FFmpeg
roqaudioenc.c
Go to the documentation of this file.
1 /*
2  * RoQ audio encoder
3  *
4  * Copyright (c) 2005 Eric Lasota
5  * Based on RoQ specs (c)2001 Tim Ferguson
6  *
7  * This file is part of FFmpeg.
8  *
9  * FFmpeg is free software; you can redistribute it and/or
10  * modify it under the terms of the GNU Lesser General Public
11  * License as published by the Free Software Foundation; either
12  * version 2.1 of the License, or (at your option) any later version.
13  *
14  * FFmpeg is distributed in the hope that it will be useful,
15  * but WITHOUT ANY WARRANTY; without even the implied warranty of
16  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
17  * Lesser General Public License for more details.
18  *
19  * You should have received a copy of the GNU Lesser General Public
20  * License along with FFmpeg; if not, write to the Free Software
21  * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
22  */
23 
24 #include "avcodec.h"
25 #include "bytestream.h"
26 #include "internal.h"
27 #include "mathops.h"
28 
29 #define ROQ_FRAME_SIZE 735
30 #define ROQ_HEADER_SIZE 8
31 
32 #define MAX_DPCM (127*127)
33 
34 
35 typedef struct ROQDPCMContext {
36  short lastSample[2];
39  int16_t *frame_buffer;
40  int64_t first_pts;
42 
43 
45 {
47 
48  av_freep(&context->frame_buffer);
49 
50  return 0;
51 }
52 
54 {
56  int ret;
57 
58  if (avctx->channels > 2) {
59  av_log(avctx, AV_LOG_ERROR, "Audio must be mono or stereo\n");
60  return AVERROR(EINVAL);
61  }
62  if (avctx->sample_rate != 22050) {
63  av_log(avctx, AV_LOG_ERROR, "Audio must be 22050 Hz\n");
64  return AVERROR(EINVAL);
65  }
66 
67  avctx->frame_size = ROQ_FRAME_SIZE;
68  avctx->bit_rate = (ROQ_HEADER_SIZE + ROQ_FRAME_SIZE * avctx->channels) *
69  (22050 / ROQ_FRAME_SIZE) * 8;
70 
71  context->frame_buffer = av_malloc(8 * ROQ_FRAME_SIZE * avctx->channels *
72  sizeof(*context->frame_buffer));
73  if (!context->frame_buffer) {
74  ret = AVERROR(ENOMEM);
75  goto error;
76  }
77 
78  context->lastSample[0] = context->lastSample[1] = 0;
79 
80  return 0;
81 error:
82  roq_dpcm_encode_close(avctx);
83  return ret;
84 }
85 
86 static unsigned char dpcm_predict(short *previous, short current)
87 {
88  int diff;
89  int negative;
90  int result;
91  int predicted;
92 
93  diff = current - *previous;
94 
95  negative = diff<0;
96  diff = FFABS(diff);
97 
98  if (diff >= MAX_DPCM)
99  result = 127;
100  else {
101  result = ff_sqrt(diff);
102  result += diff > result*result+result;
103  }
104 
105  /* See if this overflows */
106  retry:
107  diff = result*result;
108  if (negative)
109  diff = -diff;
110  predicted = *previous + diff;
111 
112  /* If it overflows, back off a step */
113  if (predicted > 32767 || predicted < -32768) {
114  result--;
115  goto retry;
116  }
117 
118  /* Add the sign bit */
119  result |= negative << 7; //if (negative) result |= 128;
120 
121  *previous = predicted;
122 
123  return result;
124 }
125 
127  const AVFrame *frame, int *got_packet_ptr)
128 {
129  int i, stereo, data_size, ret;
130  const int16_t *in = frame ? (const int16_t *)frame->data[0] : NULL;
131  uint8_t *out;
132  ROQDPCMContext *context = avctx->priv_data;
133 
134  stereo = (avctx->channels == 2);
135 
136  if (!in && context->input_frames >= 8)
137  return 0;
138 
139  if (in && context->input_frames < 8) {
140  memcpy(&context->frame_buffer[context->buffered_samples * avctx->channels],
141  in, avctx->frame_size * avctx->channels * sizeof(*in));
142  context->buffered_samples += avctx->frame_size;
143  if (context->input_frames == 0)
144  context->first_pts = frame->pts;
145  if (context->input_frames < 7) {
146  context->input_frames++;
147  return 0;
148  }
149  }
150  if (context->input_frames < 8)
151  in = context->frame_buffer;
152 
153  if (stereo) {
154  context->lastSample[0] &= 0xFF00;
155  context->lastSample[1] &= 0xFF00;
156  }
157 
158  if (context->input_frames == 7)
159  data_size = avctx->channels * context->buffered_samples;
160  else
161  data_size = avctx->channels * avctx->frame_size;
162 
163  if ((ret = ff_alloc_packet2(avctx, avpkt, ROQ_HEADER_SIZE + data_size, 0)) < 0)
164  return ret;
165  out = avpkt->data;
166 
167  bytestream_put_byte(&out, stereo ? 0x21 : 0x20);
168  bytestream_put_byte(&out, 0x10);
169  bytestream_put_le32(&out, data_size);
170 
171  if (stereo) {
172  bytestream_put_byte(&out, (context->lastSample[1])>>8);
173  bytestream_put_byte(&out, (context->lastSample[0])>>8);
174  } else
175  bytestream_put_le16(&out, context->lastSample[0]);
176 
177  /* Write the actual samples */
178  for (i = 0; i < data_size; i++)
179  *out++ = dpcm_predict(&context->lastSample[i & 1], *in++);
180 
181  avpkt->pts = context->input_frames <= 7 ? context->first_pts : frame->pts;
182  avpkt->duration = data_size / avctx->channels;
183 
184  context->input_frames++;
185  if (!in)
186  context->input_frames = FFMAX(context->input_frames, 8);
187 
188  *got_packet_ptr = 1;
189  return 0;
190 }
191 
193  .name = "roq_dpcm",
194  .long_name = NULL_IF_CONFIG_SMALL("id RoQ DPCM"),
195  .type = AVMEDIA_TYPE_AUDIO,
196  .id = AV_CODEC_ID_ROQ_DPCM,
197  .priv_data_size = sizeof(ROQDPCMContext),
199  .encode2 = roq_dpcm_encode_frame,
200  .close = roq_dpcm_encode_close,
201  .capabilities = AV_CODEC_CAP_DELAY,
202  .sample_fmts = (const enum AVSampleFormat[]){ AV_SAMPLE_FMT_S16,
204 };
#define NULL
Definition: coverity.c:32
This structure describes decoded (raw) audio or video data.
Definition: frame.h:295
int64_t bit_rate
the average bitrate
Definition: avcodec.h:1615
static av_cold int init(AVCodecContext *avctx)
Definition: avrndec.c:35
AVCodec.
Definition: avcodec.h:3481
short lastSample[2]
Definition: roqaudioenc.c:36
#define AV_CODEC_CAP_DELAY
Encoder or decoder requires flushing with NULL input at the end in order to give the complete and cor...
Definition: avcodec.h:1006
int ff_alloc_packet2(AVCodecContext *avctx, AVPacket *avpkt, int64_t size, int64_t min_size)
Check AVPacket size and/or allocate data.
Definition: encode.c:32
int64_t first_pts
Definition: roqaudioenc.c:40
uint8_t
#define av_cold
Definition: attributes.h:82
static av_cold int roq_dpcm_encode_close(AVCodecContext *avctx)
Definition: roqaudioenc.c:44
#define av_malloc(s)
int64_t duration
Duration of this packet in AVStream->time_base units, 0 if unknown.
Definition: avcodec.h:1495
int64_t pts
Presentation timestamp in time_base units (time when frame should be shown to user).
Definition: frame.h:388
int buffered_samples
Definition: roqaudioenc.c:38
uint8_t * data
Definition: avcodec.h:1477
#define av_log(a,...)
#define ff_sqrt
Definition: mathops.h:206
#define i(width, name, range_min, range_max)
Definition: cbs_h2645.c:259
#define AV_LOG_ERROR
Something went wrong and cannot losslessly be recovered.
Definition: log.h:176
#define NULL_IF_CONFIG_SMALL(x)
Return NULL if CONFIG_SMALL is true, otherwise the argument without modification. ...
Definition: internal.h:186
const char * name
Name of the codec implementation.
Definition: avcodec.h:3488
#define FFMAX(a, b)
Definition: common.h:94
int16_t * frame_buffer
Definition: roqaudioenc.c:39
static int roq_dpcm_encode_frame(AVCodecContext *avctx, AVPacket *avpkt, const AVFrame *frame, int *got_packet_ptr)
Definition: roqaudioenc.c:126
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
#define FFABS(a)
Absolute value, Note, INT_MIN / INT64_MIN result in undefined behavior as they are not representable ...
Definition: common.h:72
static void error(const char *err)
static av_cold int roq_dpcm_encode_init(AVCodecContext *avctx)
Definition: roqaudioenc.c:53
int frame_size
Number of samples per channel in an audio frame.
Definition: avcodec.h:2245
Libavcodec external API header.
AVSampleFormat
Audio sample formats.
Definition: samplefmt.h:58
int sample_rate
samples per second
Definition: avcodec.h:2225
main external API structure.
Definition: avcodec.h:1565
static unsigned char dpcm_predict(short *previous, short current)
Definition: roqaudioenc.c:86
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=ff_sample_fmt_is_planar(in_fmt, channels);out_planar=ff_sample_fmt_is_planar(out_fmt, channels);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_AARCH64) ff_audio_convert_init_aarch64(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_log(ac->avr, AV_LOG_TRACE,"%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-> in
uint8_t * data[AV_NUM_DATA_POINTERS]
pointer to the picture/channel planes.
Definition: frame.h:309
common internal api header.
signed 16 bits
Definition: samplefmt.h:61
void * priv_data
Definition: avcodec.h:1592
static av_always_inline int diff(const uint32_t a, const uint32_t b)
int channels
number of audio channels
Definition: avcodec.h:2226
#define ROQ_FRAME_SIZE
Definition: roqaudioenc.c:29
and forward the result(frame or status change) to the corresponding input.If nothing is possible
static enum AVSampleFormat sample_fmts[]
Definition: adpcmenc.c:701
FILE * out
Definition: movenc.c:54
AVCodec ff_roq_dpcm_encoder
Definition: roqaudioenc.c:192
#define av_freep(p)
#define ROQ_HEADER_SIZE
Definition: roqaudioenc.c:30
#define MAX_DPCM
Definition: roqaudioenc.c:32
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
it s the only field you need to keep assuming you have a context There is some magic you don t need to care about around this just let it vf default minimum maximum flags name is the option keep it simple and lowercase description are in without and describe what they for example set the foo of the bar offset is the offset of the field in your local context
This structure stores compressed data.
Definition: avcodec.h:1454
int64_t pts
Presentation timestamp in AVStream->time_base units; the time at which the decompressed packet will b...
Definition: avcodec.h:1470