ICU正则表达式运用方法

最近由于项目需求学习了一下ICU下的正则表达式的用法，在运用之前现在官网上下载ICU库，并编译，将include下的头文件路径与lib下的库文件路径都添加到编译器的option选项下,环境实在vs2008下，之后的编码如下

#include <iostream>
#include <list>
//#include <unicode/uregex.h>
#include "unicode/utypes.h"
//#include "unicode/parseerr.h"
#include "testConvAnyCodeUtf8.h"
#include "unicode/ucnv.h"
#include "apr_file_io.h"
#include "unicode/regex.h"
using namespace std;
void MatchFromFile(char* GBpath,list<UnicodeString> listring);
int reg_exp_match(const char*pat,const char* sour);
void print(list<UnicodeString> listString);
#pragma comment(lib,"conv_anycode_utf8.lib")
#pragma comment(lib,"libapr-1.lib")
#pragma comment(lib,"icuind.lib")
#pragma comment(lib,"icuucd.lib")
#define SUM 3
#define BUFFSIZE 1024
int g_num[SUM] = {0};
int main()
{
	list<UnicodeString> listString;
	char* pathname = "F:3_27的1.txt";
	/*listString.push_back(UnicodeString("s123s"));*/
	listString.push_back(UnicodeString("123"));
	/*listString.push_back(UnicodeString("[u4e00-u9fa5$]+好好学习"));*/
	listString.push_back(UnicodeString("好好学习"));
	listString.push_back(UnicodeString("d[o]m"));
	MatchFromFile(pathname,listString);
	print(listString);
	system("pause");
	return 0;
}
void MatchFromFile(char* GBpath,list<UnicodeString> listring)
{
	char* path = conv_anycode_utf8(GBpath,"UTF-8","GB18030");
	list<UnicodeString>::const_iterator _regter = listring.begin();
	apr_pool_t *pool = NULL;
	apr_file_t *file = NULL;
	apr_status_t res = APR_SUCCESS;
	char* inbuf = new char[BUFFSIZE + 1]; 
	char *result;
	int len = 0;
	UConverter *cv = NULL;
	UErrorCode status = U_ZERO_ERROR;
	memset(inbuf,BUFFSIZE + 1);
	apr_initialize();
	res = apr_pool_create(&pool,NULL);
	if(res != APR_SUCCESS)
	{
		printf("create pool failed!n");
		return;
	}
	res = apr_file_open(&file,path,APR_READ,APR_OS_DEFAULT,pool);
	if(res != APR_SUCCESS)
	{
		printf("open file fail!n");
		return ;
	}
	int i = 0;
	while(!apr_file_gets(inbuf,BUFFSIZE+1,file))
	{ 
		while(_regter != listring.end())
		{	
			len = (*_regter).length();
			result = new char[BUFFSIZE+1];
			memset(result,BUFFSIZE*sizeof(char)+1);
			const UChar* psrc = (*_regter).getBuffer();
			cv = ucnv_open("GB18030",&status);
			int32_t num = ucnv_fromUChars(cv,result,psrc,len,&status);
			if(status != U_ZERO_ERROR)
			{
				printf("Convert fail!n");
				break;
			}
			int n = reg_exp_match(result,inbuf);
			g_num[i] += n;
			delete [] result;
			ucnv_close(cv);
			i++;
			_regter++;
		}
		_regter = listring.begin();
		i = 0;
	}
	delete []inbuf;
}
void print(list<UnicodeString> listring)
{
	char *result;
	int len = 0;
	UConverter *cv = NULL;
	UErrorCode status = U_ZERO_ERROR;
	list<UnicodeString>::const_iterator iter = listring.begin();
	for(int j = 0;(j < SUM) && (iter != listring.end());j++,iter++)
	{
		len = (*iter).length();
		result = new char[BUFFSIZE+1];
		memset(result,BUFFSIZE*sizeof(char)+1);
		const UChar* psrc = (*iter).getBuffer();
		cv = ucnv_open("GB18030",&status);
		int32_t num = ucnv_fromUChars(cv,&status);
		/*	ucnv_toUChars(*/
		if(status != U_ZERO_ERROR)
		{
			printf("Convert fail!n");
			break;
		}
		printf("%s出现:%d次n",g_num[j]);
		delete [] result;
		ucnv_close(cv);
	}
}
int  reg_exp_match(const char*pat,const char* sour)
{
	int num = 0;
	int LEN = strlen(sour);
	int len = strlen(pat);
	UConverter *cv = NULL;
	RegexPattern *REPattern = NULL;///正则表达式
	RegexMatcher *REMatcher = NULL;//匹配器
	UErrorCode status = U_ZERO_ERROR;
	cv = ucnv_open("GB18030",&status);
	UChar* patStr = new UChar[len + 1];
	memset(patStr,len + 1);
	ucnv_toUChars(cv,patStr,len+1,pat,&status);
	ucnv_close(cv);
	UnicodeString patString(patStr);
	//Unicode正则表达式组装,这些函数经常代替构造函数来创建RegexPattern对象
	REPattern = RegexPattern::compile(patString,status);
	if (U_FAILURE(status)) 
	{
		return 0;
	}
	//把母串转换为Unicode
	UChar* result  = new UChar[LEN + 1];
	memset(result,LEN+1);
	cv = ucnv_open("utf-8",&status);
	ucnv_toUChars(cv,LEN+1,sour,LEN,&status);
	UnicodeString inputString(result);
	//剔除字符串中的一些序列
	UnicodeString unEscapedInput = inputString.unescape();
	//创建一个正则表达式匹配器
	REMatcher = REPattern->matcher(unEscapedInput,status);
	if (U_FAILURE(status))
	{
		return 0;
	}

	if (U_FAILURE(status))
	{
		return 0;
	}
	
	int64_t pos = 0;
	UnicodeString str = REMatcher->group(status);
	while(pos < LEN)
	{
		if(REMatcher->find(pos,status))
		{
			num++;
			pos += REMatcher->end64(status);
		}
		else
		{
			break;
		}
	}
	return num;
}

（编辑：李大同）

【声明】本站内容均来自网络，其相关言论仅代表作者个人观点，不代表本站立场。若无意侵犯到您的权利，请及时与联系站长删除相关内容!