add a Creative VOC (de)muxer

Originally committed as revision 4967 to svn://svn.ffmpeg.org/ffmpeg/trunk

12 files changed, 347 insertions, 3 deletions

diff --git a/Changelog b/Changelog
index 470b6dcf0b..ca0f716f2e 100644
--- a/Changelog
+++ b/Changelog
@@ -35,6 +35,7 @@ version <next>
 - tabs and trailing whitespace removed from the codebase
 - AIFF/AIFF-C audio format, encoding and decoding
 - ADTS AAC file reading and writing
+- Creative VOC file reading and writing
 
 version 0.4.9-pre1:
 
diff --git a/MAINTAINERS b/MAINTAINERS
index 556946b56d..342986a736 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -183,6 +183,7 @@ Muxers/Demuxers:
   raw.c                                 Michael Niedermayer
   rm.c                                  Roberto Togni
   segafilm.c                            Mike Melanson
+  voc.c                                 Aurelien Jacobs
   wav.c                                 Michael Niedermayer
   wc3movie.c                            Mike Melanson
   westwood.c                            Mike Melanson
diff --git a/doc/ffmpeg-doc.texi b/doc/ffmpeg-doc.texi
index 340c768fc8..5a451c1bc6 100644
--- a/doc/ffmpeg-doc.texi
+++ b/doc/ffmpeg-doc.texi
@@ -697,6 +697,7 @@ library:
 @tab Used in various EA games; files have extensions like WVE and UV2.
 @item Nullsoft Video (NSV) format @tab    @tab X
 @item ADTS AAC audio @tab X @tab X
+@item Creative VOC @tab X @tab X @tab Created for the Sound Blaster Pro.
 @end multitable
 
 @code{X} means that encoding (resp. decoding) is supported.
diff --git a/libavformat/Makefile b/libavformat/Makefile
index c5f95d36b0..6e4b20cefc 100644
--- a/libavformat/Makefile
+++ b/libavformat/Makefile
@@ -22,7 +22,8 @@ OBJS+=mpeg.o mpegts.o mpegtsenc.o ffm.o crc.o img.o img2.o raw.o rm.o \
       yuv4mpeg.o 4xm.o flvdec.o psxstr.o idroq.o ipmovie.o \
       nut.o wc3movie.o mp3.o westwood.o segafilm.o idcin.o flic.o \
       sierravmd.o matroska.o sol.o electronicarts.o nsvdec.o asf.o \
-      ogg2.o oggparsevorbis.o oggparsetheora.o oggparseflac.o daud.o aiff.o
+      ogg2.o oggparsevorbis.o oggparsetheora.o oggparseflac.o daud.o aiff.o \
+      voc.o
 
 # muxers
 ifeq ($(CONFIG_MUXERS),yes)
diff --git a/libavformat/allformats.c b/libavformat/allformats.c
index 0715d886ce..10ca3f4b4d 100644
--- a/libavformat/allformats.c
+++ b/libavformat/allformats.c
@@ -114,6 +114,7 @@ void av_register_all(void)
     ea_init();
     nsvdec_init();
     daud_init();
+    voc_init();
 
 #ifdef CONFIG_MUXERS
     /* image formats */
diff --git a/libavformat/avformat.h b/libavformat/avformat.h
index e03f13185d..573fe8944c 100644
--- a/libavformat/avformat.h
+++ b/libavformat/avformat.h
@@ -5,8 +5,8 @@
 extern "C" {
 #endif
 
-#define LIBAVFORMAT_VERSION_INT ((50<<16)+(1<<8)+0)
-#define LIBAVFORMAT_VERSION     50.1.0
+#define LIBAVFORMAT_VERSION_INT ((50<<16)+(2<<8)+0)
+#define LIBAVFORMAT_VERSION     50.2.0
 #define LIBAVFORMAT_BUILD       LIBAVFORMAT_VERSION_INT
 
 #define LIBAVFORMAT_IDENT       "Lavf" AV_STRINGIFY(LIBAVFORMAT_VERSION)
@@ -552,6 +552,9 @@ int daud_init(void);
 /* aiff.c */
 int ff_aiff_init(void);
 
+/* voc.c */
+int voc_init(void);
+
 #include "rtp.h"
 
 #include "rtsp.h"
diff --git a/libavformat/avio.h b/libavformat/avio.h
index f000cfb2c7..d015d97a5a 100644
--- a/libavformat/avio.h
+++ b/libavformat/avio.h
@@ -99,6 +99,7 @@ void put_le64(ByteIOContext *s, uint64_t val);
 void put_be64(ByteIOContext *s, uint64_t val);
 void put_le32(ByteIOContext *s, unsigned int val);
 void put_be32(ByteIOContext *s, unsigned int val);
+void put_le24(ByteIOContext *s, unsigned int val);
 void put_be24(ByteIOContext *s, unsigned int val);
 void put_le16(ByteIOContext *s, unsigned int val);
 void put_be16(ByteIOContext *s, unsigned int val);
@@ -127,6 +128,7 @@ void put_flush_packet(ByteIOContext *s);
 int get_buffer(ByteIOContext *s, unsigned char *buf, int size);
 int get_partial_buffer(ByteIOContext *s, unsigned char *buf, int size);
 int get_byte(ByteIOContext *s);
+unsigned int get_le24(ByteIOContext *s);
 unsigned int get_le32(ByteIOContext *s);
 uint64_t get_le64(ByteIOContext *s);
 unsigned int get_le16(ByteIOContext *s);
diff --git a/libavformat/aviobuf.c b/libavformat/aviobuf.c
index 2a2fa1d04d..070917d091 100644
--- a/libavformat/aviobuf.c
+++ b/libavformat/aviobuf.c
@@ -239,6 +239,12 @@ void put_be16(ByteIOContext *s, unsigned int val)
     put_byte(s, val);
 }
 
+void put_le24(ByteIOContext *s, unsigned int val)
+{
+    put_le16(s, val & 0xffff);
+    put_byte(s, val >> 16);
+}
+
 void put_be24(ByteIOContext *s, unsigned int val)
 {
     put_be16(s, val >> 8);
@@ -396,6 +402,14 @@ unsigned int get_le16(ByteIOContext *s)
     return val;
 }
 
+unsigned int get_le24(ByteIOContext *s)
+{
+    unsigned int val;
+    val = get_le16(s);
+    val |= get_byte(s) << 16;
+    return val;
+}
+
 unsigned int get_le32(ByteIOContext *s)
 {
     unsigned int val;
diff --git a/libavformat/voc.c b/libavformat/voc.c
new file mode 100644
index 0000000000..7c723a4011
--- /dev/null
+++ b/libavformat/voc.c
@@ -0,0 +1,280 @@
+/*
+ * Creative Voice File demuxer.
+ * Copyright (c) 2006  Aurelien Jacobs <aurel@gnuage.org>
+ *
+ * This library 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 of the License, or (at your option) any later version.
+ *
+ * This library 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 this library; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
+ */
+
+#include "avformat.h"
+#include "avi.h"    /* for CodecTag */
+#include "voc.h"
+
+
+typedef enum voc_type {
+    VOC_TYPE_EOF              = 0x00,
+    VOC_TYPE_VOICE_DATA       = 0x01,
+    VOC_TYPE_VOICE_DATA_CONT  = 0x02,
+    VOC_TYPE_SILENCE          = 0x03,
+    VOC_TYPE_MARKER           = 0x04,
+    VOC_TYPE_ASCII            = 0x05,
+    VOC_TYPE_REPETITION_START = 0x06,
+    VOC_TYPE_REPETITION_END   = 0x07,
+    VOC_TYPE_EXTENDED         = 0x08,
+    VOC_TYPE_NEW_VOICE_DATA   = 0x09,
+} voc_type_t;
+
+
+static const int voc_max_pkt_size = 2048;
+static const unsigned char voc_magic[] = "Creative Voice File\x1A";
+
+static const CodecTag voc_codec_tags[] = {
+    {CODEC_ID_PCM_U8,        0x00},
+    {CODEC_ID_PCM_S16LE,     0x04},
+    {CODEC_ID_PCM_ALAW,      0x06},
+    {CODEC_ID_PCM_MULAW,     0x07},
+    {CODEC_ID_ADPCM_CT,    0x0200},
+    {0, 0},
+};
+
+
+#ifdef CONFIG_DEMUXERS
+
+static int voc_probe(AVProbeData *p)
+{
+    int version, check;
+
+    if (p->buf_size < 26)
+        return 0;
+    if (memcmp(p->buf, voc_magic, sizeof(voc_magic) - 1))
+        return 0;
+    version = p->buf[22] | (p->buf[23] << 8);
+    check = p->buf[24] | (p->buf[25] << 8);
+    if (~version + 0x1234 != check)
+        return 10;
+
+    return AVPROBE_SCORE_MAX;
+}
+
+static int voc_read_header(AVFormatContext *s, AVFormatParameters *ap)
+{
+    voc_dec_context_t *voc = s->priv_data;
+    ByteIOContext *pb = &s->pb;
+    int header_size;
+    AVStream *st;
+
+    url_fskip(pb, 20);
+    header_size = get_le16(pb) - 22;
+    if (header_size != 4) {
+        av_log(s, AV_LOG_ERROR, "unkown header size: %d\n", header_size);
+        return AVERROR_NOTSUPP;
+    }
+    url_fskip(pb, header_size);
+    st = av_new_stream(s, 0);
+    if (!st)
+        return AVERROR_NOMEM;
+    st->codec->codec_type = CODEC_TYPE_AUDIO;
+
+    voc->remaining_size = 0;
+    return 0;
+}
+
+int
+voc_get_packet(AVFormatContext *s, AVPacket *pkt, AVStream *st, int max_size)
+{
+    voc_dec_context_t *voc = s->priv_data;
+    AVCodecContext *dec = st->codec;
+    ByteIOContext *pb = &s->pb;
+    voc_type_t type;
+    int size;
+    int sample_rate = 0;
+    int channels = 1;
+
+    while (!voc->remaining_size) {
+        type = get_byte(pb);
+        if (type == VOC_TYPE_EOF)
+            return AVERROR_IO;
+        voc->remaining_size = get_le24(pb);
+        max_size -= 4;
+
+        switch (type) {
+        case VOC_TYPE_VOICE_DATA:
+            dec->sample_rate = 1000000 / (256 - get_byte(pb));
+            if (sample_rate)
+                dec->sample_rate = sample_rate;
+            dec->channels = channels;
+            dec->codec_id = codec_get_id(voc_codec_tags, get_byte(pb));
+            voc->remaining_size -= 2;
+            max_size -= 2;
+            channels = 1;
+            break;
+
+        case VOC_TYPE_VOICE_DATA_CONT:
+            break;
+
+        case VOC_TYPE_EXTENDED:
+            sample_rate = get_le16(pb);
+            get_byte(pb);
+            channels = get_byte(pb) + 1;
+            sample_rate = 256000000 / (channels * (65536 - sample_rate));
+            voc->remaining_size = 0;
+            max_size -= 4;
+            break;
+
+        case VOC_TYPE_NEW_VOICE_DATA:
+            dec->sample_rate = get_le32(pb);
+            dec->bits_per_sample = get_byte(pb);
+            dec->channels = get_byte(pb);
+            dec->codec_id = codec_get_id(voc_codec_tags, get_le16(pb));
+            url_fskip(pb, 4);
+            voc->remaining_size -= 12;
+            max_size -= 12;
+            break;
+
+        default:
+            url_fskip(pb, voc->remaining_size);
+            max_size -= voc->remaining_size;
+            voc->remaining_size = 0;
+            break;
+        }
+    }
+
+    dec->bit_rate = dec->sample_rate * dec->bits_per_sample;
+
+    if (max_size <= 0)
+        max_size = voc_max_pkt_size;
+    size = FFMIN(voc->remaining_size, max_size);
+    voc->remaining_size -= size;
+    return av_get_packet(pb, pkt, size);
+}
+
+static int voc_read_packet(AVFormatContext *s, AVPacket *pkt)
+{
+    return voc_get_packet(s, pkt, s->streams[0], 0);
+}
+
+static int voc_read_close(AVFormatContext *s)
+{
+    return 0;
+}
+
+static AVInputFormat voc_iformat = {
+    "voc",
+    "Creative Voice File format",
+    sizeof(voc_dec_context_t),
+    voc_probe,
+    voc_read_header,
+    voc_read_packet,
+    voc_read_close,
+};
+
+#endif /* CONFIG_DEMUXERS */
+
+
+#ifdef CONFIG_MUXERS
+
+typedef struct voc_enc_context {
+    int param_written;
+} voc_enc_context_t;
+
+static int voc_write_header(AVFormatContext *s)
+{
+    ByteIOContext *pb = &s->pb;
+    const int header_size = 26;
+    const int version = 0x0114;
+
+    if (s->nb_streams != 1
+        || s->streams[0]->codec->codec_type != CODEC_TYPE_AUDIO)
+        return AVERROR_NOTSUPP;
+
+    put_buffer(pb, voc_magic, sizeof(voc_magic) - 1);
+    put_le16(pb, header_size);
+    put_le16(pb, version);
+    put_le16(pb, ~version + 0x1234);
+
+    return 0;
+}
+
+static int voc_write_packet(AVFormatContext *s, AVPacket *pkt)
+{
+    voc_enc_context_t *voc = s->priv_data;
+    AVCodecContext *enc = s->streams[0]->codec;
+    ByteIOContext *pb = &s->pb;
+
+    if (!voc->param_written) {
+        int format = codec_get_tag(voc_codec_tags, enc->codec_id);
+
+        if (format > 0xFF) {
+            put_byte(pb, VOC_TYPE_NEW_VOICE_DATA);
+            put_le24(pb, pkt->size + 12);
+            put_le32(pb, enc->sample_rate);
+            put_byte(pb, enc->bits_per_sample);
+            put_byte(pb, enc->channels);
+            put_le16(pb, format);
+            put_le32(pb, 0);
+        } else {
+            if (s->streams[0]->codec->channels > 1) {
+                put_byte(pb, VOC_TYPE_EXTENDED);
+                put_le24(pb, 4);
+                put_le16(pb, 65536-256000000/(enc->sample_rate*enc->channels));
+                put_byte(pb, format);
+                put_byte(pb, enc->channels - 1);
+            }
+            put_byte(pb, VOC_TYPE_VOICE_DATA);
+            put_le24(pb, pkt->size + 2);
+            put_byte(pb, 256 - 1000000 / enc->sample_rate);
+            put_byte(pb, format);
+        }
+        voc->param_written = 1;
+    } else {
+        put_byte(pb, VOC_TYPE_VOICE_DATA_CONT);
+        put_le24(pb, pkt->size);
+    }
+
+    put_buffer(pb, pkt->data, pkt->size);
+    return 0;
+}
+
+static int voc_write_trailer(AVFormatContext *s)
+{
+    put_byte(&s->pb, 0);
+    return 0;
+}
+
+static AVOutputFormat voc_oformat = {
+    "voc",
+    "Creative Voice File format",
+    "audio/x-voc",
+    "voc",
+    sizeof(voc_enc_context_t),
+    CODEC_ID_PCM_U8,
+    CODEC_ID_NONE,
+    voc_write_header,
+    voc_write_packet,
+    voc_write_trailer,
+};
+
+#endif /* CONFIG_MUXERS */
+
+
+int voc_init(void)
+{
+#ifdef CONFIG_DEMUXERS
+    av_register_input_format(&voc_iformat);
+#endif /* CONFIG_DEMUXERS */
+#ifdef CONFIG_MUXERS
+    av_register_output_format(&voc_oformat);
+#endif /* CONFIG_MUXERS */
+    return 0;
+}
diff --git a/libavformat/voc.h b/libavformat/voc.h
new file mode 100644
index 0000000000..968d77eb7c
--- /dev/null
+++ b/libavformat/voc.h
@@ -0,0 +1,32 @@
+/*
+ * Creative Voice File demuxer.
+ * Copyright (c) 2006  Aurelien Jacobs <aurel@gnuage.org>
+ *
+ * This library 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 of the License, or (at your option) any later version.
+ *
+ * This library 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 this library; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
+ */
+
+#ifndef VOC_H
+#define VOC_H
+
+#include "avformat.h"
+
+typedef struct voc_dec_context {
+    int remaining_size;
+} voc_dec_context_t;
+
+int voc_get_packet(AVFormatContext *s, AVPacket *pkt,
+                   AVStream *st, int max_size);
+
+#endif
diff --git a/tests/libav.regression.ref b/tests/libav.regression.ref
index b9e3ec02e5..f45c80d11b 100644
--- a/tests/libav.regression.ref
+++ b/tests/libav.regression.ref
@@ -65,6 +65,9 @@ e2a6d6fae17394dfe87cb5bb8ae11837 *./data/b-libav.al
 a324baee6d76c53ab7c74616cfc31616 *./data/b-libav.aif
   89168 ./data/b-libav.aif
 ./data/b-libav.aif CRC=0x2a09519c
+8d117c49d6b210abe783d1b0b897cec7 *./data/b-libav.voc
+  32768 ./data/b-libav.voc
+./data/b-libav.voc CRC=0x49972c8c
 ce356ce2708cb6033ab5d762da93cfd4 *./data/b-libav-yuv420p.yuv
  304128 ./data/b-libav-yuv420p.yuv
 ce356ce2708cb6033ab5d762da93cfd4 *./data/b-libav-yuv422p.yuv
diff --git a/tests/regression.sh b/tests/regression.sh
index 239d5c7423..52b791efc4 100755
--- a/tests/regression.sh
+++ b/tests/regression.sh
@@ -712,6 +712,11 @@ file=${outfile}libav.aif
 do_ffmpeg $file -t 1 -y -qscale 10 -f s16le -i $pcm_src $file
 do_ffmpeg_crc $file -i $file
 
+# voc
+file=${outfile}libav.voc
+do_ffmpeg $file -t 1 -y -qscale 10 -f s16le -i $pcm_src $file
+do_ffmpeg_crc $file -i $file
+
 ####################
 # pix_fmt conversions
 conversions="yuv420p yuv422p yuv444p yuv422 yuv410p yuv411p yuvj420p \