PageRenderTime 124ms CodeModel.GetById 10ms RepoModel.GetById 0ms app.codeStats 0ms

/extensions/behaviors/SluggableBehavior/Doctrine_Inflector.php

https://bitbucket.org/visualappeal/yii-sm-project
PHP | 320 lines | 211 code | 17 blank | 92 comment | 19 complexity | 3ca4da2e011b62b02a4c15f9cd642f7a MD5 | raw file
  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. * Doctrine inflector has static methods for inflecting text
  23. *
  24. * The methods in these classes are from several different sources collected
  25. * across several different php projects and several different authors. The
  26. * original author names and emails are not known
  27. *
  28. * @package Doctrine
  29. * @subpackage Inflector
  30. * @author Konsta Vesterinen <kvesteri@cc.hut.fi>
  31. * @author Jonathan H. Wage <jonwage@gmail.com>
  32. * @license http://www.opensource.org/licenses/lgpl-license.php LGPL
  33. * @version $Revision: 3189 $
  34. * @link www.doctrine-project.org
  35. * @since 1.0
  36. * @category Helper
  37. */
  38. class Doctrine_Inflector
  39. {
  40. /**
  41. * Convert word in to the format for a Doctrine table name.
  42. * Converts 'ModelName' to 'model_name'
  43. *
  44. * @param string $word Word to tableize
  45. *
  46. * @return string $word Tableized word
  47. */
  48. public static function tableize($word)
  49. {
  50. return strtolower(preg_replace('~(?<=\\w)([A-Z])~', '_$1', $word));
  51. }
  52. /**
  53. * Convert a word in to the format for a Doctrine class name.
  54. * Converts 'table_name' to 'TableName'
  55. *
  56. * @param string $word Word to classify
  57. *
  58. * @return string $word Classified word
  59. */
  60. public static function classify($word)
  61. {
  62. static $cache = array();
  63. if (!isset($cache[$word])) {
  64. $word = preg_replace('/[$]/', '', $word);
  65. $classify = preg_replace_callback(
  66. '~(_?)([-_])([\w])~',
  67. array("Doctrine_Inflector", "classifyCallback"),
  68. ucfirst(strtolower($word))
  69. );
  70. $cache[$word] = $classify;
  71. }
  72. return $cache[$word];
  73. }
  74. /**
  75. * Callback function to classify a classname properly.
  76. *
  77. * @param array $matches An array of matches from a pcre_replace call
  78. *
  79. * @return string $string String with matches 1 and 3 in upper case.
  80. */
  81. public static function classifyCallback($matches)
  82. {
  83. return $matches[1] . strtoupper($matches[3]);
  84. }
  85. /**
  86. * Check if a string has utf7 characters in it
  87. *
  88. * By bmorel at ssi dot fr
  89. *
  90. * @param string $string String to check
  91. *
  92. * @return boolean
  93. */
  94. public static function seemsUtf8($string)
  95. {
  96. for ($i = 0; $i < strlen($string); $i++) {
  97. if (ord($string[$i]) < 0x80) {
  98. continue; // 0bbbbbbb
  99. } elseif ((ord($string[$i]) & 0xE0) == 0xC0) {
  100. $n=1; // 110bbbbb
  101. } elseif ((ord($string[$i]) & 0xF0) == 0xE0) {
  102. $n=2; // 1110bbbb
  103. } elseif ((ord($string[$i]) & 0xF8) == 0xF0) {
  104. $n=3; // 11110bbb
  105. } elseif ((ord($string[$i]) & 0xFC) == 0xF8) {
  106. $n=4; // 111110bb
  107. } elseif ((ord($string[$i]) & 0xFE) == 0xFC) {
  108. $n=5; // 1111110b
  109. } else {
  110. return false; // Does not match any model
  111. }
  112. for ($j=0; $j<$n; $j++) { // n bytes matching 10bbbbbb follow ?
  113. if ((++$i == strlen($string))
  114. || ((ord($string[$i]) & 0xC0) != 0x80)
  115. ) {
  116. return false;
  117. }
  118. }
  119. }
  120. return true;
  121. }
  122. /**
  123. * Remove any illegal characters, accents, etc.
  124. *
  125. * @param string $string String to unaccent
  126. *
  127. * @return string $string Unaccented string
  128. */
  129. public static function unaccent($string)
  130. {
  131. if ( ! preg_match('/[\x80-\xff]/', $string) ) {
  132. return $string;
  133. }
  134. if (self::seemsUtf8($string)) {
  135. $chars = array(
  136. // Decompositions for Latin-1 Supplement
  137. chr(195).chr(128) => 'A', chr(195).chr(129) => 'A',
  138. chr(195).chr(130) => 'A', chr(195).chr(131) => 'A',
  139. chr(195).chr(132) => 'A', chr(195).chr(133) => 'A',
  140. chr(195).chr(135) => 'C', chr(195).chr(136) => 'E',
  141. chr(195).chr(137) => 'E', chr(195).chr(138) => 'E',
  142. chr(195).chr(139) => 'E', chr(195).chr(140) => 'I',
  143. chr(195).chr(141) => 'I', chr(195).chr(142) => 'I',
  144. chr(195).chr(143) => 'I', chr(195).chr(145) => 'N',
  145. chr(195).chr(146) => 'O', chr(195).chr(147) => 'O',
  146. chr(195).chr(148) => 'O', chr(195).chr(149) => 'O',
  147. chr(195).chr(150) => 'O', chr(195).chr(153) => 'U',
  148. chr(195).chr(154) => 'U', chr(195).chr(155) => 'U',
  149. chr(195).chr(156) => 'U', chr(195).chr(157) => 'Y',
  150. chr(195).chr(159) => 's', chr(195).chr(160) => 'a',
  151. chr(195).chr(161) => 'a', chr(195).chr(162) => 'a',
  152. chr(195).chr(163) => 'a', chr(195).chr(164) => 'a',
  153. chr(195).chr(165) => 'a', chr(195).chr(167) => 'c',
  154. chr(195).chr(168) => 'e', chr(195).chr(169) => 'e',
  155. chr(195).chr(170) => 'e', chr(195).chr(171) => 'e',
  156. chr(195).chr(172) => 'i', chr(195).chr(173) => 'i',
  157. chr(195).chr(174) => 'i', chr(195).chr(175) => 'i',
  158. chr(195).chr(177) => 'n', chr(195).chr(178) => 'o',
  159. chr(195).chr(179) => 'o', chr(195).chr(180) => 'o',
  160. chr(195).chr(181) => 'o', chr(195).chr(182) => 'o',
  161. chr(195).chr(182) => 'o', chr(195).chr(185) => 'u',
  162. chr(195).chr(186) => 'u', chr(195).chr(187) => 'u',
  163. chr(195).chr(188) => 'u', chr(195).chr(189) => 'y',
  164. chr(195).chr(191) => 'y',
  165. // Decompositions for Latin Extended-A
  166. chr(196).chr(128) => 'A', chr(196).chr(129) => 'a',
  167. chr(196).chr(130) => 'A', chr(196).chr(131) => 'a',
  168. chr(196).chr(132) => 'A', chr(196).chr(133) => 'a',
  169. chr(196).chr(134) => 'C', chr(196).chr(135) => 'c',
  170. chr(196).chr(136) => 'C', chr(196).chr(137) => 'c',
  171. chr(196).chr(138) => 'C', chr(196).chr(139) => 'c',
  172. chr(196).chr(140) => 'C', chr(196).chr(141) => 'c',
  173. chr(196).chr(142) => 'D', chr(196).chr(143) => 'd',
  174. chr(196).chr(144) => 'D', chr(196).chr(145) => 'd',
  175. chr(196).chr(146) => 'E', chr(196).chr(147) => 'e',
  176. chr(196).chr(148) => 'E', chr(196).chr(149) => 'e',
  177. chr(196).chr(150) => 'E', chr(196).chr(151) => 'e',
  178. chr(196).chr(152) => 'E', chr(196).chr(153) => 'e',
  179. chr(196).chr(154) => 'E', chr(196).chr(155) => 'e',
  180. chr(196).chr(156) => 'G', chr(196).chr(157) => 'g',
  181. chr(196).chr(158) => 'G', chr(196).chr(159) => 'g',
  182. chr(196).chr(160) => 'G', chr(196).chr(161) => 'g',
  183. chr(196).chr(162) => 'G', chr(196).chr(163) => 'g',
  184. chr(196).chr(164) => 'H', chr(196).chr(165) => 'h',
  185. chr(196).chr(166) => 'H', chr(196).chr(167) => 'h',
  186. chr(196).chr(168) => 'I', chr(196).chr(169) => 'i',
  187. chr(196).chr(170) => 'I', chr(196).chr(171) => 'i',
  188. chr(196).chr(172) => 'I', chr(196).chr(173) => 'i',
  189. chr(196).chr(174) => 'I', chr(196).chr(175) => 'i',
  190. chr(196).chr(176) => 'I', chr(196).chr(177) => 'i',
  191. chr(196).chr(178) => 'IJ',chr(196).chr(179) => 'ij',
  192. chr(196).chr(180) => 'J', chr(196).chr(181) => 'j',
  193. chr(196).chr(182) => 'K', chr(196).chr(183) => 'k',
  194. chr(196).chr(184) => 'k', chr(196).chr(185) => 'L',
  195. chr(196).chr(186) => 'l', chr(196).chr(187) => 'L',
  196. chr(196).chr(188) => 'l', chr(196).chr(189) => 'L',
  197. chr(196).chr(190) => 'l', chr(196).chr(191) => 'L',
  198. chr(197).chr(128) => 'l', chr(197).chr(129) => 'L',
  199. chr(197).chr(130) => 'l', chr(197).chr(131) => 'N',
  200. chr(197).chr(132) => 'n', chr(197).chr(133) => 'N',
  201. chr(197).chr(134) => 'n', chr(197).chr(135) => 'N',
  202. chr(197).chr(136) => 'n', chr(197).chr(137) => 'N',
  203. chr(197).chr(138) => 'n', chr(197).chr(139) => 'N',
  204. chr(197).chr(140) => 'O', chr(197).chr(141) => 'o',
  205. chr(197).chr(142) => 'O', chr(197).chr(143) => 'o',
  206. chr(197).chr(144) => 'O', chr(197).chr(145) => 'o',
  207. chr(197).chr(146) => 'OE',chr(197).chr(147) => 'oe',
  208. chr(197).chr(148) => 'R', chr(197).chr(149) => 'r',
  209. chr(197).chr(150) => 'R', chr(197).chr(151) => 'r',
  210. chr(197).chr(152) => 'R', chr(197).chr(153) => 'r',
  211. chr(197).chr(154) => 'S', chr(197).chr(155) => 's',
  212. chr(197).chr(156) => 'S', chr(197).chr(157) => 's',
  213. chr(197).chr(158) => 'S', chr(197).chr(159) => 's',
  214. chr(197).chr(160) => 'S', chr(197).chr(161) => 's',
  215. chr(197).chr(162) => 'T', chr(197).chr(163) => 't',
  216. chr(197).chr(164) => 'T', chr(197).chr(165) => 't',
  217. chr(197).chr(166) => 'T', chr(197).chr(167) => 't',
  218. chr(197).chr(168) => 'U', chr(197).chr(169) => 'u',
  219. chr(197).chr(170) => 'U', chr(197).chr(171) => 'u',
  220. chr(197).chr(172) => 'U', chr(197).chr(173) => 'u',
  221. chr(197).chr(174) => 'U', chr(197).chr(175) => 'u',
  222. chr(197).chr(176) => 'U', chr(197).chr(177) => 'u',
  223. chr(197).chr(178) => 'U', chr(197).chr(179) => 'u',
  224. chr(197).chr(180) => 'W', chr(197).chr(181) => 'w',
  225. chr(197).chr(182) => 'Y', chr(197).chr(183) => 'y',
  226. chr(197).chr(184) => 'Y', chr(197).chr(185) => 'Z',
  227. chr(197).chr(186) => 'z', chr(197).chr(187) => 'Z',
  228. chr(197).chr(188) => 'z', chr(197).chr(189) => 'Z',
  229. chr(197).chr(190) => 'z', chr(197).chr(191) => 's',
  230. // Euro Sign
  231. chr(226).chr(130).chr(172) => 'E',
  232. // GBP (Pound) Sign
  233. chr(194).chr(163) => '',
  234. 'Ä' => 'Ae', 'ä' => 'ae', 'Ü' => 'Ue', 'ü' => 'ue',
  235. 'Ö' => 'Oe', 'ö' => 'oe', 'ß' => 'ss',
  236. // Norwegian characters
  237. 'Å'=>'Aa','Æ'=>'Ae','Ø'=>'O','æ'=>'a','ø'=>'o','å'=>'aa'
  238. );
  239. $string = strtr($string, $chars);
  240. } else {
  241. // Assume ISO-8859-1 if not UTF-8
  242. $chars['in'] = chr(128).chr(131).chr(138).chr(142).chr(154).chr(158)
  243. .chr(159).chr(162).chr(165).chr(181).chr(192).chr(193).chr(194)
  244. .chr(195).chr(196).chr(197).chr(199).chr(200).chr(201).chr(202)
  245. .chr(203).chr(204).chr(205).chr(206).chr(207).chr(209).chr(210)
  246. .chr(211).chr(212).chr(213).chr(214).chr(216).chr(217).chr(218)
  247. .chr(219).chr(220).chr(221).chr(224).chr(225).chr(226).chr(227)
  248. .chr(228).chr(229).chr(231).chr(232).chr(233).chr(234).chr(235)
  249. .chr(236).chr(237).chr(238).chr(239).chr(241).chr(242).chr(243)
  250. .chr(244).chr(245).chr(246).chr(248).chr(249).chr(250).chr(251)
  251. .chr(252).chr(253).chr(255);
  252. $chars['out'] = 'EfSZszYcYuAAAAAACEEEEIIIINOOOOOOUUUUYa'
  253. . 'aaaaaceeeeiiiinoooooouuuuyy';
  254. $string = strtr($string, $chars['in'], $chars['out']);
  255. $doubleChars['in'] = array(
  256. chr(140), chr(156), chr(198),
  257. chr(208), chr(222), chr(223),
  258. chr(230), chr(240), chr(254));
  259. $doubleChars['out'] = array(
  260. 'OE', 'oe', 'AE', 'DH', 'TH', 'ss', 'ae', 'dh', 'th'
  261. );
  262. $string = str_replace(
  263. $doubleChars['in'],
  264. $doubleChars['out'],
  265. $string
  266. );
  267. }
  268. return $string;
  269. }
  270. /**
  271. * Convert any passed string to a url friendly string.
  272. * Converts 'My first blog post' to 'my-first-blog-post'
  273. *
  274. * @param string $text Text to urlize
  275. *
  276. * @return string $text Urlized text
  277. */
  278. public static function urlize($text)
  279. {
  280. // Remove all non url friendly characters with the unaccent function
  281. $text = self::unaccent($text);
  282. if (function_exists('mb_strtolower')) {
  283. $text = mb_strtolower($text);
  284. } else {
  285. $text = strtolower($text);
  286. }
  287. // Remove all none word characters
  288. $text = preg_replace('/\W/', ' ', $text);
  289. // More stripping. Replace spaces with dashes
  290. $text = strtolower(
  291. preg_replace(
  292. '/[^A-Z^a-z^0-9^\/]+/', '-', preg_replace(
  293. '/([a-z\d])([A-Z])/', '\1_\2', preg_replace(
  294. '/([A-Z]+)([A-Z][a-z])/', '\1_\2', preg_replace(
  295. '/::/', '/', $text
  296. )
  297. )
  298. )
  299. )
  300. );
  301. return trim($text, '-');
  302. }
  303. }