audiosource.cpp

VC++视频开发实例集锦(包括“远程视频监控”"语音识别系统"等13个经典例子)

//	VirtualDub - Video processing and capture application
//	Copyright (C) 1998-2001 Avery Lee
//
//	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.

#include <stdio.h>
#include <stdlib.h>

#include <windows.h>
#include <vfw.h>

#include "AudioSource.h"
#include "AVIReadHandler.h"
#include "AC3FileSrc.h"



AudioSourceWAV::AudioSourceWAV(char *szFile, LONG inputBufferSize) {
	MMIOINFO mmi;

	memset(&mmi,0,sizeof mmi);
	mmi.cchBuffer	= inputBufferSize;
	hmmioFile		= mmioOpen(szFile, &mmi, MMIO_READ | MMIO_ALLOCBUF);
}

AudioSourceWAV::~AudioSourceWAV() {
	mmioClose(hmmioFile, 0);
}

BOOL AudioSourceWAV::init() {
	if (!hmmioFile) return FALSE;

	chunkRIFF.fccType = mmioFOURCC('W','A','V','E');
	if (MMSYSERR_NOERROR != mmioDescend(hmmioFile, &chunkRIFF, NULL, MMIO_FINDRIFF))
		return FALSE;

	chunkDATA.ckid = mmioFOURCC('f','m','t',' ');
	if (MMSYSERR_NOERROR != mmioDescend(hmmioFile, &chunkDATA, &chunkRIFF, MMIO_FINDCHUNK))
		return FALSE;

	if (!allocFormat(chunkDATA.cksize)) return FALSE;
	if (chunkDATA.cksize != mmioRead(hmmioFile, (char *)getWaveFormat(), chunkDATA.cksize))
		return FALSE;

	if (MMSYSERR_NOERROR != mmioAscend(hmmioFile, &chunkDATA, 0))
		return FALSE;

	chunkDATA.ckid = mmioFOURCC('d','a','t','a');
	if (MMSYSERR_NOERROR != mmioDescend(hmmioFile, &chunkDATA, &chunkRIFF, MMIO_FINDCHUNK))
		return FALSE;

	bytesPerSample	= getWaveFormat()->nBlockAlign; //getWaveFormat()->nAvgBytesPerSec / getWaveFormat()->nSamplesPerSec;
	lSampleFirst	= 0;
	lSampleLast		= chunkDATA.cksize / bytesPerSample;
	lCurrentSample	= 0;

	streamInfo.fccType					= streamtypeAUDIO;
	streamInfo.fccHandler				= 0;
	streamInfo.dwFlags					= 0;
	streamInfo.wPriority				= 0;
	streamInfo.wLanguage				= 0;
	streamInfo.dwInitialFrames			= 0;
	streamInfo.dwScale					= bytesPerSample;
	streamInfo.dwRate					= getWaveFormat()->nAvgBytesPerSec;
	streamInfo.dwStart					= 0;
	streamInfo.dwLength					= chunkDATA.cksize / bytesPerSample;
	streamInfo.dwSuggestedBufferSize	= 0;
	streamInfo.dwQuality				= 0xffffffff;
	streamInfo.dwSampleSize				= bytesPerSample;

	return TRUE;
}

int AudioSourceWAV::_read(LONG lStart, LONG lCount, LPVOID buffer, LONG cbBuffer, LONG *lBytesRead, LONG *lSamplesRead) {
	LONG lBytes = lCount * bytesPerSample;
	
	if (buffer) {
		if (lStart != lCurrentSample)
			if (-1 == mmioSeek(hmmioFile, chunkDATA.dwDataOffset + bytesPerSample*lStart, SEEK_SET))
				return AVIERR_FILEREAD;

		if (lBytes != mmioRead(hmmioFile, (char *)buffer, lBytes))
			return AVIERR_FILEREAD;

		lCurrentSample = lStart + lCount;
	}

	*lSamplesRead = lCount;
	*lBytesRead = lBytes;

	return AVIERR_OK;
}

///////////////////////////

AudioSourceAVI::AudioSourceAVI(IAVIReadHandler *pAVI) {
	pAVIFile	= pAVI;
	pAVIStream	= NULL;
}

AudioSourceAVI::~AudioSourceAVI() {
	if (pAVIStream)
		delete pAVIStream;
}

BOOL AudioSourceAVI::init() {
	LONG format_len;

	pAVIStream = pAVIFile->GetStream(streamtypeAUDIO, 0);
	if (!pAVIStream) return FALSE;

	if (pAVIStream->Info(&streamInfo, sizeof streamInfo))
		return FALSE;

	pAVIStream->FormatSize(0, &format_len);

	if (!allocFormat(format_len)) return FALSE;

	if (pAVIStream->ReadFormat(0, getFormat(), &format_len))
		return FALSE;

	lSampleFirst = pAVIStream->Start();
	lSampleLast = pAVIStream->End();

	return TRUE;
}

void AudioSourceAVI::Reinit() {
	pAVIStream->Info(&streamInfo, sizeof streamInfo);
	lSampleFirst = pAVIStream->Start();
	lSampleLast = pAVIStream->End();
}

bool AudioSourceAVI::isStreaming() {
	return pAVIStream->isStreaming();
}

void AudioSourceAVI::streamBegin(bool fRealTime) {
	pAVIStream->BeginStreaming(lSampleFirst, lSampleLast, fRealTime ? 1000 : 2000);
}

void AudioSourceAVI::streamEnd() {
	pAVIStream->EndStreaming();

}

BOOL AudioSourceAVI::_isKey(LONG lSample) {
	return pAVIStream->IsKeyFrame(lSample);
}
int AudioSourceAVI::_read(LONG lStart, LONG lCount, LPVOID lpBuffer, LONG cbBuffer, LONG *lpBytesRead, LONG *lpSamplesRead) {
	int err;
	long lBytes, lSamples;

	// There are some video clips roaming around with truncated audio streams
	// (audio streams that state their length as being longer than they
	// really are).  We use a kludge here to get around the problem.

	err = pAVIStream->Read(lStart, lCount, lpBuffer, cbBuffer, lpBytesRead, lpSamplesRead);

	if (err != AVIERR_FILEREAD)
		return err;

	// Suspect a truncated stream.
	//
	// AVISTREAMREAD_CONVENIENT will tell us if we're actually encountering a
	// true read error or not.  At least for the AVI handler, it returns
	// AVIERR_ERROR if we've broached the end.  

	*lpBytesRead = *lpSamplesRead = 0;

	while(lCount > 0) {
		err = pAVIStream->Read(lStart, AVISTREAMREAD_CONVENIENT, NULL, 0, &lBytes, &lSamples);

		if (err)
			return 0;

		if (!lSamples) return AVIERR_OK;

		if (lSamples > lCount) lSamples = lCount;

		err = pAVIStream->Read(lStart, lSamples, lpBuffer, cbBuffer, &lBytes, &lSamples);

		if (err)
			return err;

		lpBuffer = (LPVOID)((char *)lpBuffer + lBytes);
		cbBuffer -= lBytes;
		lCount -= lSamples;

		*lpBytesRead += lBytes;
		*lpSamplesRead += lSamples;
	}

	return AVIERR_OK;
}


///////////////////////////////////////////////////////////////////////////////////////////////////

// Dummy CRC pointer
Crc16 *crc;

AudioSourceMP3::AudioSourceMP3(char *szFile) {

	stream = new Ibitstream(szFile);
	header = new Header;

	f = fopen( szFile, "rb" );
}

AudioSourceMP3::~AudioSourceMP3() {

	if( f ) fclose( f );

	delete header;
	delete stream;
}

BOOL AudioSourceMP3::init() {

	if( !f ) return FALSE;

	if (!header->read_header(stream, &crc)){
		return FALSE;
	}
	do {
	} while( header->read_header(stream, &crc) );

	real s_len = (stream->current_frame()+1)*header->ms_per_frame()/1000;

	if (!allocFormat(sizeof MPEGLAYER3WAVEFORMAT)) return FALSE;


	MPEGLAYER3WAVEFORMAT *mp3format = (MPEGLAYER3WAVEFORMAT *)getWaveFormat();
	mp3format->wfx.wFormatTag		= WAVE_FORMAT_MPEGLAYER3;		/* format type */
    mp3format->wfx.nChannels		= (header->mode() == single_channel) ? 1 : 2;							/* number of channels (i.e. mono, stereo...) */
    mp3format->wfx.nSamplesPerSec	= header->frequency();			/* sample rate */
    mp3format->wfx.nAvgBytesPerSec	= stream->file_size()/s_len;	/* for buffer estimation */
    mp3format->wfx.nBlockAlign		= 1152;							/* block size of data */
    mp3format->wfx.wBitsPerSample	= 0;							/* Number of bits per sample of mono data */
	mp3format->wfx.cbSize			= 12;							/* The count in bytes of the size of
																		extra information (after cbSize) */
	mp3format->wID					= 1;
	mp3format->fdwFlags				= 2;
	mp3format->nBlockSize			= stream->file_size()/(stream->current_frame()+1);
	mp3format->nFramesPerBlock		= 1;
	mp3format->nCodecDelay			= 0;


	lSampleFirst	= 0;
	lSampleLast		= stream->current_frame()+1;


	streamInfo.fccType					= streamtypeAUDIO;
	streamInfo.fccHandler				= 0;
	streamInfo.dwFlags					= 0;
	streamInfo.wPriority				= 0;
	streamInfo.wLanguage				= 0;
	streamInfo.dwInitialFrames			= 0;
	streamInfo.dwScale					= 1152;
	streamInfo.dwRate					= header->frequency();
	streamInfo.dwStart					= 0;
	streamInfo.dwLength					= lSampleLast;
	streamInfo.dwSuggestedBufferSize	= 0;
	streamInfo.dwQuality				= 0xffffffff;
	streamInfo.dwSampleSize				= 0;


	delete header;
	header = new Header;
	stream->reset();
	pos = 0;
	header->read_header(stream, &crc);

	return TRUE;
}

int AudioSourceMP3::_read(LONG lStart, LONG lCount, LPVOID buffer, LONG cbBuffer, LONG *lBytesRead, LONG *lSamplesRead)
{
	*lSamplesRead = 0;
	*lBytesRead = 0;

	if( buffer )
	{
		if (lStart != stream->current_frame())
		{
			delete header;
			header = new Header;
			stream->reset();
			while( stream->current_frame() != lStart )
			{
				pos = stream->file_pos();
				header->read_header(stream, &crc);
			}
		}

		uint32 frame_size = stream->file_pos() - pos;
		if( frame_size>cbBuffer ) return AVIERR_OK;

		fseek( f, pos, SEEK_SET );
		fread( buffer, frame_size, 1, f );
		cbBuffer -= frame_size;
		buffer = (void *)(((unsigned long)buffer)+frame_size);
		(*lBytesRead) += frame_size;
		pos = stream->file_pos();
		header->read_header(stream, &crc);

		(*lSamplesRead) = 1;

	}
    
	return AVIERR_OK;
}

///////////////////////////////////////////////////////////////////////////////////////////////////

AudioSourceOggVorbis::AudioSourceOggVorbis(char *szFile) {

	f = fopen( szFile, "rb" );
	pos = 0;

}

AudioSourceOggVorbis::~AudioSourceOggVorbis() {

	if( f ) fclose( f );

}

#ifndef _WAVEFORMATEXTENSIBLE_
#define _WAVEFORMATEXTENSIBLE_
#pragma pack(1)
typedef struct {
    WAVEFORMATEX    Format;
    union {
        WORD wValidBitsPerSample;       /* bits of precision  */
        WORD wSamplesPerBlock;          /* valid if wBitsPerSample==0 */
        WORD wReserved;                 /* If neither applies, set to zero. */
    } Samples;
    DWORD           dwChannelMask;      /* which channels are */
                                        /* present in stream  */
    GUID            SubFormat;
} WAVEFORMATEXTENSIBLE, *PWAVEFORMATEXTENSIBLE;
#pragma pack()
#endif // !_WAVEFORMATEXTENSIBLE_



BOOL AudioSourceOggVorbis::streamInit() {

	char	*buffer;
	int		bytes;

	eos = 0;

	while( ogg_sync_pageout( &oy, &og )!=1 ) {
		buffer = ogg_sync_buffer( &oy, 1 );
		bytes = fread( buffer, 1, 1, f );
		ogg_sync_wrote( &oy, bytes );
	}

	ogg_stream_init( &os, ogg_page_serialno( &og ) );

	vorbis_info_init( &vi );
	vorbis_comment_init( &vc );
	if( ogg_stream_pagein( &os, &og )<0 ) { 
		return FALSE;
	}
	if( ogg_stream_packetout( &os, &op )!=1 ) { 
		return FALSE;
	}
	if( vorbis_synthesis_headerin( &vi, &vc, &op )<0 ) { 
		return FALSE;
	}
	

	int i = 0;
	while( i<2 ) {
		while( i<2 ) {
			int result = ogg_sync_pageout( &oy, &og );
			if( result==0 ) break; /* Need more data */
									/* Don't complain about missing or corrupt data yet.  We'll
										catch it at the packet output phase */
			if( result==1 ) {
				ogg_stream_pagein( &os, &og ); /* we can ignore any errors here
												as they'll also become apparent
												at packetout */
				while( i<2 ) {
					result = ogg_stream_packetout( &os, &op );
					if( result==0 ) break;
					if( result<0 ) {
					/* Uh oh; data at some point was corrupted or missing!
						We can't tolerate that in a header.  Die. */
						return FALSE;
					}
					vorbis_synthesis_headerin( &vi, &vc, &op );
					i++;
				}
			}
		}
		/* no harm in not checking before adding more */
		buffer = ogg_sync_buffer( &oy, 1 );
		bytes = fread( buffer, 1, 1, f );
		if( bytes==0 && i<2 ) {
			return FALSE;
		}
		ogg_sync_wrote( &oy, bytes );
	}
	fgetpos( f, &pos );
	--pos;

	vorbis_synthesis_init( &vd, &vi );
	vorbis_block_init( &vd, &vb );

	return TRUE;
}


typedef unsigned __int8 uint8;
//typedef unsigned __int32 uint32;
typedef unsigned __int64 uint64;

bool splitHeader( const uint8* Buffer, size_t BufferSize, size_t& SplitPosition, uint8** Header,size_t*HeaderSize )
{
	// Just for your information, here's the format of an Ogg Page header:
#pragma pack(1)
	 struct PageHeader
	 {
		 // Flag values
		enum
		{
			CONTINUED=1