/src/PurString.php
PHP | 289 lines | 188 code | 10 blank | 91 comment | 27 complexity | bd9a90d9e76d0f6678a9be99cc2ed074 MD5 | raw file
- <?php
- /**
- * General static methods around strings manipulation.
- */
- class PurString{
-
- /**
- * Convert a word to its singular form.
- *
- * Exemples:
- * - friends -> friend
- * - processes -> process
- * - families -> family
- *
- * @return mixed Singular word or null if no available singular transformation
- * @param string $word
- */
- public static function toSingular($word){
- if(substr($word,strlen($word)-4,4)=='sses'){
- return substr($word,0,strlen($word)-2);
- }else if(substr($word,strlen($word)-3,3)=='ies'){
- return substr($word,0,strlen($word)-3).'y';
- }else if(substr($word,strlen($word)-1,1)=='s'){
- return substr($word,0,strlen($word)-1);
- }
- }
-
- /**
- * Convert a word to its plural form.
- *
- * Note, this is an english centric method with obvious limitations.
- *
- * Exemples:
- * assert( "friends" === PurString::toPlural("friend") );
- * assert( "processes" === PurString::toPlural("process") );
- * assert( "families" === PurString::toPlural("family") );
- *
- * @return string Plural word
- * @param string $word
- */
- public static function toPlural($word){
- if(substr($word,strlen($word)-2,2)=='ss'){
- return $word.'es';
- }else if(substr($word,strlen($word)-1,1)=='y'){
- return substr($word,0,strlen($word)-1).'ies';
- }else{
- return $word.'s';
- }
- }
- /**
- * Returns the camel cased form of a word.
- *
- * Exemple:
- * assert( "LastName" === PurString::camelize("last_name") );
- *
- * @param string $word Word to camelize
- * @return string Camelized word. likeThis.
- */
- public static function camelize($word) {
- return str_replace(" ", "", ucwords(str_replace("_", " ", $word)));
- }
-
- /**
- * Returns an underscore syntaxed version of a camel cased word.
- *
- * Exemple:
- * assert( "last_name" === PurString::underscore("LastName") );
- *
- * @param string $word Camel-cased word to be transform as underscore
- * @return string Underscore-syntaxed version of the word
- */
- public static function underscore($word) {
- return strtolower(preg_replace('/(?<=\\w)([A-Z])/', '_\\1', $word));
- }
-
- /**
- * Sanitize a string with symbols and non ascii charateres.
- *
- * Exemple:
- *
- * * $this->assertEquals(
- * * 'abc-def-ghi',
- * * PurString::path( 'àbc dêf@ghî' ));
- *
- * @return
- * @param object $path
- */
- public static function path($path){
- $path = preg_replace("/[^\w-_]/","-",self::toAscii($path));
- $path = strtolower($path);
- $path = str_replace('--','-',$path);
- if(substr($path,0,1)=='-') $path = substr($path,1);
- if(substr($path,-1)=='-') $path = substr($path,0,-1);
- return $path;
- }
-
- /**
- * Format bytes into a readable string.
- *
- * @return
- * @param object $size
- */
- public static function prettyBytes($size){
- $mb = 1024*1024;
- $gb = $mb*1024;
- if($size>$gb) {
- $mysize = sprintf("%01.2f",$size/$gb).' GB';
- }else if( $size>$mb && $size<=$gb) {
- $mysize = sprintf("%01.2f",$size/$mb).' MB';
- }else if( $size>=1024 ) {
- $mysize = sprintf("%01.2f",$size/1024).' Kb';
- }else{
- $mysize = $size.' bytes';
- }
- return $mysize;
- }
-
- /**
- * Tries to detect if a string is in Unicode encoding.
- *
- * @param text string Text to check
- * @link http://www.php.net/manual/en/function.utf8-encode.php
- */
- public static function isUtf8($text) {
- for ($i=0; $i<strlen($text); $i++) {
- if (ord($text[$i]) < 0x80) continue; # 0bbbbbbb
- elseif ((ord($text[$i]) & 0xE0) == 0xC0) $n=1; # 110bbbbb
- elseif ((ord($text[$i]) & 0xF0) == 0xE0) $n=2; # 1110bbbb
- elseif ((ord($text[$i]) & 0xF8) == 0xF0) $n=3; # 11110bbb
- elseif ((ord($text[$i]) & 0xFC) == 0xF8) $n=4; # 111110bb
- elseif ((ord($text[$i]) & 0xFE) == 0xFC) $n=5; # 1111110b
- else return false; # Does not match any model
- for ($j=0; $j<$n; $j++) { # n bytes matching 10bbbbbb follow ?
- if ((++$i == strlen($text)) || ((ord($text[$i]) & 0xC0) != 0x80))
- return false;
- }
- }
- return true;
- }
-
- /**
- * Validate a provided email.
- *
- * Note, does not check that the length of the local part is less than 65 nor
- * that the length of the domain is less than 256.
- *
- * @return boolean True if valid, false otherwise
- * @param string $email
- */
- public static function isEmail($email){
- //return preg_match('/^[A-Za-z0-9\._-]+[@][A-Za-z0-9\._-]+[\.].[A-Za-z0-9]+$/',$email);
- return (bool) preg_match('/^[a-z0-9,!#\$%&\'\*\+\/\=\?\^_`\{\|}~-]+(\.[a-z0-9,!#\$%&\'\*\+\/\=\?\^_`\{\|}~-]+)*@[a-z0-9-]+(\.[a-z0-9-]+)*\.([a-z]{2,})$/',$email);
- }
-
- /**
- * Remove accent from string by converting it from a utf-8 or a ISO-8859-1 to ASCII.
- *
- * @return
- * @param object $string
- */
- public static function toAscii($string){
- // If string is clean, no need to process it
- if(!preg_match('/[\x80-\xff]/',$string))
- return $string;
- if(self::isUtf8($string)){
- $chars = array(
- // Latin-1 Supplement
- chr(195).chr(128) => 'A', chr(195).chr(129) => 'A',
- chr(195).chr(130) => 'A', chr(195).chr(131) => 'A',
- chr(195).chr(132) => 'A', chr(195).chr(133) => 'A',
- chr(195).chr(135) => 'C', chr(195).chr(136) => 'E',
- chr(195).chr(137) => 'E', chr(195).chr(138) => 'E',
- chr(195).chr(139) => 'E', chr(195).chr(140) => 'I',
- chr(195).chr(141) => 'I', chr(195).chr(142) => 'I',
- chr(195).chr(143) => 'I', chr(195).chr(145) => 'N',
- chr(195).chr(146) => 'O', chr(195).chr(147) => 'O',
- chr(195).chr(148) => 'O', chr(195).chr(149) => 'O',
- chr(195).chr(150) => 'O', chr(195).chr(153) => 'U',
- chr(195).chr(154) => 'U', chr(195).chr(155) => 'U',
- chr(195).chr(156) => 'U', chr(195).chr(157) => 'Y',
- chr(195).chr(159) => 's', chr(195).chr(160) => 'a',
- chr(195).chr(161) => 'a', chr(195).chr(162) => 'a',
- chr(195).chr(163) => 'a', chr(195).chr(164) => 'a',
- chr(195).chr(165) => 'a', chr(195).chr(167) => 'c',
- chr(195).chr(168) => 'e', chr(195).chr(169) => 'e',
- chr(195).chr(170) => 'e', chr(195).chr(171) => 'e',
- chr(195).chr(172) => 'i', chr(195).chr(173) => 'i',
- chr(195).chr(174) => 'i', chr(195).chr(175) => 'i',
- chr(195).chr(177) => 'n', chr(195).chr(178) => 'o',
- chr(195).chr(179) => 'o', chr(195).chr(180) => 'o',
- chr(195).chr(181) => 'o', chr(195).chr(182) => 'o',
- chr(195).chr(182) => 'o', chr(195).chr(185) => 'u',
- chr(195).chr(186) => 'u', chr(195).chr(187) => 'u',
- chr(195).chr(188) => 'u', chr(195).chr(189) => 'y',
- chr(195).chr(191) => 'y',
- // Latin Extended-A
- chr(196).chr(128) => 'A', chr(196).chr(129) => 'a',
- chr(196).chr(130) => 'A', chr(196).chr(131) => 'a',
- chr(196).chr(132) => 'A', chr(196).chr(133) => 'a',
- chr(196).chr(134) => 'C', chr(196).chr(135) => 'c',
- chr(196).chr(136) => 'C', chr(196).chr(137) => 'c',
- chr(196).chr(138) => 'C', chr(196).chr(139) => 'c',
- chr(196).chr(140) => 'C', chr(196).chr(141) => 'c',
- chr(196).chr(142) => 'D', chr(196).chr(143) => 'd',
- chr(196).chr(144) => 'D', chr(196).chr(145) => 'd',
- chr(196).chr(146) => 'E', chr(196).chr(147) => 'e',
- chr(196).chr(148) => 'E', chr(196).chr(149) => 'e',
- chr(196).chr(150) => 'E', chr(196).chr(151) => 'e',
- chr(196).chr(152) => 'E', chr(196).chr(153) => 'e',
- chr(196).chr(154) => 'E', chr(196).chr(155) => 'e',
- chr(196).chr(156) => 'G', chr(196).chr(157) => 'g',
- chr(196).chr(158) => 'G', chr(196).chr(159) => 'g',
- chr(196).chr(160) => 'G', chr(196).chr(161) => 'g',
- chr(196).chr(162) => 'G', chr(196).chr(163) => 'g',
- chr(196).chr(164) => 'H', chr(196).chr(165) => 'h',
- chr(196).chr(166) => 'H', chr(196).chr(167) => 'h',
- chr(196).chr(168) => 'I', chr(196).chr(169) => 'i',
- chr(196).chr(170) => 'I', chr(196).chr(171) => 'i',
- chr(196).chr(172) => 'I', chr(196).chr(173) => 'i',
- chr(196).chr(174) => 'I', chr(196).chr(175) => 'i',
- chr(196).chr(176) => 'I', chr(196).chr(177) => 'i',
- chr(196).chr(178) => 'IJ',chr(196).chr(179) => 'ij',
- chr(196).chr(180) => 'J', chr(196).chr(181) => 'j',
- chr(196).chr(182) => 'K', chr(196).chr(183) => 'k',
- chr(196).chr(184) => 'k', chr(196).chr(185) => 'L',
- chr(196).chr(186) => 'l', chr(196).chr(187) => 'L',
- chr(196).chr(188) => 'l', chr(196).chr(189) => 'L',
- chr(196).chr(190) => 'l', chr(196).chr(191) => 'L',
- chr(197).chr(128) => 'l', chr(197).chr(129) => 'L',
- chr(197).chr(130) => 'l', chr(197).chr(131) => 'N',
- chr(197).chr(132) => 'n', chr(197).chr(133) => 'N',
- chr(197).chr(134) => 'n', chr(197).chr(135) => 'N',
- chr(197).chr(136) => 'n', chr(197).chr(137) => 'N',
- chr(197).chr(138) => 'n', chr(197).chr(139) => 'N',
- chr(197).chr(140) => 'O', chr(197).chr(141) => 'o',
- chr(197).chr(142) => 'O', chr(197).chr(143) => 'o',
- chr(197).chr(144) => 'O', chr(197).chr(145) => 'o',
- chr(197).chr(146) => 'OE',chr(197).chr(147) => 'oe',
- chr(197).chr(148) => 'R',chr(197).chr(149) => 'r',
- chr(197).chr(150) => 'R',chr(197).chr(151) => 'r',
- chr(197).chr(152) => 'R',chr(197).chr(153) => 'r',
- chr(197).chr(154) => 'S',chr(197).chr(155) => 's',
- chr(197).chr(156) => 'S',chr(197).chr(157) => 's',
- chr(197).chr(158) => 'S',chr(197).chr(159) => 's',
- chr(197).chr(160) => 'S', chr(197).chr(161) => 's',
- chr(197).chr(162) => 'T', chr(197).chr(163) => 't',
- chr(197).chr(164) => 'T', chr(197).chr(165) => 't',
- chr(197).chr(166) => 'T', chr(197).chr(167) => 't',
- chr(197).chr(168) => 'U', chr(197).chr(169) => 'u',
- chr(197).chr(170) => 'U', chr(197).chr(171) => 'u',
- chr(197).chr(172) => 'U', chr(197).chr(173) => 'u',
- chr(197).chr(174) => 'U', chr(197).chr(175) => 'u',
- chr(197).chr(176) => 'U', chr(197).chr(177) => 'u',
- chr(197).chr(178) => 'U', chr(197).chr(179) => 'u',
- chr(197).chr(180) => 'W', chr(197).chr(181) => 'w',
- chr(197).chr(182) => 'Y', chr(197).chr(183) => 'y',
- chr(197).chr(184) => 'Y', chr(197).chr(185) => 'Z',
- chr(197).chr(186) => 'z', chr(197).chr(187) => 'Z',
- chr(197).chr(188) => 'z', chr(197).chr(189) => 'Z',
- chr(197).chr(190) => 'z', chr(197).chr(191) => 's',
- // Euro Sign
- chr(226).chr(130).chr(172) => 'E',
- // GBP (Pound) Sign
- chr(194).chr(163) => '');
- $string = strtr($string, $chars);
- } else {
- // Assume ISO-8859-1 if not UTF-8
- $chars['in'] =
- chr(128).chr(131).chr(138).chr(142).chr(154).chr(158).
- chr(159).chr(162).chr(165).chr(181).chr(192).chr(193).chr(194).
- chr(195).chr(196).chr(197).chr(199).chr(200).chr(201).chr(202).
- chr(203).chr(204).chr(205).chr(206).chr(207).chr(209).chr(210).
- chr(211).chr(212).chr(213).chr(214).chr(216).chr(217).chr(218).
- chr(219).chr(220).chr(221).chr(224).chr(225).chr(226).chr(227).
- chr(228).chr(229).chr(231).chr(232).chr(233).chr(234).chr(235).
- chr(236).chr(237).chr(238).chr(239).chr(241).chr(242).chr(243).
- chr(244).chr(245).chr(246).chr(248).chr(249).chr(250).chr(251).
- chr(252).chr(253).chr(255);
- $chars['out'] = "EfSZszYcYuAAAAAACEEEEIIIINOOOOOOUUUUYaaaaaaceeeeiiiinoooooouuuuyy";
- $string = strtr($string,$chars['in'],$chars['out']);
- $double_chars['in'] = array(chr(140), chr(156), chr(198), chr(208), chr(222), chr(223), chr(230), chr(240), chr(254));
- $double_chars['out'] = array('OE', 'oe', 'AE', 'DH', 'TH', 'ss', 'ae', 'dh', 'th');
- $string = str_replace($double_chars['in'], $double_chars['out'], $string);
- }
- return $string;
- }
- }