C言語でも正規表現がしたい

#今回の目的

• 基本的な使い方を知りたい

#先人の知恵

• Cでの正規表現
• C言語で正規表現を使うには？思ったより簡単だった！
• 【C言語入門】文字列内の検索方法まとめ(文字指定、正規表現)
• 正規表現したい！
• man 3 regex
• man 7 regex
• Programming with Regex
• printfの書式の * ってなんだ？

#サンプル

regex_sample.c

#include <stdio.h>
#include <malloc.h>
#include <regex.h>

int main(void)
{
	char string[] = "abc, def, ghi";
	const char regex[] = "([a-z]+), ([a-z]+), ([a-z]+)";

	regex_t ptn_buf;
	regmatch_t *match_buf;
	size_t size;
	int si, ei;
	size_t i;

	/* compile */
	if (regcomp(&ptn_buf, regex, REG_EXTENDED | REG_NEWLINE) != 0) {
		printf("regex compile failed\n");
		return 1;
	}

	/* allocate match buffer */
	size = ptn_buf.re_nsub + 1;
	match_buf = malloc(sizeof(regmatch_t) * size);
	if (match_buf == NULL) {
		printf("no memory\n");
		goto err_ptn;
	}

	/* match */
	if (regexec(&ptn_buf, string, size, match_buf, 0) != 0) {
		printf("no match\n");
		goto err_match;
	}

	/* print result */
	for (i=0; i<size; i++) {
		si = match_buf[i].rm_so;
		ei = match_buf[i].rm_eo;
		if (si == -1 || ei == -1) {
			continue;
		}
		printf("%.*s\n", ei-si, &string[si]);
	}

	/* free resource */
err_match:
	free(match_buf);
err_ptn:
	regfree(&ptn_buf);

	return 0;
}

コンパイル.log

$ gcc --version
gcc (Ubuntu 7.4.0-1ubuntu1~18.04.1) 7.4.0
Copyright (C) 2017 Free Software Foundation, Inc.
This is free software; see the source for copying conditions.  There is NO
warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.

$ gcc -Wall -Wextra regexp_sample.c

実行結果.log

$ ./a.out
abc, def, ghi
abc
def
ghi

#正規表現コードの要素

ヘッダファイルのインクルード.c

#include <regex.h>

正規表現のコンパイル.c

regex_t ptn_buf;
const char regex[] = "([a-z]+), ([a-z]+), ([a-z]+)";

if (regcomp(&ptn_buf, regex, REG_EXTENDED | REG_NEWLINE) != 0) {
    printf("regex compile failed\n");
    return;
}

マッチデータ格納バッファの確保.c

size_t size;
regmatch_t *match_buf;

size = ptn_buf.re_nsub + 1;

match_buf = malloc(sizeof(regmatch_t) * size);
if (match_buf == NULL) {
    printf("malloc failed\n");
    return;
}

パターンマッチ実行.c

char string[] = "abc, def, ghi";

if (regexec( &ptn_buf, string, size, match_buf, 0 ) != 0) {
    printf("no match\n");
    return;
}

開放.c

regfree(&ptn_buf);
free(match_buf);

/usr/include/regex.h

struct re_pattern_buffer
{
  /* Space that holds the compiled pattern.  It is declared as
     `unsigned char *' because its elements are sometimes used as
     array indexes.  */
  unsigned char *__REPB_PREFIX(buffer);

  /* Number of bytes to which `buffer' points.  */
  unsigned long int __REPB_PREFIX(allocated);

  /* Number of bytes actually used in `buffer'.  */
  unsigned long int __REPB_PREFIX(used);

  /* Syntax setting with which the pattern was compiled.  */
  reg_syntax_t __REPB_PREFIX(syntax);

  /* Pointer to a fastmap, if any, otherwise zero.  re_search uses the
     fastmap, if there is one, to skip over impossible starting points
     for matches.  */
  char *__REPB_PREFIX(fastmap);

  /* Either a translate table to apply to all characters before
     comparing them, or zero for no translation.  The translation is
     applied to a pattern when it is compiled and to a string when it
     is matched.  */
  __RE_TRANSLATE_TYPE __REPB_PREFIX(translate);

  /* Number of subexpressions found by the compiler.  */
  size_t re_nsub;

  /* Zero if this pattern cannot match the empty string, one else.
     Well, in truth it's used only in `re_search_2', to see whether or
     not we should use the fastmap, so we don't set this absolutely
     perfectly; see `re_compile_fastmap' (the `duplicate' case).  */
  unsigned __REPB_PREFIX(can_be_null) : 1;

  /* If REGS_UNALLOCATED, allocate space in the `regs' structure
     for `max (RE_NREGS, re_nsub + 1)' groups.
     If REGS_REALLOCATE, reallocate space if necessary.
     If REGS_FIXED, use what's there.  */
#ifdef __USE_GNU
# define REGS_UNALLOCATED 0
# define REGS_REALLOCATE 1
# define REGS_FIXED 2
#endif
  unsigned __REPB_PREFIX(regs_allocated) : 2;

  /* Set to zero when `regex_compile' compiles a pattern; set to one
     by `re_compile_fastmap' if it updates the fastmap.  */
  unsigned __REPB_PREFIX(fastmap_accurate) : 1;

  /* If set, `re_match_2' does not return information about
     subexpressions.  */
  unsigned __REPB_PREFIX(no_sub) : 1;

  /* If set, a beginning-of-line anchor doesn't match at the beginning
     of the string.  */
  unsigned __REPB_PREFIX(not_bol) : 1;

  /* Similarly for an end-of-line anchor.  */
  unsigned __REPB_PREFIX(not_eol) : 1;

  /* If true, an anchor at a newline matches.  */
  unsigned __REPB_PREFIX(newline_anchor) : 1;
};

typedef struct re_pattern_buffer regex_t;