| 1 | /* searchutils.c - helper subroutines for grep's matchers.
|
|---|
| 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 | #include <config.h>
|
|---|
| 20 | #include <assert.h>
|
|---|
| 21 | #include "search.h"
|
|---|
| 22 |
|
|---|
| 23 | #define NCHAR (UCHAR_MAX + 1)
|
|---|
| 24 |
|
|---|
| 25 | void
|
|---|
| 26 | kwsinit (kwset_t *kwset)
|
|---|
| 27 | {
|
|---|
| 28 | static char trans[NCHAR];
|
|---|
| 29 | int i;
|
|---|
| 30 |
|
|---|
| 31 | if (match_icase && MB_CUR_MAX == 1)
|
|---|
| 32 | {
|
|---|
| 33 | for (i = 0; i < NCHAR; ++i)
|
|---|
| 34 | trans[i] = tolower (i);
|
|---|
| 35 |
|
|---|
| 36 | *kwset = kwsalloc (trans);
|
|---|
| 37 | }
|
|---|
| 38 | else
|
|---|
| 39 | *kwset = kwsalloc (NULL);
|
|---|
| 40 |
|
|---|
| 41 | if (!*kwset)
|
|---|
| 42 | xalloc_die ();
|
|---|
| 43 | }
|
|---|
| 44 |
|
|---|
| 45 | #if MBS_SUPPORT
|
|---|
| 46 | /* Convert the *N-byte string, BEG, to lowercase, and write the
|
|---|
| 47 | NUL-terminated result into malloc'd storage. Upon success, set *N
|
|---|
| 48 | to the length (in bytes) of the resulting string (not including the
|
|---|
| 49 | trailing NUL byte), and return a pointer to the lowercase string.
|
|---|
| 50 | Upon memory allocation failure, this function exits.
|
|---|
| 51 | Note that on input, *N must be larger than zero.
|
|---|
| 52 |
|
|---|
| 53 | Note that while this function returns a pointer to malloc'd storage,
|
|---|
| 54 | the caller must not free it, since this function retains a pointer
|
|---|
| 55 | to the buffer and reuses it on any subsequent call. As a consequence,
|
|---|
| 56 | this function is not thread-safe. */
|
|---|
| 57 | char *
|
|---|
| 58 | mbtolower (const char *beg, size_t *n)
|
|---|
| 59 | {
|
|---|
| 60 | static char *out;
|
|---|
| 61 | static size_t outalloc;
|
|---|
| 62 | size_t outlen, mb_cur_max;
|
|---|
| 63 | mbstate_t is, os;
|
|---|
| 64 | const char *end;
|
|---|
| 65 | char *p;
|
|---|
| 66 |
|
|---|
| 67 | if (*n > outalloc || outalloc == 0)
|
|---|
| 68 | {
|
|---|
| 69 | outalloc = MAX(1, *n);
|
|---|
| 70 | out = xrealloc (out, outalloc);
|
|---|
| 71 | }
|
|---|
| 72 |
|
|---|
| 73 | /* appease clang-2.6 */
|
|---|
| 74 | assert (out);
|
|---|
| 75 | if (*n == 0)
|
|---|
| 76 | return out;
|
|---|
| 77 |
|
|---|
| 78 | memset (&is, 0, sizeof (is));
|
|---|
| 79 | memset (&os, 0, sizeof (os));
|
|---|
| 80 | end = beg + *n;
|
|---|
| 81 |
|
|---|
| 82 | mb_cur_max = MB_CUR_MAX;
|
|---|
| 83 | p = out;
|
|---|
| 84 | outlen = 0;
|
|---|
| 85 | while (beg < end)
|
|---|
| 86 | {
|
|---|
| 87 | wchar_t wc;
|
|---|
| 88 | size_t mbclen = mbrtowc(&wc, beg, end - beg, &is);
|
|---|
| 89 | if (outlen + mb_cur_max >= outalloc)
|
|---|
| 90 | {
|
|---|
| 91 | out = x2nrealloc (out, &outalloc, 1);
|
|---|
| 92 | p = out + outlen;
|
|---|
| 93 | }
|
|---|
| 94 |
|
|---|
| 95 | if (mbclen == (size_t) -1 || mbclen == (size_t) -2 || mbclen == 0)
|
|---|
| 96 | {
|
|---|
| 97 | /* An invalid sequence, or a truncated multi-octet character.
|
|---|
| 98 | We treat it as a single-octet character. */
|
|---|
| 99 | *p++ = *beg++;
|
|---|
| 100 | outlen++;
|
|---|
| 101 | memset (&is, 0, sizeof (is));
|
|---|
| 102 | memset (&os, 0, sizeof (os));
|
|---|
| 103 | }
|
|---|
| 104 | else
|
|---|
| 105 | {
|
|---|
| 106 | beg += mbclen;
|
|---|
| 107 | mbclen = wcrtomb (p, towlower ((wint_t) wc), &os);
|
|---|
| 108 | p += mbclen;
|
|---|
| 109 | outlen += mbclen;
|
|---|
| 110 | }
|
|---|
| 111 | }
|
|---|
| 112 |
|
|---|
| 113 | *n = p - out;
|
|---|
| 114 | *p = 0;
|
|---|
| 115 | return out;
|
|---|
| 116 | }
|
|---|
| 117 |
|
|---|
| 118 |
|
|---|
| 119 | bool
|
|---|
| 120 | is_mb_middle (const char **good, const char *buf, const char *end,
|
|---|
| 121 | size_t match_len)
|
|---|
| 122 | {
|
|---|
| 123 | const char *p = *good;
|
|---|
| 124 | const char *prev = p;
|
|---|
| 125 | mbstate_t cur_state;
|
|---|
| 126 |
|
|---|
| 127 | /* TODO: can be optimized for UTF-8. */
|
|---|
| 128 | memset(&cur_state, 0, sizeof(mbstate_t));
|
|---|
| 129 | while (p < buf)
|
|---|
| 130 | {
|
|---|
| 131 | size_t mbclen = mbrlen(p, end - p, &cur_state);
|
|---|
| 132 |
|
|---|
| 133 | /* Store the beginning of the previous complete multibyte character. */
|
|---|
| 134 | if (mbclen != (size_t) -2)
|
|---|
| 135 | prev = p;
|
|---|
| 136 |
|
|---|
| 137 | if (mbclen == (size_t) -1 || mbclen == (size_t) -2 || mbclen == 0)
|
|---|
| 138 | {
|
|---|
| 139 | /* An invalid sequence, or a truncated multibyte character.
|
|---|
| 140 | We treat it as a single byte character. */
|
|---|
| 141 | mbclen = 1;
|
|---|
| 142 | memset(&cur_state, 0, sizeof cur_state);
|
|---|
| 143 | }
|
|---|
| 144 | p += mbclen;
|
|---|
| 145 | }
|
|---|
| 146 |
|
|---|
| 147 | *good = prev;
|
|---|
| 148 |
|
|---|
| 149 | if (p > buf)
|
|---|
| 150 | return true;
|
|---|
| 151 |
|
|---|
| 152 | /* P == BUF here. */
|
|---|
| 153 | return 0 < match_len && match_len < mbrlen (p, end - p, &cur_state);
|
|---|
| 154 | }
|
|---|
| 155 | #endif /* MBS_SUPPORT */
|
|---|