dpcm.c
Go to the documentation of this file.
1 /*
2  * Assorted DPCM codecs
3  * Copyright (c) 2003 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  * Assorted DPCM (differential pulse code modulation) audio codecs
25  * by Mike Melanson (melanson@pcisys.net)
26  * Xan DPCM decoder by Mario Brito (mbrito@student.dei.uc.pt)
27  * for more information on the specific data formats, visit:
28  * http://www.pcisys.net/~melanson/codecs/simpleaudio.html
29  * SOL DPCMs implemented by Konstantin Shishkov
30  *
31  * Note about using the Xan DPCM decoder: Xan DPCM is used in AVI files
32  * found in the Wing Commander IV computer game. These AVI files contain
33  * WAVEFORMAT headers which report the audio format as 0x01: raw PCM.
34  * Clearly incorrect. To detect Xan DPCM, you will probably have to
35  * special-case your AVI demuxer to use Xan DPCM if the file uses 'Xxan'
36  * (Xan video) for its video codec. Alternately, such AVI files also contain
37  * the fourcc 'Axan' in the 'auds' chunk of the AVI header.
38  */
39 
40 #include "libavutil/intreadwrite.h"
41 #include "avcodec.h"
42 #include "bytestream.h"
43 #include "internal.h"
44 #include "mathops.h"
45 
46 typedef struct DPCMContext {
47  int16_t roq_square_array[256];
48  int sample[2]; ///< previous sample (for SOL_DPCM)
49  const int8_t *sol_table; ///< delta table for SOL_DPCM
50 } DPCMContext;
51 
52 static const int16_t interplay_delta_table[] = {
53  0, 1, 2, 3, 4, 5, 6, 7,
54  8, 9, 10, 11, 12, 13, 14, 15,
55  16, 17, 18, 19, 20, 21, 22, 23,
56  24, 25, 26, 27, 28, 29, 30, 31,
57  32, 33, 34, 35, 36, 37, 38, 39,
58  40, 41, 42, 43, 47, 51, 56, 61,
59  66, 72, 79, 86, 94, 102, 112, 122,
60  133, 145, 158, 173, 189, 206, 225, 245,
61  267, 292, 318, 348, 379, 414, 452, 493,
62  538, 587, 640, 699, 763, 832, 908, 991,
63  1081, 1180, 1288, 1405, 1534, 1673, 1826, 1993,
64  2175, 2373, 2590, 2826, 3084, 3365, 3672, 4008,
65  4373, 4772, 5208, 5683, 6202, 6767, 7385, 8059,
66  8794, 9597, 10472, 11428, 12471, 13609, 14851, 16206,
67  17685, 19298, 21060, 22981, 25078, 27367, 29864, 32589,
68  -29973, -26728, -23186, -19322, -15105, -10503, -5481, -1,
69  1, 1, 5481, 10503, 15105, 19322, 23186, 26728,
70  29973, -32589, -29864, -27367, -25078, -22981, -21060, -19298,
71  -17685, -16206, -14851, -13609, -12471, -11428, -10472, -9597,
72  -8794, -8059, -7385, -6767, -6202, -5683, -5208, -4772,
73  -4373, -4008, -3672, -3365, -3084, -2826, -2590, -2373,
74  -2175, -1993, -1826, -1673, -1534, -1405, -1288, -1180,
75  -1081, -991, -908, -832, -763, -699, -640, -587,
76  -538, -493, -452, -414, -379, -348, -318, -292,
77  -267, -245, -225, -206, -189, -173, -158, -145,
78  -133, -122, -112, -102, -94, -86, -79, -72,
79  -66, -61, -56, -51, -47, -43, -42, -41,
80  -40, -39, -38, -37, -36, -35, -34, -33,
81  -32, -31, -30, -29, -28, -27, -26, -25,
82  -24, -23, -22, -21, -20, -19, -18, -17,
83  -16, -15, -14, -13, -12, -11, -10, -9,
84  -8, -7, -6, -5, -4, -3, -2, -1
85 
86 };
87 
88 static const int8_t sol_table_old[16] = {
89  0x0, 0x1, 0x2, 0x3, 0x6, 0xA, 0xF, 0x15,
90  -0x15, -0xF, -0xA, -0x6, -0x3, -0x2, -0x1, 0x0
91 };
92 
93 static const int8_t sol_table_new[16] = {
94  0x0, 0x1, 0x2, 0x3, 0x6, 0xA, 0xF, 0x15,
95  0x0, -0x1, -0x2, -0x3, -0x6, -0xA, -0xF, -0x15
96 };
97 
98 static const int16_t sol_table_16[128] = {
99  0x000, 0x008, 0x010, 0x020, 0x030, 0x040, 0x050, 0x060, 0x070, 0x080,
100  0x090, 0x0A0, 0x0B0, 0x0C0, 0x0D0, 0x0E0, 0x0F0, 0x100, 0x110, 0x120,
101  0x130, 0x140, 0x150, 0x160, 0x170, 0x180, 0x190, 0x1A0, 0x1B0, 0x1C0,
102  0x1D0, 0x1E0, 0x1F0, 0x200, 0x208, 0x210, 0x218, 0x220, 0x228, 0x230,
103  0x238, 0x240, 0x248, 0x250, 0x258, 0x260, 0x268, 0x270, 0x278, 0x280,
104  0x288, 0x290, 0x298, 0x2A0, 0x2A8, 0x2B0, 0x2B8, 0x2C0, 0x2C8, 0x2D0,
105  0x2D8, 0x2E0, 0x2E8, 0x2F0, 0x2F8, 0x300, 0x308, 0x310, 0x318, 0x320,
106  0x328, 0x330, 0x338, 0x340, 0x348, 0x350, 0x358, 0x360, 0x368, 0x370,
107  0x378, 0x380, 0x388, 0x390, 0x398, 0x3A0, 0x3A8, 0x3B0, 0x3B8, 0x3C0,
108  0x3C8, 0x3D0, 0x3D8, 0x3E0, 0x3E8, 0x3F0, 0x3F8, 0x400, 0x440, 0x480,
109  0x4C0, 0x500, 0x540, 0x580, 0x5C0, 0x600, 0x640, 0x680, 0x6C0, 0x700,
110  0x740, 0x780, 0x7C0, 0x800, 0x900, 0xA00, 0xB00, 0xC00, 0xD00, 0xE00,
111  0xF00, 0x1000, 0x1400, 0x1800, 0x1C00, 0x2000, 0x3000, 0x4000
112 };
113 
114 
116 {
117  DPCMContext *s = avctx->priv_data;
118  int i;
119 
120  if (avctx->channels < 1 || avctx->channels > 2) {
121  av_log(avctx, AV_LOG_ERROR, "invalid number of channels\n");
122  return AVERROR(EINVAL);
123  }
124 
125  s->sample[0] = s->sample[1] = 0;
126 
127  switch(avctx->codec->id) {
128 
130  /* initialize square table */
131  for (i = 0; i < 128; i++) {
132  int16_t square = i * i;
133  s->roq_square_array[i ] = square;
134  s->roq_square_array[i + 128] = -square;
135  }
136  break;
137 
139  switch(avctx->codec_tag){
140  case 1:
142  s->sample[0] = s->sample[1] = 0x80;
143  break;
144  case 2:
146  s->sample[0] = s->sample[1] = 0x80;
147  break;
148  case 3:
149  break;
150  default:
151  av_log(avctx, AV_LOG_ERROR, "Unknown SOL subcodec\n");
152  return -1;
153  }
154  break;
155 
156  default:
157  break;
158  }
159 
160  if (avctx->codec->id == AV_CODEC_ID_SOL_DPCM && avctx->codec_tag != 3)
161  avctx->sample_fmt = AV_SAMPLE_FMT_U8;
162  else
163  avctx->sample_fmt = AV_SAMPLE_FMT_S16;
164 
165  return 0;
166 }
167 
168 
169 static int dpcm_decode_frame(AVCodecContext *avctx, void *data,
170  int *got_frame_ptr, AVPacket *avpkt)
171 {
172  int buf_size = avpkt->size;
173  DPCMContext *s = avctx->priv_data;
174  AVFrame *frame = data;
175  int out = 0, ret;
176  int predictor[2];
177  int ch = 0;
178  int stereo = avctx->channels - 1;
179  int16_t *output_samples, *samples_end;
180  GetByteContext gb;
181 
182  if (stereo && (buf_size & 1))
183  buf_size--;
184  bytestream2_init(&gb, avpkt->data, buf_size);
185 
186  /* calculate output size */
187  switch(avctx->codec->id) {
189  out = buf_size - 8;
190  break;
192  out = buf_size - 6 - avctx->channels;
193  break;
195  out = buf_size - 2 * avctx->channels;
196  break;
198  if (avctx->codec_tag != 3)
199  out = buf_size * 2;
200  else
201  out = buf_size;
202  break;
203  }
204  if (out <= 0) {
205  av_log(avctx, AV_LOG_ERROR, "packet is too small\n");
206  return AVERROR(EINVAL);
207  }
208  if (out % avctx->channels) {
209  av_log(avctx, AV_LOG_WARNING, "channels have differing number of samples\n");
210  }
211 
212  /* get output buffer */
213  frame->nb_samples = (out + avctx->channels - 1) / avctx->channels;
214  if ((ret = ff_get_buffer(avctx, frame, 0)) < 0)
215  return ret;
216  output_samples = (int16_t *)frame->data[0];
217  samples_end = output_samples + out;
218 
219  switch(avctx->codec->id) {
220 
222  bytestream2_skipu(&gb, 6);
223 
224  if (stereo) {
225  predictor[1] = sign_extend(bytestream2_get_byteu(&gb) << 8, 16);
226  predictor[0] = sign_extend(bytestream2_get_byteu(&gb) << 8, 16);
227  } else {
228  predictor[0] = sign_extend(bytestream2_get_le16u(&gb), 16);
229  }
230 
231  /* decode the samples */
232  while (output_samples < samples_end) {
233  predictor[ch] += s->roq_square_array[bytestream2_get_byteu(&gb)];
234  predictor[ch] = av_clip_int16(predictor[ch]);
235  *output_samples++ = predictor[ch];
236 
237  /* toggle channel */
238  ch ^= stereo;
239  }
240  break;
241 
243  bytestream2_skipu(&gb, 6); /* skip over the stream mask and stream length */
244 
245  for (ch = 0; ch < avctx->channels; ch++) {
246  predictor[ch] = sign_extend(bytestream2_get_le16u(&gb), 16);
247  *output_samples++ = predictor[ch];
248  }
249 
250  ch = 0;
251  while (output_samples < samples_end) {
252  predictor[ch] += interplay_delta_table[bytestream2_get_byteu(&gb)];
253  predictor[ch] = av_clip_int16(predictor[ch]);
254  *output_samples++ = predictor[ch];
255 
256  /* toggle channel */
257  ch ^= stereo;
258  }
259  break;
260 
262  {
263  int shift[2] = { 4, 4 };
264 
265  for (ch = 0; ch < avctx->channels; ch++)
266  predictor[ch] = sign_extend(bytestream2_get_le16u(&gb), 16);
267 
268  ch = 0;
269  while (output_samples < samples_end) {
270  int diff = bytestream2_get_byteu(&gb);
271  int n = diff & 3;
272 
273  if (n == 3)
274  shift[ch]++;
275  else
276  shift[ch] -= (2 * n);
277  diff = sign_extend((diff &~ 3) << 8, 16);
278 
279  /* saturate the shifter to a lower limit of 0 */
280  if (shift[ch] < 0)
281  shift[ch] = 0;
282 
283  diff >>= shift[ch];
284  predictor[ch] += diff;
285 
286  predictor[ch] = av_clip_int16(predictor[ch]);
287  *output_samples++ = predictor[ch];
288 
289  /* toggle channel */
290  ch ^= stereo;
291  }
292  break;
293  }
295  if (avctx->codec_tag != 3) {
296  uint8_t *output_samples_u8 = frame->data[0],
297  *samples_end_u8 = output_samples_u8 + out;
298  while (output_samples_u8 < samples_end_u8) {
299  int n = bytestream2_get_byteu(&gb);
300 
301  s->sample[0] += s->sol_table[n >> 4];
302  s->sample[0] = av_clip_uint8(s->sample[0]);
303  *output_samples_u8++ = s->sample[0];
304 
305  s->sample[stereo] += s->sol_table[n & 0x0F];
306  s->sample[stereo] = av_clip_uint8(s->sample[stereo]);
307  *output_samples_u8++ = s->sample[stereo];
308  }
309  } else {
310  while (output_samples < samples_end) {
311  int n = bytestream2_get_byteu(&gb);
312  if (n & 0x80) s->sample[ch] -= sol_table_16[n & 0x7F];
313  else s->sample[ch] += sol_table_16[n & 0x7F];
314  s->sample[ch] = av_clip_int16(s->sample[ch]);
315  *output_samples++ = s->sample[ch];
316  /* toggle channel */
317  ch ^= stereo;
318  }
319  }
320  break;
321  }
322 
323  *got_frame_ptr = 1;
324 
325  return avpkt->size;
326 }
327 
328 #define DPCM_DECODER(id_, name_, long_name_) \
329 AVCodec ff_ ## name_ ## _decoder = { \
330  .name = #name_, \
331  .type = AVMEDIA_TYPE_AUDIO, \
332  .id = id_, \
333  .priv_data_size = sizeof(DPCMContext), \
334  .init = dpcm_decode_init, \
335  .decode = dpcm_decode_frame, \
336  .capabilities = CODEC_CAP_DR1, \
337  .long_name = NULL_IF_CONFIG_SMALL(long_name_), \
338 }
339 
340 DPCM_DECODER(AV_CODEC_ID_INTERPLAY_DPCM, interplay_dpcm, "DPCM Interplay");
341 DPCM_DECODER(AV_CODEC_ID_ROQ_DPCM, roq_dpcm, "DPCM id RoQ");
342 DPCM_DECODER(AV_CODEC_ID_SOL_DPCM, sol_dpcm, "DPCM Sol");
343 DPCM_DECODER(AV_CODEC_ID_XAN_DPCM, xan_dpcm, "DPCM Xan");
const struct AVCodec * codec
const char * s
Definition: avisynth_c.h:668
static int shift(int a, int b)
Definition: sonic.c:86
int16_t roq_square_array[256]
Definition: dpcm.c:47
This structure describes decoded (raw) audio or video data.
Definition: frame.h:76
static const int8_t sol_table_old[16]
Definition: dpcm.c:88
#define AV_LOG_WARNING
Something somehow does not look correct.
Definition: log.h:154
const int8_t * sol_table
delta table for SOL_DPCM
Definition: dpcm.c:49
static av_always_inline void bytestream2_init(GetByteContext *g, const uint8_t *buf, int buf_size)
Definition: bytestream.h:130
signed 16 bits
Definition: samplefmt.h:52
initialize output if(nPeaks >3)%at least 3 peaks in spectrum for trying to find f0 nf0peaks
enum AVSampleFormat sample_fmt
audio sample format
uint8_t
#define av_cold
Definition: attributes.h:78
AV_SAMPLE_FMT_U8
static const int16_t interplay_delta_table[]
Definition: dpcm.c:52
uint8_t * data
static av_always_inline void bytestream2_skipu(GetByteContext *g, unsigned int size)
Definition: bytestream.h:165
frame
Definition: stft.m:14
static void predictor(uint8_t *src, int size)
Definition: exr.c:188
enum AVCodecID id
static const int8_t sol_table_new[16]
Definition: dpcm.c:93
Spectrum Plot time data
static int dpcm_decode_frame(AVCodecContext *avctx, void *data, int *got_frame_ptr, AVPacket *avpkt)
Definition: dpcm.c:169
void av_log(void *avcl, int level, const char *fmt,...)
Definition: log.c:246
static int square(int x)
Definition: roqvideoenc.c:111
external API header
ret
Definition: avfilter.c:821
#define diff(a, as, b, bs)
Definition: vf_phase.c:80
static const int16_t sol_table_16[128]
Definition: dpcm.c:98
main external API structure.
int ff_get_buffer(AVCodecContext *avctx, AVFrame *frame, int flags)
Get a buffer for a frame.
#define AV_LOG_ERROR
Something went wrong and cannot losslessly be recovered.
Definition: log.h:148
unsigned int codec_tag
fourcc (LSB first, so "ABCD" -> (&#39;D&#39;<<24) + (&#39;C&#39;<<16) + (&#39;B&#39;<<8) + &#39;A&#39;).
synthesis window for stochastic i
Filter the word “frame” indicates either a video frame or a group of audio as stored in an AVFilterBuffer 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.Buffer references ownership and permissions
static av_const int sign_extend(int val, unsigned bits)
Definition: mathops.h:123
uint8_t * data[AV_NUM_DATA_POINTERS]
pointer to the picture/channel planes.
Definition: frame.h:87
#define DPCM_DECODER(id_, name_, long_name_)
Definition: dpcm.c:328
common internal api header.
static av_cold int dpcm_decode_init(AVCodecContext *avctx)
Definition: dpcm.c:115
struct DPCMContext DPCMContext
int channels
number of audio channels
uint8_t pi<< 24) CONV_FUNC_GROUP(AV_SAMPLE_FMT_FLT, float, AV_SAMPLE_FMT_U8, uint8_t,(*(const uint8_t *) pi-0x80)*(1.0f/(1<< 7))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_DBL, double, AV_SAMPLE_FMT_U8, uint8_t,(*(const uint8_t *) pi-0x80)*(1.0/(1<< 7))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_U8, uint8_t, AV_SAMPLE_FMT_S16, int16_t,(*(const int16_t *) pi >> 8)+0x80) CONV_FUNC_GROUP(AV_SAMPLE_FMT_FLT, float, AV_SAMPLE_FMT_S16, int16_t,*(const int16_t *) pi *(1.0f/(1<< 15))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_DBL, double, AV_SAMPLE_FMT_S16, int16_t,*(const int16_t *) pi *(1.0/(1<< 15))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_U8, uint8_t, AV_SAMPLE_FMT_S32, int32_t,(*(const int32_t *) pi >> 24)+0x80) CONV_FUNC_GROUP(AV_SAMPLE_FMT_FLT, float, AV_SAMPLE_FMT_S32, int32_t,*(const int32_t *) pi *(1.0f/(1U<< 31))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_DBL, double, AV_SAMPLE_FMT_S32, int32_t,*(const int32_t *) pi *(1.0/(1U<< 31))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_U8, uint8_t, AV_SAMPLE_FMT_FLT, float, av_clip_uint8(lrintf(*(const float *) pi *(1<< 7))+0x80)) CONV_FUNC_GROUP(AV_SAMPLE_FMT_S16, int16_t, AV_SAMPLE_FMT_FLT, float, av_clip_int16(lrintf(*(const float *) pi *(1<< 15)))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_S32, int32_t, AV_SAMPLE_FMT_FLT, float, av_clipl_int32(llrintf(*(const float *) pi *(1U<< 31)))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_U8, uint8_t, AV_SAMPLE_FMT_DBL, double, av_clip_uint8(lrint(*(const double *) pi *(1<< 7))+0x80)) CONV_FUNC_GROUP(AV_SAMPLE_FMT_S16, int16_t, AV_SAMPLE_FMT_DBL, double, av_clip_int16(lrint(*(const double *) pi *(1<< 15)))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_S32, int32_t, AV_SAMPLE_FMT_DBL, double, av_clipl_int32(llrint(*(const double *) pi *(1U<< 31))))#define SET_CONV_FUNC_GROUP(ofmt, ifmt) static void set_generic_function(AudioConvert *ac){}void ff_audio_convert_free(AudioConvert **ac){if(!*ac) return;ff_dither_free(&(*ac) ->dc);av_freep(ac);}AudioConvert *ff_audio_convert_alloc(AVAudioResampleContext *avr, enum AVSampleFormat out_fmt, enum AVSampleFormat in_fmt, int channels, int sample_rate, int apply_map){AudioConvert *ac;int in_planar, out_planar;ac=av_mallocz(sizeof(*ac));if(!ac) return NULL;ac->avr=avr;ac->out_fmt=out_fmt;ac->in_fmt=in_fmt;ac->channels=channels;ac->apply_map=apply_map;if(avr->dither_method!=AV_RESAMPLE_DITHER_NONE &&av_get_packed_sample_fmt(out_fmt)==AV_SAMPLE_FMT_S16 &&av_get_bytes_per_sample(in_fmt) > 2){ac->dc=ff_dither_alloc(avr, out_fmt, in_fmt, channels, sample_rate, apply_map);if(!ac->dc){av_free(ac);return NULL;}return ac;}in_planar=av_sample_fmt_is_planar(in_fmt);out_planar=av_sample_fmt_is_planar(out_fmt);if(in_planar==out_planar){ac->func_type=CONV_FUNC_TYPE_FLAT;ac->planes=in_planar?ac->channels:1;}else if(in_planar) ac->func_type=CONV_FUNC_TYPE_INTERLEAVE;else ac->func_type=CONV_FUNC_TYPE_DEINTERLEAVE;set_generic_function(ac);if(ARCH_ARM) ff_audio_convert_init_arm(ac);if(ARCH_X86) ff_audio_convert_init_x86(ac);return ac;}int ff_audio_convert(AudioConvert *ac, AudioData *out, AudioData *in){int use_generic=1;int len=in->nb_samples;int p;if(ac->dc){av_dlog(ac->avr,"%d samples - audio_convert: %s to %s (dithered)\n", len, av_get_sample_fmt_name(ac->in_fmt), av_get_sample_fmt_name(ac->out_fmt));return ff_convert_dither(ac-> out
This structure stores compressed data.
int sample[2]
previous sample (for SOL_DPCM)
Definition: dpcm.c:48
int nb_samples
number of audio samples (per channel) described by this frame
Definition: frame.h:127