h264_metadata: Add option to delete filler data
[libav.git] / libavfilter / af_ashowinfo.c
1 /*
2 * Copyright (c) 2011 Stefano Sabatini
3 *
4 * This file is part of Libav.
5 *
6 * Libav is free software; you can redistribute it and/or
7 * modify it under the terms of the GNU Lesser General Public
8 * License as published by the Free Software Foundation; either
9 * version 2.1 of the License, or (at your option) any later version.
10 *
11 * Libav is distributed in the hope that it will be useful,
12 * but WITHOUT ANY WARRANTY; without even the implied warranty of
13 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
14 * Lesser General Public License for more details.
15 *
16 * You should have received a copy of the GNU Lesser General Public
17 * License along with Libav; if not, write to the Free Software
18 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
19 */
20
21 /**
22 * @file
23 * filter for showing textual audio frame information
24 */
25
26 #include <inttypes.h>
27 #include <stddef.h>
28
29 #include "libavutil/adler32.h"
30 #include "libavutil/attributes.h"
31 #include "libavutil/channel_layout.h"
32 #include "libavutil/common.h"
33 #include "libavutil/downmix_info.h"
34 #include "libavutil/intreadwrite.h"
35 #include "libavutil/mem.h"
36 #include "libavutil/replaygain.h"
37 #include "libavutil/samplefmt.h"
38
39 #include "libavcodec/avcodec.h"
40
41 #include "audio.h"
42 #include "avfilter.h"
43 #include "internal.h"
44
45 typedef struct AShowInfoContext {
46 /**
47 * Scratch space for individual plane checksums for planar audio
48 */
49 uint32_t *plane_checksums;
50
51 /**
52 * Frame counter
53 */
54 uint64_t frame;
55 } AShowInfoContext;
56
57 static int config_input(AVFilterLink *inlink)
58 {
59 AShowInfoContext *s = inlink->dst->priv;
60 int channels = av_get_channel_layout_nb_channels(inlink->channel_layout);
61 s->plane_checksums = av_malloc(channels * sizeof(*s->plane_checksums));
62 if (!s->plane_checksums)
63 return AVERROR(ENOMEM);
64
65 return 0;
66 }
67
68 static av_cold void uninit(AVFilterContext *ctx)
69 {
70 AShowInfoContext *s = ctx->priv;
71 av_freep(&s->plane_checksums);
72 }
73
74 static void dump_matrixenc(AVFilterContext *ctx, AVFrameSideData *sd)
75 {
76 enum AVMatrixEncoding enc;
77
78 av_log(ctx, AV_LOG_INFO, "matrix encoding: ");
79
80 if (sd->size < sizeof(enum AVMatrixEncoding)) {
81 av_log(ctx, AV_LOG_INFO, "invalid data");
82 return;
83 }
84
85 enc = *(enum AVMatrixEncoding *)sd->data;
86 switch (enc) {
87 case AV_MATRIX_ENCODING_NONE: av_log(ctx, AV_LOG_INFO, "none"); break;
88 case AV_MATRIX_ENCODING_DOLBY: av_log(ctx, AV_LOG_INFO, "Dolby Surround"); break;
89 case AV_MATRIX_ENCODING_DPLII: av_log(ctx, AV_LOG_INFO, "Dolby Pro Logic II"); break;
90 case AV_MATRIX_ENCODING_DPLIIX: av_log(ctx, AV_LOG_INFO, "Dolby Pro Logic IIx"); break;
91 case AV_MATRIX_ENCODING_DPLIIZ: av_log(ctx, AV_LOG_INFO, "Dolby Pro Logic IIz"); break;
92 case AV_MATRIX_ENCODING_DOLBYEX: av_log(ctx, AV_LOG_INFO, "Dolby EX"); break;
93 case AV_MATRIX_ENCODING_DOLBYHEADPHONE: av_log(ctx, AV_LOG_INFO, "Dolby Headphone"); break;
94 default: av_log(ctx, AV_LOG_WARNING, "unknown"); break;
95 }
96 }
97
98 static void dump_downmix(AVFilterContext *ctx, AVFrameSideData *sd)
99 {
100 AVDownmixInfo *di;
101
102 av_log(ctx, AV_LOG_INFO, "downmix: ");
103 if (sd->size < sizeof(*di)) {
104 av_log(ctx, AV_LOG_INFO, "invalid data");
105 return;
106 }
107
108 di = (AVDownmixInfo *)sd->data;
109
110 av_log(ctx, AV_LOG_INFO, "preferred downmix type - ");
111 switch (di->preferred_downmix_type) {
112 case AV_DOWNMIX_TYPE_LORO: av_log(ctx, AV_LOG_INFO, "Lo/Ro"); break;
113 case AV_DOWNMIX_TYPE_LTRT: av_log(ctx, AV_LOG_INFO, "Lt/Rt"); break;
114 case AV_DOWNMIX_TYPE_DPLII: av_log(ctx, AV_LOG_INFO, "Dolby Pro Logic II"); break;
115 default: av_log(ctx, AV_LOG_WARNING, "unknown"); break;
116 }
117
118 av_log(ctx, AV_LOG_INFO, " Mix levels: center %f (%f ltrt) - "
119 "surround %f (%f ltrt) - lfe %f",
120 di->center_mix_level, di->center_mix_level_ltrt,
121 di->surround_mix_level, di->surround_mix_level_ltrt,
122 di->lfe_mix_level);
123 }
124
125 static void print_gain(AVFilterContext *ctx, const char *str, int32_t gain)
126 {
127 av_log(ctx, AV_LOG_INFO, "%s - ", str);
128 if (gain == INT32_MIN)
129 av_log(ctx, AV_LOG_INFO, "unknown");
130 else
131 av_log(ctx, AV_LOG_INFO, "%f", gain / 100000.0f);
132 av_log(ctx, AV_LOG_INFO, ", ");
133 }
134
135 static void print_peak(AVFilterContext *ctx, const char *str, uint32_t peak)
136 {
137 av_log(ctx, AV_LOG_INFO, "%s - ", str);
138 if (!peak)
139 av_log(ctx, AV_LOG_INFO, "unknown");
140 else
141 av_log(ctx, AV_LOG_INFO, "%f", (float)peak / UINT32_MAX);
142 av_log(ctx, AV_LOG_INFO, ", ");
143 }
144
145 static void dump_replaygain(AVFilterContext *ctx, AVFrameSideData *sd)
146 {
147 AVReplayGain *rg;
148
149 av_log(ctx, AV_LOG_INFO, "replaygain: ");
150 if (sd->size < sizeof(*rg)) {
151 av_log(ctx, AV_LOG_INFO, "invalid data");
152 return;
153 }
154 rg = (AVReplayGain*)sd->data;
155
156 print_gain(ctx, "track gain", rg->track_gain);
157 print_peak(ctx, "track peak", rg->track_peak);
158 print_gain(ctx, "album gain", rg->album_gain);
159 print_peak(ctx, "album peak", rg->album_peak);
160 }
161
162 static void dump_audio_service_type(AVFilterContext *ctx, AVFrameSideData *sd)
163 {
164 enum AVAudioServiceType *ast;
165
166 av_log(ctx, AV_LOG_INFO, "audio service type: ");
167 if (sd->size < sizeof(*ast)) {
168 av_log(ctx, AV_LOG_INFO, "invalid data");
169 return;
170 }
171 ast = (enum AVAudioServiceType*)sd->data;
172 switch (*ast) {
173 case AV_AUDIO_SERVICE_TYPE_MAIN: av_log(ctx, AV_LOG_INFO, "Main Audio Service"); break;
174 case AV_AUDIO_SERVICE_TYPE_EFFECTS: av_log(ctx, AV_LOG_INFO, "Effects"); break;
175 case AV_AUDIO_SERVICE_TYPE_VISUALLY_IMPAIRED: av_log(ctx, AV_LOG_INFO, "Visually Impaired"); break;
176 case AV_AUDIO_SERVICE_TYPE_HEARING_IMPAIRED: av_log(ctx, AV_LOG_INFO, "Hearing Impaired"); break;
177 case AV_AUDIO_SERVICE_TYPE_DIALOGUE: av_log(ctx, AV_LOG_INFO, "Dialogue"); break;
178 case AV_AUDIO_SERVICE_TYPE_COMMENTARY: av_log(ctx, AV_LOG_INFO, "Commentary"); break;
179 case AV_AUDIO_SERVICE_TYPE_EMERGENCY: av_log(ctx, AV_LOG_INFO, "Emergency"); break;
180 case AV_AUDIO_SERVICE_TYPE_VOICE_OVER: av_log(ctx, AV_LOG_INFO, "Voice Over"); break;
181 case AV_AUDIO_SERVICE_TYPE_KARAOKE: av_log(ctx, AV_LOG_INFO, "Karaoke"); break;
182 default: av_log(ctx, AV_LOG_INFO, "unknown"); break;
183 }
184 }
185
186 static void dump_unknown(AVFilterContext *ctx, AVFrameSideData *sd)
187 {
188 av_log(ctx, AV_LOG_INFO, "unknown side data type: %d, size %d bytes", sd->type, sd->size);
189 }
190
191 static int filter_frame(AVFilterLink *inlink, AVFrame *buf)
192 {
193 AVFilterContext *ctx = inlink->dst;
194 AShowInfoContext *s = ctx->priv;
195 char chlayout_str[128];
196 uint32_t checksum = 0;
197 int channels = av_get_channel_layout_nb_channels(buf->channel_layout);
198 int planar = av_sample_fmt_is_planar(buf->format);
199 int block_align = av_get_bytes_per_sample(buf->format) * (planar ? 1 : channels);
200 int data_size = buf->nb_samples * block_align;
201 int planes = planar ? channels : 1;
202 int i;
203
204 for (i = 0; i < planes; i++) {
205 uint8_t *data = buf->extended_data[i];
206
207 s->plane_checksums[i] = av_adler32_update(0, data, data_size);
208 checksum = i ? av_adler32_update(checksum, data, data_size) :
209 s->plane_checksums[0];
210 }
211
212 av_get_channel_layout_string(chlayout_str, sizeof(chlayout_str), -1,
213 buf->channel_layout);
214
215 av_log(ctx, AV_LOG_INFO,
216 "n:%"PRIu64" pts:%"PRId64" pts_time:%f "
217 "fmt:%s chlayout:%s rate:%d nb_samples:%d "
218 "checksum:%08"PRIX32" ",
219 s->frame, buf->pts, buf->pts * av_q2d(inlink->time_base),
220 av_get_sample_fmt_name(buf->format), chlayout_str,
221 buf->sample_rate, buf->nb_samples,
222 checksum);
223
224 av_log(ctx, AV_LOG_INFO, "plane_checksums: [ ");
225 for (i = 0; i < planes; i++)
226 av_log(ctx, AV_LOG_INFO, "%08"PRIX32" ", s->plane_checksums[i]);
227 av_log(ctx, AV_LOG_INFO, "]\n");
228
229 for (i = 0; i < buf->nb_side_data; i++) {
230 AVFrameSideData *sd = buf->side_data[i];
231
232 av_log(ctx, AV_LOG_INFO, " side data - ");
233 switch (sd->type) {
234 case AV_FRAME_DATA_MATRIXENCODING: dump_matrixenc (ctx, sd); break;
235 case AV_FRAME_DATA_DOWNMIX_INFO: dump_downmix (ctx, sd); break;
236 case AV_FRAME_DATA_REPLAYGAIN: dump_replaygain(ctx, sd); break;
237 case AV_FRAME_DATA_AUDIO_SERVICE_TYPE: dump_audio_service_type(ctx, sd); break;
238 default: dump_unknown (ctx, sd); break;
239 }
240
241 av_log(ctx, AV_LOG_INFO, "\n");
242 }
243
244 s->frame++;
245 return ff_filter_frame(inlink->dst->outputs[0], buf);
246 }
247
248 static const AVFilterPad inputs[] = {
249 {
250 .name = "default",
251 .type = AVMEDIA_TYPE_AUDIO,
252 .get_audio_buffer = ff_null_get_audio_buffer,
253 .config_props = config_input,
254 .filter_frame = filter_frame,
255 },
256 { NULL },
257 };
258
259 static const AVFilterPad outputs[] = {
260 {
261 .name = "default",
262 .type = AVMEDIA_TYPE_AUDIO,
263 },
264 { NULL },
265 };
266
267 AVFilter ff_af_ashowinfo = {
268 .name = "ashowinfo",
269 .description = NULL_IF_CONFIG_SMALL("Show textual information for each audio frame."),
270 .priv_size = sizeof(AShowInfoContext),
271 .uninit = uninit,
272 .inputs = inputs,
273 .outputs = outputs,
274 };