2015年(24)
分类: C/C++
2015-07-25 01:11:23
原文地址:(转)C/C++ 中使用正则表达式 作者:liujianping
CODE:
#include
#include
#include
#define SUBSLEN 10 /* 匹配子串的数量 */
#define EBUFLEN 128 /* 错误消息buffer长度 */
#define BUFLEN 1024 /* 匹配到的字符串buffer长度 */
int main()
{
size_t len;
regex_t re; /* 存储编译好的正则表达式,正则表达式在使用之前要经过编译 */
regmatch_t subs [SUBSLEN]; /* 存储匹配到的字符串位置 */
char matched [BUFLEN]; /* 存储匹配到的字符串 */
char errbuf [EBUFLEN]; /* 存储错误消息 */
int err, i;
char src [] = "111 Hello World 222"; /* 源字符串 */
char pattern [] = "(.*) "; /* pattern字符串 */
printf("String : %s\n", src);
printf("Pattern: \"%s\"\n", pattern);
/* 编译正则表达式 */
err = regcomp(&re, pattern, REG_EXTENDED);
if (err) {
len = regerror(err, &re, errbuf, sizeof(errbuf));
printf("error: regcomp: %s\n", errbuf);
return 1;
}
printf("Total has subexpression: %d\n", re.re_nsub);
/* 执行模式匹配 */
err = regexec(&re, src, (size_t) SUBSLEN, subs, 0);
if (err == REG_NOMATCH) { /* 没有匹配成功 */
printf("Sorry, no match ...\n");
regfree(&re);
return 0;
} else if (err) { /* 其它错误 */
len = regerror(err, &re, errbuf, sizeof(errbuf));
printf("error: regexec: %s\n", errbuf);
return 1;
}
/* 如果不是REG_NOMATCH并且没有其它错误,则模式匹配上 */
printf("\nOK, has matched ...\n\n");
for (i = 0; i <= re.re_nsub; i++) {
len = subs[i].rm_eo - subs[i].rm_so;
if (i == 0) {
printf ("begin: %d, len = %d ", subs[i].rm_so, len); /* 注释1 */
} else {
printf("subexpression %d begin: %d, len = %d ", i, subs[i].rm_so, len);
}
memcpy (matched, src + subs[i].rm_so, len);
matched[len] = '\0';
printf("match: %s\n", matched);
}
regfree(&re); /* 用完了别忘了释放 */
return (0);
}
执行结果是
CODE:
String : 111 Hello World 222
Pattern: "(.*) "
Total has subexpression: 1
OK, has matched ...
begin: %, len = 4 match: Hello World
subexpression 1 begin: 11, len = 11 match: Hello World
从示例程序可以看出,使用之前先用regcomp()编译一下,然后调用regexec()进行实际匹配。如果只是看有没有匹配成功,掌握这2个函数的用法即可。有时候我们想要取得匹配后的子表达式,比如示例中想获得title是什么,需要用小括号 "( )"把子表达式括起来"CODE:
/* Compile thuswise:
* gcc -Wall pcre1.c -I/usr/local/include -L/usr/local/lib -R/usr/local/lib -lpcre
*
*/
#include
#include
#include
#define OVECCOUNT 30 /* should be a multiple of 3 */
#define EBUFLEN 128
#define BUFLEN 1024
int main()
{
pcre *re;
const char *error;
int erroffset;
int ovector[OVECCOUNT];
int rc, i;
char src [] = "111 Hello World 222";
char pattern [] = "(.*) ";
printf("String : %s\n", src);
printf("Pattern: \"%s\"\n", pattern);
re = pcre_compile(pattern, 0, &error, &erroffset, NULL);
if (re == NULL) {
printf("PCRE compilation failed at offset %d: %s\n", erroffset, error);
return 1;
}
rc = pcre_exec(re, NULL, src, strlen(src), 0, 0, ovector, OVECCOUNT);
if (rc < 0) {
if (rc == PCRE_ERROR_NOMATCH) printf("Sorry, no match ...\n");
else printf("Matching error %d\n", rc);
free(re);
return 1;
}
printf("\nOK, has matched ...\n\n");
for (i = 0; i < rc; i++) {
char *substring_start = src + ovector[2*i];
int substring_length = ovector[2*i+1] - ovector[2*i];
printf("%2d: %.*s\n", i, substring_length, substring_start);
}
free(re);
return 0;
}
执行结果是:
CODE:
String : 111 Hello World 222
Pattern: "(.*) "
OK, has matched ...
0: Hello World
1: Hello World
比较这2个例子可以看出,在regex用的是regcomp()、regexec(),pcre则使用pcre_compile()、pcre_exec(),用法几乎完全一致。CODE:
/*
* g++ pcre2.cpp -I/usr/local/include -L/usr/local/lib -R/usr/local/lib -lpcre++ -lpcre
*/
#include
#include
#include
using namespace std;
using namespace pcrepp;
int main()
{
string src("111 Hello World 222");
string pattern("(.*) ");
cout << "String : " << src << endl;
cout << "Pattern : " << pattern << endl;
Pcre reg(pattern, PCRE_DOTALL);
if (reg.search(src) == true) { //
cout << "\nOK, has matched ...\n\n";
for(int pos = 0; pos < reg.matches(); pos++) {
cout << pos << ": " << reg[pos] << endl;
}
} else {
cout << "Sorry, no match ...\n";
return 1;
}
return 0;
}
执行结果是:
CODE:
String : 111 Hello World 222
Pattern : (.*)
OK, has matched ...
0: Hello World
4、oniguruma