C中的正则表达式:例子?

时间:2009-07-05 23:38:04

标签: c regex

我正在学习如何在ANSI C中使用正则表达式的一些简单示例和最佳实践。man regex.h没有提供太多帮助。

4 个答案:

答案 0 :(得分:210)

正则表达式实际上不是ANSI C的一部分。听起来你可能在谈论POSIX正则表达式库,它带有大多数(全部?)* nixes。以下是在C中使用POSIX正则表达式的示例(基于this):

#include <regex.h>        
regex_t regex;
int reti;
char msgbuf[100];

/* Compile regular expression */
reti = regcomp(&regex, "^a[[:alnum:]]", 0);
if (reti) {
    fprintf(stderr, "Could not compile regex\n");
    exit(1);
}

/* Execute regular expression */
reti = regexec(&regex, "abc", 0, NULL, 0);
if (!reti) {
    puts("Match");
}
else if (reti == REG_NOMATCH) {
    puts("No match");
}
else {
    regerror(reti, &regex, msgbuf, sizeof(msgbuf));
    fprintf(stderr, "Regex match failed: %s\n", msgbuf);
    exit(1);
}

/* Free memory allocated to the pattern buffer by regcomp() */
regfree(&regex);

或者,您可能需要查看PCRE,这是C语言中与Perl兼容的正则表达式的库.Perl语法几乎与Java,Python和许多其他语言中使用的语法相同。 POSIX语法是grepsedvi等使用的语法。

答案 1 :(得分:11)

这可能不是你想要的,但像re2c这样的工具可以将POSIX(-ish)正则表达式编译成ANSI C.它是作为lex的替代编写的,但这种方法允许你如果你真的需要,可以牺牲最后一点速度的灵活性和易读性。

答案 2 :(得分:3)

虽然上面的答案很好,但我建议使用 PCRE2 。这意味着您现在可以逐字地使用所有正则表达式示例,而不必从一些古老的正则表达式转换。

我已经为此做了一个答案,但我认为它也可以帮助你。

Regex In C To Search For Credit Card Numbers

// YOU MUST SPECIFY THE UNIT WIDTH BEFORE THE INCLUDE OF THE pcre.h

#define PCRE2_CODE_UNIT_WIDTH 8
#include <stdio.h>
#include <string.h>
#include <pcre2.h>
#include <stdbool.h>

int main(){

bool Debug = true;
bool Found = false;
pcre2_code *re;
PCRE2_SPTR pattern;
PCRE2_SPTR subject;
int errornumber;
int i;
int rc;
PCRE2_SIZE erroroffset;
PCRE2_SIZE *ovector;
size_t subject_length;
pcre2_match_data *match_data;


char * RegexStr = "(?:\\D|^)(5[1-5][0-9]{2}(?:\\ |\\-|)[0-9]{4}(?:\\ |\\-|)[0-9]{4}(?:\\ |\\-|)[0-9]{4})(?:\\D|$)";
char * source = "5111 2222 3333 4444";

pattern = (PCRE2_SPTR)RegexStr;// <<<<< This is where you pass your REGEX 
subject = (PCRE2_SPTR)source;// <<<<< This is where you pass your bufer that will be checked. 
subject_length = strlen((char *)subject);




  re = pcre2_compile(
  pattern,               /* the pattern */
  PCRE2_ZERO_TERMINATED, /* indicates pattern is zero-terminated */
  0,                     /* default options */
  &errornumber,          /* for error number */
  &erroroffset,          /* for error offset */
  NULL);                 /* use default compile context */

/* Compilation failed: print the error message and exit. */
if (re == NULL)
  {
  PCRE2_UCHAR buffer[256];
  pcre2_get_error_message(errornumber, buffer, sizeof(buffer));
  printf("PCRE2 compilation failed at offset %d: %s\n", (int)erroroffset,buffer);
  return 1;
  }


match_data = pcre2_match_data_create_from_pattern(re, NULL);

rc = pcre2_match(
  re,
  subject,              /* the subject string */
  subject_length,       /* the length of the subject */
  0,                    /* start at offset 0 in the subject */
  0,                    /* default options */
  match_data,           /* block for storing the result */
  NULL);

if (rc < 0)
  {
  switch(rc)
    {
    case PCRE2_ERROR_NOMATCH: //printf("No match\n"); //
    pcre2_match_data_free(match_data);
    pcre2_code_free(re);
    Found = 0;
    return Found;
    //  break;
    /*
    Handle other special cases if you like
    */
    default: printf("Matching error %d\n", rc); //break;
    }
  pcre2_match_data_free(match_data);   /* Release memory used for the match */
  pcre2_code_free(re);
  Found = 0;                /* data and the compiled pattern. */
  return Found;
  }


if (Debug){
ovector = pcre2_get_ovector_pointer(match_data);
printf("Match succeeded at offset %d\n", (int)ovector[0]);

if (rc == 0)
  printf("ovector was not big enough for all the captured substrings\n");


if (ovector[0] > ovector[1])
  {
  printf("\\K was used in an assertion to set the match start after its end.\n"
    "From end to start the match was: %.*s\n", (int)(ovector[0] - ovector[1]),
      (char *)(subject + ovector[1]));
  printf("Run abandoned\n");
  pcre2_match_data_free(match_data);
  pcre2_code_free(re);
  return 0;
}

for (i = 0; i < rc; i++)
  {
  PCRE2_SPTR substring_start = subject + ovector[2*i];
  size_t substring_length = ovector[2*i+1] - ovector[2*i];
  printf("%2d: %.*s\n", i, (int)substring_length, (char *)substring_start);
  }
}

else{
  if(rc > 0){
    Found = true;

    } 
} 
pcre2_match_data_free(match_data);
pcre2_code_free(re);
return Found;

}

使用以下方式安装PCRE:

wget https://ftp.pcre.org/pub/pcre/pcre2-10.31.zip
make 
sudo make install 
sudo ldconfig

使用编译:

gcc foo.c -lpcre2-8 -o foo

查看我的答案以了解更多详情。

答案 3 :(得分:1)

这是使用REG_EXTENDED的示例。 这个正则表达式

"^(-)?([0-9]+)((,|.)([0-9]+))?\n$"

允许您捕获西班牙语系统和国际中的小数。 :)

#include <regex.h>
#include <stdlib.h>
#include <stdio.h>
regex_t regex;
int reti;
char msgbuf[100];

int main(int argc, char const *argv[])
{
    while(1){
        fgets( msgbuf, 100, stdin );
        reti = regcomp(&regex, "^(-)?([0-9]+)((,|.)([0-9]+))?\n$", REG_EXTENDED);
        if (reti) {
            fprintf(stderr, "Could not compile regex\n");
            exit(1);
        }

        /* Execute regular expression */
        printf("%s\n", msgbuf);
        reti = regexec(&regex, msgbuf, 0, NULL, 0);
        if (!reti) {
            puts("Match");
        }
        else if (reti == REG_NOMATCH) {
            puts("No match");
        }
        else {
            regerror(reti, &regex, msgbuf, sizeof(msgbuf));
            fprintf(stderr, "Regex match failed: %s\n", msgbuf);
            exit(1);
        }

        /* Free memory allocated to the pattern buffer by regcomp() */
        regfree(&regex);
    }

}
相关问题