C/C++正则表达式编程
来源：互联网 发布：十字绣绣花软件 编辑：程序博客网 时间：2024/04/29 08:04
正则表达式是一种描述性的语言, 用来概括一类字符串 (或者说一个字符串集合).
正则表达式30分钟入门教程
http://deerchao.net/tutorials/regex/regex.htm
GNU/Linux有两套库可用于正则表达式编程：POSIX库和PCRE库。前者不需要单独安装，一般需求还是能满足的，速度稍慢些。后者是久负盛名的Perl正则表达式库，功能强大，匹配速度快，不过可能需要单独安装。
POSIX库
如何使用POSIX库的例子：
#include <stdio.h>
#include <sys/types.h>
#include <regex.h>
char *get_regerror (int errcode, regex_t *compiled)
{
size_t length = regerror (errcode, compiled, NULL, 0);
char *buffer = malloc(length);
if (!buffer) return NULL;
(void) regerror (errcode, compiled, buffer, length);
return buffer;
}
int regtest(const char*pattern, const char* string)
{
regex_t reg;
regmatch_t *subexprs = NULL;
int ret;
int i;
if (0 != (ret=regcomp(?, pattern, REG_EXTENDED))) {
char *buffer = get_regerror(ret, ?);
if (buffer) {
fprintf(stderr, "regcomp:[%d]%s/n", ret, buffer);
free(buffer);
}
return -1;
}
subexprs = malloc((reg.re_nsub+1)*sizeof(regmatch_t));
if (!subexprs) {
fprintf(stderr, "error malloc subexprs/n");
regfree(?);
return -1;
}
if (0 != (ret=regexec(?, string, reg.re_nsub+1, subexprs, 0))) {
char *buffer = get_regerror(ret, ?);
if (buffer) {
fprintf(stderr, "regexec:[%d]%s/n", ret, buffer);
free(buffer);
}
regfree(?);
return -1;
}
for (i = 0; i <= reg.re_nsub; i++) {
printf("[%d]:", i);
if (subexprs[i].rm_so == subexprs[i].rm_eo) {
printf("[EMPTY SUBEXPR]/n");
}
else if (subexprs[i].rm_so == -1 ||
subexprs[i].rm_eo == -1) {
printf("[NO SUBEXPR]/n");
}
else {
fwrite(string+subexprs[i].rm_so, 1,
subexprs[i].rm_eo-subexprs[i].rm_so, stdout);
printf("/n");
}
}
regfree(?);
if (subexprs) free(subexprs);
return 0;
}
int main(int argc, char *argv[])
{
if (argc != 3) {
fprintf(stderr, "Usage: regtest pattern string/n");
return -1;
}
fprintf(stderr, "pattern:%s/n", argv[1]);
fprintf(stderr, "string:%s/n", argv[2]);
return regtest(argv[1], argv[2]);
}
在字符串匹配之前，必须先编译匹配模式，这是通过regcomp实现的。这个函数的原型如下：
int regcomp (regex_t *compiled, const char *pattern, int cflags)
参数compiled有一个成员需要关注：re_nsub，代表编译后的子表达式数目，由于需要保存整个匹配到的模式，所以最终匹配的条目数是re_nsub加1。cflags用来修饰匹配模式，可取值如下：
REG_EXTENDED 启用POSIX正则库扩展，关于该扩展的详细信息可参考POSIX规范
REG_ICASE 忽略大小写
REG_NOSUB 不要存储子表达式
REG_NEWLINE 把换行符作为多行的分隔符，这样'$'可匹配每一行的行尾，'^'匹配每一行的行首，'.'不匹配换行符，[^...]不匹配新行
编译完模式后从内存中分配子表达式存储空间，然后调用regexec对串进行匹配，该函数原型如下：
int regexec (regex_t *compiled, char *string, size_t nmatch, regmatch_t matchptr [], int eflags)
nmatch指明matchptr数组的数目，该数目是compiled->re_nsub+1，也可以让nmatch为0,matchptr为NULL，表示不要保存子表达式。eflags通常为0。
匹配结束后，匹配到的子表达式在串中的偏移保存在regmatch_t结构中，该结构有两个成员：
rm_so 子表达式的起始偏移
rm_eo 子表达式的结束偏移
这是一个开区间，实际的子表达式在[rm_so,rm_eo)里。
如果没有匹配的子表达式，比如"f(o*)"匹配"fum"，实际匹配到的只有"f"，这时rm_so和rm_eo相等，都为1。如果整个模式在没有子表示式的情况下也能匹配，这时rm_so和rm_eo为-1，比如"ba(na)*"匹配"ba"。
PCRE库
PCRE库的功能虽然强大，可是并不难使用。详细信息可参考http://www.pcre.org/里的文档，附录有一个例子，比较全面地阐述了如何调用该库。
PCRE的子表达式和POSIX类似，不过它还引入了一个命名子表达式的概念。比如模式"(?P(?P(/d/d)?/d/d)-(?P/d/d)-(?P/d/d))"，其中的date, year, month, day是对子表达式的命名。如何根据这些名称来获取子表达式，PCRE文档有详细的说明。
附录：pcredemo.c
/*************************************************
* PCRE DEMONSTRATION PROGRAM *
*************************************************/
/* This is a demonstration program to illustrate the most straightforward ways
of calling the PCRE regular expression library from a C program. See the
pcresample documentation for a short discussion.
Compile thuswise:
gcc -Wall pcredemo.c -I/usr/local/include -L/usr/local/lib /
-R/usr/local/lib -lpcre
Replace "/usr/local/include" and "/usr/local/lib" with wherever the include and
library files for PCRE are installed on your system. Only some operating
systems (e.g. Solaris) use the -R option.
*/
#include <stdio.h>
#include <string.h>
#include <pcre.h>
#define OVECCOUNT 30 /* should be a multiple of 3 */
int main(int argc, char **argv)
{
pcre *re;
const char *error;
char *pattern;
char *subject;
unsigned char *name_table;
int erroffset;
int find_all;
int namecount;
int name_entry_size;
int ovector[OVECCOUNT];
int subject_length;
int rc, i;
/**************************************************************************
* First, sort out the command line. There is only one possible option at *
* the moment, "-g" to request repeated matching to find all occurrences, *
* like Perl's /g option. We set the variable find_all to a non-zero value *
* if the -g option is present. Apart from that, there must be exactly two *
* arguments. *
**************************************************************************/
find_all = 0;
for (i = 1; i < argc; i++) {
if (strcmp(argv[i], "-g") == 0) find_all = 1;
else break;
}
/* After the options, we require exactly two arguments, which are the pattern,
and the subject string. */
if (argc - i != 2) {
printf("Two arguments required: a regex and a subject string/n");
return 1;
}
pattern = argv[i];
subject = argv[i+1];
subject_length = (int)strlen(subject);
/*************************************************************************
* Now we are going to compile the regular expression pattern, and handle *
* and errors that are detected. *
*************************************************************************/
re = pcre_compile(
pattern, /* the pattern */
0, /* default options */
&error, /* for error message */
&erroffset, /* for error offset */
NULL); /* use default character tables */
/* Compilation failed: print the error message and exit */
if (re == NULL) {
printf("PCRE compilation failed at offset %d: %s/n", erroffset, error);
return 1;
}
/*************************************************************************
* If the compilation succeeded, we call PCRE again, in order to do a *
* pattern match against the subject string. This does just ONE match. If *
* further matching is needed, it will be done below. *
*************************************************************************/
rc = pcre_exec(
re, /* the compiled pattern */
NULL, /* no extra data - we didn't study the pattern */
subject, /* the subject string */
subject_length, /* the length of the subject */
0, /* start at offset 0 in the subject */
0, /* default options */
ovector, /* output vector for substring information */
OVECCOUNT); /* number of elements in the output vector */
/* Matching failed: handle error cases */
if (rc < 0) {
switch(rc) {
case PCRE_ERROR_NOMATCH: printf("No match/n"); break;
/*
Handle other special cases if you like
*/
default: printf("Matching error %d/n", rc); break;
}
free(re); /* Release memory used for the compiled pattern */
return 1;
}
/* Match succeded */
printf("/nMatch succeeded at offset %d/n", ovector[0]);
/*************************************************************************
* We have found the first match within the subject string. If the output *
* vector wasn't big enough, set its size to the maximum. Then output any *
* substrings that were captured. *
*************************************************************************/
/* The output vector wasn't big enough */
if (rc == 0) {
rc = OVECCOUNT/3;
printf("ovector only has room for %d captured substrings/n", rc - 1);
}
/* Show substrings stored in the output vector by number. Obviously, in a real
application you might want to do things other than print them. */
for (i = 0; i < rc; i++) {
char *substring_start = subject + ovector[2*i];
int substring_length = ovector[2*i+1] - ovector[2*i];
printf("%2d: %.*s/n", i, substring_length, substring_start);
}
/**************************************************************************
* That concludes the basic part of this demonstration program. We have *
* compiled a pattern, and performed a single match. The code that follows *
* first shows how to access named substrings, and then how to code for *
* repeated matches on the same subject. *
**************************************************************************/
/* See if there are any named substrings, and if so, show them by name. First
we have to extract the count of named parentheses from the pattern. */
(void)pcre_fullinfo(
re, /* the compiled pattern */
NULL, /* no extra data - we didn't study the pattern */
PCRE_INFO_NAMECOUNT, /* number of named substrings */
&namecount); /* where to put the answer */
if (namecount <= 0) printf("No named substrings/n"); else
{
unsigned char *tabptr;
printf("Named substrings/n");
/* Before we can access the substrings, we must extract the table for
translating names to numbers, and the size of each entry in the table. */
(void)pcre_fullinfo(
re, /* the compiled pattern */
NULL, /* no extra data - we didn't study the pattern */
PCRE_INFO_NAMETABLE, /* address of the table */
&name_table); /* where to put the answer */
(void)pcre_fullinfo(
re, /* the compiled pattern */
NULL, /* no extra data - we didn't study the pattern */
PCRE_INFO_NAMEENTRYSIZE, /* size of each entry in the table */
&name_entry_size); /* where to put the answer */
/* Now we can scan the table and, for each entry, print the number, the name,
and the substring itself. */
tabptr = name_table;
for (i = 0; i < namecount; i++) {
int n = (tabptr[0] << 8) | tabptr[1];
printf("(%d) %*s: %.*s/n", n, name_entry_size - 3, tabptr + 2,
ovector[2*n+1] - ovector[2*n], subject + ovector[2*n]);
tabptr += name_entry_size;
}
}
/*************************************************************************
* If the "-g" option was given on the command line, we want to continue *
* to search for additional matches in the subject string, in a similar *
* way to the /g option in Perl. This turns out to be trickier than you *
* might think because of the possibility of matching an empty string. *
* What happens is as follows: *
* *
* If the previous match was NOT for an empty string, we can just start *
* the next match at the end of the previous one. *
* *
* If the previous match WAS for an empty string, we can't do that, as it *
* would lead to an infinite loop. Instead, a special call of pcre_exec() *
* is made with the PCRE_NOTEMPTY and PCRE_ANCHORED flags set. The first *
* of these tells PCRE that an empty string is not a valid match; other *
* possibilities must be tried. The second flag restricts PCRE to one *
* match attempt at the initial string position. If this match succeeds, *
* an alternative to the empty string match has been found, and we can *
* proceed round the loop. *
*************************************************************************/
if (!find_all) {
free(re); /* Release the memory used for the compiled pattern */
return 0; /* Finish unless -g was given */
}
/* Loop for second and subsequent matches */
for (;;) {
int options = 0; /* Normally no options */
int start_offset = ovector[1]; /* Start at end of previous match */
/* If the previous match was for an empty string, we are finished if we are
at the end of the subject. Otherwise, arrange to run another match at the
same point to see if a non-empty match can be found. */
if (ovector[0] == ovector[1]) {
if (ovector[0] == subject_length) break;
options = PCRE_NOTEMPTY | PCRE_ANCHORED;
}
/* Run the next matching operation */
rc = pcre_exec(
re, /* the compiled pattern */
NULL, /* no extra data - we didn't study the pattern */
subject, /* the subject string */
subject_length, /* the length of the subject */
start_offset, /* starting offset in the subject */
options, /* options */
ovector, /* output vector for substring information */
OVECCOUNT); /* number of elements in the output vector */
/* This time, a result of NOMATCH isn't an error. If the value in "options"
is zero, it just means we have found all possible matches, so the loop ends.
Otherwise, it means we have failed to find a non-empty-string match at a
point where there was a previous empty-string match. In this case, we do what
Perl does: advance the matching position by one, and continue. We do this by
setting the "end of previous match" offset, because that is picked up at the
top of the loop as the point at which to start again. */
if (rc == PCRE_ERROR_NOMATCH) {
if (options == 0) break;
ovector[1] = start_offset + 1;
continue; /* Go round the loop again */
}
/* Other matching errors are not recoverable. */
if (rc < 0) {
printf("Matching error %d/n", rc);
free(re); /* Release memory used for the compiled pattern */
return 1;
}
/* Match succeded */
printf("/nMatch succeeded again at offset %d/n", ovector[0]);
/* The match succeeded, but the output vector wasn't big enough. */
if (rc == 0) {
rc = OVECCOUNT/3;
printf("ovector only has room for %d captured substrings/n", rc - 1);
}
/* As before, show substrings stored in the output vector by number, and then
also any named substrings. */
for (i = 0; i < rc; i++) {
char *substring_start = subject + ovector[2*i];
int substring_length = ovector[2*i+1] - ovector[2*i];
printf("%2d: %.*s/n", i, substring_length, substring_start);
}
if (namecount <= 0) printf("No named substrings/n"); else
{
unsigned char *tabptr = name_table;
printf("Named substrings/n");
for (i = 0; i < namecount; i++)
{
int n = (tabptr[0] << 8) | tabptr[1];
printf("(%d) %*s: %.*s/n", n, name_entry_size - 3, tabptr + 2,
ovector[2*n+1] - ovector[2*n], subject + ovector[2*n]);
tabptr += name_entry_size;
}
}
} /* End of loop to find second and subsequent matches */
printf("/n");
free(re); /* Release memory used for the compiled pattern */
return 0;
}
/* End of pcredemo.c */
转自：http://www.cublog.cn/u1/33888/showart_341825.html
- C/C++正则表达式编程
- C/C++正则表达式编程
- C/C++正则表达式编程
- C/C++正则表达式编程
- 基于linux c编程的正则表达式
- 正则表达式(C#)
- 正则表达式之C＃
- C＃中的正则表达式
- 正则表达式(linux/C++)
- C的正则表达式
- c＃正则表达式
- linux c 正则表达式
- linux c 正则表达式
- linux C正则表达式
- linux c 正则表达式
- C语言正则表达式
- C语言正则表达式
- C语言正则表达式
- 二分图匹配算法总结(phoenixinter)
- 基于NRF24L01的AVR双机通信
- 最近学习java遇到的几个疑问
- linux date日期输出格式
- 一个小游戏的几个关键类（敌人的移动类型）
- C/C++正则表达式编程
- acc和gcc编译动态库的区别
- 先露一下
- pku3023 Antenna Placement
- kmp hdu1711
- 微软云计算从Visual Studio 2010开始辉煌
- 学习C和C++应该看的书
- WINDOWS游戏编程大师技巧-常见编绎连接错误FAQ
- 数据库批量备份存储过程
