FFmpeg
decode_audio.c
Go to the documentation of this file.
1 /*
2  * Copyright (c) 2001 Fabrice Bellard
3  *
4  * Permission is hereby granted, free of charge, to any person obtaining a copy
5  * of this software and associated documentation files (the "Software"), to deal
6  * in the Software without restriction, including without limitation the rights
7  * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
8  * copies of the Software, and to permit persons to whom the Software is
9  * furnished to do so, subject to the following conditions:
10  *
11  * The above copyright notice and this permission notice shall be included in
12  * all copies or substantial portions of the Software.
13  *
14  * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
15  * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
16  * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
17  * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
18  * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
19  * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
20  * THE SOFTWARE.
21  */
22 
23 /**
24  * @file
25  * audio decoding with libavcodec API example
26  *
27  * @example decode_audio.c
28  */
29 
30 #include <stdio.h>
31 #include <stdlib.h>
32 #include <string.h>
33 
34 #include <libavutil/frame.h>
35 #include <libavutil/mem.h>
36 
37 #include <libavcodec/avcodec.h>
38 
39 #define AUDIO_INBUF_SIZE 20480
40 #define AUDIO_REFILL_THRESH 4096
41 
43  FILE *outfile)
44 {
45  int i, ch;
46  int ret, data_size;
47 
48  /* send the packet with the compressed data to the decoder */
49  ret = avcodec_send_packet(dec_ctx, pkt);
50  if (ret < 0) {
51  fprintf(stderr, "Error submitting the packet to the decoder\n");
52  exit(1);
53  }
54 
55  /* read all the output frames (in general there may be any number of them */
56  while (ret >= 0) {
57  ret = avcodec_receive_frame(dec_ctx, frame);
58  if (ret == AVERROR(EAGAIN) || ret == AVERROR_EOF)
59  return;
60  else if (ret < 0) {
61  fprintf(stderr, "Error during decoding\n");
62  exit(1);
63  }
64  data_size = av_get_bytes_per_sample(dec_ctx->sample_fmt);
65  if (data_size < 0) {
66  /* This should not occur, checking just for paranoia */
67  fprintf(stderr, "Failed to calculate data size\n");
68  exit(1);
69  }
70  for (i = 0; i < frame->nb_samples; i++)
71  for (ch = 0; ch < dec_ctx->channels; ch++)
72  fwrite(frame->data[ch] + data_size*i, 1, data_size, outfile);
73  }
74 }
75 
76 int main(int argc, char **argv)
77 {
78  const char *outfilename, *filename;
79  const AVCodec *codec;
81  AVCodecParserContext *parser = NULL;
82  int len, ret;
83  FILE *f, *outfile;
85  uint8_t *data;
86  size_t data_size;
87  AVPacket *pkt;
88  AVFrame *decoded_frame = NULL;
89 
90  if (argc <= 2) {
91  fprintf(stderr, "Usage: %s <input file> <output file>\n", argv[0]);
92  exit(0);
93  }
94  filename = argv[1];
95  outfilename = argv[2];
96 
97  pkt = av_packet_alloc();
98 
99  /* find the MPEG audio decoder */
101  if (!codec) {
102  fprintf(stderr, "Codec not found\n");
103  exit(1);
104  }
105 
106  parser = av_parser_init(codec->id);
107  if (!parser) {
108  fprintf(stderr, "Parser not found\n");
109  exit(1);
110  }
111 
112  c = avcodec_alloc_context3(codec);
113  if (!c) {
114  fprintf(stderr, "Could not allocate audio codec context\n");
115  exit(1);
116  }
117 
118  /* open it */
119  if (avcodec_open2(c, codec, NULL) < 0) {
120  fprintf(stderr, "Could not open codec\n");
121  exit(1);
122  }
123 
124  f = fopen(filename, "rb");
125  if (!f) {
126  fprintf(stderr, "Could not open %s\n", filename);
127  exit(1);
128  }
129  outfile = fopen(outfilename, "wb");
130  if (!outfile) {
131  av_free(c);
132  exit(1);
133  }
134 
135  /* decode until eof */
136  data = inbuf;
137  data_size = fread(inbuf, 1, AUDIO_INBUF_SIZE, f);
138 
139  while (data_size > 0) {
140  if (!decoded_frame) {
141  if (!(decoded_frame = av_frame_alloc())) {
142  fprintf(stderr, "Could not allocate audio frame\n");
143  exit(1);
144  }
145  }
146 
147  ret = av_parser_parse2(parser, c, &pkt->data, &pkt->size,
148  data, data_size,
150  if (ret < 0) {
151  fprintf(stderr, "Error while parsing\n");
152  exit(1);
153  }
154  data += ret;
155  data_size -= ret;
156 
157  if (pkt->size)
158  decode(c, pkt, decoded_frame, outfile);
159 
160  if (data_size < AUDIO_REFILL_THRESH) {
161  memmove(inbuf, data, data_size);
162  data = inbuf;
163  len = fread(data + data_size, 1,
164  AUDIO_INBUF_SIZE - data_size, f);
165  if (len > 0)
166  data_size += len;
167  }
168  }
169 
170  /* flush the decoder */
171  pkt->data = NULL;
172  pkt->size = 0;
173  decode(c, pkt, decoded_frame, outfile);
174 
175  fclose(outfile);
176  fclose(f);
177 
179  av_parser_close(parser);
180  av_frame_free(&decoded_frame);
181  av_packet_free(&pkt);
182 
183  return 0;
184 }
#define NULL
Definition: coverity.c:32
This structure describes decoded (raw) audio or video data.
Definition: frame.h:268
ptrdiff_t const GLvoid * data
Definition: opengl_enc.c:100
Memory handling functions.
int size
Definition: avcodec.h:1478
uint8_t pi<< 24) CONV_FUNC(AV_SAMPLE_FMT_S64, int64_t, AV_SAMPLE_FMT_U8,(uint64_t)((*(const uint8_t *) pi-0x80U))<< 56) CONV_FUNC(AV_SAMPLE_FMT_FLT, float, AV_SAMPLE_FMT_U8,(*(const uint8_t *) pi-0x80)*(1.0f/(1<< 7))) CONV_FUNC(AV_SAMPLE_FMT_DBL, double, AV_SAMPLE_FMT_U8,(*(const uint8_t *) pi-0x80)*(1.0/(1<< 7))) CONV_FUNC(AV_SAMPLE_FMT_U8, uint8_t, AV_SAMPLE_FMT_S16,(*(const int16_t *) pi >>8)+0x80) CONV_FUNC(AV_SAMPLE_FMT_S64, int64_t, AV_SAMPLE_FMT_S16,(uint64_t)(*(const int16_t *) pi)<< 48) CONV_FUNC(AV_SAMPLE_FMT_FLT, float, AV_SAMPLE_FMT_S16,*(const int16_t *) pi *(1.0f/(1<< 15))) CONV_FUNC(AV_SAMPLE_FMT_DBL, double, AV_SAMPLE_FMT_S16,*(const int16_t *) pi *(1.0/(1<< 15))) CONV_FUNC(AV_SAMPLE_FMT_U8, uint8_t, AV_SAMPLE_FMT_S32,(*(const int32_t *) pi >>24)+0x80) CONV_FUNC(AV_SAMPLE_FMT_S64, int64_t, AV_SAMPLE_FMT_S32,(uint64_t)(*(const int32_t *) pi)<< 32) CONV_FUNC(AV_SAMPLE_FMT_FLT, float, AV_SAMPLE_FMT_S32,*(const int32_t *) pi *(1.0f/(1U<< 31))) CONV_FUNC(AV_SAMPLE_FMT_DBL, double, AV_SAMPLE_FMT_S32,*(const int32_t *) pi *(1.0/(1U<< 31))) CONV_FUNC(AV_SAMPLE_FMT_U8, uint8_t, AV_SAMPLE_FMT_S64,(*(const int64_t *) pi >>56)+0x80) CONV_FUNC(AV_SAMPLE_FMT_FLT, float, AV_SAMPLE_FMT_S64,*(const int64_t *) pi *(1.0f/(INT64_C(1)<< 63))) CONV_FUNC(AV_SAMPLE_FMT_DBL, double, AV_SAMPLE_FMT_S64,*(const int64_t *) pi *(1.0/(INT64_C(1)<< 63))) CONV_FUNC(AV_SAMPLE_FMT_U8, uint8_t, AV_SAMPLE_FMT_FLT, av_clip_uint8(lrintf(*(const float *) pi *(1<< 7))+0x80)) CONV_FUNC(AV_SAMPLE_FMT_S16, int16_t, AV_SAMPLE_FMT_FLT, av_clip_int16(lrintf(*(const float *) pi *(1<< 15)))) CONV_FUNC(AV_SAMPLE_FMT_S32, int32_t, AV_SAMPLE_FMT_FLT, av_clipl_int32(llrintf(*(const float *) pi *(1U<< 31)))) CONV_FUNC(AV_SAMPLE_FMT_S64, int64_t, AV_SAMPLE_FMT_FLT, llrintf(*(const float *) pi *(INT64_C(1)<< 63))) CONV_FUNC(AV_SAMPLE_FMT_U8, uint8_t, AV_SAMPLE_FMT_DBL, av_clip_uint8(lrint(*(const double *) pi *(1<< 7))+0x80)) CONV_FUNC(AV_SAMPLE_FMT_S16, int16_t, AV_SAMPLE_FMT_DBL, av_clip_int16(lrint(*(const double *) pi *(1<< 15)))) CONV_FUNC(AV_SAMPLE_FMT_S32, int32_t, AV_SAMPLE_FMT_DBL, av_clipl_int32(llrint(*(const double *) pi *(1U<< 31)))) CONV_FUNC(AV_SAMPLE_FMT_S64, int64_t, AV_SAMPLE_FMT_DBL, llrint(*(const double *) pi *(INT64_C(1)<< 63)))#define FMT_PAIR_FUNC(out, in) static conv_func_type *const fmt_pair_to_conv_functions[AV_SAMPLE_FMT_NB *AV_SAMPLE_FMT_NB]={FMT_PAIR_FUNC(AV_SAMPLE_FMT_U8, AV_SAMPLE_FMT_U8), FMT_PAIR_FUNC(AV_SAMPLE_FMT_S16, AV_SAMPLE_FMT_U8), FMT_PAIR_FUNC(AV_SAMPLE_FMT_S32, AV_SAMPLE_FMT_U8), FMT_PAIR_FUNC(AV_SAMPLE_FMT_FLT, AV_SAMPLE_FMT_U8), FMT_PAIR_FUNC(AV_SAMPLE_FMT_DBL, AV_SAMPLE_FMT_U8), FMT_PAIR_FUNC(AV_SAMPLE_FMT_S64, AV_SAMPLE_FMT_U8), FMT_PAIR_FUNC(AV_SAMPLE_FMT_U8, AV_SAMPLE_FMT_S16), FMT_PAIR_FUNC(AV_SAMPLE_FMT_S16, AV_SAMPLE_FMT_S16), FMT_PAIR_FUNC(AV_SAMPLE_FMT_S32, AV_SAMPLE_FMT_S16), FMT_PAIR_FUNC(AV_SAMPLE_FMT_FLT, AV_SAMPLE_FMT_S16), FMT_PAIR_FUNC(AV_SAMPLE_FMT_DBL, AV_SAMPLE_FMT_S16), FMT_PAIR_FUNC(AV_SAMPLE_FMT_S64, AV_SAMPLE_FMT_S16), FMT_PAIR_FUNC(AV_SAMPLE_FMT_U8, AV_SAMPLE_FMT_S32), FMT_PAIR_FUNC(AV_SAMPLE_FMT_S16, AV_SAMPLE_FMT_S32), FMT_PAIR_FUNC(AV_SAMPLE_FMT_S32, AV_SAMPLE_FMT_S32), FMT_PAIR_FUNC(AV_SAMPLE_FMT_FLT, AV_SAMPLE_FMT_S32), FMT_PAIR_FUNC(AV_SAMPLE_FMT_DBL, AV_SAMPLE_FMT_S32), FMT_PAIR_FUNC(AV_SAMPLE_FMT_S64, AV_SAMPLE_FMT_S32), FMT_PAIR_FUNC(AV_SAMPLE_FMT_U8, AV_SAMPLE_FMT_FLT), FMT_PAIR_FUNC(AV_SAMPLE_FMT_S16, AV_SAMPLE_FMT_FLT), FMT_PAIR_FUNC(AV_SAMPLE_FMT_S32, AV_SAMPLE_FMT_FLT), FMT_PAIR_FUNC(AV_SAMPLE_FMT_FLT, AV_SAMPLE_FMT_FLT), FMT_PAIR_FUNC(AV_SAMPLE_FMT_DBL, AV_SAMPLE_FMT_FLT), FMT_PAIR_FUNC(AV_SAMPLE_FMT_S64, AV_SAMPLE_FMT_FLT), FMT_PAIR_FUNC(AV_SAMPLE_FMT_U8, AV_SAMPLE_FMT_DBL), FMT_PAIR_FUNC(AV_SAMPLE_FMT_S16, AV_SAMPLE_FMT_DBL), FMT_PAIR_FUNC(AV_SAMPLE_FMT_S32, AV_SAMPLE_FMT_DBL), FMT_PAIR_FUNC(AV_SAMPLE_FMT_FLT, AV_SAMPLE_FMT_DBL), FMT_PAIR_FUNC(AV_SAMPLE_FMT_DBL, AV_SAMPLE_FMT_DBL), FMT_PAIR_FUNC(AV_SAMPLE_FMT_S64, AV_SAMPLE_FMT_DBL), FMT_PAIR_FUNC(AV_SAMPLE_FMT_U8, AV_SAMPLE_FMT_S64), FMT_PAIR_FUNC(AV_SAMPLE_FMT_S16, AV_SAMPLE_FMT_S64), FMT_PAIR_FUNC(AV_SAMPLE_FMT_S32, AV_SAMPLE_FMT_S64), FMT_PAIR_FUNC(AV_SAMPLE_FMT_FLT, AV_SAMPLE_FMT_S64), FMT_PAIR_FUNC(AV_SAMPLE_FMT_DBL, AV_SAMPLE_FMT_S64), FMT_PAIR_FUNC(AV_SAMPLE_FMT_S64, AV_SAMPLE_FMT_S64),};static void cpy1(uint8_t **dst, const uint8_t **src, int len){memcpy(*dst,*src, len);}static void cpy2(uint8_t **dst, const uint8_t **src, int len){memcpy(*dst,*src, 2 *len);}static void cpy4(uint8_t **dst, const uint8_t **src, int len){memcpy(*dst,*src, 4 *len);}static void cpy8(uint8_t **dst, const uint8_t **src, int len){memcpy(*dst,*src, 8 *len);}AudioConvert *swri_audio_convert_alloc(enum AVSampleFormat out_fmt, enum AVSampleFormat in_fmt, int channels, const int *ch_map, int flags){AudioConvert *ctx;conv_func_type *f=fmt_pair_to_conv_functions[av_get_packed_sample_fmt(out_fmt)+AV_SAMPLE_FMT_NB *av_get_packed_sample_fmt(in_fmt)];if(!f) return NULL;ctx=av_mallocz(sizeof(*ctx));if(!ctx) return NULL;if(channels==1){in_fmt=av_get_planar_sample_fmt(in_fmt);out_fmt=av_get_planar_sample_fmt(out_fmt);}ctx->channels=channels;ctx->conv_f=f;ctx->ch_map=ch_map;if(in_fmt==AV_SAMPLE_FMT_U8||in_fmt==AV_SAMPLE_FMT_U8P) memset(ctx->silence, 0x80, sizeof(ctx->silence));if(out_fmt==in_fmt &&!ch_map){switch(av_get_bytes_per_sample(in_fmt)){case 1:ctx->simd_f=cpy1;break;case 2:ctx->simd_f=cpy2;break;case 4:ctx->simd_f=cpy4;break;case 8:ctx->simd_f=cpy8;break;}}if(HAVE_X86ASM &&1) swri_audio_convert_init_x86(ctx, out_fmt, in_fmt, channels);if(ARCH_ARM) swri_audio_convert_init_arm(ctx, out_fmt, in_fmt, channels);if(ARCH_AARCH64) swri_audio_convert_init_aarch64(ctx, out_fmt, in_fmt, channels);return ctx;}void swri_audio_convert_free(AudioConvert **ctx){av_freep(ctx);}int swri_audio_convert(AudioConvert *ctx, AudioData *out, AudioData *in, int len){int ch;int off=0;const int os=(out->planar?1:out->ch_count)*out->bps;unsigned misaligned=0;av_assert0(ctx->channels==out->ch_count);if(ctx->in_simd_align_mask){int planes=in->planar?in->ch_count:1;unsigned m=0;for(ch=0;ch< planes;ch++) m|=(intptr_t) in->ch[ch];misaligned|=m &ctx->in_simd_align_mask;}if(ctx->out_simd_align_mask){int planes=out->planar?out->ch_count:1;unsigned m=0;for(ch=0;ch< planes;ch++) m|=(intptr_t) out->ch[ch];misaligned|=m &ctx->out_simd_align_mask;}if(ctx->simd_f &&!ctx->ch_map &&!misaligned){off=len &~15;av_assert1(off >=0);av_assert1(off<=len);av_assert2(ctx->channels==SWR_CH_MAX||!in->ch[ctx->channels]);if(off >0){if(out->planar==in->planar){int planes=out->planar?out->ch_count:1;for(ch=0;ch< planes;ch++){ctx->simd_f(out-> ch ch
Definition: audioconvert.c:56
static AVPacket pkt
AVCodec.
Definition: avcodec.h:3477
static void decode(AVCodecContext *dec_ctx, AVPacket *pkt, AVFrame *frame, FILE *outfile)
Definition: decode_audio.c:42
void av_packet_free(AVPacket **pkt)
Free the packet, if the packet is reference counted, it will be unreferenced first.
Definition: avpacket.c:62
enum AVSampleFormat sample_fmt
audio sample format
Definition: avcodec.h:2229
uint8_t
AVFrame * av_frame_alloc(void)
Allocate an AVFrame and set its fields to default values.
Definition: frame.c:189
#define f(width, name)
Definition: cbs_vp9.c:255
Undefined Behavior In the C some operations are like signed integer dereferencing freed accessing outside allocated Undefined Behavior must not occur in a C it is not safe even if the output of undefined operations is unused The unsafety may seem nit picking but Optimizing compilers have in fact optimized code on the assumption that no undefined Behavior occurs Optimizing code based on wrong assumptions can and has in some cases lead to effects beyond the output of computations The signed integer overflow problem in speed critical code Code which is highly optimized and works with signed integers sometimes has the problem that often the output of the computation does not c
Definition: undefined.txt:32
#define AUDIO_REFILL_THRESH
Definition: decode_audio.c:40
uint8_t * data
Definition: avcodec.h:1477
#define AVERROR_EOF
End of file.
Definition: error.h:55
enum AVCodecID id
Definition: avcodec.h:3491
#define i(width, name, range_min, range_max)
Definition: cbs_h2645.c:260
void av_frame_free(AVFrame **frame)
Free the frame and any dynamically allocated objects in it, e.g.
Definition: frame.c:202
int avcodec_receive_frame(AVCodecContext *avctx, AVFrame *frame)
Return decoded output data from a decoder.
Definition: decode.c:740
reference-counted frame API
AVCodecContext * avcodec_alloc_context3(const AVCodec *codec)
Allocate an AVCodecContext and set its fields to default values.
Definition: options.c:156
int av_parser_parse2(AVCodecParserContext *s, AVCodecContext *avctx, uint8_t **poutbuf, int *poutbuf_size, const uint8_t *buf, int buf_size, int64_t pts, int64_t dts, int64_t pos)
Parse a packet.
Definition: parser.c:120
void av_parser_close(AVCodecParserContext *s)
Definition: parser.c:224
these buffered frames must be flushed immediately if a new input produces new the filter must not call request_frame to get more It must just process the frame or queue it The task of requesting more frames is left to the filter s request_frame method or the application If a filter has several the filter must be ready for frames arriving randomly on any input any filter with several inputs will most likely require some kind of queuing mechanism It is perfectly acceptable to have a limited queue and to drop frames when the inputs are too unbalanced request_frame For filters that do not use the this method is called when a frame is wanted on an output For a it should directly call filter_frame on the corresponding output For a if there are queued frames already one of these frames should be pushed If the filter should request a frame on one of its repeatedly until at least one frame has been pushed Return or at least make progress towards producing a frame
int avcodec_send_packet(AVCodecContext *avctx, const AVPacket *avpkt)
Supply raw packet data as input to a decoder.
Definition: decode.c:677
AVCodecParserContext * av_parser_init(int codec_id)
Definition: parser.c:34
Libavcodec external API header.
void avcodec_free_context(AVCodecContext **avctx)
Free the codec context and everything associated with it and write NULL to the provided pointer...
Definition: options.c:171
main external API structure.
Definition: avcodec.h:1565
AVCodec * avcodec_find_decoder(enum AVCodecID id)
Find a registered decoder with a matching codec ID.
Definition: allcodecs.c:890
#define AUDIO_INBUF_SIZE
Definition: decode_audio.c:39
int avcodec_open2(AVCodecContext *avctx, const AVCodec *codec, AVDictionary **options)
Initialize the AVCodecContext to use the given AVCodec.
Definition: utils.c:542
uint8_t * data[AV_NUM_DATA_POINTERS]
pointer to the picture/channel planes.
Definition: frame.h:282
int av_get_bytes_per_sample(enum AVSampleFormat sample_fmt)
Return number of bytes per sample.
Definition: samplefmt.c:106
static AVCodecContext * dec_ctx
#define AV_INPUT_BUFFER_PADDING_SIZE
Required number of additionally allocated bytes at the end of the input bitstream for decoding...
Definition: avcodec.h:790
#define av_free(p)
int len
int channels
number of audio channels
Definition: avcodec.h:2222
AVPacket * av_packet_alloc(void)
Allocate an AVPacket and set its fields to default values.
Definition: avpacket.c:51
int main(int argc, char **argv)
Definition: decode_audio.c:76
Filter the word “frame” indicates either a video frame or a group of audio as stored in an AVFrame structure Format for each input and each output the list of supported formats For video that means pixel format For audio that means channel sample they are references to shared objects When the negotiation mechanism computes the intersection of the formats supported at each end of a all references to both lists are replaced with a reference to the intersection And when a single format is eventually chosen for a link amongst the remaining all references to the list are updated That means that if a filter requires that its input and output have the same format amongst a supported all it has to do is use a reference to the same list of formats query_formats can leave some formats unset and return AVERROR(EAGAIN) to cause the negotiation mechanism toagain later.That can be used by filters with complex requirements to use the format negotiated on one link to set the formats supported on another.Frame references ownership and permissions
This structure stores compressed data.
Definition: avcodec.h:1454
int nb_samples
number of audio samples (per channel) described by this frame
Definition: frame.h:334
FILE * outfile
Definition: audiogen.c:96
#define AV_NOPTS_VALUE
Undefined timestamp value.
Definition: avutil.h:248