Imported FFmpegSource

Originally committed to SVN as r1223.
This commit is contained in:
Fredrik Mellbin 2007-06-16 18:45:56 +00:00
parent 5b8273d67c
commit 3e2ff3da77
6 changed files with 5251 additions and 0 deletions

File diff suppressed because it is too large Load diff

View file

@ -0,0 +1,399 @@
/*
* Copyright (c) 2004-2006 Mike Matsnev. All Rights Reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
*
* 1. Redistributions of source code must retain the above copyright
* notice immediately at the beginning of the file, without modification,
* this list of conditions, and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
* 3. Absolutely no warranty of function or purpose is made by the author
* Mike Matsnev.
*
* THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR
* IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
* OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.
* IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT,
* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
* NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
* DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
* THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
* THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*
* $Id: MatroskaParser.h,v 1.19 2006/03/11 10:57:13 mike Exp $
*
*/
#ifndef MATROSKA_PARSER_H
#define MATROSKA_PARSER_H
/* Random notes:
*
* The parser does not process frame data in any way and does not read it into
* the queue. The app should read it via mkv_ReadData if it is interested.
*
* The code here is 64-bit clean and was tested on FreeBSD/sparc 64-bit big endian
* system
*/
#ifdef MPDLLBUILD
#define X __declspec(dllexport)
#else
#ifdef MPDLL
#define X __declspec(dllimport)
#pragma comment(lib,"MatroskaParser")
#else
#define X
#endif
#endif
#define MATROSKA_COMPRESSION_SUPPORT
#define MATROSKA_INTEGER_ONLY
#ifdef __cplusplus
extern "C" {
#endif
/* 64-bit integers */
#ifdef _WIN32_WCE
typedef signed __int64 longlong;
typedef unsigned __int64 ulonglong;
#else
typedef signed long long longlong;
typedef unsigned long long ulonglong;
#endif
/* MKFLOATing point */
#ifdef MATROSKA_INTEGER_ONLY
typedef struct {
longlong v;
} MKFLOAT;
#else
typedef double MKFLOAT;
#endif
/* generic I/O */
struct InputStream {
/* read bytes from stream */
int (*read)(struct InputStream *cc,ulonglong pos,void *buffer,int count);
/* scan for a four byte signature, bytes must be nonzero */
longlong (*scan)(struct InputStream *cc,ulonglong start,unsigned signature);
/* get cache size, this is used to cap readahead */
unsigned (*getcachesize)(struct InputStream *cc);
/* fetch last error message */
const char *(*geterror)(struct InputStream *cc);
/* memory allocation */
void *(*memalloc)(struct InputStream *cc,size_t size);
void *(*memrealloc)(struct InputStream *cc,void *mem,size_t newsize);
void (*memfree)(struct InputStream *cc,void *mem);
/* zero return causes parser to abort open */
int (*progress)(struct InputStream *cc,ulonglong cur,ulonglong max);
/* get file size, optional, can be NULL or return -1 if filesize is unknown */
longlong (*getfilesize)(struct InputStream *cc);
};
typedef struct InputStream InputStream;
/* matroska file */
struct MatroskaFile; /* opaque */
typedef struct MatroskaFile MatroskaFile;
#define COMP_ZLIB 0
#define COMP_BZIP 1
#define COMP_LZO1X 2
#define COMP_PREPEND 3
#define TT_VIDEO 1
#define TT_AUDIO 2
#define TT_SUB 17
struct TrackInfo {
unsigned char Number;
unsigned char Type;
unsigned char TrackOverlay;
ulonglong UID;
ulonglong MinCache;
ulonglong MaxCache;
ulonglong DefaultDuration;
MKFLOAT TimecodeScale;
void *CodecPrivate;
unsigned CodecPrivateSize;
unsigned CompMethod;
void *CompMethodPrivate;
unsigned CompMethodPrivateSize;
unsigned MaxBlockAdditionID;
struct {
unsigned int Enabled:1;
unsigned int Default:1;
unsigned int Lacing:1;
unsigned int DecodeAll:1;
unsigned int CompEnabled:1;
};
union {
struct {
unsigned char StereoMode;
unsigned char DisplayUnit;
unsigned char AspectRatioType;
unsigned int PixelWidth;
unsigned int PixelHeight;
unsigned int DisplayWidth;
unsigned int DisplayHeight;
unsigned int CropL, CropT, CropR, CropB;
unsigned int ColourSpace;
MKFLOAT GammaValue;
struct {
unsigned int Interlaced:1;
};
} Video;
struct {
MKFLOAT SamplingFreq;
MKFLOAT OutputSamplingFreq;
unsigned char Channels;
unsigned char BitDepth;
} Audio;
} AV;
/* various strings */
char *Name;
char Language[4];
char *CodecID;
};
typedef struct TrackInfo TrackInfo;
struct SegmentInfo {
char UID[16];
char PrevUID[16];
char NextUID[16];
char *Filename;
char *PrevFilename;
char *NextFilename;
char *Title;
char *MuxingApp;
char *WritingApp;
ulonglong TimecodeScale;
ulonglong Duration;
longlong DateUTC;
char DateUTCValid;
};
typedef struct SegmentInfo SegmentInfo;
struct Attachment {
ulonglong Position;
ulonglong Length;
ulonglong UID;
char *Name;
char *Description;
char *MimeType;
};
typedef struct Attachment Attachment;
struct ChapterDisplay {
char *String;
char Language[4];
char Country[4];
};
struct ChapterCommand {
unsigned Time;
unsigned CommandLength;
void *Command;
};
struct ChapterProcess {
unsigned CodecID;
unsigned CodecPrivateLength;
void *CodecPrivate;
unsigned nCommands,nCommandsSize;
struct ChapterCommand *Commands;
};
struct Chapter {
ulonglong UID;
ulonglong Start;
ulonglong End;
unsigned nTracks,nTracksSize;
ulonglong *Tracks;
unsigned nDisplay,nDisplaySize;
struct ChapterDisplay *Display;
unsigned nChildren,nChildrenSize;
struct Chapter *Children;
unsigned nProcess,nProcessSize;
struct ChapterProcess *Process;
char SegmentUID[16];
struct {
unsigned int Hidden:1;
unsigned int Enabled:1;
// Editions
unsigned int Default:1;
unsigned int Ordered:1;
};
};
typedef struct Chapter Chapter;
#define TARGET_TRACK 0
#define TARGET_CHAPTER 1
#define TARGET_ATTACHMENT 2
#define TARGET_EDITION 3
struct Target {
ulonglong UID;
unsigned Type;
};
struct SimpleTag {
char *Name;
char *Value;
char Language[4];
unsigned Default:1;
};
struct Tag {
unsigned nTargets,nTargetsSize;
struct Target *Targets;
unsigned nSimpleTags,nSimpleTagsSize;
struct SimpleTag *SimpleTags;
};
typedef struct Tag Tag;
/* Open a matroska file
* io pointer is recorded inside MatroskaFile
*/
X MatroskaFile *mkv_Open(/* in */ InputStream *io,
/* out */ char *err_msg,
/* in */ unsigned msgsize);
#define MKVF_AVOID_SEEKS 1 /* use sequential reading only */
X MatroskaFile *mkv_OpenEx(/* in */ InputStream *io,
/* in */ ulonglong base,
/* in */ unsigned flags,
/* out */ char *err_msg,
/* in */ unsigned msgsize);
/* Close and deallocate mf
* NULL pointer is ok and is simply ignored
*/
X void mkv_Close(/* in */ MatroskaFile *mf);
/* Fetch the error message of the last failed operation */
X const char *mkv_GetLastError(/* in */ MatroskaFile *mf);
/* Get file information */
X SegmentInfo *mkv_GetFileInfo(/* in */ MatroskaFile *mf);
/* Get track information */
X unsigned int mkv_GetNumTracks(/* in */ MatroskaFile *mf);
X TrackInfo *mkv_GetTrackInfo(/* in */ MatroskaFile *mf,/* in */ unsigned track);
/* chapters, tags and attachments */
X void mkv_GetAttachments(/* in */ MatroskaFile *mf,
/* out */ Attachment **at,
/* out */ unsigned *count);
X void mkv_GetChapters(/* in */ MatroskaFile *mf,
/* out */ Chapter **ch,
/* out */ unsigned *count);
X void mkv_GetTags(/* in */ MatroskaFile *mf,
/* out */ Tag **tag,
/* out */ unsigned *count);
X ulonglong mkv_GetSegmentTop(MatroskaFile *mf);
/* Seek to specified timecode,
* if timecode is past end of file,
* all tracks are set to return EOF
* on next read
*/
#define MKVF_SEEK_TO_PREV_KEYFRAME 1
X void mkv_Seek(/* in */ MatroskaFile *mf,
/* in */ ulonglong timecode /* in ns */,
/* in */ unsigned flags);
X void mkv_SkipToKeyframe(MatroskaFile *mf);
X ulonglong mkv_GetLowestQTimecode(MatroskaFile *mf);
X int mkv_TruncFloat(MKFLOAT f);
/*************************************************************************
* reading data, pull model
*/
/* frame flags */
#define FRAME_UNKNOWN_START 0x00000001
#define FRAME_UNKNOWN_END 0x00000002
#define FRAME_KF 0x00000004
#define FRAME_GAP 0x00800000
#define FRAME_STREAM_MASK 0xff000000
#define FRAME_STREAM_SHIFT 24
/* This sets the masking flags for the parser,
* masked tracks [with 1s in their bit positions]
* will be ignored when reading file data.
* This call discards all parsed and queued frames
*/
X void mkv_SetTrackMask(/* in */ MatroskaFile *mf,/* in */ unsigned int mask);
/* Read one frame from the queue.
* mask specifies what tracks to ignore.
* Returns -1 if there are no more frames in the specified
* set of tracks, 0 on success
*/
X int mkv_ReadFrame(/* in */ MatroskaFile *mf,
/* in */ unsigned int mask,
/* out */ unsigned int *track,
/* out */ ulonglong *StartTime /* in ns */,
/* out */ ulonglong *EndTime /* in ns */,
/* out */ ulonglong *FilePos /* in bytes from start of file */,
/* out */ unsigned int *FrameSize /* in bytes */,
/* out */ unsigned int *FrameFlags);
#ifdef MATROSKA_COMPRESSION_SUPPORT
/* Compressed streams support */
struct CompressedStream;
typedef struct CompressedStream CompressedStream;
X CompressedStream *cs_Create(/* in */ MatroskaFile *mf,
/* in */ unsigned tracknum,
/* out */ char *errormsg,
/* in */ unsigned msgsize);
X void cs_Destroy(/* in */ CompressedStream *cs);
/* advance to the next frame in matroska stream, you need to pass values returned
* by mkv_ReadFrame */
X void cs_NextFrame(/* in */ CompressedStream *cs,
/* in */ ulonglong pos,
/* in */ unsigned size);
/* read and decode more data from current frame, return number of bytes decoded,
* 0 on end of frame, or -1 on error */
X int cs_ReadData(CompressedStream *cs,char *buffer,unsigned bufsize);
/* return error message for the last error */
X const char *cs_GetLastError(CompressedStream *cs);
#endif
#ifdef __cplusplus
}
#endif
#undef X
#endif

749
FFmpegSource/avisynth.h Normal file
View file

@ -0,0 +1,749 @@
// Avisynth v2.5. Copyright 2002 Ben Rudiak-Gould et al.
// http://www.avisynth.org
// This program is free software; you can redistribute it and/or modify
// it under the terms of the GNU General Public License as published by
// the Free Software Foundation; either version 2 of the License, or
// (at your option) any later version.
//
// This program 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 General Public License for more details.
//
// You should have received a copy of the GNU General Public License
// along with this program; if not, write to the Free Software
// Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA, or visit
// http://www.gnu.org/copyleft/gpl.html .
//
// Linking Avisynth statically or dynamically with other modules is making a
// combined work based on Avisynth. Thus, the terms and conditions of the GNU
// General Public License cover the whole combination.
//
// As a special exception, the copyright holders of Avisynth give you
// permission to link Avisynth with independent modules that communicate with
// Avisynth solely through the interfaces defined in avisynth.h, regardless of the license
// terms of these independent modules, and to copy and distribute the
// resulting combined work under terms of your choice, provided that
// every copy of the combined work is accompanied by a complete copy of
// the source code of Avisynth (the version of Avisynth used to produce the
// combined work), being distributed under the terms of the GNU General
// Public License plus this exception. An independent module is a module
// which is not derived from or based on Avisynth, such as 3rd-party filters,
// import and export plugins, or graphical user interfaces.
#ifndef __AVISYNTH_H__
#define __AVISYNTH_H__
enum { AVISYNTH_INTERFACE_VERSION = 3 };
/* Define all types necessary for interfacing with avisynth.dll
Moved from internal.h */
// Win32 API macros, notably the types BYTE, DWORD, ULONG, etc.
#include <windef.h>
// COM interface macros
#include <objbase.h>
// Raster types used by VirtualDub & Avisynth
#define in64 (__int64)(unsigned short)
typedef unsigned long Pixel; // this will break on 64-bit machines!
typedef unsigned long Pixel32;
typedef unsigned char Pixel8;
typedef long PixCoord;
typedef long PixDim;
typedef long PixOffset;
/* Compiler-specific crap */
// Tell MSVC to stop precompiling here
#ifdef _MSC_VER
#pragma hdrstop
#endif
// Set up debugging macros for MS compilers; for others, step down to the
// standard <assert.h> interface
#ifdef _MSC_VER
#include <crtdbg.h>
#else
#define _RPT0(a,b) ((void)0)
#define _RPT1(a,b,c) ((void)0)
#define _RPT2(a,b,c,d) ((void)0)
#define _RPT3(a,b,c,d,e) ((void)0)
#define _RPT4(a,b,c,d,e,f) ((void)0)
#define _ASSERTE(x) assert(x)
#include <assert.h>
#endif
// I had problems with Premiere wanting 1-byte alignment for its structures,
// so I now set the Avisynth struct alignment explicitly here.
#pragma pack(push,8)
#define FRAME_ALIGN 16
// Default frame alignment is 16 bytes, to help P4, when using SSE2
// The VideoInfo struct holds global information about a clip (i.e.
// information that does not depend on the frame number). The GetVideoInfo
// method in IClip returns this struct.
// Audio Sample information
typedef float SFLOAT;
enum {SAMPLE_INT8 = 1<<0,
SAMPLE_INT16 = 1<<1,
SAMPLE_INT24 = 1<<2, // Int24 is a very stupid thing to code, but it's supported by some hardware.
SAMPLE_INT32 = 1<<3,
SAMPLE_FLOAT = 1<<4};
enum {
PLANAR_Y=1<<0,
PLANAR_U=1<<1,
PLANAR_V=1<<2,
PLANAR_ALIGNED=1<<3,
PLANAR_Y_ALIGNED=PLANAR_Y|PLANAR_ALIGNED,
PLANAR_U_ALIGNED=PLANAR_U|PLANAR_ALIGNED,
PLANAR_V_ALIGNED=PLANAR_V|PLANAR_ALIGNED,
};
struct VideoInfo {
int width, height; // width=0 means no video
unsigned fps_numerator, fps_denominator;
int num_frames;
// This is more extensible than previous versions. More properties can be added seeminglesly.
// Colorspace properties.
enum {
CS_BGR = 1<<28,
CS_YUV = 1<<29,
CS_INTERLEAVED = 1<<30,
CS_PLANAR = 1<<31
};
// Specific colorformats
enum { CS_UNKNOWN = 0,
CS_BGR24 = 1<<0 | CS_BGR | CS_INTERLEAVED,
CS_BGR32 = 1<<1 | CS_BGR | CS_INTERLEAVED,
CS_YUY2 = 1<<2 | CS_YUV | CS_INTERLEAVED,
CS_YV12 = 1<<3 | CS_YUV | CS_PLANAR, // y-v-u, planar
CS_I420 = 1<<4 | CS_YUV | CS_PLANAR, // y-u-v, planar
CS_IYUV = 1<<4 | CS_YUV | CS_PLANAR // same as above
};
int pixel_type; // changed to int as of 2.5
int audio_samples_per_second; // 0 means no audio
int sample_type; // as of 2.5
__int64 num_audio_samples; // changed as of 2.5
int nchannels; // as of 2.5
// Imagetype properties
int image_type;
enum {
IT_BFF = 1<<0,
IT_TFF = 1<<1,
IT_FIELDBASED = 1<<2
};
// useful functions of the above
bool HasVideo() const { return (width!=0); }
bool HasAudio() const { return (audio_samples_per_second!=0); }
bool IsRGB() const { return !!(pixel_type&CS_BGR); }
bool IsRGB24() const { return (pixel_type&CS_BGR24)==CS_BGR24; } // Clear out additional properties
bool IsRGB32() const { return (pixel_type & CS_BGR32) == CS_BGR32 ; }
bool IsYUV() const { return !!(pixel_type&CS_YUV ); }
bool IsYUY2() const { return (pixel_type & CS_YUY2) == CS_YUY2; }
bool IsYV12() const { return ((pixel_type & CS_YV12) == CS_YV12)||((pixel_type & CS_I420) == CS_I420); }
bool IsColorSpace(int c_space) const { return ((pixel_type & c_space) == c_space); }
bool Is(int property) const { return ((pixel_type & property)==property ); }
bool IsPlanar() const { return !!(pixel_type & CS_PLANAR); }
bool IsFieldBased() const { return !!(image_type & IT_FIELDBASED); }
bool IsParityKnown() const { return ((image_type & IT_FIELDBASED)&&(image_type & (IT_BFF|IT_TFF))); }
bool IsBFF() const { return !!(image_type & IT_BFF); }
bool IsTFF() const { return !!(image_type & IT_TFF); }
bool IsVPlaneFirst() const {return ((pixel_type & CS_YV12) == CS_YV12); } // Don't use this
int BytesFromPixels(int pixels) const { return pixels * (BitsPerPixel()>>3); } // Will not work on planar images, but will return only luma planes
int RowSize() const { return BytesFromPixels(width); } // Also only returns first plane on planar images
int BMPSize() const { if (IsPlanar()) {int p = height * ((RowSize()+3) & ~3); p+=p>>1; return p; } return height * ((RowSize()+3) & ~3); }
__int64 AudioSamplesFromFrames(__int64 frames) const { return (fps_numerator && HasVideo()) ? ((__int64)(frames) * audio_samples_per_second * fps_denominator / fps_numerator) : 0; }
int FramesFromAudioSamples(__int64 samples) const { return (fps_denominator && HasAudio()) ? (int)((samples * (__int64)fps_numerator)/((__int64)fps_denominator * (__int64)audio_samples_per_second)) : 0; }
__int64 AudioSamplesFromBytes(__int64 bytes) const { return HasAudio() ? bytes / BytesPerAudioSample() : 0; }
__int64 BytesFromAudioSamples(__int64 samples) const { return samples * BytesPerAudioSample(); }
int AudioChannels() const { return HasAudio() ? nchannels : 0; }
int SampleType() const{ return sample_type;}
bool IsSampleType(int testtype) const{ return !!(sample_type&testtype);}
int SamplesPerSecond() const { return audio_samples_per_second; }
int BytesPerAudioSample() const { return nchannels*BytesPerChannelSample();}
void SetFieldBased(bool isfieldbased) { if (isfieldbased) image_type|=IT_FIELDBASED; else image_type&=~IT_FIELDBASED; }
void Set(int property) { image_type|=property; }
void Clear(int property) { image_type&=~property; }
int BitsPerPixel() const {
switch (pixel_type) {
case CS_BGR24:
return 24;
case CS_BGR32:
return 32;
case CS_YUY2:
return 16;
case CS_YV12:
case CS_I420:
return 12;
default:
return 0;
}
}
int BytesPerChannelSample() const {
switch (sample_type) {
case SAMPLE_INT8:
return sizeof(signed char);
case SAMPLE_INT16:
return sizeof(signed short);
case SAMPLE_INT24:
return 3;
case SAMPLE_INT32:
return sizeof(signed int);
case SAMPLE_FLOAT:
return sizeof(SFLOAT);
default:
_ASSERTE("Sample type not recognized!");
return 0;
}
}
// useful mutator
void SetFPS(unsigned numerator, unsigned denominator) {
if ((numerator == 0) || (denominator == 0)) {
fps_numerator = 0;
fps_denominator = 1;
}
else {
unsigned x=numerator, y=denominator;
while (y) { // find gcd
unsigned t = x%y; x = y; y = t;
}
fps_numerator = numerator/x;
fps_denominator = denominator/x;
}
}
// Range protected multiply-divide of FPS
void MulDivFPS(unsigned multiplier, unsigned divisor) {
unsigned __int64 numerator = UInt32x32To64(fps_numerator, multiplier);
unsigned __int64 denominator = UInt32x32To64(fps_denominator, divisor);
unsigned __int64 x=numerator, y=denominator;
while (y) { // find gcd
unsigned __int64 t = x%y; x = y; y = t;
}
numerator /= x; // normalize
denominator /= x;
unsigned __int64 temp = numerator | denominator; // Just looking top bit
unsigned u = 0;
while (temp & 0xffffffff80000000) { // or perhaps > 16777216*2
temp = Int64ShrlMod32(temp, 1);
u++;
}
if (u) { // Scale to fit
const unsigned round = 1 << (u-1);
SetFPS( (unsigned)Int64ShrlMod32(numerator + round, u),
(unsigned)Int64ShrlMod32(denominator + round, u) );
}
else {
fps_numerator = (unsigned)numerator;
fps_denominator = (unsigned)denominator;
}
}
// Test for same colorspace
bool IsSameColorspace(const VideoInfo& vi) const {
if (vi.pixel_type == pixel_type) return TRUE;
if (IsYV12() && vi.IsYV12()) return TRUE;
return FALSE;
}
};
// VideoFrameBuffer holds information about a memory block which is used
// for video data. For efficiency, instances of this class are not deleted
// when the refcount reaches zero; instead they're stored in a linked list
// to be reused. The instances are deleted when the corresponding AVS
// file is closed.
class VideoFrameBuffer {
BYTE* const data;
const int data_size;
// sequence_number is incremented every time the buffer is changed, so
// that stale views can tell they're no longer valid.
long sequence_number;
friend class VideoFrame;
friend class Cache;
friend class ScriptEnvironment;
long refcount;
public:
VideoFrameBuffer(int size);
VideoFrameBuffer();
~VideoFrameBuffer();
const BYTE* GetReadPtr() const { return data; }
BYTE* GetWritePtr() { ++sequence_number; return data; }
int GetDataSize() { return data_size; }
int GetSequenceNumber() { return sequence_number; }
int GetRefcount() { return refcount; }
};
class IClip;
class PClip;
class PVideoFrame;
class IScriptEnvironment;
class AVSValue;
// VideoFrame holds a "window" into a VideoFrameBuffer. Operator new
// is overloaded to recycle class instances.
class VideoFrame {
int refcount;
VideoFrameBuffer* const vfb;
const int offset, pitch, row_size, height, offsetU, offsetV, pitchUV; // U&V offsets are from top of picture.
friend class PVideoFrame;
void AddRef() { InterlockedIncrement((long *)&refcount); }
void Release() { if (refcount==1) InterlockedDecrement(&vfb->refcount); InterlockedDecrement((long *)&refcount); }
friend class ScriptEnvironment;
friend class Cache;
VideoFrame(VideoFrameBuffer* _vfb, int _offset, int _pitch, int _row_size, int _height);
VideoFrame(VideoFrameBuffer* _vfb, int _offset, int _pitch, int _row_size, int _height, int _offsetU, int _offsetV, int _pitchUV);
void* operator new(unsigned size);
// TESTME: OFFSET U/V may be switched to what could be expected from AVI standard!
public:
int GetPitch() const { return pitch; }
int GetPitch(int plane) const { switch (plane) {case PLANAR_U: case PLANAR_V: return pitchUV;} return pitch; }
int GetRowSize() const { return row_size; }
int GetRowSize(int plane) const {
switch (plane) {
case PLANAR_U: case PLANAR_V: if (pitchUV) return row_size>>1; else return 0;
case PLANAR_U_ALIGNED: case PLANAR_V_ALIGNED:
if (pitchUV) {
int r = ((row_size+FRAME_ALIGN-1)&(~(FRAME_ALIGN-1)) )>>1; // Aligned rowsize
if (r<=pitchUV)
return r;
return row_size>>1;
} else return 0;
case PLANAR_Y_ALIGNED:
int r = (row_size+FRAME_ALIGN-1)&(~(FRAME_ALIGN-1)); // Aligned rowsize
if (r<=pitch)
return r;
return row_size;
}
return row_size; }
int GetHeight() const { return height; }
int GetHeight(int plane) const { switch (plane) {case PLANAR_U: case PLANAR_V: if (pitchUV) return height>>1; return 0;} return height; }
// generally you shouldn't use these three
VideoFrameBuffer* GetFrameBuffer() const { return vfb; }
int GetOffset() const { return offset; }
int GetOffset(int plane) const { switch (plane) {case PLANAR_U: return offsetU;case PLANAR_V: return offsetV;default: return offset;}; }
// in plugins use env->SubFrame()
VideoFrame* Subframe(int rel_offset, int new_pitch, int new_row_size, int new_height) const;
VideoFrame* Subframe(int rel_offset, int new_pitch, int new_row_size, int new_height, int rel_offsetU, int rel_offsetV, int pitchUV) const;
const BYTE* GetReadPtr() const { return vfb->GetReadPtr() + offset; }
const BYTE* GetReadPtr(int plane) const { return vfb->GetReadPtr() + GetOffset(plane); }
bool IsWritable() const { return (refcount == 1 && vfb->refcount == 1); }
BYTE* GetWritePtr() const {
if (vfb->GetRefcount()>1) {
_ASSERT(FALSE);
//throw AvisynthError("Internal Error - refcount was more than one!");
}
return IsWritable() ? (vfb->GetWritePtr() + offset) : 0;
}
BYTE* GetWritePtr(int plane) const {
if (plane==PLANAR_Y) {
if (vfb->GetRefcount()>1) {
_ASSERT(FALSE);
// throw AvisynthError("Internal Error - refcount was more than one!");
}
return IsWritable() ? vfb->GetWritePtr() + GetOffset(plane) : 0;
}
return vfb->data + GetOffset(plane);
}
~VideoFrame() { InterlockedDecrement(&vfb->refcount); }
};
enum {
CACHE_NOTHING=0,
CACHE_RANGE=1,
CACHE_ALL=2,
CACHE_AUDIO=3,
CACHE_AUDIO_NONE=4
};
// Base class for all filters.
class IClip {
friend class PClip;
friend class AVSValue;
int refcnt;
void AddRef() { InterlockedIncrement((long *)&refcnt); }
void Release() { InterlockedDecrement((long *)&refcnt); if (!refcnt) delete this; }
public:
IClip() : refcnt(0) {}
virtual int __stdcall GetVersion() { return AVISYNTH_INTERFACE_VERSION; }
virtual PVideoFrame __stdcall GetFrame(int n, IScriptEnvironment* env) = 0;
virtual bool __stdcall GetParity(int n) = 0; // return field parity if field_based, else parity of first field in frame
virtual void __stdcall GetAudio(void* buf, __int64 start, __int64 count, IScriptEnvironment* env) = 0; // start and count are in samples
virtual void __stdcall SetCacheHints(int cachehints,int frame_range) = 0 ; // We do not pass cache requests upwards, only to the next filter.
virtual const VideoInfo& __stdcall GetVideoInfo() = 0;
virtual __stdcall ~IClip() {}
};
// smart pointer to IClip
class PClip {
IClip* p;
IClip* GetPointerWithAddRef() const { if (p) p->AddRef(); return p; }
friend class AVSValue;
friend class VideoFrame;
void Init(IClip* x) {
if (x) x->AddRef();
p=x;
}
void Set(IClip* x) {
if (x) x->AddRef();
if (p) p->Release();
p=x;
}
public:
PClip() { p = 0; }
PClip(const PClip& x) { Init(x.p); }
PClip(IClip* x) { Init(x); }
void operator=(IClip* x) { Set(x); }
void operator=(const PClip& x) { Set(x.p); }
IClip* operator->() const { return p; }
// useful in conditional expressions
operator void*() const { return p; }
bool operator!() const { return !p; }
~PClip() { if (p) p->Release(); }
};
// smart pointer to VideoFrame
class PVideoFrame {
VideoFrame* p;
void Init(VideoFrame* x) {
if (x) x->AddRef();
p=x;
}
void Set(VideoFrame* x) {
if (x) x->AddRef();
if (p) p->Release();
p=x;
}
public:
PVideoFrame() { p = 0; }
PVideoFrame(const PVideoFrame& x) { Init(x.p); }
PVideoFrame(VideoFrame* x) { Init(x); }
void operator=(VideoFrame* x) { Set(x); }
void operator=(const PVideoFrame& x) { Set(x.p); }
VideoFrame* operator->() const { return p; }
// for conditional expressions
operator void*() const { return p; }
bool operator!() const { return !p; }
~PVideoFrame() { if (p) p->Release();}
};
class AVSValue {
public:
AVSValue() { type = 'v'; }
AVSValue(IClip* c) { type = 'c'; clip = c; if (c) c->AddRef(); }
AVSValue(const PClip& c) { type = 'c'; clip = c.GetPointerWithAddRef(); }
AVSValue(bool b) { type = 'b'; boolean = b; }
AVSValue(int i) { type = 'i'; integer = i; }
// AVSValue(__int64 l) { type = 'l'; longlong = l; }
AVSValue(float f) { type = 'f'; floating_pt = f; }
AVSValue(double f) { type = 'f'; floating_pt = float(f); }
AVSValue(const char* s) { type = 's'; string = s; }
AVSValue(const AVSValue* a, int size) { type = 'a'; array = a; array_size = size; }
AVSValue(const AVSValue& v) { Assign(&v, true); }
~AVSValue() { if (IsClip() && clip) clip->Release(); }
AVSValue& operator=(const AVSValue& v) { Assign(&v, false); return *this; }
// Note that we transparently allow 'int' to be treated as 'float'.
// There are no int<->bool conversions, though.
bool Defined() const { return type != 'v'; }
bool IsClip() const { return type == 'c'; }
bool IsBool() const { return type == 'b'; }
bool IsInt() const { return type == 'i'; }
// bool IsLong() const { return (type == 'l'|| type == 'i'); }
bool IsFloat() const { return type == 'f' || type == 'i'; }
bool IsString() const { return type == 's'; }
bool IsArray() const { return type == 'a'; }
PClip AsClip() const { _ASSERTE(IsClip()); return IsClip()?clip:0; }
bool AsBool() const { _ASSERTE(IsBool()); return boolean; }
int AsInt() const { _ASSERTE(IsInt()); return integer; }
// int AsLong() const { _ASSERTE(IsLong()); return longlong; }
const char* AsString() const { _ASSERTE(IsString()); return IsString()?string:0; }
double AsFloat() const { _ASSERTE(IsFloat()); return IsInt()?integer:floating_pt; }
bool AsBool(bool def) const { _ASSERTE(IsBool()||!Defined()); return IsBool() ? boolean : def; }
int AsInt(int def) const { _ASSERTE(IsInt()||!Defined()); return IsInt() ? integer : def; }
double AsFloat(double def) const { _ASSERTE(IsFloat()||!Defined()); return IsInt() ? integer : type=='f' ? floating_pt : def; }
const char* AsString(const char* def) const { _ASSERTE(IsString()||!Defined()); return IsString() ? string : def; }
int ArraySize() const { _ASSERTE(IsArray()); return IsArray()?array_size:1; }
const AVSValue& operator[](int index) const {
_ASSERTE(IsArray() && index>=0 && index<array_size);
return (IsArray() && index>=0 && index<array_size) ? array[index] : *this;
}
private:
short type; // 'a'rray, 'c'lip, 'b'ool, 'i'nt, 'f'loat, 's'tring, 'v'oid, or 'l'ong
short array_size;
union {
IClip* clip;
bool boolean;
int integer;
float floating_pt;
const char* string;
const AVSValue* array;
// __int64 longlong;
};
void Assign(const AVSValue* src, bool init) {
if (src->IsClip() && src->clip)
src->clip->AddRef();
if (!init && IsClip() && clip)
clip->Release();
// make sure this copies the whole struct!
((__int32*)this)[0] = ((__int32*)src)[0];
((__int32*)this)[1] = ((__int32*)src)[1];
}
};
// instantiable null filter
class GenericVideoFilter : public IClip {
protected:
PClip child;
VideoInfo vi;
public:
GenericVideoFilter(PClip _child) : child(_child) { vi = child->GetVideoInfo(); }
PVideoFrame __stdcall GetFrame(int n, IScriptEnvironment* env) { return child->GetFrame(n, env); }
void __stdcall GetAudio(void* buf, __int64 start, __int64 count, IScriptEnvironment* env) { child->GetAudio(buf, start, count, env); }
const VideoInfo& __stdcall GetVideoInfo() { return vi; }
bool __stdcall GetParity(int n) { return child->GetParity(n); }
void __stdcall SetCacheHints(int cachehints,int frame_range) { } ; // We do not pass cache requests upwards, only to the next filter.
};
class AvisynthError /* exception */ {
public:
const char* const msg;
AvisynthError(const char* _msg) : msg(_msg) {}
};
/* Helper classes useful to plugin authors */
class AlignPlanar : public GenericVideoFilter
{
public:
AlignPlanar(PClip _clip);
static PClip Create(PClip clip);
PVideoFrame __stdcall GetFrame(int n, IScriptEnvironment* env);
};
class FillBorder : public GenericVideoFilter
{
public:
FillBorder(PClip _clip);
static PClip Create(PClip clip);
PVideoFrame __stdcall GetFrame(int n, IScriptEnvironment* env);
};
class ConvertAudio : public GenericVideoFilter
/**
* Helper class to convert audio to any format
**/
{
public:
ConvertAudio(PClip _clip, int prefered_format);
void __stdcall GetAudio(void* buf, __int64 start, __int64 count, IScriptEnvironment* env);
void __stdcall SetCacheHints(int cachehints,int frame_range); // We do pass cache requests upwards, to the cache!
static PClip Create(PClip clip, int sample_type, int prefered_type);
static AVSValue __cdecl Create_float(AVSValue args, void*, IScriptEnvironment*);
static AVSValue __cdecl Create_32bit(AVSValue args, void*, IScriptEnvironment*);
static AVSValue __cdecl Create_24bit(AVSValue args, void*, IScriptEnvironment*);
static AVSValue __cdecl Create_16bit(AVSValue args, void*, IScriptEnvironment*);
static AVSValue __cdecl Create_8bit(AVSValue args, void*, IScriptEnvironment*);
virtual ~ConvertAudio();
private:
void convertToFloat(char* inbuf, float* outbuf, char sample_type, int count);
void convertToFloat_3DN(char* inbuf, float* outbuf, char sample_type, int count);
void convertToFloat_SSE(char* inbuf, float* outbuf, char sample_type, int count);
void convertToFloat_SSE2(char* inbuf, float* outbuf, char sample_type, int count);
void convertFromFloat(float* inbuf, void* outbuf, char sample_type, int count);
void convertFromFloat_3DN(float* inbuf, void* outbuf, char sample_type, int count);
void convertFromFloat_SSE(float* inbuf, void* outbuf, char sample_type, int count);
void convertFromFloat_SSE2(float* inbuf, void* outbuf, char sample_type, int count);
__inline int Saturate_int8(float n);
__inline short Saturate_int16(float n);
__inline int Saturate_int24(float n);
__inline int Saturate_int32(float n);
char src_format;
char dst_format;
int src_bps;
char *tempbuffer;
SFLOAT *floatbuffer;
int tempbuffer_size;
};
// For GetCPUFlags. These are backwards-compatible with those in VirtualDub.
enum {
/* slowest CPU to support extension */
CPUF_FORCE = 0x01, // N/A
CPUF_FPU = 0x02, // 386/486DX
CPUF_MMX = 0x04, // P55C, K6, PII
CPUF_INTEGER_SSE = 0x08, // PIII, Athlon
CPUF_SSE = 0x10, // PIII, Athlon XP/MP
CPUF_SSE2 = 0x20, // PIV, Hammer
CPUF_3DNOW = 0x40, // K6-2
CPUF_3DNOW_EXT = 0x80, // Athlon
CPUF_X86_64 = 0xA0, // Hammer (note: equiv. to 3DNow + SSE2, which only Hammer
// will have anyway)
CPUF_SSE3 = 0x100, // Some P4 & Athlon 64.
};
#define MAX_INT 0x7fffffff
#define MIN_INT -0x7fffffff
class IScriptEnvironment {
public:
virtual __stdcall ~IScriptEnvironment() {}
virtual /*static*/ long __stdcall GetCPUFlags() = 0;
virtual char* __stdcall SaveString(const char* s, int length = -1) = 0;
virtual char* __stdcall Sprintf(const char* fmt, ...) = 0;
// note: val is really a va_list; I hope everyone typedefs va_list to a pointer
virtual char* __stdcall VSprintf(const char* fmt, void* val) = 0;
__declspec(noreturn) virtual void __stdcall ThrowError(const char* fmt, ...) = 0;
class NotFound /*exception*/ {}; // thrown by Invoke and GetVar
typedef AVSValue (__cdecl *ApplyFunc)(AVSValue args, void* user_data, IScriptEnvironment* env);
virtual void __stdcall AddFunction(const char* name, const char* params, ApplyFunc apply, void* user_data) = 0;
virtual bool __stdcall FunctionExists(const char* name) = 0;
virtual AVSValue __stdcall Invoke(const char* name, const AVSValue args, const char** arg_names=0) = 0;
virtual AVSValue __stdcall GetVar(const char* name) = 0;
virtual bool __stdcall SetVar(const char* name, const AVSValue& val) = 0;
virtual bool __stdcall SetGlobalVar(const char* name, const AVSValue& val) = 0;
virtual void __stdcall PushContext(int level=0) = 0;
virtual void __stdcall PopContext() = 0;
// align should be 4 or 8
virtual PVideoFrame __stdcall NewVideoFrame(const VideoInfo& vi, int align=FRAME_ALIGN) = 0;
virtual bool __stdcall MakeWritable(PVideoFrame* pvf) = 0;
virtual /*static*/ void __stdcall BitBlt(BYTE* dstp, int dst_pitch, const BYTE* srcp, int src_pitch, int row_size, int height) = 0;
typedef void (__cdecl *ShutdownFunc)(void* user_data, IScriptEnvironment* env);
virtual void __stdcall AtExit(ShutdownFunc function, void* user_data) = 0;
virtual void __stdcall CheckVersion(int version = AVISYNTH_INTERFACE_VERSION) = 0;
virtual PVideoFrame __stdcall Subframe(PVideoFrame src, int rel_offset, int new_pitch, int new_row_size, int new_height) = 0;
virtual int __stdcall SetMemoryMax(int mem) = 0;
virtual int __stdcall SetWorkingDir(const char * newdir) = 0;
virtual void* __stdcall ManageCache(int key, void* data) = 0;
enum PlanarChromaAlignmentMode {
PlanarChromaAlignmentOff,
PlanarChromaAlignmentOn,
PlanarChromaAlignmentTest };
virtual bool __stdcall PlanarChromaAlignment(PlanarChromaAlignmentMode key) = 0;
virtual PVideoFrame __stdcall SubframePlanar(PVideoFrame src, int rel_offset, int new_pitch, int new_row_size, int new_height, int rel_offsetU, int rel_offsetV, int new_pitchUV) = 0;
};
// avisynth.dll exports this; it's a way to use it as a library, without
// writing an AVS script or without going through AVIFile.
IScriptEnvironment* __stdcall CreateScriptEnvironment(int version = AVISYNTH_INTERFACE_VERSION);
#pragma pack(pop)
#endif //__AVISYNTH_H__

View file

@ -0,0 +1,686 @@
#include <windows.h>
#include <stdio.h>
#include <map>
#include <vector>
#include <assert.h>
#include <stdlib.h>
#include <stdio.h>
#include <errno.h>
#include <string.h>
#include <fcntl.h>
#include <io.h>
extern "C" {
#include <ffmpeg\avformat.h>
#include <ffmpeg\avcodec.h>
#include <ffmpeg\swscale.h>
}
#include "MatroskaParser.h"
#include "avisynth.h"
#include "stdiostream.cpp"
class FFBase : public IClip {
private:
SwsContext *SWS;
int ConvertToFormat;
int ConvertFromFormat;
protected:
VideoInfo VI;
void SetOutputFormat(int CurrentFormat, IScriptEnvironment *Env) {
int Loss;
int BestFormat = avcodec_find_best_pix_fmt((1 << PIX_FMT_YUV420P) | (1 << PIX_FMT_YUYV422) | (1 << PIX_FMT_RGB32) | (1 << PIX_FMT_BGR24), CurrentFormat, 1, &Loss);
switch (BestFormat) {
case PIX_FMT_YUV420P: VI.pixel_type = VideoInfo::CS_I420; break;
case PIX_FMT_YUYV422: VI.pixel_type = VideoInfo::CS_YUY2; break;
case PIX_FMT_RGB32: VI.pixel_type = VideoInfo::CS_BGR32; break;
case PIX_FMT_BGR24: VI.pixel_type = VideoInfo::CS_BGR24; break;
default:
Env->ThrowError("No suitable output format found");
}
if (BestFormat != CurrentFormat) {
ConvertFromFormat = CurrentFormat;
ConvertToFormat = BestFormat;
SWS = sws_getContext(VI.width, VI.height, ConvertFromFormat, VI.width, VI.height, ConvertToFormat, SWS_LANCZOS, NULL, NULL, NULL);
}
}
PVideoFrame OutputFrame(AVFrame *Frame, IScriptEnvironment *Env) {
PVideoFrame Dst = Env->NewVideoFrame(VI);
if (ConvertToFormat != PIX_FMT_NONE && VI.pixel_type == VideoInfo::CS_I420) {
uint8_t *DstData[3] = {Dst->GetWritePtr(PLANAR_Y), Dst->GetWritePtr(PLANAR_U), Dst->GetWritePtr(PLANAR_V)};
int DstStride[3] = {Dst->GetPitch(PLANAR_Y), Dst->GetPitch(PLANAR_U), Dst->GetPitch(PLANAR_V)};
sws_scale(SWS, Frame->data, Frame->linesize, 0, VI.height, DstData, DstStride);
} else if (ConvertToFormat != PIX_FMT_NONE) {
if (VI.IsRGB()) {
uint8_t *DstData[1] = {Dst->GetWritePtr() + Dst->GetPitch() * (Dst->GetHeight() - 1)};
int DstStride[1] = {-Dst->GetPitch()};
sws_scale(SWS, Frame->data, Frame->linesize, 0, VI.height, DstData, DstStride);
} else {
uint8_t *DstData[1] = {Dst->GetWritePtr()};
int DstStride[1] = {Dst->GetPitch()};
sws_scale(SWS, Frame->data, Frame->linesize, 0, VI.height, DstData, DstStride);
}
} else if (VI.pixel_type == VideoInfo::CS_I420) {
Env->BitBlt(Dst->GetWritePtr(PLANAR_Y), Dst->GetPitch(PLANAR_Y), Frame->data[0], Frame->linesize[0], Dst->GetRowSize(PLANAR_Y), Dst->GetHeight(PLANAR_Y));
Env->BitBlt(Dst->GetWritePtr(PLANAR_U), Dst->GetPitch(PLANAR_U), Frame->data[1], Frame->linesize[1], Dst->GetRowSize(PLANAR_U), Dst->GetHeight(PLANAR_U));
Env->BitBlt(Dst->GetWritePtr(PLANAR_V), Dst->GetPitch(PLANAR_V), Frame->data[2], Frame->linesize[2], Dst->GetRowSize(PLANAR_V), Dst->GetHeight(PLANAR_V));
} else {
if (VI.IsRGB())
Env->BitBlt(Dst->GetWritePtr() + Dst->GetPitch() * (Dst->GetHeight() - 1), -Dst->GetPitch(), Frame->data[0], Frame->linesize[0], Dst->GetRowSize(), Dst->GetHeight());
else
Env->BitBlt(Dst->GetWritePtr(), Dst->GetPitch(), Frame->data[0], Frame->linesize[0], Dst->GetRowSize(), Dst->GetHeight());
}
return Dst;
}
public:
virtual bool __stdcall GetParity(int n) { return 0; }
virtual void __stdcall GetAudio(void* buf, __int64 start, __int64 count, IScriptEnvironment* env) { }
virtual void __stdcall SetCacheHints(int cachehints, int frame_range) { }
virtual const VideoInfo& __stdcall GetVideoInfo() { return VI; }
FFBase() {
SWS = NULL;
ConvertToFormat = PIX_FMT_NONE;
ConvertFromFormat = PIX_FMT_NONE;
memset(&VI, 0, sizeof(VI));
}
};
class FFMKVSource : public FFBase {
private:
AVCodecContext CodecContext;
AVCodec *Codec;
AVFrame *Frame;
int CurrentFrame;
struct FFMKVFrameInfo {
ulonglong DTS;
bool KeyFrame;
};
std::vector<FFMKVFrameInfo> FrameToDTS;
std::map<ulonglong, int> DTSToFrame;
StdIoStream ST;
MatroskaFile *MF;
char ErrorMessage[256];
unsigned int BufferSize;
void *Buffer;
CompressedStream *CS;
int ReadNextFrame(AVFrame *Frame, ulonglong *StartTime, IScriptEnvironment* Env);
CodecID MatroskaToFFCodecID(TrackInfo *TI) {
char *Codec = TI->CodecID;
if (!strcmp(Codec, "V_MS/VFW/FOURCC")) {
switch (((BITMAPINFOHEADER *)TI->CodecPrivate)->biCompression) {
case MAKEFOURCC('F', 'F', 'D', 'S'):
case MAKEFOURCC('F', 'V', 'F', 'W'):
case MAKEFOURCC('X', 'V', 'I', 'D'):
case MAKEFOURCC('D', 'I', 'V', 'X'):
case MAKEFOURCC('D', 'X', '5', '0'):
case MAKEFOURCC('M', 'P', '4', 'V'):
case MAKEFOURCC('3', 'I', 'V', 'X'):
case MAKEFOURCC('W', 'V', '1', 'F'):
case MAKEFOURCC('F', 'M', 'P', '4'):
case MAKEFOURCC('S', 'M', 'P', '4'):
return CODEC_ID_MPEG4;
case MAKEFOURCC('D', 'I', 'V', '3'):
case MAKEFOURCC('D', 'V', 'X', '3'):
case MAKEFOURCC('M', 'P', '4', '3'):
return CODEC_ID_MSMPEG4V3;
case MAKEFOURCC('M', 'P', '4', '2'):
return CODEC_ID_MSMPEG4V2;
case MAKEFOURCC('M', 'P', '4', '1'):
return CODEC_ID_MSMPEG4V1;
case MAKEFOURCC('W', 'M', 'V', '1'):
return CODEC_ID_WMV1;
case MAKEFOURCC('W', 'M', 'V', '2'):
return CODEC_ID_WMV2;
case MAKEFOURCC('W', 'M', 'V', '3'):
return CODEC_ID_WMV3;
/*
case MAKEFOURCC('M', 'S', 'S', '1'):
case MAKEFOURCC('M', 'S', 'S', '2'):
case MAKEFOURCC('W', 'V', 'P', '2'):
case MAKEFOURCC('W', 'M', 'V', 'P'):
return CODEC_ID_WMV9_LIB;
*/
case MAKEFOURCC('W', 'V', 'C', '1'):
return CODEC_ID_VC1;
case MAKEFOURCC('V', 'P', '5', '0'):
return CODEC_ID_VP5;
case MAKEFOURCC('V', 'P', '6', '0'):
case MAKEFOURCC('V', 'P', '6', '1'):
case MAKEFOURCC('V', 'P', '6', '2'):
return CODEC_ID_VP6;
case MAKEFOURCC('V', 'P', '6', 'F'):
case MAKEFOURCC('F', 'L', 'V', '4'):
return CODEC_ID_VP6F;
case MAKEFOURCC('C', 'A', 'V', 'S'):
return CODEC_ID_CAVS;
case MAKEFOURCC('M', 'P', 'G', '1'):
case MAKEFOURCC('M', 'P', 'E', 'G'):
return CODEC_ID_MPEG2VIDEO; // not a typo
case MAKEFOURCC('M', 'P', 'G', '2'):
case MAKEFOURCC('E', 'M', '2', 'V'):
case MAKEFOURCC('M', 'M', 'E', 'S'):
return CODEC_ID_MPEG2VIDEO;
case MAKEFOURCC('H', '2', '6', '3'):
case MAKEFOURCC('S', '2', '6', '3'):
case MAKEFOURCC('L', '2', '6', '3'):
case MAKEFOURCC('M', '2', '6', '3'):
case MAKEFOURCC('U', '2', '6', '3'):
case MAKEFOURCC('X', '2', '6', '3'):
return CODEC_ID_H263;
case MAKEFOURCC('H', '2', '6', '4'):
case MAKEFOURCC('X', '2', '6', '4'):
case MAKEFOURCC('V', 'S', 'S', 'H'):
case MAKEFOURCC('D', 'A', 'V', 'C'):
case MAKEFOURCC('P', 'A', 'V', 'C'):
case MAKEFOURCC('A', 'V', 'C', '1'):
return CODEC_ID_H264;
case MAKEFOURCC('M', 'J', 'P', 'G'):
case MAKEFOURCC('L', 'J', 'P', 'G'):
case MAKEFOURCC('M', 'J', 'L', 'S'):
case MAKEFOURCC('J', 'P', 'E', 'G'): // questionable fourcc?
case MAKEFOURCC('A', 'V', 'R', 'N'):
case MAKEFOURCC('M', 'J', 'P', 'A'):
return CODEC_ID_MJPEG;
case MAKEFOURCC('D', 'V', 'S', 'D'):
case MAKEFOURCC('D', 'V', '2', '5'):
case MAKEFOURCC('D', 'V', '5', '0'):
case MAKEFOURCC('C', 'D', 'V', 'C'):
case MAKEFOURCC('C', 'D', 'V', '5'):
case MAKEFOURCC('D', 'V', 'I', 'S'):
case MAKEFOURCC('P', 'D', 'V', 'C'):
return CODEC_ID_DVVIDEO;
case MAKEFOURCC('H', 'F', 'Y', 'U'):
case MAKEFOURCC('F', 'F', 'V', 'H'):
return CODEC_ID_HUFFYUV;
case MAKEFOURCC('C', 'Y', 'U', 'V'):
return CODEC_ID_CYUV;
case MAKEFOURCC('A', 'S', 'V', '1'):
return CODEC_ID_ASV1;
case MAKEFOURCC('A', 'S', 'V', '2'):
return CODEC_ID_ASV2;
case MAKEFOURCC('V', 'C', 'R', '1'):
return CODEC_ID_VCR1;
case MAKEFOURCC('T', 'H', 'E', 'O'):
return CODEC_ID_THEORA;
case MAKEFOURCC('S', 'V', 'Q', '1'):
return CODEC_ID_SVQ1;
case MAKEFOURCC('S', 'V', 'Q', '3'):
return CODEC_ID_SVQ3;
case MAKEFOURCC('R', 'P', 'Z', 'A'):
return CODEC_ID_RPZA;
case MAKEFOURCC('F', 'F', 'V', '1'):
return CODEC_ID_FFV1;
case MAKEFOURCC('V', 'P', '3', '1'):
return CODEC_ID_VP3;
case MAKEFOURCC('R', 'L', 'E', '8'):
return CODEC_ID_MSRLE;
case MAKEFOURCC('M', 'S', 'Z', 'H'):
return CODEC_ID_MSZH;
case MAKEFOURCC('Z', 'L', 'I', 'B'):
return CODEC_ID_FLV1;
case MAKEFOURCC('F', 'L', 'V', '1'):
return CODEC_ID_ZLIB;
/*
case MAKEFOURCC('P', 'N', 'G', '1'):
return CODEC_ID_COREPNG;
*/
case MAKEFOURCC('M', 'P', 'N', 'G'):
return CODEC_ID_PNG;
/*
case MAKEFOURCC('A', 'V', 'I', 'S'):
return CODEC_ID_AVISYNTH;
*/
case MAKEFOURCC('C', 'R', 'A', 'M'):
return CODEC_ID_MSVIDEO1;
case MAKEFOURCC('R', 'T', '2', '1'):
return CODEC_ID_INDEO2;
case MAKEFOURCC('I', 'V', '3', '2'):
case MAKEFOURCC('I', 'V', '3', '1'):
return CODEC_ID_INDEO3;
case MAKEFOURCC('C', 'V', 'I', 'D'):
return CODEC_ID_CINEPAK;
case MAKEFOURCC('R', 'V', '1', '0'):
return CODEC_ID_RV10;
case MAKEFOURCC('R', 'V', '2', '0'):
return CODEC_ID_RV20;
case MAKEFOURCC('8', 'B', 'P', 'S'):
return CODEC_ID_8BPS;
case MAKEFOURCC('Q', 'R', 'L', 'E'):
return CODEC_ID_QTRLE;
case MAKEFOURCC('D', 'U', 'C', 'K'):
return CODEC_ID_TRUEMOTION1;
case MAKEFOURCC('T', 'M', '2', '0'):
return CODEC_ID_TRUEMOTION2;
case MAKEFOURCC('T', 'S', 'C', 'C'):
return CODEC_ID_TSCC;
case MAKEFOURCC('S', 'N', 'O', 'W'):
return CODEC_ID_SNOW;
case MAKEFOURCC('Q', 'P', 'E', 'G'):
case MAKEFOURCC('Q', '1', '_', '0'):
case MAKEFOURCC('Q', '1', '_', '1'):
return CODEC_ID_QPEG;
case MAKEFOURCC('H', '2', '6', '1'):
case MAKEFOURCC('M', '2', '6', '1'):
return CODEC_ID_H261;
case MAKEFOURCC('L', 'O', 'C', 'O'):
return CODEC_ID_LOCO;
case MAKEFOURCC('W', 'N', 'V', '1'):
return CODEC_ID_WNV1;
case MAKEFOURCC('C', 'S', 'C', 'D'):
return CODEC_ID_CSCD;
case MAKEFOURCC('Z', 'M', 'B', 'V'):
return CODEC_ID_ZMBV;
case MAKEFOURCC('U', 'L', 'T', 'I'):
return CODEC_ID_ULTI;
case MAKEFOURCC('V', 'I', 'X', 'L'):
return CODEC_ID_VIXL;
case MAKEFOURCC('A', 'A', 'S', 'C'):
return CODEC_ID_AASC;
case MAKEFOURCC('F', 'P', 'S', '1'):
return CODEC_ID_FRAPS;
default:
return CODEC_ID_NONE;
}
} else if (!strcmp(Codec, "V_MPEG4/ISO/AVC"))
return CODEC_ID_H264;
else if (!strcmp(Codec, "V_MPEG4/ISO/ASP"))
return CODEC_ID_MPEG4;
else if (!strcmp(Codec, "V_MPEG2"))
return CODEC_ID_MPEG2VIDEO;
else if (!strcmp(Codec, "V_MPEG1"))
return CODEC_ID_MPEG2VIDEO; // still not a typo
else if (!strcmp(Codec, "V_SNOW"))
return CODEC_ID_SNOW;
else if (!strcmp(Codec, "V_THEORA"))
return CODEC_ID_THEORA;
else if (!strncmp(Codec, "V_REAL/RV", 9)) {
switch (Codec[9]) {
case '1':
return CODEC_ID_RV10;
case '2':
return CODEC_ID_RV20;
case '3':
return CODEC_ID_RV30;
case '4':
return CODEC_ID_RV40;
default:
return CODEC_ID_NONE;
}
} else
return CODEC_ID_NONE;
}
public:
FFMKVSource(const char *Source, int Track, IScriptEnvironment* Env) {
BufferSize = 0;
Buffer = NULL;
Frame = NULL;
CS = NULL;
CurrentFrame = 0;
memset(&ST,0,sizeof(ST));
ST.base.read = (int (__cdecl *)(InputStream *,ulonglong,void *,int))StdIoRead;
ST.base.scan = (longlong (__cdecl *)(InputStream *,ulonglong,unsigned int))StdIoScan;
ST.base.getcachesize = (unsigned int (__cdecl *)(InputStream *))StdIoGetCacheSize;
ST.base.geterror = (const char *(__cdecl *)(InputStream *))StdIoGetLastError;
ST.base.memalloc = (void *(__cdecl *)(InputStream *,size_t))StdIoMalloc;
ST.base.memrealloc = (void *(__cdecl *)(InputStream *,void *,size_t))StdIoRealloc;
ST.base.memfree = (void (__cdecl *)(InputStream *,void *)) StdIoFree;
ST.base.progress = (int (__cdecl *)(InputStream *,ulonglong,ulonglong))StdIoProgress;
ST.fp = fopen(Source ,"rb");
if (ST.fp == NULL)
Env->ThrowError("Can't open '%s': %s\n", Source, strerror(errno));
setvbuf(ST.fp, NULL, _IOFBF, CACHESIZE);
MF = mkv_OpenEx(&ST.base, 0, 0, ErrorMessage, sizeof(ErrorMessage));
if (MF == NULL) {
fclose(ST.fp);
Env->ThrowError("Can't parse Matroska file: %s\n", ErrorMessage);
}
if (Track < 0)
for (unsigned int i = 0; i < mkv_GetNumTracks(MF); i++)
if (mkv_GetTrackInfo(MF, i)->Type == TT_VIDEO) {
Track = i;
break;
}
if (Track < 0)
Env->ThrowError("No video track found");
if ((unsigned)Track >= mkv_GetNumTracks(MF))
Env->ThrowError("Invalid track number: %d\n", Track);
TrackInfo *TI = mkv_GetTrackInfo(MF, Track);
if (TI->Type != TT_VIDEO)
Env->ThrowError("Selected track is not video");
mkv_SetTrackMask(MF, ~(1 << Track));
if (TI->CompEnabled) {
CS = cs_Create(MF, Track, ErrorMessage, sizeof(ErrorMessage));
if (CS == NULL)
Env->ThrowError("Can't create decompressor: %s\n", ErrorMessage);
}
avcodec_get_context_defaults(&CodecContext);
CodecContext.extradata = (uint8_t *)TI->CodecPrivate;
CodecContext.extradata_size = TI->CodecPrivateSize;
Codec = avcodec_find_decoder(MatroskaToFFCodecID(TI));
if(Codec == NULL)
Env->ThrowError("Codec not found");
if(avcodec_open(&CodecContext, Codec) < 0)
Env->ThrowError("Could not open codec");
VI.image_type = VideoInfo::IT_TFF;
VI.width = TI->AV.Video.PixelWidth;
VI.height = TI->AV.Video.PixelHeight;
VI.fps_denominator = 1;
VI.fps_numerator = 30;
SetOutputFormat(CodecContext.pix_fmt, Env);
unsigned TrackNumber, FrameSize, FrameFlags;
ulonglong StartTime, EndTime, FilePos;
while (mkv_ReadFrame(MF, 0, &TrackNumber, &StartTime, &EndTime, &FilePos, &FrameSize, &FrameFlags) == 0) {
FFMKVFrameInfo FI;
FI.DTS = StartTime;
FI.KeyFrame = (FrameFlags & FRAME_KF) != 0;
FrameToDTS.push_back(FI);
DTSToFrame[StartTime] = VI.num_frames;
VI.num_frames++;
}
Frame = avcodec_alloc_frame();
mkv_Seek(MF, FrameToDTS[0].DTS, MKVF_SEEK_TO_PREV_KEYFRAME);
}
~FFMKVSource() {
free(Buffer);
mkv_Close(MF);
fclose(ST.fp);
av_free(Frame);
avcodec_close(&CodecContext);
}
PVideoFrame __stdcall GetFrame(int n, IScriptEnvironment* Env);
};
int FFMKVSource::ReadNextFrame(AVFrame *Frame, ulonglong *StartTime, IScriptEnvironment* Env) {
unsigned TrackNumber, FrameFlags, FrameSize;
ulonglong EndTime, FilePos, StartTime2;
*StartTime = -1;
int FrameFinished = 0;
int Ret = -1;
while (mkv_ReadFrame(MF, 0, &TrackNumber, &StartTime2, &EndTime, &FilePos, &FrameSize, &FrameFlags) == 0) {
if ((longlong)*StartTime < 0)
*StartTime = StartTime2;
if (CS) {
char CSBuffer[1024];
cs_NextFrame(CS, FilePos, FrameSize);
for (;;) {
int ReadBytes = cs_ReadData(CS, CSBuffer, sizeof(CSBuffer));
if (ReadBytes < 0)
Env->ThrowError("Error decompressing data: %s\n", cs_GetLastError(CS));
if (ReadBytes == 0)
break;
Ret = avcodec_decode_video(&CodecContext, Frame, &FrameFinished, (uint8_t *)CSBuffer, ReadBytes);
if (FrameFinished)
goto Done;
}
} else {
size_t ReadBytes;
if (fseek(ST.fp, FilePos, SEEK_SET))
Env->ThrowError("fseek(): %s\n", strerror(errno));
if (BufferSize < FrameSize) {
BufferSize = FrameSize;
Buffer = realloc(Buffer, BufferSize);
if (Buffer == NULL)
Env->ThrowError("Out of memory\n");
}
ReadBytes = fread(Buffer, 1, FrameSize, ST.fp);
if (ReadBytes != FrameSize) {
if (ReadBytes == 0) {
if (feof(ST.fp))
fprintf(stderr, "Unexpected EOF while reading frame\n");
else
fprintf(stderr, "Error reading frame: %s\n", strerror(errno));
} else
fprintf(stderr,"Short read while reading frame\n");
goto Done;
}
Ret = avcodec_decode_video(&CodecContext, Frame, &FrameFinished, (uint8_t *)Buffer, FrameSize);
if (FrameFinished)
goto Done;
}
}
Done:
return Ret;
}
PVideoFrame __stdcall FFMKVSource::GetFrame(int n, IScriptEnvironment* Env) {
bool HasSeeked = false;
bool HasBiggerKF = false;
for (int i = CurrentFrame + 1; i <= n; i++)
if (FrameToDTS[i].KeyFrame) {
HasBiggerKF = true;
break;
}
if (n < CurrentFrame || HasBiggerKF) {
mkv_Seek(MF, FrameToDTS[n].DTS, MKVF_SEEK_TO_PREV_KEYFRAME);
avcodec_flush_buffers(&CodecContext);
HasSeeked = true;
}
do {
ulonglong StartTime;
int Ret = ReadNextFrame(Frame, &StartTime, Env);
if (HasSeeked) {
CurrentFrame = DTSToFrame[StartTime];
HasSeeked = false;
}
CurrentFrame++;
} while (CurrentFrame <= n);
return OutputFrame(Frame, Env);
}
class FFMpegSource : public FFBase {
private:
AVFormatContext *FormatContext;
AVCodecContext *CodecContext;
AVCodec *Codec;
AVFrame *Frame;
int Track;
int CurrentFrame;
std::vector<int64_t> FrameToDTS;
std::map<int64_t, int> DTSToFrame;
bool ForceSeek;
int ReadNextFrame(AVFrame *Frame, int64_t *DTS);
public:
FFMpegSource(const char *Source, int _Track, bool _ForceSeek, IScriptEnvironment* Env) : Track(_Track), ForceSeek(_ForceSeek) {
CurrentFrame = 0;
if(av_open_input_file(&FormatContext, Source, NULL, 0, NULL) != 0)
Env->ThrowError("Couldn't open \"%s\"", Source);
if(av_find_stream_info(FormatContext) < 0)
Env->ThrowError("Couldn't find stream information");
if (Track >= (int)FormatContext->nb_streams)
Env->ThrowError("Invalid track number");
if (Track < 0)
for(unsigned int i = 0; i < FormatContext->nb_streams; i++)
if(FormatContext->streams[i]->codec->codec_type == CODEC_TYPE_VIDEO) {
Track = i;
break;
}
if(Track < -1)
Env->ThrowError("Couldn't find a video stream");
if (FormatContext->streams[Track]->codec->codec_type != CODEC_TYPE_VIDEO)
Env->ThrowError("Selected stream doesn't contain video");
CodecContext = FormatContext->streams[Track]->codec;
Codec = avcodec_find_decoder(CodecContext->codec_id);
if(Codec == NULL)
Env->ThrowError("Codec not found");
if(avcodec_open(CodecContext, Codec) < 0)
Env->ThrowError("Could not open codec");
VI.image_type = VideoInfo::IT_TFF;
VI.width = CodecContext->width;
VI.height = CodecContext->height;
VI.fps_denominator = CodecContext->time_base.num * 1000;
VI.fps_numerator = CodecContext->time_base.den;
// sanity check framerate
if (VI.fps_numerator < VI.fps_denominator || CodecContext->time_base.num <= 0 || CodecContext->time_base.den <= 0) {
VI.fps_denominator = 1;
VI.fps_numerator = 30;
}
SetOutputFormat(CodecContext->pix_fmt, Env);
AVPacket Packet;
while (av_read_frame(FormatContext, &Packet) >= 0) {
if (Packet.stream_index == Track) {
FrameToDTS.push_back(Packet.dts);
DTSToFrame[Packet.dts] = VI.num_frames;
VI.num_frames++;
}
av_free_packet(&Packet);
}
Frame = avcodec_alloc_frame();
av_seek_frame(FormatContext, Track, 0, AVSEEK_FLAG_BACKWARD);
}
~FFMpegSource() {
av_free(Frame);
avcodec_close(CodecContext);
av_close_input_file(FormatContext);
}
PVideoFrame __stdcall GetFrame(int n, IScriptEnvironment* Env);
};
int FFMpegSource::ReadNextFrame(AVFrame *Frame, int64_t *DTS) {
AVPacket Packet;
int FrameFinished = 0;
int Ret = -1;
*DTS = -1;
while (av_read_frame(FormatContext, &Packet) >= 0) {
if (Packet.stream_index == Track) {
Ret = avcodec_decode_video(CodecContext, Frame, &FrameFinished, Packet.data, Packet.size);
if (*DTS < 0)
*DTS = Packet.dts;
}
av_free_packet(&Packet);
if (FrameFinished)
break;
}
return Ret;
}
PVideoFrame __stdcall FFMpegSource::GetFrame(int n, IScriptEnvironment* Env) {
bool HasSeeked = false;
int IndexPosition = av_index_search_timestamp(FormatContext->streams[Track], FrameToDTS[n], AVSEEK_FLAG_BACKWARD);
int64_t NearestIndexDTS = -1;
if (IndexPosition >= 0)
NearestIndexDTS = FormatContext->streams[Track]->index_entries[IndexPosition].timestamp;
if (n < CurrentFrame || NearestIndexDTS > FrameToDTS[CurrentFrame] || (ForceSeek && IndexPosition == -1 && n > CurrentFrame + 10)) {
av_seek_frame(FormatContext, Track, FrameToDTS[n], AVSEEK_FLAG_BACKWARD);
avcodec_flush_buffers(CodecContext);
HasSeeked = true;
}
do {
int64_t DTS;
int Ret = ReadNextFrame(Frame, &DTS);
if (HasSeeked) {
CurrentFrame = DTSToFrame[DTS];
HasSeeked = DTS < 0;
}
CurrentFrame++;
} while (CurrentFrame <= n || HasSeeked);
return OutputFrame(Frame, Env);
}
AVSValue __cdecl CreateFFMpegSource(AVSValue Args, void* UserData, IScriptEnvironment* Env) {
if (!Args[0].Defined())
Env->ThrowError("No source specified");
av_register_all();
AVFormatContext *FormatContext;
if (av_open_input_file(&FormatContext, Args[0].AsString(), NULL, 0, NULL) != 0)
Env->ThrowError("Couldn't open \"%s\"", Args[0].AsString());
bool IsMatroska = !strcmp(FormatContext->iformat->name, "matroska");
av_close_input_file(FormatContext);
if (IsMatroska)
return new FFMKVSource(Args[0].AsString(), Args[1].AsInt(-1), Env);
else
return new FFMpegSource(Args[0].AsString(), Args[1].AsInt(-1), Args[2].AsBool(false), Env);
}
extern "C" __declspec(dllexport) const char* __stdcall AvisynthPluginInit2(IScriptEnvironment* Env) {
Env->AddFunction("FFMpegSource", "[source]s[track]i[forceseek]b", CreateFFMpegSource, 0);
return "FFMpegSource";
};

View file

@ -0,0 +1,24 @@
Usage
FFMpegSource(string source, int track = -1, bool forceseek = false)
source: source file
track: video track nubmer as seen by the relevant demuxer, must be a video track
negative values means the first found video track
forceseek: seek even if the format has no registered index, only useful for containers with limited avformat support
Compatibility
AVI, MKV, MP4, FLV1: Frame accurate
OGM: Messed up first frame and seeking produces smearing with forceseek=true, incredibly slow seeking without
WMV: No seeking
VOB: No rff flags, otherwise it appears to work
TS: Seeking goes way off, number of total frames is probably off too
Compiling
zlib compiled DLL from http://www.zlib.net/
ffmpeg svn from http://ffmpeg.mplayerhq.hu/
required configuration
./configure --enable-shared --disable-static --enable-memalign-hack --enable-swscaler --enable-gpl
suggested additions
--disable-encoders --disable-muxers

View file

@ -0,0 +1,82 @@
/* first we need to create an I/O object that the parser will use to read the
* source file
*/
struct StdIoStream {
struct InputStream base;
FILE *fp;
int error;
};
typedef struct StdIoStream StdIoStream;
#define CACHESIZE 65536
/* StdIoStream methods */
/* read count bytes into buffer starting at file position pos
* return the number of bytes read, -1 on error or 0 on EOF
*/
int StdIoRead(StdIoStream *st, ulonglong pos, void *buffer, int count) {
size_t rd;
if (fseek(st->fp, pos, SEEK_SET)) {
st->error = errno;
return -1;
}
rd = fread(buffer, 1, count, st->fp);
if (rd == 0) {
if (feof(st->fp))
return 0;
st->error = errno;
return -1;
}
return rd;
}
/* scan for a signature sig(big-endian) starting at file position pos
* return position of the first byte of signature or -1 if error/not found
*/
longlong StdIoScan(StdIoStream *st, ulonglong start, unsigned signature) {
int c;
unsigned cmp = 0;
FILE *fp = st->fp;
if (fseek(fp, start, SEEK_SET))
return -1;
while ((c = getc(fp)) != EOF) {
cmp = ((cmp << 8) | c) & 0xffffffff;
if (cmp == signature)
return ftell(fp) - 4;
}
return -1;
}
/* return cache size, this is used to limit readahead */
unsigned StdIoGetCacheSize(StdIoStream *st) {
return CACHESIZE;
}
/* return last error message */
const char *StdIoGetLastError(StdIoStream *st) {
return strerror(st->error);
}
/* memory allocation, this is done via stdlib */
void *StdIoMalloc(StdIoStream *st, size_t size) {
return malloc(size);
}
void *StdIoRealloc(StdIoStream *st, void *mem, size_t size) {
return realloc(mem,size);
}
void StdIoFree(StdIoStream *st, void *mem) {
free(mem);
}
/* progress report handler for lengthy operations
* returns 0 to abort operation, nonzero to continue
*/
int StdIoProgress(StdIoStream *st, ulonglong cur, ulonglong max) {
return 1;
}