| 1 |
1275 |
phoenix |
/*
|
| 2 |
|
|
* unistr.c - Unicode string handling. Part of the Linux-NTFS project.
|
| 3 |
|
|
*
|
| 4 |
|
|
* Copyright (c) 2000,2001 Anton Altaparmakov.
|
| 5 |
|
|
*
|
| 6 |
|
|
* This program/include file is free software; you can redistribute it and/or
|
| 7 |
|
|
* modify it under the terms of the GNU General Public License as published
|
| 8 |
|
|
* by the Free Software Foundation; either version 2 of the License, or
|
| 9 |
|
|
* (at your option) any later version.
|
| 10 |
|
|
*
|
| 11 |
|
|
* This program/include file is distributed in the hope that it will be
|
| 12 |
|
|
* useful, but WITHOUT ANY WARRANTY; without even the implied warranty
|
| 13 |
|
|
* of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
| 14 |
|
|
* GNU General Public License for more details.
|
| 15 |
|
|
*
|
| 16 |
|
|
* You should have received a copy of the GNU General Public License
|
| 17 |
|
|
* along with this program (in the main directory of the Linux-NTFS
|
| 18 |
|
|
* distribution in the file COPYING); if not, write to the Free Software
|
| 19 |
|
|
* Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
|
| 20 |
|
|
*/
|
| 21 |
|
|
|
| 22 |
|
|
#include <linux/string.h>
|
| 23 |
|
|
#include <asm/byteorder.h>
|
| 24 |
|
|
|
| 25 |
|
|
#include "unistr.h"
|
| 26 |
|
|
#include "macros.h"
|
| 27 |
|
|
|
| 28 |
|
|
/*
|
| 29 |
|
|
* This is used by the name collation functions to quickly determine what
|
| 30 |
|
|
* characters are (in)valid.
|
| 31 |
|
|
*/
|
| 32 |
|
|
const __u8 legal_ansi_char_array[0x40] = {
|
| 33 |
|
|
0x00, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10,
|
| 34 |
|
|
0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10,
|
| 35 |
|
|
|
| 36 |
|
|
0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10,
|
| 37 |
|
|
0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10,
|
| 38 |
|
|
|
| 39 |
|
|
0x17, 0x07, 0x18, 0x17, 0x17, 0x17, 0x17, 0x17,
|
| 40 |
|
|
0x17, 0x17, 0x18, 0x16, 0x16, 0x17, 0x07, 0x00,
|
| 41 |
|
|
|
| 42 |
|
|
0x17, 0x17, 0x17, 0x17, 0x17, 0x17, 0x17, 0x17,
|
| 43 |
|
|
0x17, 0x17, 0x04, 0x16, 0x18, 0x16, 0x18, 0x18,
|
| 44 |
|
|
};
|
| 45 |
|
|
|
| 46 |
|
|
/**
|
| 47 |
|
|
* ntfs_are_names_equal - compare two Unicode names for equality
|
| 48 |
|
|
* @s1: name to compare to @s2
|
| 49 |
|
|
* @s1_len: length in Unicode characters of @s1
|
| 50 |
|
|
* @s2: name to compare to @s1
|
| 51 |
|
|
* @s2_len: length in Unicode characters of @s2
|
| 52 |
|
|
* @ic: ignore case bool
|
| 53 |
|
|
* @upcase: upcase table (only if @ic == IGNORE_CASE)
|
| 54 |
|
|
* @upcase_size: length in Unicode characters of @upcase (if present)
|
| 55 |
|
|
*
|
| 56 |
|
|
* Compare the names @s1 and @s2 and return TRUE (1) if the names are
|
| 57 |
|
|
* identical, or FALSE (0) if they are not identical. If @ic is IGNORE_CASE,
|
| 58 |
|
|
* the @upcase table is used to performa a case insensitive comparison.
|
| 59 |
|
|
*/
|
| 60 |
|
|
int ntfs_are_names_equal(wchar_t *s1, size_t s1_len,
|
| 61 |
|
|
wchar_t *s2, size_t s2_len, int ic,
|
| 62 |
|
|
wchar_t *upcase, __u32 upcase_size)
|
| 63 |
|
|
{
|
| 64 |
|
|
if (s1_len != s2_len)
|
| 65 |
|
|
return 0;
|
| 66 |
|
|
if (!ic)
|
| 67 |
|
|
return memcmp(s1, s2, s1_len << 1) ? 0: 1;
|
| 68 |
|
|
return ntfs_wcsncasecmp(s1, s2, s1_len, upcase, upcase_size) ? 0: 1;
|
| 69 |
|
|
}
|
| 70 |
|
|
|
| 71 |
|
|
/**
|
| 72 |
|
|
* ntfs_collate_names - collate two Unicode names
|
| 73 |
|
|
* @upcase: upcase table (ignored if @ic is CASE_SENSITIVE)
|
| 74 |
|
|
* @upcase_len: upcase table size (ignored if @ic is CASE_SENSITIVE)
|
| 75 |
|
|
* @name1: first Unicode name to compare
|
| 76 |
|
|
* @name2: second Unicode name to compare
|
| 77 |
|
|
* @ic: either CASE_SENSITIVE or IGNORE_CASE
|
| 78 |
|
|
* @err_val: if @name1 contains an invalid character return this value
|
| 79 |
|
|
*
|
| 80 |
|
|
* ntfs_collate_names collates two Unicode names and returns:
|
| 81 |
|
|
*
|
| 82 |
|
|
* -1 if the first name collates before the second one,
|
| 83 |
|
|
* 0 if the names match,
|
| 84 |
|
|
* 1 if the second name collates before the first one, or
|
| 85 |
|
|
* @ec if an invalid character is encountered in @name1 during the comparison.
|
| 86 |
|
|
*
|
| 87 |
|
|
* The following characters are considered invalid: '"', '*', '<', '>' and '?'.
|
| 88 |
|
|
*/
|
| 89 |
|
|
int ntfs_collate_names(wchar_t *upcase, __u32 upcase_len,
|
| 90 |
|
|
wchar_t *name1, __u32 name1_len,
|
| 91 |
|
|
wchar_t *name2, __u32 name2_len,
|
| 92 |
|
|
int ic, int err_val)
|
| 93 |
|
|
{
|
| 94 |
|
|
__u32 cnt, min_len;
|
| 95 |
|
|
wchar_t c1, c2;
|
| 96 |
|
|
|
| 97 |
|
|
min_len = name1_len;
|
| 98 |
|
|
if (min_len > name2_len)
|
| 99 |
|
|
min_len = name2_len;
|
| 100 |
|
|
for (cnt = 0; cnt < min_len; ++cnt) {
|
| 101 |
|
|
c1 = le16_to_cpu(*name1++);
|
| 102 |
|
|
c2 = le16_to_cpu(*name2++);
|
| 103 |
|
|
if (ic) {
|
| 104 |
|
|
if (c1 < upcase_len)
|
| 105 |
|
|
c1 = le16_to_cpu(upcase[c1]);
|
| 106 |
|
|
if (c2 < upcase_len)
|
| 107 |
|
|
c2 = le16_to_cpu(upcase[c2]);
|
| 108 |
|
|
}
|
| 109 |
|
|
if (c1 < 64 && legal_ansi_char_array[c1] & 8)
|
| 110 |
|
|
return err_val;
|
| 111 |
|
|
if (c1 < c2)
|
| 112 |
|
|
return -1;
|
| 113 |
|
|
if (c1 > c2)
|
| 114 |
|
|
return 1;
|
| 115 |
|
|
++name1;
|
| 116 |
|
|
++name2;
|
| 117 |
|
|
}
|
| 118 |
|
|
if (name1_len < name2_len)
|
| 119 |
|
|
return -1;
|
| 120 |
|
|
if (name1_len == name2_len)
|
| 121 |
|
|
return 0;
|
| 122 |
|
|
/* name1_len > name2_len */
|
| 123 |
|
|
c1 = le16_to_cpu(*name1);
|
| 124 |
|
|
if (c1 < 64 && legal_ansi_char_array[c1] & 8)
|
| 125 |
|
|
return err_val;
|
| 126 |
|
|
return 1;
|
| 127 |
|
|
}
|
| 128 |
|
|
|
| 129 |
|
|
/**
|
| 130 |
|
|
* ntfs_wcsncasecmp - compare two little endian Unicode strings, ignoring case
|
| 131 |
|
|
* @s1: first string
|
| 132 |
|
|
* @s2: second string
|
| 133 |
|
|
* @n: maximum unicode characters to compare
|
| 134 |
|
|
* @upcase: upcase table
|
| 135 |
|
|
* @upcase_size: upcase table size in Unicode characters
|
| 136 |
|
|
*
|
| 137 |
|
|
* Compare the first @n characters of the Unicode strings @s1 and @s2,
|
| 138 |
|
|
* ignoring case. The strings in little endian format and appropriate
|
| 139 |
|
|
* le16_to_cpu() conversion is performed on non-little endian machines.
|
| 140 |
|
|
*
|
| 141 |
|
|
* Each character is uppercased using the @upcase table before the comparison.
|
| 142 |
|
|
*
|
| 143 |
|
|
* The function returns an integer less than, equal to, or greater than zero
|
| 144 |
|
|
* if @s1 (or the first @n Unicode characters thereof) is found, respectively,
|
| 145 |
|
|
* to be less than, to match, or be greater than @s2.
|
| 146 |
|
|
*/
|
| 147 |
|
|
int ntfs_wcsncasecmp(wchar_t *s1, wchar_t *s2, size_t n,
|
| 148 |
|
|
wchar_t *upcase, __u32 upcase_size)
|
| 149 |
|
|
{
|
| 150 |
|
|
wchar_t c1, c2;
|
| 151 |
|
|
size_t i;
|
| 152 |
|
|
|
| 153 |
|
|
for (i = 0; i < n; ++i) {
|
| 154 |
|
|
if ((c1 = le16_to_cpu(s1[i])) < upcase_size)
|
| 155 |
|
|
c1 = le16_to_cpu(upcase[c1]);
|
| 156 |
|
|
if ((c2 = le16_to_cpu(s2[i])) < upcase_size)
|
| 157 |
|
|
c2 = le16_to_cpu(upcase[c2]);
|
| 158 |
|
|
if (c1 < c2)
|
| 159 |
|
|
return -1;
|
| 160 |
|
|
if (c1 > c2)
|
| 161 |
|
|
return 1;
|
| 162 |
|
|
if (!c1)
|
| 163 |
|
|
break;
|
| 164 |
|
|
}
|
| 165 |
|
|
return 0;
|
| 166 |
|
|
}
|
| 167 |
|
|
|
