regexhelper.h
#ifndef REGEX_HELPER_H_INCLUDE
#define REGEX_HELPER_H_INCLUDE
#include<string>
#include<vector>
namespace Framework{
class RegexHelper
{
public:
RegexHelper();
virtual ~RegexHelper();
/*
* 是否包含匹配字符串
* @param: input 输入字符串
* @param:pattern 正则表达式
*/
static bool IsMatch(const char* input,const char* pattern);
/*
* 获取首个匹配字符串或其字串
* @param: input 输入字符串
* @param:pattern 正则表达式
* @param:group 子捕获组
*/
static std::string Match(const char* input,const char* pattern,int group = 0);
/*
* 获取首个匹配字符串所有捕获组
* @param: input 输入字符串
* @param:pattern 正则表达式
* @param: results 输出的字符串数组
*/
static int Match(const char* input,const char* pattern,std::vector<std::string>& results);
/*
* 匹配字符串数目
* @param: input 输入字符串
* @param:pattern 正则表达式
*/
static int Matches(const char* input,const char* pattern);
/*
* 输出所有匹配字符串或其捕获组
* @param: input 输入字符串
* @param:pattern 正则表达式
* @param: results 输出的字符串数组
* @param:group 捕获组
*/
static int Matches(const char* input,const char* pattern,std::vector<std::string>& results,int group = 0);
/*
* 替换首个匹配字符串
* @param: input 输入字符串
* @param:pattern 正则表达式
* @param:repValue 被替换值,可以是捕获组的组合
*/
static std::string ReplaceFirst(const char* input,const char* pattern,const char* repValue);
/*
* 替换所有匹配字符串
* @param: input 输入字符串
* @param:pattern 正则表达式
* @param:repValue 被替换值,可以是捕获组的组合
*/
static std::string ReplaceAll(const char* input,const char* pattern,const char* repValue);
/*
* 分割字符串并输出结果
* @param: input 输入字符串
* @param:pattern 正则表达式
* @param: results 输出的字符串数组
*/
static int Split(const char* input,const char* pattern,std::vector<std::string>& results);
/*
* 分割字符串并根据捕获组输出
* @param: input 输入字符串
* @param:pattern 正则表达式
* @param:subs 捕获组
* @param: results 输出的字符串数组
*/
static int Split(const char* input,const char* pattern,std::vector<int>& subs,std::vector<std::string>& results);
protected:
private:
};
}
#endif // REGEX_HELPER_H_INCLUDE
regexhelper.cpp
#include "regexhelper.h"
#include<boost/regex.hpp>
namespace Framework{
RegexHelper::RegexHelper()
{
//ctor
}
RegexHelper::~RegexHelper()
{
//dtor
}
bool RegexHelper::IsMatch(const char* input,const char* pattern)
{
boost::regex reg( pattern , boost::regex::perl|boost::regex::icase);
bool ret = boost::regex_search( input , reg);
return ret;
}
std::string RegexHelper::Match(const char* input,const char* pattern,int group)
{
if(group < 0)group = 0;
boost::cmatch mat;
boost::regex reg( pattern , boost::regex::perl|boost::regex::icase);
bool success = boost::regex_search( input, mat, reg);
if(success){
if(mat[group].matched){
return std::string(mat[group]);
}
}
return std::string("");
}
int RegexHelper::Match(const char* input,const char* pattern,std::vector<std::string>& results)
{
boost::cmatch mat;
boost::regex reg( pattern , boost::regex::perl|boost::regex::icase );
bool success =boost::regex_search( input, mat, reg);
int total = 0;
if(success){ //如果匹配成功
//cout << "match success" << endl;
//显示所有子串
for(boost::cmatch::iterator itr=mat.begin(); itr!=mat.end(); ++itr){
// 指向子串对应首位置 指向子串对应尾位置 子串内容
//cout << itr->first-szStr << ' ' << itr->second-szStr << ' ' << *itr << endl;
results.push_back(std::string(*itr));
total++ ;
}
}
return total;
}
int RegexHelper::Matches(const char* input,const char* pattern)
{
boost::regex reg( pattern, boost::regex::perl|boost::regex::icase); //查找字符串里的数字
boost::cregex_iterator itrBegin = make_regex_iterator(input,reg); //(szStr, szStr+strlen(szStr), reg);
boost::cregex_iterator itrEnd;
int total = 0;
for(boost::cregex_iterator itr=itrBegin; itr!=itrEnd; ++itr){
//cout << (*itr)[0].first-szStr << ' ' << (*itr)[0].second-szStr << ' ' << *itr << endl;
total++;
}
return total;
}
int RegexHelper::Matches(const char* input,const char* pattern,std::vector<std::string>& results,int group)
{
if(group < 0)group = 0;
boost::regex reg( pattern, boost::regex::perl|boost::regex::icase); //查找字符串里的数字
boost::cregex_iterator itrBegin = make_regex_iterator(input,reg); //(szStr, szStr+strlen(szStr), reg);
boost::cregex_iterator itrEnd;
int total = 0;
for(boost::cregex_iterator itr=itrBegin; itr!=itrEnd; ++itr){
//cout << (*itr)[0].first-szStr << ' ' << (*itr)[0].second-szStr << ' ' << *itr << endl;
results.push_back(std::string((*itr)[group]));
total++;
}
return total;
}
std::string RegexHelper::ReplaceFirst(const char* input,const char* pattern,const char* repValue)
{
//( 1 ) (( 3 ) 2 )(( 5 )4)( 6 )
//(/w+)://((/w+/.)*/w+)((//w*)*)(//w+/./w+)?
//^协议://网址(x.x...x)/路径(n个/字串)/网页文件(xxx.xxx)
//const char *szReg = "(\\w+)://((\\w+\\.)*\\w+)((/\\w*)*)(/\\w+\\.\\w+)?";
//const char *szStr = "http://www.cppprog.com/2009/0112/48.html";
//repValue = ""
boost::regex reg( pattern , boost::regex::perl|boost::regex::icase);
std::string sret = boost::regex_replace( std::string(input), reg, std::string(repValue));
return sret;
}
std::string RegexHelper::ReplaceAll(const char* input,const char* pattern,const char* repValue)
{
//string s1 = "(<)|(>)|(&)";
//string s2 = "(?1<)(?2>)(?3&)";
boost::regex reg( pattern , boost::regex::perl|boost::regex::icase);
std::string sret = boost::regex_replace( std::string(input), reg, std::string(repValue), boost::match_default | boost::format_all);
return sret;
}
int RegexHelper::Split(const char* input,const char* pattern,std::vector<std::string>& results)
{
boost::regex reg(pattern, boost::regex::perl|boost::regex::icase); //按/符拆分字符串
boost::cregex_token_iterator itrBegin = make_regex_token_iterator(input,reg,-1); //使用-1参数时拆分,使用其它数字时表示取第几个子串,可使用数组取多个串
boost::cregex_token_iterator itrEnd;
int total = 0;
for(boost::cregex_token_iterator itr=itrBegin; itr!=itrEnd; ++itr){
//cout << *itr << endl;
results.push_back(std::string(*itr));
total++;
}
return total;
}
int RegexHelper::Split(const char* input,const char* pattern,std::vector<int>& subs,std::vector<std::string>& results)
{
boost::regex reg(pattern, boost::regex::perl|boost::regex::icase); //取/的前一字符和后一字符(这个字符串形象貌似有点邪恶-_-)
boost::cregex_token_iterator itrBegin = make_regex_token_iterator(input,reg,subs); //使用-1参数时拆分,使用其它数字时表示取第几个子串,可使用数组取多个串
boost::cregex_token_iterator itrEnd;
int total = 0;
for(boost::cregex_token_iterator itr=itrBegin; itr!=itrEnd; ++itr){
//cout << *itr << endl;
results.push_back(std::string(*itr));
total++;
}
return total;
}
}
测试代码
void testregex()
{
//( 1 ) (( 3 ) 2 )(( 5 )4)( 6 )
//(/w+)://((/w+/.)*/w+)((//w*)*)(//w+/./w+)?
//^协议://网址(x.x...x)/路径(n个/字串)/网页文件(xxx.xxx)
const char *szReg = "(\\w+)://((\\w+\\.)*\\w+)((/\\w*)*)(/\\w+\\.\\w+)?";
const char *szStr = "sss http://www.cppprog.com/2009/0112/48.html";
{ //字符串匹配
cout <<"match:"<< Framework::RegexHelper::IsMatch(szStr,szReg)<<endl;
//assert(r);
}
{ //提取子串
vector<string> results;
int total = Framework::RegexHelper::Match(szStr,szReg,results);
cout << "total="<<total<<endl;
if(total > 0){
for(vector<string>::const_iterator it = results.begin(); it != results.end(); ++it){
cout<< *it <<endl;
}
}
}
{ //查找
cout<<Framework::RegexHelper::Match(szStr,"\\d+")<<endl;
}
{ //替换
cout<<Framework::RegexHelper::ReplaceFirst(szStr,szReg,"ftp://$2$5")<<endl;
}
{ //替换2,把<>&转换成网页字符
string s1 = "(<)|(>)|(&)";
string s2 = "(?1<)(?2>)(?3&)";
cout<<Framework::RegexHelper::ReplaceFirst("cout << a&b << endl;",s1.c_str(),s2.c_str())<<endl;
cout<<Framework::RegexHelper::ReplaceAll("cout << a&b << endl;",s1.c_str(),s2.c_str())<<endl;
}
{ //使用迭代器找出所有数字
vector<string> results;
int total = Framework::RegexHelper::Matches(szStr,"\\d+",results);
cout << "total="<<total<<endl;
if(total > 0){
for(vector<string>::const_iterator it = results.begin(); it != results.end(); ++it){
cout<< *it <<endl;
}
}
}
{ //使用迭代器拆分字符串
vector<string> results;
int total = Framework::RegexHelper::Split(szStr,"/",results);
cout << "total="<<total<<endl;
if(total > 0){
for(vector<string>::const_iterator it = results.begin(); it != results.end(); ++it){
cout<< *it <<endl;
}
}
}
{ //使用迭代器拆分字符串2
vector<string> results;
// 第一子串和第二子串
vector<int> subv;subv.push_back(1),subv.push_back(2);
//取/的前一字符和后一字符(这个字符串形象貌似有点邪恶-_-)
int total = Framework::RegexHelper::Split(szStr,"(.)/(.)",subv,results);
cout << "total="<<total<<endl;
if(total > 0){
for(vector<string>::const_iterator it = results.begin(); it != results.end(); ++it){
cout<< *it <<endl;
}
}
}
}