takechar_asm.c

Takechar 可以从不同种类的源代码中取出中文字符.它对于嵌入式设备的小字体开发非常有帮助.

/****************************************************
	Takechar V1.00 Takes out Chinese characters from source code.
	Copyright(C) 2007 ShiQizheng([e-mail])
	http://newexperience.51.net

	All rights reserved.

	Released under GPL. Please see "gpl.txt" for details.
****************************************************/

#include "takechar_asm.h"

static FILE *pInputFile;
static char gszInputFileName[ MAX_FILENAME_LENGTH];

static int giSCCounter;	// ;
static int giStringCounter;  // ''
static int giChineseCounter;

static CHARCHAIN *pChain;

int TakeChar_ASM_Init( int iFunctionNumber, int *piResult)
{
	pInputFile = 0;

	giSCCounter = 0;
	giStringCounter = 0;
	giChineseCounter = 0;

	pInputFile = fopen( gszInputFileName, "rb");
	if ( !pInputFile)
	{
		*piResult = RESULT_FILE_ERROR;
		return TAKECHAR_ASM_DONE;
	}

	return TAKECHAR_ASM_P;

}

int TakeChar_ASM_P( int iFunctionNumber, int *piResult)
{
	// +
	char cChar;
	int iReadResult;
	
	iReadResult = ReadOneByte( pInputFile, &cChar);

	switch( iReadResult)
	{
		case RESULT_FILE_EOF:
			return TAKECHAR_ASM_DONE;

		case RESULT_FILE_ERROR:
			*piResult = RESULT_FILE_ERROR;		
			return TAKECHAR_ASM_DONE;
	}

	switch ( cChar)
	{
		case ';':
//			Log( ";");
			giSCCounter ++;
			return TAKECHAR_ASM_SC;

		case '\'':
			return TAKECHAR_ASM_SQ;

		default:
			return TAKECHAR_ASM_P;
	}
}

int TakeChar_ASM_SC( int iFunctionNumber, int *piResult)
{
	// ;
	char cChar;
	int iReadResult;
	
	iReadResult = ReadOneByte( pInputFile, &cChar);

	switch( iReadResult)
	{
		case RESULT_FILE_EOF:
			return TAKECHAR_ASM_DONE;

		case RESULT_FILE_ERROR:
			*piResult = RESULT_FILE_ERROR;		
			return TAKECHAR_ASM_DONE;
	}

	switch ( cChar)
	{
		case 0x0a:
			return TAKECHAR_ASM_P;

		default:
			return TAKECHAR_ASM_SC;
	}
}

int TakeChar_ASM_SQ( int iFunctionNumber, int *piResult)
{
	// '
	char cChar;
	char cChar2;
	int iReadResult;
	char szChineseChar[3];
	
	iReadResult = ReadOneByte( pInputFile, &cChar);

	switch( iReadResult)
	{
		case RESULT_FILE_EOF:
			return TAKECHAR_ASM_DONE;

		case RESULT_FILE_ERROR:
			*piResult = RESULT_FILE_ERROR;		
			return TAKECHAR_ASM_DONE;
	}

	switch ( cChar)
	{
		case '\'':
//			Log( "''");
			giStringCounter ++;
			return TAKECHAR_ASM_P;

		default:
			if ( cChar & 0x80)
			{
				iReadResult = ReadOneByte( pInputFile, &cChar2);

				switch( iReadResult)
				{
					case RESULT_FILE_EOF:
						return TAKECHAR_ASM_DONE;

					case RESULT_FILE_ERROR:
						*piResult = RESULT_FILE_ERROR;
						return TAKECHAR_ASM_DONE;

					default:
						if ( cChar2 & 0x80)
						{
							//Find one Chinese char
							szChineseChar[0] = cChar;
							szChineseChar[1] = cChar2;
							szChineseChar[2] = 0;
							Log( "Found one Chinese char:%s", szChineseChar);
							giChineseCounter ++;
							if ( pChain == 0)
							{
								if ( CharChain_Init( &pChain, szChineseChar) != CHARCHINA_OK)
								{
									Log( "ERROR: Can not init char chain.");
									*piResult = RESULT_ERROR;
									return TAKECHAR_ASM_DONE;
								}
							}else
							{
								if ( CharChain_AddChar( pChain, szChineseChar) != CHARCHINA_OK)
								{
									Log( "ERROR: Can not add char to chain.");
									*piResult = RESULT_ERROR;
									return TAKECHAR_ASM_DONE;
								}
							}
							return TAKECHAR_ASM_SQ;
						}else
						{
							//Other chars
							switch ( cChar)
							{
								case '\'':
//									Log( "''");
									giStringCounter ++;
									return TAKECHAR_ASM_P;

								default:
									return TAKECHAR_ASM_SQ;
							}
						}
						return TAKECHAR_ASM_SQ;
				}
			}else
			{
				return TAKECHAR_ASM_SQ;
			}

	}
}

int TakeChar_ASM_Done( int iFunctionNumber, int *piResult)
{
	if ( pInputFile)
	{
		fclose( pInputFile);
	}

	switch( *piResult)
	{
		case RESULT_DONE:
/*
			Log( "giSCCounter=%d", giSCCounter);
			Log( "giStringCounter=%d", giStringCounter);
			Log( "giChineseCounter=%d", giChineseCounter);
*/
			Log( "Done.");
			break;

		case RESULT_FILE_ERROR:
			Log( "ERROR: Can not read one byte from input file:%s\n", gszInputFileName);			
			break;

		default:
			Log( "ERROR.");
			break;
	}

	return TAKECHAR_ASM_EXIT;

}

int TakeCharFromFile_ASM( char *pszInputFileName, CHARCHAIN **ppOutputChain)
{
	FUNCTIONTABLE Functions[] =
	{
		{ TAKECHAR_ASM_INIT, TakeChar_ASM_Init},
		{ TAKECHAR_ASM_P, TakeChar_ASM_P},
		{ TAKECHAR_ASM_SC, TakeChar_ASM_SC},
		{ TAKECHAR_ASM_SQ, TakeChar_ASM_SQ},
		{ TAKECHAR_ASM_DONE, TakeChar_ASM_Done},
		{ -1, 0}
	};
	FUNCTIONTABLE *p;
	int iFunctionNumber;
	int iResult = RESULT_DONE;

	strcpy( gszInputFileName, pszInputFileName);
	pChain = *ppOutputChain;

	iFunctionNumber = TAKECHAR_ASM_INIT;
	
	while ( iFunctionNumber != TAKECHAR_ASM_EXIT)
	{
		for ( p = ( FUNCTIONTABLE*)Functions; p->pFunction!= 0; p++ )
		{
			if ( iFunctionNumber == p->iFunctionNumber)
			{
				iFunctionNumber = ( *p->pFunction)( iFunctionNumber, &iResult);
				break;
			}
		}
		
		if ( p->pFunction == 0 )
		{
			iFunctionNumber = TAKECHAR_ASM_EXIT;
		}
	}

	*ppOutputChain = pChain;
	return iResult;
}