c、c++字符串匹配

 

fnmatch(pattern, str, FNM_NOESCAPE)

 

头文件：https://github.com/gcc-mirror/gcc/blob/master/include/fnmatch.h

源文件：https://github.com/gcc-mirror/gcc/blob/master/libiberty/fnmatch.c

 

源码解析，转自：https://www.cnblogs.com/oloroso/p/6861576.html

/*
* Copyright (c) 1989, 1993, 1994
*    The Regents of the University of California.  All rights reserved.
*
* This code is derived from software contributed to Berkeley by
* Guido van Rossum.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
*    notice, this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
*    notice, this list of conditions and the following disclaimer in the
*    documentation and/or other materials provided with the distribution.
* 3. All advertising materials mentioning features or use of this software
*    must display the following acknowledgement:
*    This product includes software developed by the University of
*    California, Berkeley and its contributors.
* 4. Neither the name of the University nor the names of its contributors
*    may be used to endorse or promote products derived from this software
*    without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
* ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
* OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
* SUCH DAMAGE.
*
* From FreeBSD fnmatch.c 1.11
* $Id: fnmatch.c,v 1.3 1997/08/19 02:34:30 jdp Exp $
*/

#ifndef    _FNMATCH_H_
#define    _FNMATCH_H_

#define    FNM_NOMATCH    1    /* Match failed. */

#define    FNM_NOESCAPE    0x01    /* 禁用反斜杠进行转义 */
#define    FNM_PATHNAME    0x02    /* 斜杠只能被斜杠匹配(即不能被*或者?匹配) */
#define    FNM_PERIOD    0x04    /* Period must be matched by period. */
/*如果这个标志设置了，string 里的起始点号必须匹配 pattern 里的点号。
一个点号被认为是起始点号，如果它是string 第一个字符，或者如果同时设
置了 FNM_PATHNAME，紧跟在斜杠后面的点号。
*/
#define    FNM_LEADING_DIR    0x08    /* Ignore /<tail> after Imatch. */
/*如果这个标志(GNU 扩展)设置了，模式必须匹配跟随在斜杠之后的 string
的初始片断。这个标志主要是给 glibc 内部使用并且只在一定条件下实现。
即只匹配目录路径部分，不匹配到具体文件名
*/
#define    FNM_CASEFOLD    0x10    /* 模式匹配忽略大小写. */
#define FNM_PREFIX_DIRS    0x20    /* Directory prefixes of pattern match too. */

/* Make this compile successfully with "gcc -traditional" */
#ifndef __STDC__
#define const    /* empty */
#endif

int     fnmatch(const char *, const char *, int);

#endif /* !_FNMATCH_H_ */

#if defined(LIBC_SCCS) && !defined(lint)
static char sccsid[] = "@(#)fnmatch.c    8.2 (Berkeley) 4/16/94";
#endif /* LIBC_SCCS and not lint */

/*
* 函数fnmatch()，如POSIX 1003.2-1992 B.6节所述。
* 将文件名或者目录名与pattern进行比较
*/

#include <ctype.h>
#include <string.h>
#include <stdio.h>

// 定义字符串结尾标志
#define    EOS    '\0'

static const char *rangematch(const char *, char, int);

int
fnmatch(const char *pattern, const char *string, int flags)
{
    const char *stringstart;
    char c, test;

    for (stringstart = string;;){
        // 逐个取匹配字符串中的成分(分为*?和range三种)
        switch (c = *pattern++) {
        case EOS:   // 没有匹配串的情况
            // 如果忽略'/'后面的部分，则匹配成功
            if ((flags & FNM_LEADING_DIR) && *string == '/'){
                return (0);
            }
            // 如果string也是空串，则匹配成功
            return (*string == EOS ? 0 : FNM_NOMATCH);
        case '?':   // 匹配单个任意字符
            // string为空则不能匹配
            if (*string == EOS){
                return (FNM_NOMATCH);
            }
            // 判断'/'是否只能由'/'进行匹配
            if (*string == '/' && (flags & FNM_PATHNAME)){
                return (FNM_NOMATCH);
            }
            // 判断是否string中的起始'.'必须匹配pattern中的'.'（即'?'不能匹配'.'）
            if (*string == '.' && (flags & FNM_PERIOD) &&
                (string == stringstart ||
                ((flags & FNM_PATHNAME) && *(string - 1) == '/'))){
                return (FNM_NOMATCH);
            }
            // 匹配成功则匹配string的下一个字符
            ++string;
            break;
        case '*':   // 匹配单个或多个任意字符
            c = *pattern;
            /* 多个'*'当做一个 */
            while (c == '*'){
                c = *++pattern;
            }
            // 判断是否需要对'.'进行处理
            if (*string == '.' && (flags & FNM_PERIOD) &&
                (string == stringstart ||
                ((flags & FNM_PATHNAME) && *(string - 1) == '/'))){
                return (FNM_NOMATCH);
            }

            /* 优化 * 在匹配串结尾或者在 /. 之前的匹配*/
            if (c == EOS){  // 在结尾
                // 判断 * 是否不匹配斜杠
                if (flags & FNM_PATHNAME){
                    // 不匹配斜杠，则判断是否忽略'/'之后部分
                    return ((flags & FNM_LEADING_DIR) ||
                        ((strchr(string, '/') == NULL) ? 0 : FNM_NOMATCH));
                }else{
                    return (0);
                }
            }
            else if (c == '/' && flags & FNM_PATHNAME) { // 在 /. 之前
                // 如果string后没有 '/'则匹配失败
                if ((string = strchr(string, '/')) == NULL){
                    return (FNM_NOMATCH);
                }
                break;
            }

            /* 非特殊情况下，递归匹配 */
            while ((test = *string) != EOS) {
                // 不对'.'进行特殊处理，进行匹配（则只需判断'/'匹配情况）
                if (!fnmatch(pattern, string, flags & ~FNM_PERIOD)){
                    return (0); // 匹配成功
                }
                // 对 '/'进行处理（斜杠只匹配斜杠，则匹配失败）
                if (test == '/' && flags & FNM_PATHNAME){
                    break;
                }
                ++string;
            }
            // 返回匹配失败（即*没有匹配成功,'.'和'/'上的匹配没有成功）
            return (FNM_NOMATCH);
        case '[':   // range 范围匹配
            if (*string == EOS){
                return (FNM_NOMATCH);   // 空串匹配失败
            }
            if (*string == '/' && flags & FNM_PATHNAME){
                return (FNM_NOMATCH);   // '/'匹配失败
            }
            if ((pattern =
                rangematch(pattern, *string, flags)) == NULL){
                return (FNM_NOMATCH);   // 范围匹配失败
            }
            ++string;
            break;
        case '\\':  // 斜杠匹配（判断是否需要转义）
            if (!(flags & FNM_NOESCAPE)) {
                if ((c = *pattern++) == EOS) {
                    c = '\\';
                    --pattern;
                }
            }
            /* 非上述部分，则直接匹配单个字符 */
        default:
            if (c == *string){
                ;   // 直接匹配上了
            }else if ((flags & FNM_CASEFOLD) &&
                (tolower((unsigned char)c) ==
                    tolower((unsigned char)*string))){
                ;   // 忽略大小写匹配成功
            }
            else if ((flags & FNM_PREFIX_DIRS) && *string == EOS &&
                ((c == '/' && string != stringstart) ||
                (string == stringstart + 1 && *stringstart == '/'))){
                return (0); // 匹配成功
            }
            else{
                return (FNM_NOMATCH); // 匹配失败
            }
            string++;
            break;
        }
    }
    /* NOTREACHED */
}

// 字符范围匹配
// pattern传入如 [a-x]*** 形式的字符串
// 匹配失败或匹配到EOS结束(也是失败)，返回NULL
// 成功返回匹配串的下一个匹配成分首地址
static const char *
rangematch(const char *pattern, char test, int flags)
{
    // 此处没有对c进行初始化，可能出问题（栈上变量默认值未定）
    int negate, ok;
    char c, c2;

    /*
    * A bracket expression starting with an unquoted circumflex
    * character produces unspecified results
    * 以无引号 ^ 字符开始的方括号表达式，将产生未指定的结果
    * (IEEE 1003.2-1992,3.13.2).  此实现将其视为 '!',以与正则表达式语法保持一致.
    * J.T. Conklin (conklin@ngai.kaleida.com)
    */
    // 检测方括号表达式中第一个字符
    // 如果为!或者^，则对后面匹配的结果取反
    if ((negate = (*pattern == '!' || *pattern == '^'))){
        ++pattern;
    }

    // 忽略大小写，则转为小写处理
    if (flags & FNM_CASEFOLD){
        test = tolower((unsigned char)test);
    }
    // 循环到方括号表达式结束
    for (ok = 0; (c = *pattern++) != ']';) {
        // 如果没有禁用转义，获取字符
        if (c == '\\' && !(flags & FNM_NOESCAPE)){
            c = *pattern++;
        }
        // 匹配结束
        if (c == EOS){
            return (NULL);
        }
        // 忽略大小写，则转为小写
        if (flags & FNM_CASEFOLD){
            c = tolower((unsigned char)c);
        }
        // 如果当前匹配项c 的下一个是'-'，则获取'-'后面的一个字符
        // 例如，匹配串为 [a-x] 当前c为a,则c2为x，表示匹配a-x之间字符
        if (*pattern == '-'
            && (c2 = *(pattern + 1)) != EOS && c2 != ']') {
            pattern += 2;
            // 判断是否需要转义
            if (c2 == '\\' && !(flags & FNM_NOESCAPE)){
                c2 = *pattern++;
            }
            if (c2 == EOS){
                return (NULL);
            }
            // 判断是否区分大小写
            if (flags & FNM_CASEFOLD){
                c2 = tolower((unsigned char)c2);
            }
            // 判断test是否位于 [c,c2]区间
            if ((unsigned char)c <= (unsigned char)test &&
                (unsigned char)test <= (unsigned char)c2){
                ok = 1;
            }
        }
        else if (c == test){
            ok = 1;
        }
    }
    // 返回匹配结果
    return (ok == negate ? NULL : pattern);
}