preprocess_init(avctx); + s->coder = &ff_aac_coders[2]; + + s->lambda = avctx->global_quality ? avctx->global_quality : 120; + + ff_aac_tableinit(); + + return 0; +fail: + aac_encode_end(avctx); + return ret; +} + #define AACENC_FLAGS AV_OPT_FLAG_ENCODING_PARAM | AV_OPT_FLAG_AUDIO_PARAM static const AVOption aacenc_options[] = { {"stereo_mode", "Stereo coding method", offsetof(AACEncContext, options.stereo_mode), AV_OPT_TYPE_INT, {.dbl = 0}, -1, 1, AACENC_FLAGS, "stereo_mode"}, From 843cd4a3edf254c2a42663777c1633d67cbef238 Mon Sep 17 00:00:00 2001 From: Nathan Caldwell Date: Sat, 7 Jan 2012 14:16:10 -0700 Subject: [PATCH 07/16] aacpsy: cosmetics, change a FIXME to a NOTE about subshort comparisons Also fix a typo. Signed-off-by: Alex Converse --- libavcodec/aacpsy.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/libavcodec/aacpsy.c b/libavcodec/aacpsy.c index 38d9d9f7d8..04feea388c 100644 --- a/libavcodec/aacpsy.c +++ b/libavcodec/aacpsy.c @@ -827,12 +827,12 @@ static FFPsyWindowInfo psy_lame_window(FFPsyContext *ctx, p = fabsf(*pf); pch->prev_energy_subshort[i] = energy_subshort[i + PSY_LAME_NUM_SUBBLOCKS] = p; energy_short[1 + i / PSY_LAME_NUM_SUBBLOCKS] += p; - /* FIXME: The indexes below are [i + 3 - 2] in the LAME source. - * Obviously the 3 and 2 have some significance, or this would be just [i + 1] - * (which is what we use here). What the 3 stands for is ambigious, as it is both - * number of short blocks, and the number of sub-short blocks. - * It seems that LAME is comparing each sub-block to sub-block + 1 in the - * previous block. + /* NOTE: The indexes below are [i + 3 - 2] in the LAME source. + * Obviously the 3 and 2 have some significance, or this would be just [i + 1] + * (which is what we use here). What the 3 stands for is ambiguous, as it is both + * number of short blocks, and the number of sub-short blocks. + * It seems that LAME is comparing each sub-block to sub-block + 1 in the + * previous block. */ if (p > energy_subshort[i + 1]) p = p / energy_subshort[i + 1]; From 207bf44d161300ec864663371eb65a3e4c8abfca Mon Sep 17 00:00:00 2001 From: Nathan Caldwell Date: Sun, 8 Jan 2012 18:38:39 -0700 Subject: [PATCH 08/16] aacenc: cosmetics, replace 'rd' with 'bits' in codebook_trellis_rate to make it more clear what is being calculated. Signed-off-by: Alex Converse --- libavcodec/aaccoder.c | 28 ++++++++++++++-------------- 1 file changed, 14 insertions(+), 14 deletions(-) diff --git a/libavcodec/aaccoder.c b/libavcodec/aaccoder.c index f8a8f3d844..ec78acc936 100644 --- a/libavcodec/aaccoder.c +++ b/libavcodec/aaccoder.c @@ -420,7 +420,7 @@ static void codebook_trellis_rate(AACEncContext *s, SingleChannelElement *sce, const int run_esc = (1 << run_bits) - 1; int idx, ppos, count; int stackrun[120], stackcb[120], stack_len; - float next_minrd = INFINITY; + float next_minbits = INFINITY; int next_mincb = 0; abs_pow34_v(s->scoefs, sce->coeffs, 1024); @@ -434,7 +434,7 @@ static void codebook_trellis_rate(AACEncContext *s, SingleChannelElement *sce, size = sce->ics.swb_sizes[swb]; if (sce->zeroes[win*16 + swb]) { float cost_stay_here = path[swb][0].cost; - float cost_get_here = next_minrd + run_bits + 4; + float cost_get_here = next_minbits + run_bits + 4; if ( run_value_bits[sce->ics.num_windows == 8][path[swb][0].run] != run_value_bits[sce->ics.num_windows == 8][path[swb][0].run+1]) cost_stay_here += run_bits; @@ -447,7 +447,7 @@ static void codebook_trellis_rate(AACEncContext *s, SingleChannelElement *sce, path[swb+1][0].cost = cost_stay_here; path[swb+1][0].run = path[swb][0].run + 1; } - next_minrd = path[swb+1][0].cost; + next_minbits = path[swb+1][0].cost; next_mincb = 0; for (cb = 1; cb < 12; cb++) { path[swb+1][cb].cost = 61450; @@ -455,10 +455,10 @@ static void codebook_trellis_rate(AACEncContext *s, SingleChannelElement *sce, path[swb+1][cb].run = 0; } } else { - float minrd = next_minrd; + float minbits = next_minbits; int mincb = next_mincb; int startcb = sce->band_type[win*16+swb]; - next_minrd = INFINITY; + next_minbits = INFINITY; next_mincb = 0; for (cb = 0; cb < startcb; cb++) { path[swb+1][cb].cost = 61450; @@ -467,15 +467,15 @@ static void codebook_trellis_rate(AACEncContext *s, SingleChannelElement *sce, } for (cb = startcb; cb < 12; cb++) { float cost_stay_here, cost_get_here; - float rd = 0.0f; + float bits = 0.0f; for (w = 0; w < group_len; w++) { - rd += quantize_band_cost(s, sce->coeffs + start + w*128, - s->scoefs + start + w*128, size, - sce->sf_idx[(win+w)*16+swb], cb, - 0, INFINITY, NULL); + bits += quantize_band_cost(s, sce->coeffs + start + w*128, + s->scoefs + start + w*128, size, + sce->sf_idx[(win+w)*16+swb], cb, + 0, INFINITY, NULL); } - cost_stay_here = path[swb][cb].cost + rd; - cost_get_here = minrd + rd + run_bits + 4; + cost_stay_here = path[swb][cb].cost + bits; + cost_get_here = minbits + bits + run_bits + 4; if ( run_value_bits[sce->ics.num_windows == 8][path[swb][cb].run] != run_value_bits[sce->ics.num_windows == 8][path[swb][cb].run+1]) cost_stay_here += run_bits; @@ -488,8 +488,8 @@ static void codebook_trellis_rate(AACEncContext *s, SingleChannelElement *sce, path[swb+1][cb].cost = cost_stay_here; path[swb+1][cb].run = path[swb][cb].run + 1; } - if (path[swb+1][cb].cost < next_minrd) { - next_minrd = path[swb+1][cb].cost; + if (path[swb+1][cb].cost < next_minbits) { + next_minbits = path[swb+1][cb].cost; next_mincb = cb; } } From 6381f913d19d78513bab06fad7c50548975475a3 Mon Sep 17 00:00:00 2001 From: Nathan Caldwell Date: Sat, 7 Jan 2012 14:21:35 -0700 Subject: [PATCH 09/16] aacpsy: Replace an if with FFMAX in LAME windowing. Signed-off-by: Alex Converse --- libavcodec/aacpsy.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/libavcodec/aacpsy.c b/libavcodec/aacpsy.c index 04feea388c..577d8fba80 100644 --- a/libavcodec/aacpsy.c +++ b/libavcodec/aacpsy.c @@ -823,8 +823,7 @@ static FFPsyWindowInfo psy_lame_window(FFPsyContext *ctx, float const *const pfe = pf + AAC_BLOCK_SIZE_LONG / (AAC_NUM_BLOCKS_SHORT * PSY_LAME_NUM_SUBBLOCKS); float p = 1.0f; for (; pf < pfe; pf++) - if (p < fabsf(*pf)) - p = fabsf(*pf); + p = FFMAX(p, fabsf(*pf)); pch->prev_energy_subshort[i] = energy_subshort[i + PSY_LAME_NUM_SUBBLOCKS] = p; energy_short[1 + i / PSY_LAME_NUM_SUBBLOCKS] += p; /* NOTE: The indexes below are [i + 3 - 2] in the LAME source. From 025ccf1f8bd669f45b628acf51e7febcb1fddd3b Mon Sep 17 00:00:00 2001 From: Nathan Caldwell Date: Sat, 17 Dec 2011 18:45:55 -0700 Subject: [PATCH 10/16] aacenc: Request normalized float samples instead of converting s16 samples to float. Signed-off-by: Alex Converse --- libavcodec/aacenc.c | 12 ++++++------ libavcodec/aacenc.h | 2 +- libavcodec/aacpsy.c | 10 +++++----- libavcodec/psymodel.c | 7 +++---- libavcodec/psymodel.h | 7 +++---- 5 files changed, 18 insertions(+), 20 deletions(-) diff --git a/libavcodec/aacenc.c b/libavcodec/aacenc.c index 33396b2e83..3bd04bffe1 100644 --- a/libavcodec/aacenc.c +++ b/libavcodec/aacenc.c @@ -167,7 +167,7 @@ static void put_audio_specific_config(AVCodecContext *avctx) } static void apply_window_and_mdct(AVCodecContext *avctx, AACEncContext *s, - SingleChannelElement *sce, short *audio) + SingleChannelElement *sce, float *audio) { int i, k; const int chans = avctx->channels; @@ -434,7 +434,7 @@ static int aac_encode_frame(AVCodecContext *avctx, uint8_t *frame, int buf_size, void *data) { AACEncContext *s = avctx->priv_data; - int16_t *samples = s->samples, *samples2, *la; + float *samples = s->samples, *samples2, *la; ChannelElement *cpe; int i, ch, w, g, chans, tag, start_ch; int chan_el_counter[4]; @@ -452,7 +452,7 @@ static int aac_encode_frame(AVCodecContext *avctx, for (i = 0; i < s->chan_map[0]; i++) { tag = s->chan_map[i+1]; chans = tag == TYPE_CPE ? 2 : 1; - ff_psy_preprocess(s->psypp, (uint16_t*)data + start_ch, + ff_psy_preprocess(s->psypp, (float*)data + start_ch, samples2 + start_ch, start_ch, chans); start_ch += chans; } @@ -621,9 +621,9 @@ static av_cold int dsp_init(AVCodecContext *avctx, AACEncContext *s) ff_init_ff_sine_windows(10); ff_init_ff_sine_windows(7); - if (ret = ff_mdct_init(&s->mdct1024, 11, 0, 1.0)) + if (ret = ff_mdct_init(&s->mdct1024, 11, 0, 32768.0)) return ret; - if (ret = ff_mdct_init(&s->mdct128, 8, 0, 1.0)) + if (ret = ff_mdct_init(&s->mdct128, 8, 0, 32768.0)) return ret; return 0; @@ -722,7 +722,7 @@ AVCodec ff_aac_encoder = { .encode = aac_encode_frame, .close = aac_encode_end, .capabilities = CODEC_CAP_SMALL_LAST_FRAME | CODEC_CAP_DELAY | CODEC_CAP_EXPERIMENTAL, - .sample_fmts = (const enum AVSampleFormat[]){AV_SAMPLE_FMT_S16,AV_SAMPLE_FMT_NONE}, + .sample_fmts = (const enum AVSampleFormat[]){AV_SAMPLE_FMT_FLT,AV_SAMPLE_FMT_NONE}, .long_name = NULL_IF_CONFIG_SMALL("Advanced Audio Coding"), .priv_class = &aacenc_class, }; diff --git a/libavcodec/aacenc.h b/libavcodec/aacenc.h index acd185a809..1f5e6503ca 100644 --- a/libavcodec/aacenc.h +++ b/libavcodec/aacenc.h @@ -58,7 +58,7 @@ typedef struct AACEncContext { FFTContext mdct1024; ///< long (1024 samples) frame transform context FFTContext mdct128; ///< short (128 samples) frame transform context DSPContext dsp; - int16_t *samples; ///< saved preprocessed input + float *samples; ///< saved preprocessed input int samplerate_index; ///< MPEG-4 samplerate index const uint8_t *chan_map; ///< channel configuration map diff --git a/libavcodec/aacpsy.c b/libavcodec/aacpsy.c index 577d8fba80..5e9e3913e8 100644 --- a/libavcodec/aacpsy.c +++ b/libavcodec/aacpsy.c @@ -776,9 +776,8 @@ static void lame_apply_block_type(AacPsyChannel *ctx, FFPsyWindowInfo *wi, int u ctx->next_window_seq = blocktype; } -static FFPsyWindowInfo psy_lame_window(FFPsyContext *ctx, - const int16_t *audio, const int16_t *la, - int channel, int prev_type) +static FFPsyWindowInfo psy_lame_window(FFPsyContext *ctx, const float *audio, + const float *la, int channel, int prev_type) { AacPsyContext *pctx = (AacPsyContext*) ctx->model_priv_data; AacPsyChannel *pch = &pctx->ch[channel]; @@ -796,7 +795,7 @@ static FFPsyWindowInfo psy_lame_window(FFPsyContext *ctx, float energy_subshort[(AAC_NUM_BLOCKS_SHORT + 1) * PSY_LAME_NUM_SUBBLOCKS]; float energy_short[AAC_NUM_BLOCKS_SHORT + 1] = { 0 }; int chans = ctx->avctx->channels; - const int16_t *firbuf = la + (AAC_BLOCK_SIZE_SHORT/4 - PSY_LAME_FIR_LEN) * chans; + const float *firbuf = la + (AAC_BLOCK_SIZE_SHORT/4 - PSY_LAME_FIR_LEN) * chans; int j, att_sum = 0; /* LAME comment: apply high pass filter of fs/4 */ @@ -808,7 +807,8 @@ static FFPsyWindowInfo psy_lame_window(FFPsyContext *ctx, sum1 += psy_fir_coeffs[j] * (firbuf[(i + j) * chans] + firbuf[(i + PSY_LAME_FIR_LEN - j) * chans]); sum2 += psy_fir_coeffs[j + 1] * (firbuf[(i + j + 1) * chans] + firbuf[(i + PSY_LAME_FIR_LEN - j - 1) * chans]); } - hpfsmpl[i] = sum1 + sum2; + /* NOTE: The LAME psymodel expects it's input in the range -32768 to 32768. Tuning this for normalized floats would be difficult. */ + hpfsmpl[i] = (sum1 + sum2) * 32768.0f; } /* Calculate the energies of each sub-shortblock */ diff --git a/libavcodec/psymodel.c b/libavcodec/psymodel.c index 740d859456..49df1189e4 100644 --- a/libavcodec/psymodel.c +++ b/libavcodec/psymodel.c @@ -112,14 +112,13 @@ av_cold struct FFPsyPreprocessContext* ff_psy_preprocess_init(AVCodecContext *av return ctx; } -void ff_psy_preprocess(struct FFPsyPreprocessContext *ctx, - const int16_t *audio, int16_t *dest, - int tag, int channels) +void ff_psy_preprocess(struct FFPsyPreprocessContext *ctx, const float *audio, + float *dest, int tag, int channels) { int ch, i; if (ctx->fstate) { for (ch = 0; ch < channels; ch++) - ff_iir_filter(ctx->fcoeffs, ctx->fstate[tag+ch], ctx->avctx->frame_size, + ff_iir_filter_flt(ctx->fcoeffs, ctx->fstate[tag+ch], ctx->avctx->frame_size, audio + ch, ctx->avctx->channels, dest + ch, ctx->avctx->channels); } else { diff --git a/libavcodec/psymodel.h b/libavcodec/psymodel.h index 3e866e40cc..03d078ed58 100644 --- a/libavcodec/psymodel.h +++ b/libavcodec/psymodel.h @@ -109,7 +109,7 @@ typedef struct FFPsyModel { * * @return suggested window information in a structure */ - FFPsyWindowInfo (*window)(FFPsyContext *ctx, const int16_t *audio, const int16_t *la, int channel, int prev_type); + FFPsyWindowInfo (*window)(FFPsyContext *ctx, const float *audio, const float *la, int channel, int prev_type); /** * Perform psychoacoustic analysis and set band info (threshold, energy) for a group of channels. @@ -179,9 +179,8 @@ av_cold struct FFPsyPreprocessContext* ff_psy_preprocess_init(AVCodecContext *av * @param tag channel number * @param channels number of channel to preprocess (some additional work may be done on stereo pair) */ -void ff_psy_preprocess(struct FFPsyPreprocessContext *ctx, - const int16_t *audio, int16_t *dest, - int tag, int channels); +void ff_psy_preprocess(struct FFPsyPreprocessContext *ctx, const float *audio, + float *dest, int tag, int channels); /** * Cleanup audio preprocessing module. From 80d44277e6ae6291a1ddba476939bb394a2ed822 Mon Sep 17 00:00:00 2001 From: Nathan Caldwell Date: Fri, 6 Jan 2012 14:24:37 -0700 Subject: [PATCH 11/16] aacenc: Move Q^3/4 calculation to it's own table This should be moved to tablegen at some point. Signed-off-by: Alex Converse --- libavcodec/aaccoder.c | 7 ++++--- libavcodec/aacenc.c | 5 +++++ libavcodec/aacenc.h | 2 ++ 3 files changed, 11 insertions(+), 3 deletions(-) diff --git a/libavcodec/aaccoder.c b/libavcodec/aaccoder.c index ec78acc936..72be2a272b 100644 --- a/libavcodec/aaccoder.c +++ b/libavcodec/aaccoder.c @@ -110,14 +110,15 @@ static av_always_inline float quantize_and_encode_band_cost_template( int *bits, int BT_ZERO, int BT_UNSIGNED, int BT_PAIR, int BT_ESC) { - const float IQ = ff_aac_pow2sf_tab[POW_SF2_ZERO + scale_idx - SCALE_ONE_POS + SCALE_DIV_512]; - const float Q = ff_aac_pow2sf_tab[POW_SF2_ZERO - scale_idx + SCALE_ONE_POS - SCALE_DIV_512]; + const int q_idx = POW_SF2_ZERO - scale_idx + SCALE_ONE_POS - SCALE_DIV_512; + const float Q = ff_aac_pow2sf_tab [q_idx]; + const float Q34 = ff_aac_pow34sf_tab[q_idx]; + const float IQ = ff_aac_pow2sf_tab [POW_SF2_ZERO + scale_idx - SCALE_ONE_POS + SCALE_DIV_512]; const float CLIPPED_ESCAPE = 165140.0f*IQ; int i, j; float cost = 0; const int dim = BT_PAIR ? 2 : 4; int resbits = 0; - const float Q34 = sqrtf(Q * sqrtf(Q)); const int range = aac_cb_range[cb]; const int maxval = aac_cb_maxval[cb]; int off; diff --git a/libavcodec/aacenc.c b/libavcodec/aacenc.c index 3bd04bffe1..8356ca8db3 100644 --- a/libavcodec/aacenc.c +++ b/libavcodec/aacenc.c @@ -52,6 +52,8 @@ return AVERROR(EINVAL); \ } +float ff_aac_pow34sf_tab[428]; + static const uint8_t swb_size_1024_96[] = { 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 8, 8, 8, 8, 8, 12, 12, 12, 12, 12, 16, 16, 24, 28, 36, 44, @@ -691,6 +693,9 @@ static av_cold int aac_encode_init(AVCodecContext *avctx) ff_aac_tableinit(); + for (i = 0; i < 428; i++) + ff_aac_pow34sf_tab[i] = sqrt(ff_aac_pow2sf_tab[i] * sqrt(ff_aac_pow2sf_tab[i])); + return 0; fail: aac_encode_end(avctx); diff --git a/libavcodec/aacenc.h b/libavcodec/aacenc.h index 1f5e6503ca..79d542f70a 100644 --- a/libavcodec/aacenc.h +++ b/libavcodec/aacenc.h @@ -74,4 +74,6 @@ typedef struct AACEncContext { DECLARE_ALIGNED(32, float, scoefs)[1024]; ///< scaled coefficients } AACEncContext; +extern float ff_aac_pow34sf_tab[428]; + #endif /* AVCODEC_AACENC_H */ From 04af2efaae661fd48334bab52f6561450a403f20 Mon Sep 17 00:00:00 2001 From: Nathan Caldwell Date: Wed, 7 Dec 2011 15:20:10 -0700 Subject: [PATCH 12/16] aacenc: Store channel count in AACEncContext. Signed-off-by: Alex Converse --- libavcodec/aacenc.c | 42 ++++++++++++++++++++++-------------------- libavcodec/aacenc.h | 1 + 2 files changed, 23 insertions(+), 20 deletions(-) diff --git a/libavcodec/aacenc.c b/libavcodec/aacenc.c index 8356ca8db3..a25edeb62a 100644 --- a/libavcodec/aacenc.c +++ b/libavcodec/aacenc.c @@ -155,7 +155,7 @@ static void put_audio_specific_config(AVCodecContext *avctx) init_put_bits(&pb, avctx->extradata, avctx->extradata_size*8); put_bits(&pb, 5, 2); //object type - AAC-LC put_bits(&pb, 4, s->samplerate_index); //sample rate index - put_bits(&pb, 4, avctx->channels); + put_bits(&pb, 4, s->channels); //GASpecificConfig put_bits(&pb, 1, 0); //frame length - 1024 samples put_bits(&pb, 1, 0); //does not depend on core coder @@ -168,11 +168,11 @@ static void put_audio_specific_config(AVCodecContext *avctx) flush_put_bits(&pb); } -static void apply_window_and_mdct(AVCodecContext *avctx, AACEncContext *s, - SingleChannelElement *sce, float *audio) +static void apply_window_and_mdct(AACEncContext *s, SingleChannelElement *sce, + float *audio) { int i, k; - const int chans = avctx->channels; + const int chans = s->channels; const float * lwindow = sce->ics.use_kb_window[0] ? ff_aac_kbd_long_1024 : ff_sine_1024; const float * swindow = sce->ics.use_kb_window[0] ? ff_aac_kbd_short_128 : ff_sine_128; const float * pwindow = sce->ics.use_kb_window[1] ? ff_aac_kbd_short_128 : ff_sine_128; @@ -446,11 +446,11 @@ static int aac_encode_frame(AVCodecContext *avctx, return 0; if (data) { if (!s->psypp) { - memcpy(s->samples + 1024 * avctx->channels, data, - 1024 * avctx->channels * sizeof(s->samples[0])); + memcpy(s->samples + 1024 * s->channels, data, + 1024 * s->channels * sizeof(s->samples[0])); } else { start_ch = 0; - samples2 = s->samples + 1024 * avctx->channels; + samples2 = s->samples + 1024 * s->channels; for (i = 0; i < s->chan_map[0]; i++) { tag = s->chan_map[i+1]; chans = tag == TYPE_CPE ? 2 : 1; @@ -461,8 +461,8 @@ static int aac_encode_frame(AVCodecContext *avctx, } } if (!avctx->frame_number) { - memcpy(s->samples, s->samples + 1024 * avctx->channels, - 1024 * avctx->channels * sizeof(s->samples[0])); + memcpy(s->samples, s->samples + 1024 * s->channels, + 1024 * s->channels * sizeof(s->samples[0])); return 0; } @@ -476,7 +476,7 @@ static int aac_encode_frame(AVCodecContext *avctx, IndividualChannelStream *ics = &cpe->ch[ch].ics; int cur_channel = start_ch + ch; samples2 = samples + cur_channel; - la = samples2 + (448+64) * avctx->channels; + la = samples2 + (448+64) * s->channels; if (!data) la = NULL; if (tag == TYPE_LFE) { @@ -504,7 +504,7 @@ static int aac_encode_frame(AVCodecContext *avctx, for (w = 0; w < ics->num_windows; w++) ics->group_len[w] = wi[ch].grouping[w]; - apply_window_and_mdct(avctx, s, &cpe->ch[ch], samples2); + apply_window_and_mdct(s, &cpe->ch[ch], samples2); } start_ch += chans; } @@ -570,8 +570,8 @@ static int aac_encode_frame(AVCodecContext *avctx, } frame_bits = put_bits_count(&s->pb); - if (frame_bits <= 6144 * avctx->channels - 3) { - s->psy.bitres.bits = frame_bits / avctx->channels; + if (frame_bits <= 6144 * s->channels - 3) { + s->psy.bitres.bits = frame_bits / s->channels; break; } @@ -592,8 +592,8 @@ static int aac_encode_frame(AVCodecContext *avctx, if (!data) s->last_frame = 1; - memcpy(s->samples, s->samples + 1024 * avctx->channels, - 1024 * avctx->channels * sizeof(s->samples[0])); + memcpy(s->samples, s->samples + 1024 * s->channels, + 1024 * s->channels * sizeof(s->samples[0])); return put_bits_count(&s->pb)>>3; } @@ -633,7 +633,7 @@ static av_cold int dsp_init(AVCodecContext *avctx, AACEncContext *s) static av_cold int alloc_buffers(AVCodecContext *avctx, AACEncContext *s) { - FF_ALLOC_OR_GOTO (avctx, s->samples, 2 * 1024 * avctx->channels * sizeof(s->samples[0]), alloc_fail); + FF_ALLOC_OR_GOTO (avctx, s->samples, 2 * 1024 * s->channels * sizeof(s->samples[0]), alloc_fail); FF_ALLOCZ_OR_GOTO(avctx, s->cpe, sizeof(ChannelElement) * s->chan_map[0], alloc_fail); FF_ALLOCZ_OR_GOTO(avctx, avctx->extradata, 5 + FF_INPUT_BUFFER_PADDING_SIZE, alloc_fail); @@ -656,18 +656,20 @@ static av_cold int aac_encode_init(AVCodecContext *avctx) if (avctx->sample_rate == avpriv_mpeg4audio_sample_rates[i]) break; + s->channels = avctx->channels; + ERROR_IF(i == 16, "Unsupported sample rate %d\n", avctx->sample_rate); - ERROR_IF(avctx->channels > AAC_MAX_CHANNELS, - "Unsupported number of channels: %d\n", avctx->channels); + ERROR_IF(s->channels > AAC_MAX_CHANNELS, + "Unsupported number of channels: %d\n", s->channels); ERROR_IF(avctx->profile != FF_PROFILE_UNKNOWN && avctx->profile != FF_PROFILE_AAC_LOW, "Unsupported profile %d\n", avctx->profile); - ERROR_IF(1024.0 * avctx->bit_rate / avctx->sample_rate > 6144 * avctx->channels, + ERROR_IF(1024.0 * avctx->bit_rate / avctx->sample_rate > 6144 * s->channels, "Too many bits per frame requested\n"); s->samplerate_index = i; - s->chan_map = aac_chan_configs[avctx->channels-1]; + s->chan_map = aac_chan_configs[s->channels-1]; if (ret = dsp_init(avctx, s)) goto fail; diff --git a/libavcodec/aacenc.h b/libavcodec/aacenc.h index 79d542f70a..211c70a805 100644 --- a/libavcodec/aacenc.h +++ b/libavcodec/aacenc.h @@ -61,6 +61,7 @@ typedef struct AACEncContext { float *samples; ///< saved preprocessed input int samplerate_index; ///< MPEG-4 samplerate index + int channels; ///< channel count const uint8_t *chan_map; ///< channel configuration map ChannelElement *cpe; ///< channel elements From 9b8e2a870957293898998209c6e9bed290cc9bef Mon Sep 17 00:00:00 2001 From: Nathan Caldwell Date: Wed, 14 Dec 2011 19:43:56 -0700 Subject: [PATCH 13/16] aacenc: Deinterleave input samples before processing. Signed-off-by: Alex Converse --- libavcodec/aacenc.c | 100 ++++++++++++++++++++++++++---------------- libavcodec/aacenc.h | 6 ++- libavcodec/aacpsy.c | 11 +++-- libavcodec/psymodel.c | 16 +++---- libavcodec/psymodel.h | 9 ++-- 5 files changed, 80 insertions(+), 62 deletions(-) diff --git a/libavcodec/aacenc.c b/libavcodec/aacenc.c index a25edeb62a..742fee9cd1 100644 --- a/libavcodec/aacenc.c +++ b/libavcodec/aacenc.c @@ -143,6 +143,18 @@ static const uint8_t aac_chan_configs[6][5] = { {4, TYPE_SCE, TYPE_CPE, TYPE_CPE, TYPE_LFE}, // 6 channels - front center + stereo + back stereo + LFE }; +/** + * Table to remap channels from Libav's default order to AAC order. + */ +static const uint8_t aac_chan_maps[AAC_MAX_CHANNELS][AAC_MAX_CHANNELS] = { + { 0 }, + { 0, 1 }, + { 2, 0, 1 }, + { 2, 0, 1, 3 }, + { 2, 0, 1, 3, 4 }, + { 2, 0, 1, 4, 5, 3 }, +}; + /** * Make AAC audio config object. * @see 1.6.2.1 "Syntax - AudioSpecificConfig" @@ -172,34 +184,29 @@ static void apply_window_and_mdct(AACEncContext *s, SingleChannelElement *sce, float *audio) { int i, k; - const int chans = s->channels; const float * lwindow = sce->ics.use_kb_window[0] ? ff_aac_kbd_long_1024 : ff_sine_1024; const float * swindow = sce->ics.use_kb_window[0] ? ff_aac_kbd_short_128 : ff_sine_128; const float * pwindow = sce->ics.use_kb_window[1] ? ff_aac_kbd_short_128 : ff_sine_128; float *output = sce->ret; if (sce->ics.window_sequence[0] != EIGHT_SHORT_SEQUENCE) { - memcpy(output, sce->saved, sizeof(float)*1024); + memcpy(output, sce->saved, sizeof(output[0])*1024); if (sce->ics.window_sequence[0] == LONG_STOP_SEQUENCE) { memset(output, 0, sizeof(output[0]) * 448); for (i = 448; i < 576; i++) output[i] = sce->saved[i] * pwindow[i - 448]; - for (i = 576; i < 704; i++) - output[i] = sce->saved[i]; } if (sce->ics.window_sequence[0] != LONG_START_SEQUENCE) { for (i = 0; i < 1024; i++) { - output[i+1024] = audio[i * chans] * lwindow[1024 - i - 1]; - sce->saved[i] = audio[i * chans] * lwindow[i]; + output[i+1024] = audio[i] * lwindow[1024 - i - 1]; + sce->saved[i] = audio[i] * lwindow[i]; } } else { - for (i = 0; i < 448; i++) - output[i+1024] = audio[i * chans]; + memcpy(output + 1024, audio, sizeof(output[0]) * 448); for (; i < 576; i++) - output[i+1024] = audio[i * chans] * swindow[576 - i - 1]; + output[i+1024] = audio[i] * swindow[576 - i - 1]; memset(output+1024+576, 0, sizeof(output[0]) * 448); - for (i = 0; i < 1024; i++) - sce->saved[i] = audio[i * chans]; + memcpy(sce->saved, audio, sizeof(sce->saved[0]) * 1024); } s->mdct1024.mdct_calc(&s->mdct1024, sce->coeffs, output); } else { @@ -207,13 +214,12 @@ static void apply_window_and_mdct(AACEncContext *s, SingleChannelElement *sce, for (i = 448 + k; i < 448 + k + 256; i++) output[i - 448 - k] = (i < 1024) ? sce->saved[i] - : audio[(i-1024)*chans]; + : audio[i-1024]; s->dsp.vector_fmul (output, output, k ? swindow : pwindow, 128); s->dsp.vector_fmul_reverse(output+128, output+128, swindow, 128); s->mdct128.mdct_calc(&s->mdct128, sce->coeffs + k, output); } - for (i = 0; i < 1024; i++) - sce->saved[i] = audio[i * chans]; + memcpy(sce->saved, audio, sizeof(sce->saved[0]) * 1024); } } @@ -432,11 +438,37 @@ static void put_bitstream_info(AVCodecContext *avctx, AACEncContext *s, put_bits(&s->pb, 12 - padbits, 0); } +/* + * Deinterleave input samples. + * Channels are reordered from Libav's default order to AAC order. + */ +static void deinterleave_input_samples(AACEncContext *s, + const float *samples) +{ + int ch, i; + const int sinc = s->channels; + const uint8_t *channel_map = aac_chan_maps[sinc - 1]; + + /* deinterleave and remap input samples */ + for (ch = 0; ch < sinc; ch++) { + const float *sptr = samples + channel_map[ch]; + + /* copy last 1024 samples of previous frame to the start of the current frame */ + memcpy(&s->planar_samples[ch][0], &s->planar_samples[ch][1024], 1024 * sizeof(s->planar_samples[0][0])); + + /* deinterleave */ + for (i = 1024; i < 1024 * 2; i++) { + s->planar_samples[ch][i] = *sptr; + sptr += sinc; + } + } +} + static int aac_encode_frame(AVCodecContext *avctx, uint8_t *frame, int buf_size, void *data) { AACEncContext *s = avctx->priv_data; - float *samples = s->samples, *samples2, *la; + float **samples = s->planar_samples, *samples2, *la; ChannelElement *cpe; int i, ch, w, g, chans, tag, start_ch; int chan_el_counter[4]; @@ -444,27 +476,15 @@ static int aac_encode_frame(AVCodecContext *avctx, if (s->last_frame) return 0; + if (data) { - if (!s->psypp) { - memcpy(s->samples + 1024 * s->channels, data, - 1024 * s->channels * sizeof(s->samples[0])); - } else { - start_ch = 0; - samples2 = s->samples + 1024 * s->channels; - for (i = 0; i < s->chan_map[0]; i++) { - tag = s->chan_map[i+1]; - chans = tag == TYPE_CPE ? 2 : 1; - ff_psy_preprocess(s->psypp, (float*)data + start_ch, - samples2 + start_ch, start_ch, chans); - start_ch += chans; - } - } + deinterleave_input_samples(s, data); + if (s->psypp) + ff_psy_preprocess(s->psypp, s->planar_samples, s->channels); } - if (!avctx->frame_number) { - memcpy(s->samples, s->samples + 1024 * s->channels, - 1024 * s->channels * sizeof(s->samples[0])); + + if (!avctx->frame_number) return 0; - } start_ch = 0; for (i = 0; i < s->chan_map[0]; i++) { @@ -475,8 +495,8 @@ static int aac_encode_frame(AVCodecContext *avctx, for (ch = 0; ch < chans; ch++) { IndividualChannelStream *ics = &cpe->ch[ch].ics; int cur_channel = start_ch + ch; - samples2 = samples + cur_channel; - la = samples2 + (448+64) * s->channels; + samples2 = &samples[cur_channel][0]; + la = samples2 + (448+64); if (!data) la = NULL; if (tag == TYPE_LFE) { @@ -592,8 +612,7 @@ static int aac_encode_frame(AVCodecContext *avctx, if (!data) s->last_frame = 1; - memcpy(s->samples, s->samples + 1024 * s->channels, - 1024 * s->channels * sizeof(s->samples[0])); + return put_bits_count(&s->pb)>>3; } @@ -606,7 +625,7 @@ static av_cold int aac_encode_end(AVCodecContext *avctx) ff_psy_end(&s->psy); if (s->psypp) ff_psy_preprocess_end(s->psypp); - av_freep(&s->samples); + av_freep(&s->buffer.samples); av_freep(&s->cpe); return 0; } @@ -633,10 +652,13 @@ static av_cold int dsp_init(AVCodecContext *avctx, AACEncContext *s) static av_cold int alloc_buffers(AVCodecContext *avctx, AACEncContext *s) { - FF_ALLOC_OR_GOTO (avctx, s->samples, 2 * 1024 * s->channels * sizeof(s->samples[0]), alloc_fail); + FF_ALLOCZ_OR_GOTO(avctx, s->buffer.samples, 2 * 1024 * s->channels * sizeof(s->buffer.samples[0]), alloc_fail); FF_ALLOCZ_OR_GOTO(avctx, s->cpe, sizeof(ChannelElement) * s->chan_map[0], alloc_fail); FF_ALLOCZ_OR_GOTO(avctx, avctx->extradata, 5 + FF_INPUT_BUFFER_PADDING_SIZE, alloc_fail); + for(int ch = 0; ch < s->channels; ch++) + s->planar_samples[ch] = s->buffer.samples + 2 * 1024 * ch; + return 0; alloc_fail: return AVERROR(ENOMEM); diff --git a/libavcodec/aacenc.h b/libavcodec/aacenc.h index 211c70a805..44ab13bf47 100644 --- a/libavcodec/aacenc.h +++ b/libavcodec/aacenc.h @@ -58,7 +58,7 @@ typedef struct AACEncContext { FFTContext mdct1024; ///< long (1024 samples) frame transform context FFTContext mdct128; ///< short (128 samples) frame transform context DSPContext dsp; - float *samples; ///< saved preprocessed input + float *planar_samples[6]; ///< saved preprocessed input int samplerate_index; ///< MPEG-4 samplerate index int channels; ///< channel count @@ -73,6 +73,10 @@ typedef struct AACEncContext { float lambda; DECLARE_ALIGNED(16, int, qcoefs)[96]; ///< quantized coefficients DECLARE_ALIGNED(32, float, scoefs)[1024]; ///< scaled coefficients + + struct { + float *samples; + } buffer; } AACEncContext; extern float ff_aac_pow34sf_tab[428]; diff --git a/libavcodec/aacpsy.c b/libavcodec/aacpsy.c index 5e9e3913e8..8ee393ad1d 100644 --- a/libavcodec/aacpsy.c +++ b/libavcodec/aacpsy.c @@ -400,7 +400,7 @@ static av_unused FFPsyWindowInfo psy_3gpp_window(FFPsyContext *ctx, int stay_short = 0; for (i = 0; i < 8; i++) { for (j = 0; j < 128; j++) { - v = iir_filter(la[(i*128+j)*ctx->avctx->channels], pch->iir_state); + v = iir_filter(la[i*128+j], pch->iir_state); sum += v*v; } s[i] = sum; @@ -794,18 +794,17 @@ static FFPsyWindowInfo psy_lame_window(FFPsyContext *ctx, const float *audio, float attack_intensity[(AAC_NUM_BLOCKS_SHORT + 1) * PSY_LAME_NUM_SUBBLOCKS]; float energy_subshort[(AAC_NUM_BLOCKS_SHORT + 1) * PSY_LAME_NUM_SUBBLOCKS]; float energy_short[AAC_NUM_BLOCKS_SHORT + 1] = { 0 }; - int chans = ctx->avctx->channels; - const float *firbuf = la + (AAC_BLOCK_SIZE_SHORT/4 - PSY_LAME_FIR_LEN) * chans; + const float *firbuf = la + (AAC_BLOCK_SIZE_SHORT/4 - PSY_LAME_FIR_LEN); int j, att_sum = 0; /* LAME comment: apply high pass filter of fs/4 */ for (i = 0; i < AAC_BLOCK_SIZE_LONG; i++) { float sum1, sum2; - sum1 = firbuf[(i + ((PSY_LAME_FIR_LEN - 1) / 2)) * chans]; + sum1 = firbuf[i + (PSY_LAME_FIR_LEN - 1) / 2]; sum2 = 0.0; for (j = 0; j < ((PSY_LAME_FIR_LEN - 1) / 2) - 1; j += 2) { - sum1 += psy_fir_coeffs[j] * (firbuf[(i + j) * chans] + firbuf[(i + PSY_LAME_FIR_LEN - j) * chans]); - sum2 += psy_fir_coeffs[j + 1] * (firbuf[(i + j + 1) * chans] + firbuf[(i + PSY_LAME_FIR_LEN - j - 1) * chans]); + sum1 += psy_fir_coeffs[j] * (firbuf[i + j] + firbuf[i + PSY_LAME_FIR_LEN - j]); + sum2 += psy_fir_coeffs[j + 1] * (firbuf[i + j + 1] + firbuf[i + PSY_LAME_FIR_LEN - j - 1]); } /* NOTE: The LAME psymodel expects it's input in the range -32768 to 32768. Tuning this for normalized floats would be difficult. */ hpfsmpl[i] = (sum1 + sum2) * 32768.0f; diff --git a/libavcodec/psymodel.c b/libavcodec/psymodel.c index 49df1189e4..316076a904 100644 --- a/libavcodec/psymodel.c +++ b/libavcodec/psymodel.c @@ -112,19 +112,15 @@ av_cold struct FFPsyPreprocessContext* ff_psy_preprocess_init(AVCodecContext *av return ctx; } -void ff_psy_preprocess(struct FFPsyPreprocessContext *ctx, const float *audio, - float *dest, int tag, int channels) +void ff_psy_preprocess(struct FFPsyPreprocessContext *ctx, float **audio, int channels) { - int ch, i; + int ch; + int frame_size = ctx->avctx->frame_size; + if (ctx->fstate) { for (ch = 0; ch < channels; ch++) - ff_iir_filter_flt(ctx->fcoeffs, ctx->fstate[tag+ch], ctx->avctx->frame_size, - audio + ch, ctx->avctx->channels, - dest + ch, ctx->avctx->channels); - } else { - for (ch = 0; ch < channels; ch++) - for (i = 0; i < ctx->avctx->frame_size; i++) - dest[i*ctx->avctx->channels + ch] = audio[i*ctx->avctx->channels + ch]; + ff_iir_filter_flt(ctx->fcoeffs, ctx->fstate[ch], frame_size, + &audio[ch][frame_size], 1, &audio[ch][frame_size], 1); } } diff --git a/libavcodec/psymodel.h b/libavcodec/psymodel.h index 03d078ed58..34b20d7d04 100644 --- a/libavcodec/psymodel.h +++ b/libavcodec/psymodel.h @@ -174,13 +174,10 @@ av_cold struct FFPsyPreprocessContext* ff_psy_preprocess_init(AVCodecContext *av * Preprocess several channel in audio frame in order to compress it better. * * @param ctx preprocessing context - * @param audio samples to preprocess - * @param dest place to put filtered samples - * @param tag channel number - * @param channels number of channel to preprocess (some additional work may be done on stereo pair) + * @param audio samples to be filtered (in place) + * @param channels number of channel to preprocess */ -void ff_psy_preprocess(struct FFPsyPreprocessContext *ctx, const float *audio, - float *dest, int tag, int channels); +void ff_psy_preprocess(struct FFPsyPreprocessContext *ctx, float **audio, int channels); /** * Cleanup audio preprocessing module. From 7946a5acfbd7b43cbeed3048be5f9043b129abc4 Mon Sep 17 00:00:00 2001 From: Nathan Caldwell Date: Sat, 24 Dec 2011 15:24:16 -0700 Subject: [PATCH 14/16] aacenc: Move saved overlap samples to the beginning of the same buffer as incoming samples. Signed-off-by: Alex Converse --- libavcodec/aacenc.c | 31 +++++++++++++++---------------- 1 file changed, 15 insertions(+), 16 deletions(-) diff --git a/libavcodec/aacenc.c b/libavcodec/aacenc.c index 742fee9cd1..33e339b545 100644 --- a/libavcodec/aacenc.c +++ b/libavcodec/aacenc.c @@ -190,36 +190,34 @@ static void apply_window_and_mdct(AACEncContext *s, SingleChannelElement *sce, float *output = sce->ret; if (sce->ics.window_sequence[0] != EIGHT_SHORT_SEQUENCE) { - memcpy(output, sce->saved, sizeof(output[0])*1024); + memcpy(output, audio, sizeof(output[0])*1024); if (sce->ics.window_sequence[0] == LONG_STOP_SEQUENCE) { memset(output, 0, sizeof(output[0]) * 448); for (i = 448; i < 576; i++) - output[i] = sce->saved[i] * pwindow[i - 448]; + output[i] = audio[i] * pwindow[i - 448]; } if (sce->ics.window_sequence[0] != LONG_START_SEQUENCE) { for (i = 0; i < 1024; i++) { - output[i+1024] = audio[i] * lwindow[1024 - i - 1]; - sce->saved[i] = audio[i] * lwindow[i]; + output[i+1024] = audio[i + 1024] * lwindow[1024 - i - 1]; + audio[i] = audio[i + 1024] * lwindow[i]; } } else { - memcpy(output + 1024, audio, sizeof(output[0]) * 448); + memcpy(output + 1024, audio + 1024, sizeof(output[0]) * 448); for (; i < 576; i++) - output[i+1024] = audio[i] * swindow[576 - i - 1]; + output[i+1024] = audio[i+1024] * swindow[576 - i - 1]; memset(output+1024+576, 0, sizeof(output[0]) * 448); - memcpy(sce->saved, audio, sizeof(sce->saved[0]) * 1024); + memcpy(audio, audio + 1024, sizeof(audio[0]) * 1024); } s->mdct1024.mdct_calc(&s->mdct1024, sce->coeffs, output); } else { for (k = 0; k < 1024; k += 128) { for (i = 448 + k; i < 448 + k + 256; i++) - output[i - 448 - k] = (i < 1024) - ? sce->saved[i] - : audio[i-1024]; + output[i - 448 - k] = audio[i]; s->dsp.vector_fmul (output, output, k ? swindow : pwindow, 128); s->dsp.vector_fmul_reverse(output+128, output+128, swindow, 128); s->mdct128.mdct_calc(&s->mdct128, sce->coeffs + k, output); } - memcpy(sce->saved, audio, sizeof(sce->saved[0]) * 1024); + memcpy(audio, audio + 1024, sizeof(audio[0]) * 1024); } } @@ -468,7 +466,7 @@ static int aac_encode_frame(AVCodecContext *avctx, uint8_t *frame, int buf_size, void *data) { AACEncContext *s = avctx->priv_data; - float **samples = s->planar_samples, *samples2, *la; + float **samples = s->planar_samples, *samples2, *la, *overlap; ChannelElement *cpe; int i, ch, w, g, chans, tag, start_ch; int chan_el_counter[4]; @@ -495,7 +493,8 @@ static int aac_encode_frame(AVCodecContext *avctx, for (ch = 0; ch < chans; ch++) { IndividualChannelStream *ics = &cpe->ch[ch].ics; int cur_channel = start_ch + ch; - samples2 = &samples[cur_channel][0]; + overlap = &samples[cur_channel][0]; + samples2 = overlap + 1024; la = samples2 + (448+64); if (!data) la = NULL; @@ -524,7 +523,7 @@ static int aac_encode_frame(AVCodecContext *avctx, for (w = 0; w < ics->num_windows; w++) ics->group_len[w] = wi[ch].grouping[w]; - apply_window_and_mdct(s, &cpe->ch[ch], samples2); + apply_window_and_mdct(s, &cpe->ch[ch], overlap); } start_ch += chans; } @@ -652,12 +651,12 @@ static av_cold int dsp_init(AVCodecContext *avctx, AACEncContext *s) static av_cold int alloc_buffers(AVCodecContext *avctx, AACEncContext *s) { - FF_ALLOCZ_OR_GOTO(avctx, s->buffer.samples, 2 * 1024 * s->channels * sizeof(s->buffer.samples[0]), alloc_fail); + FF_ALLOCZ_OR_GOTO(avctx, s->buffer.samples, 3 * 1024 * s->channels * sizeof(s->buffer.samples[0]), alloc_fail); FF_ALLOCZ_OR_GOTO(avctx, s->cpe, sizeof(ChannelElement) * s->chan_map[0], alloc_fail); FF_ALLOCZ_OR_GOTO(avctx, avctx->extradata, 5 + FF_INPUT_BUFFER_PADDING_SIZE, alloc_fail); for(int ch = 0; ch < s->channels; ch++) - s->planar_samples[ch] = s->buffer.samples + 2 * 1024 * ch; + s->planar_samples[ch] = s->buffer.samples + 3 * 1024 * ch; return 0; alloc_fail: From 9292fe4a1db90c3705d7e6275f3ddb9728b2d363 Mon Sep 17 00:00:00 2001 From: Nathan Caldwell Date: Fri, 23 Dec 2011 17:36:15 -0700 Subject: [PATCH 15/16] aacenc: Simplify windowing Signed-off-by: Alex Converse --- libavcodec/aacenc.c | 101 +++++++++++++++++++++++++++++--------------- 1 file changed, 68 insertions(+), 33 deletions(-) diff --git a/libavcodec/aacenc.c b/libavcodec/aacenc.c index 33e339b545..7607362142 100644 --- a/libavcodec/aacenc.c +++ b/libavcodec/aacenc.c @@ -180,45 +180,80 @@ static void put_audio_specific_config(AVCodecContext *avctx) flush_put_bits(&pb); } +#define WINDOW_FUNC(type) \ +static void apply_ ##type ##_window(DSPContext *dsp, SingleChannelElement *sce, const float *audio) + +WINDOW_FUNC(only_long) +{ + const float *lwindow = sce->ics.use_kb_window[0] ? ff_aac_kbd_long_1024 : ff_sine_1024; + const float *pwindow = sce->ics.use_kb_window[1] ? ff_aac_kbd_long_1024 : ff_sine_1024; + float *out = sce->ret; + + dsp->vector_fmul (out, audio, lwindow, 1024); + dsp->vector_fmul_reverse(out + 1024, audio + 1024, pwindow, 1024); +} + +WINDOW_FUNC(long_start) +{ + const float *lwindow = sce->ics.use_kb_window[1] ? ff_aac_kbd_long_1024 : ff_sine_1024; + const float *swindow = sce->ics.use_kb_window[0] ? ff_aac_kbd_short_128 : ff_sine_128; + float *out = sce->ret; + + dsp->vector_fmul(out, audio, lwindow, 1024); + memcpy(out + 1024, audio, sizeof(out[0]) * 448); + dsp->vector_fmul_reverse(out + 1024 + 448, audio, swindow, 128); + memset(out + 1024 + 576, 0, sizeof(out[0]) * 448); +} + +WINDOW_FUNC(long_stop) +{ + const float *lwindow = sce->ics.use_kb_window[0] ? ff_aac_kbd_long_1024 : ff_sine_1024; + const float *swindow = sce->ics.use_kb_window[1] ? ff_aac_kbd_short_128 : ff_sine_128; + float *out = sce->ret; + + memset(out, 0, sizeof(out[0]) * 448); + dsp->vector_fmul(out + 448, audio + 448, swindow, 128); + memcpy(out + 576, audio + 576, sizeof(out[0]) * 448); + dsp->vector_fmul_reverse(out + 1024, audio + 1024, lwindow, 1024); +} + +WINDOW_FUNC(eight_short) +{ + const float *swindow = sce->ics.use_kb_window[0] ? ff_aac_kbd_short_128 : ff_sine_128; + const float *pwindow = sce->ics.use_kb_window[1] ? ff_aac_kbd_short_128 : ff_sine_128; + const float *in = audio + 448; + float *out = sce->ret; + + for (int w = 0; w < 8; w++) { + dsp->vector_fmul (out, in, w ? pwindow : swindow, 128); + out += 128; + in += 128; + dsp->vector_fmul_reverse(out, in, swindow, 128); + out += 128; + } +} + +static void (*const apply_window[4])(DSPContext *dsp, SingleChannelElement *sce, const float *audio) = { + [ONLY_LONG_SEQUENCE] = apply_only_long_window, + [LONG_START_SEQUENCE] = apply_long_start_window, + [EIGHT_SHORT_SEQUENCE] = apply_eight_short_window, + [LONG_STOP_SEQUENCE] = apply_long_stop_window +}; + static void apply_window_and_mdct(AACEncContext *s, SingleChannelElement *sce, float *audio) { - int i, k; - const float * lwindow = sce->ics.use_kb_window[0] ? ff_aac_kbd_long_1024 : ff_sine_1024; - const float * swindow = sce->ics.use_kb_window[0] ? ff_aac_kbd_short_128 : ff_sine_128; - const float * pwindow = sce->ics.use_kb_window[1] ? ff_aac_kbd_short_128 : ff_sine_128; + int i; float *output = sce->ret; - if (sce->ics.window_sequence[0] != EIGHT_SHORT_SEQUENCE) { - memcpy(output, audio, sizeof(output[0])*1024); - if (sce->ics.window_sequence[0] == LONG_STOP_SEQUENCE) { - memset(output, 0, sizeof(output[0]) * 448); - for (i = 448; i < 576; i++) - output[i] = audio[i] * pwindow[i - 448]; - } - if (sce->ics.window_sequence[0] != LONG_START_SEQUENCE) { - for (i = 0; i < 1024; i++) { - output[i+1024] = audio[i + 1024] * lwindow[1024 - i - 1]; - audio[i] = audio[i + 1024] * lwindow[i]; - } - } else { - memcpy(output + 1024, audio + 1024, sizeof(output[0]) * 448); - for (; i < 576; i++) - output[i+1024] = audio[i+1024] * swindow[576 - i - 1]; - memset(output+1024+576, 0, sizeof(output[0]) * 448); - memcpy(audio, audio + 1024, sizeof(audio[0]) * 1024); - } + apply_window[sce->ics.window_sequence[0]](&s->dsp, sce, audio); + + if (sce->ics.window_sequence[0] != EIGHT_SHORT_SEQUENCE) s->mdct1024.mdct_calc(&s->mdct1024, sce->coeffs, output); - } else { - for (k = 0; k < 1024; k += 128) { - for (i = 448 + k; i < 448 + k + 256; i++) - output[i - 448 - k] = audio[i]; - s->dsp.vector_fmul (output, output, k ? swindow : pwindow, 128); - s->dsp.vector_fmul_reverse(output+128, output+128, swindow, 128); - s->mdct128.mdct_calc(&s->mdct128, sce->coeffs + k, output); - } - memcpy(audio, audio + 1024, sizeof(audio[0]) * 1024); - } + else + for (i = 0; i < 1024; i += 128) + s->mdct128.mdct_calc(&s->mdct128, sce->coeffs + i, output + i*2); + memcpy(audio, audio + 1024, sizeof(audio[0]) * 1024); } /** From 0fec2cb15cc6ff1fcc724c774ec36abadcb7b6ad Mon Sep 17 00:00:00 2001 From: Anton Khirnov Date: Thu, 12 Jan 2012 11:12:15 +0100 Subject: [PATCH 16/16] Remove ffmpeg. --- .gitignore | 1 - Makefile | 3 +- configure | 3 - doc/ffmpeg.texi | 1091 ------------ ffmpeg.c | 4415 ----------------------------------------------- 5 files changed, 1 insertion(+), 5512 deletions(-) delete mode 100644 doc/ffmpeg.texi delete mode 100644 ffmpeg.c diff --git a/.gitignore b/.gitignore index 2118a5115e..3508635b05 100644 --- a/.gitignore +++ b/.gitignore @@ -11,7 +11,6 @@ doc/*.1 doc/*.html doc/*.pod doxy -ffmpeg avconv avplay avprobe diff --git a/Makefile b/Makefile index 19b8df42d3..d1b55ba3d1 100644 --- a/Makefile +++ b/Makefile @@ -52,7 +52,6 @@ COMPILE_S = $(call COMPILE,AS) %.c %.h: TAG = GEN -PROGS-$(CONFIG_FFMPEG) += ffmpeg PROGS-$(CONFIG_AVCONV) += avconv PROGS-$(CONFIG_AVPLAY) += avplay PROGS-$(CONFIG_AVPROBE) += avprobe @@ -65,7 +64,7 @@ HOSTPROGS := $(TESTTOOLS:%=tests/%) TOOLS = qt-faststart trasher TOOLS-$(CONFIG_ZLIB) += cws2fws -BASENAMES = ffmpeg avconv avplay avprobe avserver +BASENAMES = avconv avplay avprobe avserver ALLPROGS = $(BASENAMES:%=%$(EXESUF)) ALLMANPAGES = $(BASENAMES:%=%.1) diff --git a/configure b/configure index ad7d9d4c5b..aff889457e 100755 --- a/configure +++ b/configure @@ -80,7 +80,6 @@ Configuration options: --enable-nonfree allow use of nonfree code, the resulting libs and binaries will be unredistributable [no] --disable-doc do not build documentation - --disable-ffmpeg disable ffmpeg build --disable-avconv disable avconv build --disable-avplay disable avplay build --disable-avprobe disable avprobe build @@ -911,7 +910,6 @@ PROGRAM_LIST=" avplay avprobe avserver - ffmpeg " CONFIG_LIST=" @@ -1536,7 +1534,6 @@ avplay_select="rdft" avprobe_deps="avcodec avformat" avserver_deps="avformat ffm_muxer fork rtp_protocol rtsp_demuxer !shared" avserver_extralibs='$ldl' -ffmpeg_deps="avcodec avformat swscale" doc_deps="texi2html" diff --git a/doc/ffmpeg.texi b/doc/ffmpeg.texi deleted file mode 100644 index 968d4f68b7..0000000000 --- a/doc/ffmpeg.texi +++ /dev/null @@ -1,1091 +0,0 @@ -\input texinfo @c -*- texinfo -*- - -@settitle ffmpeg Documentation -@titlepage -@center @titlefont{ffmpeg Documentation} -@end titlepage - -@top - -@contents - -@chapter Synopsis - -The generic syntax is: - -@example -@c man begin SYNOPSIS -ffmpeg [[infile options][@option{-i} @var{infile}]]... @{[outfile options] @var{outfile}@}... -@c man end -@end example - -@chapter Description -@c man begin DESCRIPTION - -ffmpeg is a very fast video and audio converter that can also grab from -a live audio/video source. It can also convert between arbitrary sample -rates and resize video on the fly with a high quality polyphase filter. - -The command line interface is designed to be intuitive, in the sense -that ffmpeg tries to figure out all parameters that can possibly be -derived automatically. You usually only have to specify the target -bitrate you want. - -As a general rule, options are applied to the next specified -file. Therefore, order is important, and you can have the same -option on the command line multiple times. Each occurrence is -then applied to the next input or output file. - -@itemize -@item -To set the video bitrate of the output file to 64kbit/s: -@example -ffmpeg -i input.avi -b 64k output.avi -@end example - -@item -To force the frame rate of the output file to 24 fps: -@example -ffmpeg -i input.avi -r 24 output.avi -@end example - -@item -To force the frame rate of the input file (valid for raw formats only) -to 1 fps and the frame rate of the output file to 24 fps: -@example -ffmpeg -r 1 -i input.m2v -r 24 output.avi -@end example -@end itemize - -The format option may be needed for raw input files. - -By default ffmpeg tries to convert as losslessly as possible: It -uses the same audio and video parameters for the outputs as the one -specified for the inputs. - -@c man end DESCRIPTION - -@chapter Options -@c man begin OPTIONS - -@include avtools-common-opts.texi - -@section Main options - -@table @option - -@item -f @var{fmt} -Force format. - -@item -i @var{filename} -input file name - -@item -y -Overwrite output files. - -@item -t @var{duration} -Restrict the transcoded/captured video sequence -to the duration specified in seconds. -@code{hh:mm:ss[.xxx]} syntax is also supported. - -@item -fs @var{limit_size} -Set the file size limit. - -@item -ss @var{position} -Seek to given time position in seconds. -@code{hh:mm:ss[.xxx]} syntax is also supported. - -@item -itsoffset @var{offset} -Set the input time offset in seconds. -@code{[-]hh:mm:ss[.xxx]} syntax is also supported. -This option affects all the input files that follow it. -The offset is added to the timestamps of the input files. -Specifying a positive offset means that the corresponding -streams are delayed by 'offset' seconds. - -@item -timestamp @var{time} -Set the recording timestamp in the container. -The syntax for @var{time} is: -@example -now|([(YYYY-MM-DD|YYYYMMDD)[T|t| ]]((HH[:MM[:SS[.m...]]])|(HH[MM[SS[.m...]]]))[Z|z]) -@end example -If the value is "now" it takes the current time. -Time is local time unless 'Z' or 'z' is appended, in which case it is -interpreted as UTC. -If the year-month-day part is not specified it takes the current -year-month-day. - -@item -metadata @var{key}=@var{value} -Set a metadata key/value pair. - -For example, for setting the title in the output file: -@example -ffmpeg -i in.avi -metadata title="my title" out.flv -@end example - -@item -v @var{number} -Set the logging verbosity level. - -@item -target @var{type} -Specify target file type ("vcd", "svcd", "dvd", "dv", "dv50", "pal-vcd", -"ntsc-svcd", ... ). All the format options (bitrate, codecs, -buffer sizes) are then set automatically. You can just type: - -@example -ffmpeg -i myfile.avi -target vcd /tmp/vcd.mpg -@end example - -Nevertheless you can specify additional options as long as you know -they do not conflict with the standard, as in: - -@example -ffmpeg -i myfile.avi -target vcd -bf 2 /tmp/vcd.mpg -@end example - -@item -dframes @var{number} -Set the number of data frames to record. - -@item -scodec @var{codec} -Force subtitle codec ('copy' to copy stream). - -@item -newsubtitle -Add a new subtitle stream to the current output stream. - -@item -slang @var{code} -Set the ISO 639 language code (3 letters) of the current subtitle stream. - -@end table - -@section Video Options - -@table @option -@item -vframes @var{number} -Set the number of video frames to record. -@item -r @var{fps} -Set frame rate (Hz value, fraction or abbreviation), (default = 25). -@item -s @var{size} -Set frame size. The format is @samp{wxh} (avserver default = 160x128, ffmpeg default = same as source). -The following abbreviations are recognized: -@table @samp -@item sqcif -128x96 -@item qcif -176x144 -@item cif -352x288 -@item 4cif -704x576 -@item 16cif -1408x1152 -@item qqvga -160x120 -@item qvga -320x240 -@item vga -640x480 -@item svga -800x600 -@item xga -1024x768 -@item uxga -1600x1200 -@item qxga -2048x1536 -@item sxga -1280x1024 -@item qsxga -2560x2048 -@item hsxga -5120x4096 -@item wvga -852x480 -@item wxga -1366x768 -@item wsxga -1600x1024 -@item wuxga -1920x1200 -@item woxga -2560x1600 -@item wqsxga -3200x2048 -@item wquxga -3840x2400 -@item whsxga -6400x4096 -@item whuxga -7680x4800 -@item cga -320x200 -@item ega -640x350 -@item hd480 -852x480 -@item hd720 -1280x720 -@item hd1080 -1920x1080 -@end table - -@item -aspect @var{aspect} -Set the video display aspect ratio specified by @var{aspect}. - -@var{aspect} can be a floating point number string, or a string of the -form @var{num}:@var{den}, where @var{num} and @var{den} are the -numerator and denominator of the aspect ratio. For example "4:3", -"16:9", "1.3333", and "1.7777" are valid argument values. - -@item -croptop @var{size} -@item -cropbottom @var{size} -@item -cropleft @var{size} -@item -cropright @var{size} -All the crop options have been removed. Use -vf -crop=width:height:x:y instead. - -@item -padtop @var{size} -@item -padbottom @var{size} -@item -padleft @var{size} -@item -padright @var{size} -@item -padcolor @var{hex_color} -All the pad options have been removed. Use -vf -pad=width:height:x:y:color instead. -@item -vn -Disable video recording. -@item -bt @var{tolerance} -Set video bitrate tolerance (in bits, default 4000k). -Has a minimum value of: (target_bitrate/target_framerate). -In 1-pass mode, bitrate tolerance specifies how far ratecontrol is -willing to deviate from the target average bitrate value. This is -not related to min/max bitrate. Lowering tolerance too much has -an adverse effect on quality. -@item -maxrate @var{bitrate} -Set max video bitrate (in bit/s). -Requires -bufsize to be set. -@item -minrate @var{bitrate} -Set min video bitrate (in bit/s). -Most useful in setting up a CBR encode: -@example -ffmpeg -i myfile.avi -b 4000k -minrate 4000k -maxrate 4000k -bufsize 1835k out.m2v -@end example -It is of little use elsewise. -@item -bufsize @var{size} -Set video buffer verifier buffer size (in bits). -@item -vcodec @var{codec} -Force video codec to @var{codec}. Use the @code{copy} special value to -tell that the raw codec data must be copied as is. -@item -sameq -Use same quantizer as source (implies VBR). - -@item -pass @var{n} -Select the pass number (1 or 2). It is used to do two-pass -video encoding. The statistics of the video are recorded in the first -pass into a log file (see also the option -passlogfile), -and in the second pass that log file is used to generate the video -at the exact requested bitrate. -On pass 1, you may just deactivate audio and set output to null, -examples for Windows and Unix: -@example -ffmpeg -i foo.mov -vcodec libxvid -pass 1 -an -f rawvideo -y NUL -ffmpeg -i foo.mov -vcodec libxvid -pass 1 -an -f rawvideo -y /dev/null -@end example - -@item -passlogfile @var{prefix} -Set two-pass log file name prefix to @var{prefix}, the default file name -prefix is ``ffmpeg2pass''. The complete file name will be -@file{PREFIX-N.log}, where N is a number specific to the output -stream. - -@item -newvideo -Add a new video stream to the current output stream. - -@item -vlang @var{code} -Set the ISO 639 language code (3 letters) of the current video stream. - -@item -vf @var{filter_graph} -@var{filter_graph} is a description of the filter graph to apply to -the input video. -Use the option "-filters" to show all the available filters (including -also sources and sinks). - -@end table - -@section Advanced Video Options - -@table @option -@item -pix_fmt @var{format} -Set pixel format. Use 'list' as parameter to show all the supported -pixel formats. -@item -sws_flags @var{flags} -Set SwScaler flags. -@item -g @var{gop_size} -Set the group of pictures size. -@item -intra -Use only intra frames. -@item -vdt @var{n} -Discard threshold. -@item -qscale @var{q} -Use fixed video quantizer scale (VBR). -@item -qmin @var{q} -minimum video quantizer scale (VBR) -@item -qmax @var{q} -maximum video quantizer scale (VBR) -@item -qdiff @var{q} -maximum difference between the quantizer scales (VBR) -@item -qblur @var{blur} -video quantizer scale blur (VBR) (range 0.0 - 1.0) -@item -qcomp @var{compression} -video quantizer scale compression (VBR) (default 0.5). -Constant of ratecontrol equation. Recommended range for default rc_eq: 0.0-1.0 - -@item -lmin @var{lambda} -minimum video lagrange factor (VBR) -@item -lmax @var{lambda} -max video lagrange factor (VBR) -@item -mblmin @var{lambda} -minimum macroblock quantizer scale (VBR) -@item -mblmax @var{lambda} -maximum macroblock quantizer scale (VBR) - -These four options (lmin, lmax, mblmin, mblmax) use 'lambda' units, -but you may use the QP2LAMBDA constant to easily convert from 'q' units: -@example -ffmpeg -i src.ext -lmax 21*QP2LAMBDA dst.ext -@end example - -@item -rc_init_cplx @var{complexity} -initial complexity for single pass encoding -@item -b_qfactor @var{factor} -qp factor between P- and B-frames -@item -i_qfactor @var{factor} -qp factor between P- and I-frames -@item -b_qoffset @var{offset} -qp offset between P- and B-frames -@item -i_qoffset @var{offset} -qp offset between P- and I-frames -@item -rc_eq @var{equation} -Set rate control equation (see section "Expression Evaluation") -(default = @code{tex^qComp}). - -When computing the rate control equation expression, besides the -standard functions defined in the section "Expression Evaluation", the -following functions are available: -@table @var -@item bits2qp(bits) -@item qp2bits(qp) -@end table - -and the following constants are available: -@table @var -@item iTex -@item pTex -@item tex -@item mv -@item fCode -@item iCount -@item mcVar -@item var -@item isI -@item isP -@item isB -@item avgQP -@item qComp -@item avgIITex -@item avgPITex -@item avgPPTex -@item avgBPTex -@item avgTex -@end table - -@item -rc_override @var{override} -rate control override for specific intervals -@item -me_method @var{method} -Set motion estimation method to @var{method}. -Available methods are (from lowest to best quality): -@table @samp -@item zero -Try just the (0, 0) vector. -@item phods -@item log -@item x1 -@item hex -@item umh -@item epzs -(default method) -@item full -exhaustive search (slow and marginally better than epzs) -@end table - -@item -dct_algo @var{algo} -Set DCT algorithm to @var{algo}. Available values are: -@table @samp -@item 0 -FF_DCT_AUTO (default) -@item 1 -FF_DCT_FASTINT -@item 2 -FF_DCT_INT -@item 3 -FF_DCT_MMX -@item 4 -FF_DCT_MLIB -@item 5 -FF_DCT_ALTIVEC -@end table - -@item -idct_algo @var{algo} -Set IDCT algorithm to @var{algo}. Available values are: -@table @samp -@item 0 -FF_IDCT_AUTO (default) -@item 1 -FF_IDCT_INT -@item 2 -FF_IDCT_SIMPLE -@item 3 -FF_IDCT_SIMPLEMMX -@item 4 -FF_IDCT_LIBMPEG2MMX -@item 5 -FF_IDCT_PS2 -@item 6 -FF_IDCT_MLIB -@item 7 -FF_IDCT_ARM -@item 8 -FF_IDCT_ALTIVEC -@item 9 -FF_IDCT_SH4 -@item 10 -FF_IDCT_SIMPLEARM -@end table - -@item -er @var{n} -Set error resilience to @var{n}. -@table @samp -@item 1 -FF_ER_CAREFUL (default) -@item 2 -FF_ER_COMPLIANT -@item 3 -FF_ER_AGGRESSIVE -@item 4 -FF_ER_EXPLODE -@end table - -@item -ec @var{bit_mask} -Set error concealment to @var{bit_mask}. @var{bit_mask} is a bit mask of -the following values: -@table @samp -@item 1 -FF_EC_GUESS_MVS (default = enabled) -@item 2 -FF_EC_DEBLOCK (default = enabled) -@end table - -@item -bf @var{frames} -Use 'frames' B-frames (supported for MPEG-1, MPEG-2 and MPEG-4). -@item -mbd @var{mode} -macroblock decision -@table @samp -@item 0 -FF_MB_DECISION_SIMPLE: Use mb_cmp (cannot change it yet in ffmpeg). -@item 1 -FF_MB_DECISION_BITS: Choose the one which needs the fewest bits. -@item 2 -FF_MB_DECISION_RD: rate distortion -@end table - -@item -4mv -Use four motion vector by macroblock (MPEG-4 only). -@item -part -Use data partitioning (MPEG-4 only). -@item -bug @var{param} -Work around encoder bugs that are not auto-detected. -@item -strict @var{strictness} -How strictly to follow the standards. -@item -aic -Enable Advanced intra coding (h263+). -@item -umv -Enable Unlimited Motion Vector (h263+) - -@item -deinterlace -Deinterlace pictures. -@item -ilme -Force interlacing support in encoder (MPEG-2 and MPEG-4 only). -Use this option if your input file is interlaced and you want -to keep the interlaced format for minimum losses. -The alternative is to deinterlace the input stream with -@option{-deinterlace}, but deinterlacing introduces losses. -@item -psnr -Calculate PSNR of compressed frames. -@item -vstats -Dump video coding statistics to @file{vstats_HHMMSS.log}. -@item -vstats_file @var{file} -Dump video coding statistics to @var{file}. -@item -top @var{n} -top=1/bottom=0/auto=-1 field first -@item -dc @var{precision} -Intra_dc_precision. -@item -vtag @var{fourcc/tag} -Force video tag/fourcc. -@item -qphist -Show QP histogram. -@item -vbsf @var{bitstream_filter} -Bitstream filters available are "dump_extra", "remove_extra", "noise", "h264_mp4toannexb", "imxdump", "mjpegadump", "mjpeg2jpeg". -@example -ffmpeg -i h264.mp4 -vcodec copy -vbsf h264_mp4toannexb -an out.h264 -@end example -@item -force_key_frames @var{time}[,@var{time}...] -Force key frames at the specified timestamps, more precisely at the first -frames after each specified time. -This option can be useful to ensure that a seek point is present at a -chapter mark or any other designated place in the output file. -The timestamps must be specified in ascending order. -@end table - -@section Audio Options - -@table @option -@item -aframes @var{number} -Set the number of audio frames to record. -@item -ar @var{freq} -Set the audio sampling frequency. For output streams it is set by -default to the frequency of the corresponding input stream. For input -streams this option only makes sense for audio grabbing devices and raw -demuxers and is mapped to the corresponding demuxer options. -@item -aq @var{q} -Set the audio quality (codec-specific, VBR). -@item -ac @var{channels} -Set the number of audio channels. For output streams it is set by -default to the number of input audio channels. For input streams -this option only makes sense for audio grabbing devices and raw demuxers -and is mapped to the corresponding demuxer options. -@item -an -Disable audio recording. -@item -acodec @var{codec} -Force audio codec to @var{codec}. Use the @code{copy} special value to -specify that the raw codec data must be copied as is. -@item -newaudio -Add a new audio track to the output file. If you want to specify parameters, -do so before @code{-newaudio} (@code{-acodec}, @code{-ab}, etc..). - -Mapping will be done automatically, if the number of output streams is equal to -the number of input streams, else it will pick the first one that matches. You -can override the mapping using @code{-map} as usual. - -Example: -@example -ffmpeg -i file.mpg -vcodec copy -acodec ac3 -ab 384k test.mpg -acodec mp2 -ab 192k -newaudio -@end example -@item -alang @var{code} -Set the ISO 639 language code (3 letters) of the current audio stream. -@end table - -@section Advanced Audio options: - -@table @option -@item -atag @var{fourcc/tag} -Force audio tag/fourcc. -@item -audio_service_type @var{type} -Set the type of service that the audio stream contains. -@table @option -@item ma -Main Audio Service (default) -@item ef -Effects -@item vi -Visually Impaired -@item hi -Hearing Impaired -@item di -Dialogue -@item co -Commentary -@item em -Emergency -@item vo -Voice Over -@item ka -Karaoke -@end table -@item -absf @var{bitstream_filter} -Bitstream filters available are "dump_extra", "remove_extra", "noise", "mp3comp", "mp3decomp". -@end table - -@section Subtitle options: - -@table @option -@item -scodec @var{codec} -Force subtitle codec ('copy' to copy stream). -@item -newsubtitle -Add a new subtitle stream to the current output stream. -@item -slang @var{code} -Set the ISO 639 language code (3 letters) of the current subtitle stream. -@item -sn -Disable subtitle recording. -@item -sbsf @var{bitstream_filter} -Bitstream filters available are "mov2textsub", "text2movsub". -@example -ffmpeg -i file.mov -an -vn -sbsf mov2textsub -scodec copy -f rawvideo sub.txt -@end example -@end table - -@section Audio/Video grab options - -@table @option -@item -vc @var{channel} -Set video grab channel (DV1394 only). -@item -tvstd @var{standard} -Set television standard (NTSC, PAL (SECAM)). -@item -isync -Synchronize read on input. -@end table - -@section Advanced options - -@table @option -@item -map @var{input_file_id}.@var{input_stream_id}[:@var{sync_file_id}.@var{sync_stream_id}] - -Designate an input stream as a source for the output file. Each input -stream is identified by the input file index @var{input_file_id} and -the input stream index @var{input_stream_id} within the input -file. Both indexes start at 0. If specified, -@var{sync_file_id}.@var{sync_stream_id} sets which input stream -is used as a presentation sync reference. - -The @code{-map} options must be specified just after the output file. -If any @code{-map} options are used, the number of @code{-map} options -on the command line must match the number of streams in the output -file. The first @code{-map} option on the command line specifies the -source for output stream 0, the second @code{-map} option specifies -the source for output stream 1, etc. - -For example, if you have two audio streams in the first input file, -these streams are identified by "0.0" and "0.1". You can use -@code{-map} to select which stream to place in an output file. For -example: -@example -ffmpeg -i INPUT out.wav -map 0.1 -@end example -will map the input stream in @file{INPUT} identified by "0.1" to -the (single) output stream in @file{out.wav}. - -For example, to select the stream with index 2 from input file -@file{a.mov} (specified by the identifier "0.2"), and stream with -index 6 from input @file{b.mov} (specified by the identifier "1.6"), -and copy them to the output file @file{out.mov}: -@example -ffmpeg -i a.mov -i b.mov -vcodec copy -acodec copy out.mov -map 0.2 -map 1.6 -@end example - -To add more streams to the output file, you can use the -@code{-newaudio}, @code{-newvideo}, @code{-newsubtitle} options. - -@item -map_meta_data @var{outfile}[,@var{metadata}]:@var{infile}[,@var{metadata}] -Deprecated, use @var{-map_metadata} instead. - -@item -map_metadata @var{outfile}[,@var{metadata}]:@var{infile}[,@var{metadata}] -Set metadata information of @var{outfile} from @var{infile}. Note that those -are file indices (zero-based), not filenames. -Optional @var{metadata} parameters specify, which metadata to copy - (g)lobal -(i.e. metadata that applies to the whole file), per-(s)tream, per-(c)hapter or -per-(p)rogram. All metadata specifiers other than global must be followed by the -stream/chapter/program number. If metadata specifier is omitted, it defaults to -global. - -By default, global metadata is copied from the first input file to all output files, -per-stream and per-chapter metadata is copied along with streams/chapters. These -default mappings are disabled by creating any mapping of the relevant type. A negative -file index can be used to create a dummy mapping that just disables automatic copying. - -For example to copy metadata from the first stream of the input file to global metadata -of the output file: -@example -ffmpeg -i in.ogg -map_metadata 0:0,s0 out.mp3 -@end example -@item -map_chapters @var{outfile}:@var{infile} -Copy chapters from @var{infile} to @var{outfile}. If no chapter mapping is specified, -then chapters are copied from the first input file with at least one chapter to all -output files. Use a negative file index to disable any chapter copying. -@item -debug -Print specific debug info. -@item -benchmark -Show benchmarking information at the end of an encode. -Shows CPU time used and maximum memory consumption. -Maximum memory consumption is not supported on all systems, -it will usually display as 0 if not supported. -@item -dump -Dump each input packet. -@item -hex -When dumping packets, also dump the payload. -@item -bitexact -Only use bit exact algorithms (for codec testing). -@item -ps @var{size} -Set RTP payload size in bytes. -@item -re -Read input at native frame rate. Mainly used to simulate a grab device. -@item -loop_input -Loop over the input stream. Currently it works only for image -streams. This option is used for automatic AVserver testing. -This option is deprecated, use -loop. -@item -loop_output @var{number_of_times} -Repeatedly loop output for formats that support looping such as animated GIF -(0 will loop the output infinitely). -This option is deprecated, use -loop. -@item -threads @var{count} -Thread count. -@item -vsync @var{parameter} -Video sync method. - -@table @option -@item 0 -Each frame is passed with its timestamp from the demuxer to the muxer. -@item 1 -Frames will be duplicated and dropped to achieve exactly the requested -constant framerate. -@item 2 -Frames are passed through with their timestamp or dropped so as to -prevent 2 frames from having the same timestamp. -@item -1 -Chooses between 1 and 2 depending on muxer capabilities. This is the -default method. -@end table - -With -map you can select from which stream the timestamps should be -taken. You can leave either video or audio unchanged and sync the -remaining stream(s) to the unchanged one. - -@item -async @var{samples_per_second} -Audio sync method. "Stretches/squeezes" the audio stream to match the timestamps, -the parameter is the maximum samples per second by which the audio is changed. --async 1 is a special case where only the start of the audio stream is corrected -without any later correction. -@item -copyts -Copy timestamps from input to output. -@item -copytb -Copy input stream time base from input to output when stream copying. -@item -shortest -Finish encoding when the shortest input stream ends. -@item -dts_delta_threshold -Timestamp discontinuity delta threshold. -@item -muxdelay @var{seconds} -Set the maximum demux-decode delay. -@item -muxpreload @var{seconds} -Set the initial demux-decode delay. -@item -streamid @var{output-stream-index}:@var{new-value} -Assign a new stream-id value to an output stream. This option should be -specified prior to the output filename to which it applies. -For the situation where multiple output files exist, a streamid -may be reassigned to a different value. - -For example, to set the stream 0 PID to 33 and the stream 1 PID to 36 for -an output mpegts file: -@example -ffmpeg -i infile -streamid 0:33 -streamid 1:36 out.ts -@end example -@end table - -@section Preset files - -A preset file contains a sequence of @var{option}=@var{value} pairs, -one for each line, specifying a sequence of options which would be -awkward to specify on the command line. Lines starting with the hash -('#') character are ignored and are used to provide comments. Check -the @file{presets} directory in the Libav source tree for examples. - -Preset files are specified with the @code{vpre}, @code{apre}, -@code{spre}, and @code{fpre} options. The @code{fpre} option takes the -filename of the preset instead of a preset name as input and can be -used for any kind of codec. For the @code{vpre}, @code{apre}, and -@code{spre} options, the options specified in a preset file are -applied to the currently selected codec of the same type as the preset -option. - -The argument passed to the @code{vpre}, @code{apre}, and @code{spre} -preset options identifies the preset file to use according to the -following rules: - -First ffmpeg searches for a file named @var{arg}.ffpreset in the -directories @file{$AVCONV_DATADIR} (if set), and @file{$HOME/.avconv}, and in -the datadir defined at configuration time (usually @file{PREFIX/share/avconv}) -in that order. For example, if the argument is @code{libx264-max}, it will -search for the file @file{libx264-max.ffpreset}. - -If no such file is found, then ffmpeg will search for a file named -@var{codec_name}-@var{arg}.ffpreset in the above-mentioned -directories, where @var{codec_name} is the name of the codec to which -the preset file options will be applied. For example, if you select -the video codec with @code{-vcodec libx264} and use @code{-vpre max}, -then it will search for the file @file{libx264-max.ffpreset}. -@c man end - -@chapter Tips -@c man begin TIPS - -@itemize -@item -For streaming at very low bitrate application, use a low frame rate -and a small GOP size. This is especially true for RealVideo where -the Linux player does not seem to be very fast, so it can miss -frames. An example is: - -@example -ffmpeg -g 3 -r 3 -t 10 -b 50k -s qcif -f rv10 /tmp/b.rm -@end example - -@item -The parameter 'q' which is displayed while encoding is the current -quantizer. The value 1 indicates that a very good quality could -be achieved. The value 31 indicates the worst quality. If q=31 appears -too often, it means that the encoder cannot compress enough to meet -your bitrate. You must either increase the bitrate, decrease the -frame rate or decrease the frame size. - -@item -If your computer is not fast enough, you can speed up the -compression at the expense of the compression ratio. You can use -'-me zero' to speed up motion estimation, and '-intra' to disable -motion estimation completely (you have only I-frames, which means it -is about as good as JPEG compression). - -@item -To have very low audio bitrates, reduce the sampling frequency -(down to 22050 Hz for MPEG audio, 22050 or 11025 for AC-3). - -@item -To have a constant quality (but a variable bitrate), use the option -'-qscale n' when 'n' is between 1 (excellent quality) and 31 (worst -quality). - -@item -When converting video files, you can use the '-sameq' option which -uses the same quality factor in the encoder as in the decoder. -It allows almost lossless encoding. - -@end itemize -@c man end TIPS - -@chapter Examples -@c man begin EXAMPLES - -@section Video and Audio grabbing - -If you specify the input format and device then ffmpeg can grab video -and audio directly. - -@example -ffmpeg -f oss -i /dev/dsp -f video4linux2 -i /dev/video0 /tmp/out.mpg -@end example - -Note that you must activate the right video source and channel before -launching ffmpeg with any TV viewer such as -@uref{http://linux.bytesex.org/xawtv/, xawtv} by Gerd Knorr. You also -have to set the audio recording levels correctly with a -standard mixer. - -@section X11 grabbing - -Grab the X11 display with ffmpeg via - -@example -ffmpeg -f x11grab -s cif -r 25 -i :0.0 /tmp/out.mpg -@end example - -0.0 is display.screen number of your X11 server, same as -the DISPLAY environment variable. - -@example -ffmpeg -f x11grab -s cif -r 25 -i :0.0+10,20 /tmp/out.mpg -@end example - -10 is the x-offset and 20 the y-offset for the grabbing. - -@example -ffmpeg -f x11grab -follow_mouse centered -s cif -r 25 -i :0.0 /tmp/out.mpg -@end example - -The grabbing region follows the mouse pointer, which stays at the center of -region. - -@example -ffmpeg -f x11grab -follow_mouse 100 -s cif -r 25 -i :0.0 /tmp/out.mpg -@end example - -Only follows when mouse pointer reaches within 100 pixels to the edge of -region. - -@example -ffmpeg -f x11grab -show_region 1 -s cif -r 25 -i :0.0+10,20 /tmp/out.mpg -@end example - -The grabbing region will be indicated on screen. - -@example -ffmpeg -f x11grab -follow_mouse centered -show_region 1 -s cif -r 25 -i :0.0 /tmp/out.mpg -@end example - -The grabbing region indication will follow the mouse pointer. - - -@section Video and Audio file format conversion - -Any supported file format and protocol can serve as input to ffmpeg: - -Examples: -@itemize -@item -You can use YUV files as input: - -@example -ffmpeg -i /tmp/test%d.Y /tmp/out.mpg -@end example - -It will use the files: -@example -/tmp/test0.Y, /tmp/test0.U, /tmp/test0.V, -/tmp/test1.Y, /tmp/test1.U, /tmp/test1.V, etc... -@end example - -The Y files use twice the resolution of the U and V files. They are -raw files, without header. They can be generated by all decent video -decoders. You must specify the size of the image with the @option{-s} option -if ffmpeg cannot guess it. - -@item -You can input from a raw YUV420P file: - -@example -ffmpeg -i /tmp/test.yuv /tmp/out.avi -@end example - -test.yuv is a file containing raw YUV planar data. Each frame is composed -of the Y plane followed by the U and V planes at half vertical and -horizontal resolution. - -@item -You can output to a raw YUV420P file: - -@example -ffmpeg -i mydivx.avi hugefile.yuv -@end example - -@item -You can set several input files and output files: - -@example -ffmpeg -i /tmp/a.wav -s 640x480 -i /tmp/a.yuv /tmp/a.mpg -@end example - -Converts the audio file a.wav and the raw YUV video file a.yuv -to MPEG file a.mpg. - -@item -You can also do audio and video conversions at the same time: - -@example -ffmpeg -i /tmp/a.wav -ar 22050 /tmp/a.mp2 -@end example - -Converts a.wav to MPEG audio at 22050 Hz sample rate. - -@item -You can encode to several formats at the same time and define a -mapping from input stream to output streams: - -@example -ffmpeg -i /tmp/a.wav -ab 64k /tmp/a.mp2 -ab 128k /tmp/b.mp2 -map 0:0 -map 0:0 -@end example - -Converts a.wav to a.mp2 at 64 kbits and to b.mp2 at 128 kbits. '-map -file:index' specifies which input stream is used for each output -stream, in the order of the definition of output streams. - -@item -You can transcode decrypted VOBs: - -@example -ffmpeg -i snatch_1.vob -f avi -vcodec mpeg4 -b 800k -g 300 -bf 2 -acodec libmp3lame -ab 128k snatch.avi -@end example - -This is a typical DVD ripping example; the input is a VOB file, the -output an AVI file with MPEG-4 video and MP3 audio. Note that in this -command we use B-frames so the MPEG-4 stream is DivX5 compatible, and -GOP size is 300 which means one intra frame every 10 seconds for 29.97fps -input video. Furthermore, the audio stream is MP3-encoded so you need -to enable LAME support by passing @code{--enable-libmp3lame} to configure. -The mapping is particularly useful for DVD transcoding -to get the desired audio language. - -NOTE: To see the supported input formats, use @code{ffmpeg -formats}. - -@item -You can extract images from a video, or create a video from many images: - -For extracting images from a video: -@example -ffmpeg -i foo.avi -r 1 -s WxH -f image2 foo-%03d.jpeg -@end example - -This will extract one video frame per second from the video and will -output them in files named @file{foo-001.jpeg}, @file{foo-002.jpeg}, -etc. Images will be rescaled to fit the new WxH values. - -If you want to extract just a limited number of frames, you can use the -above command in combination with the -vframes or -t option, or in -combination with -ss to start extracting from a certain point in time. - -For creating a video from many images: -@example -ffmpeg -f image2 -i foo-%03d.jpeg -r 12 -s WxH foo.avi -@end example - -The syntax @code{foo-%03d.jpeg} specifies to use a decimal number -composed of three digits padded with zeroes to express the sequence -number. It is the same syntax supported by the C printf function, but -only formats accepting a normal integer are suitable. - -@item -You can put many streams of the same type in the output: - -@example -ffmpeg -i test1.avi -i test2.avi -vcodec copy -acodec copy -vcodec copy -acodec copy test12.avi -newvideo -newaudio -@end example - -In addition to the first video and audio streams, the resulting -output file @file{test12.avi} will contain the second video -and the second audio stream found in the input streams list. - -The @code{-newvideo}, @code{-newaudio} and @code{-newsubtitle} -options have to be specified immediately after the name of the output -file to which you want to add them. - -@end itemize -@c man end EXAMPLES - -@include eval.texi -@include encoders.texi -@include demuxers.texi -@include muxers.texi -@include indevs.texi -@include outdevs.texi -@include protocols.texi -@include bitstream_filters.texi -@include filters.texi -@include metadata.texi - -@ignore - -@setfilename ffmpeg -@settitle ffmpeg video converter - -@c man begin SEEALSO -avplay(1), avprobe(1), avserver(1) and the Libav HTML documentation -@c man end - -@c man begin AUTHORS -The Libav developers -@c man end - -@end ignore - -@bye diff --git a/ffmpeg.c b/ffmpeg.c deleted file mode 100644 index f61de33a33..0000000000 --- a/ffmpeg.c +++ /dev/null @@ -1,4415 +0,0 @@ -/* - * ffmpeg main - * Copyright (c) 2000-2003 Fabrice Bellard - * - * This file is part of Libav. - * - * Libav 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, - * 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 - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA - */ - -#include "config.h" -#include -#include -#include -#include -#include -#include -#include -#include -#include "libavformat/avformat.h" -#include "libavdevice/avdevice.h" -#include "libswscale/swscale.h" -#include "libavutil/opt.h" -#include "libavcodec/audioconvert.h" -#include "libavutil/audioconvert.h" -#include "libavutil/parseutils.h" -#include "libavutil/samplefmt.h" -#include "libavutil/colorspace.h" -#include "libavutil/fifo.h" -#include "libavutil/intreadwrite.h" -#include "libavutil/dict.h" -#include "libavutil/mathematics.h" -#include "libavutil/pixdesc.h" -#include "libavutil/avstring.h" -#include "libavutil/libm.h" -#include "libavformat/os_support.h" - -#if CONFIG_AVFILTER -# include "libavfilter/avfilter.h" -# include "libavfilter/avfiltergraph.h" -# include "libavfilter/vsrc_buffer.h" -#endif - -#if HAVE_SYS_RESOURCE_H -#include -#include -#include -#elif HAVE_GETPROCESSTIMES -#include -#endif -#if HAVE_GETPROCESSMEMORYINFO -#include -#include -#endif - -#if HAVE_SYS_SELECT_H -#include -#endif - -#include - -#include "cmdutils.h" - -#include "libavutil/avassert.h" - -const char program_name[] = "ffmpeg"; -const int program_birth_year = 2000; - -/* select an input stream for an output stream */ -typedef struct StreamMap { - int file_index; - int stream_index; - int sync_file_index; - int sync_stream_index; -} StreamMap; - -/** - * select an input file for an output file - */ -typedef struct MetadataMap { - int file; ///< file index - char type; ///< type of metadata to copy -- (g)lobal, (s)tream, (c)hapter or (p)rogram - int index; ///< stream/chapter/program number -} MetadataMap; - -typedef struct ChapterMap { - int in_file; - int out_file; -} ChapterMap; - -static const OptionDef options[]; - -#define MAX_FILES 100 - -static const char *last_asked_format = NULL; -static double *ts_scale; -static int nb_ts_scale; - -static AVFormatContext *output_files[MAX_FILES]; -static AVDictionary *output_opts[MAX_FILES]; -static int nb_output_files = 0; - -static StreamMap *stream_maps = NULL; -static int nb_stream_maps; - -/* first item specifies output metadata, second is input */ -static MetadataMap (*meta_data_maps)[2] = NULL; -static int nb_meta_data_maps; -static int metadata_global_autocopy = 1; -static int metadata_streams_autocopy = 1; -static int metadata_chapters_autocopy = 1; - -static ChapterMap *chapter_maps = NULL; -static int nb_chapter_maps; - -/* indexed by output file stream index */ -static int *streamid_map = NULL; -static int nb_streamid_map = 0; - -static int frame_width = 0; -static int frame_height = 0; -static float frame_aspect_ratio = 0; -static enum PixelFormat frame_pix_fmt = PIX_FMT_NONE; -static enum AVSampleFormat audio_sample_fmt = AV_SAMPLE_FMT_NONE; -static int max_frames[4] = {INT_MAX, INT_MAX, INT_MAX, INT_MAX}; -static AVRational frame_rate; -static float video_qscale = 0; -static uint16_t *intra_matrix = NULL; -static uint16_t *inter_matrix = NULL; -static const char *video_rc_override_string=NULL; -static int video_disable = 0; -static int video_discard = 0; -static char *video_codec_name = NULL; -static unsigned int video_codec_tag = 0; -static char *video_language = NULL; -static int same_quality = 0; -static int do_deinterlace = 0; -static int top_field_first = -1; -static int me_threshold = 0; -static int intra_dc_precision = 8; -static int loop_input = 0; -static int loop_output = AVFMT_NOOUTPUTLOOP; -static int qp_hist = 0; -#if CONFIG_AVFILTER -static char *vfilters = NULL; -#endif - -static int intra_only = 0; -static int audio_sample_rate = 0; -#define QSCALE_NONE -99999 -static float audio_qscale = QSCALE_NONE; -static int audio_disable = 0; -static int audio_channels = 0; -static char *audio_codec_name = NULL; -static unsigned int audio_codec_tag = 0; -static char *audio_language = NULL; - -static int subtitle_disable = 0; -static char *subtitle_codec_name = NULL; -static char *subtitle_language = NULL; -static unsigned int subtitle_codec_tag = 0; - -static int data_disable = 0; -static char *data_codec_name = NULL; -static unsigned int data_codec_tag = 0; - -static float mux_preload= 0.5; -static float mux_max_delay= 0.7; - -static int64_t recording_time = INT64_MAX; -static int64_t start_time = 0; -static int64_t input_ts_offset = 0; -static int file_overwrite = 0; -static AVDictionary *metadata; -static int do_benchmark = 0; -static int do_hex_dump = 0; -static int do_pkt_dump = 0; -static int do_psnr = 0; -static int do_pass = 0; -static char *pass_logfilename_prefix = NULL; -static int audio_stream_copy = 0; -static int video_stream_copy = 0; -static int subtitle_stream_copy = 0; -static int data_stream_copy = 0; -static int video_sync_method= -1; -static int audio_sync_method= 0; -static float audio_drift_threshold= 0.1; -static int copy_ts= 0; -static int copy_tb; -static int opt_shortest = 0; -static char *vstats_filename; -static FILE *vstats_file; -static int opt_programid = 0; -static int copy_initial_nonkeyframes = 0; - -static int rate_emu = 0; - -static int audio_volume = 256; - -static int exit_on_error = 0; -static int using_stdin = 0; -static int verbose = 1; -static int thread_count= 1; -static int64_t video_size = 0; -static int64_t audio_size = 0; -static int64_t extra_size = 0; -static int nb_frames_dup = 0; -static int nb_frames_drop = 0; -static int input_sync; -static uint64_t limit_filesize = 0; -static int force_fps = 0; -static char *forced_key_frames = NULL; - -static float dts_delta_threshold = 10; - -static int64_t timer_start; - -static uint8_t *audio_buf; -static uint8_t *audio_out; -static unsigned int allocated_audio_out_size, allocated_audio_buf_size; - -static short *samples; - -static AVBitStreamFilterContext *video_bitstream_filters=NULL; -static AVBitStreamFilterContext *audio_bitstream_filters=NULL; -static AVBitStreamFilterContext *subtitle_bitstream_filters=NULL; - -#define DEFAULT_PASS_LOGFILENAME_PREFIX "ffmpeg2pass" - -struct InputStream; - -typedef struct OutputStream { - int file_index; /* file index */ - int index; /* stream index in the output file */ - int source_index; /* InputStream index */ - AVStream *st; /* stream in the output file */ - int encoding_needed; /* true if encoding needed for this stream */ - int frame_number; - /* input pts and corresponding output pts - for A/V sync */ - //double sync_ipts; /* dts from the AVPacket of the demuxer in second units */ - struct InputStream *sync_ist; /* input stream to sync against */ - int64_t sync_opts; /* output frame counter, could be changed to some true timestamp */ //FIXME look at frame_number - AVBitStreamFilterContext *bitstream_filters; - AVCodec *enc; - - /* video only */ - int video_resample; - AVFrame pict_tmp; /* temporary image for resampling */ - struct SwsContext *img_resample_ctx; /* for image resampling */ - int resample_height; - int resample_width; - int resample_pix_fmt; - AVRational frame_rate; - - float frame_aspect_ratio; - - /* forced key frames */ - int64_t *forced_kf_pts; - int forced_kf_count; - int forced_kf_index; - - /* audio only */ - int audio_resample; - ReSampleContext *resample; /* for audio resampling */ - int resample_sample_fmt; - int resample_channels; - int resample_sample_rate; - int reformat_pair; - AVAudioConvert *reformat_ctx; - AVFifoBuffer *fifo; /* for compression: one audio fifo per codec */ - FILE *logfile; - -#if CONFIG_AVFILTER - AVFilterContext *output_video_filter; - AVFilterContext *input_video_filter; - AVFilterBufferRef *picref; - char *avfilter; - AVFilterGraph *graph; -#endif - - int sws_flags; - AVDictionary *opts; -} OutputStream; - -static OutputStream **output_streams_for_file[MAX_FILES] = { NULL }; -static int nb_output_streams_for_file[MAX_FILES] = { 0 }; - -typedef struct InputStream { - int file_index; - AVStream *st; - int discard; /* true if stream data should be discarded */ - int decoding_needed; /* true if the packets must be decoded in 'raw_fifo' */ - AVCodec *dec; - - int64_t start; /* time when read started */ - int64_t next_pts; /* synthetic pts for cases where pkt.pts - is not defined */ - int64_t pts; /* current pts */ - PtsCorrectionContext pts_ctx; - double ts_scale; - int is_start; /* is 1 at the start and after a discontinuity */ - int showed_multi_packet_warning; - int is_past_recording_time; - AVDictionary *opts; -} InputStream; - -typedef struct InputFile { - AVFormatContext *ctx; - int eof_reached; /* true if eof reached */ - int ist_index; /* index of first stream in ist_table */ - int buffer_size; /* current total buffer size */ - int64_t ts_offset; - int nb_streams; /* nb streams we are aware of */ -} InputFile; - -static InputStream *input_streams = NULL; -static int nb_input_streams = 0; -static InputFile *input_files = NULL; -static int nb_input_files = 0; - -#if CONFIG_AVFILTER - -static int configure_video_filters(InputStream *ist, OutputStream *ost) -{ - AVFilterContext *last_filter, *filter; - /** filter graph containing all filters including input & output */ - AVCodecContext *codec = ost->st->codec; - AVCodecContext *icodec = ist->st->codec; - AVSinkContext avsink_ctx = { .pix_fmt = codec->pix_fmt }; - AVRational sample_aspect_ratio; - char args[255]; - int ret; - - ost->graph = avfilter_graph_alloc(); - - if (ist->st->sample_aspect_ratio.num){ - sample_aspect_ratio = ist->st->sample_aspect_ratio; - }else - sample_aspect_ratio = ist->st->codec->sample_aspect_ratio; - - snprintf(args, 255, "%d:%d:%d:%d:%d:%d:%d", ist->st->codec->width, - ist->st->codec->height, ist->st->codec->pix_fmt, 1, AV_TIME_BASE, - sample_aspect_ratio.num, sample_aspect_ratio.den); - - ret = avfilter_graph_create_filter(&ost->input_video_filter, avfilter_get_by_name("buffer"), - "src", args, NULL, ost->graph); - if (ret < 0) - return ret; - ret = avfilter_graph_create_filter(&ost->output_video_filter, &avsink, - "out", NULL, &avsink_ctx, ost->graph); - if (ret < 0) - return ret; - last_filter = ost->input_video_filter; - - if (codec->width != icodec->width || codec->height != icodec->height) { - snprintf(args, 255, "%d:%d:flags=0x%X", - codec->width, - codec->height, - ost->sws_flags); - if ((ret = avfilter_graph_create_filter(&filter, avfilter_get_by_name("scale"), - NULL, args, NULL, ost->graph)) < 0) - return ret; - if ((ret = avfilter_link(last_filter, 0, filter, 0)) < 0) - return ret; - last_filter = filter; - } - - snprintf(args, sizeof(args), "flags=0x%X", ost->sws_flags); - ost->graph->scale_sws_opts = av_strdup(args); - - if (ost->avfilter) { - AVFilterInOut *outputs = av_malloc(sizeof(AVFilterInOut)); - AVFilterInOut *inputs = av_malloc(sizeof(AVFilterInOut)); - - outputs->name = av_strdup("in"); - outputs->filter_ctx = last_filter; - outputs->pad_idx = 0; - outputs->next = NULL; - - inputs->name = av_strdup("out"); - inputs->filter_ctx = ost->output_video_filter; - inputs->pad_idx = 0; - inputs->next = NULL; - - if ((ret = avfilter_graph_parse(ost->graph, ost->avfilter, inputs, outputs, NULL)) < 0) - return ret; - av_freep(&ost->avfilter); - } else { - if ((ret = avfilter_link(last_filter, 0, ost->output_video_filter, 0)) < 0) - return ret; - } - - if ((ret = avfilter_graph_config(ost->graph, NULL)) < 0) - return ret; - - codec->width = ost->output_video_filter->inputs[0]->w; - codec->height = ost->output_video_filter->inputs[0]->h; - codec->sample_aspect_ratio = ost->st->sample_aspect_ratio = - ost->frame_aspect_ratio ? // overriden by the -aspect cli option - av_d2q(ost->frame_aspect_ratio*codec->height/codec->width, 255) : - ost->output_video_filter->inputs[0]->sample_aspect_ratio; - - return 0; -} -#endif /* CONFIG_AVFILTER */ - -static void term_exit(void) -{ - av_log(NULL, AV_LOG_QUIET, ""); -} - -static volatile int received_sigterm = 0; -static volatile int received_nb_signals = 0; - -static void -sigterm_handler(int sig) -{ - received_sigterm = sig; - received_nb_signals++; - term_exit(); -} - -static void term_init(void) -{ - signal(SIGINT , sigterm_handler); /* Interrupt (ANSI). */ - signal(SIGTERM, sigterm_handler); /* Termination (ANSI). */ -#ifdef SIGXCPU - signal(SIGXCPU, sigterm_handler); -#endif -} - -static int decode_interrupt_cb(void) -{ - return received_nb_signals > 1; -} - -void exit_program(int ret) -{ - int i; - - /* close files */ - for(i=0;ioformat->flags & AVFMT_NOFILE) && s->pb) - avio_close(s->pb); - avformat_free_context(s); - av_free(output_streams_for_file[i]); - av_dict_free(&output_opts[i]); - } - for(i=0;ikey); - exit_program(1); - } -} - -static void assert_codec_experimental(AVCodecContext *c, int encoder) -{ - const char *codec_string = encoder ? "encoder" : "decoder"; - AVCodec *codec; - if (c->codec->capabilities & CODEC_CAP_EXPERIMENTAL && - c->strict_std_compliance > FF_COMPLIANCE_EXPERIMENTAL) { - av_log(NULL, AV_LOG_ERROR, "%s '%s' is experimental and might produce bad " - "results.\nAdd '-strict experimental' if you want to use it.\n", - codec_string, c->codec->name); - codec = encoder ? avcodec_find_encoder(c->codec->id) : avcodec_find_decoder(c->codec->id); - if (!(codec->capabilities & CODEC_CAP_EXPERIMENTAL)) - av_log(NULL, AV_LOG_ERROR, "Or use the non experimental %s '%s'.\n", - codec_string, codec->name); - exit_program(1); - } -} - -static void choose_sample_fmt(AVStream *st, AVCodec *codec) -{ - if(codec && codec->sample_fmts){ - const enum AVSampleFormat *p= codec->sample_fmts; - for(; *p!=-1; p++){ - if(*p == st->codec->sample_fmt) - break; - } - if (*p == -1) { - av_log(NULL, AV_LOG_WARNING, - "Incompatible sample format '%s' for codec '%s', auto-selecting format '%s'\n", - av_get_sample_fmt_name(st->codec->sample_fmt), - codec->name, - av_get_sample_fmt_name(codec->sample_fmts[0])); - st->codec->sample_fmt = codec->sample_fmts[0]; - } - } -} - -/** - * Update the requested input sample format based on the output sample format. - * This is currently only used to request float output from decoders which - * support multiple sample formats, one of which is AV_SAMPLE_FMT_FLT. - * Ideally this will be removed in the future when decoders do not do format - * conversion and only output in their native format. - */ -static void update_sample_fmt(AVCodecContext *dec, AVCodec *dec_codec, - AVCodecContext *enc) -{ - /* if sample formats match or a decoder sample format has already been - requested, just return */ - if (enc->sample_fmt == dec->sample_fmt || - dec->request_sample_fmt > AV_SAMPLE_FMT_NONE) - return; - - /* if decoder supports more than one output format */ - if (dec_codec && dec_codec->sample_fmts && - dec_codec->sample_fmts[0] != AV_SAMPLE_FMT_NONE && - dec_codec->sample_fmts[1] != AV_SAMPLE_FMT_NONE) { - const enum AVSampleFormat *p; - int min_dec = -1, min_inc = -1; - - /* find a matching sample format in the encoder */ - for (p = dec_codec->sample_fmts; *p != AV_SAMPLE_FMT_NONE; p++) { - if (*p == enc->sample_fmt) { - dec->request_sample_fmt = *p; - return; - } else if (*p > enc->sample_fmt) { - min_inc = FFMIN(min_inc, *p - enc->sample_fmt); - } else - min_dec = FFMIN(min_dec, enc->sample_fmt - *p); - } - - /* if none match, provide the one that matches quality closest */ - dec->request_sample_fmt = min_inc > 0 ? enc->sample_fmt + min_inc : - enc->sample_fmt - min_dec; - } -} - -static void choose_sample_rate(AVStream *st, AVCodec *codec) -{ - if(codec && codec->supported_samplerates){ - const int *p= codec->supported_samplerates; - int best=0; - int best_dist=INT_MAX; - for(; *p; p++){ - int dist= abs(st->codec->sample_rate - *p); - if(dist < best_dist){ - best_dist= dist; - best= *p; - } - } - if(best_dist){ - av_log(st->codec, AV_LOG_WARNING, "Requested sampling rate unsupported using closest supported (%d)\n", best); - } - st->codec->sample_rate= best; - } -} - -static void choose_pixel_fmt(AVStream *st, AVCodec *codec) -{ - if(codec && codec->pix_fmts){ - const enum PixelFormat *p= codec->pix_fmts; - if(st->codec->strict_std_compliance <= FF_COMPLIANCE_UNOFFICIAL){ - if(st->codec->codec_id==CODEC_ID_MJPEG){ - p= (const enum PixelFormat[]){PIX_FMT_YUVJ420P, PIX_FMT_YUVJ422P, PIX_FMT_YUV420P, PIX_FMT_YUV422P, PIX_FMT_NONE}; - }else if(st->codec->codec_id==CODEC_ID_LJPEG){ - p= (const enum PixelFormat[]){PIX_FMT_YUVJ420P, PIX_FMT_YUVJ422P, PIX_FMT_YUVJ444P, PIX_FMT_YUV420P, PIX_FMT_YUV422P, PIX_FMT_YUV444P, PIX_FMT_BGRA, PIX_FMT_NONE}; - } - } - for(; *p!=-1; p++){ - if(*p == st->codec->pix_fmt) - break; - } - if (*p == -1) { - if(st->codec->pix_fmt != PIX_FMT_NONE) - av_log(NULL, AV_LOG_WARNING, - "Incompatible pixel format '%s' for codec '%s', auto-selecting format '%s'\n", - av_pix_fmt_descriptors[st->codec->pix_fmt].name, - codec->name, - av_pix_fmt_descriptors[codec->pix_fmts[0]].name); - st->codec->pix_fmt = codec->pix_fmts[0]; - } - } -} - -static OutputStream *new_output_stream(AVFormatContext *oc, int file_idx, AVCodec *codec) -{ - OutputStream *ost; - AVStream *st = av_new_stream(oc, oc->nb_streams < nb_streamid_map ? streamid_map[oc->nb_streams] : 0); - int idx = oc->nb_streams - 1; - - if (!st) { - av_log(NULL, AV_LOG_ERROR, "Could not alloc stream.\n"); - exit_program(1); - } - - output_streams_for_file[file_idx] = - grow_array(output_streams_for_file[file_idx], - sizeof(*output_streams_for_file[file_idx]), - &nb_output_streams_for_file[file_idx], - oc->nb_streams); - ost = output_streams_for_file[file_idx][idx] = - av_mallocz(sizeof(OutputStream)); - if (!ost) { - fprintf(stderr, "Could not alloc output stream\n"); - exit_program(1); - } - ost->file_index = file_idx; - ost->index = idx; - ost->st = st; - ost->enc = codec; - if (codec) - ost->opts = filter_codec_opts(codec_opts, codec->id, oc, st); - - avcodec_get_context_defaults3(st->codec, codec); - - ost->sws_flags = av_get_int(sws_opts, "sws_flags", NULL); - return ost; -} - -static int read_avserver_streams(AVFormatContext *s, const char *filename) -{ - int i, err; - AVFormatContext *ic = NULL; - - err = avformat_open_input(&ic, filename, NULL, NULL); - if (err < 0) - return err; - /* copy stream format */ - for(i=0;inb_streams;i++) { - AVStream *st; - OutputStream *ost; - AVCodec *codec; - - codec = avcodec_find_encoder(ic->streams[i]->codec->codec_id); - ost = new_output_stream(s, nb_output_files, codec); - st = ost->st; - - // FIXME: a more elegant solution is needed - memcpy(st, ic->streams[i], sizeof(AVStream)); - st->info = NULL; - avcodec_copy_context(st->codec, ic->streams[i]->codec); - - if (st->codec->codec_type == AVMEDIA_TYPE_AUDIO) { - if (audio_stream_copy) { - st->stream_copy = 1; - } else - choose_sample_fmt(st, codec); - } else if (st->codec->codec_type == AVMEDIA_TYPE_VIDEO) { - if (video_stream_copy) { - st->stream_copy = 1; - } else - choose_pixel_fmt(st, codec); - } - } - - av_close_input_file(ic); - return 0; -} - -static double -get_sync_ipts(const OutputStream *ost) -{ - const InputStream *ist = ost->sync_ist; - return (double)(ist->pts - start_time)/AV_TIME_BASE; -} - -static void write_frame(AVFormatContext *s, AVPacket *pkt, AVCodecContext *avctx, AVBitStreamFilterContext *bsfc){ - int ret; - - while(bsfc){ - AVPacket new_pkt= *pkt; - int a= av_bitstream_filter_filter(bsfc, avctx, NULL, - &new_pkt.data, &new_pkt.size, - pkt->data, pkt->size, - pkt->flags & AV_PKT_FLAG_KEY); - if(a>0){ - av_free_packet(pkt); - new_pkt.destruct= av_destruct_packet; - } else if(a<0){ - fprintf(stderr, "%s failed for stream %d, codec %s", - bsfc->filter->name, pkt->stream_index, - avctx->codec ? avctx->codec->name : "copy"); - print_error("", a); - if (exit_on_error) - exit_program(1); - } - *pkt= new_pkt; - - bsfc= bsfc->next; - } - - ret= av_interleaved_write_frame(s, pkt); - if(ret < 0){ - print_error("av_interleaved_write_frame()", ret); - exit_program(1); - } -} - -#define MAX_AUDIO_PACKET_SIZE (128 * 1024) - -static void do_audio_out(AVFormatContext *s, - OutputStream *ost, - InputStream *ist, - unsigned char *buf, int size) -{ - uint8_t *buftmp; - int64_t audio_out_size, audio_buf_size; - int64_t allocated_for_size= size; - - int size_out, frame_bytes, ret, resample_changed; - AVCodecContext *enc= ost->st->codec; - AVCodecContext *dec= ist->st->codec; - int osize = av_get_bytes_per_sample(enc->sample_fmt); - int isize = av_get_bytes_per_sample(dec->sample_fmt); - const int coded_bps = av_get_bits_per_sample(enc->codec->id); - -need_realloc: - audio_buf_size= (allocated_for_size + isize*dec->channels - 1) / (isize*dec->channels); - audio_buf_size= (audio_buf_size*enc->sample_rate + dec->sample_rate) / dec->sample_rate; - audio_buf_size= audio_buf_size*2 + 10000; //safety factors for the deprecated resampling API - audio_buf_size= FFMAX(audio_buf_size, enc->frame_size); - audio_buf_size*= osize*enc->channels; - - audio_out_size= FFMAX(audio_buf_size, enc->frame_size * osize * enc->channels); - if(coded_bps > 8*osize) - audio_out_size= audio_out_size * coded_bps / (8*osize); - audio_out_size += FF_MIN_BUFFER_SIZE; - - if(audio_out_size > INT_MAX || audio_buf_size > INT_MAX){ - fprintf(stderr, "Buffer sizes too large\n"); - exit_program(1); - } - - av_fast_malloc(&audio_buf, &allocated_audio_buf_size, audio_buf_size); - av_fast_malloc(&audio_out, &allocated_audio_out_size, audio_out_size); - if (!audio_buf || !audio_out){ - fprintf(stderr, "Out of memory in do_audio_out\n"); - exit_program(1); - } - - if (enc->channels != dec->channels || enc->sample_rate != dec->sample_rate) - ost->audio_resample = 1; - - resample_changed = ost->resample_sample_fmt != dec->sample_fmt || - ost->resample_channels != dec->channels || - ost->resample_sample_rate != dec->sample_rate; - - if ((ost->audio_resample && !ost->resample) || resample_changed) { - if (resample_changed) { - av_log(NULL, AV_LOG_INFO, "Input stream #%d.%d frame changed from rate:%d fmt:%s ch:%d to rate:%d fmt:%s ch:%d\n", - ist->file_index, ist->st->index, - ost->resample_sample_rate, av_get_sample_fmt_name(ost->resample_sample_fmt), ost->resample_channels, - dec->sample_rate, av_get_sample_fmt_name(dec->sample_fmt), dec->channels); - ost->resample_sample_fmt = dec->sample_fmt; - ost->resample_channels = dec->channels; - ost->resample_sample_rate = dec->sample_rate; - if (ost->resample) - audio_resample_close(ost->resample); - } - /* if audio_sync_method is >1 the resampler is needed for audio drift compensation */ - if (audio_sync_method <= 1 && - ost->resample_sample_fmt == enc->sample_fmt && - ost->resample_channels == enc->channels && - ost->resample_sample_rate == enc->sample_rate) { - ost->resample = NULL; - ost->audio_resample = 0; - } else if (ost->audio_resample) { - if (dec->sample_fmt != AV_SAMPLE_FMT_S16) - fprintf(stderr, "Warning, using s16 intermediate sample format for resampling\n"); - ost->resample = av_audio_resample_init(enc->channels, dec->channels, - enc->sample_rate, dec->sample_rate, - enc->sample_fmt, dec->sample_fmt, - 16, 10, 0, 0.8); - if (!ost->resample) { - fprintf(stderr, "Can not resample %d channels @ %d Hz to %d channels @ %d Hz\n", - dec->channels, dec->sample_rate, - enc->channels, enc->sample_rate); - exit_program(1); - } - } - } - -#define MAKE_SFMT_PAIR(a,b) ((a)+AV_SAMPLE_FMT_NB*(b)) - if (!ost->audio_resample && dec->sample_fmt!=enc->sample_fmt && - MAKE_SFMT_PAIR(enc->sample_fmt,dec->sample_fmt)!=ost->reformat_pair) { - if (ost->reformat_ctx) - av_audio_convert_free(ost->reformat_ctx); - ost->reformat_ctx = av_audio_convert_alloc(enc->sample_fmt, 1, - dec->sample_fmt, 1, NULL, 0); - if (!ost->reformat_ctx) { - fprintf(stderr, "Cannot convert %s sample format to %s sample format\n", - av_get_sample_fmt_name(dec->sample_fmt), - av_get_sample_fmt_name(enc->sample_fmt)); - exit_program(1); - } - ost->reformat_pair=MAKE_SFMT_PAIR(enc->sample_fmt,dec->sample_fmt); - } - - if(audio_sync_method){ - double delta = get_sync_ipts(ost) * enc->sample_rate - ost->sync_opts - - av_fifo_size(ost->fifo)/(enc->channels * 2); - double idelta= delta*dec->sample_rate / enc->sample_rate; - int byte_delta= ((int)idelta)*2*dec->channels; - - //FIXME resample delay - if(fabs(delta) > 50){ - if(ist->is_start || fabs(delta) > audio_drift_threshold*enc->sample_rate){ - if(byte_delta < 0){ - byte_delta= FFMAX(byte_delta, -size); - size += byte_delta; - buf -= byte_delta; - if(verbose > 2) - fprintf(stderr, "discarding %d audio samples\n", (int)-delta); - if(!size) - return; - ist->is_start=0; - }else{ - static uint8_t *input_tmp= NULL; - input_tmp= av_realloc(input_tmp, byte_delta + size); - - if(byte_delta > allocated_for_size - size){ - allocated_for_size= byte_delta + (int64_t)size; - goto need_realloc; - } - ist->is_start=0; - - memset(input_tmp, 0, byte_delta); - memcpy(input_tmp + byte_delta, buf, size); - buf= input_tmp; - size += byte_delta; - if(verbose > 2) - fprintf(stderr, "adding %d audio samples of silence\n", (int)delta); - } - }else if(audio_sync_method>1){ - int comp= av_clip(delta, -audio_sync_method, audio_sync_method); - av_assert0(ost->audio_resample); - if(verbose > 2) - fprintf(stderr, "compensating audio timestamp drift:%f compensation:%d in:%d\n", delta, comp, enc->sample_rate); -// fprintf(stderr, "drift:%f len:%d opts:%"PRId64" ipts:%"PRId64" fifo:%d\n", delta, -1, ost->sync_opts, (int64_t)(get_sync_ipts(ost) * enc->sample_rate), av_fifo_size(ost->fifo)/(ost->st->codec->channels * 2)); - av_resample_compensate(*(struct AVResampleContext**)ost->resample, comp, enc->sample_rate); - } - } - }else - ost->sync_opts= lrintf(get_sync_ipts(ost) * enc->sample_rate) - - av_fifo_size(ost->fifo)/(enc->channels * 2); //FIXME wrong - - if (ost->audio_resample) { - buftmp = audio_buf; - size_out = audio_resample(ost->resample, - (short *)buftmp, (short *)buf, - size / (dec->channels * isize)); - size_out = size_out * enc->channels * osize; - } else { - buftmp = buf; - size_out = size; - } - - if (!ost->audio_resample && dec->sample_fmt!=enc->sample_fmt) { - const void *ibuf[6]= {buftmp}; - void *obuf[6]= {audio_buf}; - int istride[6]= {isize}; - int ostride[6]= {osize}; - int len= size_out/istride[0]; - if (av_audio_convert(ost->reformat_ctx, obuf, ostride, ibuf, istride, len)<0) { - printf("av_audio_convert() failed\n"); - if (exit_on_error) - exit_program(1); - return; - } - buftmp = audio_buf; - size_out = len*osize; - } - - /* now encode as many frames as possible */ - if (enc->frame_size > 1) { - /* output resampled raw samples */ - if (av_fifo_realloc2(ost->fifo, av_fifo_size(ost->fifo) + size_out) < 0) { - fprintf(stderr, "av_fifo_realloc2() failed\n"); - exit_program(1); - } - av_fifo_generic_write(ost->fifo, buftmp, size_out, NULL); - - frame_bytes = enc->frame_size * osize * enc->channels; - - while (av_fifo_size(ost->fifo) >= frame_bytes) { - AVPacket pkt; - av_init_packet(&pkt); - - av_fifo_generic_read(ost->fifo, audio_buf, frame_bytes, NULL); - - //FIXME pass ost->sync_opts as AVFrame.pts in avcodec_encode_audio() - - ret = avcodec_encode_audio(enc, audio_out, audio_out_size, - (short *)audio_buf); - if (ret < 0) { - fprintf(stderr, "Audio encoding failed\n"); - exit_program(1); - } - audio_size += ret; - pkt.stream_index= ost->index; - pkt.data= audio_out; - pkt.size= ret; - if(enc->coded_frame && enc->coded_frame->pts != AV_NOPTS_VALUE) - pkt.pts= av_rescale_q(enc->coded_frame->pts, enc->time_base, ost->st->time_base); - pkt.flags |= AV_PKT_FLAG_KEY; - write_frame(s, &pkt, enc, ost->bitstream_filters); - - ost->sync_opts += enc->frame_size; - } - } else { - AVPacket pkt; - av_init_packet(&pkt); - - ost->sync_opts += size_out / (osize * enc->channels); - - /* output a pcm frame */ - /* determine the size of the coded buffer */ - size_out /= osize; - if (coded_bps) - size_out = size_out*coded_bps/8; - - if(size_out > audio_out_size){ - fprintf(stderr, "Internal error, buffer size too small\n"); - exit_program(1); - } - - //FIXME pass ost->sync_opts as AVFrame.pts in avcodec_encode_audio() - ret = avcodec_encode_audio(enc, audio_out, size_out, - (short *)buftmp); - if (ret < 0) { - fprintf(stderr, "Audio encoding failed\n"); - exit_program(1); - } - audio_size += ret; - pkt.stream_index= ost->index; - pkt.data= audio_out; - pkt.size= ret; - if(enc->coded_frame && enc->coded_frame->pts != AV_NOPTS_VALUE) - pkt.pts= av_rescale_q(enc->coded_frame->pts, enc->time_base, ost->st->time_base); - pkt.flags |= AV_PKT_FLAG_KEY; - write_frame(s, &pkt, enc, ost->bitstream_filters); - } -} - -static void pre_process_video_frame(InputStream *ist, AVPicture *picture, void **bufp) -{ - AVCodecContext *dec; - AVPicture *picture2; - AVPicture picture_tmp; - uint8_t *buf = 0; - - dec = ist->st->codec; - - /* deinterlace : must be done before any resize */ - if (do_deinterlace) { - int size; - - /* create temporary picture */ - size = avpicture_get_size(dec->pix_fmt, dec->width, dec->height); - buf = av_malloc(size); - if (!buf) - return; - - picture2 = &picture_tmp; - avpicture_fill(picture2, buf, dec->pix_fmt, dec->width, dec->height); - - if(avpicture_deinterlace(picture2, picture, - dec->pix_fmt, dec->width, dec->height) < 0) { - /* if error, do not deinterlace */ - fprintf(stderr, "Deinterlacing failed\n"); - av_free(buf); - buf = NULL; - picture2 = picture; - } - } else { - picture2 = picture; - } - - if (picture != picture2) - *picture = *picture2; - *bufp = buf; -} - -/* we begin to correct av delay at this threshold */ -#define AV_DELAY_MAX 0.100 - -static void do_subtitle_out(AVFormatContext *s, - OutputStream *ost, - InputStream *ist, - AVSubtitle *sub, - int64_t pts) -{ - static uint8_t *subtitle_out = NULL; - int subtitle_out_max_size = 1024 * 1024; - int subtitle_out_size, nb, i; - AVCodecContext *enc; - AVPacket pkt; - - if (pts == AV_NOPTS_VALUE) { - fprintf(stderr, "Subtitle packets must have a pts\n"); - if (exit_on_error) - exit_program(1); - return; - } - - enc = ost->st->codec; - - if (!subtitle_out) { - subtitle_out = av_malloc(subtitle_out_max_size); - } - - /* Note: DVB subtitle need one packet to draw them and one other - packet to clear them */ - /* XXX: signal it in the codec context ? */ - if (enc->codec_id == CODEC_ID_DVB_SUBTITLE) - nb = 2; - else - nb = 1; - - for(i = 0; i < nb; i++) { - sub->pts = av_rescale_q(pts, ist->st->time_base, AV_TIME_BASE_Q); - // start_display_time is required to be 0 - sub->pts += av_rescale_q(sub->start_display_time, (AVRational){1, 1000}, AV_TIME_BASE_Q); - sub->end_display_time -= sub->start_display_time; - sub->start_display_time = 0; - subtitle_out_size = avcodec_encode_subtitle(enc, subtitle_out, - subtitle_out_max_size, sub); - if (subtitle_out_size < 0) { - fprintf(stderr, "Subtitle encoding failed\n"); - exit_program(1); - } - - av_init_packet(&pkt); - pkt.stream_index = ost->index; - pkt.data = subtitle_out; - pkt.size = subtitle_out_size; - pkt.pts = av_rescale_q(sub->pts, AV_TIME_BASE_Q, ost->st->time_base); - if (enc->codec_id == CODEC_ID_DVB_SUBTITLE) { - /* XXX: the pts correction is handled here. Maybe handling - it in the codec would be better */ - if (i == 0) - pkt.pts += 90 * sub->start_display_time; - else - pkt.pts += 90 * sub->end_display_time; - } - write_frame(s, &pkt, ost->st->codec, ost->bitstream_filters); - } -} - -static int bit_buffer_size= 1024*256; -static uint8_t *bit_buffer= NULL; - -static void do_video_out(AVFormatContext *s, - OutputStream *ost, - InputStream *ist, - AVFrame *in_picture, - int *frame_size, float quality) -{ - int nb_frames, i, ret, resample_changed; - AVFrame *final_picture, *formatted_picture; - AVCodecContext *enc, *dec; - double sync_ipts; - - enc = ost->st->codec; - dec = ist->st->codec; - - sync_ipts = get_sync_ipts(ost) / av_q2d(enc->time_base); - - /* by default, we output a single frame */ - nb_frames = 1; - - *frame_size = 0; - - if(video_sync_method){ - double vdelta = sync_ipts - ost->sync_opts; - //FIXME set to 0.5 after we fix some dts/pts bugs like in avidec.c - if (vdelta < -1.1) - nb_frames = 0; - else if (video_sync_method == 2 || (video_sync_method<0 && (s->oformat->flags & AVFMT_VARIABLE_FPS))){ - if(vdelta<=-0.6){ - nb_frames=0; - }else if(vdelta>0.6) - ost->sync_opts= lrintf(sync_ipts); - }else if (vdelta > 1.1) - nb_frames = lrintf(vdelta); -//fprintf(stderr, "vdelta:%f, ost->sync_opts:%"PRId64", ost->sync_ipts:%f nb_frames:%d\n", vdelta, ost->sync_opts, get_sync_ipts(ost), nb_frames); - if (nb_frames == 0){ - ++nb_frames_drop; - if (verbose>2) - fprintf(stderr, "*** drop!\n"); - }else if (nb_frames > 1) { - nb_frames_dup += nb_frames - 1; - if (verbose>2) - fprintf(stderr, "*** %d dup!\n", nb_frames-1); - } - }else - ost->sync_opts= lrintf(sync_ipts); - - nb_frames= FFMIN(nb_frames, max_frames[AVMEDIA_TYPE_VIDEO] - ost->frame_number); - if (nb_frames <= 0) - return; - - formatted_picture = in_picture; - final_picture = formatted_picture; - - resample_changed = ost->resample_width != dec->width || - ost->resample_height != dec->height || - ost->resample_pix_fmt != dec->pix_fmt; - - if (resample_changed) { - av_log(NULL, AV_LOG_INFO, - "Input stream #%d.%d frame changed from size:%dx%d fmt:%s to size:%dx%d fmt:%s\n", - ist->file_index, ist->st->index, - ost->resample_width, ost->resample_height, av_get_pix_fmt_name(ost->resample_pix_fmt), - dec->width , dec->height , av_get_pix_fmt_name(dec->pix_fmt)); - if(!ost->video_resample) - exit_program(1); - } - -#if !CONFIG_AVFILTER - if (ost->video_resample) { - final_picture = &ost->pict_tmp; - if (resample_changed) { - /* initialize a new scaler context */ - sws_freeContext(ost->img_resample_ctx); - ost->img_resample_ctx = sws_getContext( - ist->st->codec->width, - ist->st->codec->height, - ist->st->codec->pix_fmt, - ost->st->codec->width, - ost->st->codec->height, - ost->st->codec->pix_fmt, - ost->sws_flags, NULL, NULL, NULL); - if (ost->img_resample_ctx == NULL) { - fprintf(stderr, "Cannot get resampling context\n"); - exit_program(1); - } - } - sws_scale(ost->img_resample_ctx, formatted_picture->data, formatted_picture->linesize, - 0, ost->resample_height, final_picture->data, final_picture->linesize); - } -#endif - - /* duplicates frame if needed */ - for(i=0;iindex; - - if (s->oformat->flags & AVFMT_RAWPICTURE) { - /* raw pictures are written as AVPicture structure to - avoid any copies. We support temorarily the older - method. */ - AVFrame* old_frame = enc->coded_frame; - enc->coded_frame = dec->coded_frame; //FIXME/XXX remove this hack - pkt.data= (uint8_t *)final_picture; - pkt.size= sizeof(AVPicture); - pkt.pts= av_rescale_q(ost->sync_opts, enc->time_base, ost->st->time_base); - pkt.flags |= AV_PKT_FLAG_KEY; - - write_frame(s, &pkt, ost->st->codec, ost->bitstream_filters); - enc->coded_frame = old_frame; - } else { - AVFrame big_picture; - - big_picture= *final_picture; - /* better than nothing: use input picture interlaced - settings */ - big_picture.interlaced_frame = in_picture->interlaced_frame; - if (ost->st->codec->flags & (CODEC_FLAG_INTERLACED_DCT|CODEC_FLAG_INTERLACED_ME)) { - if(top_field_first == -1) - big_picture.top_field_first = in_picture->top_field_first; - else - big_picture.top_field_first = top_field_first; - } - - /* handles sameq here. This is not correct because it may - not be a global option */ - big_picture.quality = quality; - if(!me_threshold) - big_picture.pict_type = 0; -// big_picture.pts = AV_NOPTS_VALUE; - big_picture.pts= ost->sync_opts; -// big_picture.pts= av_rescale(ost->sync_opts, AV_TIME_BASE*(int64_t)enc->time_base.num, enc->time_base.den); -//av_log(NULL, AV_LOG_DEBUG, "%"PRId64" -> encoder\n", ost->sync_opts); - if (ost->forced_kf_index < ost->forced_kf_count && - big_picture.pts >= ost->forced_kf_pts[ost->forced_kf_index]) { - big_picture.pict_type = AV_PICTURE_TYPE_I; - ost->forced_kf_index++; - } - ret = avcodec_encode_video(enc, - bit_buffer, bit_buffer_size, - &big_picture); - if (ret < 0) { - fprintf(stderr, "Video encoding failed\n"); - exit_program(1); - } - - if(ret>0){ - pkt.data= bit_buffer; - pkt.size= ret; - if(enc->coded_frame->pts != AV_NOPTS_VALUE) - pkt.pts= av_rescale_q(enc->coded_frame->pts, enc->time_base, ost->st->time_base); -/*av_log(NULL, AV_LOG_DEBUG, "encoder -> %"PRId64"/%"PRId64"\n", - pkt.pts != AV_NOPTS_VALUE ? av_rescale(pkt.pts, enc->time_base.den, AV_TIME_BASE*(int64_t)enc->time_base.num) : -1, - pkt.dts != AV_NOPTS_VALUE ? av_rescale(pkt.dts, enc->time_base.den, AV_TIME_BASE*(int64_t)enc->time_base.num) : -1);*/ - - if(enc->coded_frame->key_frame) - pkt.flags |= AV_PKT_FLAG_KEY; - write_frame(s, &pkt, ost->st->codec, ost->bitstream_filters); - *frame_size = ret; - video_size += ret; - //fprintf(stderr,"\nFrame: %3d size: %5d type: %d", - // enc->frame_number-1, ret, enc->pict_type); - /* if two pass, output log */ - if (ost->logfile && enc->stats_out) { - fprintf(ost->logfile, "%s", enc->stats_out); - } - } - } - ost->sync_opts++; - ost->frame_number++; - } -} - -static double psnr(double d){ - return -10.0*log(d)/log(10.0); -} - -static void do_video_stats(AVFormatContext *os, OutputStream *ost, - int frame_size) -{ - AVCodecContext *enc; - int frame_number; - double ti1, bitrate, avg_bitrate; - - /* this is executed just the first time do_video_stats is called */ - if (!vstats_file) { - vstats_file = fopen(vstats_filename, "w"); - if (!vstats_file) { - perror("fopen"); - exit_program(1); - } - } - - enc = ost->st->codec; - if (enc->codec_type == AVMEDIA_TYPE_VIDEO) { - frame_number = ost->frame_number; - fprintf(vstats_file, "frame= %5d q= %2.1f ", frame_number, enc->coded_frame->quality/(float)FF_QP2LAMBDA); - if (enc->flags&CODEC_FLAG_PSNR) - fprintf(vstats_file, "PSNR= %6.2f ", psnr(enc->coded_frame->error[0]/(enc->width*enc->height*255.0*255.0))); - - fprintf(vstats_file,"f_size= %6d ", frame_size); - /* compute pts value */ - ti1 = ost->sync_opts * av_q2d(enc->time_base); - if (ti1 < 0.01) - ti1 = 0.01; - - bitrate = (frame_size * 8) / av_q2d(enc->time_base) / 1000.0; - avg_bitrate = (double)(video_size * 8) / ti1 / 1000.0; - fprintf(vstats_file, "s_size= %8.0fkB time= %0.3f br= %7.1fkbits/s avg_br= %7.1fkbits/s ", - (double)video_size / 1024, ti1, bitrate, avg_bitrate); - fprintf(vstats_file, "type= %c\n", av_get_picture_type_char(enc->coded_frame->pict_type)); - } -} - -static void print_report(AVFormatContext **output_files, - OutputStream **ost_table, int nb_ostreams, - int is_last_report) -{ - char buf[1024]; - OutputStream *ost; - AVFormatContext *oc; - int64_t total_size; - AVCodecContext *enc; - int frame_number, vid, i; - double bitrate, ti1, pts; - static int64_t last_time = -1; - static int qp_histogram[52]; - - if (!is_last_report) { - int64_t cur_time; - /* display the report every 0.5 seconds */ - cur_time = av_gettime(); - if (last_time == -1) { - last_time = cur_time; - return; - } - if ((cur_time - last_time) < 500000) - return; - last_time = cur_time; - } - - - oc = output_files[0]; - - total_size = avio_size(oc->pb); - if(total_size<0) // FIXME improve avio_size() so it works with non seekable output too - total_size= avio_tell(oc->pb); - - buf[0] = '\0'; - ti1 = 1e10; - vid = 0; - for(i=0;ist->codec; - if (!ost->st->stream_copy && enc->coded_frame) - q = enc->coded_frame->quality/(float)FF_QP2LAMBDA; - if (vid && enc->codec_type == AVMEDIA_TYPE_VIDEO) { - snprintf(buf + strlen(buf), sizeof(buf) - strlen(buf), "q=%2.1f ", q); - } - if (!vid && enc->codec_type == AVMEDIA_TYPE_VIDEO) { - float t = (av_gettime()-timer_start) / 1000000.0; - - frame_number = ost->frame_number; - snprintf(buf + strlen(buf), sizeof(buf) - strlen(buf), "frame=%5d fps=%3d q=%3.1f ", - frame_number, (t>1)?(int)(frame_number/t+0.5) : 0, q); - if(is_last_report) - snprintf(buf + strlen(buf), sizeof(buf) - strlen(buf), "L"); - if(qp_hist){ - int j; - int qp = lrintf(q); - if(qp>=0 && qpflags&CODEC_FLAG_PSNR){ - int j; - double error, error_sum=0; - double scale, scale_sum=0; - char type[3]= {'Y','U','V'}; - snprintf(buf + strlen(buf), sizeof(buf) - strlen(buf), "PSNR="); - for(j=0; j<3; j++){ - if(is_last_report){ - error= enc->error[j]; - scale= enc->width*enc->height*255.0*255.0*frame_number; - }else{ - error= enc->coded_frame->error[j]; - scale= enc->width*enc->height*255.0*255.0; - } - if(j) scale/=4; - error_sum += error; - scale_sum += scale; - snprintf(buf + strlen(buf), sizeof(buf) - strlen(buf), "%c:%2.2f ", type[j], psnr(error/scale)); - } - snprintf(buf + strlen(buf), sizeof(buf) - strlen(buf), "*:%2.2f ", psnr(error_sum/scale_sum)); - } - vid = 1; - } - /* compute min output value */ - pts = (double)ost->st->pts.val * av_q2d(ost->st->time_base); - if ((pts < ti1) && (pts > 0)) - ti1 = pts; - } - if (ti1 < 0.01) - ti1 = 0.01; - - if (verbose > 0 || is_last_report) { - bitrate = (double)(total_size * 8) / ti1 / 1000.0; - - snprintf(buf + strlen(buf), sizeof(buf) - strlen(buf), - "size=%8.0fkB time=%0.2f bitrate=%6.1fkbits/s", - (double)total_size / 1024, ti1, bitrate); - - if (nb_frames_dup || nb_frames_drop) - snprintf(buf + strlen(buf), sizeof(buf) - strlen(buf), " dup=%d drop=%d", - nb_frames_dup, nb_frames_drop); - - if (verbose >= 0) - fprintf(stderr, "%s \r", buf); - - fflush(stderr); - } - - if (is_last_report && verbose >= 0){ - int64_t raw= audio_size + video_size + extra_size; - fprintf(stderr, "\n"); - fprintf(stderr, "video:%1.0fkB audio:%1.0fkB global headers:%1.0fkB muxing overhead %f%%\n", - video_size/1024.0, - audio_size/1024.0, - extra_size/1024.0, - 100.0*(total_size - raw)/raw - ); - } -} - -static void generate_silence(uint8_t* buf, enum AVSampleFormat sample_fmt, size_t size) -{ - int fill_char = 0x00; - if (sample_fmt == AV_SAMPLE_FMT_U8) - fill_char = 0x80; - memset(buf, fill_char, size); -} - -/* pkt = NULL means EOF (needed to flush decoder buffers) */ -static int output_packet(InputStream *ist, int ist_index, - OutputStream **ost_table, int nb_ostreams, - const AVPacket *pkt) -{ - AVFormatContext *os; - OutputStream *ost; - int ret, i; - int got_output; - AVFrame picture; - void *buffer_to_free = NULL; - static unsigned int samples_size= 0; - AVSubtitle subtitle, *subtitle_to_free; - int64_t pkt_pts = AV_NOPTS_VALUE; -#if CONFIG_AVFILTER - int frame_available; -#endif - float quality; - - AVPacket avpkt; - int bps = av_get_bytes_per_sample(ist->st->codec->sample_fmt); - - if(ist->next_pts == AV_NOPTS_VALUE) - ist->next_pts= ist->pts; - - if (pkt == NULL) { - /* EOF handling */ - av_init_packet(&avpkt); - avpkt.data = NULL; - avpkt.size = 0; - goto handle_eof; - } else { - avpkt = *pkt; - } - - if(pkt->dts != AV_NOPTS_VALUE) - ist->next_pts = ist->pts = av_rescale_q(pkt->dts, ist->st->time_base, AV_TIME_BASE_Q); - if(pkt->pts != AV_NOPTS_VALUE) - pkt_pts = av_rescale_q(pkt->pts, ist->st->time_base, AV_TIME_BASE_Q); - - //while we have more to decode or while the decoder did output something on EOF - while (avpkt.size > 0 || (!pkt && got_output)) { - uint8_t *data_buf, *decoded_data_buf; - int data_size, decoded_data_size; - handle_eof: - ist->pts= ist->next_pts; - - if(avpkt.size && avpkt.size != pkt->size && - ((!ist->showed_multi_packet_warning && verbose>0) || verbose>1)){ - fprintf(stderr, "Multiple frames in a packet from stream %d\n", pkt->stream_index); - ist->showed_multi_packet_warning=1; - } - - /* decode the packet if needed */ - decoded_data_buf = NULL; /* fail safe */ - decoded_data_size= 0; - data_buf = avpkt.data; - data_size = avpkt.size; - subtitle_to_free = NULL; - if (ist->decoding_needed) { - switch(ist->st->codec->codec_type) { - case AVMEDIA_TYPE_AUDIO:{ - if(pkt && samples_size < FFMAX(pkt->size*sizeof(*samples), AVCODEC_MAX_AUDIO_FRAME_SIZE)) { - samples_size = FFMAX(pkt->size*sizeof(*samples), AVCODEC_MAX_AUDIO_FRAME_SIZE); - av_free(samples); - samples= av_malloc(samples_size); - } - decoded_data_size= samples_size; - /* XXX: could avoid copy if PCM 16 bits with same - endianness as CPU */ - ret = avcodec_decode_audio3(ist->st->codec, samples, &decoded_data_size, - &avpkt); - if (ret < 0) - return ret; - avpkt.data += ret; - avpkt.size -= ret; - data_size = ret; - got_output = decoded_data_size > 0; - /* Some bug in mpeg audio decoder gives */ - /* decoded_data_size < 0, it seems they are overflows */ - if (!got_output) { - /* no audio frame */ - continue; - } - decoded_data_buf = (uint8_t *)samples; - ist->next_pts += ((int64_t)AV_TIME_BASE/bps * decoded_data_size) / - (ist->st->codec->sample_rate * ist->st->codec->channels); - break;} - case AVMEDIA_TYPE_VIDEO: - decoded_data_size = (ist->st->codec->width * ist->st->codec->height * 3) / 2; - /* XXX: allocate picture correctly */ - avcodec_get_frame_defaults(&picture); - avpkt.pts = pkt_pts; - avpkt.dts = ist->pts; - pkt_pts = AV_NOPTS_VALUE; - - ret = avcodec_decode_video2(ist->st->codec, - &picture, &got_output, &avpkt); - quality = same_quality ? picture.quality : 0; - if (ret < 0) - return ret; - if (!got_output) { - /* no picture yet */ - goto discard_packet; - } - ist->next_pts = ist->pts = guess_correct_pts(&ist->pts_ctx, picture.pkt_pts, picture.pkt_dts); - if (ist->st->codec->time_base.num != 0) { - int ticks= ist->st->parser ? ist->st->parser->repeat_pict+1 : ist->st->codec->ticks_per_frame; - ist->next_pts += ((int64_t)AV_TIME_BASE * - ist->st->codec->time_base.num * ticks) / - ist->st->codec->time_base.den; - } - avpkt.size = 0; - buffer_to_free = NULL; - pre_process_video_frame(ist, (AVPicture *)&picture, &buffer_to_free); - break; - case AVMEDIA_TYPE_SUBTITLE: - ret = avcodec_decode_subtitle2(ist->st->codec, - &subtitle, &got_output, &avpkt); - if (ret < 0) - return ret; - if (!got_output) { - goto discard_packet; - } - subtitle_to_free = &subtitle; - avpkt.size = 0; - break; - default: - return -1; - } - } else { - switch(ist->st->codec->codec_type) { - case AVMEDIA_TYPE_AUDIO: - ist->next_pts += ((int64_t)AV_TIME_BASE * ist->st->codec->frame_size) / - ist->st->codec->sample_rate; - break; - case AVMEDIA_TYPE_VIDEO: - if (ist->st->codec->time_base.num != 0) { - int ticks= ist->st->parser ? ist->st->parser->repeat_pict+1 : ist->st->codec->ticks_per_frame; - ist->next_pts += ((int64_t)AV_TIME_BASE * - ist->st->codec->time_base.num * ticks) / - ist->st->codec->time_base.den; - } - break; - } - ret = avpkt.size; - avpkt.size = 0; - } - -#if CONFIG_AVFILTER - if (ist->st->codec->codec_type == AVMEDIA_TYPE_VIDEO) { - for (i = 0; i < nb_ostreams; i++) { - ost = ost_table[i]; - if (ost->input_video_filter && ost->source_index == ist_index) { - AVRational sar; - if (ist->st->sample_aspect_ratio.num) - sar = ist->st->sample_aspect_ratio; - else - sar = ist->st->codec->sample_aspect_ratio; - // add it to be filtered - av_vsrc_buffer_add_frame(ost->input_video_filter, &picture, - ist->pts, - sar); - } - } - } -#endif - - // preprocess audio (volume) - if (ist->st->codec->codec_type == AVMEDIA_TYPE_AUDIO) { - if (audio_volume != 256) { - short *volp; - volp = samples; - for(i=0;i<(decoded_data_size / sizeof(short));i++) { - int v = ((*volp) * audio_volume + 128) >> 8; - if (v < -32768) v = -32768; - if (v > 32767) v = 32767; - *volp++ = v; - } - } - } - - /* frame rate emulation */ - if (rate_emu) { - int64_t pts = av_rescale(ist->pts, 1000000, AV_TIME_BASE); - int64_t now = av_gettime() - ist->start; - if (pts > now) - usleep(pts - now); - } - /* if output time reached then transcode raw format, - encode packets and output them */ - if (start_time == 0 || ist->pts >= start_time) - for(i=0;isource_index == ist_index) { -#if CONFIG_AVFILTER - frame_available = ist->st->codec->codec_type != AVMEDIA_TYPE_VIDEO || - !ost->output_video_filter || avfilter_poll_frame(ost->output_video_filter->inputs[0]); - while (frame_available) { - AVRational ist_pts_tb; - if (ist->st->codec->codec_type == AVMEDIA_TYPE_VIDEO && ost->output_video_filter) - get_filtered_video_frame(ost->output_video_filter, &picture, &ost->picref, &ist_pts_tb); - if (ost->picref) - ist->pts = av_rescale_q(ost->picref->pts, ist_pts_tb, AV_TIME_BASE_Q); -#endif - os = output_files[ost->file_index]; - - /* set the input output pts pairs */ - //ost->sync_ipts = (double)(ist->pts + input_files[ist->file_index].ts_offset - start_time)/ AV_TIME_BASE; - - if (ost->encoding_needed) { - av_assert0(ist->decoding_needed); - switch(ost->st->codec->codec_type) { - case AVMEDIA_TYPE_AUDIO: - do_audio_out(os, ost, ist, decoded_data_buf, decoded_data_size); - break; - case AVMEDIA_TYPE_VIDEO: -#if CONFIG_AVFILTER - if (ost->picref->video && !ost->frame_aspect_ratio) - ost->st->codec->sample_aspect_ratio = ost->picref->video->pixel_aspect; -#endif - do_video_out(os, ost, ist, &picture, &frame_size, - same_quality ? quality : ost->st->codec->global_quality); - if (vstats_filename && frame_size) - do_video_stats(os, ost, frame_size); - break; - case AVMEDIA_TYPE_SUBTITLE: - do_subtitle_out(os, ost, ist, &subtitle, - pkt->pts); - break; - default: - abort(); - } - } else { - AVFrame avframe; //FIXME/XXX remove this - AVPacket opkt; - int64_t ost_tb_start_time= av_rescale_q(start_time, AV_TIME_BASE_Q, ost->st->time_base); - - av_init_packet(&opkt); - - if ((!ost->frame_number && !(pkt->flags & AV_PKT_FLAG_KEY)) && !copy_initial_nonkeyframes) -#if !CONFIG_AVFILTER - continue; -#else - goto cont; -#endif - - /* no reencoding needed : output the packet directly */ - /* force the input stream PTS */ - - avcodec_get_frame_defaults(&avframe); - ost->st->codec->coded_frame= &avframe; - avframe.key_frame = pkt->flags & AV_PKT_FLAG_KEY; - - if(ost->st->codec->codec_type == AVMEDIA_TYPE_AUDIO) - audio_size += data_size; - else if (ost->st->codec->codec_type == AVMEDIA_TYPE_VIDEO) { - video_size += data_size; - ost->sync_opts++; - } - - opkt.stream_index= ost->index; - if(pkt->pts != AV_NOPTS_VALUE) - opkt.pts= av_rescale_q(pkt->pts, ist->st->time_base, ost->st->time_base) - ost_tb_start_time; - else - opkt.pts= AV_NOPTS_VALUE; - - if (pkt->dts == AV_NOPTS_VALUE) - opkt.dts = av_rescale_q(ist->pts, AV_TIME_BASE_Q, ost->st->time_base); - else - opkt.dts = av_rescale_q(pkt->dts, ist->st->time_base, ost->st->time_base); - opkt.dts -= ost_tb_start_time; - - opkt.duration = av_rescale_q(pkt->duration, ist->st->time_base, ost->st->time_base); - opkt.flags= pkt->flags; - - //FIXME remove the following 2 lines they shall be replaced by the bitstream filters - if( ost->st->codec->codec_id != CODEC_ID_H264 - && ost->st->codec->codec_id != CODEC_ID_MPEG1VIDEO - && ost->st->codec->codec_id != CODEC_ID_MPEG2VIDEO - ) { - if(av_parser_change(ist->st->parser, ost->st->codec, &opkt.data, &opkt.size, data_buf, data_size, pkt->flags & AV_PKT_FLAG_KEY)) - opkt.destruct= av_destruct_packet; - } else { - opkt.data = data_buf; - opkt.size = data_size; - } - - write_frame(os, &opkt, ost->st->codec, ost->bitstream_filters); - ost->st->codec->frame_number++; - ost->frame_number++; - av_free_packet(&opkt); - } -#if CONFIG_AVFILTER - cont: - frame_available = (ist->st->codec->codec_type == AVMEDIA_TYPE_VIDEO) && - ost->output_video_filter && avfilter_poll_frame(ost->output_video_filter->inputs[0]); - if (ost->picref) - avfilter_unref_buffer(ost->picref); - } -#endif - } - } - - av_free(buffer_to_free); - /* XXX: allocate the subtitles in the codec ? */ - if (subtitle_to_free) { - avsubtitle_free(subtitle_to_free); - subtitle_to_free = NULL; - } - } - discard_packet: - if (pkt == NULL) { - /* EOF handling */ - - for(i=0;isource_index == ist_index) { - AVCodecContext *enc= ost->st->codec; - os = output_files[ost->file_index]; - - if(ost->st->codec->codec_type == AVMEDIA_TYPE_AUDIO && enc->frame_size <=1) - continue; - if(ost->st->codec->codec_type == AVMEDIA_TYPE_VIDEO && (os->oformat->flags & AVFMT_RAWPICTURE)) - continue; - - if (ost->encoding_needed) { - for(;;) { - AVPacket pkt; - int fifo_bytes; - av_init_packet(&pkt); - pkt.stream_index= ost->index; - - switch(ost->st->codec->codec_type) { - case AVMEDIA_TYPE_AUDIO: - fifo_bytes = av_fifo_size(ost->fifo); - ret = 0; - /* encode any samples remaining in fifo */ - if (fifo_bytes > 0) { - int osize = av_get_bytes_per_sample(enc->sample_fmt); - int fs_tmp = enc->frame_size; - - av_fifo_generic_read(ost->fifo, audio_buf, fifo_bytes, NULL); - if (enc->codec->capabilities & CODEC_CAP_SMALL_LAST_FRAME) { - enc->frame_size = fifo_bytes / (osize * enc->channels); - } else { /* pad */ - int frame_bytes = enc->frame_size*osize*enc->channels; - if (allocated_audio_buf_size < frame_bytes) - exit_program(1); - generate_silence(audio_buf+fifo_bytes, enc->sample_fmt, frame_bytes - fifo_bytes); - } - - ret = avcodec_encode_audio(enc, bit_buffer, bit_buffer_size, (short *)audio_buf); - pkt.duration = av_rescale((int64_t)enc->frame_size*ost->st->time_base.den, - ost->st->time_base.num, enc->sample_rate); - enc->frame_size = fs_tmp; - } - if(ret <= 0) { - ret = avcodec_encode_audio(enc, bit_buffer, bit_buffer_size, NULL); - } - if (ret < 0) { - fprintf(stderr, "Audio encoding failed\n"); - exit_program(1); - } - audio_size += ret; - pkt.flags |= AV_PKT_FLAG_KEY; - break; - case AVMEDIA_TYPE_VIDEO: - ret = avcodec_encode_video(enc, bit_buffer, bit_buffer_size, NULL); - if (ret < 0) { - fprintf(stderr, "Video encoding failed\n"); - exit_program(1); - } - video_size += ret; - if(enc->coded_frame && enc->coded_frame->key_frame) - pkt.flags |= AV_PKT_FLAG_KEY; - if (ost->logfile && enc->stats_out) { - fprintf(ost->logfile, "%s", enc->stats_out); - } - break; - default: - ret=-1; - } - - if(ret<=0) - break; - pkt.data= bit_buffer; - pkt.size= ret; - if(enc->coded_frame && enc->coded_frame->pts != AV_NOPTS_VALUE) - pkt.pts= av_rescale_q(enc->coded_frame->pts, enc->time_base, ost->st->time_base); - write_frame(os, &pkt, ost->st->codec, ost->bitstream_filters); - } - } - } - } - } - - return 0; -} - -static void print_sdp(AVFormatContext **avc, int n) -{ - char sdp[2048]; - - av_sdp_create(avc, n, sdp, sizeof(sdp)); - printf("SDP:\n%s\n", sdp); - fflush(stdout); -} - -static int copy_chapters(int infile, int outfile) -{ - AVFormatContext *is = input_files[infile].ctx; - AVFormatContext *os = output_files[outfile]; - int i; - - for (i = 0; i < is->nb_chapters; i++) { - AVChapter *in_ch = is->chapters[i], *out_ch; - int64_t ts_off = av_rescale_q(start_time - input_files[infile].ts_offset, - AV_TIME_BASE_Q, in_ch->time_base); - int64_t rt = (recording_time == INT64_MAX) ? INT64_MAX : - av_rescale_q(recording_time, AV_TIME_BASE_Q, in_ch->time_base); - - - if (in_ch->end < ts_off) - continue; - if (rt != INT64_MAX && in_ch->start > rt + ts_off) - break; - - out_ch = av_mallocz(sizeof(AVChapter)); - if (!out_ch) - return AVERROR(ENOMEM); - - out_ch->id = in_ch->id; - out_ch->time_base = in_ch->time_base; - out_ch->start = FFMAX(0, in_ch->start - ts_off); - out_ch->end = FFMIN(rt, in_ch->end - ts_off); - - if (metadata_chapters_autocopy) - av_dict_copy(&out_ch->metadata, in_ch->metadata, 0); - - os->nb_chapters++; - os->chapters = av_realloc(os->chapters, sizeof(AVChapter)*os->nb_chapters); - if (!os->chapters) - return AVERROR(ENOMEM); - os->chapters[os->nb_chapters - 1] = out_ch; - } - return 0; -} - -static void parse_forced_key_frames(char *kf, OutputStream *ost, - AVCodecContext *avctx) -{ - char *p; - int n = 1, i; - int64_t t; - - for (p = kf; *p; p++) - if (*p == ',') - n++; - ost->forced_kf_count = n; - ost->forced_kf_pts = av_malloc(sizeof(*ost->forced_kf_pts) * n); - if (!ost->forced_kf_pts) { - av_log(NULL, AV_LOG_FATAL, "Could not allocate forced key frames array.\n"); - exit_program(1); - } - for (i = 0; i < n; i++) { - p = i ? strchr(p, ',') + 1 : kf; - t = parse_time_or_die("force_key_frames", p, 1); - ost->forced_kf_pts[i] = av_rescale_q(t, AV_TIME_BASE_Q, avctx->time_base); - } -} - -/* - * The following code is the main loop of the file converter - */ -static int transcode(AVFormatContext **output_files, - int nb_output_files, - InputFile *input_files, - int nb_input_files, - StreamMap *stream_maps, int nb_stream_maps) -{ - int ret = 0, i, j, k, n, nb_ostreams = 0; - AVFormatContext *is, *os; - AVCodecContext *codec, *icodec; - OutputStream *ost, **ost_table = NULL; - InputStream *ist; - char error[1024]; - int want_sdp = 1; - uint8_t no_packet[MAX_FILES]={0}; - int no_packet_count=0; - - if (rate_emu) - for (i = 0; i < nb_input_streams; i++) - input_streams[i].start = av_gettime(); - - /* output stream init */ - nb_ostreams = 0; - for(i=0;inb_streams && !(os->oformat->flags & AVFMT_NOSTREAMS)) { - av_dump_format(output_files[i], i, output_files[i]->filename, 1); - fprintf(stderr, "Output file #%d does not contain any stream\n", i); - ret = AVERROR(EINVAL); - goto fail; - } - nb_ostreams += os->nb_streams; - } - if (nb_stream_maps > 0 && nb_stream_maps != nb_ostreams) { - fprintf(stderr, "Number of stream maps must match number of output streams\n"); - ret = AVERROR(EINVAL); - goto fail; - } - - /* Sanity check the mapping args -- do the input files & streams exist? */ - for(i=0;i nb_input_files - 1 || - si < 0 || si > input_files[fi].nb_streams - 1) { - fprintf(stderr,"Could not find input stream #%d.%d\n", fi, si); - ret = AVERROR(EINVAL); - goto fail; - } - fi = stream_maps[i].sync_file_index; - si = stream_maps[i].sync_stream_index; - if (fi < 0 || fi > nb_input_files - 1 || - si < 0 || si > input_files[fi].nb_streams - 1) { - fprintf(stderr,"Could not find sync stream #%d.%d\n", fi, si); - ret = AVERROR(EINVAL); - goto fail; - } - } - - ost_table = av_mallocz(sizeof(OutputStream *) * nb_ostreams); - if (!ost_table) - goto fail; - n = 0; - for(k=0;knb_streams;i++,n++) { - int found; - ost = ost_table[n] = output_streams_for_file[k][i]; - if (nb_stream_maps > 0) { - ost->source_index = input_files[stream_maps[n].file_index].ist_index + - stream_maps[n].stream_index; - - /* Sanity check that the stream types match */ - if (input_streams[ost->source_index].st->codec->codec_type != ost->st->codec->codec_type) { - int i= ost->file_index; - av_dump_format(output_files[i], i, output_files[i]->filename, 1); - fprintf(stderr, "Codec type mismatch for mapping #%d.%d -> #%d.%d\n", - stream_maps[n].file_index, stream_maps[n].stream_index, - ost->file_index, ost->index); - exit_program(1); - } - - } else { - int best_nb_frames=-1; - /* get corresponding input stream index : we select the first one with the right type */ - found = 0; - for (j = 0; j < nb_input_streams; j++) { - int skip=0; - ist = &input_streams[j]; - if(opt_programid){ - int pi,si; - AVFormatContext *f = input_files[ist->file_index].ctx; - skip=1; - for(pi=0; pinb_programs; pi++){ - AVProgram *p= f->programs[pi]; - if(p->id == opt_programid) - for(si=0; sinb_stream_indexes; si++){ - if(f->streams[ p->stream_index[si] ] == ist->st) - skip=0; - } - } - } - if (ist->discard && ist->st->discard != AVDISCARD_ALL && !skip && - ist->st->codec->codec_type == ost->st->codec->codec_type) { - if(best_nb_frames < ist->st->codec_info_nb_frames){ - best_nb_frames= ist->st->codec_info_nb_frames; - ost->source_index = j; - found = 1; - } - } - } - - if (!found) { - if(! opt_programid) { - /* try again and reuse existing stream */ - for (j = 0; j < nb_input_streams; j++) { - ist = &input_streams[j]; - if ( ist->st->codec->codec_type == ost->st->codec->codec_type - && ist->st->discard != AVDISCARD_ALL) { - ost->source_index = j; - found = 1; - } - } - } - if (!found) { - int i= ost->file_index; - av_dump_format(output_files[i], i, output_files[i]->filename, 1); - fprintf(stderr, "Could not find input stream matching output stream #%d.%d\n", - ost->file_index, ost->index); - exit_program(1); - } - } - } - ist = &input_streams[ost->source_index]; - ist->discard = 0; - ost->sync_ist = (nb_stream_maps > 0) ? - &input_streams[input_files[stream_maps[n].sync_file_index].ist_index + - stream_maps[n].sync_stream_index] : ist; - } - } - - /* for each output stream, we compute the right encoding parameters */ - for(i=0;ifile_index]; - ist = &input_streams[ost->source_index]; - - codec = ost->st->codec; - icodec = ist->st->codec; - - if (metadata_streams_autocopy) - av_dict_copy(&ost->st->metadata, ist->st->metadata, - AV_DICT_DONT_OVERWRITE); - - ost->st->disposition = ist->st->disposition; - codec->bits_per_raw_sample= icodec->bits_per_raw_sample; - codec->chroma_sample_location = icodec->chroma_sample_location; - - if (ost->st->stream_copy) { - uint64_t extra_size = (uint64_t)icodec->extradata_size + FF_INPUT_BUFFER_PADDING_SIZE; - - if (extra_size > INT_MAX) - goto fail; - - /* if stream_copy is selected, no need to decode or encode */ - codec->codec_id = icodec->codec_id; - codec->codec_type = icodec->codec_type; - - if(!codec->codec_tag){ - if( !os->oformat->codec_tag - || av_codec_get_id (os->oformat->codec_tag, icodec->codec_tag) == codec->codec_id - || av_codec_get_tag(os->oformat->codec_tag, icodec->codec_id) <= 0) - codec->codec_tag = icodec->codec_tag; - } - - codec->bit_rate = icodec->bit_rate; - codec->rc_max_rate = icodec->rc_max_rate; - codec->rc_buffer_size = icodec->rc_buffer_size; - codec->extradata= av_mallocz(extra_size); - if (!codec->extradata) - goto fail; - memcpy(codec->extradata, icodec->extradata, icodec->extradata_size); - codec->extradata_size= icodec->extradata_size; - if(!copy_tb && av_q2d(icodec->time_base)*icodec->ticks_per_frame > av_q2d(ist->st->time_base) && av_q2d(ist->st->time_base) < 1.0/500){ - codec->time_base = icodec->time_base; - codec->time_base.num *= icodec->ticks_per_frame; - av_reduce(&codec->time_base.num, &codec->time_base.den, - codec->time_base.num, codec->time_base.den, INT_MAX); - }else - codec->time_base = ist->st->time_base; - switch(codec->codec_type) { - case AVMEDIA_TYPE_AUDIO: - if(audio_volume != 256) { - fprintf(stderr,"-acodec copy and -vol are incompatible (frames are not decoded)\n"); - exit_program(1); - } - codec->channel_layout = icodec->channel_layout; - codec->sample_rate = icodec->sample_rate; - codec->channels = icodec->channels; - codec->frame_size = icodec->frame_size; - codec->audio_service_type = icodec->audio_service_type; - codec->block_align= icodec->block_align; - if(codec->block_align == 1 && codec->codec_id == CODEC_ID_MP3) - codec->block_align= 0; - if(codec->codec_id == CODEC_ID_AC3) - codec->block_align= 0; - break; - case AVMEDIA_TYPE_VIDEO: - codec->pix_fmt = icodec->pix_fmt; - codec->width = icodec->width; - codec->height = icodec->height; - codec->has_b_frames = icodec->has_b_frames; - if (!codec->sample_aspect_ratio.num) { - codec->sample_aspect_ratio = - ost->st->sample_aspect_ratio = - ist->st->sample_aspect_ratio.num ? ist->st->sample_aspect_ratio : - ist->st->codec->sample_aspect_ratio.num ? - ist->st->codec->sample_aspect_ratio : (AVRational){0, 1}; - } - break; - case AVMEDIA_TYPE_SUBTITLE: - codec->width = icodec->width; - codec->height = icodec->height; - break; - case AVMEDIA_TYPE_DATA: - break; - default: - abort(); - } - } else { - if (!ost->enc) - ost->enc = avcodec_find_encoder(ost->st->codec->codec_id); - switch(codec->codec_type) { - case AVMEDIA_TYPE_AUDIO: - ost->fifo= av_fifo_alloc(1024); - if(!ost->fifo) - goto fail; - ost->reformat_pair = MAKE_SFMT_PAIR(AV_SAMPLE_FMT_NONE,AV_SAMPLE_FMT_NONE); - if (!codec->sample_rate) { - codec->sample_rate = icodec->sample_rate; - if (icodec->lowres) - codec->sample_rate >>= icodec->lowres; - } - choose_sample_rate(ost->st, ost->enc); - codec->time_base = (AVRational){1, codec->sample_rate}; - if (codec->sample_fmt == AV_SAMPLE_FMT_NONE) - codec->sample_fmt = icodec->sample_fmt; - choose_sample_fmt(ost->st, ost->enc); - if (!codec->channels) - codec->channels = icodec->channels; - codec->channel_layout = icodec->channel_layout; - if (av_get_channel_layout_nb_channels(codec->channel_layout) != codec->channels) - codec->channel_layout = 0; - ost->audio_resample = codec->sample_rate != icodec->sample_rate || audio_sync_method > 1; - icodec->request_channels = codec->channels; - ist->decoding_needed = 1; - ost->encoding_needed = 1; - ost->resample_sample_fmt = icodec->sample_fmt; - ost->resample_sample_rate = icodec->sample_rate; - ost->resample_channels = icodec->channels; - break; - case AVMEDIA_TYPE_VIDEO: - if (codec->pix_fmt == PIX_FMT_NONE) - codec->pix_fmt = icodec->pix_fmt; - choose_pixel_fmt(ost->st, ost->enc); - - if (ost->st->codec->pix_fmt == PIX_FMT_NONE) { - fprintf(stderr, "Video pixel format is unknown, stream cannot be encoded\n"); - exit_program(1); - } - - if (!codec->width || !codec->height) { - codec->width = icodec->width; - codec->height = icodec->height; - } - - ost->video_resample = codec->width != icodec->width || - codec->height != icodec->height || - codec->pix_fmt != icodec->pix_fmt; - if (ost->video_resample) { -#if !CONFIG_AVFILTER - avcodec_get_frame_defaults(&ost->pict_tmp); - if(avpicture_alloc((AVPicture*)&ost->pict_tmp, codec->pix_fmt, - codec->width, codec->height)) { - fprintf(stderr, "Cannot allocate temp picture, check pix fmt\n"); - exit_program(1); - } - ost->img_resample_ctx = sws_getContext( - icodec->width, - icodec->height, - icodec->pix_fmt, - codec->width, - codec->height, - codec->pix_fmt, - ost->sws_flags, NULL, NULL, NULL); - if (ost->img_resample_ctx == NULL) { - fprintf(stderr, "Cannot get resampling context\n"); - exit_program(1); - } -#endif - codec->bits_per_raw_sample= 0; - } - - ost->resample_height = icodec->height; - ost->resample_width = icodec->width; - ost->resample_pix_fmt= icodec->pix_fmt; - ost->encoding_needed = 1; - ist->decoding_needed = 1; - - if (!ost->frame_rate.num) - ost->frame_rate = ist->st->r_frame_rate.num ? ist->st->r_frame_rate : (AVRational){25,1}; - if (ost->enc && ost->enc->supported_framerates && !force_fps) { - int idx = av_find_nearest_q_idx(ost->frame_rate, ost->enc->supported_framerates); - ost->frame_rate = ost->enc->supported_framerates[idx]; - } - codec->time_base = (AVRational){ost->frame_rate.den, ost->frame_rate.num}; - -#if CONFIG_AVFILTER - if (configure_video_filters(ist, ost)) { - fprintf(stderr, "Error opening filters!\n"); - exit(1); - } -#endif - break; - case AVMEDIA_TYPE_SUBTITLE: - ost->encoding_needed = 1; - ist->decoding_needed = 1; - break; - default: - abort(); - break; - } - /* two pass mode */ - if (ost->encoding_needed && - (codec->flags & (CODEC_FLAG_PASS1 | CODEC_FLAG_PASS2))) { - char logfilename[1024]; - FILE *f; - - snprintf(logfilename, sizeof(logfilename), "%s-%d.log", - pass_logfilename_prefix ? pass_logfilename_prefix : DEFAULT_PASS_LOGFILENAME_PREFIX, - i); - if (codec->flags & CODEC_FLAG_PASS1) { - f = fopen(logfilename, "wb"); - if (!f) { - fprintf(stderr, "Cannot write log file '%s' for pass-1 encoding: %s\n", logfilename, strerror(errno)); - exit_program(1); - } - ost->logfile = f; - } else { - char *logbuffer; - size_t logbuffer_size; - if (cmdutils_read_file(logfilename, &logbuffer, &logbuffer_size) < 0) { - fprintf(stderr, "Error reading log file '%s' for pass-2 encoding\n", logfilename); - exit_program(1); - } - codec->stats_in = logbuffer; - } - } - } - if(codec->codec_type == AVMEDIA_TYPE_VIDEO){ - int size= codec->width * codec->height; - bit_buffer_size= FFMAX(bit_buffer_size, 6*size + 200); - } - } - - if (!bit_buffer) - bit_buffer = av_malloc(bit_buffer_size); - if (!bit_buffer) { - fprintf(stderr, "Cannot allocate %d bytes output buffer\n", - bit_buffer_size); - ret = AVERROR(ENOMEM); - goto fail; - } - - /* open each encoder */ - for(i=0;iencoding_needed) { - AVCodec *codec = ost->enc; - AVCodecContext *dec = input_streams[ost->source_index].st->codec; - if (!codec) { - snprintf(error, sizeof(error), "Encoder (codec id %d) not found for output stream #%d.%d", - ost->st->codec->codec_id, ost->file_index, ost->index); - ret = AVERROR(EINVAL); - goto dump_format; - } - if (dec->subtitle_header) { - ost->st->codec->subtitle_header = av_malloc(dec->subtitle_header_size); - if (!ost->st->codec->subtitle_header) { - ret = AVERROR(ENOMEM); - goto dump_format; - } - memcpy(ost->st->codec->subtitle_header, dec->subtitle_header, dec->subtitle_header_size); - ost->st->codec->subtitle_header_size = dec->subtitle_header_size; - } - if (avcodec_open2(ost->st->codec, codec, &ost->opts) < 0) { - snprintf(error, sizeof(error), "Error while opening encoder for output stream #%d.%d - maybe incorrect parameters such as bit_rate, rate, width or height", - ost->file_index, ost->index); - ret = AVERROR(EINVAL); - goto dump_format; - } - assert_codec_experimental(ost->st->codec, 1); - assert_avoptions(ost->opts); - if (ost->st->codec->bit_rate && ost->st->codec->bit_rate < 1000) - av_log(NULL, AV_LOG_WARNING, "The bitrate parameter is set too low." - "It takes bits/s as argument, not kbits/s\n"); - extra_size += ost->st->codec->extradata_size; - } - } - - /* open each decoder */ - for (i = 0; i < nb_input_streams; i++) { - ist = &input_streams[i]; - if (ist->decoding_needed) { - AVCodec *codec = ist->dec; - if (!codec) - codec = avcodec_find_decoder(ist->st->codec->codec_id); - if (!codec) { - snprintf(error, sizeof(error), "Decoder (codec id %d) not found for input stream #%d.%d", - ist->st->codec->codec_id, ist->file_index, ist->st->index); - ret = AVERROR(EINVAL); - goto dump_format; - } - - /* update requested sample format for the decoder based on the - corresponding encoder sample format */ - for (j = 0; j < nb_ostreams; j++) { - ost = ost_table[j]; - if (ost->source_index == i) { - update_sample_fmt(ist->st->codec, codec, ost->st->codec); - break; - } - } - - if (avcodec_open2(ist->st->codec, codec, &ist->opts) < 0) { - snprintf(error, sizeof(error), "Error while opening decoder for input stream #%d.%d", - ist->file_index, ist->st->index); - ret = AVERROR(EINVAL); - goto dump_format; - } - assert_codec_experimental(ist->st->codec, 0); - assert_avoptions(ost->opts); - } - } - - /* init pts */ - for (i = 0; i < nb_input_streams; i++) { - AVStream *st; - ist = &input_streams[i]; - st= ist->st; - ist->pts = st->avg_frame_rate.num ? - st->codec->has_b_frames*AV_TIME_BASE / av_q2d(st->avg_frame_rate) : 0; - ist->next_pts = AV_NOPTS_VALUE; - init_pts_correction(&ist->pts_ctx); - ist->is_start = 1; - } - - /* set meta data information from input file if required */ - for (i=0;i= (nb_elems)) {\ - snprintf(error, sizeof(error), "Invalid %s index %d while processing metadata maps\n",\ - (desc), (index));\ - ret = AVERROR(EINVAL);\ - goto dump_format;\ - } - - int out_file_index = meta_data_maps[i][0].file; - int in_file_index = meta_data_maps[i][1].file; - if (in_file_index < 0 || out_file_index < 0) - continue; - METADATA_CHECK_INDEX(out_file_index, nb_output_files, "output file") - METADATA_CHECK_INDEX(in_file_index, nb_input_files, "input file") - - files[0] = output_files[out_file_index]; - files[1] = input_files[in_file_index].ctx; - - for (j = 0; j < 2; j++) { - MetadataMap *map = &meta_data_maps[i][j]; - - switch (map->type) { - case 'g': - meta[j] = &files[j]->metadata; - break; - case 's': - METADATA_CHECK_INDEX(map->index, files[j]->nb_streams, "stream") - meta[j] = &files[j]->streams[map->index]->metadata; - break; - case 'c': - METADATA_CHECK_INDEX(map->index, files[j]->nb_chapters, "chapter") - meta[j] = &files[j]->chapters[map->index]->metadata; - break; - case 'p': - METADATA_CHECK_INDEX(map->index, files[j]->nb_programs, "program") - meta[j] = &files[j]->programs[map->index]->metadata; - break; - } - } - - av_dict_copy(meta[0], *meta[1], AV_DICT_DONT_OVERWRITE); - } - - /* copy global metadata by default */ - if (metadata_global_autocopy) { - - for (i = 0; i < nb_output_files; i++) - av_dict_copy(&output_files[i]->metadata, input_files[0].ctx->metadata, - AV_DICT_DONT_OVERWRITE); - } - - /* copy chapters according to chapter maps */ - for (i = 0; i < nb_chapter_maps; i++) { - int infile = chapter_maps[i].in_file; - int outfile = chapter_maps[i].out_file; - - if (infile < 0 || outfile < 0) - continue; - if (infile >= nb_input_files) { - snprintf(error, sizeof(error), "Invalid input file index %d in chapter mapping.\n", infile); - ret = AVERROR(EINVAL); - goto dump_format; - } - if (outfile >= nb_output_files) { - snprintf(error, sizeof(error), "Invalid output file index %d in chapter mapping.\n",outfile); - ret = AVERROR(EINVAL); - goto dump_format; - } - copy_chapters(infile, outfile); - } - - /* copy chapters from the first input file that has them*/ - if (!nb_chapter_maps) - for (i = 0; i < nb_input_files; i++) { - if (!input_files[i].ctx->nb_chapters) - continue; - - for (j = 0; j < nb_output_files; j++) - if ((ret = copy_chapters(i, j)) < 0) - goto dump_format; - break; - } - - /* open files and write file headers */ - for(i=0;ioformat->name, "rtp")) { - want_sdp = 0; - } - } - - dump_format: - /* dump the file output parameters - cannot be done before in case - of stream copy */ - for(i=0;ifilename, 1); - } - - /* dump the stream mapping */ - if (verbose >= 0) { - fprintf(stderr, "Stream mapping:\n"); - for(i=0;i #%d.%d", - input_streams[ost->source_index].file_index, - input_streams[ost->source_index].st->index, - ost->file_index, - ost->index); - if (ost->sync_ist != &input_streams[ost->source_index]) - fprintf(stderr, " [sync #%d.%d]", - ost->sync_ist->file_index, - ost->sync_ist->st->index); - fprintf(stderr, "\n"); - } - } - - if (ret) { - fprintf(stderr, "%s\n", error); - goto fail; - } - - if (want_sdp) { - print_sdp(output_files, nb_output_files); - } - - if (verbose >= 0) - fprintf(stderr, "Press ctrl-c to stop encoding\n"); - term_init(); - - timer_start = av_gettime(); - - for(; received_sigterm == 0;) { - int file_index, ist_index; - AVPacket pkt; - double ipts_min; - double opts_min; - - redo: - ipts_min= 1e100; - opts_min= 1e100; - - /* select the stream that we must read now by looking at the - smallest output pts */ - file_index = -1; - for(i=0;ifile_index]; - ist = &input_streams[ost->source_index]; - if(ist->is_past_recording_time || no_packet[ist->file_index]) - continue; - opts = ost->st->pts.val * av_q2d(ost->st->time_base); - ipts = (double)ist->pts; - if (!input_files[ist->file_index].eof_reached){ - if(ipts < ipts_min) { - ipts_min = ipts; - if(input_sync ) file_index = ist->file_index; - } - if(opts < opts_min) { - opts_min = opts; - if(!input_sync) file_index = ist->file_index; - } - } - if(ost->frame_number >= max_frames[ost->st->codec->codec_type]){ - file_index= -1; - break; - } - } - /* if none, if is finished */ - if (file_index < 0) { - if(no_packet_count){ - no_packet_count=0; - memset(no_packet, 0, sizeof(no_packet)); - usleep(10000); - continue; - } - break; - } - - /* finish if limit size exhausted */ - if (limit_filesize != 0 && limit_filesize <= avio_tell(output_files[0]->pb)) - break; - - /* read a frame from it and output it in the fifo */ - is = input_files[file_index].ctx; - ret= av_read_frame(is, &pkt); - if(ret == AVERROR(EAGAIN)){ - no_packet[file_index]=1; - no_packet_count++; - continue; - } - if (ret < 0) { - input_files[file_index].eof_reached = 1; - if (opt_shortest) - break; - else - continue; - } - - no_packet_count=0; - memset(no_packet, 0, sizeof(no_packet)); - - if (do_pkt_dump) { - av_pkt_dump_log2(NULL, AV_LOG_DEBUG, &pkt, do_hex_dump, - is->streams[pkt.stream_index]); - } - /* the following test is needed in case new streams appear - dynamically in stream : we ignore them */ - if (pkt.stream_index >= input_files[file_index].nb_streams) - goto discard_packet; - ist_index = input_files[file_index].ist_index + pkt.stream_index; - ist = &input_streams[ist_index]; - if (ist->discard) - goto discard_packet; - - if (pkt.dts != AV_NOPTS_VALUE) - pkt.dts += av_rescale_q(input_files[ist->file_index].ts_offset, AV_TIME_BASE_Q, ist->st->time_base); - if (pkt.pts != AV_NOPTS_VALUE) - pkt.pts += av_rescale_q(input_files[ist->file_index].ts_offset, AV_TIME_BASE_Q, ist->st->time_base); - - if (ist->ts_scale) { - if(pkt.pts != AV_NOPTS_VALUE) - pkt.pts *= ist->ts_scale; - if(pkt.dts != AV_NOPTS_VALUE) - pkt.dts *= ist->ts_scale; - } - -// fprintf(stderr, "next:%"PRId64" dts:%"PRId64" off:%"PRId64" %d\n", ist->next_pts, pkt.dts, input_files[ist->file_index].ts_offset, ist->st->codec->codec_type); - if (pkt.dts != AV_NOPTS_VALUE && ist->next_pts != AV_NOPTS_VALUE - && (is->iformat->flags & AVFMT_TS_DISCONT)) { - int64_t pkt_dts= av_rescale_q(pkt.dts, ist->st->time_base, AV_TIME_BASE_Q); - int64_t delta= pkt_dts - ist->next_pts; - if((FFABS(delta) > 1LL*dts_delta_threshold*AV_TIME_BASE || pkt_dts+1pts)&& !copy_ts){ - input_files[ist->file_index].ts_offset -= delta; - if (verbose > 2) - fprintf(stderr, "timestamp discontinuity %"PRId64", new offset= %"PRId64"\n", - delta, input_files[ist->file_index].ts_offset); - pkt.dts-= av_rescale_q(delta, AV_TIME_BASE_Q, ist->st->time_base); - if(pkt.pts != AV_NOPTS_VALUE) - pkt.pts-= av_rescale_q(delta, AV_TIME_BASE_Q, ist->st->time_base); - } - } - - /* finish if recording time exhausted */ - if (recording_time != INT64_MAX && - av_compare_ts(pkt.pts, ist->st->time_base, recording_time + start_time, (AVRational){1, 1000000}) >= 0) { - ist->is_past_recording_time = 1; - goto discard_packet; - } - - //fprintf(stderr,"read #%d.%d size=%d\n", ist->file_index, ist->st->index, pkt.size); - if (output_packet(ist, ist_index, ost_table, nb_ostreams, &pkt) < 0) { - - if (verbose >= 0) - fprintf(stderr, "Error while decoding stream #%d.%d\n", - ist->file_index, ist->st->index); - if (exit_on_error) - exit_program(1); - av_free_packet(&pkt); - goto redo; - } - - discard_packet: - av_free_packet(&pkt); - - /* dump report by using the output first video and audio streams */ - print_report(output_files, ost_table, nb_ostreams, 0); - } - - /* at the end of stream, we must flush the decoder buffers */ - for (i = 0; i < nb_input_streams; i++) { - ist = &input_streams[i]; - if (ist->decoding_needed) { - output_packet(ist, i, ost_table, nb_ostreams, NULL); - } - } - - term_exit(); - - /* write the trailer if needed and close file */ - for(i=0;iencoding_needed) { - av_freep(&ost->st->codec->stats_in); - avcodec_close(ost->st->codec); - } -#if CONFIG_AVFILTER - avfilter_graph_free(&ost->graph); -#endif - } - - /* close each decoder */ - for (i = 0; i < nb_input_streams; i++) { - ist = &input_streams[i]; - if (ist->decoding_needed) { - avcodec_close(ist->st->codec); - } - } - - /* finished ! */ - ret = 0; - - fail: - av_freep(&bit_buffer); - - if (ost_table) { - for(i=0;ist->stream_copy) - av_freep(&ost->st->codec->extradata); - if (ost->logfile) { - fclose(ost->logfile); - ost->logfile = NULL; - } - av_fifo_free(ost->fifo); /* works even if fifo is not - initialized but set to zero */ - av_freep(&ost->st->codec->subtitle_header); - av_free(ost->pict_tmp.data[0]); - av_free(ost->forced_kf_pts); - if (ost->video_resample) - sws_freeContext(ost->img_resample_ctx); - if (ost->resample) - audio_resample_close(ost->resample); - if (ost->reformat_ctx) - av_audio_convert_free(ost->reformat_ctx); - av_dict_free(&ost->opts); - av_free(ost); - } - } - av_free(ost_table); - } - return ret; -} - -static int opt_format(const char *opt, const char *arg) -{ - last_asked_format = arg; - return 0; -} - -static int opt_video_rc_override_string(const char *opt, const char *arg) -{ - video_rc_override_string = arg; - return 0; -} - -static int opt_me_threshold(const char *opt, const char *arg) -{ - me_threshold = parse_number_or_die(opt, arg, OPT_INT64, INT_MIN, INT_MAX); - return 0; -} - -static int opt_verbose(const char *opt, const char *arg) -{ - verbose = parse_number_or_die(opt, arg, OPT_INT64, -10, 10); - return 0; -} - -static int opt_frame_rate(const char *opt, const char *arg) -{ - if (av_parse_video_rate(&frame_rate, arg) < 0) { - fprintf(stderr, "Incorrect value for %s: %s\n", opt, arg); - exit_program(1); - } - return 0; -} - -static int opt_frame_crop(const char *opt, const char *arg) -{ - fprintf(stderr, "Option '%s' has been removed, use the crop filter instead\n", opt); - return AVERROR(EINVAL); -} - -static int opt_frame_size(const char *opt, const char *arg) -{ - if (av_parse_video_size(&frame_width, &frame_height, arg) < 0) { - fprintf(stderr, "Incorrect frame size\n"); - return AVERROR(EINVAL); - } - return 0; -} - -static int opt_pad(const char *opt, const char *arg) { - fprintf(stderr, "Option '%s' has been removed, use the pad filter instead\n", opt); - return -1; -} - -static int opt_frame_pix_fmt(const char *opt, const char *arg) -{ - if (strcmp(arg, "list")) { - frame_pix_fmt = av_get_pix_fmt(arg); - if (frame_pix_fmt == PIX_FMT_NONE) { - fprintf(stderr, "Unknown pixel format requested: %s\n", arg); - return AVERROR(EINVAL); - } - } else { - show_pix_fmts(); - exit_program(0); - } - return 0; -} - -static int opt_frame_aspect_ratio(const char *opt, const char *arg) -{ - int x = 0, y = 0; - double ar = 0; - const char *p; - char *end; - - p = strchr(arg, ':'); - if (p) { - x = strtol(arg, &end, 10); - if (end == p) - y = strtol(end+1, &end, 10); - if (x > 0 && y > 0) - ar = (double)x / (double)y; - } else - ar = strtod(arg, NULL); - - if (!ar) { - fprintf(stderr, "Incorrect aspect ratio specification.\n"); - return AVERROR(EINVAL); - } - frame_aspect_ratio = ar; - return 0; -} - -static int opt_metadata(const char *opt, const char *arg) -{ - char *mid= strchr(arg, '='); - - if(!mid){ - fprintf(stderr, "Missing =\n"); - exit_program(1); - } - *mid++= 0; - - av_dict_set(&metadata, arg, mid, 0); - - return 0; -} - -static int opt_qscale(const char *opt, const char *arg) -{ - video_qscale = parse_number_or_die(opt, arg, OPT_FLOAT, 0, 255); - if (video_qscale == 0) { - fprintf(stderr, "qscale must be > 0.0 and <= 255\n"); - return AVERROR(EINVAL); - } - return 0; -} - -static int opt_top_field_first(const char *opt, const char *arg) -{ - top_field_first = parse_number_or_die(opt, arg, OPT_INT, 0, 1); - return 0; -} - -static int opt_thread_count(const char *opt, const char *arg) -{ - thread_count= parse_number_or_die(opt, arg, OPT_INT64, 0, INT_MAX); -#if !HAVE_THREADS - if (verbose >= 0) - fprintf(stderr, "Warning: not compiled with thread support, using thread emulation\n"); -#endif - return 0; -} - -static int opt_audio_sample_fmt(const char *opt, const char *arg) -{ - if (strcmp(arg, "list")) { - audio_sample_fmt = av_get_sample_fmt(arg); - if (audio_sample_fmt == AV_SAMPLE_FMT_NONE) { - av_log(NULL, AV_LOG_ERROR, "Invalid sample format '%s'\n", arg); - return AVERROR(EINVAL); - } - } else { - int i; - char fmt_str[128]; - for (i = -1; i < AV_SAMPLE_FMT_NB; i++) - printf("%s\n", av_get_sample_fmt_string(fmt_str, sizeof(fmt_str), i)); - exit_program(0); - } - return 0; -} - -static int opt_audio_rate(const char *opt, const char *arg) -{ - audio_sample_rate = parse_number_or_die(opt, arg, OPT_INT64, 0, INT_MAX); - return 0; -} - -static int opt_audio_channels(const char *opt, const char *arg) -{ - audio_channels = parse_number_or_die(opt, arg, OPT_INT64, 0, INT_MAX); - return 0; -} - -static int opt_video_channel(const char *opt, const char *arg) -{ - av_log(NULL, AV_LOG_WARNING, "This option is deprecated, use -channel.\n"); - opt_default("channel", arg); - return 0; -} - -static int opt_video_standard(const char *opt, const char *arg) -{ - av_log(NULL, AV_LOG_WARNING, "This option is deprecated, use -standard.\n"); - opt_default("standard", arg); - return 0; -} - -static int opt_codec(int *pstream_copy, char **pcodec_name, - int codec_type, const char *arg) -{ - av_freep(pcodec_name); - if (!strcmp(arg, "copy")) { - *pstream_copy = 1; - } else { - *pcodec_name = av_strdup(arg); - } - return 0; -} - -static int opt_audio_codec(const char *opt, const char *arg) -{ - return opt_codec(&audio_stream_copy, &audio_codec_name, AVMEDIA_TYPE_AUDIO, arg); -} - -static int opt_video_codec(const char *opt, const char *arg) -{ - return opt_codec(&video_stream_copy, &video_codec_name, AVMEDIA_TYPE_VIDEO, arg); -} - -static int opt_subtitle_codec(const char *opt, const char *arg) -{ - return opt_codec(&subtitle_stream_copy, &subtitle_codec_name, AVMEDIA_TYPE_SUBTITLE, arg); -} - -static int opt_data_codec(const char *opt, const char *arg) -{ - return opt_codec(&data_stream_copy, &data_codec_name, AVMEDIA_TYPE_DATA, arg); -} - -static int opt_codec_tag(const char *opt, const char *arg) -{ - char *tail; - uint32_t *codec_tag; - - codec_tag = !strcmp(opt, "atag") ? &audio_codec_tag : - !strcmp(opt, "vtag") ? &video_codec_tag : - !strcmp(opt, "stag") ? &subtitle_codec_tag : NULL; - if (!codec_tag) - return -1; - - *codec_tag = strtol(arg, &tail, 0); - if (!tail || *tail) - *codec_tag = AV_RL32(arg); - - return 0; -} - -static int opt_map(const char *opt, const char *arg) -{ - StreamMap *m; - char *p; - - stream_maps = grow_array(stream_maps, sizeof(*stream_maps), &nb_stream_maps, nb_stream_maps + 1); - m = &stream_maps[nb_stream_maps-1]; - - m->file_index = strtol(arg, &p, 0); - if (*p) - p++; - - m->stream_index = strtol(p, &p, 0); - if (*p) { - p++; - m->sync_file_index = strtol(p, &p, 0); - if (*p) - p++; - m->sync_stream_index = strtol(p, &p, 0); - } else { - m->sync_file_index = m->file_index; - m->sync_stream_index = m->stream_index; - } - return 0; -} - -static void parse_meta_type(char *arg, char *type, int *index, char **endptr) -{ - *endptr = arg; - if (*arg == ',') { - *type = *(++arg); - switch (*arg) { - case 'g': - break; - case 's': - case 'c': - case 'p': - *index = strtol(++arg, endptr, 0); - break; - default: - fprintf(stderr, "Invalid metadata type %c.\n", *arg); - exit_program(1); - } - } else - *type = 'g'; -} - -static int opt_map_metadata(const char *opt, const char *arg) -{ - MetadataMap *m, *m1; - char *p; - - meta_data_maps = grow_array(meta_data_maps, sizeof(*meta_data_maps), - &nb_meta_data_maps, nb_meta_data_maps + 1); - - m = &meta_data_maps[nb_meta_data_maps - 1][0]; - m->file = strtol(arg, &p, 0); - parse_meta_type(p, &m->type, &m->index, &p); - if (*p) - p++; - - m1 = &meta_data_maps[nb_meta_data_maps - 1][1]; - m1->file = strtol(p, &p, 0); - parse_meta_type(p, &m1->type, &m1->index, &p); - - if (m->type == 'g' || m1->type == 'g') - metadata_global_autocopy = 0; - if (m->type == 's' || m1->type == 's') - metadata_streams_autocopy = 0; - if (m->type == 'c' || m1->type == 'c') - metadata_chapters_autocopy = 0; - - return 0; -} - -static int opt_map_meta_data(const char *opt, const char *arg) -{ - fprintf(stderr, "-map_meta_data is deprecated and will be removed soon. " - "Use -map_metadata instead.\n"); - return opt_map_metadata(opt, arg); -} - -static int opt_map_chapters(const char *opt, const char *arg) -{ - ChapterMap *c; - char *p; - - chapter_maps = grow_array(chapter_maps, sizeof(*chapter_maps), &nb_chapter_maps, - nb_chapter_maps + 1); - c = &chapter_maps[nb_chapter_maps - 1]; - c->out_file = strtol(arg, &p, 0); - if (*p) - p++; - - c->in_file = strtol(p, &p, 0); - return 0; -} - -static int opt_input_ts_scale(const char *opt, const char *arg) -{ - unsigned int stream; - double scale; - char *p; - - stream = strtol(arg, &p, 0); - if (*p) - p++; - scale= strtod(p, &p); - - ts_scale = grow_array(ts_scale, sizeof(*ts_scale), &nb_ts_scale, stream + 1); - ts_scale[stream] = scale; - return 0; -} - -static int opt_recording_time(const char *opt, const char *arg) -{ - recording_time = parse_time_or_die(opt, arg, 1); - return 0; -} - -static int opt_start_time(const char *opt, const char *arg) -{ - start_time = parse_time_or_die(opt, arg, 1); - return 0; -} - -static int opt_recording_timestamp(const char *opt, const char *arg) -{ - char buf[128]; - int64_t recording_timestamp = parse_time_or_die(opt, arg, 0) / 1E6; - struct tm time = *gmtime((time_t*)&recording_timestamp); - strftime(buf, sizeof(buf), "creation_time=%FT%T%z", &time); - opt_metadata("metadata", buf); - - av_log(NULL, AV_LOG_WARNING, "%s is deprecated, set the 'creation_time' metadata " - "tag instead.\n", opt); - return 0; -} - -static int opt_input_ts_offset(const char *opt, const char *arg) -{ - input_ts_offset = parse_time_or_die(opt, arg, 1); - return 0; -} - -static enum CodecID find_codec_or_die(const char *name, int type, int encoder) -{ - const char *codec_string = encoder ? "encoder" : "decoder"; - AVCodec *codec; - - if(!name) - return CODEC_ID_NONE; - codec = encoder ? - avcodec_find_encoder_by_name(name) : - avcodec_find_decoder_by_name(name); - if(!codec) { - fprintf(stderr, "Unknown %s '%s'\n", codec_string, name); - exit_program(1); - } - if(codec->type != type) { - fprintf(stderr, "Invalid %s type '%s'\n", codec_string, name); - exit_program(1); - } - return codec->id; -} - -static int opt_input_file(const char *opt, const char *filename) -{ - AVFormatContext *ic; - AVInputFormat *file_iformat = NULL; - int err, i, ret, rfps, rfps_base; - int64_t timestamp; - uint8_t buf[128]; - AVDictionary **opts; - int orig_nb_streams; // number of streams before avformat_find_stream_info - - if (last_asked_format) { - if (!(file_iformat = av_find_input_format(last_asked_format))) { - fprintf(stderr, "Unknown input format: '%s'\n", last_asked_format); - exit_program(1); - } - last_asked_format = NULL; - } - - if (!strcmp(filename, "-")) - filename = "pipe:"; - - using_stdin |= !strncmp(filename, "pipe:", 5) || - !strcmp(filename, "/dev/stdin"); - - /* get default parameters from command line */ - ic = avformat_alloc_context(); - if (!ic) { - print_error(filename, AVERROR(ENOMEM)); - exit_program(1); - } - if (audio_sample_rate) { - snprintf(buf, sizeof(buf), "%d", audio_sample_rate); - av_dict_set(&format_opts, "sample_rate", buf, 0); - } - if (audio_channels) { - snprintf(buf, sizeof(buf), "%d", audio_channels); - av_dict_set(&format_opts, "channels", buf, 0); - } - if (frame_rate.num) { - snprintf(buf, sizeof(buf), "%d/%d", frame_rate.num, frame_rate.den); - av_dict_set(&format_opts, "framerate", buf, 0); - } - if (frame_width && frame_height) { - snprintf(buf, sizeof(buf), "%dx%d", frame_width, frame_height); - av_dict_set(&format_opts, "video_size", buf, 0); - } - if (frame_pix_fmt != PIX_FMT_NONE) - av_dict_set(&format_opts, "pixel_format", av_get_pix_fmt_name(frame_pix_fmt), 0); - - ic->video_codec_id = - find_codec_or_die(video_codec_name , AVMEDIA_TYPE_VIDEO , 0); - ic->audio_codec_id = - find_codec_or_die(audio_codec_name , AVMEDIA_TYPE_AUDIO , 0); - ic->subtitle_codec_id= - find_codec_or_die(subtitle_codec_name, AVMEDIA_TYPE_SUBTITLE, 0); - ic->flags |= AVFMT_FLAG_NONBLOCK; - - /* open the input file with generic libav function */ - err = avformat_open_input(&ic, filename, file_iformat, &format_opts); - if (err < 0) { - print_error(filename, err); - exit_program(1); - } - assert_avoptions(format_opts); - - if(opt_programid) { - int i, j; - int found=0; - for(i=0; inb_streams; i++){ - ic->streams[i]->discard= AVDISCARD_ALL; - } - for(i=0; inb_programs; i++){ - AVProgram *p= ic->programs[i]; - if(p->id != opt_programid){ - p->discard = AVDISCARD_ALL; - }else{ - found=1; - for(j=0; jnb_stream_indexes; j++){ - ic->streams[p->stream_index[j]]->discard= AVDISCARD_DEFAULT; - } - } - } - if(!found){ - fprintf(stderr, "Specified program id not found\n"); - exit_program(1); - } - opt_programid=0; - } - - if (loop_input) { - av_log(NULL, AV_LOG_WARNING, "-loop_input is deprecated, use -loop 1\n"); - ic->loop_input = loop_input; - } - - /* Set AVCodecContext options for avformat_find_stream_info */ - opts = setup_find_stream_info_opts(ic, codec_opts); - orig_nb_streams = ic->nb_streams; - - /* If not enough info to get the stream parameters, we decode the - first frames to get it. (used in mpeg case for example) */ - ret = avformat_find_stream_info(ic, opts); - if (ret < 0 && verbose >= 0) { - fprintf(stderr, "%s: could not find codec parameters\n", filename); - av_close_input_file(ic); - exit_program(1); - } - - timestamp = start_time; - /* add the stream start time */ - if (ic->start_time != AV_NOPTS_VALUE) - timestamp += ic->start_time; - - /* if seeking requested, we execute it */ - if (start_time != 0) { - ret = av_seek_frame(ic, -1, timestamp, AVSEEK_FLAG_BACKWARD); - if (ret < 0) { - fprintf(stderr, "%s: could not seek to position %0.3f\n", - filename, (double)timestamp / AV_TIME_BASE); - } - /* reset seek info */ - start_time = 0; - } - - /* update the current parameters so that they match the one of the input stream */ - for(i=0;inb_streams;i++) { - AVStream *st = ic->streams[i]; - AVCodecContext *dec = st->codec; - InputStream *ist; - - dec->thread_count = thread_count; - - input_streams = grow_array(input_streams, sizeof(*input_streams), &nb_input_streams, nb_input_streams + 1); - ist = &input_streams[nb_input_streams - 1]; - ist->st = st; - ist->file_index = nb_input_files; - ist->discard = 1; - ist->opts = filter_codec_opts(codec_opts, ist->st->codec->codec_id, ic, st); - - if (i < nb_ts_scale) - ist->ts_scale = ts_scale[i]; - - switch (dec->codec_type) { - case AVMEDIA_TYPE_AUDIO: - ist->dec = avcodec_find_decoder_by_name(audio_codec_name); - if(audio_disable) - st->discard= AVDISCARD_ALL; - break; - case AVMEDIA_TYPE_VIDEO: - ist->dec = avcodec_find_decoder_by_name(video_codec_name); - rfps = ic->streams[i]->r_frame_rate.num; - rfps_base = ic->streams[i]->r_frame_rate.den; - if (dec->lowres) { - dec->flags |= CODEC_FLAG_EMU_EDGE; - dec->height >>= dec->lowres; - dec->width >>= dec->lowres; - } - if(me_threshold) - dec->debug |= FF_DEBUG_MV; - - if (dec->time_base.den != rfps*dec->ticks_per_frame || dec->time_base.num != rfps_base) { - - if (verbose >= 0) - fprintf(stderr,"\nSeems stream %d codec frame rate differs from container frame rate: %2.2f (%d/%d) -> %2.2f (%d/%d)\n", - i, (float)dec->time_base.den / dec->time_base.num, dec->time_base.den, dec->time_base.num, - - (float)rfps / rfps_base, rfps, rfps_base); - } - - if(video_disable) - st->discard= AVDISCARD_ALL; - else if(video_discard) - st->discard= video_discard; - break; - case AVMEDIA_TYPE_DATA: - break; - case AVMEDIA_TYPE_SUBTITLE: - ist->dec = avcodec_find_decoder_by_name(subtitle_codec_name); - if(subtitle_disable) - st->discard = AVDISCARD_ALL; - break; - case AVMEDIA_TYPE_ATTACHMENT: - case AVMEDIA_TYPE_UNKNOWN: - break; - default: - abort(); - } - } - - /* dump the file content */ - if (verbose >= 0) - av_dump_format(ic, nb_input_files, filename, 0); - - input_files = grow_array(input_files, sizeof(*input_files), &nb_input_files, nb_input_files + 1); - input_files[nb_input_files - 1].ctx = ic; - input_files[nb_input_files - 1].ist_index = nb_input_streams - ic->nb_streams; - input_files[nb_input_files - 1].ts_offset = input_ts_offset - (copy_ts ? 0 : timestamp); - input_files[nb_input_files - 1].nb_streams = ic->nb_streams; - - frame_rate = (AVRational){0, 0}; - frame_pix_fmt = PIX_FMT_NONE; - frame_height = 0; - frame_width = 0; - audio_sample_rate = 0; - audio_channels = 0; - audio_sample_fmt = AV_SAMPLE_FMT_NONE; - av_freep(&ts_scale); - nb_ts_scale = 0; - - for (i = 0; i < orig_nb_streams; i++) - av_dict_free(&opts[i]); - av_freep(&opts); - av_freep(&video_codec_name); - av_freep(&audio_codec_name); - av_freep(&subtitle_codec_name); - uninit_opts(); - init_opts(); - return 0; -} - -static void check_inputs(int *has_video_ptr, - int *has_audio_ptr, - int *has_subtitle_ptr, - int *has_data_ptr) -{ - int has_video, has_audio, has_subtitle, has_data, i, j; - AVFormatContext *ic; - - has_video = 0; - has_audio = 0; - has_subtitle = 0; - has_data = 0; - - for(j=0;jnb_streams;i++) { - AVCodecContext *enc = ic->streams[i]->codec; - switch(enc->codec_type) { - case AVMEDIA_TYPE_AUDIO: - has_audio = 1; - break; - case AVMEDIA_TYPE_VIDEO: - has_video = 1; - break; - case AVMEDIA_TYPE_SUBTITLE: - has_subtitle = 1; - break; - case AVMEDIA_TYPE_DATA: - case AVMEDIA_TYPE_ATTACHMENT: - case AVMEDIA_TYPE_UNKNOWN: - has_data = 1; - break; - default: - abort(); - } - } - } - *has_video_ptr = has_video; - *has_audio_ptr = has_audio; - *has_subtitle_ptr = has_subtitle; - *has_data_ptr = has_data; -} - -static void new_video_stream(AVFormatContext *oc, int file_idx) -{ - AVStream *st; - OutputStream *ost; - AVCodecContext *video_enc; - enum CodecID codec_id = CODEC_ID_NONE; - AVCodec *codec= NULL; - - if(!video_stream_copy){ - if (video_codec_name) { - codec_id = find_codec_or_die(video_codec_name, AVMEDIA_TYPE_VIDEO, 1); - codec = avcodec_find_encoder_by_name(video_codec_name); - } else { - codec_id = av_guess_codec(oc->oformat, NULL, oc->filename, NULL, AVMEDIA_TYPE_VIDEO); - codec = avcodec_find_encoder(codec_id); - } - } - - ost = new_output_stream(oc, file_idx, codec); - st = ost->st; - if (!video_stream_copy) { - ost->frame_aspect_ratio = frame_aspect_ratio; - frame_aspect_ratio = 0; -#if CONFIG_AVFILTER - ost->avfilter= vfilters; - vfilters = NULL; -#endif - } - - ost->bitstream_filters = video_bitstream_filters; - video_bitstream_filters= NULL; - - st->codec->thread_count= thread_count; - - video_enc = st->codec; - - if(video_codec_tag) - video_enc->codec_tag= video_codec_tag; - - if(oc->oformat->flags & AVFMT_GLOBALHEADER) { - video_enc->flags |= CODEC_FLAG_GLOBAL_HEADER; - } - - video_enc->codec_type = AVMEDIA_TYPE_VIDEO; - if (video_stream_copy) { - st->stream_copy = 1; - video_enc->sample_aspect_ratio = - st->sample_aspect_ratio = av_d2q(frame_aspect_ratio*frame_height/frame_width, 255); - } else { - const char *p; - int i; - - if (frame_rate.num) - ost->frame_rate = frame_rate; - video_enc->codec_id = codec_id; - - video_enc->width = frame_width; - video_enc->height = frame_height; - video_enc->pix_fmt = frame_pix_fmt; - st->sample_aspect_ratio = video_enc->sample_aspect_ratio; - - if (intra_only) - video_enc->gop_size = 0; - if (video_qscale || same_quality) { - video_enc->flags |= CODEC_FLAG_QSCALE; - video_enc->global_quality = FF_QP2LAMBDA * video_qscale; - } - - if(intra_matrix) - video_enc->intra_matrix = intra_matrix; - if(inter_matrix) - video_enc->inter_matrix = inter_matrix; - - p= video_rc_override_string; - for(i=0; p; i++){ - int start, end, q; - int e=sscanf(p, "%d,%d,%d", &start, &end, &q); - if(e!=3){ - fprintf(stderr, "error parsing rc_override\n"); - exit_program(1); - } - video_enc->rc_override= - av_realloc(video_enc->rc_override, - sizeof(RcOverride)*(i+1)); - video_enc->rc_override[i].start_frame= start; - video_enc->rc_override[i].end_frame = end; - if(q>0){ - video_enc->rc_override[i].qscale= q; - video_enc->rc_override[i].quality_factor= 1.0; - } - else{ - video_enc->rc_override[i].qscale= 0; - video_enc->rc_override[i].quality_factor= -q/100.0; - } - p= strchr(p, '/'); - if(p) p++; - } - video_enc->rc_override_count=i; - if (!video_enc->rc_initial_buffer_occupancy) - video_enc->rc_initial_buffer_occupancy = video_enc->rc_buffer_size*3/4; - video_enc->me_threshold= me_threshold; - video_enc->intra_dc_precision= intra_dc_precision - 8; - - if (do_psnr) - video_enc->flags|= CODEC_FLAG_PSNR; - - /* two pass mode */ - if (do_pass) { - if (do_pass == 1) { - video_enc->flags |= CODEC_FLAG_PASS1; - } else { - video_enc->flags |= CODEC_FLAG_PASS2; - } - } - - if (forced_key_frames) - parse_forced_key_frames(forced_key_frames, ost, video_enc); - } - if (video_language) { - av_dict_set(&st->metadata, "language", video_language, 0); - av_freep(&video_language); - } - - /* reset some key parameters */ - video_disable = 0; - av_freep(&video_codec_name); - av_freep(&forced_key_frames); - video_stream_copy = 0; - frame_pix_fmt = PIX_FMT_NONE; -} - -static void new_audio_stream(AVFormatContext *oc, int file_idx) -{ - AVStream *st; - OutputStream *ost; - AVCodec *codec= NULL; - AVCodecContext *audio_enc; - enum CodecID codec_id = CODEC_ID_NONE; - - if(!audio_stream_copy){ - if (audio_codec_name) { - codec_id = find_codec_or_die(audio_codec_name, AVMEDIA_TYPE_AUDIO, 1); - codec = avcodec_find_encoder_by_name(audio_codec_name); - } else { - codec_id = av_guess_codec(oc->oformat, NULL, oc->filename, NULL, AVMEDIA_TYPE_AUDIO); - codec = avcodec_find_encoder(codec_id); - } - } - ost = new_output_stream(oc, file_idx, codec); - st = ost->st; - - ost->bitstream_filters = audio_bitstream_filters; - audio_bitstream_filters= NULL; - - st->codec->thread_count= thread_count; - - audio_enc = st->codec; - audio_enc->codec_type = AVMEDIA_TYPE_AUDIO; - - if(audio_codec_tag) - audio_enc->codec_tag= audio_codec_tag; - - if (oc->oformat->flags & AVFMT_GLOBALHEADER) { - audio_enc->flags |= CODEC_FLAG_GLOBAL_HEADER; - } - if (audio_stream_copy) { - st->stream_copy = 1; - } else { - audio_enc->codec_id = codec_id; - - if (audio_qscale > QSCALE_NONE) { - audio_enc->flags |= CODEC_FLAG_QSCALE; - audio_enc->global_quality = FF_QP2LAMBDA * audio_qscale; - } - if (audio_channels) - audio_enc->channels = audio_channels; - if (audio_sample_fmt != AV_SAMPLE_FMT_NONE) - audio_enc->sample_fmt = audio_sample_fmt; - if (audio_sample_rate) - audio_enc->sample_rate = audio_sample_rate; - } - if (audio_language) { - av_dict_set(&st->metadata, "language", audio_language, 0); - av_freep(&audio_language); - } - - /* reset some key parameters */ - audio_disable = 0; - av_freep(&audio_codec_name); - audio_stream_copy = 0; -} - -static void new_data_stream(AVFormatContext *oc, int file_idx) -{ - AVStream *st; - OutputStream *ost; - AVCodecContext *data_enc; - - ost = new_output_stream(oc, file_idx, NULL); - st = ost->st; - data_enc = st->codec; - if (!data_stream_copy) { - fprintf(stderr, "Data stream encoding not supported yet (only streamcopy)\n"); - exit_program(1); - } - - data_enc->codec_type = AVMEDIA_TYPE_DATA; - - if (data_codec_tag) - data_enc->codec_tag= data_codec_tag; - - if (oc->oformat->flags & AVFMT_GLOBALHEADER) { - data_enc->flags |= CODEC_FLAG_GLOBAL_HEADER; - } - if (data_stream_copy) { - st->stream_copy = 1; - } - - data_disable = 0; - av_freep(&data_codec_name); - data_stream_copy = 0; -} - -static void new_subtitle_stream(AVFormatContext *oc, int file_idx) -{ - AVStream *st; - OutputStream *ost; - AVCodec *codec=NULL; - AVCodecContext *subtitle_enc; - enum CodecID codec_id = CODEC_ID_NONE; - - if(!subtitle_stream_copy){ - if (subtitle_codec_name) { - codec_id = find_codec_or_die(subtitle_codec_name, AVMEDIA_TYPE_SUBTITLE, 1); - codec = avcodec_find_encoder_by_name(subtitle_codec_name); - } else { - codec_id = av_guess_codec(oc->oformat, NULL, oc->filename, NULL, AVMEDIA_TYPE_SUBTITLE); - codec = avcodec_find_encoder(codec_id); - } - } - ost = new_output_stream(oc, file_idx, codec); - st = ost->st; - subtitle_enc = st->codec; - - ost->bitstream_filters = subtitle_bitstream_filters; - subtitle_bitstream_filters= NULL; - - subtitle_enc->codec_type = AVMEDIA_TYPE_SUBTITLE; - - if(subtitle_codec_tag) - subtitle_enc->codec_tag= subtitle_codec_tag; - - if (oc->oformat->flags & AVFMT_GLOBALHEADER) { - subtitle_enc->flags |= CODEC_FLAG_GLOBAL_HEADER; - } - if (subtitle_stream_copy) { - st->stream_copy = 1; - } else { - subtitle_enc->codec_id = codec_id; - } - - if (subtitle_language) { - av_dict_set(&st->metadata, "language", subtitle_language, 0); - av_freep(&subtitle_language); - } - - subtitle_disable = 0; - av_freep(&subtitle_codec_name); - subtitle_stream_copy = 0; -} - -static int opt_new_stream(const char *opt, const char *arg) -{ - AVFormatContext *oc; - int file_idx = nb_output_files - 1; - if (nb_output_files <= 0) { - fprintf(stderr, "At least one output file must be specified\n"); - exit_program(1); - } - oc = output_files[file_idx]; - - if (!strcmp(opt, "newvideo" )) new_video_stream (oc, file_idx); - else if (!strcmp(opt, "newaudio" )) new_audio_stream (oc, file_idx); - else if (!strcmp(opt, "newsubtitle")) new_subtitle_stream(oc, file_idx); - else if (!strcmp(opt, "newdata" )) new_data_stream (oc, file_idx); - else av_assert0(0); - return 0; -} - -/* arg format is "output-stream-index:streamid-value". */ -static int opt_streamid(const char *opt, const char *arg) -{ - int idx; - char *p; - char idx_str[16]; - - av_strlcpy(idx_str, arg, sizeof(idx_str)); - p = strchr(idx_str, ':'); - if (!p) { - fprintf(stderr, - "Invalid value '%s' for option '%s', required syntax is 'index:value'\n", - arg, opt); - exit_program(1); - } - *p++ = '\0'; - idx = parse_number_or_die(opt, idx_str, OPT_INT, 0, INT_MAX); - streamid_map = grow_array(streamid_map, sizeof(*streamid_map), &nb_streamid_map, idx+1); - streamid_map[idx] = parse_number_or_die(opt, p, OPT_INT, 0, INT_MAX); - return 0; -} - -static void opt_output_file(void *optctx, const char *filename) -{ - AVFormatContext *oc; - int err, use_video, use_audio, use_subtitle, use_data; - int input_has_video, input_has_audio, input_has_subtitle, input_has_data; - AVOutputFormat *file_oformat; - - if (!strcmp(filename, "-")) - filename = "pipe:"; - - oc = avformat_alloc_context(); - if (!oc) { - print_error(filename, AVERROR(ENOMEM)); - exit_program(1); - } - - if (last_asked_format) { - file_oformat = av_guess_format(last_asked_format, NULL, NULL); - if (!file_oformat) { - fprintf(stderr, "Requested output format '%s' is not a suitable output format\n", last_asked_format); - exit_program(1); - } - last_asked_format = NULL; - } else { - file_oformat = av_guess_format(NULL, filename, NULL); - if (!file_oformat) { - fprintf(stderr, "Unable to find a suitable output format for '%s'\n", - filename); - exit_program(1); - } - } - - oc->oformat = file_oformat; - av_strlcpy(oc->filename, filename, sizeof(oc->filename)); - - if (!strcmp(file_oformat->name, "ffm") && - av_strstart(filename, "http:", NULL)) { - /* special case for files sent to avserver: we get the stream - parameters from avserver */ - int err = read_avserver_streams(oc, filename); - if (err < 0) { - print_error(filename, err); - exit_program(1); - } - } else { - use_video = file_oformat->video_codec != CODEC_ID_NONE || video_stream_copy || video_codec_name; - use_audio = file_oformat->audio_codec != CODEC_ID_NONE || audio_stream_copy || audio_codec_name; - use_subtitle = file_oformat->subtitle_codec != CODEC_ID_NONE || subtitle_stream_copy || subtitle_codec_name; - use_data = data_stream_copy || data_codec_name; /* XXX once generic data codec will be available add a ->data_codec reference and use it here */ - - /* disable if no corresponding type found */ - check_inputs(&input_has_video, - &input_has_audio, - &input_has_subtitle, - &input_has_data); - - if (!input_has_video) - use_video = 0; - if (!input_has_audio) - use_audio = 0; - if (!input_has_subtitle) - use_subtitle = 0; - if (!input_has_data) - use_data = 0; - - /* manual disable */ - if (audio_disable) use_audio = 0; - if (video_disable) use_video = 0; - if (subtitle_disable) use_subtitle = 0; - if (data_disable) use_data = 0; - - if (use_video) new_video_stream(oc, nb_output_files); - if (use_audio) new_audio_stream(oc, nb_output_files); - if (use_subtitle) new_subtitle_stream(oc, nb_output_files); - if (use_data) new_data_stream(oc, nb_output_files); - - av_dict_copy(&oc->metadata, metadata, 0); - av_dict_free(&metadata); - } - - av_dict_copy(&output_opts[nb_output_files], format_opts, 0); - output_files[nb_output_files++] = oc; - - /* check filename in case of an image number is expected */ - if (oc->oformat->flags & AVFMT_NEEDNUMBER) { - if (!av_filename_number_test(oc->filename)) { - print_error(oc->filename, AVERROR(EINVAL)); - exit_program(1); - } - } - - if (!(oc->oformat->flags & AVFMT_NOFILE)) { - /* test if it already exists to avoid losing precious files */ - if (!file_overwrite && - (strchr(filename, ':') == NULL || - filename[1] == ':' || - av_strstart(filename, "file:", NULL))) { - if (avio_check(filename, 0) == 0) { - if (!using_stdin) { - fprintf(stderr,"File '%s' already exists. Overwrite ? [y/N] ", filename); - fflush(stderr); - if (!read_yesno()) { - fprintf(stderr, "Not overwriting - exiting\n"); - exit_program(1); - } - } - else { - fprintf(stderr,"File '%s' already exists. Exiting.\n", filename); - exit_program(1); - } - } - } - - /* open the file */ - if ((err = avio_open(&oc->pb, filename, AVIO_FLAG_WRITE)) < 0) { - print_error(filename, err); - exit_program(1); - } - } - - oc->preload= (int)(mux_preload*AV_TIME_BASE); - oc->max_delay= (int)(mux_max_delay*AV_TIME_BASE); - if (loop_output >= 0) { - av_log(NULL, AV_LOG_WARNING, "-loop_output is deprecated, use -loop\n"); - oc->loop_output = loop_output; - } - oc->flags |= AVFMT_FLAG_NONBLOCK; - - frame_rate = (AVRational){0, 0}; - frame_width = 0; - frame_height = 0; - audio_sample_rate = 0; - audio_channels = 0; - audio_sample_fmt = AV_SAMPLE_FMT_NONE; - - av_freep(&forced_key_frames); - uninit_opts(); - init_opts(); -} - -/* same option as mencoder */ -static int opt_pass(const char *opt, const char *arg) -{ - do_pass = parse_number_or_die(opt, arg, OPT_INT, 1, 2); - return 0; -} - -static int64_t getutime(void) -{ -#if HAVE_GETRUSAGE - struct rusage rusage; - - getrusage(RUSAGE_SELF, &rusage); - return (rusage.ru_utime.tv_sec * 1000000LL) + rusage.ru_utime.tv_usec; -#elif HAVE_GETPROCESSTIMES - HANDLE proc; - FILETIME c, e, k, u; - proc = GetCurrentProcess(); - GetProcessTimes(proc, &c, &e, &k, &u); - return ((int64_t) u.dwHighDateTime << 32 | u.dwLowDateTime) / 10; -#else - return av_gettime(); -#endif -} - -static int64_t getmaxrss(void) -{ -#if HAVE_GETRUSAGE && HAVE_STRUCT_RUSAGE_RU_MAXRSS - struct rusage rusage; - getrusage(RUSAGE_SELF, &rusage); - return (int64_t)rusage.ru_maxrss * 1024; -#elif HAVE_GETPROCESSMEMORYINFO - HANDLE proc; - PROCESS_MEMORY_COUNTERS memcounters; - proc = GetCurrentProcess(); - memcounters.cb = sizeof(memcounters); - GetProcessMemoryInfo(proc, &memcounters, sizeof(memcounters)); - return memcounters.PeakPagefileUsage; -#else - return 0; -#endif -} - -static void parse_matrix_coeffs(uint16_t *dest, const char *str) -{ - int i; - const char *p = str; - for(i = 0;; i++) { - dest[i] = atoi(p); - if(i == 63) - break; - p = strchr(p, ','); - if(!p) { - fprintf(stderr, "Syntax error in matrix \"%s\" at coeff %d\n", str, i); - exit_program(1); - } - p++; - } -} - -static void opt_inter_matrix(const char *arg) -{ - inter_matrix = av_mallocz(sizeof(uint16_t) * 64); - parse_matrix_coeffs(inter_matrix, arg); -} - -static void opt_intra_matrix(const char *arg) -{ - intra_matrix = av_mallocz(sizeof(uint16_t) * 64); - parse_matrix_coeffs(intra_matrix, arg); -} - -static void show_usage(void) -{ - printf("Hyper fast Audio and Video encoder\n"); - printf("usage: ffmpeg [options] [[infile options] -i infile]... {[outfile options] outfile}...\n"); - printf("\n"); -} - -static void show_help(void) -{ - AVCodec *c; - AVOutputFormat *oformat = NULL; - AVInputFormat *iformat = NULL; - const AVClass *class; - - av_log_set_callback(log_callback_help); - show_usage(); - show_help_options(options, "Main options:\n", - OPT_EXPERT | OPT_AUDIO | OPT_VIDEO | OPT_SUBTITLE | OPT_GRAB, 0); - show_help_options(options, "\nAdvanced options:\n", - OPT_EXPERT | OPT_AUDIO | OPT_VIDEO | OPT_SUBTITLE | OPT_GRAB, - OPT_EXPERT); - show_help_options(options, "\nVideo options:\n", - OPT_EXPERT | OPT_AUDIO | OPT_VIDEO | OPT_GRAB, - OPT_VIDEO); - show_help_options(options, "\nAdvanced Video options:\n", - OPT_EXPERT | OPT_AUDIO | OPT_VIDEO | OPT_GRAB, - OPT_VIDEO | OPT_EXPERT); - show_help_options(options, "\nAudio options:\n", - OPT_EXPERT | OPT_AUDIO | OPT_VIDEO | OPT_GRAB, - OPT_AUDIO); - show_help_options(options, "\nAdvanced Audio options:\n", - OPT_EXPERT | OPT_AUDIO | OPT_VIDEO | OPT_GRAB, - OPT_AUDIO | OPT_EXPERT); - show_help_options(options, "\nSubtitle options:\n", - OPT_SUBTITLE | OPT_GRAB, - OPT_SUBTITLE); - show_help_options(options, "\nAudio/Video grab options:\n", - OPT_GRAB, - OPT_GRAB); - printf("\n"); - class = avcodec_get_class(); - av_opt_show2(&class, NULL, AV_OPT_FLAG_ENCODING_PARAM|AV_OPT_FLAG_DECODING_PARAM, 0); - printf("\n"); - - /* individual codec options */ - c = NULL; - while ((c = av_codec_next(c))) { - if (c->priv_class) { - av_opt_show2(&c->priv_class, NULL, AV_OPT_FLAG_ENCODING_PARAM|AV_OPT_FLAG_DECODING_PARAM, 0); - printf("\n"); - } - } - - class = avformat_get_class(); - av_opt_show2(&class, NULL, AV_OPT_FLAG_ENCODING_PARAM|AV_OPT_FLAG_DECODING_PARAM, 0); - printf("\n"); - - /* individual muxer options */ - while ((oformat = av_oformat_next(oformat))) { - if (oformat->priv_class) { - av_opt_show2(&oformat->priv_class, NULL, AV_OPT_FLAG_ENCODING_PARAM, 0); - printf("\n"); - } - } - - /* individual demuxer options */ - while ((iformat = av_iformat_next(iformat))) { - if (iformat->priv_class) { - av_opt_show2(&iformat->priv_class, NULL, AV_OPT_FLAG_DECODING_PARAM, 0); - printf("\n"); - } - } - - class = sws_get_class(); - av_opt_show2(&class, NULL, AV_OPT_FLAG_ENCODING_PARAM|AV_OPT_FLAG_DECODING_PARAM, 0); -} - -static int opt_target(const char *opt, const char *arg) -{ - enum { PAL, NTSC, FILM, UNKNOWN } norm = UNKNOWN; - static const char *const frame_rates[] = {"25", "30000/1001", "24000/1001"}; - - if(!strncmp(arg, "pal-", 4)) { - norm = PAL; - arg += 4; - } else if(!strncmp(arg, "ntsc-", 5)) { - norm = NTSC; - arg += 5; - } else if(!strncmp(arg, "film-", 5)) { - norm = FILM; - arg += 5; - } else { - int fr; - /* Calculate FR via float to avoid int overflow */ - fr = (int)(frame_rate.num * 1000.0 / frame_rate.den); - if(fr == 25000) { - norm = PAL; - } else if((fr == 29970) || (fr == 23976)) { - norm = NTSC; - } else { - /* Try to determine PAL/NTSC by peeking in the input files */ - if(nb_input_files) { - int i, j; - for (j = 0; j < nb_input_files; j++) { - for (i = 0; i < input_files[j].ctx->nb_streams; i++) { - AVCodecContext *c = input_files[j].ctx->streams[i]->codec; - if(c->codec_type != AVMEDIA_TYPE_VIDEO) - continue; - fr = c->time_base.den * 1000 / c->time_base.num; - if(fr == 25000) { - norm = PAL; - break; - } else if((fr == 29970) || (fr == 23976)) { - norm = NTSC; - break; - } - } - if(norm != UNKNOWN) - break; - } - } - } - if(verbose > 0 && norm != UNKNOWN) - fprintf(stderr, "Assuming %s for target.\n", norm == PAL ? "PAL" : "NTSC"); - } - - if(norm == UNKNOWN) { - fprintf(stderr, "Could not determine norm (PAL/NTSC/NTSC-Film) for target.\n"); - fprintf(stderr, "Please prefix target with \"pal-\", \"ntsc-\" or \"film-\",\n"); - fprintf(stderr, "or set a framerate with \"-r xxx\".\n"); - exit_program(1); - } - - if(!strcmp(arg, "vcd")) { - opt_video_codec("vcodec", "mpeg1video"); - opt_audio_codec("vcodec", "mp2"); - opt_format("f", "vcd"); - - opt_frame_size("s", norm == PAL ? "352x288" : "352x240"); - opt_frame_rate("r", frame_rates[norm]); - opt_default("g", norm == PAL ? "15" : "18"); - - opt_default("b", "1150000"); - opt_default("maxrate", "1150000"); - opt_default("minrate", "1150000"); - opt_default("bufsize", "327680"); // 40*1024*8; - - opt_default("ab", "224000"); - audio_sample_rate = 44100; - audio_channels = 2; - - opt_default("packetsize", "2324"); - opt_default("muxrate", "1411200"); // 2352 * 75 * 8; - - /* We have to offset the PTS, so that it is consistent with the SCR. - SCR starts at 36000, but the first two packs contain only padding - and the first pack from the other stream, respectively, may also have - been written before. - So the real data starts at SCR 36000+3*1200. */ - mux_preload= (36000+3*1200) / 90000.0; //0.44 - } else if(!strcmp(arg, "svcd")) { - - opt_video_codec("vcodec", "mpeg2video"); - opt_audio_codec("acodec", "mp2"); - opt_format("f", "svcd"); - - opt_frame_size("s", norm == PAL ? "480x576" : "480x480"); - opt_frame_rate("r", frame_rates[norm]); - opt_default("g", norm == PAL ? "15" : "18"); - - opt_default("b", "2040000"); - opt_default("maxrate", "2516000"); - opt_default("minrate", "0"); //1145000; - opt_default("bufsize", "1835008"); //224*1024*8; - opt_default("flags", "+scan_offset"); - - - opt_default("ab", "224000"); - audio_sample_rate = 44100; - - opt_default("packetsize", "2324"); - - } else if(!strcmp(arg, "dvd")) { - - opt_video_codec("vcodec", "mpeg2video"); - opt_audio_codec("vcodec", "ac3"); - opt_format("f", "dvd"); - - opt_frame_size("vcodec", norm == PAL ? "720x576" : "720x480"); - opt_frame_rate("r", frame_rates[norm]); - opt_default("g", norm == PAL ? "15" : "18"); - - opt_default("b", "6000000"); - opt_default("maxrate", "9000000"); - opt_default("minrate", "0"); //1500000; - opt_default("bufsize", "1835008"); //224*1024*8; - - opt_default("packetsize", "2048"); // from www.mpucoder.com: DVD sectors contain 2048 bytes of data, this is also the size of one pack. - opt_default("muxrate", "10080000"); // from mplex project: data_rate = 1260000. mux_rate = data_rate * 8 - - opt_default("ab", "448000"); - audio_sample_rate = 48000; - - } else if(!strncmp(arg, "dv", 2)) { - - opt_format("f", "dv"); - - opt_frame_size("s", norm == PAL ? "720x576" : "720x480"); - opt_frame_pix_fmt("pix_fmt", !strncmp(arg, "dv50", 4) ? "yuv422p" : - norm == PAL ? "yuv420p" : "yuv411p"); - opt_frame_rate("r", frame_rates[norm]); - - audio_sample_rate = 48000; - audio_channels = 2; - - } else { - fprintf(stderr, "Unknown target: %s\n", arg); - return AVERROR(EINVAL); - } - return 0; -} - -static int opt_vstats_file(const char *opt, const char *arg) -{ - av_free (vstats_filename); - vstats_filename=av_strdup (arg); - return 0; -} - -static int opt_vstats(const char *opt, const char *arg) -{ - char filename[40]; - time_t today2 = time(NULL); - struct tm *today = localtime(&today2); - - snprintf(filename, sizeof(filename), "vstats_%02d%02d%02d.log", today->tm_hour, today->tm_min, - today->tm_sec); - return opt_vstats_file(opt, filename); -} - -static int opt_bsf(const char *opt, const char *arg) -{ - AVBitStreamFilterContext *bsfc= av_bitstream_filter_init(arg); //FIXME split name and args for filter at '=' - AVBitStreamFilterContext **bsfp; - - if(!bsfc){ - fprintf(stderr, "Unknown bitstream filter %s\n", arg); - exit_program(1); - } - - bsfp= *opt == 'v' ? &video_bitstream_filters : - *opt == 'a' ? &audio_bitstream_filters : - &subtitle_bitstream_filters; - while(*bsfp) - bsfp= &(*bsfp)->next; - - *bsfp= bsfc; - - return 0; -} - -static int opt_preset(const char *opt, const char *arg) -{ - FILE *f=NULL; - char filename[1000], tmp[1000], tmp2[1000], line[1000]; - char *codec_name = *opt == 'v' ? video_codec_name : - *opt == 'a' ? audio_codec_name : - subtitle_codec_name; - - if (!(f = get_preset_file(filename, sizeof(filename), arg, *opt == 'f', codec_name))) { - fprintf(stderr, "File for preset '%s' not found\n", arg); - exit_program(1); - } - - while(!feof(f)){ - int e= fscanf(f, "%999[^\n]\n", line) - 1; - if(line[0] == '#' && !e) - continue; - e|= sscanf(line, "%999[^=]=%999[^\n]\n", tmp, tmp2) - 2; - if(e){ - fprintf(stderr, "%s: Invalid syntax: '%s'\n", filename, line); - exit_program(1); - } - if(!strcmp(tmp, "acodec")){ - opt_audio_codec(tmp, tmp2); - }else if(!strcmp(tmp, "vcodec")){ - opt_video_codec(tmp, tmp2); - }else if(!strcmp(tmp, "scodec")){ - opt_subtitle_codec(tmp, tmp2); - }else if(!strcmp(tmp, "dcodec")){ - opt_data_codec(tmp, tmp2); - }else if(opt_default(tmp, tmp2) < 0){ - fprintf(stderr, "%s: Invalid option or argument: '%s', parsed as '%s' = '%s'\n", filename, line, tmp, tmp2); - exit_program(1); - } - } - - fclose(f); - - return 0; -} - -static const OptionDef options[] = { - /* main options */ -#include "cmdutils_common_opts.h" - { "f", HAS_ARG, {(void*)opt_format}, "force format", "fmt" }, - { "i", HAS_ARG, {(void*)opt_input_file}, "input file name", "filename" }, - { "y", OPT_BOOL, {(void*)&file_overwrite}, "overwrite output files" }, - { "map", HAS_ARG | OPT_EXPERT, {(void*)opt_map}, "set input stream mapping", "file.stream[:syncfile.syncstream]" }, - { "map_meta_data", HAS_ARG | OPT_EXPERT, {(void*)opt_map_meta_data}, "DEPRECATED set meta data information of outfile from infile", - "outfile[,metadata]:infile[,metadata]" }, - { "map_metadata", HAS_ARG | OPT_EXPERT, {(void*)opt_map_metadata}, "set metadata information of outfile from infile", - "outfile[,metadata]:infile[,metadata]" }, - { "map_chapters", HAS_ARG | OPT_EXPERT, {(void*)opt_map_chapters}, "set chapters mapping", "outfile:infile" }, - { "t", HAS_ARG, {(void*)opt_recording_time}, "record or transcode \"duration\" seconds of audio/video", "duration" }, - { "fs", HAS_ARG | OPT_INT64, {(void*)&limit_filesize}, "set the limit file size in bytes", "limit_size" }, // - { "ss", HAS_ARG, {(void*)opt_start_time}, "set the start time offset", "time_off" }, - { "itsoffset", HAS_ARG, {(void*)opt_input_ts_offset}, "set the input ts offset", "time_off" }, - { "itsscale", HAS_ARG, {(void*)opt_input_ts_scale}, "set the input ts scale", "stream:scale" }, - { "timestamp", HAS_ARG, {(void*)opt_recording_timestamp}, "set the recording timestamp ('now' to set the current time)", "time" }, - { "metadata", HAS_ARG, {(void*)opt_metadata}, "add metadata", "string=string" }, - { "dframes", OPT_INT | HAS_ARG, {(void*)&max_frames[AVMEDIA_TYPE_DATA]}, "set the number of data frames to record", "number" }, - { "benchmark", OPT_BOOL | OPT_EXPERT, {(void*)&do_benchmark}, - "add timings for benchmarking" }, - { "timelimit", HAS_ARG, {(void*)opt_timelimit}, "set max runtime in seconds", "limit" }, - { "dump", OPT_BOOL | OPT_EXPERT, {(void*)&do_pkt_dump}, - "dump each input packet" }, - { "hex", OPT_BOOL | OPT_EXPERT, {(void*)&do_hex_dump}, - "when dumping packets, also dump the payload" }, - { "re", OPT_BOOL | OPT_EXPERT, {(void*)&rate_emu}, "read input at native frame rate", "" }, - { "loop_input", OPT_BOOL | OPT_EXPERT, {(void*)&loop_input}, "deprecated, use -loop" }, - { "loop_output", HAS_ARG | OPT_INT | OPT_EXPERT, {(void*)&loop_output}, "deprecated, use -loop", "" }, - { "v", HAS_ARG, {(void*)opt_verbose}, "set ffmpeg verbosity level", "number" }, - { "target", HAS_ARG, {(void*)opt_target}, "specify target file type (\"vcd\", \"svcd\", \"dvd\", \"dv\", \"dv50\", \"pal-vcd\", \"ntsc-svcd\", ...)", "type" }, - { "threads", HAS_ARG | OPT_EXPERT, {(void*)opt_thread_count}, "thread count", "count" }, - { "vsync", HAS_ARG | OPT_INT | OPT_EXPERT, {(void*)&video_sync_method}, "video sync method", "" }, - { "async", HAS_ARG | OPT_INT | OPT_EXPERT, {(void*)&audio_sync_method}, "audio sync method", "" }, - { "adrift_threshold", HAS_ARG | OPT_FLOAT | OPT_EXPERT, {(void*)&audio_drift_threshold}, "audio drift threshold", "threshold" }, - { "copyts", OPT_BOOL | OPT_EXPERT, {(void*)©_ts}, "copy timestamps" }, - { "copytb", OPT_BOOL | OPT_EXPERT, {(void*)©_tb}, "copy input stream time base when stream copying" }, - { "shortest", OPT_BOOL | OPT_EXPERT, {(void*)&opt_shortest}, "finish encoding within shortest input" }, // - { "dts_delta_threshold", HAS_ARG | OPT_FLOAT | OPT_EXPERT, {(void*)&dts_delta_threshold}, "timestamp discontinuity delta threshold", "threshold" }, - { "programid", HAS_ARG | OPT_INT | OPT_EXPERT, {(void*)&opt_programid}, "desired program number", "" }, - { "xerror", OPT_BOOL, {(void*)&exit_on_error}, "exit on error", "error" }, - { "copyinkf", OPT_BOOL | OPT_EXPERT, {(void*)©_initial_nonkeyframes}, "copy initial non-keyframes" }, - - /* video options */ - { "vframes", OPT_INT | HAS_ARG | OPT_VIDEO, {(void*)&max_frames[AVMEDIA_TYPE_VIDEO]}, "set the number of video frames to record", "number" }, - { "r", HAS_ARG | OPT_VIDEO, {(void*)opt_frame_rate}, "set frame rate (Hz value, fraction or abbreviation)", "rate" }, - { "s", HAS_ARG | OPT_VIDEO, {(void*)opt_frame_size}, "set frame size (WxH or abbreviation)", "size" }, - { "aspect", HAS_ARG | OPT_VIDEO, {(void*)opt_frame_aspect_ratio}, "set aspect ratio (4:3, 16:9 or 1.3333, 1.7777)", "aspect" }, - { "pix_fmt", HAS_ARG | OPT_EXPERT | OPT_VIDEO, {(void*)opt_frame_pix_fmt}, "set pixel format, 'list' as argument shows all the pixel formats supported", "format" }, - { "croptop", HAS_ARG | OPT_VIDEO, {(void*)opt_frame_crop}, "Removed, use the crop filter instead", "size" }, - { "cropbottom", HAS_ARG | OPT_VIDEO, {(void*)opt_frame_crop}, "Removed, use the crop filter instead", "size" }, - { "cropleft", HAS_ARG | OPT_VIDEO, {(void*)opt_frame_crop}, "Removed, use the crop filter instead", "size" }, - { "cropright", HAS_ARG | OPT_VIDEO, {(void*)opt_frame_crop}, "Removed, use the crop filter instead", "size" }, - { "padtop", HAS_ARG | OPT_VIDEO, {(void*)opt_pad}, "Removed, use the pad filter instead", "size" }, - { "padbottom", HAS_ARG | OPT_VIDEO, {(void*)opt_pad}, "Removed, use the pad filter instead", "size" }, - { "padleft", HAS_ARG | OPT_VIDEO, {(void*)opt_pad}, "Removed, use the pad filter instead", "size" }, - { "padright", HAS_ARG | OPT_VIDEO, {(void*)opt_pad}, "Removed, use the pad filter instead", "size" }, - { "padcolor", HAS_ARG | OPT_VIDEO, {(void*)opt_pad}, "Removed, use the pad filter instead", "color" }, - { "intra", OPT_BOOL | OPT_EXPERT | OPT_VIDEO, {(void*)&intra_only}, "use only intra frames"}, - { "vn", OPT_BOOL | OPT_VIDEO, {(void*)&video_disable}, "disable video" }, - { "vdt", OPT_INT | HAS_ARG | OPT_EXPERT | OPT_VIDEO, {(void*)&video_discard}, "discard threshold", "n" }, - { "qscale", HAS_ARG | OPT_EXPERT | OPT_VIDEO, {(void*)opt_qscale}, "use fixed video quantizer scale (VBR)", "q" }, - { "rc_override", HAS_ARG | OPT_EXPERT | OPT_VIDEO, {(void*)opt_video_rc_override_string}, "rate control override for specific intervals", "override" }, - { "vcodec", HAS_ARG | OPT_VIDEO, {(void*)opt_video_codec}, "force video codec ('copy' to copy stream)", "codec" }, - { "me_threshold", HAS_ARG | OPT_EXPERT | OPT_VIDEO, {(void*)opt_me_threshold}, "motion estimaton threshold", "threshold" }, - { "sameq", OPT_BOOL | OPT_VIDEO, {(void*)&same_quality}, - "use same quantizer as source (implies VBR)" }, - { "pass", HAS_ARG | OPT_VIDEO, {(void*)opt_pass}, "select the pass number (1 or 2)", "n" }, - { "passlogfile", HAS_ARG | OPT_STRING | OPT_VIDEO, {(void*)&pass_logfilename_prefix}, "select two pass log file name prefix", "prefix" }, - { "deinterlace", OPT_BOOL | OPT_EXPERT | OPT_VIDEO, {(void*)&do_deinterlace}, - "deinterlace pictures" }, - { "psnr", OPT_BOOL | OPT_EXPERT | OPT_VIDEO, {(void*)&do_psnr}, "calculate PSNR of compressed frames" }, - { "vstats", OPT_EXPERT | OPT_VIDEO, {(void*)&opt_vstats}, "dump video coding statistics to file" }, - { "vstats_file", HAS_ARG | OPT_EXPERT | OPT_VIDEO, {(void*)opt_vstats_file}, "dump video coding statistics to file", "file" }, -#if CONFIG_AVFILTER - { "vf", OPT_STRING | HAS_ARG, {(void*)&vfilters}, "video filters", "filter list" }, -#endif - { "intra_matrix", HAS_ARG | OPT_EXPERT | OPT_VIDEO, {(void*)opt_intra_matrix}, "specify intra matrix coeffs", "matrix" }, - { "inter_matrix", HAS_ARG | OPT_EXPERT | OPT_VIDEO, {(void*)opt_inter_matrix}, "specify inter matrix coeffs", "matrix" }, - { "top", HAS_ARG | OPT_EXPERT | OPT_VIDEO, {(void*)opt_top_field_first}, "top=1/bottom=0/auto=-1 field first", "" }, - { "dc", OPT_INT | HAS_ARG | OPT_EXPERT | OPT_VIDEO, {(void*)&intra_dc_precision}, "intra_dc_precision", "precision" }, - { "vtag", HAS_ARG | OPT_EXPERT | OPT_VIDEO, {(void*)opt_codec_tag}, "force video tag/fourcc", "fourcc/tag" }, - { "newvideo", OPT_VIDEO, {(void*)opt_new_stream}, "add a new video stream to the current output stream" }, - { "vlang", HAS_ARG | OPT_STRING | OPT_VIDEO, {(void *)&video_language}, "set the ISO 639 language code (3 letters) of the current video stream" , "code" }, - { "qphist", OPT_BOOL | OPT_EXPERT | OPT_VIDEO, { (void *)&qp_hist }, "show QP histogram" }, - { "force_fps", OPT_BOOL | OPT_EXPERT | OPT_VIDEO, {(void*)&force_fps}, "force the selected framerate, disable the best supported framerate selection" }, - { "streamid", HAS_ARG | OPT_EXPERT, {(void*)opt_streamid}, "set the value of an outfile streamid", "streamIndex:value" }, - { "force_key_frames", OPT_STRING | HAS_ARG | OPT_EXPERT | OPT_VIDEO, {(void *)&forced_key_frames}, "force key frames at specified timestamps", "timestamps" }, - - /* audio options */ - { "aframes", OPT_INT | HAS_ARG | OPT_AUDIO, {(void*)&max_frames[AVMEDIA_TYPE_AUDIO]}, "set the number of audio frames to record", "number" }, - { "aq", OPT_FLOAT | HAS_ARG | OPT_AUDIO, {(void*)&audio_qscale}, "set audio quality (codec-specific)", "quality", }, - { "ar", HAS_ARG | OPT_AUDIO, {(void*)opt_audio_rate}, "set audio sampling rate (in Hz)", "rate" }, - { "ac", HAS_ARG | OPT_AUDIO, {(void*)opt_audio_channels}, "set number of audio channels", "channels" }, - { "an", OPT_BOOL | OPT_AUDIO, {(void*)&audio_disable}, "disable audio" }, - { "acodec", HAS_ARG | OPT_AUDIO, {(void*)opt_audio_codec}, "force audio codec ('copy' to copy stream)", "codec" }, - { "atag", HAS_ARG | OPT_EXPERT | OPT_AUDIO, {(void*)opt_codec_tag}, "force audio tag/fourcc", "fourcc/tag" }, - { "vol", OPT_INT | HAS_ARG | OPT_AUDIO, {(void*)&audio_volume}, "change audio volume (256=normal)" , "volume" }, // - { "newaudio", OPT_AUDIO, {(void*)opt_new_stream}, "add a new audio stream to the current output stream" }, - { "alang", HAS_ARG | OPT_STRING | OPT_AUDIO, {(void *)&audio_language}, "set the ISO 639 language code (3 letters) of the current audio stream" , "code" }, - { "sample_fmt", HAS_ARG | OPT_EXPERT | OPT_AUDIO, {(void*)opt_audio_sample_fmt}, "set sample format, 'list' as argument shows all the sample formats supported", "format" }, - - /* subtitle options */ - { "sn", OPT_BOOL | OPT_SUBTITLE, {(void*)&subtitle_disable}, "disable subtitle" }, - { "scodec", HAS_ARG | OPT_SUBTITLE, {(void*)opt_subtitle_codec}, "force subtitle codec ('copy' to copy stream)", "codec" }, - { "newsubtitle", OPT_SUBTITLE, {(void*)opt_new_stream}, "add a new subtitle stream to the current output stream" }, - { "slang", HAS_ARG | OPT_STRING | OPT_SUBTITLE, {(void *)&subtitle_language}, "set the ISO 639 language code (3 letters) of the current subtitle stream" , "code" }, - { "stag", HAS_ARG | OPT_EXPERT | OPT_SUBTITLE, {(void*)opt_codec_tag}, "force subtitle tag/fourcc", "fourcc/tag" }, - - /* grab options */ - { "vc", HAS_ARG | OPT_EXPERT | OPT_VIDEO | OPT_GRAB, {(void*)opt_video_channel}, "deprecated, use -channel", "channel" }, - { "tvstd", HAS_ARG | OPT_EXPERT | OPT_VIDEO | OPT_GRAB, {(void*)opt_video_standard}, "deprecated, use -standard", "standard" }, - { "isync", OPT_BOOL | OPT_EXPERT | OPT_GRAB, {(void*)&input_sync}, "sync read on input", "" }, - - /* muxer options */ - { "muxdelay", OPT_FLOAT | HAS_ARG | OPT_EXPERT, {(void*)&mux_max_delay}, "set the maximum demux-decode delay", "seconds" }, - { "muxpreload", OPT_FLOAT | HAS_ARG | OPT_EXPERT, {(void*)&mux_preload}, "set the initial demux-decode delay", "seconds" }, - - { "absf", HAS_ARG | OPT_AUDIO | OPT_EXPERT, {(void*)opt_bsf}, "", "bitstream_filter" }, - { "vbsf", HAS_ARG | OPT_VIDEO | OPT_EXPERT, {(void*)opt_bsf}, "", "bitstream_filter" }, - { "sbsf", HAS_ARG | OPT_SUBTITLE | OPT_EXPERT, {(void*)opt_bsf}, "", "bitstream_filter" }, - - { "apre", HAS_ARG | OPT_AUDIO | OPT_EXPERT, {(void*)opt_preset}, "set the audio options to the indicated preset", "preset" }, - { "vpre", HAS_ARG | OPT_VIDEO | OPT_EXPERT, {(void*)opt_preset}, "set the video options to the indicated preset", "preset" }, - { "spre", HAS_ARG | OPT_SUBTITLE | OPT_EXPERT, {(void*)opt_preset}, "set the subtitle options to the indicated preset", "preset" }, - { "fpre", HAS_ARG | OPT_EXPERT, {(void*)opt_preset}, "set options from indicated preset file", "filename" }, - /* data codec support */ - { "dcodec", HAS_ARG | OPT_DATA, {(void*)opt_data_codec}, "force data codec ('copy' to copy stream)", "codec" }, - - { "default", HAS_ARG | OPT_AUDIO | OPT_VIDEO | OPT_EXPERT, {(void*)opt_default}, "generic catch all option", "" }, - { NULL, }, -}; - -int main(int argc, char **argv) -{ - int64_t ti; - - av_log_set_flags(AV_LOG_SKIP_REPEATED); - parse_loglevel(argc, argv, options); - - avcodec_register_all(); -#if CONFIG_AVDEVICE - avdevice_register_all(); -#endif -#if CONFIG_AVFILTER - avfilter_register_all(); -#endif - av_register_all(); - avformat_network_init(); - - avio_set_interrupt_cb(decode_interrupt_cb); - - init_opts(); - - show_banner(); - - av_log(NULL, AV_LOG_WARNING, "This program is not developed anymore and is only " - "provided for compatibility. Use avconv instead " - "(see Changelog for the list of incompatible changes).\n"); - - /* parse options */ - parse_options(NULL, argc, argv, options, opt_output_file); - - if(nb_output_files <= 0 && nb_input_files == 0) { - show_usage(); - fprintf(stderr, "Use -h to get full help or, even better, run 'man ffmpeg'\n"); - exit_program(1); - } - - /* file converter / grab */ - if (nb_output_files <= 0) { - fprintf(stderr, "At least one output file must be specified\n"); - exit_program(1); - } - - if (nb_input_files == 0) { - fprintf(stderr, "At least one input file must be specified\n"); - exit_program(1); - } - - ti = getutime(); - if (transcode(output_files, nb_output_files, input_files, nb_input_files, - stream_maps, nb_stream_maps) < 0) - exit_program(1); - ti = getutime() - ti; - if (do_benchmark) { - int maxrss = getmaxrss() / 1024; - printf("bench: utime=%0.3fs maxrss=%ikB\n", ti / 1000000.0, maxrss); - } - - exit_program(0); - return 0; -}