aboutsummaryrefslogtreecommitdiffstats
path: root/libavformat/sierravmd.c
blob: 831638890b4c00d04dd4f3b9b08ae2a91611b613 (plain) (blame)
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
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
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
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
/*
 * Sierra VMD Format Demuxer
 * Copyright (c) 2004 The ffmpeg Project
 *
 * 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
 * Sierra VMD file demuxer
 * by Vladimir "VAG" Gneushev (vagsoft at mail.ru)
 * for more information on the Sierra VMD file format, visit:
 *   http://www.pcisys.net/~melanson/codecs/
 */

#include "libavutil/channel_layout.h"
#include "libavutil/intreadwrite.h"
#include "avformat.h"
#include "internal.h"

#define VMD_HEADER_SIZE 0x0330
#define BYTES_PER_FRAME_RECORD 16

typedef struct {
  int stream_index;
  int64_t frame_offset;
  unsigned int frame_size;
  int64_t pts;
  int keyframe;
  unsigned char frame_record[BYTES_PER_FRAME_RECORD];
} vmd_frame;

typedef struct VmdDemuxContext {
    int video_stream_index;
    int audio_stream_index;

    unsigned int frame_count;
    unsigned int frames_per_block;
    vmd_frame *frame_table;
    unsigned int current_frame;
    int is_indeo3;

    int sample_rate;
    int64_t audio_sample_counter;
    int skiphdr;

    unsigned char vmd_header[VMD_HEADER_SIZE];
} VmdDemuxContext;

static int vmd_probe(AVProbeData *p)
{
    int w, h;
    if (p->buf_size < 16)
        return 0;
    /* check if the first 2 bytes of the file contain the appropriate size
     * of a VMD header chunk */
    if (AV_RL16(&p->buf[0]) != VMD_HEADER_SIZE - 2)
        return 0;
    w = AV_RL16(&p->buf[12]);
    h = AV_RL16(&p->buf[14]);
    if (!w || w > 2048 || !h || h > 2048)
        return 0;

    /* only return half certainty since this check is a bit sketchy */
    return AVPROBE_SCORE_EXTENSION;
}

static int vmd_read_header(AVFormatContext *s)
{
    VmdDemuxContext *vmd = s->priv_data;
    AVIOContext *pb = s->pb;
    AVStream *st = NULL, *vst;
    unsigned int toc_offset;
    unsigned char *raw_frame_table;
    int raw_frame_table_size;
    int64_t current_offset;
    int i, j, ret;
    unsigned int total_frames;
    int64_t current_audio_pts = 0;
    unsigned char chunk[BYTES_PER_FRAME_RECORD];
    int num, den;
    int sound_buffers;

    /* fetch the main header, including the 2 header length bytes */
    avio_seek(pb, 0, SEEK_SET);
    if (avio_read(pb, vmd->vmd_header, VMD_HEADER_SIZE) != VMD_HEADER_SIZE)
        return AVERROR(EIO);

    if(vmd->vmd_header[24] == 'i' && vmd->vmd_header[25] == 'v' && vmd->vmd_header[26] == '3')
        vmd->is_indeo3 = 1;
    else
        vmd->is_indeo3 = 0;
    /* start up the decoders */
    vst = avformat_new_stream(s, NULL);
    if (!vst)
        return AVERROR(ENOMEM);
    avpriv_set_pts_info(vst, 33, 1, 10);
    vmd->video_stream_index = vst->index;
    vst->codec->codec_type = AVMEDIA_TYPE_VIDEO;
    vst->codec->codec_id = vmd->is_indeo3 ? AV_CODEC_ID_INDEO3 : AV_CODEC_ID_VMDVIDEO;
    vst->codec->codec_tag = 0;  /* no fourcc */
    vst->codec->width = AV_RL16(&vmd->vmd_header[12]);
    vst->codec->height = AV_RL16(&vmd->vmd_header[14]);
    if(vmd->is_indeo3 && vst->codec->width > 320){
        vst->codec->width >>= 1;
        vst->codec->height >>= 1;
    }
    vst->codec->extradata_size = VMD_HEADER_SIZE;
    vst->codec->extradata = av_mallocz(VMD_HEADER_SIZE + FF_INPUT_BUFFER_PADDING_SIZE);
    memcpy(vst->codec->extradata, vmd->vmd_header, VMD_HEADER_SIZE);

    /* if sample rate is 0, assume no audio */
    vmd->sample_rate = AV_RL16(&vmd->vmd_header[804]);
    if (vmd->sample_rate) {
        st = avformat_new_stream(s, NULL);
        if (!st)
            return AVERROR(ENOMEM);
        vmd->audio_stream_index = st->index;
        st->codec->codec_type = AVMEDIA_TYPE_AUDIO;
        st->codec->codec_id = AV_CODEC_ID_VMDAUDIO;
        st->codec->codec_tag = 0;  /* no fourcc */
        if (vmd->vmd_header[811] & 0x80) {
            st->codec->channels       = 2;
            st->codec->channel_layout = AV_CH_LAYOUT_STEREO;
        } else {
            st->codec->channels       = 1;
            st->codec->channel_layout = AV_CH_LAYOUT_MONO;
        }
        st->codec->sample_rate = vmd->sample_rate;
        st->codec->block_align = AV_RL16(&vmd->vmd_header[806]);
        if (st->codec->block_align & 0x8000) {
            st->codec->bits_per_coded_sample = 16;
            st->codec->block_align = -(st->codec->block_align - 0x10000);
        } else {
            st->codec->bits_per_coded_sample = 8;
        }
        st->codec->bit_rate = st->codec->sample_rate *
            st->codec->bits_per_coded_sample * st->codec->channels;

        /* calculate pts */
        num = st->codec->block_align;
        den = st->codec->sample_rate * st->codec->channels;
        av_reduce(&den, &num, den, num, (1UL<<31)-1);
        avpriv_set_pts_info(vst, 33, num, den);
        avpriv_set_pts_info(st, 33, num, den);
    }

    toc_offset = AV_RL32(&vmd->vmd_header[812]);
    vmd->frame_count = AV_RL16(&vmd->vmd_header[6]);
    vmd->frames_per_block = AV_RL16(&vmd->vmd_header[18]);
    avio_seek(pb, toc_offset, SEEK_SET);

    raw_frame_table = NULL;
    vmd->frame_table = NULL;
    sound_buffers = AV_RL16(&vmd->vmd_header[808]);
    raw_frame_table_size = vmd->frame_count * 6;
    if(vmd->frame_count * vmd->frames_per_block >= UINT_MAX / sizeof(vmd_frame) - sound_buffers){
        av_log(s, AV_LOG_ERROR, "vmd->frame_count * vmd->frames_per_block too large\n");
        return -1;
    }
    raw_frame_table = av_malloc(raw_frame_table_size);
    vmd->frame_table = av_malloc((vmd->frame_count * vmd->frames_per_block + sound_buffers) * sizeof(vmd_frame));
    if (!raw_frame_table || !vmd->frame_table) {
        ret = AVERROR(ENOMEM);
        goto error;
    }
    if (avio_read(pb, raw_frame_table, raw_frame_table_size) !=
        raw_frame_table_size) {
        ret = AVERROR(EIO);
        goto error;
    }

    total_frames = 0;
    for (i = 0; i < vmd->frame_count; i++) {

        current_offset = AV_RL32(&raw_frame_table[6 * i + 2]);

        /* handle each entry in index block */
        for (j = 0; j < vmd->frames_per_block; j++) {
            int type;
            uint32_t size;

            avio_read(pb, chunk, BYTES_PER_FRAME_RECORD);
            type = chunk[0];
            size = AV_RL32(&chunk[2]);
            if (size > INT_MAX / 2) {
                av_log(s, AV_LOG_ERROR, "Invalid frame size\n");
                ret = AVERROR_INVALIDDATA;
                goto error;
            }
            if(!size && type != 1)
                continue;
            switch(type) {
            case 1: /* Audio Chunk */
                if (!st) break;
                /* first audio chunk contains several audio buffers */
                vmd->frame_table[total_frames].frame_offset = current_offset;
                vmd->frame_table[total_frames].stream_index = vmd->audio_stream_index;
                vmd->frame_table[total_frames].frame_size = size;
                memcpy(vmd->frame_table[total_frames].frame_record, chunk, BYTES_PER_FRAME_RECORD);
                vmd->frame_table[total_frames].pts = current_audio_pts;
                total_frames++;
                if(!current_audio_pts)
                    current_audio_pts += sound_buffers - 1;
                else
                    current_audio_pts++;
                break;
            case 2: /* Video Chunk */
                vmd->frame_table[total_frames].frame_offset = current_offset;
                vmd->frame_table[total_frames].stream_index = vmd->video_stream_index;
                vmd->frame_table[total_frames].frame_size = size;
                memcpy(vmd->frame_table[total_frames].frame_record, chunk, BYTES_PER_FRAME_RECORD);
                vmd->frame_table[total_frames].pts = i;
                total_frames++;
                break;
            }
            current_offset += size;
        }
    }

    av_free(raw_frame_table);

    vmd->current_frame = 0;
    vmd->frame_count = total_frames;

    return 0;

error:
    av_free(raw_frame_table);
    av_free(vmd->frame_table);
    return ret;
}

static int vmd_read_packet(AVFormatContext *s,
                           AVPacket *pkt)
{
    VmdDemuxContext *vmd = s->priv_data;
    AVIOContext *pb = s->pb;
    int ret = 0;
    vmd_frame *frame;

    if (vmd->current_frame >= vmd->frame_count)
        return AVERROR(EIO);

    frame = &vmd->frame_table[vmd->current_frame];
    /* position the stream (will probably be there already) */
    avio_seek(pb, frame->frame_offset, SEEK_SET);

    if (av_new_packet(pkt, frame->frame_size + BYTES_PER_FRAME_RECORD))
        return AVERROR(ENOMEM);
    pkt->pos= avio_tell(pb);
    memcpy(pkt->data, frame->frame_record, BYTES_PER_FRAME_RECORD);
    if(vmd->is_indeo3 && frame->frame_record[0] == 0x02)
        ret = avio_read(pb, pkt->data, frame->frame_size);
    else
        ret = avio_read(pb, pkt->data + BYTES_PER_FRAME_RECORD,
            frame->frame_size);

    if (ret != frame->frame_size) {
        av_free_packet(pkt);
        ret = AVERROR(EIO);
    }
    pkt->stream_index = frame->stream_index;
    pkt->pts = frame->pts;
    av_log(s, AV_LOG_DEBUG, " dispatching %s frame with %d bytes and pts %"PRId64"\n",
            (frame->frame_record[0] == 0x02) ? "video" : "audio",
            frame->frame_size + BYTES_PER_FRAME_RECORD,
            pkt->pts);

    vmd->current_frame++;

    return ret;
}

static int vmd_read_close(AVFormatContext *s)
{
    VmdDemuxContext *vmd = s->priv_data;

    av_free(vmd->frame_table);

    return 0;
}

AVInputFormat ff_vmd_demuxer = {
    .name           = "vmd",
    .long_name      = NULL_IF_CONFIG_SMALL("Sierra VMD"),
    .priv_data_size = sizeof(VmdDemuxContext),
    .read_probe     = vmd_probe,
    .read_header    = vmd_read_header,
    .read_packet    = vmd_read_packet,
    .read_close     = vmd_read_close,
};