| 1 |
lars |
1 |
<?php
|
|
|
2 |
/*
|
|
|
3 |
* $Id: Inflector.php 3189 2007-11-18 20:37:44Z meus $
|
|
|
4 |
*
|
|
|
5 |
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
|
|
|
6 |
* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
|
|
|
7 |
* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
|
|
|
8 |
* A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
|
|
|
9 |
* OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
|
|
|
10 |
* SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
|
|
|
11 |
* LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
|
|
|
12 |
* DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
|
|
|
13 |
* THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
|
|
14 |
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
|
|
15 |
* OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
|
|
16 |
*
|
|
|
17 |
* This software consists of voluntary contributions made by many individuals
|
|
|
18 |
* and is licensed under the LGPL. For more information, see
|
|
|
19 |
* <http://www.doctrine-project.org>.
|
|
|
20 |
*/
|
|
|
21 |
|
|
|
22 |
/**
|
|
|
23 |
* Doctrine inflector has static methods for inflecting text
|
|
|
24 |
*
|
|
|
25 |
* The methods in these classes are from several different sources collected
|
|
|
26 |
* across several different php projects and several different authors. The
|
|
|
27 |
* original author names and emails are not known
|
|
|
28 |
*
|
|
|
29 |
* @package Doctrine
|
|
|
30 |
* @subpackage Inflector
|
|
|
31 |
* @license http://www.opensource.org/licenses/lgpl-license.php LGPL
|
|
|
32 |
* @link www.doctrine-project.org
|
|
|
33 |
* @since 1.0
|
|
|
34 |
* @version $Revision: 3189 $
|
|
|
35 |
* @author Konsta Vesterinen <kvesteri@cc.hut.fi>
|
|
|
36 |
* @author Jonathan H. Wage <jonwage@gmail.com>
|
|
|
37 |
*/
|
|
|
38 |
class Doctrine_Inflector
|
|
|
39 |
{
|
|
|
40 |
/**
|
|
|
41 |
* Convert word in to the format for a Doctrine table name. Converts 'ModelName' to 'model_name'
|
|
|
42 |
*
|
|
|
43 |
* @param string $word Word to tableize
|
|
|
44 |
* @return string $word Tableized word
|
|
|
45 |
*/
|
|
|
46 |
public static function tableize($word)
|
|
|
47 |
{
|
|
|
48 |
return strtolower(preg_replace('~(?<=\\w)([A-Z])~', '_$1', $word));
|
|
|
49 |
}
|
|
|
50 |
|
|
|
51 |
/**
|
|
|
52 |
* Convert a word in to the format for a Doctrine class name. Converts 'table_name' to 'TableName'
|
|
|
53 |
*
|
|
|
54 |
* @param string $word Word to classify
|
|
|
55 |
* @return string $word Classified word
|
|
|
56 |
*/
|
|
|
57 |
public static function classify($word)
|
|
|
58 |
{
|
|
|
59 |
static $cache = array();
|
|
|
60 |
|
|
|
61 |
if (!isset($cache[$word])) {
|
|
|
62 |
$word = preg_replace('/[$]/', '', $word);
|
|
|
63 |
$classify = preg_replace_callback('~(_?)([-_])([\w])~', array("Doctrine_Inflector", "classifyCallback"), ucfirst(strtolower($word)));
|
|
|
64 |
$cache[$word] = $classify;
|
|
|
65 |
}
|
|
|
66 |
return $cache[$word];
|
|
|
67 |
}
|
|
|
68 |
|
|
|
69 |
/**
|
|
|
70 |
* Callback function to classify a classname properly.
|
|
|
71 |
*
|
|
|
72 |
* @param array $matches An array of matches from a pcre_replace call
|
|
|
73 |
* @return string $string A string with matches 1 and mathces 3 in upper case.
|
|
|
74 |
*/
|
|
|
75 |
public static function classifyCallback($matches)
|
|
|
76 |
{
|
|
|
77 |
return $matches[1] . strtoupper($matches[3]);
|
|
|
78 |
}
|
|
|
79 |
|
|
|
80 |
/**
|
|
|
81 |
* Check if a string has utf7 characters in it
|
|
|
82 |
*
|
|
|
83 |
* By bmorel at ssi dot fr
|
|
|
84 |
*
|
|
|
85 |
* @param string $string
|
|
|
86 |
* @return boolean $bool
|
|
|
87 |
*/
|
|
|
88 |
public static function seemsUtf8($string)
|
|
|
89 |
{
|
|
|
90 |
for ($i = 0; $i < strlen($string); $i++) {
|
|
|
91 |
if (ord($string[$i]) < 0x80) continue; # 0bbbbbbb
|
|
|
92 |
elseif ((ord($string[$i]) & 0xE0) == 0xC0) $n=1; # 110bbbbb
|
|
|
93 |
elseif ((ord($string[$i]) & 0xF0) == 0xE0) $n=2; # 1110bbbb
|
|
|
94 |
elseif ((ord($string[$i]) & 0xF8) == 0xF0) $n=3; # 11110bbb
|
|
|
95 |
elseif ((ord($string[$i]) & 0xFC) == 0xF8) $n=4; # 111110bb
|
|
|
96 |
elseif ((ord($string[$i]) & 0xFE) == 0xFC) $n=5; # 1111110b
|
|
|
97 |
else return false; # Does not match any model
|
|
|
98 |
for ($j=0; $j<$n; $j++) { # n bytes matching 10bbbbbb follow ?
|
|
|
99 |
if ((++$i == strlen($string)) || ((ord($string[$i]) & 0xC0) != 0x80))
|
|
|
100 |
return false;
|
|
|
101 |
}
|
|
|
102 |
}
|
|
|
103 |
return true;
|
|
|
104 |
}
|
|
|
105 |
|
|
|
106 |
/**
|
|
|
107 |
* Remove any illegal characters, accents, etc.
|
|
|
108 |
*
|
|
|
109 |
* @param string $string String to unaccent
|
|
|
110 |
* @return string $string Unaccented string
|
|
|
111 |
*/
|
|
|
112 |
public static function unaccent($string)
|
|
|
113 |
{
|
|
|
114 |
if ( ! preg_match('/[\x80-\xff]/', $string) ) {
|
|
|
115 |
return $string;
|
|
|
116 |
}
|
|
|
117 |
|
|
|
118 |
if (self::seemsUtf8($string)) {
|
|
|
119 |
$chars = array(
|
|
|
120 |
// Decompositions for Latin-1 Supplement
|
|
|
121 |
chr(195).chr(128) => 'A', chr(195).chr(129) => 'A',
|
|
|
122 |
chr(195).chr(130) => 'A', chr(195).chr(131) => 'A',
|
|
|
123 |
chr(195).chr(132) => 'A', chr(195).chr(133) => 'A',
|
|
|
124 |
chr(195).chr(135) => 'C', chr(195).chr(136) => 'E',
|
|
|
125 |
chr(195).chr(137) => 'E', chr(195).chr(138) => 'E',
|
|
|
126 |
chr(195).chr(139) => 'E', chr(195).chr(140) => 'I',
|
|
|
127 |
chr(195).chr(141) => 'I', chr(195).chr(142) => 'I',
|
|
|
128 |
chr(195).chr(143) => 'I', chr(195).chr(145) => 'N',
|
|
|
129 |
chr(195).chr(146) => 'O', chr(195).chr(147) => 'O',
|
|
|
130 |
chr(195).chr(148) => 'O', chr(195).chr(149) => 'O',
|
|
|
131 |
chr(195).chr(150) => 'O', chr(195).chr(153) => 'U',
|
|
|
132 |
chr(195).chr(154) => 'U', chr(195).chr(155) => 'U',
|
|
|
133 |
chr(195).chr(156) => 'U', chr(195).chr(157) => 'Y',
|
|
|
134 |
chr(195).chr(159) => 's', chr(195).chr(160) => 'a',
|
|
|
135 |
chr(195).chr(161) => 'a', chr(195).chr(162) => 'a',
|
|
|
136 |
chr(195).chr(163) => 'a', chr(195).chr(164) => 'a',
|
|
|
137 |
chr(195).chr(165) => 'a', chr(195).chr(167) => 'c',
|
|
|
138 |
chr(195).chr(168) => 'e', chr(195).chr(169) => 'e',
|
|
|
139 |
chr(195).chr(170) => 'e', chr(195).chr(171) => 'e',
|
|
|
140 |
chr(195).chr(172) => 'i', chr(195).chr(173) => 'i',
|
|
|
141 |
chr(195).chr(174) => 'i', chr(195).chr(175) => 'i',
|
|
|
142 |
chr(195).chr(177) => 'n', chr(195).chr(178) => 'o',
|
|
|
143 |
chr(195).chr(179) => 'o', chr(195).chr(180) => 'o',
|
|
|
144 |
chr(195).chr(181) => 'o', chr(195).chr(182) => 'o',
|
|
|
145 |
chr(195).chr(182) => 'o', chr(195).chr(185) => 'u',
|
|
|
146 |
chr(195).chr(186) => 'u', chr(195).chr(187) => 'u',
|
|
|
147 |
chr(195).chr(188) => 'u', chr(195).chr(189) => 'y',
|
|
|
148 |
chr(195).chr(191) => 'y',
|
|
|
149 |
// Decompositions for Latin Extended-A
|
|
|
150 |
chr(196).chr(128) => 'A', chr(196).chr(129) => 'a',
|
|
|
151 |
chr(196).chr(130) => 'A', chr(196).chr(131) => 'a',
|
|
|
152 |
chr(196).chr(132) => 'A', chr(196).chr(133) => 'a',
|
|
|
153 |
chr(196).chr(134) => 'C', chr(196).chr(135) => 'c',
|
|
|
154 |
chr(196).chr(136) => 'C', chr(196).chr(137) => 'c',
|
|
|
155 |
chr(196).chr(138) => 'C', chr(196).chr(139) => 'c',
|
|
|
156 |
chr(196).chr(140) => 'C', chr(196).chr(141) => 'c',
|
|
|
157 |
chr(196).chr(142) => 'D', chr(196).chr(143) => 'd',
|
|
|
158 |
chr(196).chr(144) => 'D', chr(196).chr(145) => 'd',
|
|
|
159 |
chr(196).chr(146) => 'E', chr(196).chr(147) => 'e',
|
|
|
160 |
chr(196).chr(148) => 'E', chr(196).chr(149) => 'e',
|
|
|
161 |
chr(196).chr(150) => 'E', chr(196).chr(151) => 'e',
|
|
|
162 |
chr(196).chr(152) => 'E', chr(196).chr(153) => 'e',
|
|
|
163 |
chr(196).chr(154) => 'E', chr(196).chr(155) => 'e',
|
|
|
164 |
chr(196).chr(156) => 'G', chr(196).chr(157) => 'g',
|
|
|
165 |
chr(196).chr(158) => 'G', chr(196).chr(159) => 'g',
|
|
|
166 |
chr(196).chr(160) => 'G', chr(196).chr(161) => 'g',
|
|
|
167 |
chr(196).chr(162) => 'G', chr(196).chr(163) => 'g',
|
|
|
168 |
chr(196).chr(164) => 'H', chr(196).chr(165) => 'h',
|
|
|
169 |
chr(196).chr(166) => 'H', chr(196).chr(167) => 'h',
|
|
|
170 |
chr(196).chr(168) => 'I', chr(196).chr(169) => 'i',
|
|
|
171 |
chr(196).chr(170) => 'I', chr(196).chr(171) => 'i',
|
|
|
172 |
chr(196).chr(172) => 'I', chr(196).chr(173) => 'i',
|
|
|
173 |
chr(196).chr(174) => 'I', chr(196).chr(175) => 'i',
|
|
|
174 |
chr(196).chr(176) => 'I', chr(196).chr(177) => 'i',
|
|
|
175 |
chr(196).chr(178) => 'IJ',chr(196).chr(179) => 'ij',
|
|
|
176 |
chr(196).chr(180) => 'J', chr(196).chr(181) => 'j',
|
|
|
177 |
chr(196).chr(182) => 'K', chr(196).chr(183) => 'k',
|
|
|
178 |
chr(196).chr(184) => 'k', chr(196).chr(185) => 'L',
|
|
|
179 |
chr(196).chr(186) => 'l', chr(196).chr(187) => 'L',
|
|
|
180 |
chr(196).chr(188) => 'l', chr(196).chr(189) => 'L',
|
|
|
181 |
chr(196).chr(190) => 'l', chr(196).chr(191) => 'L',
|
|
|
182 |
chr(197).chr(128) => 'l', chr(197).chr(129) => 'L',
|
|
|
183 |
chr(197).chr(130) => 'l', chr(197).chr(131) => 'N',
|
|
|
184 |
chr(197).chr(132) => 'n', chr(197).chr(133) => 'N',
|
|
|
185 |
chr(197).chr(134) => 'n', chr(197).chr(135) => 'N',
|
|
|
186 |
chr(197).chr(136) => 'n', chr(197).chr(137) => 'N',
|
|
|
187 |
chr(197).chr(138) => 'n', chr(197).chr(139) => 'N',
|
|
|
188 |
chr(197).chr(140) => 'O', chr(197).chr(141) => 'o',
|
|
|
189 |
chr(197).chr(142) => 'O', chr(197).chr(143) => 'o',
|
|
|
190 |
chr(197).chr(144) => 'O', chr(197).chr(145) => 'o',
|
|
|
191 |
chr(197).chr(146) => 'OE',chr(197).chr(147) => 'oe',
|
|
|
192 |
chr(197).chr(148) => 'R', chr(197).chr(149) => 'r',
|
|
|
193 |
chr(197).chr(150) => 'R', chr(197).chr(151) => 'r',
|
|
|
194 |
chr(197).chr(152) => 'R', chr(197).chr(153) => 'r',
|
|
|
195 |
chr(197).chr(154) => 'S', chr(197).chr(155) => 's',
|
|
|
196 |
chr(197).chr(156) => 'S', chr(197).chr(157) => 's',
|
|
|
197 |
chr(197).chr(158) => 'S', chr(197).chr(159) => 's',
|
|
|
198 |
chr(197).chr(160) => 'S', chr(197).chr(161) => 's',
|
|
|
199 |
chr(197).chr(162) => 'T', chr(197).chr(163) => 't',
|
|
|
200 |
chr(197).chr(164) => 'T', chr(197).chr(165) => 't',
|
|
|
201 |
chr(197).chr(166) => 'T', chr(197).chr(167) => 't',
|
|
|
202 |
chr(197).chr(168) => 'U', chr(197).chr(169) => 'u',
|
|
|
203 |
chr(197).chr(170) => 'U', chr(197).chr(171) => 'u',
|
|
|
204 |
chr(197).chr(172) => 'U', chr(197).chr(173) => 'u',
|
|
|
205 |
chr(197).chr(174) => 'U', chr(197).chr(175) => 'u',
|
|
|
206 |
chr(197).chr(176) => 'U', chr(197).chr(177) => 'u',
|
|
|
207 |
chr(197).chr(178) => 'U', chr(197).chr(179) => 'u',
|
|
|
208 |
chr(197).chr(180) => 'W', chr(197).chr(181) => 'w',
|
|
|
209 |
chr(197).chr(182) => 'Y', chr(197).chr(183) => 'y',
|
|
|
210 |
chr(197).chr(184) => 'Y', chr(197).chr(185) => 'Z',
|
|
|
211 |
chr(197).chr(186) => 'z', chr(197).chr(187) => 'Z',
|
|
|
212 |
chr(197).chr(188) => 'z', chr(197).chr(189) => 'Z',
|
|
|
213 |
chr(197).chr(190) => 'z', chr(197).chr(191) => 's',
|
|
|
214 |
// Euro Sign
|
|
|
215 |
chr(226).chr(130).chr(172) => 'E',
|
|
|
216 |
// GBP (Pound) Sign
|
|
|
217 |
chr(194).chr(163) => '',
|
|
|
218 |
'Ä' => 'Ae', 'ä' => 'ae', 'Ü' => 'Ue', 'ü' => 'ue',
|
|
|
219 |
'Ö' => 'Oe', 'ö' => 'oe', 'ß' => 'ss',
|
|
|
220 |
// Norwegian characters
|
|
|
221 |
'Å'=>'Aa','Æ'=>'Ae','Ø'=>'O','æ'=>'a','ø'=>'o','å'=>'aa'
|
|
|
222 |
);
|
|
|
223 |
|
|
|
224 |
$string = strtr($string, $chars);
|
|
|
225 |
} else {
|
|
|
226 |
// Assume ISO-8859-1 if not UTF-8
|
|
|
227 |
$chars['in'] = chr(128).chr(131).chr(138).chr(142).chr(154).chr(158)
|
|
|
228 |
.chr(159).chr(162).chr(165).chr(181).chr(192).chr(193).chr(194)
|
|
|
229 |
.chr(195).chr(196).chr(197).chr(199).chr(200).chr(201).chr(202)
|
|
|
230 |
.chr(203).chr(204).chr(205).chr(206).chr(207).chr(209).chr(210)
|
|
|
231 |
.chr(211).chr(212).chr(213).chr(214).chr(216).chr(217).chr(218)
|
|
|
232 |
.chr(219).chr(220).chr(221).chr(224).chr(225).chr(226).chr(227)
|
|
|
233 |
.chr(228).chr(229).chr(231).chr(232).chr(233).chr(234).chr(235)
|
|
|
234 |
.chr(236).chr(237).chr(238).chr(239).chr(241).chr(242).chr(243)
|
|
|
235 |
.chr(244).chr(245).chr(246).chr(248).chr(249).chr(250).chr(251)
|
|
|
236 |
.chr(252).chr(253).chr(255);
|
|
|
237 |
|
|
|
238 |
$chars['out'] = "EfSZszYcYuAAAAAACEEEEIIIINOOOOOOUUUUYaaaaaaceeeeiiiinoooooouuuuyy";
|
|
|
239 |
|
|
|
240 |
$string = strtr($string, $chars['in'], $chars['out']);
|
|
|
241 |
$doubleChars['in'] = array(chr(140), chr(156), chr(198), chr(208), chr(222), chr(223), chr(230), chr(240), chr(254));
|
|
|
242 |
$doubleChars['out'] = array('OE', 'oe', 'AE', 'DH', 'TH', 'ss', 'ae', 'dh', 'th');
|
|
|
243 |
$string = str_replace($doubleChars['in'], $doubleChars['out'], $string);
|
|
|
244 |
}
|
|
|
245 |
|
|
|
246 |
return $string;
|
|
|
247 |
}
|
|
|
248 |
|
|
|
249 |
/**
|
|
|
250 |
* Convert any passed string to a url friendly string. Converts 'My first blog post' to 'my-first-blog-post'
|
|
|
251 |
*
|
|
|
252 |
* @param string $text Text to urlize
|
|
|
253 |
* @return string $text Urlized text
|
|
|
254 |
*/
|
|
|
255 |
public static function urlize($text)
|
|
|
256 |
{
|
|
|
257 |
// Remove all non url friendly characters with the unaccent function
|
|
|
258 |
$text = self::unaccent($text);
|
|
|
259 |
|
|
|
260 |
if (function_exists('mb_strtolower'))
|
|
|
261 |
{
|
|
|
262 |
$text = mb_strtolower($text);
|
|
|
263 |
} else {
|
|
|
264 |
$text = strtolower($text);
|
|
|
265 |
}
|
|
|
266 |
|
|
|
267 |
// Remove all none word characters
|
|
|
268 |
$text = preg_replace('/\W/', ' ', $text);
|
|
|
269 |
|
|
|
270 |
// More stripping. Replace spaces with dashes
|
|
|
271 |
$text = strtolower(preg_replace('/[^A-Z^a-z^0-9^\/]+/', '-',
|
|
|
272 |
preg_replace('/([a-z\d])([A-Z])/', '\1_\2',
|
|
|
273 |
preg_replace('/([A-Z]+)([A-Z][a-z])/', '\1_\2',
|
|
|
274 |
preg_replace('/::/', '/', $text)))));
|
|
|
275 |
|
|
|
276 |
return trim($text, '-');
|
|
|
277 |
}
|
|
|
278 |
}
|