regsub.c

   1 /* $OpenBSD$ */
   2
   3 /*
   4  * Copyright (c) 2019 Nicholas Marriott <nicholas.marriott@gmail.com>
   5  *
   6  * Permission to use, copy, modify, and distribute this software for any
   7  * purpose with or without fee is hereby granted, provided that the above
   8  * copyright notice and this permission notice appear in all copies.
   9  *
  10  * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
  11  * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
  12  * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
  13  * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
  14  * WHATSOEVER RESULTING FROM LOSS OF MIND, USE, DATA OR PROFITS, WHETHER
  15  * IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING
  16  * OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
  17  */
  18
  19 #include <sys/types.h>
  20
  21 #include <regex.h>
  22 #include <string.h>
  23
  24 #include "tmux.h"
  25
  26 static void
  27 regsub_copy(char **buf, size_t *len, const char *text, size_t start, size_t end)
  28 {
  29         size_t  add = end - start;
  30
  31         *buf = xrealloc(*buf, (*len) + add + 1);
  32         memcpy((*buf) + *len, text + start, add);
  33         (*len) += add;
  34 }
  35
  36 static void
  37 regsub_expand(char **buf, size_t *len, const char *with, const char *text,
  38     regmatch_t *m, u_int n)
  39 {
  40         const char      *cp;
  41         u_int            i;
  42
  43         for (cp = with; *cp != '\0'; cp++) {
  44                 if (*cp == '\\') {
  45                         cp++;
  46                         if (*cp >= '0' && *cp <= '9') {
  47                                 i = *cp - '0';
  48                                 if (i < n && m[i].rm_so != m[i].rm_eo) {
  49                                         regsub_copy(buf, len, text, m[i].rm_so,
  50                                             m[i].rm_eo);
  51                                         continue;
  52                                 }
  53                         }
  54                 }
  55                 *buf = xrealloc(*buf, (*len) + 2);
  56                 (*buf)[(*len)++] = *cp;
  57         }
  58 }
  59
  60 char *
  61 regsub(const char *pattern, const char *with, const char *text, int flags)
  62 {
  63         regex_t          r;
  64         regmatch_t       m[10];
  65         ssize_t          start, end, last, len = 0;
  66         int              empty = 0;
  67         char            *buf = NULL;
  68
  69         if (*text == '\0')
  70                 return (xstrdup(""));
  71         if (regcomp(&r, pattern, flags) != 0)
  72                 return (NULL);
  73
  74         start = 0;
  75         last = 0;
  76         end = strlen(text);
  77
  78         while (start <= end) {
  79                 if (regexec(&r, text + start, nitems(m), m, 0) != 0) {
  80                         regsub_copy(&buf, &len, text, start, end);
  81                         break;
  82                 }
  83
  84                 /*
  85                  * Append any text not part of this match (from the end of the
  86                  * last match).
  87                  */
  88                 regsub_copy(&buf, &len, text, last, m[0].rm_so + start);
  89
  90                 /*
  91                  * If the last match was empty and this one isn't (it is either
  92                  * later or has matched text), expand this match. If it is
  93                  * empty, move on one character and try again from there.
  94                  */
  95                 if (empty ||
  96                     start + m[0].rm_so != last ||
  97                     m[0].rm_so != m[0].rm_eo) {
  98                         regsub_expand(&buf, &len, with, text + start, m,
  99                             nitems(m));
 100
 101                         last = start + m[0].rm_eo;
 102                         start += m[0].rm_eo;
 103                         empty = 0;
 104                 } else {
 105                         last = start + m[0].rm_eo;
 106                         start += m[0].rm_eo + 1;
 107                         empty = 1;
 108                 }
 109
 110                 /* Stop now if anchored to start. */
 111                 if (*pattern == '^') {
 112                         regsub_copy(&buf, &len, text, start, end);
 113                         break;
 114                 }
 115         }
 116         buf[len] = '\0';
 117
 118         regfree(&r);
 119         return (buf);
 120 }