123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321 |
- <?php
- /**
- * @package Kohana/ORM
- * @author Koseven Team
- * @copyright (c) 2016-2018 Koseven Team
- * @license https://koseven.ga/LICENSE.md
- */
- class ORM_Behavior_Slug extends ORM_Behavior {
- /**
- * Prefered column to generate slug
- * @var string
- */
- protected $_slug_source_column = 'name';
- /**
- * Table column for slug value
- * @var string
- */
- protected $_slug_column = 'slug';
- /**
- * Constructs a behavior object
- *
- * @param array $config Configuration parameters
- */
- protected function __construct($config)
- {
- parent::__construct($config);
- $this->_slug_source_column = Arr::get($config, 'source', $this->_slug_source_column);
- $this->_slug_column = Arr::get($config, 'column', $this->_slug_column);
- }
- /**
- * Constructs a new model and loads a record if given
- *
- * @param ORM $model The model
- * @param mixed $id Parameter for find or object to load
- */
- public function on_construct($model, $id)
- {
- if (($id !== NULL) AND ! is_array($id) AND ! ctype_digit($id))
- {
- $model->where($this->_slug_column, '=', $id)->find();
- // Prevent further record loading
- return FALSE;
- }
- return TRUE;
- }
- /**
- * The model is updated, add a slug value if empty
- *
- * @param ORM $model The model
- */
- public function on_update($model)
- {
- $this->create_slug($model);
- }
- /**
- * A new model is created, add a slug value
- *
- * @param ORM $model The model
- */
- public function on_create($model)
- {
- $this->create_slug($model);
- }
- private function create_slug($model)
- {
- $index = 0;
- $current_slug = $model->get($this->_slug_column);
- // Create a valid slug name
- $source = $model->get($this->_slug_source_column);
- if (empty($source))
- {
- $source = $model->object_name();
- }
- // Prepare the query
- $query = DB::select()->from($model->table_name())
- ->where($this->_slug_column, '=', ':slug')
- ->where($model->primary_key(), '!=', $model->pk())
- ->limit(1);
- // Create a slugged value
- $slug_base = $this->slugify($source);
- if ($current_slug !== $slug_base)
- {
- // Just the base slug
- $current_slug = $slug_base;
- $query->param(':slug', $current_slug);
- // Default slug invalid, add index
- if ($query->execute()->get($model->primary_key(), FALSE) !== FALSE)
- {
- // Base slug string with an index
- do
- {
- $current_slug = sprintf('%s-%d', $slug_base, $index);
- $query->param(':slug', $current_slug);
- if ($query->execute()->get($model->primary_key(), FALSE) !== FALSE)
- {
- $index++;
- $current_slug = '';
- }
- }
- while (empty($current_slug));
- }
- $model->set($this->_slug_column, $current_slug);
- }
- }
- /**
- * Create a safe pathname
- */
- protected function slugify($text, $strict = TRUE)
- {
- $text = $this->remove_accents($text);
- // replace non letter or digits by -
- $text = preg_replace('~[^\\pL\d.]+~u', '-', $text);
- // trim
- $text = trim($text, '-');
- // lowercase
- $text = strtolower($text);
- // remove unwanted characters
- $text = preg_replace('~[^-\w.]+~', '', $text);
- if ($strict)
- {
- $text = str_replace('.', '', $text);
- }
- return $text;
- }
- /**
- * Check if the input file looks like an utf8 string
- */
- function seems_utf8($str)
- {
- $length = strlen($str);
- for ($i=0; $i<$length; $i++)
- {
- $c = ord($str[$i]);
- if ($c < 0x80) { $n = 0; } // 0bbbbbbb
- elseif (($c & 0xE0) == 0xC0) { $n = 1; } // 110bbbbb
- elseif (($c & 0xF0) == 0xE0) { $n = 2; } // 1110bbbb
- elseif (($c & 0xF8) == 0xF0) { $n = 3; } // 11110bbb
- elseif (($c & 0xFC) == 0xF8) { $n = 4; } // 111110bb
- elseif (($c & 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 == $length) OR ((ord($str[$i]) & 0xC0) != 0x80))
- return FALSE;
- }
- }
- return TRUE;
- }
- /**
- * Replace the accents
- */
- function remove_accents($string)
- {
- if ( ! preg_match('/[\x80-\xff]/', $string))
- return $string;
- if ($this->seems_utf8($string))
- {
- $chars = [
- // Decompositions for 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(134) => 'AE', 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(144) => 'D', 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(158) => 'TH', 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(166) => 'ae', 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(176) => 'd', 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(184) => '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(190) => 'th',
- chr(195).chr(191) => 'y',
- // Decompositions for 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',
- // Decompositions for Latin Extended-B
- chr(200).chr(152) => 'S', chr(200).chr(153) => 's',
- chr(200).chr(154) => 'T', chr(200).chr(155) => 't',
- // 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'] = [chr(140), chr(156), chr(198), chr(208), chr(222), chr(223), chr(230), chr(240), chr(254)];
- $double_chars['out'] = ['OE', 'oe', 'AE', 'DH', 'TH', 'ss', 'ae', 'dh', 'th'];
- $string = str_replace($double_chars['in'], $double_chars['out'], $string);
- }
- return $string;
- }
- }
|