af_ashowinfo.c 8.02 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29
/*
 * Copyright (c) 2011 Stefano Sabatini
 *
 * This file is part of Libav.
 *
 * Libav is free software; you can redistribute it and/or
 * modify it under the terms of the GNU Lesser General Public
 * License as published by the Free Software Foundation; either
 * version 2.1 of the License, or (at your option) any later version.
 *
 * Libav is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 * Lesser General Public License for more details.
 *
 * You should have received a copy of the GNU Lesser General Public
 * License along with Libav; if not, write to the Free Software
 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
 */

/**
 * @file
 * filter for showing textual audio frame information
 */

#include <inttypes.h>
#include <stddef.h>

#include "libavutil/adler32.h"
30
#include "libavutil/attributes.h"
31
#include "libavutil/channel_layout.h"
32
#include "libavutil/common.h"
33 34
#include "libavutil/downmix_info.h"
#include "libavutil/intreadwrite.h"
35
#include "libavutil/mem.h"
36
#include "libavutil/replaygain.h"
37 38 39 40
#include "libavutil/samplefmt.h"

#include "audio.h"
#include "avfilter.h"
41
#include "internal.h"
42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65

typedef struct AShowInfoContext {
    /**
     * Scratch space for individual plane checksums for planar audio
     */
    uint32_t *plane_checksums;

    /**
     * Frame counter
     */
    uint64_t frame;
} AShowInfoContext;

static int config_input(AVFilterLink *inlink)
{
    AShowInfoContext *s = inlink->dst->priv;
    int channels = av_get_channel_layout_nb_channels(inlink->channel_layout);
    s->plane_checksums = av_malloc(channels * sizeof(*s->plane_checksums));
    if (!s->plane_checksums)
        return AVERROR(ENOMEM);

    return 0;
}

66
static av_cold void uninit(AVFilterContext *ctx)
67 68 69 70 71
{
    AShowInfoContext *s = ctx->priv;
    av_freep(&s->plane_checksums);
}

72 73 74 75 76 77 78 79 80 81 82 83 84 85
static void dump_matrixenc(AVFilterContext *ctx, AVFrameSideData *sd)
{
    enum AVMatrixEncoding enc;

    av_log(ctx, AV_LOG_INFO, "matrix encoding: ");

    if (sd->size < sizeof(enum AVMatrixEncoding)) {
        av_log(ctx, AV_LOG_INFO, "invalid data");
        return;
    }

    enc = *(enum AVMatrixEncoding *)sd->data;
    switch (enc) {
    case AV_MATRIX_ENCODING_NONE:           av_log(ctx, AV_LOG_INFO, "none");                break;
86
    case AV_MATRIX_ENCODING_DOLBY:          av_log(ctx, AV_LOG_INFO, "Dolby Surround");      break;
87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164
    case AV_MATRIX_ENCODING_DPLII:          av_log(ctx, AV_LOG_INFO, "Dolby Pro Logic II");  break;
    case AV_MATRIX_ENCODING_DPLIIX:         av_log(ctx, AV_LOG_INFO, "Dolby Pro Logic IIx"); break;
    case AV_MATRIX_ENCODING_DPLIIZ:         av_log(ctx, AV_LOG_INFO, "Dolby Pro Logic IIz"); break;
    case AV_MATRIX_ENCODING_DOLBYEX:        av_log(ctx, AV_LOG_INFO, "Dolby EX");            break;
    case AV_MATRIX_ENCODING_DOLBYHEADPHONE: av_log(ctx, AV_LOG_INFO, "Dolby Headphone");     break;
    default:                                av_log(ctx, AV_LOG_WARNING, "unknown");          break;
    }
}

static void dump_downmix(AVFilterContext *ctx, AVFrameSideData *sd)
{
    AVDownmixInfo *di;

    av_log(ctx, AV_LOG_INFO, "downmix: ");
    if (sd->size < sizeof(*di)) {
        av_log(ctx, AV_LOG_INFO, "invalid data");
        return;
    }

    di = (AVDownmixInfo *)sd->data;

    av_log(ctx, AV_LOG_INFO, "preferred downmix type - ");
    switch (di->preferred_downmix_type) {
    case AV_DOWNMIX_TYPE_LORO:    av_log(ctx, AV_LOG_INFO, "Lo/Ro");              break;
    case AV_DOWNMIX_TYPE_LTRT:    av_log(ctx, AV_LOG_INFO, "Lt/Rt");              break;
    case AV_DOWNMIX_TYPE_DPLII:   av_log(ctx, AV_LOG_INFO, "Dolby Pro Logic II"); break;
    default:                      av_log(ctx, AV_LOG_WARNING, "unknown");         break;
    }

    av_log(ctx, AV_LOG_INFO, " Mix levels: center %f (%f ltrt) - "
           "surround %f (%f ltrt) - lfe %f",
           di->center_mix_level, di->center_mix_level_ltrt,
           di->surround_mix_level, di->surround_mix_level_ltrt,
           di->lfe_mix_level);
}

static void print_gain(AVFilterContext *ctx, const char *str, int32_t gain)
{
    av_log(ctx, AV_LOG_INFO, "%s - ", str);
    if (gain == INT32_MIN)
        av_log(ctx, AV_LOG_INFO, "unknown");
    else
        av_log(ctx, AV_LOG_INFO, "%f", gain / 100000.0f);
    av_log(ctx, AV_LOG_INFO, ", ");
}

static void print_peak(AVFilterContext *ctx, const char *str, uint32_t peak)
{
    av_log(ctx, AV_LOG_INFO, "%s - ", str);
    if (!peak)
        av_log(ctx, AV_LOG_INFO, "unknown");
    else
        av_log(ctx, AV_LOG_INFO, "%f", (float)peak / UINT32_MAX);
    av_log(ctx, AV_LOG_INFO, ", ");
}

static void dump_replaygain(AVFilterContext *ctx, AVFrameSideData *sd)
{
    AVReplayGain *rg;

    av_log(ctx, AV_LOG_INFO, "replaygain: ");
    if (sd->size < sizeof(*rg)) {
        av_log(ctx, AV_LOG_INFO, "invalid data");
        return;
    }
    rg = (AVReplayGain*)sd->data;

    print_gain(ctx, "track gain", rg->track_gain);
    print_peak(ctx, "track peak", rg->track_peak);
    print_gain(ctx, "album gain", rg->album_gain);
    print_peak(ctx, "album peak", rg->album_peak);
}

static void dump_unknown(AVFilterContext *ctx, AVFrameSideData *sd)
{
    av_log(ctx, AV_LOG_INFO, "unknown side data type: %d, size %d bytes", sd->type, sd->size);
}

165
static int filter_frame(AVFilterLink *inlink, AVFrame *buf)
166 167 168 169 170
{
    AVFilterContext *ctx = inlink->dst;
    AShowInfoContext *s  = ctx->priv;
    char chlayout_str[128];
    uint32_t checksum = 0;
171
    int channels    = av_get_channel_layout_nb_channels(buf->channel_layout);
172 173
    int planar      = av_sample_fmt_is_planar(buf->format);
    int block_align = av_get_bytes_per_sample(buf->format) * (planar ? 1 : channels);
174
    int data_size   = buf->nb_samples * block_align;
175 176 177 178 179 180 181 182 183 184 185 186
    int planes      = planar ? channels : 1;
    int i;

    for (i = 0; i < planes; i++) {
        uint8_t *data = buf->extended_data[i];

        s->plane_checksums[i] = av_adler32_update(0, data, data_size);
        checksum = i ? av_adler32_update(checksum, data, data_size) :
                       s->plane_checksums[0];
    }

    av_get_channel_layout_string(chlayout_str, sizeof(chlayout_str), -1,
187
                                 buf->channel_layout);
188 189 190 191

    av_log(ctx, AV_LOG_INFO,
           "n:%"PRIu64" pts:%"PRId64" pts_time:%f "
           "fmt:%s chlayout:%s rate:%d nb_samples:%d "
192
           "checksum:%08"PRIX32" ",
193 194
           s->frame, buf->pts, buf->pts * av_q2d(inlink->time_base),
           av_get_sample_fmt_name(buf->format), chlayout_str,
195
           buf->sample_rate, buf->nb_samples,
196 197 198 199
           checksum);

    av_log(ctx, AV_LOG_INFO, "plane_checksums: [ ");
    for (i = 0; i < planes; i++)
200
        av_log(ctx, AV_LOG_INFO, "%08"PRIX32" ", s->plane_checksums[i]);
201 202
    av_log(ctx, AV_LOG_INFO, "]\n");

203 204 205 206 207 208 209 210 211 212 213 214 215 216
    for (i = 0; i < buf->nb_side_data; i++) {
        AVFrameSideData *sd = buf->side_data[i];

        av_log(ctx, AV_LOG_INFO, "  side data - ");
        switch (sd->type) {
        case AV_FRAME_DATA_MATRIXENCODING: dump_matrixenc (ctx, sd); break;
        case AV_FRAME_DATA_DOWNMIX_INFO:   dump_downmix   (ctx, sd); break;
        case AV_FRAME_DATA_REPLAYGAIN:     dump_replaygain(ctx, sd); break;
        default:                           dump_unknown   (ctx, sd); break;
        }

        av_log(ctx, AV_LOG_INFO, "\n");
    }

217
    s->frame++;
218
    return ff_filter_frame(inlink->dst->outputs[0], buf);
219 220 221 222 223 224 225 226
}

static const AVFilterPad inputs[] = {
    {
        .name       = "default",
        .type             = AVMEDIA_TYPE_AUDIO,
        .get_audio_buffer = ff_null_get_audio_buffer,
        .config_props     = config_input,
227
        .filter_frame     = filter_frame,
228 229 230 231 232 233 234 235 236 237 238 239
    },
    { NULL },
};

static const AVFilterPad outputs[] = {
    {
        .name = "default",
        .type = AVMEDIA_TYPE_AUDIO,
    },
    { NULL },
};

240
AVFilter ff_af_ashowinfo = {
241 242 243 244 245 246 247
    .name        = "ashowinfo",
    .description = NULL_IF_CONFIG_SMALL("Show textual information for each audio frame."),
    .priv_size   = sizeof(AShowInfoContext),
    .uninit      = uninit,
    .inputs      = inputs,
    .outputs     = outputs,
};