FFmpeg
vmdaudio.c
Go to the documentation of this file.
1 /*
2  * Sierra VMD audio decoder
3  * Copyright (c) 2004 The FFmpeg Project
4  *
5  * This file is part of FFmpeg.
6  *
7  * FFmpeg is free software; you can redistribute it and/or
8  * modify it under the terms of the GNU Lesser General Public
9  * License as published by the Free Software Foundation; either
10  * version 2.1 of the License, or (at your option) any later version.
11  *
12  * FFmpeg is distributed in the hope that it will be useful,
13  * but WITHOUT ANY WARRANTY; without even the implied warranty of
14  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
15  * Lesser General Public License for more details.
16  *
17  * You should have received a copy of the GNU Lesser General Public
18  * License along with FFmpeg; if not, write to the Free Software
19  * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
20  */
21 
22 /**
23  * @file
24  * Sierra VMD audio decoder
25  * by Vladimir "VAG" Gneushev (vagsoft at mail.ru)
26  * for more information on the Sierra VMD format, visit:
27  * http://www.pcisys.net/~melanson/codecs/
28  *
29  * The audio decoder, expects each encoded data
30  * chunk to be prepended with the appropriate 16-byte frame information
31  * record from the VMD file. It does not require the 0x330-byte VMD file
32  * header, but it does need the audio setup parameters passed in through
33  * normal libavcodec API means.
34  */
35 
36 #include <string.h>
37 
38 #include "libavutil/avassert.h"
40 #include "libavutil/common.h"
41 #include "libavutil/intreadwrite.h"
42 
43 #include "avcodec.h"
44 #include "codec_internal.h"
45 #include "decode.h"
46 
47 #define BLOCK_TYPE_AUDIO 1
48 #define BLOCK_TYPE_INITIAL 2
49 #define BLOCK_TYPE_SILENCE 3
50 
51 typedef struct VmdAudioContext {
52  int out_bps;
55 
56 static const uint16_t vmdaudio_table[128] = {
57  0x000, 0x008, 0x010, 0x020, 0x030, 0x040, 0x050, 0x060, 0x070, 0x080,
58  0x090, 0x0A0, 0x0B0, 0x0C0, 0x0D0, 0x0E0, 0x0F0, 0x100, 0x110, 0x120,
59  0x130, 0x140, 0x150, 0x160, 0x170, 0x180, 0x190, 0x1A0, 0x1B0, 0x1C0,
60  0x1D0, 0x1E0, 0x1F0, 0x200, 0x208, 0x210, 0x218, 0x220, 0x228, 0x230,
61  0x238, 0x240, 0x248, 0x250, 0x258, 0x260, 0x268, 0x270, 0x278, 0x280,
62  0x288, 0x290, 0x298, 0x2A0, 0x2A8, 0x2B0, 0x2B8, 0x2C0, 0x2C8, 0x2D0,
63  0x2D8, 0x2E0, 0x2E8, 0x2F0, 0x2F8, 0x300, 0x308, 0x310, 0x318, 0x320,
64  0x328, 0x330, 0x338, 0x340, 0x348, 0x350, 0x358, 0x360, 0x368, 0x370,
65  0x378, 0x380, 0x388, 0x390, 0x398, 0x3A0, 0x3A8, 0x3B0, 0x3B8, 0x3C0,
66  0x3C8, 0x3D0, 0x3D8, 0x3E0, 0x3E8, 0x3F0, 0x3F8, 0x400, 0x440, 0x480,
67  0x4C0, 0x500, 0x540, 0x580, 0x5C0, 0x600, 0x640, 0x680, 0x6C0, 0x700,
68  0x740, 0x780, 0x7C0, 0x800, 0x900, 0xA00, 0xB00, 0xC00, 0xD00, 0xE00,
69  0xF00, 0x1000, 0x1400, 0x1800, 0x1C00, 0x2000, 0x3000, 0x4000
70 };
71 
73 {
74  VmdAudioContext *s = avctx->priv_data;
75  int channels = avctx->ch_layout.nb_channels;
76 
78  av_log(avctx, AV_LOG_ERROR, "invalid number of channels\n");
79  return AVERROR(EINVAL);
80  }
81  if (avctx->block_align < 1 || avctx->block_align % channels ||
82  avctx->block_align > INT_MAX - channels) {
83  av_log(avctx, AV_LOG_ERROR, "invalid block align\n");
84  return AVERROR(EINVAL);
85  }
86 
89 
90  if (avctx->bits_per_coded_sample == 16)
92  else
94  s->out_bps = av_get_bytes_per_sample(avctx->sample_fmt);
95 
96  s->chunk_size = avctx->block_align + channels * (s->out_bps == 2);
97 
98  av_log(avctx, AV_LOG_DEBUG, "%d channels, %d bits/sample, "
99  "block align = %d, sample rate = %d\n",
101  avctx->sample_rate);
102 
103  return 0;
104 }
105 
106 static void decode_audio_s16(int16_t *out, const uint8_t *buf, int buf_size,
107  int channels)
108 {
109  int ch;
110  const uint8_t *buf_end = buf + buf_size;
111  int predictor[2];
112  int st = channels - 1;
113 
114  /* decode initial raw sample */
115  for (ch = 0; ch < channels; ch++) {
116  predictor[ch] = (int16_t)AV_RL16(buf);
117  buf += 2;
118  *out++ = predictor[ch];
119  }
120 
121  /* decode DPCM samples */
122  ch = 0;
123  while (buf < buf_end) {
124  uint8_t b = *buf++;
125  if (b & 0x80)
126  predictor[ch] -= vmdaudio_table[b & 0x7F];
127  else
128  predictor[ch] += vmdaudio_table[b];
129  predictor[ch] = av_clip_int16(predictor[ch]);
130  *out++ = predictor[ch];
131  ch ^= st;
132  }
133 }
134 
136  int *got_frame_ptr, AVPacket *avpkt)
137 {
138  const uint8_t *buf = avpkt->data;
139  const uint8_t *buf_end;
140  int buf_size = avpkt->size;
141  VmdAudioContext *s = avctx->priv_data;
142  int block_type, silent_chunks, audio_chunks;
143  int ret;
144  uint8_t *output_samples_u8;
145  int16_t *output_samples_s16;
146  int channels = avctx->ch_layout.nb_channels;
147 
148  if (buf_size < 16) {
149  av_log(avctx, AV_LOG_WARNING, "skipping small junk packet\n");
150  *got_frame_ptr = 0;
151  return buf_size;
152  }
153 
154  block_type = buf[6];
155  if (block_type < BLOCK_TYPE_AUDIO || block_type > BLOCK_TYPE_SILENCE) {
156  av_log(avctx, AV_LOG_ERROR, "unknown block type: %d\n", block_type);
157  return AVERROR(EINVAL);
158  }
159  buf += 16;
160  buf_size -= 16;
161 
162  /* get number of silent chunks */
163  silent_chunks = 0;
164  if (block_type == BLOCK_TYPE_INITIAL) {
165  uint32_t flags;
166  if (buf_size < 4) {
167  av_log(avctx, AV_LOG_ERROR, "packet is too small\n");
168  return AVERROR(EINVAL);
169  }
170  flags = AV_RB32(buf);
171  silent_chunks = av_popcount(flags);
172  buf += 4;
173  buf_size -= 4;
174  } else if (block_type == BLOCK_TYPE_SILENCE) {
175  silent_chunks = 1;
176  buf_size = 0; // should already be zero but set it just to be sure
177  }
178 
179  /* ensure output buffer is large enough */
180  audio_chunks = buf_size / s->chunk_size;
181 
182  /* drop incomplete chunks */
183  buf_size = audio_chunks * s->chunk_size;
184 
185  if (silent_chunks + audio_chunks >= INT_MAX / avctx->block_align)
186  return AVERROR_INVALIDDATA;
187 
188  /* get output buffer */
189  frame->nb_samples = ((silent_chunks + audio_chunks) * avctx->block_align) /
190  avctx->ch_layout.nb_channels;
191  if ((ret = ff_get_buffer(avctx, frame, 0)) < 0)
192  return ret;
193  output_samples_u8 = frame->data[0];
194  output_samples_s16 = (int16_t *)frame->data[0];
195 
196  /* decode silent chunks */
197  if (silent_chunks > 0) {
198  int silent_size = avctx->block_align * silent_chunks;
199  av_assert0(avctx->block_align * silent_chunks <= frame->nb_samples * avctx->ch_layout.nb_channels);
200 
201  if (s->out_bps == 2) {
202  memset(output_samples_s16, 0x00, silent_size * 2);
203  output_samples_s16 += silent_size;
204  } else {
205  memset(output_samples_u8, 0x80, silent_size);
206  output_samples_u8 += silent_size;
207  }
208  }
209 
210  /* decode audio chunks */
211  if (audio_chunks > 0) {
212  buf_end = buf + buf_size;
213  av_assert0((buf_size & (avctx->ch_layout.nb_channels > 1)) == 0);
214  while (buf_end - buf >= s->chunk_size) {
215  if (s->out_bps == 2) {
216  decode_audio_s16(output_samples_s16, buf, s->chunk_size, channels);
217  output_samples_s16 += avctx->block_align;
218  } else {
219  memcpy(output_samples_u8, buf, s->chunk_size);
220  output_samples_u8 += avctx->block_align;
221  }
222  buf += s->chunk_size;
223  }
224  }
225 
226  *got_frame_ptr = 1;
227 
228  return avpkt->size;
229 }
230 
232  .p.name = "vmdaudio",
233  CODEC_LONG_NAME("Sierra VMD audio"),
234  .p.type = AVMEDIA_TYPE_AUDIO,
235  .p.id = AV_CODEC_ID_VMDAUDIO,
236  .priv_data_size = sizeof(VmdAudioContext),
239  .p.capabilities = AV_CODEC_CAP_DR1,
240 };
vmdaudio_decode_frame
static int vmdaudio_decode_frame(AVCodecContext *avctx, AVFrame *frame, int *got_frame_ptr, AVPacket *avpkt)
Definition: vmdaudio.c:135
AV_LOG_WARNING
#define AV_LOG_WARNING
Something somehow does not look correct.
Definition: log.h:186
AVERROR
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
out
FILE * out
Definition: movenc.c:54
AVCodecContext::sample_rate
int sample_rate
samples per second
Definition: avcodec.h:1034
AVFrame
This structure describes decoded (raw) audio or video data.
Definition: frame.h:330
AVPacket::data
uint8_t * data
Definition: packet.h:374
b
#define b
Definition: input.c:41
FFCodec
Definition: codec_internal.h:127
av_popcount
#define av_popcount
Definition: common.h:149
AVChannelLayout::nb_channels
int nb_channels
Number of channels in this layout.
Definition: channel_layout.h:311
ff_vmdaudio_decoder
const FFCodec ff_vmdaudio_decoder
Definition: vmdaudio.c:231
FFCodec::p
AVCodec p
The public AVCodec.
Definition: codec_internal.h:131
AVCodecContext::ch_layout
AVChannelLayout ch_layout
Audio channel layout.
Definition: avcodec.h:2054
BLOCK_TYPE_SILENCE
#define BLOCK_TYPE_SILENCE
Definition: vmdaudio.c:49
vmdaudio_decode_init
static av_cold int vmdaudio_decode_init(AVCodecContext *avctx)
Definition: vmdaudio.c:72
avassert.h
AV_LOG_ERROR
#define AV_LOG_ERROR
Something went wrong and cannot losslessly be recovered.
Definition: log.h:180
av_cold
#define av_cold
Definition: attributes.h:90
FF_CODEC_DECODE_CB
#define FF_CODEC_DECODE_CB(func)
Definition: codec_internal.h:306
intreadwrite.h
s
#define s(width, name)
Definition: cbs_vp9.c:256
AVMEDIA_TYPE_AUDIO
@ AVMEDIA_TYPE_AUDIO
Definition: avutil.h:202
AV_CODEC_ID_VMDAUDIO
@ AV_CODEC_ID_VMDAUDIO
Definition: codec_id.h:449
init
int(* init)(AVBSFContext *ctx)
Definition: dts2pts_bsf.c:365
av_assert0
#define av_assert0(cond)
assert() equivalent, that is always enabled.
Definition: avassert.h:37
AV_LOG_DEBUG
#define AV_LOG_DEBUG
Stuff which is only useful for libav* developers.
Definition: log.h:201
channels
channels
Definition: aptx.h:31
decode.h
AV_RL16
uint64_t_TMPL AV_WL64 unsigned int_TMPL AV_WL32 unsigned int_TMPL AV_WL24 unsigned int_TMPL AV_RL16
Definition: bytestream.h:94
CODEC_LONG_NAME
#define CODEC_LONG_NAME(str)
Definition: codec_internal.h:272
if
if(ret)
Definition: filter_design.txt:179
av_clip_int16
#define av_clip_int16
Definition: common.h:110
decode_audio_s16
static void decode_audio_s16(int16_t *out, const uint8_t *buf, int buf_size, int channels)
Definition: vmdaudio.c:106
VmdAudioContext::out_bps
int out_bps
Definition: vmdaudio.c:52
ff_get_buffer
int ff_get_buffer(AVCodecContext *avctx, AVFrame *frame, int flags)
Get a buffer for a frame.
Definition: decode.c:1473
AV_CODEC_CAP_DR1
#define AV_CODEC_CAP_DR1
Codec uses get_buffer() or get_encode_buffer() for allocating buffers and supports custom allocators.
Definition: codec.h:52
AVPacket::size
int size
Definition: packet.h:375
codec_internal.h
AVCodecContext::sample_fmt
enum AVSampleFormat sample_fmt
audio sample format
Definition: avcodec.h:1050
AV_RB32
uint64_t_TMPL AV_WL64 unsigned int_TMPL AV_WL32 unsigned int_TMPL AV_WL24 unsigned int_TMPL AV_WL16 uint64_t_TMPL AV_WB64 unsigned int_TMPL AV_RB32
Definition: bytestream.h:96
predictor
static void predictor(uint8_t *src, ptrdiff_t size)
Definition: exrenc.c:170
av_channel_layout_default
void av_channel_layout_default(AVChannelLayout *ch_layout, int nb_channels)
Get the default channel layout for a given number of channels.
Definition: channel_layout.c:962
AVCodecContext::bits_per_coded_sample
int bits_per_coded_sample
bits per sample/pixel from the demuxer (needed for huffyuv).
Definition: avcodec.h:1480
av_get_bytes_per_sample
int av_get_bytes_per_sample(enum AVSampleFormat sample_fmt)
Return number of bytes per sample.
Definition: samplefmt.c:108
AV_SAMPLE_FMT_U8
@ AV_SAMPLE_FMT_U8
unsigned 8 bits
Definition: samplefmt.h:57
vmdaudio_table
static const uint16_t vmdaudio_table[128]
Definition: vmdaudio.c:56
common.h
VmdAudioContext
Definition: vmdaudio.c:51
AV_SAMPLE_FMT_S16
@ AV_SAMPLE_FMT_S16
signed 16 bits
Definition: samplefmt.h:58
AVCodec::name
const char * name
Name of the codec implementation.
Definition: codec.h:191
BLOCK_TYPE_INITIAL
#define BLOCK_TYPE_INITIAL
Definition: vmdaudio.c:48
avcodec.h
ret
ret
Definition: filter_design.txt:187
AVCodecContext::block_align
int block_align
number of bytes per packet if constant and known or 0 Used by some WAV based audio codecs.
Definition: avcodec.h:1083
frame
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
Definition: filter_design.txt:264
AVCodecContext
main external API structure.
Definition: avcodec.h:426
channel_layout.h
av_channel_layout_uninit
void av_channel_layout_uninit(AVChannelLayout *channel_layout)
Free any allocated data in the channel layout and reset the channel count to 0.
Definition: channel_layout.c:632
AVPacket
This structure stores compressed data.
Definition: packet.h:351
AVCodecContext::priv_data
void * priv_data
Definition: avcodec.h:453
flags
#define flags(name, subs,...)
Definition: cbs_av1.c:561
av_log
#define av_log(a,...)
Definition: tableprint_vlc.h:27
AVERROR_INVALIDDATA
#define AVERROR_INVALIDDATA
Invalid data found when processing input.
Definition: error.h:61
VmdAudioContext::chunk_size
int chunk_size
Definition: vmdaudio.c:53