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
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
|
/*
+----------------------------------------------------------------------+
| PHP Version 5 |
+----------------------------------------------------------------------+
| This source file is subject to version 3.01 of the PHP license, |
| that is bundled with this package in the file LICENSE, and is |
| available through the world-wide-web at the following url: |
| http://www.php.net/license/3_01.txt |
| If you did not receive a copy of the PHP license and are unable to |
| obtain it through the world-wide-web, please send a note to |
| license@php.net so we can mail you a copy immediately. |
+----------------------------------------------------------------------+
| Authors: Ed Batutis <ed@batutis.com> |
+----------------------------------------------------------------------+
*/
#ifdef HAVE_CONFIG_H
#include "config.h"
#endif
#include "php_intl.h"
#include "unicode/unorm.h"
#include "normalizer.h"
#include "normalizer_class.h"
#include "normalizer_normalize.h"
#include "intl_convert.h"
/* {{{ proto string Normalizer::normalize( string $input [, string $form = FORM_C] )
* Normalize a string. }}} */
/* {{{ proto string normalizer_normalize( string $input [, string $form = FORM_C] )
* Normalize a string.
*/
PHP_FUNCTION( normalizer_normalize )
{
char* input = NULL;
/* form is optional, defaults to FORM_C */
php_int_t form = NORMALIZER_DEFAULT;
int input_len = 0;
UChar* uinput = NULL;
int uinput_len = 0;
int expansion_factor = 1;
UErrorCode status = U_ZERO_ERROR;
UChar* uret_buf = NULL;
int uret_len = 0;
char* ret_buf = NULL;
int32_t ret_len = 0;
int32_t size_needed;
intl_error_reset( NULL TSRMLS_CC );
/* Parse parameters. */
if( zend_parse_method_parameters( ZEND_NUM_ARGS() TSRMLS_CC, getThis(), "s|i",
&input, &input_len, &form ) == FAILURE )
{
intl_error_set( NULL, U_ILLEGAL_ARGUMENT_ERROR,
"normalizer_normalize: unable to parse input params", 0 TSRMLS_CC );
RETURN_FALSE;
}
expansion_factor = 1;
switch(form) {
case NORMALIZER_NONE:
break;
case NORMALIZER_FORM_D:
expansion_factor = 3;
break;
case NORMALIZER_FORM_KD:
expansion_factor = 3;
break;
case NORMALIZER_FORM_C:
case NORMALIZER_FORM_KC:
break;
default:
intl_error_set( NULL, U_ILLEGAL_ARGUMENT_ERROR,
"normalizer_normalize: illegal normalization form", 0 TSRMLS_CC );
RETURN_FALSE;
}
/*
* Normalize string (converting it to UTF-16 first).
*/
/* First convert the string to UTF-16. */
intl_convert_utf8_to_utf16(&uinput, &uinput_len, input, input_len, &status );
if( U_FAILURE( status ) )
{
/* Set global error code. */
intl_error_set_code( NULL, status TSRMLS_CC );
/* Set error messages. */
intl_error_set_custom_msg( NULL, "Error converting input string to UTF-16", 0 TSRMLS_CC );
if (uinput) {
efree( uinput );
}
RETURN_FALSE;
}
/* Allocate memory for the destination buffer for normalization */
uret_len = uinput_len * expansion_factor;
uret_buf = eumalloc( uret_len + 1 );
/* normalize */
size_needed = unorm_normalize( uinput, uinput_len, form, (int32_t) 0 /* options */, uret_buf, uret_len, &status);
/* Bail out if an unexpected error occurred.
* (U_BUFFER_OVERFLOW_ERROR means that *target buffer is not large enough).
* (U_STRING_NOT_TERMINATED_WARNING usually means that the input string is empty).
*/
if( U_FAILURE(status) && status != U_BUFFER_OVERFLOW_ERROR && status != U_STRING_NOT_TERMINATED_WARNING ) {
efree( uret_buf );
efree( uinput );
RETURN_NULL();
}
if ( size_needed > uret_len ) {
/* realloc does not seem to work properly - memory is corrupted
* uret_buf = eurealloc(uret_buf, size_needed + 1);
*/
efree( uret_buf );
uret_buf = eumalloc( size_needed + 1 );
uret_len = size_needed;
status = U_ZERO_ERROR;
/* try normalize again */
size_needed = unorm_normalize( uinput, uinput_len, form, (int32_t) 0 /* options */, uret_buf, uret_len, &status);
/* Bail out if an unexpected error occurred. */
if( U_FAILURE(status) ) {
/* Set error messages. */
intl_error_set_custom_msg( NULL,"Error normalizing string", 0 TSRMLS_CC );
efree( uret_buf );
efree( uinput );
RETURN_FALSE;
}
}
efree( uinput );
/* the buffer we actually used */
uret_len = size_needed;
/* Convert normalized string from UTF-16 to UTF-8. */
intl_convert_utf16_to_utf8( &ret_buf, &ret_len, uret_buf, uret_len, &status );
efree( uret_buf );
if( U_FAILURE( status ) )
{
intl_error_set( NULL, status,
"normalizer_normalize: error converting normalized text UTF-8", 0 TSRMLS_CC );
RETURN_FALSE;
}
/* Return it. */
RETVAL_STRINGL( ret_buf, ret_len );
//???
efree(ret_buf);
}
/* }}} */
/* {{{ proto bool Normalizer::isNormalized( string $input [, string $form = FORM_C] )
* Test if a string is in a given normalization form. }}} */
/* {{{ proto bool normalizer_is_normalize( string $input [, string $form = FORM_C] )
* Test if a string is in a given normalization form.
*/
PHP_FUNCTION( normalizer_is_normalized )
{
char* input = NULL;
/* form is optional, defaults to FORM_C */
php_int_t form = NORMALIZER_DEFAULT;
int input_len = 0;
UChar* uinput = NULL;
int uinput_len = 0;
UErrorCode status = U_ZERO_ERROR;
UBool uret = FALSE;
intl_error_reset( NULL TSRMLS_CC );
/* Parse parameters. */
if( zend_parse_method_parameters( ZEND_NUM_ARGS() TSRMLS_CC, getThis(), "s|i",
&input, &input_len, &form) == FAILURE )
{
intl_error_set( NULL, U_ILLEGAL_ARGUMENT_ERROR,
"normalizer_is_normalized: unable to parse input params", 0 TSRMLS_CC );
RETURN_FALSE;
}
switch(form) {
/* case NORMALIZER_NONE: not allowed - doesn't make sense */
case NORMALIZER_FORM_D:
case NORMALIZER_FORM_KD:
case NORMALIZER_FORM_C:
case NORMALIZER_FORM_KC:
break;
default:
intl_error_set( NULL, U_ILLEGAL_ARGUMENT_ERROR,
"normalizer_normalize: illegal normalization form", 0 TSRMLS_CC );
RETURN_FALSE;
}
/*
* Test normalization of string (converting it to UTF-16 first).
*/
/* First convert the string to UTF-16. */
intl_convert_utf8_to_utf16(&uinput, &uinput_len, input, input_len, &status );
if( U_FAILURE( status ) )
{
/* Set global error code. */
intl_error_set_code( NULL, status TSRMLS_CC );
/* Set error messages. */
intl_error_set_custom_msg( NULL, "Error converting string to UTF-16.", 0 TSRMLS_CC );
if (uinput) {
efree( uinput );
}
RETURN_FALSE;
}
/* test string */
uret = unorm_isNormalizedWithOptions( uinput, uinput_len, form, (int32_t) 0 /* options */, &status);
efree( uinput );
/* Bail out if an unexpected error occurred. */
if( U_FAILURE(status) ) {
/* Set error messages. */
intl_error_set_custom_msg( NULL,"Error testing if string is the given normalization form.", 0 TSRMLS_CC );
RETURN_FALSE;
}
if ( uret )
RETURN_TRUE;
RETURN_FALSE;
}
/* }}} */
/*
* Local variables:
* tab-width: 4
* c-basic-offset: 4
* End:
* vim600: noet sw=4 ts=4 fdm=marker
* vim<600: noet sw=4 ts=4
*/
|
