[原创]C语言利用pcre正则表达式库

C语言使用正则表达式，可以利用pcre库，这个比较不错的哦。

在使用过程中，利用python进行测试正则表达式是否OK，后发现出现了问题。如下所示：

regex.c:11:18: warning: unknown escape sequence: '\/' [enabled by default]
char* url_re="(https?|ftp|mms):\/\/([A-z0-9]+[_\-]?[A-z0-9]?\.)*[A-z0-9]+\-?[A-z0-9]+\.[A-z]{2,}(\/.*)?";
^
regex.c:11:18: warning: unknown escape sequence: '\/' [enabled by default]
regex.c:11:18: warning: unknown escape sequence: '\-' [enabled by default]
regex.c:11:18: warning: unknown escape sequence: '\.' [enabled by default]
regex.c:11:18: warning: unknown escape sequence: '\-' [enabled by default]
regex.c:11:18: warning: unknown escape sequence: '\.' [enabled by default]
regex.c:11:18: warning: unknown escape sequence: '\/' [enabled by default]

这到底怎么回事呢？利用Python执行结果是OK的呀。代码如下：

#!/usr/bin/env python
#
import re
import sys
import os
#restr="(https?|ftp|mms):\/\/([A-z0-9]+[_\-]?[A-z0-9]+\.)*[A-z0-9]+\-?[A-z0-9]+\.[A-z]{2,}(\/.*)*\/?"
def geturl(url=''):
restr="(https?|ftp|mms):\/\/([A-z0-9]+[_\-]?[A-z0-9]?\.)*[A-z0-9]+\-?[A-z0-9]+\.[A-z]{2,}"
pattern = re.compile(restr)
match=re.search(pattern, url)
if match:
return match.group()
################# GetLine ############################
def dealUrl(fmtfile):
i=0
file = open(fmtfile,'r')
fo = open("tmp.txt",'w')
while 1:
line = file.readline()
if not line:
break
newline=geturl(line)
if(newline!=None):
print(i, newline)
fo.writelines(''.join([newline,'\n']))
i+=1
################# Main ##############################
if __name__=='__main__':
if(len(sys.argv)<2):
filename='url.info'
else:
filename=sys.argv[1]
dealUrl(filename)

查询后，发现有可能是在C语言中，如果使用正则表达式，那么转移字符需要使用双份的，也即："/"需要用“\\/”，对url_re做了调整后，再次测试发现编译告警消失，执行结果也是OK啦。

int filter(char* str,char* url)
{
pcre *re;
const char* error;
int erroffset;
int ovector[RE_OVERCOUNT];
int rc;
char* url_re="(https?|ftp|mms):\\/\\/([A-z0-9]+[_\\-]?[A-z0-9]?\\.)*[A-z0-9]+\\-?[A-z0-9]+\\.[A-z]{2,}";

if(str==NULL || url==NULL) return 0;
printf("str: %s\n", str);
re = pcre_compile(url_re, 0, &error, &erroffset, NULL);
if(re == NULL){
printf("PCRE pcre_compile failed at offset %d: %s\n", erroffset, error);
return 0;
}
char *p=str;
if((rc=pcre_exec(re,NULL,p,strlen(p),0,0,ovector,RE_OVERCOUNT))!=PCRE_ERROR_NOMATCH){
char* url_start = p + ovector[0];
int urllen = ovector[1] - ovector[0];
strncpy(url, url_start, urllen);
printf("urllen %d, url:%s\n", urllen, url);
return urllen;
}
pcre_free(re);
return 0;
}