C++11正则表达式 ECMAScript文法

突然想写个爬虫，然后发现，如果有正则表达式，会方便些。

C++11提供了Regex类.可以用来完成：

1.Match: 将整个输入拿来比对（匹配）某个正则表达式。

2.Search:查找“与正则表达式吻合”的子序列。

3.Tokenize:正则表达式作为分割器，得到分割器之前的字符串。

4.Replace:将与正则表达式吻合之的子序列替换掉

主要函数有： regex_match(),regex_search(),regex_replace();

主要对象：sregex_iterator,sregex_token_iterator，regex,smatch

例子:

[_[:alpha:]][_[:alnum:]]* 表示，以_或字母开头，后面接着任意个_或字母的组合

[123]?[0-9]\.1?[0-9]\.20[0-9]{2} 表示german format,如 24.12.2010

C++11默认使用 ECMAScript 文法,告诉你怎么构造正则表达式

附上一个测试例子：

#include <regex>
#include <iostream>
#include <string>
#include <iomanip>
#include <algorithm>

using namespace std;

void out(bool b){
    cout << ( b? "found" : "not found") << endl;
}

void regex1();
void regex2();
void regex3();
void regex4();
void regex5();
void regex6();

int main(){
    //regex1();
    //regex2();
    //regex3();
    //regex4();
    //regex5();
    //regex6();

    string data = "1994-06-25\n"
                  "2015-09-13\n"
                  "2015 09 13\n";
    smatch m;
    regex reg("(\\d{4})[- ](\\d{2})[- ](\\d{2})");
    //sregex_iterator pos(data.cbegin(),data.cend(),regex("(\\d{4})[- ](\\d{2})[- ](\\d{2})"));
    sregex_iterator pos(data.cbegin(),data.cend(),reg);
    sregex_iterator end;
        for( ; pos!=end ;pos++){
            cout << pos->str() << " ";
            cout << pos->str(1) << " " <<pos->str(2) <<" " << pos->str(3) << endl;
        }

    system("pause");
    return 0;
}

/*
 * regex_replace(string,reg1,reg2)
 * 将reg1匹配到的子串，用reg2替换掉
 */
void regex6(){
    string data = "<person>\n"
        "<first>Nico</first>\n"
        "<last>Josuttis</last>\n"
        "</person>\n";
    regex reg("<(.*)>(.*)</(\\1)>");

    cout << regex_replace(data,reg,"<$1 value=\"$2\"/>") << endl;

    string res2;

    regex_replace (back_inserter(res2),
                   data.begin(),data.end(),
                   reg,
                   "<$1 value=\"$2\"/>",
                   regex_constants::format_no_copy
                   | regex_constants::format_first_only);
    cout << res2 << endl;
}

/*
 * sregex_token_iteartor 分割器
 * 详情看函数输出，比如，通过这个，可以取出下面的名字
 */
void regex5(){
    string data = "<person>\n"
        "<first>Nico</first>\n"
        "<last>Josuttis</last>\n"
        "</person>\n";
    regex reg("<(.*)>(.*)</(\\1)>");

    sregex_token_iterator pos(data.cbegin(),data.cend(),reg,0);
    sregex_token_iterator end;

    for(; pos!=end;pos++){
        cout << "match:    "<<pos->str() << endl;
    }
    cout<< endl;

    string names = "nico,jim,helmut,paul,tim,john paul,rita";
    regex sep("[ \t\n]*[,;.][ \t\n]*");
    sregex_token_iterator p(names.cbegin(),names.cend(),sep,-1);
    sregex_token_iterator e;
    for(; p!=e;p++){
        cout << "name:    "<<*p << endl;
    }
}

/*
 * sregex_iterator 迭代器，通过这样个来遍历所以满足的子串
 * 注意传进去的 begin,end 必须是const 所以使用 cbegin()
 */
void regex4(){
    string data = "<person>\n"
        "<first>Nico</first>\n"
        "<last>Josuttis</last>\n"
        "</person>\n";
    regex reg("<(.*)>(.*)</(\\1)>");

    sregex_iterator pos(data.cbegin(),data.cend(),reg);
    sregex_iterator end;
    for(;pos != end;++pos){
        cout << "match:    "<< pos->str(0) << endl;
        cout << "tag:    "<< pos->str(1)<< endl;
        cout << "value    "<< pos->str(2) << endl;
    }

    sregex_iterator beg(data.cbegin(),data.cend(),reg);
    for_each(beg,end,[](const smatch& m){
        cout << "match:    "<< m.str() << endl;
        cout << "tag:    "<< m.str(1)<< endl;
        cout << "value    "<< m.str(2) << endl;
    });
}

/*
 *  bool regex_search(string , smatch ,regex )
 *  对整个字符串，用这个regex进行匹配，找到第一个满足的子串，
 *  通过前面的例子，可以发现 m.suffix() 指得是，满足子串后面的，
 *  一个字符的索引，所以，通过一个循环，可以不断找出后面满足的
 */
void regex3(){
    string data = "<person>\n"
        "<first>Nico</first>\n"
        "<last>Josuttis</last>\n"
        "</person>\n";
    regex reg("<(.*)>(.*)</(\\1)>");

    auto pos = data.cbegin();
    auto end = data.cend();

    smatch m;

    for(; regex_search(pos,end,m,reg);pos = m.suffix().first){
        cout << "match:        "<<m.str() << endl;
        cout << "tag:        "<<m.str(1) << endl;
        cout << "value:  " << m.str(2) << endl;
        cout << "m.prefix():    "<<m.prefix().str() << endl;
        cout << "m.suffix():    "<<m.suffix().str() << endl;
    }
}

/*
 *  bool regex_search(string , smatch ,regex )
 *  对整个字符串，用这个regex进行匹配，找到第一个满足的子串，
 *  下面是通过smatch 获取子串内容的方法，索印对应群组
 */
void regex2(){
    string data = "XML tag: <tag-name>the value</tag-name>.";
    cout << "data:        "<<data << "\n\n";

    smatch m;
    bool found = regex_search(data,m,regex("<(.*)>(.*)</(\\1)>"));

    cout << "m.empty():        "<<boolalpha << m.empty() << endl;
    cout << "m.size():        "<<m.size() << endl;
    if(found){
        cout << "m.str():        "<<m.str() << endl;
        cout << "m.length():        "<<m.length()<<endl;
        cout << "m.position():        "<<m.position()<<endl;
        cout << "m.prefix().str():  "<<m.prefix().str()<< endl;
        cout << "m.suffix().str():  "<<m.suffix().str() << endl;
        cout << endl;

        for(int i = 0;i<m.size();i++){
            cout << "m["<<i<<"].str():        " << m[i].str() << endl;
            cout << "m.str("<<i << "):        " << m.str(i) << endl;
            cout << "m.position(" << i << "):        "<<m.position(i)<<endl;
        }
        cout << endl;

        cout << "matches:" << endl;
        for(auto pos = m.begin();pos!=m.end();pos++){
            cout << " "<< *pos << " ";
            cout << "(length:  " << pos->length() << ")" << endl;
        }
    }
}

/*
 *  bool regex_match(string , regex )
 *  对整个字符串，用这个regex进行匹配，会匹配最大满足的字符串
 */
void regex1(){
    regex reg1("<.*>.*</.*>");
    bool found = regex_match("<tag>value</tag>",reg1);
    out(found);

    regex reg2("<(.*)>.*</\\1>");
    found = regex_match("<tag>value</tag>",reg2);
    out(found);

    regex reg3("<\\(.*\\)>.*</\\1>",regex_constants::grep);
    found = regex_match("<tag>value</tag>",reg3);
    out(found);

    found = regex_match("<tag>value</tag>",regex("<(.*)>.*</\\1>"));
    out(found);

    cout << endl;

    found = regex_match("XML tag: <tag>value</tag>",
        regex("<(.*)>.*</\\1>"));
    out(found);

    found = regex_match("XML tag: <tag>value</tag>",
        regex(".*<(.*)>.*</\\1>"));
    out(found);

    found = regex_search("XML tag: <tag>value</tag>",
        regex("<(.*)>.*</\\1>"));
    out(found);

    found = regex_search("XML tag: <tag>value</tag>",
        regex(".*<(.*)>.*</\\1>"));
    out(found);
}