| 1 | /* kwsearch.c - searching subroutines using kwset for grep.
|
|---|
| 2 | Copyright 1992, 1998, 2000, 2007, 2009-2012 Free Software Foundation, Inc.
|
|---|
| 3 |
|
|---|
| 4 | This program is free software; you can redistribute it and/or modify
|
|---|
| 5 | it under the terms of the GNU General Public License as published by
|
|---|
| 6 | the Free Software Foundation; either version 3, or (at your option)
|
|---|
| 7 | any later version.
|
|---|
| 8 |
|
|---|
| 9 | This program is distributed in the hope that it will be useful,
|
|---|
| 10 | but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|---|
| 11 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|---|
| 12 | GNU General Public License for more details.
|
|---|
| 13 |
|
|---|
| 14 | You should have received a copy of the GNU General Public License
|
|---|
| 15 | along with this program; if not, write to the Free Software
|
|---|
| 16 | Foundation, Inc., 51 Franklin Street - Fifth Floor, Boston, MA
|
|---|
| 17 | 02110-1301, USA. */
|
|---|
| 18 |
|
|---|
| 19 | /* Written August 1992 by Mike Haertel. */
|
|---|
| 20 |
|
|---|
| 21 | #include <config.h>
|
|---|
| 22 | #include "search.h"
|
|---|
| 23 |
|
|---|
| 24 | /* For -w, we also consider _ to be word constituent. */
|
|---|
| 25 | #define WCHAR(C) (isalnum (C) || (C) == '_')
|
|---|
| 26 |
|
|---|
| 27 | /* KWset compiled pattern. For Ecompile and Gcompile, we compile
|
|---|
| 28 | a list of strings, at least one of which is known to occur in
|
|---|
| 29 | any string matching the regexp. */
|
|---|
| 30 | static kwset_t kwset;
|
|---|
| 31 |
|
|---|
| 32 | void
|
|---|
| 33 | Fcompile (char const *pattern, size_t size)
|
|---|
| 34 | {
|
|---|
| 35 | char const *err;
|
|---|
| 36 | size_t psize = size;
|
|---|
| 37 | char const *pat = (match_icase && MB_CUR_MAX > 1
|
|---|
| 38 | ? mbtolower (pattern, &psize)
|
|---|
| 39 | : pattern);
|
|---|
| 40 |
|
|---|
| 41 | kwsinit (&kwset);
|
|---|
| 42 |
|
|---|
| 43 | char const *beg = pat;
|
|---|
| 44 | do
|
|---|
| 45 | {
|
|---|
| 46 | char const *lim;
|
|---|
| 47 | char const *end;
|
|---|
| 48 | for (lim = beg;; ++lim)
|
|---|
| 49 | {
|
|---|
| 50 | end = lim;
|
|---|
| 51 | if (lim >= pat + psize)
|
|---|
| 52 | break;
|
|---|
| 53 | if (*lim == '\n')
|
|---|
| 54 | {
|
|---|
| 55 | lim++;
|
|---|
| 56 | break;
|
|---|
| 57 | }
|
|---|
| 58 | #if HAVE_DOS_FILE_CONTENTS
|
|---|
| 59 | if (*lim == '\r' && lim + 1 < pat + psize && lim[1] == '\n')
|
|---|
| 60 | {
|
|---|
| 61 | lim += 2;
|
|---|
| 62 | break;
|
|---|
| 63 | }
|
|---|
| 64 | #endif
|
|---|
| 65 | }
|
|---|
| 66 |
|
|---|
| 67 | if ((err = kwsincr (kwset, beg, end - beg)) != NULL)
|
|---|
| 68 | error (EXIT_TROUBLE, 0, "%s", err);
|
|---|
| 69 | beg = lim;
|
|---|
| 70 | }
|
|---|
| 71 | while (beg < pat + psize);
|
|---|
| 72 |
|
|---|
| 73 | if ((err = kwsprep (kwset)) != NULL)
|
|---|
| 74 | error (EXIT_TROUBLE, 0, "%s", err);
|
|---|
| 75 | }
|
|---|
| 76 |
|
|---|
| 77 | size_t
|
|---|
| 78 | Fexecute (char const *buf, size_t size, size_t *match_size,
|
|---|
| 79 | char const *start_ptr)
|
|---|
| 80 | {
|
|---|
| 81 | char const *beg, *try, *end, *mb_start;
|
|---|
| 82 | size_t len;
|
|---|
| 83 | char eol = eolbyte;
|
|---|
| 84 | struct kwsmatch kwsmatch;
|
|---|
| 85 | size_t ret_val;
|
|---|
| 86 | if (MB_CUR_MAX > 1)
|
|---|
| 87 | {
|
|---|
| 88 | if (match_icase)
|
|---|
| 89 | {
|
|---|
| 90 | char *case_buf = mbtolower (buf, &size);
|
|---|
| 91 | if (start_ptr)
|
|---|
| 92 | start_ptr = case_buf + (start_ptr - buf);
|
|---|
| 93 | buf = case_buf;
|
|---|
| 94 | }
|
|---|
| 95 | }
|
|---|
| 96 |
|
|---|
| 97 | for (mb_start = beg = start_ptr ? start_ptr : buf; beg <= buf + size; beg++)
|
|---|
| 98 | {
|
|---|
| 99 | size_t offset = kwsexec (kwset, beg, buf + size - beg, &kwsmatch);
|
|---|
| 100 | if (offset == (size_t) -1)
|
|---|
| 101 | goto failure;
|
|---|
| 102 | len = kwsmatch.size[0];
|
|---|
| 103 | if (MB_CUR_MAX > 1
|
|---|
| 104 | && is_mb_middle (&mb_start, beg + offset, buf + size, len))
|
|---|
| 105 | {
|
|---|
| 106 | /* The match was a part of multibyte character, advance at least
|
|---|
| 107 | one byte to ensure no infinite loop happens. */
|
|---|
| 108 | mbstate_t s;
|
|---|
| 109 | memset (&s, 0, sizeof s);
|
|---|
| 110 | size_t mb_len = mbrlen (mb_start, (buf + size) - (beg + offset), &s);
|
|---|
| 111 | if (mb_len == (size_t) -2)
|
|---|
| 112 | goto failure;
|
|---|
| 113 | beg = mb_start;
|
|---|
| 114 | if (mb_len != (size_t) -1)
|
|---|
| 115 | beg += mb_len - 1;
|
|---|
| 116 | continue;
|
|---|
| 117 | }
|
|---|
| 118 | beg += offset;
|
|---|
| 119 | if (start_ptr && !match_words)
|
|---|
| 120 | goto success_in_beg_and_len;
|
|---|
| 121 | if (match_lines)
|
|---|
| 122 | {
|
|---|
| 123 | if (beg > buf && beg[-1] != eol)
|
|---|
| 124 | continue;
|
|---|
| 125 | if (beg + len < buf + size && beg[len] != eol)
|
|---|
| 126 | continue;
|
|---|
| 127 | goto success;
|
|---|
| 128 | }
|
|---|
| 129 | else if (match_words)
|
|---|
| 130 | for (try = beg; ; )
|
|---|
| 131 | {
|
|---|
| 132 | if (try > buf && WCHAR((unsigned char) try[-1]))
|
|---|
| 133 | break;
|
|---|
| 134 | if (try + len < buf + size && WCHAR((unsigned char) try[len]))
|
|---|
| 135 | {
|
|---|
| 136 | if (!len)
|
|---|
| 137 | break;
|
|---|
| 138 | offset = kwsexec (kwset, beg, --len, &kwsmatch);
|
|---|
| 139 | if (offset == (size_t) -1)
|
|---|
| 140 | break;
|
|---|
| 141 | try = beg + offset;
|
|---|
| 142 | len = kwsmatch.size[0];
|
|---|
| 143 | }
|
|---|
| 144 | else if (!start_ptr)
|
|---|
| 145 | goto success;
|
|---|
| 146 | else
|
|---|
| 147 | goto success_in_beg_and_len;
|
|---|
| 148 | } /* for (try) */
|
|---|
| 149 | else
|
|---|
| 150 | goto success;
|
|---|
| 151 | } /* for (beg in buf) */
|
|---|
| 152 |
|
|---|
| 153 | failure:
|
|---|
| 154 | ret_val = -1;
|
|---|
| 155 | goto out;
|
|---|
| 156 |
|
|---|
| 157 | success:
|
|---|
| 158 | if ((end = memchr (beg + len, eol, (buf + size) - (beg + len))) != NULL)
|
|---|
| 159 | end++;
|
|---|
| 160 | else
|
|---|
| 161 | end = buf + size;
|
|---|
| 162 | while (buf < beg && beg[-1] != eol)
|
|---|
| 163 | --beg;
|
|---|
| 164 | len = end - beg;
|
|---|
| 165 | success_in_beg_and_len:
|
|---|
| 166 | *match_size = len;
|
|---|
| 167 | ret_val = beg - buf;
|
|---|
| 168 | out:
|
|---|
| 169 | return ret_val;
|
|---|
| 170 | }
|
|---|