Duplicate code is one of the most pungent code smells. A rule that is often used is to re-structure code once it is duplicated in three or more places.
Common duplication problems, and corresponding solutions are:
Complex classes like Unicode often do a lot of different things. To break such a class down, we need to identify a cohesive component within that class. A common approach to find such a component is to look for fields/methods that share the same prefixes, or suffixes. You can also have a look at the cohesion graph to spot any un-connected, or weakly-connected components.
Once you have determined the fields that belong together, you can apply the Extract Class refactoring. If the component makes sense as a sub-class, Extract Subclass is also a candidate, and is often faster.
While breaking up the class, it is a good idea to analyze how other classes use Unicode, and based on these observations, apply Extract Interface, too.
1 | <?php |
||
15 | class Unicode { |
||
16 | |||
17 | /** |
||
18 | * Matches Unicode characters that are word boundaries. |
||
19 | * |
||
20 | * Characters with the following General_category (gc) property values are used |
||
21 | * as word boundaries. While this does not fully conform to the Word Boundaries |
||
22 | * algorithm described in http://unicode.org/reports/tr29, as PCRE does not |
||
23 | * contain the Word_Break property table, this simpler algorithm has to do. |
||
24 | * - Cc, Cf, Cn, Co, Cs: Other. |
||
25 | * - Pc, Pd, Pe, Pf, Pi, Po, Ps: Punctuation. |
||
26 | * - Sc, Sk, Sm, So: Symbols. |
||
27 | * - Zl, Zp, Zs: Separators. |
||
28 | * |
||
29 | * Non-boundary characters include the following General_category (gc) property |
||
30 | * values: |
||
31 | * - Ll, Lm, Lo, Lt, Lu: Letters. |
||
32 | * - Mc, Me, Mn: Combining Marks. |
||
33 | * - Nd, Nl, No: Numbers. |
||
34 | * |
||
35 | * Note that the PCRE property matcher is not used because we wanted to be |
||
36 | * compatible with Unicode 5.2.0 regardless of the PCRE version used (and any |
||
37 | * bugs in PCRE property tables). |
||
38 | * |
||
39 | * @see http://unicode.org/glossary |
||
40 | */ |
||
41 | const PREG_CLASS_WORD_BOUNDARY = <<<'EOD' |
||
42 | \x{0}-\x{2F}\x{3A}-\x{40}\x{5B}-\x{60}\x{7B}-\x{A9}\x{AB}-\x{B1}\x{B4} |
||
43 | \x{B6}-\x{B8}\x{BB}\x{BF}\x{D7}\x{F7}\x{2C2}-\x{2C5}\x{2D2}-\x{2DF} |
||
44 | \x{2E5}-\x{2EB}\x{2ED}\x{2EF}-\x{2FF}\x{375}\x{37E}-\x{385}\x{387}\x{3F6} |
||
45 | \x{482}\x{55A}-\x{55F}\x{589}-\x{58A}\x{5BE}\x{5C0}\x{5C3}\x{5C6} |
||
46 | \x{5F3}-\x{60F}\x{61B}-\x{61F}\x{66A}-\x{66D}\x{6D4}\x{6DD}\x{6E9} |
||
47 | \x{6FD}-\x{6FE}\x{700}-\x{70F}\x{7F6}-\x{7F9}\x{830}-\x{83E} |
||
48 | \x{964}-\x{965}\x{970}\x{9F2}-\x{9F3}\x{9FA}-\x{9FB}\x{AF1}\x{B70} |
||
49 | \x{BF3}-\x{BFA}\x{C7F}\x{CF1}-\x{CF2}\x{D79}\x{DF4}\x{E3F}\x{E4F} |
||
50 | \x{E5A}-\x{E5B}\x{F01}-\x{F17}\x{F1A}-\x{F1F}\x{F34}\x{F36}\x{F38} |
||
51 | \x{F3A}-\x{F3D}\x{F85}\x{FBE}-\x{FC5}\x{FC7}-\x{FD8}\x{104A}-\x{104F} |
||
52 | \x{109E}-\x{109F}\x{10FB}\x{1360}-\x{1368}\x{1390}-\x{1399}\x{1400} |
||
53 | \x{166D}-\x{166E}\x{1680}\x{169B}-\x{169C}\x{16EB}-\x{16ED} |
||
54 | \x{1735}-\x{1736}\x{17B4}-\x{17B5}\x{17D4}-\x{17D6}\x{17D8}-\x{17DB} |
||
55 | \x{1800}-\x{180A}\x{180E}\x{1940}-\x{1945}\x{19DE}-\x{19FF} |
||
56 | \x{1A1E}-\x{1A1F}\x{1AA0}-\x{1AA6}\x{1AA8}-\x{1AAD}\x{1B5A}-\x{1B6A} |
||
57 | \x{1B74}-\x{1B7C}\x{1C3B}-\x{1C3F}\x{1C7E}-\x{1C7F}\x{1CD3}\x{1FBD} |
||
58 | \x{1FBF}-\x{1FC1}\x{1FCD}-\x{1FCF}\x{1FDD}-\x{1FDF}\x{1FED}-\x{1FEF} |
||
59 | \x{1FFD}-\x{206F}\x{207A}-\x{207E}\x{208A}-\x{208E}\x{20A0}-\x{20B8} |
||
60 | \x{2100}-\x{2101}\x{2103}-\x{2106}\x{2108}-\x{2109}\x{2114} |
||
61 | \x{2116}-\x{2118}\x{211E}-\x{2123}\x{2125}\x{2127}\x{2129}\x{212E} |
||
62 | \x{213A}-\x{213B}\x{2140}-\x{2144}\x{214A}-\x{214D}\x{214F} |
||
63 | \x{2190}-\x{244A}\x{249C}-\x{24E9}\x{2500}-\x{2775}\x{2794}-\x{2B59} |
||
64 | \x{2CE5}-\x{2CEA}\x{2CF9}-\x{2CFC}\x{2CFE}-\x{2CFF}\x{2E00}-\x{2E2E} |
||
65 | \x{2E30}-\x{3004}\x{3008}-\x{3020}\x{3030}\x{3036}-\x{3037} |
||
66 | \x{303D}-\x{303F}\x{309B}-\x{309C}\x{30A0}\x{30FB}\x{3190}-\x{3191} |
||
67 | \x{3196}-\x{319F}\x{31C0}-\x{31E3}\x{3200}-\x{321E}\x{322A}-\x{3250} |
||
68 | \x{3260}-\x{327F}\x{328A}-\x{32B0}\x{32C0}-\x{33FF}\x{4DC0}-\x{4DFF} |
||
69 | \x{A490}-\x{A4C6}\x{A4FE}-\x{A4FF}\x{A60D}-\x{A60F}\x{A673}\x{A67E} |
||
70 | \x{A6F2}-\x{A716}\x{A720}-\x{A721}\x{A789}-\x{A78A}\x{A828}-\x{A82B} |
||
71 | \x{A836}-\x{A839}\x{A874}-\x{A877}\x{A8CE}-\x{A8CF}\x{A8F8}-\x{A8FA} |
||
72 | \x{A92E}-\x{A92F}\x{A95F}\x{A9C1}-\x{A9CD}\x{A9DE}-\x{A9DF} |
||
73 | \x{AA5C}-\x{AA5F}\x{AA77}-\x{AA79}\x{AADE}-\x{AADF}\x{ABEB} |
||
74 | \x{E000}-\x{F8FF}\x{FB29}\x{FD3E}-\x{FD3F}\x{FDFC}-\x{FDFD} |
||
75 | \x{FE10}-\x{FE19}\x{FE30}-\x{FE6B}\x{FEFF}-\x{FF0F}\x{FF1A}-\x{FF20} |
||
76 | \x{FF3B}-\x{FF40}\x{FF5B}-\x{FF65}\x{FFE0}-\x{FFFD} |
||
77 | EOD; |
||
78 | |||
79 | /** |
||
80 | * Indicates that standard PHP (emulated) unicode support is being used. |
||
81 | */ |
||
82 | const STATUS_SINGLEBYTE = 0; |
||
83 | |||
84 | /** |
||
85 | * Indicates that full unicode support with the PHP mbstring extension is |
||
86 | * being used. |
||
87 | */ |
||
88 | const STATUS_MULTIBYTE = 1; |
||
89 | |||
90 | /** |
||
91 | * Indicates an error during check for PHP unicode support. |
||
92 | */ |
||
93 | const STATUS_ERROR = -1; |
||
94 | |||
95 | /** |
||
96 | * Holds the multibyte capabilities of the current environment. |
||
97 | * |
||
98 | * @var int |
||
99 | */ |
||
100 | protected static $status = 0; |
||
101 | |||
102 | /** |
||
103 | * Gets the current status of unicode/multibyte support on this environment. |
||
104 | * |
||
105 | * @return int |
||
106 | * The status of multibyte support. It can be one of: |
||
107 | * - \Drupal\Component\Utility\Unicode::STATUS_MULTIBYTE |
||
108 | * Full unicode support using an extension. |
||
109 | * - \Drupal\Component\Utility\Unicode::STATUS_SINGLEBYTE |
||
110 | * Standard PHP (emulated) unicode support. |
||
111 | * - \Drupal\Component\Utility\Unicode::STATUS_ERROR |
||
112 | * An error occurred. No unicode support. |
||
113 | */ |
||
114 | public static function getStatus() { |
||
115 | return static::$status; |
||
116 | } |
||
117 | |||
118 | /** |
||
119 | * Sets the value for multibyte support status for the current environment. |
||
120 | * |
||
121 | * The following status keys are supported: |
||
122 | * - \Drupal\Component\Utility\Unicode::STATUS_MULTIBYTE |
||
123 | * Full unicode support using an extension. |
||
124 | * - \Drupal\Component\Utility\Unicode::STATUS_SINGLEBYTE |
||
125 | * Standard PHP (emulated) unicode support. |
||
126 | * - \Drupal\Component\Utility\Unicode::STATUS_ERROR |
||
127 | * An error occurred. No unicode support. |
||
128 | * |
||
129 | * @param int $status |
||
130 | * The new status of multibyte support. |
||
131 | */ |
||
132 | public static function setStatus($status) { |
||
133 | if (!in_array($status, array(static::STATUS_SINGLEBYTE, static::STATUS_MULTIBYTE, static::STATUS_ERROR))) { |
||
134 | throw new \InvalidArgumentException('Invalid status value for unicode support.'); |
||
135 | } |
||
136 | static::$status = $status; |
||
137 | } |
||
138 | |||
139 | /** |
||
140 | * Checks for Unicode support in PHP and sets the proper settings if possible. |
||
141 | * |
||
142 | * Because of the need to be able to handle text in various encodings, we do |
||
143 | * not support mbstring function overloading. HTTP input/output conversion |
||
144 | * must be disabled for similar reasons. |
||
145 | * |
||
146 | * @return string |
||
147 | * A string identifier of a failed multibyte extension check, if any. |
||
148 | * Otherwise, an empty string. |
||
149 | */ |
||
150 | public static function check() { |
||
151 | // Check for mbstring extension. |
||
152 | if (!function_exists('mb_strlen')) { |
||
153 | static::$status = static::STATUS_SINGLEBYTE; |
||
154 | return 'mb_strlen'; |
||
155 | } |
||
156 | |||
157 | // Check mbstring configuration. |
||
158 | if (ini_get('mbstring.func_overload') != 0) { |
||
159 | static::$status = static::STATUS_ERROR; |
||
160 | return 'mbstring.func_overload'; |
||
161 | } |
||
162 | if (ini_get('mbstring.encoding_translation') != 0) { |
||
163 | static::$status = static::STATUS_ERROR; |
||
164 | return 'mbstring.encoding_translation'; |
||
165 | } |
||
166 | // mbstring.http_input and mbstring.http_output are deprecated and empty by |
||
167 | // default in PHP 5.6. |
||
168 | if (version_compare(PHP_VERSION, '5.6.0') == -1) { |
||
169 | if (ini_get('mbstring.http_input') != 'pass') { |
||
170 | static::$status = static::STATUS_ERROR; |
||
171 | return 'mbstring.http_input'; |
||
172 | } |
||
173 | if (ini_get('mbstring.http_output') != 'pass') { |
||
174 | static::$status = static::STATUS_ERROR; |
||
175 | return 'mbstring.http_output'; |
||
176 | } |
||
177 | } |
||
178 | |||
179 | // Set appropriate configuration. |
||
180 | mb_internal_encoding('utf-8'); |
||
181 | mb_language('uni'); |
||
182 | static::$status = static::STATUS_MULTIBYTE; |
||
183 | return ''; |
||
184 | } |
||
185 | |||
186 | /** |
||
187 | * Decodes UTF byte-order mark (BOM) into the encoding's name. |
||
188 | * |
||
189 | * @param string $data |
||
190 | * The data possibly containing a BOM. This can be the entire contents of |
||
191 | * a file, or just a fragment containing at least the first five bytes. |
||
192 | * |
||
193 | * @return string|bool |
||
194 | * The name of the encoding, or FALSE if no byte order mark was present. |
||
195 | */ |
||
196 | public static function encodingFromBOM($data) { |
||
197 | static $bomMap = array( |
||
198 | "\xEF\xBB\xBF" => 'UTF-8', |
||
199 | "\xFE\xFF" => 'UTF-16BE', |
||
200 | "\xFF\xFE" => 'UTF-16LE', |
||
201 | "\x00\x00\xFE\xFF" => 'UTF-32BE', |
||
202 | "\xFF\xFE\x00\x00" => 'UTF-32LE', |
||
203 | "\x2B\x2F\x76\x38" => 'UTF-7', |
||
204 | "\x2B\x2F\x76\x39" => 'UTF-7', |
||
205 | "\x2B\x2F\x76\x2B" => 'UTF-7', |
||
206 | "\x2B\x2F\x76\x2F" => 'UTF-7', |
||
207 | "\x2B\x2F\x76\x38\x2D" => 'UTF-7', |
||
208 | ); |
||
209 | |||
210 | foreach ($bomMap as $bom => $encoding) { |
||
211 | if (strpos($data, $bom) === 0) { |
||
212 | return $encoding; |
||
213 | } |
||
214 | } |
||
215 | return FALSE; |
||
216 | } |
||
217 | |||
218 | /** |
||
219 | * Converts data to UTF-8. |
||
220 | * |
||
221 | * Requires the iconv, GNU recode or mbstring PHP extension. |
||
222 | * |
||
223 | * @param string $data |
||
224 | * The data to be converted. |
||
225 | * @param string $encoding |
||
226 | * The encoding that the data is in. |
||
227 | * |
||
228 | * @return string|bool |
||
229 | * Converted data or FALSE. |
||
230 | */ |
||
231 | public static function convertToUtf8($data, $encoding) { |
||
232 | if (function_exists('iconv')) { |
||
233 | return @iconv($encoding, 'utf-8', $data); |
||
234 | } |
||
235 | elseif (function_exists('mb_convert_encoding')) { |
||
236 | return @mb_convert_encoding($data, 'utf-8', $encoding); |
||
237 | } |
||
238 | elseif (function_exists('recode_string')) { |
||
239 | return @recode_string($encoding . '..utf-8', $data); |
||
240 | } |
||
241 | // Cannot convert. |
||
242 | return FALSE; |
||
243 | } |
||
244 | |||
245 | /** |
||
246 | * Truncates a UTF-8-encoded string safely to a number of bytes. |
||
247 | * |
||
248 | * If the end position is in the middle of a UTF-8 sequence, it scans backwards |
||
249 | * until the beginning of the byte sequence. |
||
250 | * |
||
251 | * Use this function whenever you want to chop off a string at an unsure |
||
252 | * location. On the other hand, if you're sure that you're splitting on a |
||
253 | * character boundary (e.g. after using strpos() or similar), you can safely |
||
254 | * use substr() instead. |
||
255 | * |
||
256 | * @param string $string |
||
257 | * The string to truncate. |
||
258 | * @param int $len |
||
259 | * An upper limit on the returned string length. |
||
260 | * |
||
261 | * @return string |
||
262 | * The truncated string. |
||
263 | */ |
||
264 | public static function truncateBytes($string, $len) { |
||
265 | if (strlen($string) <= $len) { |
||
266 | return $string; |
||
267 | } |
||
268 | if ((ord($string[$len]) < 0x80) || (ord($string[$len]) >= 0xC0)) { |
||
269 | return substr($string, 0, $len); |
||
270 | } |
||
271 | // Scan backwards to beginning of the byte sequence. |
||
272 | while (--$len >= 0 && ord($string[$len]) >= 0x80 && ord($string[$len]) < 0xC0); |
||
273 | |||
274 | return substr($string, 0, $len); |
||
275 | } |
||
276 | |||
277 | /** |
||
278 | * Counts the number of characters in a UTF-8 string. |
||
279 | * |
||
280 | * This is less than or equal to the byte count. |
||
281 | * |
||
282 | * @param string $text |
||
283 | * The string to run the operation on. |
||
284 | * |
||
285 | * @return int |
||
286 | * The length of the string. |
||
287 | */ |
||
288 | public static function strlen($text) { |
||
289 | if (static::getStatus() == static::STATUS_MULTIBYTE) { |
||
290 | return mb_strlen($text); |
||
291 | } |
||
292 | else { |
||
293 | // Do not count UTF-8 continuation bytes. |
||
294 | return strlen(preg_replace("/[\x80-\xBF]/", '', $text)); |
||
295 | } |
||
296 | } |
||
297 | |||
298 | /** |
||
299 | * Converts a UTF-8 string to uppercase. |
||
300 | * |
||
301 | * @param string $text |
||
302 | * The string to run the operation on. |
||
303 | * |
||
304 | * @return string |
||
305 | * The string in uppercase. |
||
306 | */ |
||
307 | View Code Duplication | public static function strtoupper($text) { |
|
308 | if (static::getStatus() == static::STATUS_MULTIBYTE) { |
||
309 | return mb_strtoupper($text); |
||
310 | } |
||
311 | else { |
||
312 | // Use C-locale for ASCII-only uppercase. |
||
313 | $text = strtoupper($text); |
||
314 | // Case flip Latin-1 accented letters. |
||
315 | $text = preg_replace_callback('/\xC3[\xA0-\xB6\xB8-\xBE]/', '\Drupal\Component\Utility\Unicode::caseFlip', $text); |
||
316 | return $text; |
||
317 | } |
||
318 | } |
||
319 | |||
320 | /** |
||
321 | * Converts a UTF-8 string to lowercase. |
||
322 | * |
||
323 | * @param string $text |
||
324 | * The string to run the operation on. |
||
325 | * |
||
326 | * @return string |
||
327 | * The string in lowercase. |
||
328 | */ |
||
329 | View Code Duplication | public static function strtolower($text) { |
|
330 | if (static::getStatus() == static::STATUS_MULTIBYTE) { |
||
331 | return mb_strtolower($text); |
||
332 | } |
||
333 | else { |
||
334 | // Use C-locale for ASCII-only lowercase. |
||
335 | $text = strtolower($text); |
||
336 | // Case flip Latin-1 accented letters. |
||
337 | $text = preg_replace_callback('/\xC3[\x80-\x96\x98-\x9E]/', '\Drupal\Component\Utility\Unicode::caseFlip', $text); |
||
338 | return $text; |
||
339 | } |
||
340 | } |
||
341 | |||
342 | /** |
||
343 | * Capitalizes the first character of a UTF-8 string. |
||
344 | * |
||
345 | * @param string $text |
||
346 | * The string to convert. |
||
347 | * |
||
348 | * @return string |
||
349 | * The string with the first character as uppercase. |
||
350 | */ |
||
351 | public static function ucfirst($text) { |
||
352 | return static::strtoupper(static::substr($text, 0, 1)) . static::substr($text, 1); |
||
353 | } |
||
354 | |||
355 | /** |
||
356 | * Converts the first character of a UTF-8 string to lowercase. |
||
357 | * |
||
358 | * @param string $text |
||
359 | * The string that will be converted. |
||
360 | * |
||
361 | * @return string |
||
362 | * The string with the first character as lowercase. |
||
363 | * |
||
364 | * @ingroup php_wrappers |
||
365 | */ |
||
366 | public static function lcfirst($text) { |
||
367 | // Note: no mbstring equivalent! |
||
368 | return static::strtolower(static::substr($text, 0, 1)) . static::substr($text, 1); |
||
369 | } |
||
370 | |||
371 | /** |
||
372 | * Capitalizes the first character of each word in a UTF-8 string. |
||
373 | * |
||
374 | * @param string $text |
||
375 | * The text that will be converted. |
||
376 | * |
||
377 | * @return string |
||
378 | * The input $text with each word capitalized. |
||
379 | * |
||
380 | * @ingroup php_wrappers |
||
381 | */ |
||
382 | public static function ucwords($text) { |
||
383 | $regex = '/(^|[' . static::PREG_CLASS_WORD_BOUNDARY . '])([^' . static::PREG_CLASS_WORD_BOUNDARY . '])/u'; |
||
384 | return preg_replace_callback($regex, function(array $matches) { |
||
385 | return $matches[1] . Unicode::strtoupper($matches[2]); |
||
386 | }, $text); |
||
387 | } |
||
388 | |||
389 | /** |
||
390 | * Cuts off a piece of a string based on character indices and counts. |
||
391 | * |
||
392 | * Follows the same behavior as PHP's own substr() function. Note that for |
||
393 | * cutting off a string at a known character/substring location, the usage of |
||
394 | * PHP's normal strpos/substr is safe and much faster. |
||
395 | * |
||
396 | * @param string $text |
||
397 | * The input string. |
||
398 | * @param int $start |
||
399 | * The position at which to start reading. |
||
400 | * @param int $length |
||
401 | * The number of characters to read. |
||
402 | * |
||
403 | * @return string |
||
404 | * The shortened string. |
||
405 | */ |
||
406 | public static function substr($text, $start, $length = NULL) { |
||
492 | |||
493 | /** |
||
494 | * Truncates a UTF-8-encoded string safely to a number of characters. |
||
495 | * |
||
496 | * @param string $string |
||
497 | * The string to truncate. |
||
498 | * @param int $max_length |
||
499 | * An upper limit on the returned string length, including trailing ellipsis |
||
500 | * if $add_ellipsis is TRUE. |
||
501 | * @param bool $wordsafe |
||
502 | * If TRUE, attempt to truncate on a word boundary. Word boundaries are |
||
503 | * spaces, punctuation, and Unicode characters used as word boundaries in |
||
504 | * non-Latin languages; see Unicode::PREG_CLASS_WORD_BOUNDARY for more |
||
505 | * information. If a word boundary cannot be found that would make the length |
||
506 | * of the returned string fall within length guidelines (see parameters |
||
507 | * $max_length and $min_wordsafe_length), word boundaries are ignored. |
||
508 | * @param bool $add_ellipsis |
||
509 | * If TRUE, add '...' to the end of the truncated string (defaults to |
||
510 | * FALSE). The string length will still fall within $max_length. |
||
511 | * @param int $min_wordsafe_length |
||
512 | * If $wordsafe is TRUE, the minimum acceptable length for truncation (before |
||
513 | * adding an ellipsis, if $add_ellipsis is TRUE). Has no effect if $wordsafe |
||
514 | * is FALSE. This can be used to prevent having a very short resulting string |
||
515 | * that will not be understandable. For instance, if you are truncating the |
||
516 | * string "See myverylongurlexample.com for more information" to a word-safe |
||
517 | * return length of 20, the only available word boundary within 20 characters |
||
518 | * is after the word "See", which wouldn't leave a very informative string. If |
||
519 | * you had set $min_wordsafe_length to 10, though, the function would realise |
||
520 | * that "See" alone is too short, and would then just truncate ignoring word |
||
521 | * boundaries, giving you "See myverylongurl..." (assuming you had set |
||
522 | * $add_ellipses to TRUE). |
||
523 | * |
||
524 | * @return string |
||
525 | * The truncated string. |
||
526 | */ |
||
527 | public static function truncate($string, $max_length, $wordsafe = FALSE, $add_ellipsis = FALSE, $min_wordsafe_length = 1) { |
||
528 | $ellipsis = ''; |
||
529 | $max_length = max($max_length, 0); |
||
530 | $min_wordsafe_length = max($min_wordsafe_length, 0); |
||
531 | |||
532 | if (static::strlen($string) <= $max_length) { |
||
533 | // No truncation needed, so don't add ellipsis, just return. |
||
534 | return $string; |
||
535 | } |
||
536 | |||
537 | if ($add_ellipsis) { |
||
538 | // Truncate ellipsis in case $max_length is small. |
||
539 | $ellipsis = static::substr('…', 0, $max_length); |
||
540 | $max_length -= static::strlen($ellipsis); |
||
541 | $max_length = max($max_length, 0); |
||
542 | } |
||
543 | |||
544 | if ($max_length <= $min_wordsafe_length) { |
||
545 | // Do not attempt word-safe if lengths are bad. |
||
546 | $wordsafe = FALSE; |
||
547 | } |
||
548 | |||
549 | if ($wordsafe) { |
||
550 | $matches = array(); |
||
551 | // Find the last word boundary, if there is one within $min_wordsafe_length |
||
552 | // to $max_length characters. preg_match() is always greedy, so it will |
||
553 | // find the longest string possible. |
||
554 | $found = preg_match('/^(.{' . $min_wordsafe_length . ',' . $max_length . '})[' . Unicode::PREG_CLASS_WORD_BOUNDARY . ']/u', $string, $matches); |
||
555 | if ($found) { |
||
556 | $string = $matches[1]; |
||
557 | } |
||
558 | else { |
||
559 | $string = static::substr($string, 0, $max_length); |
||
560 | } |
||
561 | } |
||
562 | else { |
||
563 | $string = static::substr($string, 0, $max_length); |
||
564 | } |
||
565 | |||
566 | if ($add_ellipsis) { |
||
567 | // If we're adding an ellipsis, remove any trailing periods. |
||
568 | $string = rtrim($string, '.'); |
||
569 | |||
570 | $string .= $ellipsis; |
||
571 | } |
||
572 | |||
573 | return $string; |
||
574 | } |
||
575 | |||
576 | /** |
||
577 | * Compares UTF-8-encoded strings in a binary safe case-insensitive manner. |
||
578 | * |
||
579 | * @param string $str1 |
||
580 | * The first string. |
||
581 | * @param string $str2 |
||
582 | * The second string. |
||
583 | * |
||
584 | * @return int |
||
585 | * Returns < 0 if $str1 is less than $str2; > 0 if $str1 is greater than |
||
586 | * $str2, and 0 if they are equal. |
||
587 | */ |
||
588 | public static function strcasecmp($str1 , $str2) { |
||
589 | return strcmp(static::strtoupper($str1), static::strtoupper($str2)); |
||
590 | } |
||
591 | |||
592 | /** |
||
593 | * Encodes MIME/HTTP headers that contain incorrectly encoded characters. |
||
594 | * |
||
595 | * For example, Unicode::mimeHeaderEncode('tést.txt') returns |
||
596 | * "=?UTF-8?B?dMOpc3QudHh0?=". |
||
597 | * |
||
598 | * See http://www.rfc-editor.org/rfc/rfc2047.txt for more information. |
||
599 | * |
||
600 | * Notes: |
||
601 | * - Only encode strings that contain non-ASCII characters. |
||
602 | * - We progressively cut-off a chunk with self::truncateBytes(). This ensures |
||
603 | * each chunk starts and ends on a character boundary. |
||
604 | * - Using \n as the chunk separator may cause problems on some systems and |
||
605 | * may have to be changed to \r\n or \r. |
||
606 | * |
||
607 | * @param string $string |
||
608 | * The header to encode. |
||
609 | * |
||
610 | * @return string |
||
611 | * The mime-encoded header. |
||
612 | */ |
||
613 | public static function mimeHeaderEncode($string) { |
||
614 | if (preg_match('/[^\x20-\x7E]/', $string)) { |
||
615 | $chunk_size = 47; // floor((75 - strlen("=?UTF-8?B??=")) * 0.75); |
||
616 | $len = strlen($string); |
||
617 | $output = ''; |
||
618 | while ($len > 0) { |
||
619 | $chunk = static::truncateBytes($string, $chunk_size); |
||
620 | $output .= ' =?UTF-8?B?' . base64_encode($chunk) . "?=\n"; |
||
621 | $c = strlen($chunk); |
||
622 | $string = substr($string, $c); |
||
623 | $len -= $c; |
||
624 | } |
||
625 | return trim($output); |
||
626 | } |
||
627 | return $string; |
||
628 | } |
||
629 | |||
630 | /** |
||
631 | * Decodes MIME/HTTP encoded header values. |
||
632 | * |
||
633 | * @param string $header |
||
634 | * The header to decode. |
||
635 | * |
||
636 | * @return string |
||
637 | * The mime-decoded header. |
||
638 | */ |
||
639 | public static function mimeHeaderDecode($header) { |
||
640 | $callback = function ($matches) { |
||
641 | $data = ($matches[2] == 'B') ? base64_decode($matches[3]) : str_replace('_', ' ', quoted_printable_decode($matches[3])); |
||
642 | if (strtolower($matches[1]) != 'utf-8') { |
||
643 | $data = static::convertToUtf8($data, $matches[1]); |
||
644 | } |
||
645 | return $data; |
||
646 | }; |
||
647 | // First step: encoded chunks followed by other encoded chunks (need to collapse whitespace) |
||
648 | $header = preg_replace_callback('/=\?([^?]+)\?(Q|B)\?([^?]+|\?(?!=))\?=\s+(?==\?)/', $callback, $header); |
||
649 | // Second step: remaining chunks (do not collapse whitespace) |
||
650 | return preg_replace_callback('/=\?([^?]+)\?(Q|B)\?([^?]+|\?(?!=))\?=/', $callback, $header); |
||
651 | } |
||
652 | |||
653 | /** |
||
654 | * Flip U+C0-U+DE to U+E0-U+FD and back. Can be used as preg_replace callback. |
||
655 | * |
||
656 | * @param array $matches |
||
657 | * An array of matches by preg_replace_callback(). |
||
658 | * |
||
659 | * @return string |
||
660 | * The flipped text. |
||
661 | */ |
||
662 | public static function caseFlip($matches) { |
||
663 | return $matches[0][0] . chr(ord($matches[0][1]) ^ 32); |
||
664 | } |
||
665 | |||
666 | /** |
||
667 | * Checks whether a string is valid UTF-8. |
||
668 | * |
||
669 | * All functions designed to filter input should use drupal_validate_utf8 |
||
670 | * to ensure they operate on valid UTF-8 strings to prevent bypass of the |
||
671 | * filter. |
||
672 | * |
||
673 | * When text containing an invalid UTF-8 lead byte (0xC0 - 0xFF) is presented |
||
674 | * as UTF-8 to Internet Explorer 6, the program may misinterpret subsequent |
||
675 | * bytes. When these subsequent bytes are HTML control characters such as |
||
676 | * quotes or angle brackets, parts of the text that were deemed safe by filters |
||
677 | * end up in locations that are potentially unsafe; An onerror attribute that |
||
678 | * is outside of a tag, and thus deemed safe by a filter, can be interpreted |
||
679 | * by the browser as if it were inside the tag. |
||
680 | * |
||
681 | * The function does not return FALSE for strings containing character codes |
||
682 | * above U+10FFFF, even though these are prohibited by RFC 3629. |
||
683 | * |
||
684 | * @param string $text |
||
685 | * The text to check. |
||
686 | * |
||
687 | * @return bool |
||
688 | * TRUE if the text is valid UTF-8, FALSE if not. |
||
689 | */ |
||
690 | public static function validateUtf8($text) { |
||
691 | if (strlen($text) == 0) { |
||
692 | return TRUE; |
||
693 | } |
||
694 | // With the PCRE_UTF8 modifier 'u', preg_match() fails silently on strings |
||
695 | // containing invalid UTF-8 byte sequences. It does not reject character |
||
696 | // codes above U+10FFFF (represented by 4 or more octets), though. |
||
697 | return (preg_match('/^./us', $text) == 1); |
||
698 | } |
||
699 | |||
700 | /** |
||
701 | * Finds the position of the first occurrence of a string in another string. |
||
702 | * |
||
703 | * @param string $haystack |
||
704 | * The string to search in. |
||
705 | * @param string $needle |
||
706 | * The string to find in $haystack. |
||
707 | * @param int $offset |
||
708 | * If specified, start the search at this number of characters from the |
||
709 | * beginning (default 0). |
||
710 | * |
||
711 | * @return int|false |
||
712 | * The position where $needle occurs in $haystack, always relative to the |
||
713 | * beginning (independent of $offset), or FALSE if not found. Note that |
||
714 | * a return value of 0 is not the same as FALSE. |
||
715 | */ |
||
716 | public static function strpos($haystack, $needle, $offset = 0) { |
||
728 | |||
729 | } |
||
730 |
Duplicated code is one of the most pungent code smells. If you need to duplicate the same code in three or more different places, we strongly encourage you to look into extracting the code into a single class or operation.
You can also find more detailed suggestions in the “Code” section of your repository.