[FFmpeg-cvslog] vmd: Split audio and video decoder

Nidhi Makhijani git at videolan.org
Mon Jul 7 18:47:18 CEST 2014


ffmpeg | branch: master | Nidhi Makhijani <nidhimj22 at gmail.com> | Mon Jul  7 09:59:04 2014 +0530| [246f869590b8c7313d26e1c2ef56db01f6fd2503] | committer: Diego Biurrun

vmd: Split audio and video decoder

Signed-off-by: Diego Biurrun <diego at biurrun.de>

> http://git.videolan.org/gitweb.cgi/ffmpeg.git/?a=commit;h=246f869590b8c7313d26e1c2ef56db01f6fd2503
---

 libavcodec/Makefile                |    4 +-
 libavcodec/vmdaudio.c              |  233 ++++++++++++++++++++++++++++++++++++
 libavcodec/{vmdav.c => vmdvideo.c} |  220 +---------------------------------
 3 files changed, 238 insertions(+), 219 deletions(-)

diff --git a/libavcodec/Makefile b/libavcodec/Makefile
index d3d531e..fcd35cd 100644
--- a/libavcodec/Makefile
+++ b/libavcodec/Makefile
@@ -390,8 +390,8 @@ OBJS-$(CONFIG_VBLE_DECODER)            += vble.o
 OBJS-$(CONFIG_VC1_DECODER)             += vc1dec.o vc1.o vc1data.o vc1dsp.o \
                                           msmpeg4dec.o msmpeg4.o msmpeg4data.o
 OBJS-$(CONFIG_VCR1_DECODER)            += vcr1.o
-OBJS-$(CONFIG_VMDAUDIO_DECODER)        += vmdav.o
-OBJS-$(CONFIG_VMDVIDEO_DECODER)        += vmdav.o
+OBJS-$(CONFIG_VMDAUDIO_DECODER)        += vmdaudio.o
+OBJS-$(CONFIG_VMDVIDEO_DECODER)        += vmdvideo.o
 OBJS-$(CONFIG_VMNC_DECODER)            += vmnc.o
 OBJS-$(CONFIG_VORBIS_DECODER)          += vorbisdec.o vorbisdsp.o vorbis.o \
                                           vorbis_data.o xiph.o
diff --git a/libavcodec/vmdaudio.c b/libavcodec/vmdaudio.c
new file mode 100644
index 0000000..66c5865
--- /dev/null
+++ b/libavcodec/vmdaudio.c
@@ -0,0 +1,233 @@
+/*
+ * Sierra VMD audio decoder
+ *
+ * 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 audio decoder
+ * by Vladimir "VAG" Gneushev (vagsoft at mail.ru)
+ * for more information on the Sierra VMD format, visit:
+ *   http://www.pcisys.net/~melanson/codecs/
+ *
+ * The audio decoder, expects each encoded data
+ * chunk to be prepended with the appropriate 16-byte frame information
+ * record from the VMD file. It does not require the 0x330-byte VMD file
+ * header, but it does need the audio setup parameters passed in through
+ * normal libavcodec API means.
+ */
+
+#include <string.h>
+
+#include "libavutil/channel_layout.h"
+#include "libavutil/common.h"
+#include "libavutil/intreadwrite.h"
+
+#include "avcodec.h"
+#include "internal.h"
+
+#define BLOCK_TYPE_AUDIO    1
+#define BLOCK_TYPE_INITIAL  2
+#define BLOCK_TYPE_SILENCE  3
+
+typedef struct VmdAudioContext {
+    int out_bps;
+    int chunk_size;
+} VmdAudioContext;
+
+static const uint16_t vmdaudio_table[128] = {
+    0x000, 0x008, 0x010, 0x020, 0x030, 0x040, 0x050, 0x060, 0x070, 0x080,
+    0x090, 0x0A0, 0x0B0, 0x0C0, 0x0D0, 0x0E0, 0x0F0, 0x100, 0x110, 0x120,
+    0x130, 0x140, 0x150, 0x160, 0x170, 0x180, 0x190, 0x1A0, 0x1B0, 0x1C0,
+    0x1D0, 0x1E0, 0x1F0, 0x200, 0x208, 0x210, 0x218, 0x220, 0x228, 0x230,
+    0x238, 0x240, 0x248, 0x250, 0x258, 0x260, 0x268, 0x270, 0x278, 0x280,
+    0x288, 0x290, 0x298, 0x2A0, 0x2A8, 0x2B0, 0x2B8, 0x2C0, 0x2C8, 0x2D0,
+    0x2D8, 0x2E0, 0x2E8, 0x2F0, 0x2F8, 0x300, 0x308, 0x310, 0x318, 0x320,
+    0x328, 0x330, 0x338, 0x340, 0x348, 0x350, 0x358, 0x360, 0x368, 0x370,
+    0x378, 0x380, 0x388, 0x390, 0x398, 0x3A0, 0x3A8, 0x3B0, 0x3B8, 0x3C0,
+    0x3C8, 0x3D0, 0x3D8, 0x3E0, 0x3E8, 0x3F0, 0x3F8, 0x400, 0x440, 0x480,
+    0x4C0, 0x500, 0x540, 0x580, 0x5C0, 0x600, 0x640, 0x680, 0x6C0, 0x700,
+    0x740, 0x780, 0x7C0, 0x800, 0x900, 0xA00, 0xB00, 0xC00, 0xD00, 0xE00,
+    0xF00, 0x1000, 0x1400, 0x1800, 0x1C00, 0x2000, 0x3000, 0x4000
+};
+
+static av_cold int vmdaudio_decode_init(AVCodecContext *avctx)
+{
+    VmdAudioContext *s = avctx->priv_data;
+
+    if (avctx->channels < 1 || avctx->channels > 2) {
+        av_log(avctx, AV_LOG_ERROR, "invalid number of channels\n");
+        return AVERROR(EINVAL);
+    }
+    if (avctx->block_align < 1) {
+        av_log(avctx, AV_LOG_ERROR, "invalid block align\n");
+        return AVERROR(EINVAL);
+    }
+
+    avctx->channel_layout = avctx->channels == 1 ? AV_CH_LAYOUT_MONO :
+                                                   AV_CH_LAYOUT_STEREO;
+
+    if (avctx->bits_per_coded_sample == 16)
+        avctx->sample_fmt = AV_SAMPLE_FMT_S16;
+    else
+        avctx->sample_fmt = AV_SAMPLE_FMT_U8;
+    s->out_bps = av_get_bytes_per_sample(avctx->sample_fmt);
+
+    s->chunk_size = avctx->block_align + avctx->channels * (s->out_bps == 2);
+
+    av_log(avctx, AV_LOG_DEBUG, "%d channels, %d bits/sample, "
+           "block align = %d, sample rate = %d\n",
+           avctx->channels, avctx->bits_per_coded_sample, avctx->block_align,
+           avctx->sample_rate);
+
+    return 0;
+}
+
+static void decode_audio_s16(int16_t *out, const uint8_t *buf, int buf_size,
+                             int channels)
+{
+    int ch;
+    const uint8_t *buf_end = buf + buf_size;
+    int predictor[2];
+    int st = channels - 1;
+
+    /* decode initial raw sample */
+    for (ch = 0; ch < channels; ch++) {
+        predictor[ch] = (int16_t)AV_RL16(buf);
+        buf += 2;
+        *out++ = predictor[ch];
+    }
+
+    /* decode DPCM samples */
+    ch = 0;
+    while (buf < buf_end) {
+        uint8_t b = *buf++;
+        if (b & 0x80)
+            predictor[ch] -= vmdaudio_table[b & 0x7F];
+        else
+            predictor[ch] += vmdaudio_table[b];
+        predictor[ch] = av_clip_int16(predictor[ch]);
+        *out++ = predictor[ch];
+        ch ^= st;
+    }
+}
+
+static int vmdaudio_decode_frame(AVCodecContext *avctx, void *data,
+                                 int *got_frame_ptr, AVPacket *avpkt)
+{
+    AVFrame *frame     = data;
+    const uint8_t *buf = avpkt->data;
+    const uint8_t *buf_end;
+    int buf_size = avpkt->size;
+    VmdAudioContext *s = avctx->priv_data;
+    int block_type, silent_chunks, audio_chunks;
+    int ret;
+    uint8_t *output_samples_u8;
+    int16_t *output_samples_s16;
+
+    if (buf_size < 16) {
+        av_log(avctx, AV_LOG_WARNING, "skipping small junk packet\n");
+        *got_frame_ptr = 0;
+        return buf_size;
+    }
+
+    block_type = buf[6];
+    if (block_type < BLOCK_TYPE_AUDIO || block_type > BLOCK_TYPE_SILENCE) {
+        av_log(avctx, AV_LOG_ERROR, "unknown block type: %d\n", block_type);
+        return AVERROR(EINVAL);
+    }
+    buf      += 16;
+    buf_size -= 16;
+
+    /* get number of silent chunks */
+    silent_chunks = 0;
+    if (block_type == BLOCK_TYPE_INITIAL) {
+        uint32_t flags;
+        if (buf_size < 4) {
+            av_log(avctx, AV_LOG_ERROR, "packet is too small\n");
+            return AVERROR(EINVAL);
+        }
+        flags         = AV_RB32(buf);
+        silent_chunks = av_popcount(flags);
+        buf      += 4;
+        buf_size -= 4;
+    } else if (block_type == BLOCK_TYPE_SILENCE) {
+        silent_chunks = 1;
+        buf_size = 0; // should already be zero but set it just to be sure
+    }
+
+    /* ensure output buffer is large enough */
+    audio_chunks = buf_size / s->chunk_size;
+
+    /* drop incomplete chunks */
+    buf_size     = audio_chunks * s->chunk_size;
+
+    /* get output buffer */
+    frame->nb_samples = ((silent_chunks + audio_chunks) * avctx->block_align) /
+                        avctx->channels;
+    if ((ret = ff_get_buffer(avctx, frame, 0)) < 0) {
+        av_log(avctx, AV_LOG_ERROR, "get_buffer() failed\n");
+        return ret;
+    }
+    output_samples_u8  =            frame->data[0];
+    output_samples_s16 = (int16_t *)frame->data[0];
+
+    /* decode silent chunks */
+    if (silent_chunks > 0) {
+        int silent_size = FFMIN(avctx->block_align * silent_chunks,
+                                frame->nb_samples * avctx->channels);
+        if (s->out_bps == 2) {
+            memset(output_samples_s16, 0x00, silent_size * 2);
+            output_samples_s16 += silent_size;
+        } else {
+            memset(output_samples_u8,  0x80, silent_size);
+            output_samples_u8 += silent_size;
+        }
+    }
+
+    /* decode audio chunks */
+    if (audio_chunks > 0) {
+        buf_end = buf + (buf_size & ~(avctx->channels > 1));
+        while (buf + s->chunk_size <= buf_end) {
+            if (s->out_bps == 2) {
+                decode_audio_s16(output_samples_s16, buf, s->chunk_size,
+                                 avctx->channels);
+                output_samples_s16 += avctx->block_align;
+            } else {
+                memcpy(output_samples_u8, buf, s->chunk_size);
+                output_samples_u8  += avctx->block_align;
+            }
+            buf += s->chunk_size;
+        }
+    }
+
+    *got_frame_ptr = 1;
+
+    return avpkt->size;
+}
+
+AVCodec ff_vmdaudio_decoder = {
+    .name           = "vmdaudio",
+    .long_name      = NULL_IF_CONFIG_SMALL("Sierra VMD audio"),
+    .type           = AVMEDIA_TYPE_AUDIO,
+    .id             = AV_CODEC_ID_VMDAUDIO,
+    .priv_data_size = sizeof(VmdAudioContext),
+    .init           = vmdaudio_decode_init,
+    .decode         = vmdaudio_decode_frame,
+    .capabilities   = CODEC_CAP_DR1,
+};
diff --git a/libavcodec/vmdav.c b/libavcodec/vmdvideo.c
similarity index 67%
rename from libavcodec/vmdav.c
rename to libavcodec/vmdvideo.c
index a1e39c0..aaeff43 100644
--- a/libavcodec/vmdav.c
+++ b/libavcodec/vmdvideo.c
@@ -1,6 +1,5 @@
 /*
- * Sierra VMD Audio & Video Decoders
- * Copyright (C) 2004 the ffmpeg project
+ * Sierra VMD video decoder
  *
  * This file is part of Libav.
  *
@@ -21,7 +20,7 @@
 
 /**
  * @file
- * Sierra VMD audio & video decoders
+ * Sierra VMD video decoder
  * by Vladimir "VAG" Gneushev (vagsoft at mail.ru)
  * for more information on the Sierra VMD format, visit:
  *   http://www.pcisys.net/~melanson/codecs/
@@ -31,21 +30,13 @@
  * codec initialization. Each encoded frame that is sent to this decoder
  * is expected to be prepended with the appropriate 16-byte frame
  * information record from the VMD file.
- *
- * The audio decoder, like the video decoder, expects each encoded data
- * chunk to be prepended with the appropriate 16-byte frame information
- * record from the VMD file. It does not require the 0x330-byte VMD file
- * header, but it does need the audio setup parameters passed in through
- * normal libavcodec API means.
  */
 
-#include <stdio.h>
-#include <stdlib.h>
 #include <string.h>
 
-#include "libavutil/channel_layout.h"
 #include "libavutil/common.h"
 #include "libavutil/intreadwrite.h"
+
 #include "avcodec.h"
 #include "internal.h"
 #include "bytestream.h"
@@ -53,10 +44,6 @@
 #define VMD_HEADER_SIZE 0x330
 #define PALETTE_COUNT 256
 
-/*
- * Video Decoder
- */
-
 typedef struct VmdVideoContext {
 
     AVCodecContext *avctx;
@@ -467,196 +454,6 @@ static int vmdvideo_decode_frame(AVCodecContext *avctx,
     return buf_size;
 }
 
-
-/*
- * Audio Decoder
- */
-
-#define BLOCK_TYPE_AUDIO    1
-#define BLOCK_TYPE_INITIAL  2
-#define BLOCK_TYPE_SILENCE  3
-
-typedef struct VmdAudioContext {
-    int out_bps;
-    int chunk_size;
-} VmdAudioContext;
-
-static const uint16_t vmdaudio_table[128] = {
-    0x000, 0x008, 0x010, 0x020, 0x030, 0x040, 0x050, 0x060, 0x070, 0x080,
-    0x090, 0x0A0, 0x0B0, 0x0C0, 0x0D0, 0x0E0, 0x0F0, 0x100, 0x110, 0x120,
-    0x130, 0x140, 0x150, 0x160, 0x170, 0x180, 0x190, 0x1A0, 0x1B0, 0x1C0,
-    0x1D0, 0x1E0, 0x1F0, 0x200, 0x208, 0x210, 0x218, 0x220, 0x228, 0x230,
-    0x238, 0x240, 0x248, 0x250, 0x258, 0x260, 0x268, 0x270, 0x278, 0x280,
-    0x288, 0x290, 0x298, 0x2A0, 0x2A8, 0x2B0, 0x2B8, 0x2C0, 0x2C8, 0x2D0,
-    0x2D8, 0x2E0, 0x2E8, 0x2F0, 0x2F8, 0x300, 0x308, 0x310, 0x318, 0x320,
-    0x328, 0x330, 0x338, 0x340, 0x348, 0x350, 0x358, 0x360, 0x368, 0x370,
-    0x378, 0x380, 0x388, 0x390, 0x398, 0x3A0, 0x3A8, 0x3B0, 0x3B8, 0x3C0,
-    0x3C8, 0x3D0, 0x3D8, 0x3E0, 0x3E8, 0x3F0, 0x3F8, 0x400, 0x440, 0x480,
-    0x4C0, 0x500, 0x540, 0x580, 0x5C0, 0x600, 0x640, 0x680, 0x6C0, 0x700,
-    0x740, 0x780, 0x7C0, 0x800, 0x900, 0xA00, 0xB00, 0xC00, 0xD00, 0xE00,
-    0xF00, 0x1000, 0x1400, 0x1800, 0x1C00, 0x2000, 0x3000, 0x4000
-};
-
-static av_cold int vmdaudio_decode_init(AVCodecContext *avctx)
-{
-    VmdAudioContext *s = avctx->priv_data;
-
-    if (avctx->channels < 1 || avctx->channels > 2) {
-        av_log(avctx, AV_LOG_ERROR, "invalid number of channels\n");
-        return AVERROR(EINVAL);
-    }
-    if (avctx->block_align < 1) {
-        av_log(avctx, AV_LOG_ERROR, "invalid block align\n");
-        return AVERROR(EINVAL);
-    }
-
-    avctx->channel_layout = avctx->channels == 1 ? AV_CH_LAYOUT_MONO :
-                                                   AV_CH_LAYOUT_STEREO;
-
-    if (avctx->bits_per_coded_sample == 16)
-        avctx->sample_fmt = AV_SAMPLE_FMT_S16;
-    else
-        avctx->sample_fmt = AV_SAMPLE_FMT_U8;
-    s->out_bps = av_get_bytes_per_sample(avctx->sample_fmt);
-
-    s->chunk_size = avctx->block_align + avctx->channels * (s->out_bps == 2);
-
-    av_log(avctx, AV_LOG_DEBUG, "%d channels, %d bits/sample, "
-           "block align = %d, sample rate = %d\n",
-           avctx->channels, avctx->bits_per_coded_sample, avctx->block_align,
-           avctx->sample_rate);
-
-    return 0;
-}
-
-static void decode_audio_s16(int16_t *out, const uint8_t *buf, int buf_size,
-                             int channels)
-{
-    int ch;
-    const uint8_t *buf_end = buf + buf_size;
-    int predictor[2];
-    int st = channels - 1;
-
-    /* decode initial raw sample */
-    for (ch = 0; ch < channels; ch++) {
-        predictor[ch] = (int16_t)AV_RL16(buf);
-        buf += 2;
-        *out++ = predictor[ch];
-    }
-
-    /* decode DPCM samples */
-    ch = 0;
-    while (buf < buf_end) {
-        uint8_t b = *buf++;
-        if (b & 0x80)
-            predictor[ch] -= vmdaudio_table[b & 0x7F];
-        else
-            predictor[ch] += vmdaudio_table[b];
-        predictor[ch] = av_clip_int16(predictor[ch]);
-        *out++ = predictor[ch];
-        ch ^= st;
-    }
-}
-
-static int vmdaudio_decode_frame(AVCodecContext *avctx, void *data,
-                                 int *got_frame_ptr, AVPacket *avpkt)
-{
-    AVFrame *frame     = data;
-    const uint8_t *buf = avpkt->data;
-    const uint8_t *buf_end;
-    int buf_size = avpkt->size;
-    VmdAudioContext *s = avctx->priv_data;
-    int block_type, silent_chunks, audio_chunks;
-    int ret;
-    uint8_t *output_samples_u8;
-    int16_t *output_samples_s16;
-
-    if (buf_size < 16) {
-        av_log(avctx, AV_LOG_WARNING, "skipping small junk packet\n");
-        *got_frame_ptr = 0;
-        return buf_size;
-    }
-
-    block_type = buf[6];
-    if (block_type < BLOCK_TYPE_AUDIO || block_type > BLOCK_TYPE_SILENCE) {
-        av_log(avctx, AV_LOG_ERROR, "unknown block type: %d\n", block_type);
-        return AVERROR(EINVAL);
-    }
-    buf      += 16;
-    buf_size -= 16;
-
-    /* get number of silent chunks */
-    silent_chunks = 0;
-    if (block_type == BLOCK_TYPE_INITIAL) {
-        uint32_t flags;
-        if (buf_size < 4) {
-            av_log(avctx, AV_LOG_ERROR, "packet is too small\n");
-            return AVERROR(EINVAL);
-        }
-        flags         = AV_RB32(buf);
-        silent_chunks = av_popcount(flags);
-        buf      += 4;
-        buf_size -= 4;
-    } else if (block_type == BLOCK_TYPE_SILENCE) {
-        silent_chunks = 1;
-        buf_size = 0; // should already be zero but set it just to be sure
-    }
-
-    /* ensure output buffer is large enough */
-    audio_chunks = buf_size / s->chunk_size;
-
-    /* drop incomplete chunks */
-    buf_size     = audio_chunks * s->chunk_size;
-
-    /* get output buffer */
-    frame->nb_samples = ((silent_chunks + audio_chunks) * avctx->block_align) /
-                        avctx->channels;
-    if ((ret = ff_get_buffer(avctx, frame, 0)) < 0) {
-        av_log(avctx, AV_LOG_ERROR, "get_buffer() failed\n");
-        return ret;
-    }
-    output_samples_u8  =            frame->data[0];
-    output_samples_s16 = (int16_t *)frame->data[0];
-
-    /* decode silent chunks */
-    if (silent_chunks > 0) {
-        int silent_size = FFMIN(avctx->block_align * silent_chunks,
-                                frame->nb_samples * avctx->channels);
-        if (s->out_bps == 2) {
-            memset(output_samples_s16, 0x00, silent_size * 2);
-            output_samples_s16 += silent_size;
-        } else {
-            memset(output_samples_u8,  0x80, silent_size);
-            output_samples_u8 += silent_size;
-        }
-    }
-
-    /* decode audio chunks */
-    if (audio_chunks > 0) {
-        buf_end = buf + (buf_size & ~(avctx->channels > 1));
-        while (buf + s->chunk_size <= buf_end) {
-            if (s->out_bps == 2) {
-                decode_audio_s16(output_samples_s16, buf, s->chunk_size,
-                                 avctx->channels);
-                output_samples_s16 += avctx->block_align;
-            } else {
-                memcpy(output_samples_u8, buf, s->chunk_size);
-                output_samples_u8  += avctx->block_align;
-            }
-            buf += s->chunk_size;
-        }
-    }
-
-    *got_frame_ptr = 1;
-
-    return avpkt->size;
-}
-
-
-/*
- * Public Data Structures
- */
-
 AVCodec ff_vmdvideo_decoder = {
     .name           = "vmdvideo",
     .long_name      = NULL_IF_CONFIG_SMALL("Sierra VMD video"),
@@ -668,14 +465,3 @@ AVCodec ff_vmdvideo_decoder = {
     .decode         = vmdvideo_decode_frame,
     .capabilities   = CODEC_CAP_DR1,
 };
-
-AVCodec ff_vmdaudio_decoder = {
-    .name           = "vmdaudio",
-    .long_name      = NULL_IF_CONFIG_SMALL("Sierra VMD audio"),
-    .type           = AVMEDIA_TYPE_AUDIO,
-    .id             = AV_CODEC_ID_VMDAUDIO,
-    .priv_data_size = sizeof(VmdAudioContext),
-    .init           = vmdaudio_decode_init,
-    .decode         = vmdaudio_decode_frame,
-    .capabilities   = CODEC_CAP_DR1,
-};



More information about the ffmpeg-cvslog mailing list