1/* 2 * Sierra VMD audio decoder 3 * Copyright (c) 2004 The FFmpeg Project 4 * 5 * This file is part of FFmpeg. 6 * 7 * FFmpeg is free software; you can redistribute it and/or 8 * modify it under the terms of the GNU Lesser General Public 9 * License as published by the Free Software Foundation; either 10 * version 2.1 of the License, or (at your option) any later version. 11 * 12 * FFmpeg is distributed in the hope that it will be useful, 13 * but WITHOUT ANY WARRANTY; without even the implied warranty of 14 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU 15 * Lesser General Public License for more details. 16 * 17 * You should have received a copy of the GNU Lesser General Public 18 * License along with FFmpeg; if not, write to the Free Software 19 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA 20 */ 21 22/** 23 * @file 24 * Sierra VMD audio decoder 25 * by Vladimir "VAG" Gneushev (vagsoft at mail.ru) 26 * for more information on the Sierra VMD format, visit: 27 * http://www.pcisys.net/~melanson/codecs/ 28 * 29 * The audio decoder, expects each encoded data 30 * chunk to be prepended with the appropriate 16-byte frame information 31 * record from the VMD file. It does not require the 0x330-byte VMD file 32 * header, but it does need the audio setup parameters passed in through 33 * normal libavcodec API means. 34 */ 35 36#include <string.h> 37 38#include "libavutil/avassert.h" 39#include "libavutil/channel_layout.h" 40#include "libavutil/common.h" 41#include "libavutil/intreadwrite.h" 42 43#include "avcodec.h" 44#include "codec_internal.h" 45#include "internal.h" 46 47#define BLOCK_TYPE_AUDIO 1 48#define BLOCK_TYPE_INITIAL 2 49#define BLOCK_TYPE_SILENCE 3 50 51typedef struct VmdAudioContext { 52 int out_bps; 53 int chunk_size; 54} VmdAudioContext; 55 56static const uint16_t vmdaudio_table[128] = { 57 0x000, 0x008, 0x010, 0x020, 0x030, 0x040, 0x050, 0x060, 0x070, 0x080, 58 0x090, 0x0A0, 0x0B0, 0x0C0, 0x0D0, 0x0E0, 0x0F0, 0x100, 0x110, 0x120, 59 0x130, 0x140, 0x150, 0x160, 0x170, 0x180, 0x190, 0x1A0, 0x1B0, 0x1C0, 60 0x1D0, 0x1E0, 0x1F0, 0x200, 0x208, 0x210, 0x218, 0x220, 0x228, 0x230, 61 0x238, 0x240, 0x248, 0x250, 0x258, 0x260, 0x268, 0x270, 0x278, 0x280, 62 0x288, 0x290, 0x298, 0x2A0, 0x2A8, 0x2B0, 0x2B8, 0x2C0, 0x2C8, 0x2D0, 63 0x2D8, 0x2E0, 0x2E8, 0x2F0, 0x2F8, 0x300, 0x308, 0x310, 0x318, 0x320, 64 0x328, 0x330, 0x338, 0x340, 0x348, 0x350, 0x358, 0x360, 0x368, 0x370, 65 0x378, 0x380, 0x388, 0x390, 0x398, 0x3A0, 0x3A8, 0x3B0, 0x3B8, 0x3C0, 66 0x3C8, 0x3D0, 0x3D8, 0x3E0, 0x3E8, 0x3F0, 0x3F8, 0x400, 0x440, 0x480, 67 0x4C0, 0x500, 0x540, 0x580, 0x5C0, 0x600, 0x640, 0x680, 0x6C0, 0x700, 68 0x740, 0x780, 0x7C0, 0x800, 0x900, 0xA00, 0xB00, 0xC00, 0xD00, 0xE00, 69 0xF00, 0x1000, 0x1400, 0x1800, 0x1C00, 0x2000, 0x3000, 0x4000 70}; 71 72static av_cold int vmdaudio_decode_init(AVCodecContext *avctx) 73{ 74 VmdAudioContext *s = avctx->priv_data; 75 int channels = avctx->ch_layout.nb_channels; 76 77 if (channels < 1 || channels > 2) { 78 av_log(avctx, AV_LOG_ERROR, "invalid number of channels\n"); 79 return AVERROR(EINVAL); 80 } 81 if (avctx->block_align < 1 || avctx->block_align % channels || 82 avctx->block_align > INT_MAX - channels) { 83 av_log(avctx, AV_LOG_ERROR, "invalid block align\n"); 84 return AVERROR(EINVAL); 85 } 86 87 av_channel_layout_uninit(&avctx->ch_layout); 88 av_channel_layout_default(&avctx->ch_layout, channels); 89 90 if (avctx->bits_per_coded_sample == 16) 91 avctx->sample_fmt = AV_SAMPLE_FMT_S16; 92 else 93 avctx->sample_fmt = AV_SAMPLE_FMT_U8; 94 s->out_bps = av_get_bytes_per_sample(avctx->sample_fmt); 95 96 s->chunk_size = avctx->block_align + channels * (s->out_bps == 2); 97 98 av_log(avctx, AV_LOG_DEBUG, "%d channels, %d bits/sample, " 99 "block align = %d, sample rate = %d\n", 100 channels, avctx->bits_per_coded_sample, avctx->block_align, 101 avctx->sample_rate); 102 103 return 0; 104} 105 106static void decode_audio_s16(int16_t *out, const uint8_t *buf, int buf_size, 107 int channels) 108{ 109 int ch; 110 const uint8_t *buf_end = buf + buf_size; 111 int predictor[2]; 112 int st = channels - 1; 113 114 /* decode initial raw sample */ 115 for (ch = 0; ch < channels; ch++) { 116 predictor[ch] = (int16_t)AV_RL16(buf); 117 buf += 2; 118 *out++ = predictor[ch]; 119 } 120 121 /* decode DPCM samples */ 122 ch = 0; 123 while (buf < buf_end) { 124 uint8_t b = *buf++; 125 if (b & 0x80) 126 predictor[ch] -= vmdaudio_table[b & 0x7F]; 127 else 128 predictor[ch] += vmdaudio_table[b]; 129 predictor[ch] = av_clip_int16(predictor[ch]); 130 *out++ = predictor[ch]; 131 ch ^= st; 132 } 133} 134 135static int vmdaudio_decode_frame(AVCodecContext *avctx, AVFrame *frame, 136 int *got_frame_ptr, AVPacket *avpkt) 137{ 138 const uint8_t *buf = avpkt->data; 139 const uint8_t *buf_end; 140 int buf_size = avpkt->size; 141 VmdAudioContext *s = avctx->priv_data; 142 int block_type, silent_chunks, audio_chunks; 143 int ret; 144 uint8_t *output_samples_u8; 145 int16_t *output_samples_s16; 146 int channels = avctx->ch_layout.nb_channels; 147 148 if (buf_size < 16) { 149 av_log(avctx, AV_LOG_WARNING, "skipping small junk packet\n"); 150 *got_frame_ptr = 0; 151 return buf_size; 152 } 153 154 block_type = buf[6]; 155 if (block_type < BLOCK_TYPE_AUDIO || block_type > BLOCK_TYPE_SILENCE) { 156 av_log(avctx, AV_LOG_ERROR, "unknown block type: %d\n", block_type); 157 return AVERROR(EINVAL); 158 } 159 buf += 16; 160 buf_size -= 16; 161 162 /* get number of silent chunks */ 163 silent_chunks = 0; 164 if (block_type == BLOCK_TYPE_INITIAL) { 165 uint32_t flags; 166 if (buf_size < 4) { 167 av_log(avctx, AV_LOG_ERROR, "packet is too small\n"); 168 return AVERROR(EINVAL); 169 } 170 flags = AV_RB32(buf); 171 silent_chunks = av_popcount(flags); 172 buf += 4; 173 buf_size -= 4; 174 } else if (block_type == BLOCK_TYPE_SILENCE) { 175 silent_chunks = 1; 176 buf_size = 0; // should already be zero but set it just to be sure 177 } 178 179 /* ensure output buffer is large enough */ 180 audio_chunks = buf_size / s->chunk_size; 181 182 /* drop incomplete chunks */ 183 buf_size = audio_chunks * s->chunk_size; 184 185 if (silent_chunks + audio_chunks >= INT_MAX / avctx->block_align) 186 return AVERROR_INVALIDDATA; 187 188 /* get output buffer */ 189 frame->nb_samples = ((silent_chunks + audio_chunks) * avctx->block_align) / 190 avctx->ch_layout.nb_channels; 191 if ((ret = ff_get_buffer(avctx, frame, 0)) < 0) 192 return ret; 193 output_samples_u8 = frame->data[0]; 194 output_samples_s16 = (int16_t *)frame->data[0]; 195 196 /* decode silent chunks */ 197 if (silent_chunks > 0) { 198 int silent_size = avctx->block_align * silent_chunks; 199 av_assert0(avctx->block_align * silent_chunks <= frame->nb_samples * avctx->ch_layout.nb_channels); 200 201 if (s->out_bps == 2) { 202 memset(output_samples_s16, 0x00, silent_size * 2); 203 output_samples_s16 += silent_size; 204 } else { 205 memset(output_samples_u8, 0x80, silent_size); 206 output_samples_u8 += silent_size; 207 } 208 } 209 210 /* decode audio chunks */ 211 if (audio_chunks > 0) { 212 buf_end = buf + buf_size; 213 av_assert0((buf_size & (avctx->ch_layout.nb_channels > 1)) == 0); 214 while (buf_end - buf >= s->chunk_size) { 215 if (s->out_bps == 2) { 216 decode_audio_s16(output_samples_s16, buf, s->chunk_size, channels); 217 output_samples_s16 += avctx->block_align; 218 } else { 219 memcpy(output_samples_u8, buf, s->chunk_size); 220 output_samples_u8 += avctx->block_align; 221 } 222 buf += s->chunk_size; 223 } 224 } 225 226 *got_frame_ptr = 1; 227 228 return avpkt->size; 229} 230 231const FFCodec ff_vmdaudio_decoder = { 232 .p.name = "vmdaudio", 233 .p.long_name = NULL_IF_CONFIG_SMALL("Sierra VMD audio"), 234 .p.type = AVMEDIA_TYPE_AUDIO, 235 .p.id = AV_CODEC_ID_VMDAUDIO, 236 .priv_data_size = sizeof(VmdAudioContext), 237 .init = vmdaudio_decode_init, 238 FF_CODEC_DECODE_CB(vmdaudio_decode_frame), 239 .p.capabilities = AV_CODEC_CAP_DR1, 240 .caps_internal = FF_CODEC_CAP_INIT_THREADSAFE, 241}; 242