1: <?php
2:
3: 4: 5: 6: 7: 8: 9: 10:
11:
12: namespace Nette;
13:
14: use Nette;
15:
16:
17:
18: 19: 20: 21: 22:
23: final class String
24: {
25:
26: 27: 28:
29: final public function __construct()
30: {
31: throw new \LogicException("Cannot instantiate static class " . get_class($this));
32: }
33:
34:
35:
36: 37: 38: 39: 40: 41:
42: public static function checkEncoding($s, $encoding = 'UTF-8')
43: {
44: return $s === self::fixEncoding($s, $encoding);
45: }
46:
47:
48:
49: 50: 51: 52: 53: 54:
55: public static function fixEncoding($s, $encoding = 'UTF-8')
56: {
57: 58: return @iconv('UTF-16', $encoding . '//IGNORE', iconv($encoding, 'UTF-16//IGNORE', $s)); 59: }
60:
61:
62:
63: 64: 65: 66: 67: 68:
69: public static function chr($code, $encoding = 'UTF-8')
70: {
71: return iconv('UTF-32BE', $encoding . '//IGNORE', pack('N', $code));
72: }
73:
74:
75:
76: 77: 78: 79: 80: 81:
82: public static function startsWith($haystack, $needle)
83: {
84: return strncmp($haystack, $needle, strlen($needle)) === 0;
85: }
86:
87:
88:
89: 90: 91: 92: 93: 94:
95: public static function endsWith($haystack, $needle)
96: {
97: return strlen($needle) === 0 || substr($haystack, -strlen($needle)) === $needle;
98: }
99:
100:
101:
102: 103: 104: 105: 106:
107: public static function normalize($s)
108: {
109: 110: $s = str_replace("\r\n", "\n", $s); 111: $s = strtr($s, "\r", "\n"); 112:
113: 114: $s = preg_replace('#[\x00-\x08\x0B-\x1F]+#', '', $s);
115:
116: 117: $s = preg_replace("#[\t ]+$#m", '', $s);
118:
119: 120: $s = trim($s, "\n");
121:
122: return $s;
123: }
124:
125:
126:
127: 128: 129: 130: 131:
132: public static function toAscii($s)
133: {
134: $s = preg_replace('#[^\x09\x0A\x0D\x20-\x7E\xA0-\x{10FFFF}]#u', '', $s);
135: $s = strtr($s, '`\'"^~', "\x01\x02\x03\x04\x05");
136: if (ICONV_IMPL === 'glibc') {
137: $s = @iconv('UTF-8', 'WINDOWS-1250//TRANSLIT', $s); 138: $s = strtr($s, "\xa5\xa3\xbc\x8c\xa7\x8a\xaa\x8d\x8f\x8e\xaf\xb9\xb3\xbe\x9c\x9a\xba\x9d\x9f\x9e\xbf\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2"
139: ."\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf8\xf9\xfa\xfb\xfc\xfd\xfe",
140: "ALLSSSSTZZZallssstzzzRAAAALCCCEEEEIIDDNNOOOOxRUUUUYTsraaaalccceeeeiiddnnooooruuuuyt");
141: } else {
142: $s = @iconv('UTF-8', 'ASCII//TRANSLIT', $s); 143: }
144: $s = str_replace(array('`', "'", '"', '^', '~'), '', $s);
145: return strtr($s, "\x01\x02\x03\x04\x05", '`\'"^~');
146: }
147:
148:
149:
150: 151: 152: 153: 154: 155: 156:
157: public static function webalize($s, $charlist = NULL, $lower = TRUE)
158: {
159: $s = self::toAscii($s);
160: if ($lower) $s = strtolower($s);
161: $s = preg_replace('#[^a-z0-9' . preg_quote($charlist, '#') . ']+#i', '-', $s);
162: $s = trim($s, '-');
163: return $s;
164: }
165:
166:
167:
168: 169: 170: 171: 172: 173: 174:
175: public static function truncate($s, $maxLen, $append = "\xE2\x80\xA6")
176: {
177: if (self::length($s) > $maxLen) {
178: $maxLen = $maxLen - self::length($append);
179: if ($maxLen < 1) {
180: return $append;
181:
182: } elseif ($matches = self::match($s, '#^.{1,'.$maxLen.'}(?=[\s\x00-@\[-`{-~])#us')) {
183: return $matches[0] . $append;
184:
185: } else {
186: return iconv_substr($s, 0, $maxLen, 'UTF-8') . $append;
187: }
188: }
189: return $s;
190: }
191:
192:
193:
194: 195: 196: 197: 198: 199: 200:
201: public static function indent($s, $level = 1, $chars = "\t")
202: {
203: return $level < 1 ? $s : self::replace($s, '#(?:^|[\r\n]+)(?=[^\r\n])#', '$0' . str_repeat($chars, $level));
204: }
205:
206:
207:
208: 209: 210: 211: 212:
213: public static function lower($s)
214: {
215: return mb_strtolower($s, 'UTF-8');
216: }
217:
218:
219:
220: 221: 222: 223: 224:
225: public static function upper($s)
226: {
227: return mb_strtoupper($s, 'UTF-8');
228: }
229:
230:
231:
232: 233: 234: 235: 236:
237: public static function capitalize($s)
238: {
239: return mb_convert_case($s, MB_CASE_TITLE, 'UTF-8');
240: }
241:
242:
243:
244: 245: 246: 247: 248: 249: 250:
251: public static function compare($left, $right, $len = NULL)
252: {
253: if ($len < 0) {
254: $left = iconv_substr($left, $len, -$len, 'UTF-8');
255: $right = iconv_substr($right, $len, -$len, 'UTF-8');
256: } elseif ($len !== NULL) {
257: $left = iconv_substr($left, 0, $len, 'UTF-8');
258: $right = iconv_substr($right, 0, $len, 'UTF-8');
259: }
260: return self::lower($left) === self::lower($right);
261: }
262:
263:
264:
265: 266: 267: 268: 269:
270: public static function length($s)
271: {
272: return function_exists('mb_strlen') ? mb_strlen($s, 'UTF-8') : strlen(utf8_decode($s));
273: }
274:
275:
276:
277: 278: 279: 280: 281: 282:
283: public static function trim($s, $charlist = " \t\n\r\0\x0B\xC2\xA0")
284: {
285: $charlist = preg_quote($charlist, '#');
286: return self::replace($s, '#^['.$charlist.']+|['.$charlist.']+$#u', '');
287: }
288:
289:
290:
291: 292: 293: 294: 295: 296: 297:
298: public static function padLeft($s, $length, $pad = ' ')
299: {
300: $length = max(0, $length - self::length($s));
301: $padLen = self::length($pad);
302: return str_repeat($pad, $length / $padLen) . iconv_substr($pad, 0, $length % $padLen, 'UTF-8') . $s;
303: }
304:
305:
306:
307: 308: 309: 310: 311: 312: 313:
314: public static function padRight($s, $length, $pad = ' ')
315: {
316: $length = max(0, $length - self::length($s));
317: $padLen = self::length($pad);
318: return $s . str_repeat($pad, $length / $padLen) . iconv_substr($pad, 0, $length % $padLen, 'UTF-8');
319: }
320:
321:
322:
323: 324: 325: 326: 327: 328: 329:
330: public static function split($subject, $pattern, $flags = 0)
331: {
332: Debug::tryError();
333: $res = preg_split($pattern, $subject, -1, $flags | PREG_SPLIT_DELIM_CAPTURE);
334: self::catchPregError($pattern);
335: return $res;
336: }
337:
338:
339:
340: 341: 342: 343: 344: 345: 346: 347:
348: public static function match($subject, $pattern, $flags = 0, $offset = 0)
349: {
350: Debug::tryError();
351: $res = preg_match($pattern, $subject, $m, $flags, $offset);
352: self::catchPregError($pattern);
353: if ($res) {
354: return $m;
355: }
356: }
357:
358:
359:
360: 361: 362: 363: 364: 365: 366: 367:
368: public static function matchAll($subject, $pattern, $flags = 0, $offset = 0)
369: {
370: Debug::tryError();
371: $res = preg_match_all($pattern, $subject, $m, ($flags & PREG_PATTERN_ORDER) ? $flags : ($flags | PREG_SET_ORDER), $offset);
372: self::catchPregError($pattern);
373: return $m;
374: }
375:
376:
377:
378: 379: 380: 381: 382: 383: 384: 385:
386: public static function replace($subject, $pattern, $replacement = NULL, $limit = -1)
387: {
388: Debug::tryError();
389: if (is_object($replacement) || is_array($replacement)) {
390: if (!is_callable($replacement, FALSE, $textual)) {
391: Debug::catchError($foo);
392: throw new \InvalidStateException("Callback '$textual' is not callable.");
393: }
394: $res = preg_replace_callback($pattern, $replacement, $subject, $limit);
395:
396: } elseif (is_array($pattern)) {
397: $res = preg_replace(array_keys($pattern), array_values($pattern), $subject, $limit);
398:
399: } else {
400: $res = preg_replace($pattern, $replacement, $subject, $limit);
401: }
402: self::catchPregError($pattern);
403: return $res;
404: }
405:
406:
407:
408:
409: public static function catchPregError($pattern)
410: {
411: if (Debug::catchError($message)) { 412: throw new RegexpException("$message in pattern: $pattern");
413:
414: } elseif (preg_last_error()) { 415: static $messages = array(
416: PREG_INTERNAL_ERROR => 'Internal error',
417: PREG_BACKTRACK_LIMIT_ERROR => 'Backtrack limit was exhausted',
418: PREG_RECURSION_LIMIT_ERROR => 'Recursion limit was exhausted',
419: PREG_BAD_UTF8_ERROR => 'Malformed UTF-8 data',
420: 5 => 'Offset didn\'t correspond to the begin of a valid UTF-8 code point', 421: );
422: $code = preg_last_error();
423: throw new RegexpException((isset($messages[$code]) ? $messages[$code] : 'Unknown error') . " (pattern: $pattern)", $code);
424: }
425: }
426:
427: }
428:
429:
430:
431: 432: 433:
434: class RegexpException extends \Exception
435: {
436: }
437: