1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
|
/* -*- Mode: C++; tab-width: 4; indent-tabs-mode: nil; c-basic-offset: 4 -*- */
/***************************************************************************
* Copyright (C) 2006 by Jocelyn Merand *
* joc.mer@gmail.com *
* *
* THE BSD LICENSE
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
*
* - Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
*
* - Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the
* distribution.
*
* - Neither the name of the WiseGuys Internet B.V. nor the names of
* its contributors may be used to endorse or promote products derived
* from this software without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
* A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
* OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
* SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
* LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
* DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
* THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
* OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
***************************************************************************/
#include "utf8misc.h"
/* #include <stdio.h> */
/**
* These variables are used in character processing functions
* These have been added to manage utf-8 symbols, particularly escape chars
*/
#ifndef _UTF8_
#define _UTF8_
#endif
#ifdef _UTF8_
#define ESCAPE_MASK 0x80
#define WEIGHT_MASK 0xF0
#else
#define ESCAPE_MASK 0xFF
#define WEIGHT_MASK 0x00
#endif
const char* utf8_next_char(const char *str)
{
if (*str & ESCAPE_MASK)
{
/* if the first bit of the current char is 1
* then *str is an escape character
*/
char escape_char = ((*str & WEIGHT_MASK) << 1);
/* and we use it to count (by bit translation) following characters
* (only the weightest part)
*/
while (escape_char & ESCAPE_MASK && *str)
{
/* every step, we move the byte of 1 bit left,
* when first bit is 0, it's finished
*/
escape_char = escape_char << 1;
++str;
}
}
if (*str)
{
/* finaly, if we are not on the \0 character,
* we jump to the next character
*/
++str;
}
return str;
}
int utf8_charcopy(const char *str, char *dest)
{
int pointer = 0;
if (str[pointer] & ESCAPE_MASK)
{ /* if the first bit of the current char is 1 */
/* then str[pointer] is an escape character */
char escape_char = ((str[pointer] & WEIGHT_MASK) << 1); /* and we use
it to count
following
characters
(only the
weightest
part) */
while (escape_char & ESCAPE_MASK && str[pointer])
{ /* every step, we move the byte of 1 bit left,
when first bit is 0, it's finished */
dest[pointer] = str[pointer];
escape_char = escape_char << 1;
++pointer;
}
}
if (str[pointer])
{
dest[pointer] = str[pointer];
++pointer;
}
return pointer;
}
int utf8_issame(char *lex, char *key, int len)
{
/* printf("[%s] prefix of [%s] with length %i", lex, key, len); */
int char_counter = 0;
int pointer = 0;
while (char_counter < len)
{
if (key[pointer] & ESCAPE_MASK)
{ /* if the first bit of the current char is 1 */
/* then key[pointer] is an escap character */
char escape_char = ((key[pointer] & WEIGHT_MASK) << 1); /* and we
use it
to
count
(only
the
weightest
part) */
while (escape_char & ESCAPE_MASK && key[pointer] == lex[pointer])
{
escape_char = escape_char << 1;
++pointer;
}
}
++char_counter; /* and we are on a new utf8 character */
if (key[pointer] != lex[pointer])
{
return 0;
/* printf(" NO\n", lex, key, len); */
}
++pointer;
}
if (lex[pointer] != '\0')
{
return 0;
/* printf(" NO\n"); */
}
/* printf(" YES\n"); */
return 1;
}
extern int utf8_strlen(const char *str)
{
int char_counter = 0;
while (*str)
{
str = utf8_next_char(str);
++char_counter; /* and we are on a new utf8 character */
}
return char_counter;
}
/* vim:set shiftwidth=4 softtabstop=4 expandtab: */
|
