avisynth.h

the De-interlace video processing developed with C++ enviroment in Motion adaptive in 3D and Bi-indi

// 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 = 2 };


/* 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 HasVideo() ? ((__int64)(frames) * audio_samples_per_second * fps_denominator / fps_numerator) : 0; }
  int FramesFromAudioSamples(__int64 samples) const { return (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 nchannels; }
  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) {
    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;
  }
  // Test for same colorspace
  bool IsSameColorspace(const VideoInfo& vi) {
    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;