1 /*
2 * Copyright (c) 2011 Stefano Sabatini
3 *
4 * This file is part of FFmpeg.
5 *
6 * FFmpeg 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 * FFmpeg 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 FFmpeg; 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/timestamp.h"
38 #include "libavutil/samplefmt.h"
39
40 #include "libavcodec/avcodec.h"
41
42 #include "audio.h"
43 #include "avfilter.h"
44 #include "internal.h"
45
46 typedef struct AShowInfoContext {
47 /**
48 * Scratch space for individual plane checksums for planar audio
49 */
50 uint32_t *plane_checksums;
51 } AShowInfoContext;
52
uninit(AVFilterContext * ctx)53 static av_cold void uninit(AVFilterContext *ctx)
54 {
55 AShowInfoContext *s = ctx->priv;
56 av_freep(&s->plane_checksums);
57 }
58
dump_matrixenc(AVFilterContext * ctx,AVFrameSideData * sd)59 static void dump_matrixenc(AVFilterContext *ctx, AVFrameSideData *sd)
60 {
61 enum AVMatrixEncoding enc;
62
63 av_log(ctx, AV_LOG_INFO, "matrix encoding: ");
64
65 if (sd->size < sizeof(enum AVMatrixEncoding)) {
66 av_log(ctx, AV_LOG_INFO, "invalid data");
67 return;
68 }
69
70 enc = *(enum AVMatrixEncoding *)sd->data;
71 switch (enc) {
72 case AV_MATRIX_ENCODING_NONE: av_log(ctx, AV_LOG_INFO, "none"); break;
73 case AV_MATRIX_ENCODING_DOLBY: av_log(ctx, AV_LOG_INFO, "Dolby Surround"); break;
74 case AV_MATRIX_ENCODING_DPLII: av_log(ctx, AV_LOG_INFO, "Dolby Pro Logic II"); break;
75 case AV_MATRIX_ENCODING_DPLIIX: av_log(ctx, AV_LOG_INFO, "Dolby Pro Logic IIx"); break;
76 case AV_MATRIX_ENCODING_DPLIIZ: av_log(ctx, AV_LOG_INFO, "Dolby Pro Logic IIz"); break;
77 case AV_MATRIX_ENCODING_DOLBYEX: av_log(ctx, AV_LOG_INFO, "Dolby EX"); break;
78 case AV_MATRIX_ENCODING_DOLBYHEADPHONE: av_log(ctx, AV_LOG_INFO, "Dolby Headphone"); break;
79 default: av_log(ctx, AV_LOG_WARNING, "unknown"); break;
80 }
81 }
82
dump_downmix(AVFilterContext * ctx,AVFrameSideData * sd)83 static void dump_downmix(AVFilterContext *ctx, AVFrameSideData *sd)
84 {
85 AVDownmixInfo *di;
86
87 av_log(ctx, AV_LOG_INFO, "downmix: ");
88 if (sd->size < sizeof(*di)) {
89 av_log(ctx, AV_LOG_INFO, "invalid data");
90 return;
91 }
92
93 di = (AVDownmixInfo *)sd->data;
94
95 av_log(ctx, AV_LOG_INFO, "preferred downmix type - ");
96 switch (di->preferred_downmix_type) {
97 case AV_DOWNMIX_TYPE_LORO: av_log(ctx, AV_LOG_INFO, "Lo/Ro"); break;
98 case AV_DOWNMIX_TYPE_LTRT: av_log(ctx, AV_LOG_INFO, "Lt/Rt"); break;
99 case AV_DOWNMIX_TYPE_DPLII: av_log(ctx, AV_LOG_INFO, "Dolby Pro Logic II"); break;
100 default: av_log(ctx, AV_LOG_WARNING, "unknown"); break;
101 }
102
103 av_log(ctx, AV_LOG_INFO, " Mix levels: center %f (%f ltrt) - "
104 "surround %f (%f ltrt) - lfe %f",
105 di->center_mix_level, di->center_mix_level_ltrt,
106 di->surround_mix_level, di->surround_mix_level_ltrt,
107 di->lfe_mix_level);
108 }
109
print_gain(AVFilterContext * ctx,const char * str,int32_t gain)110 static void print_gain(AVFilterContext *ctx, const char *str, int32_t gain)
111 {
112 av_log(ctx, AV_LOG_INFO, "%s - ", str);
113 if (gain == INT32_MIN)
114 av_log(ctx, AV_LOG_INFO, "unknown");
115 else
116 av_log(ctx, AV_LOG_INFO, "%f", gain / 100000.0f);
117 av_log(ctx, AV_LOG_INFO, ", ");
118 }
119
print_peak(AVFilterContext * ctx,const char * str,uint32_t peak)120 static void print_peak(AVFilterContext *ctx, const char *str, uint32_t peak)
121 {
122 av_log(ctx, AV_LOG_INFO, "%s - ", str);
123 if (!peak)
124 av_log(ctx, AV_LOG_INFO, "unknown");
125 else
126 av_log(ctx, AV_LOG_INFO, "%f", (float)peak / UINT32_MAX);
127 av_log(ctx, AV_LOG_INFO, ", ");
128 }
129
dump_replaygain(AVFilterContext * ctx,AVFrameSideData * sd)130 static void dump_replaygain(AVFilterContext *ctx, AVFrameSideData *sd)
131 {
132 AVReplayGain *rg;
133
134 av_log(ctx, AV_LOG_INFO, "replaygain: ");
135 if (sd->size < sizeof(*rg)) {
136 av_log(ctx, AV_LOG_INFO, "invalid data");
137 return;
138 }
139 rg = (AVReplayGain*)sd->data;
140
141 print_gain(ctx, "track gain", rg->track_gain);
142 print_peak(ctx, "track peak", rg->track_peak);
143 print_gain(ctx, "album gain", rg->album_gain);
144 print_peak(ctx, "album peak", rg->album_peak);
145 }
146
dump_audio_service_type(AVFilterContext * ctx,AVFrameSideData * sd)147 static void dump_audio_service_type(AVFilterContext *ctx, AVFrameSideData *sd)
148 {
149 enum AVAudioServiceType *ast;
150
151 av_log(ctx, AV_LOG_INFO, "audio service type: ");
152 if (sd->size < sizeof(*ast)) {
153 av_log(ctx, AV_LOG_INFO, "invalid data");
154 return;
155 }
156 ast = (enum AVAudioServiceType*)sd->data;
157 switch (*ast) {
158 case AV_AUDIO_SERVICE_TYPE_MAIN: av_log(ctx, AV_LOG_INFO, "Main Audio Service"); break;
159 case AV_AUDIO_SERVICE_TYPE_EFFECTS: av_log(ctx, AV_LOG_INFO, "Effects"); break;
160 case AV_AUDIO_SERVICE_TYPE_VISUALLY_IMPAIRED: av_log(ctx, AV_LOG_INFO, "Visually Impaired"); break;
161 case AV_AUDIO_SERVICE_TYPE_HEARING_IMPAIRED: av_log(ctx, AV_LOG_INFO, "Hearing Impaired"); break;
162 case AV_AUDIO_SERVICE_TYPE_DIALOGUE: av_log(ctx, AV_LOG_INFO, "Dialogue"); break;
163 case AV_AUDIO_SERVICE_TYPE_COMMENTARY: av_log(ctx, AV_LOG_INFO, "Commentary"); break;
164 case AV_AUDIO_SERVICE_TYPE_EMERGENCY: av_log(ctx, AV_LOG_INFO, "Emergency"); break;
165 case AV_AUDIO_SERVICE_TYPE_VOICE_OVER: av_log(ctx, AV_LOG_INFO, "Voice Over"); break;
166 case AV_AUDIO_SERVICE_TYPE_KARAOKE: av_log(ctx, AV_LOG_INFO, "Karaoke"); break;
167 default: av_log(ctx, AV_LOG_INFO, "unknown"); break;
168 }
169 }
170
dump_unknown(AVFilterContext * ctx,AVFrameSideData * sd)171 static void dump_unknown(AVFilterContext *ctx, AVFrameSideData *sd)
172 {
173 av_log(ctx, AV_LOG_INFO, "unknown side data type: %d, size %d bytes", sd->type, sd->size);
174 }
175
filter_frame(AVFilterLink * inlink,AVFrame * buf)176 static int filter_frame(AVFilterLink *inlink, AVFrame *buf)
177 {
178 AVFilterContext *ctx = inlink->dst;
179 AShowInfoContext *s = ctx->priv;
180 char chlayout_str[128];
181 uint32_t checksum = 0;
182 int channels = inlink->channels;
183 int planar = av_sample_fmt_is_planar(buf->format);
184 int block_align = av_get_bytes_per_sample(buf->format) * (planar ? 1 : channels);
185 int data_size = buf->nb_samples * block_align;
186 int planes = planar ? channels : 1;
187 int i;
188 void *tmp_ptr = av_realloc_array(s->plane_checksums, channels, sizeof(*s->plane_checksums));
189
190 if (!tmp_ptr)
191 return AVERROR(ENOMEM);
192 s->plane_checksums = tmp_ptr;
193
194 for (i = 0; i < planes; i++) {
195 uint8_t *data = buf->extended_data[i];
196
197 s->plane_checksums[i] = av_adler32_update(0, data, data_size);
198 checksum = i ? av_adler32_update(checksum, data, data_size) :
199 s->plane_checksums[0];
200 }
201
202 av_get_channel_layout_string(chlayout_str, sizeof(chlayout_str), buf->channels,
203 buf->channel_layout);
204
205 av_log(ctx, AV_LOG_INFO,
206 "n:%"PRId64" pts:%s pts_time:%s pos:%"PRId64" "
207 "fmt:%s channels:%d chlayout:%s rate:%d nb_samples:%d "
208 "checksum:%08"PRIX32" ",
209 inlink->frame_count_out,
210 av_ts2str(buf->pts), av_ts2timestr(buf->pts, &inlink->time_base),
211 buf->pkt_pos,
212 av_get_sample_fmt_name(buf->format), buf->channels, chlayout_str,
213 buf->sample_rate, buf->nb_samples,
214 checksum);
215
216 av_log(ctx, AV_LOG_INFO, "plane_checksums: [ ");
217 for (i = 0; i < planes; i++)
218 av_log(ctx, AV_LOG_INFO, "%08"PRIX32" ", s->plane_checksums[i]);
219 av_log(ctx, AV_LOG_INFO, "]\n");
220
221 for (i = 0; i < buf->nb_side_data; i++) {
222 AVFrameSideData *sd = buf->side_data[i];
223
224 av_log(ctx, AV_LOG_INFO, " side data - ");
225 switch (sd->type) {
226 case AV_FRAME_DATA_MATRIXENCODING: dump_matrixenc (ctx, sd); break;
227 case AV_FRAME_DATA_DOWNMIX_INFO: dump_downmix (ctx, sd); break;
228 case AV_FRAME_DATA_REPLAYGAIN: dump_replaygain(ctx, sd); break;
229 case AV_FRAME_DATA_AUDIO_SERVICE_TYPE: dump_audio_service_type(ctx, sd); break;
230 default: dump_unknown (ctx, sd); break;
231 }
232
233 av_log(ctx, AV_LOG_INFO, "\n");
234 }
235
236 return ff_filter_frame(inlink->dst->outputs[0], buf);
237 }
238
239 static const AVFilterPad inputs[] = {
240 {
241 .name = "default",
242 .type = AVMEDIA_TYPE_AUDIO,
243 .filter_frame = filter_frame,
244 },
245 { NULL }
246 };
247
248 static const AVFilterPad outputs[] = {
249 {
250 .name = "default",
251 .type = AVMEDIA_TYPE_AUDIO,
252 },
253 { NULL }
254 };
255
256 AVFilter ff_af_ashowinfo = {
257 .name = "ashowinfo",
258 .description = NULL_IF_CONFIG_SMALL("Show textual information for each audio frame."),
259 .priv_size = sizeof(AShowInfoContext),
260 .uninit = uninit,
261 .inputs = inputs,
262 .outputs = outputs,
263 };
264