C++正则表达式

基本组件

//定义正则表达式
typedef basic_regex<char> regex;
typedef basic_regex<wchar_t> wregex;

//匹配结果的集合
typedef match_results<const char *> cmatch;
typedef match_results<const wchar_t *> wcmatch;
typedef match_results<string::const_iterator> smatch;
typedef match_results<wstring::const_iterator> wsmatch;

//匹配结果的集合中的元素
typedef sub_match<const char *> csub_match;
typedef sub_match<const wchar_t *> wcsub_match;
typedef sub_match<string::const_iterator> ssub_match;
typedef sub_match<wstring::const_iterator> wssub_match;

//迭代器适配器
typedef regex_iterator<const char *> cregex_iterator;
typedef regex_iterator<const wchar_t *> wcregex_iterator;
typedef regex_iterator<string::const_iterator> sregex_iterator;
typedef regex_iterator<wstring::const_iterator> wsregex_iterator;

regex_match     //匹配测试
regex_search    //搜索
regex_replace   //替换

• 使用示例

#include <regex>
#include <string>
#include <vector>

using namespace std;

int _tmain(int argc, _TCHAR* argv[])
{
    string str("12ab34cd");
    regex aRex[] =
    {
        regex("([0-9]+)([a-z]+)"),
        regex("(([0-9]+)([a-z]+))+")
    };

    bool aRe[2] = 
    {
        regex_match(str, aRex[0]),      //false
        regex_match(str, aRex[1])       //true
    };

    smatch sm;
    bool nRe = regex_search(str, sm, aRex[0]);
    string aStrRe[3] = 
    {
        sm.str(0),      //[0] = "12ab"
        sm.str(1),      //[1] = "12"
        sm.str(2)       //[2] = "ab"
    };

    string aStrReplace[] = 
    {
        regex_replace(str, aRex[0], string("New")), //[0] = "NewNew"
        regex_replace(str, aRex[0], string("New"),  //[1] = "New34cd"
            std::regex_constants::format_first_only),
        regex_replace(str, aRex[0], string("$1|$2"))//[2] = "12|ab34|cd"
    };

    /*
    match_default = 0x0000,     //默认
    match_not_bol = 0x0001,     //不将首字符作为行首处理
    match_not_eol = 0x0002,     //不将尾字符作为行尾处理
    match_not_bow = 0x0004,     //不将首字符作为单词首处理
    match_not_eow = 0x0008,     //不将尾字符作为单词尾处理
    match_any = 0x0010,         //若存在多个匹配，则返回任意一个匹配
    match_not_null = 0x0020,    //不匹配任何空序列
    match_continuous = 0x0040,  //匹配必须从输入的首字符开始
    match_prev_avail = 0x0100,  //输入序列包含第一个匹配之前的内容
    format_default = 0x0000,    //用ECMAScript规则替换字符串
    format_sed = 0x0400,        //用POXIS sed规则替换字符串
    format_no_copy = 0x0800,    //不输出输入部分中未匹配的部分
    format_first_only = 0x1000  //只替换子表达式第一次出现的位置
    */

    vector<string> aVecStr[2];
    for (sregex_iterator it(str.begin(), str.end(), aRex[0]), itEnd; 
        it != itEnd; ++it)
    {
        aVecStr[0].emplace_back(it->str());
        aVecStr[1].emplace_back(it->str(1));
    }
    /*
    aVecStr[0]:
        [0] = "12ab"
        [1] = "34cd"

    aVecStr[1]:
        [0] = "12"
        [1] = "34"
    */

    return 0;
}

匹配规则

一般匹配

regex_match("1", regex("\x31"));    //true

regex_match("a1.+-*/-=\\|][{}?/.,!@#$%^&*()_+", regex(".*"));   //true
regex_match("\n a1.+-*/-=\\|][{}?/.,!@#$%^&*()_+", regex(".*"));//false

regex_match("1", regex("1|2"));    //true

regex_match("1", regex("[12]"));    //true
regex_match("a", regex("[^12]"));   //true
regex_match("a", regex("[a-z]"));   //true
regex_match("1", regex("[^a-z]"));  //true

cmatch cm;
regex_search("abcd abc", cm, regex("[a-z]*c\\b"));   //true
string str = cm.str();  //str = "abc"

cmatch cm;
regex_search("zyc abcd", cm, regex("[a-z]*c\\B"));   //true
string str = cm.str();  //str = "abc"

regex_match("1", regex("\\d"));   //true

regex_match("1", regex("\\D"));   //false
regex_match("A", regex("\\D"));   //true

regex_match(" \f\n\r\t\v", regex("[\\s]{6}"));          //true
regex_match(" \f\n\r\t\v", regex("[ \f\n\r\t\v]{6}"));  //true
regex_match("a1.+-*/-=\\|][{}?/.,!@#$%^&*()_+", regex("[\\S]+"));   //true

regex_match("a_1_A", regex("\\w+"));         //true
regex_match(" \r\t\v\f\n", regex("\\W+"));   //true

次数匹配

regex_match("", regex("[0-9]*"));       //true
regex_match("123", regex("[0-9]*"));    //true

regex_match("", regex("[0-9]+"));       //false
regex_match("123", regex("[0-9]+"));    //true

regex_match("", regex("[0-9]?"));       //true
regex_match("123", regex("[0-9]?"));    //false

regex_match("123", regex("[0-9]{3}"));  //true
regex_match("123", regex("[0-9]{4}"));  //false
regex_match("123", regex("[0-9]{1,}")); //true
regex_match("123", regex("[0-9]{1,2}"));//false


cmatch cm;
string str;

regex_search("111", cm, regex("1*?"));  //true
str = cm.str(); //str = ""

regex_search("111", cm, regex("1+?"));  //true
str = cm.str(); //str = "1"

regex_search("111", cm, regex("1??"));  //true
str = cm.str(); //str = ""

regex_search("111", cm, regex("1{2}?"));//true
str = cm.str(); //str = "11"

regex_search("111", cm, regex("1{2,}?"));//true
str = cm.str(); //str = "11"

regex_search("111", cm, regex("1{1,3}?"));//true
str = cm.str(); //str = "1"

子表达式匹配

cmatch cm;
regex_search("abc 123efg", cm, regex("[0-9]{3}([a-z]*)"));  //true
string aStr[] = 
{
    cm.str(0),  //[0] = "123efg"
    cm.str(1),  //[1] = "efg"
};

cmatch cm;
regex re("[0-9]{3}(?:[a-z]*)([0-9]*)");
regex_search("abc 123efg456", cm, re);  //true
string aStr[] =
{
    cm.str(0),  //[0] = "123efg456"
    cm.str(1),  //[1] = "456"
};


cmatch cm;
regex re("[a-z]*(1|2|3)");
regex_search("abc4 efg1", cm, re);  //true
string aStr[] =
{
    cm.str(0),  //[0] = "efg1"
    cm.str(1),  //[1] = "1"
};

cmatch cm;
regex re("[a-z]*(?=1|2|3)");
regex_search("abc4 efg1", cm, re);  //true
string aStr[] =
{
    cm.str(0),  //[0] = "efg"
    cm.str(1),  //[1] = ""
};

cmatch cm;
regex re("[a-z]*(?=1|2|3)([0-9]*)");
regex_search("abc4 efg1", cm, re);  //true
string aStr[] =
{
    cm.str(0),  //[0] = "efg1"
    cm.str(1),  //[1] = "1"
    cm.str(2),  //[2] = ""
};

cmatch cm;
regex re("[a-z]*(?!1|2|3)");
bRe = regex_search("abc4 efg1", cm, re);    //true
string aStr[] =
{
    cm.str(0),  //[0] = "abc"
    cm.str(1),  //[1] = ""
};

位置匹配

cmatch cm;
regex_search("123 abc", cm, regex("^[a-z]+"));      //false
regex_search("123 abc efg", cm, regex("[a-z]+$"));  //true
string str = cm.str();      //str = "efg"