windows代码页转换工具wincp.exe

happy886rr

[tvcp已经更名为wincp，修复数个bug，版本号升级为1.1]
wincp代码页转化工具，支持文本编码转换，BOM头修改、伪造BOM、去BOM，自动修正参数，BOM自动偏移 等功能。

下载：存外链图为a.zip解压便是。


WINCP.EXE  (TEXT CODEPAGE CONVERSION TOOL, BY LEO, VERSION 1.1)

摘要：
=========================================================================
代码页转化工具，支持文本编码转换，BOM头修改、伪造、去BOM，自动修正参数，
BOM自动偏移... 等功能。

用处特殊，效果奇佳。不仅仅是编码转换，更具代码页翻译、伪造、BOM自定义，加
密等等。

补充：code_page参数可以是代码页数字入936，也可以是代码页缩写如GBK，具体对
照详见 备注（常见代码页缩写）。
=========================================================================


用法：
-------------------------------------------------------------------------
wincp [input_file] -f [code_page] -t [code_page] -s [skip_number] -b[fill_BOM] -o [out_file]
-------------------------------------------------------------------------
  -f  From the code page
  -t  Translate to the code page
  -s  Skip the number of bytes
  -b  Filling BOM
  -o  Output file name
  -h  Show help information
-------------------------------------------------------------------------


举例：
-------------------------------------------------------------------------
REM 将test.txt从BIG5编码转为UTF8编码
wincp test.txt -o out.txt -f BIG5 -t UTF8

REM 将test.txt从ANSI编码转为UTF8编码
wincp test.txt -o out.txt -f 936 -t 65001

REM 将test.txt从UTF8编码转为UCS-2LE编码，即通常的UNICODE编码，并填充其BOM头为0xFFFE。
wincp test.txt -f 65001 -t 1200 -s 0 -b 0xFFFE -o out.txt

REM 将test.txt从UNICODE大端编码转为UTF8编码
wincp test.txt -o out.txt -f UCS2BE -t UTF8
wincp test.txt -oout.txt -fUNICODEBE -tUTF8

REM 将test.txt去除BOM
wincp test.txt -oout.txt

REM 伪造BOM
wincp test.txt -oout.txt -b0xADFF0000
...
-------------------------------------------------------------------------


备注：（常见代码页缩写）
-------------------------------------------------------------------------
ANSI    0
GBK     936
GB18030 54936
BIG5    950

UNICODE   UTF16    UCS2    1200
UNICODEBE UTF16BE  UCS2BE  1201

UTF8    65001
UTF7    65000

UTF32   12000
UTF32BE 12001
-------------------------------------------------------------------------


代码页：（通用代码页对照表）
-------------------------------------------------------------------------
  437 — 最初的 IBM PC 代码页，实现了扩展ASCII字符集
  737 — 希腊语
  850 — Latin-1(西欧语言)
  852 — Latin-2(中欧及东欧语言)
  855 — 西里尔(Cyril)字母
  857 — 土耳其语
  858 — 带欧元符号的“多语言”
  860 — 葡萄牙语
  861 — 冰岛语
  863 — 法语 加拿大英语
  865 — 北欧
  866 — 西里尔(Cyril)字母
  869 — 希腊语
  874 — 泰文字母
  932 — 日本
  949 — 韩国
  936 — GBK中文编码
  950 — BIG5繁体中文
1200 — UCS-2LE Unicode 小端序
1201 — UCS-2BE Unicode 大端序
1250 — 东欧拉丁字母
1251 — 古斯拉夫语
1252 — 西欧拉丁字母 ISO-8859-1.
1253 — 希腊语
1254 — 土耳其语
1255 — 希伯来语
1256 — 阿拉伯语
1257 — 巴尔
1258 — 越南
1254 — 土耳其语
10000 — Macintosh Roman encoding (followed by several other Mac character sets)
10007 — Macintosh Cyrillic encoding
10029 — Macintosh Central European encoding
12000 — utf-32 Unicode UTF-32, little endian byte order; available only to managed applications
12001 — utf-32BE Unicode UTF-32, big endian byte order; available only to managed applications
28591 — iso-8859-1 ISO 8859-1 Latin 1; Western European (ISO)
51936 — EUC-CN EUC Simplified Chinese; Chinese Simplified (EUC)
54936 — GB18030
65000 — UTF-7 Unicode
65001 — UTF-8 Unicode
-------------------------------------------------------------------------


BOM：（常见字节顺序标记）
-------------------------------------------------------------------------
UTF-8       EF BB BF
UTF-16 (LE) FF FE
UTF-16 (BE) FE FF
UTF-32 (LE) FF FE 00 00
UTF-32 (BE) 00 00 FE FF
UTF-7       2B 2F 76 +[38|39|2B|2F]
UTF-1       F7 64 4C
UTF-EBCDIC  DD 73 66 73
SCSU        0E FE FF
BOCU-1      FB EE 28 (+FF)
GB-18030    84 31 95 33
-------------------------------------------------------------------------

版本：
VERSION 1.0

源码支持单宽字符，各类win编译器编译。

/*
	TEXT CODEPAGE CONVERSION TOOL, COPYRIGHT@2017~2019 BY LEO, VERSION 1.1
	WINCP.EXE

	UNICODE COMPILATION:
	==> G++ wincp.cpp -D _UNICODE -D UNICODE -municode -O2 -static
	==> CL  wincp.cpp /O2 /Oy- /D "WIN32" /D "NDEBUG" /D "_CONSOLE" /D "_UNICODE" /D "UNICODE" /MD

	ANSI COMPILATION:
	==> G++ wincp.cpp -O2 -static
	==> CL  wincp.cpp /O2 /Oy- /D "WIN32" /D "NDEBUG" /D "_CONSOLE" /MD
*/


#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <windows.h>
#include <locale.h>
#include <ctype.h>
#include <tchar.h>
#include <time.h>

#if !defined(_MSC_VER) && !defined(bool)
#include <stdbool.h>
#endif

#if !defined(WIN32) && !defined(__WIN32__)
#error Only run on windows system
#endif

/***************定义宏变量***************/
//文件限制
#define MAX_FILE_SIZE 1024 * 1024

//标准行长
#define BUFF_SIZE 1024

//BOM容器长度
#define BOMS_SIZE 4

//编码检测阈值（字节）
#define CHECK_SIZE 16383

//定义帮助说明
#define HELP_INFORMATION _T("\
wincp v1.1 - Console text codepage conv tool - Copyright (C) 2017-2019 by LEO\n\
Usage: wincp [input_file] -f [code_page] -t [code_page] -s [skip_number] -b[fill_BOM] -o [out_file]\n\
\n\
General options:\n\
  -f  From the code page\n\
  -t  Translate to the code page\n\
  -s  Skip the number of bytes\n\
  -b  Filling BOM\n\
  -o  Output file name\n\
  -h  Show help information\n\
\n\
Official website:\n\
      http://www.bathome.net/thread-44343-1-1.html\n\
")

/*
Microsoft code pages:\n\
  897 – IBM-PC SBCS Japanese (JIS X 0201-1976)
  941 – IBM-PC Japanese DBCS for Open environment
  947 – IBM-PC DBCS for (Big5 encoding)
  950 – Traditional Chinese MIX (Big5 encoding) (1114 + 947) (same with euro: 1370)
 1114 – IBM-PC SBCS (Simplified Chinese; GBK; Traditional Chinese; Big5 encoding) 
 1126 – IBM-PC Korean SBCS
 1162 – Windows Thai (Extension of 874; but still called that in Windows)
 1169 – Windows Cyrillic Asian
 1250 – Windows Central Europe
 1251 – Windows Cyrillic
 1252 – Windows Western
 1253 – Windows Greek
 1254 – Windows Turkish
 1255 – Windows Hebrew
 1256 – Windows Arabic
 1257 – Windows Baltic
 1258 – Windows Vietnamese
 1361 – Korean (JOHAB)
 1362 – Korean Hangul DBCS
 1363 – Windows Korean (1126 + 1362) (Windows CP 949)
 1372 – IBM-PC MS T Chinese Big5 encoding (Special for DB2)
 1373 – Windows Traditional Chinese (extension of 950)
 1374 – IBM-PC DB Big5 encoding extension for HKSCS
 1375 – Mixed Big5 encoding extension for HKSCS (intended to match 950)
 1385 – IBM-PC Simplified Chinese DBCS (Growing CS for GB18030, also used for GBK PC-DATA.)
 1386 – IBM-PC Simplified Chinese GBK (1114 + 1385) (Windows CP 936)
 1391 – Simplified Chinese 4 Byte (Growing CS for GB18030, also used for GBK PC-DATA.)
 1392 – IBM-PC Simplified Chinese MIX (1252 + 1385 + 1391)
 ...
*/

//开关解析宏名
#define _OPT_TEOF -1
#define _OPT_TILL -2
#define _OPT_TERR -3

//开关解析变量
int OPTIND=1, OPTOPT, UNOPTIND=-1;
TCHAR* OPTARG;

#if defined(_UNICODE) || defined(UNICODE)
#define TCHARFORMAT WCHAR
#else
#define TCHARFORMAT CHAR
#endif

//BOM转UINT宏函数
#define BOM2UINT(x) (unsigned int)(((unsigned char)(x)[0]<<24)|((unsigned char)(x)[1]<<16)|((unsigned char)(x)[2]<<8)|((unsigned char)(x)[3]))

/***************功能函数群***************/
//判断纯数字
int _istPositiveNumber(TCHAR* instr)
{
	//过滤前空
	while(_istspace(*instr))
	{
		instr++;
	}

	//过滤空值和负数
	if(*instr == _T('\0') || *instr == _T('-'))
	{
		return -1;
	}

	//判断每一位是数字
	while(_istdigit(*(instr)))
	{
		instr++;
	}

	//判断结尾
	return (*instr == _T('\0')) ?0 :1;
}

//获取代码页
int _tgetCP(TCHAR* instr)
{
	//空指针
	if(instr == NULL)
	{
		return -1;
	}

	//设置返回值
	int retCP;
	switch(_istPositiveNumber(instr))
	{
	case -1:
		return -1;

	case  0:
		return _ttoi((TCHARFORMAT*)instr);

	case  1:
		break;
	}

	if     (_tcsicmp(instr, _T("ANSI")   ) ==0)
	{
		retCP=CP_ACP;
	}
	else if(_tcsicmp(instr, _T("GBK")    ) ==0)
	{
		retCP=936;
	}
	else if(_tcsicmp(instr, _T("GB18030")) ==0)
	{
		retCP=54936;
	}
	else if(_tcsicmp(instr, _T("BIG5")   ) ==0)
	{
		retCP=950;
	}
	else if(
	    _tcsicmp(instr, _T("UNICODE")  ) ==0 ||
	    _tcsicmp(instr, _T("UTF16")    ) ==0 ||
	    _tcsicmp(instr, _T("UCS2")     ) ==0
	)
	{
		retCP=1200;
	}
	else if(
	    _tcsicmp(instr, _T("UNICODEBE")) ==0 ||
	    _tcsicmp(instr, _T("UTF16BE")  ) ==0 ||
	    _tcsicmp(instr, _T("UCS2BE")   ) ==0
	)
	{
		retCP=1201;
	}
	else if(_tcsicmp(instr, _T("UTF7")   ) ==0)
	{
		retCP=65000;
	}
	else if(_tcsicmp(instr, _T("UTF8")   ) ==0)
	{
		retCP=65001;
	}
	else if(_tcsicmp(instr, _T("UTF32")  ) ==0)
	{
		retCP=12000;
	}
	else if(_tcsicmp(instr, _T("UTF32BE")) ==0)
	{
		retCP=12001;
	}
	else
	{
		retCP=-1;
	}
	return retCP;
}

//字符转HEX
int C2HEX(TCHAR intc)
{
	int hret=-1;
	if     (_T('0')<=intc && intc<=_T('9'))
	{
		hret=intc-48;
	}
	else if(_T('A')<=intc && intc<=_T('F'))
	{
		hret=intc-55;
	}
	else if(_T('a')<=intc && intc<=_T('f'))
	{
		hret=intc-87;
	}
	else
	{
		hret=-1;
	}

	return hret;
}

//BOM头转BINBYTE
int TCHARRAY2BIN(TCHAR* instr, BYTE* &tainer)
{
	memset(tainer, 0, BOMS_SIZE);

	if(*instr == _T('x') || *instr == _T('X'))
	{
		instr ++;
	}
	if(_tcsnicmp(instr, _T("0x"), 2) ==0)
	{
		instr += 2;
	}

	int i=-1, hexNUM;
	while(++i<BOMS_SIZE)
	{
		hexNUM=C2HEX(*instr++);
		if(hexNUM != -1)
		{
			tainer[i] |= (hexNUM<<4);
		}
		else
		{
			break;
		}

		hexNUM=C2HEX(*instr++);
		if(hexNUM != -1)
		{
			tainer[i] |= hexNUM;
		}
		else
		{
			break;
		}
	}

	return i;
}

//开关解析模块
int _tgetopt(int nargc, TCHAR* nargv[], TCHAR* ostr)
{
	static TCHAR* place = (TCHAR*)_T("");
	static TCHAR* lastostr = NULL;
	register TCHAR* oli;

	if(ostr!=lastostr)
	{
		lastostr=ostr;
		place=(TCHAR*)_T("");
	}

	if(!*place)
	{
		if(
		    (OPTIND>=nargc)                           ||
		    (*(place=nargv[OPTIND]) !=(TCHAR)_T('-')) ||
		    (!*(++place))
		)
		{
			if(*place !=(TCHAR)_T('-') && OPTIND <nargc)
			{
				place =(TCHAR*)_T("");
				if(UNOPTIND == -1)
				{
					UNOPTIND = OPTIND++;
					return _OPT_TILL;
				}
				else
				{
					return _OPT_TERR;
				}
			}

			place=(TCHAR*)_T("");
			return _OPT_TEOF;
		}
		if (*place == (TCHAR)_T('-') && *(place+1) == (TCHAR)_T('\0'))
		{
			++OPTIND;
			return _OPT_TEOF;
		}
	}

	if (
	    (OPTOPT=*place++) == (TCHAR)_T(':') ||
	    !(oli=(TCHAR*)_tcschr((TCHARFORMAT*)ostr, (TCHAR)OPTOPT))
	)
	{
		if(!*place)
		{
			++OPTIND;
		}
	}

	if (oli != NULL && *(++oli) !=(TCHAR)_T(':'))
	{
		OPTARG=NULL;
		if(!*place)
		{
			++OPTIND;
		}
	}
	else
	{
		if(*place)
		{
			OPTARG=place;
		}
		else if(nargc <= ++OPTIND)
		{
			place=(TCHAR*)_T("");
		}
		else
		{
			OPTARG=nargv[OPTIND];
		}
		place=(TCHAR*)_T("");
		++OPTIND;
	}
	return OPTOPT;
}

//代码页转化
void PageTurnAround(const BYTE* input, int inputSIZE, int inPAGE, int outPAGE, BYTE* &outDATA, int &oLEN)
{
	int wLEN;
	char* outCACHE=NULL;
	wchar_t* wcsCACHE=NULL;

	if(inPAGE == outPAGE)
	{
		outDATA=(BYTE*)input, oLEN=inputSIZE;
		return;
	}

	//针对UCS-2输入代码页
	if(inPAGE == 1200)
	{
		wcsCACHE=(wchar_t*)input;
		wLEN=inputSIZE/2+1;
		goto TOMCS;
	}
	if(inPAGE == 1201)
	{
		wchar_t* wp=(wchar_t*)input;
		while(*wp)
		{
			*wp = (((*wp)&0x00FF)<<8)|(((*wp)&0xFF00)>>8);
			wp ++;
		}
		wcsCACHE=(wchar_t*)input;
		wLEN=inputSIZE/2+1;
		goto TOMCS;
	}

	//输入代码页 过渡到 UNICODE中转代码页
	wLEN=MultiByteToWideChar(inPAGE, 0, (char*)input,-1, NULL, 0);
	if(wLEN <1)
	{
		_ftprintf(stderr, _T("Unable to convert code page\n"));
		exit(1);
	}
	wcsCACHE=(wchar_t*)malloc(wLEN * sizeof(wchar_t));
	MultiByteToWideChar(inPAGE, 0, (char*)input, -1, wcsCACHE, wLEN);

TOMCS:
	//针对UCS-2输出代码页
	if(outPAGE == 1200)
	{
		outDATA=(BYTE*)wcsCACHE, oLEN=(wLEN-1)*2;
		return;
	}
	if(outPAGE == 1201)
	{
		wchar_t* wp=(wchar_t*)wcsCACHE;
		while(*wp)
		{
			*wp = (((*wp)&0x00FF)<<8)|(((*wp)&0xFF00)>>8);
			wp ++;
		}
		outDATA=(BYTE*)wcsCACHE, oLEN=(wLEN-1)*2;
		return;
	}

	//UNICODE中转代码页 过渡到 输出代码页
	int uLEN=WideCharToMultiByte(outPAGE, 0, wcsCACHE, -1, NULL, 0, NULL, NULL);
	if(uLEN <1)
	{
		_ftprintf(stderr, _T("Unable to convert code page\n"));
		exit(1);
	}
	outCACHE=(char*)malloc(uLEN);
	WideCharToMultiByte(outPAGE, 0, wcsCACHE, -1, outCACHE, uLEN, NULL, NULL);

	outDATA=(BYTE*)outCACHE, oLEN=uLEN-1;
	return;
}

//文本转化核心
bool ConveTextFile(TCHAR* inFILE, TCHAR* outFILE, int inPAGE, int outPAGE, int skipNUMBER, int binBOM_SIZE, BYTE* tainerBOM_BIN)
{
	//读取输入文件
	FILE* inFP=_tfopen(inFILE, _T("rb"));
	if(inFP == NULL)
	{
		_ftprintf(stderr, _T("Open input file error\n"));
		exit(1);
	}

	//获取字典文件尺寸
	fseek(inFP, 0, SEEK_END);
	int fsize = ftell(inFP);
	if(fsize > MAX_FILE_SIZE)
	{
		_ftprintf(stderr, _T("The input file is too large, can not be greater than %dKB\n"), MAX_FILE_SIZE/1024);
		exit(1);
	}

	fseek(inFP, (long)skipNUMBER, SEEK_SET);

	//动态分配文本容器
	BYTE* inDATA=(BYTE*)malloc(fsize+1);

	//将文本流读入内存
	int readSIZE=fsize-skipNUMBER;
	fread(inDATA, sizeof(BYTE), readSIZE, inFP);
	fclose(inFP);
	inDATA[fsize-skipNUMBER]='\0';

	//转化代码页
	int oLEN=0;
	BYTE* outDATA=NULL;

	//调用代码页转换函数
	PageTurnAround(inDATA, readSIZE, inPAGE, outPAGE, outDATA, oLEN);

	if(oLEN <1)
	{
		return false;
	}

	//读取输出文件
	FILE* outFP=_tfopen(outFILE, _T("wb"));
	if(outFP == NULL)
	{
		_ftprintf(stderr, _T("Open output file error\n"));
		exit(1);
	}

	fwrite(tainerBOM_BIN, sizeof(BYTE), binBOM_SIZE, outFP);
	fwrite(outDATA, sizeof(BYTE), oLEN, outFP);
	fclose(outFP);

	free(inDATA);
	return true;
}

#if defined _MSC_VER
#else
extern "C"
#endif

//*************MAIN主函数入口*************/
int _tmain(int argc, TCHAR** argv)
{
	if(argc<2)
	{
		//无参数则退出
		_ftprintf(stdout, HELP_INFORMATION);
		return 0;
	}

	//设置传入参数
	TCHAR *opeOUTFILE=NULL,  *opeINFILE=NULL;
	int    opeIN_PAGE=CP_ACP, opeOUT_PAGE=CP_ACP, opeSKIP_NUMBER=0, opeBOM_SIZE=0;
	BYTE   opeFLAG=0x00, *pTAINER=NULL, tainerBOM_BIN[BOMS_SIZE]= {0};

	//开关解析
	int K=_OPT_TEOF;
	while( (K=_tgetopt(argc, argv, (TCHAR*)_T("f:t:s:b:o:hF:T:S:B:O:H"))) != _OPT_TEOF)
	{
		switch(K)
		{
		case _T('f'):
		case _T('F'):
			opeIN_PAGE =_tgetCP(OPTARG);
			if(opeIN_PAGE == -1)
			{
				_ftprintf(stderr, _T("The switch '-f' needs a positive number\n"));
				exit(1);
			}
			opeFLAG |= 0x01;
			break;
	
		case _T('t'):
		case _T('T'):
			opeOUT_PAGE =_tgetCP(OPTARG);
			if(opeIN_PAGE == -1)
			{
				_ftprintf(stderr, _T("The switch '-t' needs a positive number\n"));
				exit(1);
	
			}
			opeFLAG |= 0x02;
			break;
	
		case _T('s'):
		case _T('S'):
			if(OPTARG == NULL)
			{
				_ftprintf(stderr, _T("The switch '-s' needs a positive number\n"));
				exit(1);
			}
			opeSKIP_NUMBER = _ttoi((TCHARFORMAT*)OPTARG);
			if(! (0<= opeSKIP_NUMBER && opeSKIP_NUMBER <=4 ) )
			{
				_ftprintf(stderr, _T("The switch '-s' needs a number between {0,4}\n"));
				exit(1);
			}
			opeFLAG |= 0x04;
			break;
	
		case _T('b'):
		case _T('B'):
			if(OPTARG != NULL && _tcslen(OPTARG) <= 8)
			{
				_ftprintf(stderr, _T("The switch '-b' needs binary number\n"));
				exit(1);
			}
			pTAINER=(BYTE*)tainerBOM_BIN;
			opeBOM_SIZE = TCHARRAY2BIN(OPTARG, pTAINER);
			opeFLAG |= 0x08;
			break;
	
		case _T('o'):
		case _T('O'):
			if(OPTARG != NULL)
			{
				opeFLAG |= 0x10;
				opeOUTFILE = OPTARG;
			}
			break;
	
		case _T('h'):
		case _T('H'):
			_ftprintf(stdout, HELP_INFORMATION);
			return 0;
	
		case _OPT_TILL:
			//第一个无选项的参数识别为输入名
			opeINFILE = argv[UNOPTIND];
			break;
	
		case _OPT_TERR:
			_ftprintf(stderr, _T("Extra parameters \"%s\"\n"), argv[OPTIND]);
			exit(1);
	
		default:
			_ftprintf(stderr, _T("Unknown switch '-%c'\n"), K);
			exit(1);
		}
	}

	//无输入，强制退出
	if(opeINFILE == NULL)
	{
		_ftprintf(stderr, _T("Needs input file name\n"));
		exit(1);
	}

	//无输出，强制覆盖
	if(opeOUTFILE == NULL)
	{
		opeOUTFILE=opeINFILE;
	}

	//无参数，SKIP智能偏移
	if((opeFLAG&0x04) == 0)
	{

		FILE* inFP=_tfopen(opeINFILE, _T("rb"));
		if(inFP == NULL)
		{
			_ftprintf(stderr, _T("Open input file error\n"));
			exit(1);
		}
		fread(tainerBOM_BIN, sizeof(BYTE), BOMS_SIZE, inFP);
		fclose(inFP);

		UINT uBOM_VALUE = BOM2UINT(tainerBOM_BIN);

		//倒序识别BOM
		switch(uBOM_VALUE)
		{
		case 0xFFFE0000:
		case 0x0000FEFF:
		case 0x2B2F7638:
		case 0x84319533:
			opeSKIP_NUMBER = 4;
			break;

		default:
			if(
			    (uBOM_VALUE>>16) == 0xFFFE ||
			    (uBOM_VALUE>>16) == 0xFEFF
			)
			{
				opeSKIP_NUMBER = 2;
			}
			else if((uBOM_VALUE>>8) == 0xEFBBBF)
			{
				opeSKIP_NUMBER = 3;
			}
			else
			{
				opeSKIP_NUMBER = 0;
			}
			break;
		}
	}

	//无参数，BOM自动修正
	if((opeFLAG&0x08) == 0)
	{
		TCHAR* tcsBIN =_T("");
		switch(opeOUT_PAGE)
		{
		case 1200:
			tcsBIN =_T("0xFFFE");
			break;

		case 1201:
			tcsBIN =_T("0xFEFF");
			break;

		case 12000:
			tcsBIN =_T("0xFFFE0000");
			break;

		case 12001:
			tcsBIN =_T("0x0000FEFF");
			break;

		case 65001:
			tcsBIN =_T("0xEFBBBF");
			break;

		case 65007:
			tcsBIN =_T("0x2B2F7638");
			break;

		case 54936:
			tcsBIN =_T("0x84319533");
			break;

		default:
			break;
		}

		//填充BOM缓存
		pTAINER = (BYTE*)tainerBOM_BIN;
		opeBOM_SIZE = TCHARRAY2BIN(tcsBIN, pTAINER);
	}

	//执行代码页转化
	if(! ConveTextFile(opeINFILE, opeOUTFILE, opeIN_PAGE, opeOUT_PAGE, opeSKIP_NUMBER, opeBOM_SIZE, tainerBOM_BIN))
	{
		_ftprintf(stderr, _T("Conver file error\n"));
		return 1;
	}

	return 0;
}
复制代码

happy886rr

回复 2# 3518228042
建议直接用sed，处理这些最好用脚本和正则。当然，C语言也能做，但是代码将会很繁琐。

3518228042

演示下将本地的目录“小说”目录下的所有网页转换成txt，
希望可以做到去除非段落换行，比如浏览器打开网页文件显示：
脸
　　
色当即羞红了起来
网页代码应该去除两个<br/>　　<br/>及之间的内容：
“脸<br/>　　<br/>色当即羞红了起来”替换成“脸色当即羞红了起来”

如果<br/>　　<br/>左边有中文右边有正规的段落换行(全角半角空格多个)，不希望替换；
如果<br/>　　<br/>左边有中文右边有中文，必须替换；
如果<br/>　　<br/>左边第一个字是，、“：；，必须替换；
如果<br/>　　<br/>右边是，。、“”：；！？…，必须替换；
如果<br/>　　<br/>左边第一个字是。？！”……右边是……不希望替换；
如果<br/>　　<br/>左边是：右边是“必须替换；

还有有时候所有的换行不是<br/>　　<br/>而是</P><P>、<br/><br/>或
<br/>
<br/>

最后提取标题和<br/>之间内容，自定义的替换广告内容，和对多个空字符换行被清理掉，变成干净的ANSI文本

我这里有几个测试网页