\u6b63\u5219\u8868\u8fbe\u5f0f\u5728\u7f16\u7a0b\u4e2d\u7684\u5e94\u7528\u662f\u975e\u5e38\u5e7f\u6cdb\u7684\uff0c\u5728C\u8bed\u8a00\u4e2d\uff0c\u540c\u6837\u6709\u7740\u6b63\u5219\u8868\u8fbe\u5f0f\u7684\u5e93\uff0c\u6211\u4eec\u4f7f\u7528regex.h\u8fd9\u4e2a\u5934\u8bf4\u5305\u542b\u7684\u51fd\u6570\u6765\u5b8c\u6210\u6211\u4eec\u7684\u9700\u8981\uff1a
\n\u5148\u770b\u4e00\u6bb5\u4f8b\u5b50\uff1a<\/p>\n
#include <regex.h>\r\n#include <stdio.h>\r\n#include <string.h>\r\n#include <stdlib.h>\r\n\r\nchar *sub_string(char *str, int start, int end)\r\n{\r\nstatic char * st = NULL;\r\nint i = start, j = 0;\r\nst ? free(st) : 0;\r\nst = (char *)malloc(sizeof(char) * (end - start + 1));\r\nwhile(i < end){\r\nst[j++] = str[i++];\r\n}\r\nst[j] = '\\0';\r\nreturn st;\r\n}\r\n\r\nint main()\r\n{\r\nregmatch_t pm[4];\r\nregex_t preg;\r\nchar *pattern = \"(href\\\\ *=\\\\ *\\\\\\\")([^\\\\\\\"]*)(\\\\\\\")\"; \/\/\u5339\u914d\u4e32\r\nchar *file = \"<a href=\\\"http:\/\/www.awaysoft.com\\\">Awaysoft.com<\/a><a href=\\\"http:\/\/www.awaysoft2.com\\\">Awaysoft2.com<\/a><a href=\\\"http:\/\/www.awaysoft3.com\\\">Awaysoft.com3<\/a>\", *st; \/\/\u88ab\u5339\u914d\u4e32\r\n\r\nif (regcomp(&preg, pattern, REG_EXTENDED |REG_NEWLINE) != 0){ \/\/\u7f16\u8bd1\u6b63\u5219\u8868\u8fbe\u5f0f\r\nfprintf(stderr, \"Cannot regex compile!\");\r\nreturn -1;\r\n}\r\nst = file;\r\n\r\nwhile (st && regexec(&preg, st, 4, pm, REG_NOTEOL) != REG_NOMATCH){ \/\/\u5f00\u59cb\u5339\u914d\r\nprintf(\"%s\\n\",sub_string(st, pm[2].rm_so, pm[2].rm_eo));\r\nst = &st[pm[3].rm_eo];\/\/\u8f6c\u5230\u4e0b\u4e00\u4e2a\u5339\u914d\u7684\u521d\u59cb\u4f4d\u7f6e\r\n}\r\nreturn 0;\r\n}<\/pre>\n\u8fd9\u6bb5\u7a0b\u5e8f\u7684\u8fd0\u884c\u7ed3\u679c\u662f\uff1a<\/p>\n
http:\/\/www.awaysoft.com\r\nhttp:\/\/www.awaysoft2.com\r\nhttp:\/\/www.awaysoft3.com<\/pre>\n\u8981\u6ce8\u610f\u7684\u662fregexec\u4ec5\u4ec5\u80fd\u8fdb\u884c\u4e00\u6b21\u5339\u914d<\/strong>\uff0c\u8981\u591a\u6b21\u5339\u914d\u9700\u8981\u7528\u5faa\u73af\uff01
\n\u6240\u4ee5\uff0c\u6211\u7528\u4e86\u4e00\u4e2awhile\u8bed\u53e5\uff0cpm\u8fd9\u4e2a\u6570\u7ec4\u8868\u793a\u7684\u662f\u5206\u7ec4\u6570\u76ee\uff0c\u4e0d\u662f\u5339\u914d\u4e2a\u6570\u3002\u770b\u5230\u6b63\u5219\u8868\u8fbe\u5f0f\u4e2d\uff0c\u67093\u7ec4()\uff0c\u90a3\u4e48\u5c31\u4ee3\u8868\u67093+1\u4e2a\u5206\u7ec4\uff0c+1\u662f\u6307\u88ab\u5339\u914d\u7684\u5168\u90e8\u5b57\u7b26\u4e32\u3002\u7528\u4e0a\u9762\u7ed9\u7684\u4f8b\u5b50\uff0c\u90a3\u4e48pm\u5c31\u662f4,\u5176\u4e2dpm[0] == “href=\\”http:\/\/www.awaysoft.com\\””,pm[1] == “href=\\””,pm[2] == “http:\/\/www.awaysoft.com”, pm[3] = “\\””;
\nst = &st[pm[3].rm_eo];\u8fd9\u53e5\u662f\u5c06\u6307\u9488\u79fb\u52a8\u5230\u4e0b\u4e00\u6b21\u5339\u914d\u5f00\u59cb\u7684\u5b57\u7b26\u3002<\/p>\n\u9644\uff1a
\n\u6b63\u5219\u8868\u8fbe\u5f0f\u5feb\u901f\u5165\u95e8<\/a><\/p>\n\u4e0b\u9762\uff0c\u8f6c\u4e86\u4e00\u7bc7regex\u7684\u8be6\u7ec6\u7528\u6cd5\uff1a
\n \u7f16\u8bd1\u6b63\u5219\u8868\u8fbe\u5f0f<\/p>\n
\u4e3a\u4e86\u63d0\u9ad8\u6548\u7387\uff0c\u5728\u5c06\u4e00\u4e2a\u5b57\u7b26\u4e32\u548c\u6b63\u5219\u8868\u8fbe\u5f0f\u8fdb\u884c\u6bd4\u8f83\u4e4b\u524d\uff0c\u9996\u5148\u8981\u7528regcomp()\u51fd\u6570\u5bf9\u4ed6\u8fdb\u884c\u7f16\u8bd1\uff0c\u5c06\u5176\u8f6c\u5316\u4e3aregex_t\u7ed3\u6784\uff1a<\/p>\n
int regcomp(regex_t *preg, const char *regex, int cflags);<\/p>\n
\u53c2\u6570regex\u662f\u4e2a\u5b57\u7b26\u4e32\uff0c\u4ed6\u4ee3\u8868\u5c06\u8981\u88ab\u7f16\u8bd1\u7684\u6b63\u5219\u8868\u8fbe\u5f0f\uff1b\u53c2\u6570preg\u6307\u5411\u4e00\u4e2a\u58f0\u660e\u4e3aregex_t\u7684\u6570\u636e\u7ed3\u6784\uff0c\u7528\u6765\u4fdd\u5b58\u7f16\u8bd1\u7ed3\u679c\uff1b\u53c2\u6570cflags\u51b3\u5b9a\u4e86\u6b63\u5219\u8868\u8fbe\u5f0f\u8be5\u600e\u4e48\u88ab\u5904\u7406\u7684\u7ec6\u8282\u3002<\/p>\n
\u5982\u679c\u51fd\u6570regcomp()\u6267\u884c\u6210\u529f\uff0c\u5e76\u4e14\u7f16\u8bd1\u7ed3\u679c\u88ab\u6b63\u786e\u586b\u5145\u5230preg\u4e2d\u540e\uff0c\u51fd\u6570\u5c06\u8fd4\u56de0\uff0c\u6240\u6709\u5176\u4ed6\u7684\u8fd4\u56de\u7ed3\u679c\u90fd\u4ee3\u8868\u6709\u67d0\u79cd\u9519\u8bef\u4ea7\u751f\u3002<\/p>\n
\u5339\u914d\u6b63\u5219\u8868\u8fbe\u5f0f<\/p>\n
\u4e00\u65e6\u7528regcomp()\u51fd\u6570\u6210\u529f\u5730\u7f16\u8bd1\u4e86\u6b63\u5219\u8868\u8fbe\u5f0f\uff0c\u63a5\u4e0b\u6765\u5c31\u80fd\u8c03\u7528regexec()\u51fd\u6570\u5b8c\u6210\u6a21\u5f0f\u5339\u914d\uff1a<\/p>\n
int regexec(const regex_t *preg, const char *string, size_t nmatch,regmatch_t pmatch[], int eflags);\r\ntypedef struct {\r\nregoff_t rm_so;\r\nregoff_t rm_eo;\r\n} regmatch_t;<\/pre>\n <\/p>\n
\u53c2\u6570preg\u6307\u5411\u7f16\u8bd1\u540e\u7684\u6b63\u5219\u8868\u8fbe\u5f0f\uff0c\u53c2\u6570string\u662f\u5c06\u8981\u8fdb\u884c\u5339\u914d\u7684\u5b57\u7b26\u4e32\uff0c\u800c\u53c2\u6570nmatch\u548cpmatch\u5219\u7528\u4e8e\u628a\u5339\u914d\u7ed3\u679c\u8fd4\u56de\u7ed9\u8c03\u7528\u7a0b\u5f0f\uff0c\u6700\u540e\u4e00\u4e2a\u53c2\u6570eflags\u51b3\u5b9a\u4e86\u5339\u914d\u7684\u7ec6\u8282\u3002<\/p>\n
\u5728\u8c03\u7528\u51fd\u6570regexec()\u8fdb\u884c\u6a21\u5f0f\u5339\u914d\u7684\u8fc7\u7a0b\u4e2d\uff0c\u53ef\u80fd\u5728\u5b57\u7b26\u4e32string\u4e2d\u4f1a\u6709\u591a\u5904\u548c\u7ed9\u5b9a\u7684\u6b63\u5219\u8868\u8fbe\u5f0f\u76f8\u5339\u914d\uff0c\u53c2\u6570pmatch\u5c31\u662f\u7528\u6765\u4fdd\u5b58\u8fd9\u4e9b\u5339\u914d\u4f4d\u7f6e\u7684\uff0c\u800c\u53c2\u6570nmatch\u5219\u544a\u8bc9\u51fd\u6570regexec()\u6700\u591a\u80fd\u628a\u591a\u5c11\u4e2a\u5339\u914d\u7ed3\u679c\u586b\u5145\u5230pmatch\u6570\u7ec4\u4e2d\u3002\u5f53regexec()\u51fd\u6570\u6210\u529f\u8fd4\u56de\u65f6\uff0c\u4ecestring+pmatch[0].rm_so\u5230string+pmatch[0].rm_eo\u662f\u7b2c\u4e00\u4e2a\u5339\u914d\u7684\u5b57\u7b26\u4e32\uff0c\u800c\u4ecestring+pmatch[1].rm_so\u5230string+pmatch[1].rm_eo\uff0c\u5219\u662f\u7b2c\u4e8c\u4e2a\u5339\u914d\u7684\u5b57\u7b26\u4e32\uff0c\u4f9d\u6b64\u7c7b\u63a8\u3002<\/p>\n
\u91ca\u653e\u6b63\u5219\u8868\u8fbe\u5f0f<\/p>\n
\u65e0\u8bba\u4ec0\u4e48\u65f6\u5019\uff0c\u5f53\u4e0d\u518d\u9700\u8981\u5df2\u7f16\u8bd1\u8fc7\u7684\u6b63\u5219\u8868\u8fbe\u5f0f\u65f6\uff0c\u90fd\u5e94\u8be5\u8c03\u7528\u51fd\u6570regfree()\u5c06\u5176\u91ca\u653e\uff0c\u4ee5\u514d\u4ea7\u751f\u5185\u5b58\u6cc4\u6f0f\u3002<\/p>\n
void regfree(regex_t *preg);<\/p>\n
\u51fd\u6570regfree()\u4e0d\u4f1a\u8fd4\u56de\u6240\u6709\u7ed3\u679c\uff0c\u4ed6\u4ec5\u63a5\u6536\u4e00\u4e2a\u6307\u5411regex_t\u6570\u636e\u7c7b\u578b\u7684\u6307\u9488\uff0c\u8fd9\u662f\u4e4b\u524d\u8c03\u7528regcomp()\u51fd\u6570\u6240\u5f97\u5230\u7684\u7f16\u8bd1\u7ed3\u679c\u3002<\/p>\n
\u5982\u679c\u5728\u7a0b\u5f0f\u4e2d\u9488\u5bf9\u540c\u4e00\u4e2aregex_t\u7ed3\u6784\u8c03\u7528\u4e86\u591a\u6b21regcomp()\u51fd\u6570\uff0cPOSIX\u6807\u51c6\u5e76\u6ca1\u6709\u89c4\u5b9a\u662f\u5426\u6bcf\u6b21\u90fd\u5fc5\u987b\u8c03\u7528regfree()\u51fd\u6570\u8fdb\u884c\u91ca\u653e\uff0c\u4f46\u5efa\u8bae\u6bcf\u6b21\u8c03\u7528regcomp()\u51fd\u6570\u5bf9\u6b63\u5219\u8868\u8fbe\u5f0f\u8fdb\u884c\u7f16\u8bd1\u540e\u90fd\u8c03\u7528\u4e00\u6b21regfree()\u51fd\u6570\uff0c\u4ee5\u5c3d\u65e9\u91ca\u653e\u5360\u7528\u7684\u5b58\u50a8\u7a7a\u95f4\u3002<\/p>\n
\u62a5\u544a\u9519\u8bef\u4fe1\u606f<\/p>\n
\u5982\u679c\u8c03\u7528\u51fd\u6570regcomp()\u6216regexec()\u5f97\u5230\u7684\u662f\u4e2a\u975e0\u7684\u8fd4\u56de\u503c\uff0c\u5219\u8868\u660e\u5728\u5bf9\u6b63\u5219\u8868\u8fbe\u5f0f\u7684\u5904\u7406\u8fc7\u7a0b\u4e2d\u51fa\u73b0\u4e86\u67d0\u79cd\u9519\u8bef\uff0c\u6b64\u65f6\u80fd\u901a\u8fc7\u8c03\u7528\u51fd\u6570regerror()\u5f97\u5230\u5468\u8be6\u7684\u9519\u8bef\u4fe1\u606f\u3002<\/p>\n
size_t regerror(int errcode, const regex_t *preg, char *errbuf, size_t errbuf_size);<\/p>\n
\u53c2\u6570errcode\u662f\u6765\u81ea\u51fd\u6570regcomp()\u6216regexec()\u7684\u9519\u8bef\u4ee3\u7801\uff0c\u800c\u53c2\u6570preg\u5219\u662f\u7531\u51fd\u6570regcomp()\u5f97\u5230\u7684\u7f16\u8bd1\u7ed3\u679c\uff0c\u5176\u76ee\u7684\u662f\u628a\u683c\u5f0f\u5316\u6d88\u606f\u6240\u5fc5\u987b\u7684\u4e0a\u4e0b\u6587\u63d0\u4f9b\u7ed9regerror()\u51fd\u6570\u3002\u5728\u6267\u884c\u51fd\u6570regerror()\u65f6\uff0c\u5c06\u6309\u7167\u53c2\u6570errbuf_size\u6307\u660e\u7684\u6700\u5927\u5b57\u8282\u6570\uff0c\u5728errbuf\u7f13\u51b2\u533a\u4e2d\u586b\u5165\u683c\u5f0f\u5316\u540e\u7684\u9519\u8bef\u4fe1\u606f\uff0c\u540c\u65f6\u8fd4\u56de\u9519\u8bef\u4fe1\u606f\u7684\u957f\u5ea6\u3002<\/p>\n
\u5e94\u7528\u6b63\u5219\u8868\u8fbe\u5f0f<\/p>\n
\u6700\u540e\u7ed9\u51fa\u4e00\u4e2a\u5177\u4f53\u7684\u5b9e\u4f8b\uff0c\u4ecb\u7ecd\u600e\u4e48\u5728C\u8bed\u8a00\u7a0b\u5f0f\u4e2d\u5904\u7406\u6b63\u5219\u8868\u8fbe\u5f0f\u3002<\/p>\n
#include <regex.h>\r\n#include <stdio.h>\r\n#include <string.h>\r\n#include <stdlib.h><\/pre>\n\/* \u53d6\u5b50\u4e32\u7684\u51fd\u6570 *\/\r\nstatic char* substr(const char*str, unsigned start, unsigned end)\r\n{\r\nunsigned n = end - start;\r\nstatic char stbuf[256];\r\nstrncpy(stbuf, str + start, n);\r\nstbuf[n] = 0;\r\nreturn stbuf;\r\n}\r\n\/* \u4e3b\u7a0b\u5f0f *\/\r\nint main(int argc, char** argv)\r\n{\r\nchar * pattern;\r\nint x, z, lno = 0, cflags = 0;\r\nchar ebuf[128], lbuf[256];\r\nregex_t reg;\r\nregmatch_t pm[10];\r\nconst size_t nmatch = 10;\r\n\/* \u7f16\u8bd1\u6b63\u5219\u8868\u8fbe\u5f0f*\/\r\npattern = argv[1];\r\nz = regcomp(\u00ae, pattern, cflags);\r\nif (z != 0){\r\nregerror(z, \u00ae, ebuf, sizeof(ebuf));\r\nfprintf(stderr, \"%s: pattern \u2019%s\u2019 \uff3cn\", ebuf, pattern);\r\nreturn 1;\r\n}\r\n\/* \u9010\u884c\u5904\u7406\u8f93\u5165\u7684\u6570\u636e *\/\r\nwhile(fgets(lbuf, sizeof(lbuf), stdin)) {\r\n++lno;\r\nif ((z = strlen(lbuf)) > 0 && lbuf[z-1] == \u2019\uff3cn\u2019)\r\nlbuf[z - 1] = 0;\r\n\/* \u5bf9\u6bcf\u4e00\u884c\u5e94\u7528\u6b63\u5219\u8868\u8fbe\u5f0f\u8fdb\u884c\u5339\u914d *\/\r\nz = regexec(\u00ae, lbuf, nmatch, pm, 0);\r\nif (z == REG_NOMATCH) continue;\r\nelse if (z != 0) {\r\nregerror(z, \u00ae, ebuf, sizeof(ebuf));\r\nfprintf(stderr, \"%s: regcom(\u2019%s\u2019)\uff3cn\", ebuf, lbuf);\r\nreturn 2;\r\n}\r\n\/* \u8f93\u51fa\u5904\u7406\u7ed3\u679c *\/\r\nfor (x = 0; x < nmatch && pm[x].rm_so != -1; ++ x) {\r\nif (!x) printf(\"%04d: %s\uff3cn\", lno, lbuf);\r\nprintf(\" $%d=\u2019%s\u2019\uff3cn\", x, substr(lbuf, pm[x].rm_so, pm[x].rm_eo));\r\n}\r\n}\r\n\/* \u91ca\u653e\u6b63\u5219\u8868\u8fbe\u5f0f *\/\r\nregfree(\u00ae);\r\nreturn 0;\r\n}<\/pre>\n <\/p>\n
\u4e0a\u8ff0\u7a0b\u5f0f\u8d1f\u8d23\u4ece\u547d\u4ee4\u884c\u83b7\u53d6\u6b63\u5219\u8868\u8fbe\u5f0f\uff0c\u7136\u540e\u5c06\u5176\u8fd0\u7528\u4e8e\u4ece\u6807\u51c6\u8f93\u5165\u5f97\u5230\u7684\u6bcf\u884c\u6570\u636e\uff0c\u5e76\u6253\u5370\u51fa\u5339\u914d\u7ed3\u679c\u3002\u6267\u884c\u4e0b\u9762\u7684\u547d\u4ee4\u80fd\u7f16\u8bd1\u5e76\u6267\u884c\u8be5\u7a0b\u5f0f\uff1a<\/p>\n
# gcc regexp.c -o regexp\r\n# .\/regexp \u2019regex[a-z]*\u2019 < regexp.c\r\n0003: #include\r\n=\u2019regex\u2019\r\n0027: regex_t reg;\r\n=\u2019regex\u2019\r\n0054: z = regexec(\u00ae, lbuf, nmatch, pm, 0);\r\n=\u2019regexec\u2019<\/pre>\n <\/p>\n
\u5c0f\u7ed3<\/p>\n
\u5bf9\u90a3\u4e9b\u9700\u8981\u8fdb\u884c\u590d\u6742\u6570\u636e\u5904\u7406\u7684\u7a0b\u5f0f\u6765\u8bf4\uff0c\u6b63\u5219\u8868\u8fbe\u5f0f\u65e0\u7591\u662f\u4e2a\u975e\u5e38\u6709\u7528\u7684\u5de5\u5177\u3002\u672c\u6587\u91cd\u70b9\u5728\u4e8e\u9610\u8ff0\u600e\u4e48\u5728C\u8bed\u8a00\u4e2d\u5229\u7528\u6b63\u5219\u8868\u8fbe\u5f0f\u6765\u7b80\u5316\u5b57\u7b26\u4e32\u5904\u7406\uff0c\u4ee5\u4fbf\u5728\u6570\u636e\u5904\u7406\u65b9\u9762\u80fd\u591f\u83b7\u5f97\u548cPerl\u8bed\u8a00\u7c7b\u4f3c\u7684\u7075\u6d3b\u6027\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"
\u6b63\u5219\u8868\u8fbe\u5f0f\u5728\u7f16\u7a0b\u4e2d\u7684\u5e94\u7528\u662f\u975e\u5e38\u5e7f\u6cdb\u7684\uff0c\u5728C\u8bed\u8a00\u4e2d\uff0c\u540c\u6837\u6709\u7740\u6b63\u5219\u8868\u8fbe\u5f0f\u7684\u5e93\uff0c\u6211\u4eec\u4f7f … Read More »<\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[4],"tags":[],"_links":{"self":[{"href":"https:\/\/actom.me\/blog\/wp-json\/wp\/v2\/posts\/639"}],"collection":[{"href":"https:\/\/actom.me\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/actom.me\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/actom.me\/blog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/actom.me\/blog\/wp-json\/wp\/v2\/comments?post=639"}],"version-history":[{"count":5,"href":"https:\/\/actom.me\/blog\/wp-json\/wp\/v2\/posts\/639\/revisions"}],"predecessor-version":[{"id":918,"href":"https:\/\/actom.me\/blog\/wp-json\/wp\/v2\/posts\/639\/revisions\/918"}],"wp:attachment":[{"href":"https:\/\/actom.me\/blog\/wp-json\/wp\/v2\/media?parent=639"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/actom.me\/blog\/wp-json\/wp\/v2\/categories?post=639"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/actom.me\/blog\/wp-json\/wp\/v2\/tags?post=639"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}