4 * DirectionDetector plugin, detects notices with RTL content & sets RTL
7 * This program is free software: you can redistribute it and/or modify
8 * it under the terms of the GNU General Public License as published by
9 * the Free Software Foundation, either version 3 of the License, or
10 * (at your option) any later version.
12 * This program is distributed in the hope that it will be useful,
13 * but WITHOUT ANY WARRANTY; without even the implied warranty of
14 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
15 * GNU General Public License for more details.
17 * You should have received a copy of the GNU General Public License
18 * along with this program. If not, see <http://www.gnu.org/licenses/>.
22 * @author Behrooz shabani (everplays) - <behrooz@rock.com>
23 * @copyright 2009-2010 Behrooz shabani
24 * @license http://www.fsf.org/licensing/licenses/agpl-3.0.html AGPL 3.0
28 if (!defined('STATUSNET')) {
32 define('DIRECTIONDETECTORPLUGIN_VERSION', '0.1.1');
34 class DirectionDetectorPlugin extends Plugin {
36 * SN plugin API, here we will make changes on rendered column
38 * @param object $notice notice is going to be saved
40 public function onStartNoticeSave(&$notice){
41 if(self::isRTL($notice->content))
42 $notice->rendered = '<span class="rtl">'.$notice->rendered.'</span>';
47 * SN plugin API, here we will add css needed for modifiyed rendered
51 public function onEndShowStatusNetStyles(&$xml){
52 $xml->element('style', array('type' => 'text/css'), 'span.rtl {display:block;direction:rtl;text-align:right;float:right;width:490px;} .notice .author {float:left}');
55 * checks that passed string is a RTL language or not
57 * @param string $str string to be checked
59 public static function isRTL($str){
60 self::getClearText($str);
61 if( is_array($cc = self::utf8ToUnicode(mb_substr($str, 0, 1, 'utf-8'))) )
65 if($cc>=1536 && $cc<=1791) // arabic, persian, urdu, kurdish, ...
67 if($cc>=65136 && $cc<=65279) // arabic peresent 2
69 if($cc>=64336 && $cc<=65023) // arabic peresent 1
71 if($cc>=1424 && $cc<=1535) // hebrew
73 if($cc>=64256 && $cc<=64335) // hebrew peresent
75 if($cc>=1792 && $cc<=1871) // Syriac
77 if($cc>=1920 && $cc<=1983) // Thaana
79 if($cc>=1984 && $cc<=2047) // NKo
81 if($cc>=11568 && $cc<=11647) // Tifinagh
87 * clears text from replys, tags, groups, reteets & whitespaces
89 * @param string &$str string to be cleared
91 private static function getClearText(&$str){
92 $str = preg_replace('/@[^ ]+|![^ ]+|#[^ ]+/u', '', $str); // reply, tag, group
93 $str = preg_replace('/^RT[: ]{1}| RT | RT: |^RD[: ]{1}| RD | RD: |[♺♻:]/u', '', $str); // redent, retweet
94 $str = preg_replace("/[ \r\t\n]+/", ' ', trim($str)); // remove spaces
98 * Takes an UTF-8 string and returns an array of ints representing the
99 * Unicode characters. Astral planes are supported ie. the ints in the
100 * output can be > 0xFFFF. O$ccurrances of the BOM are ignored. Surrogates
101 * are not allowed. ### modified ### returns first character code
103 * Returns false if the input string isn't a valid UTF-8 octet sequence.
105 private static function utf8ToUnicode(&$str){
106 $mState = 0; // cached expected number of octets after the current octet
107 // until the beginning of the next UTF8 character sequence
108 $mUcs4 = 0; // cached Unicode character
109 $mBytes = 1; // cached expected number of octets in the current sequence
113 for($i = 0; $i < $len; $i++) {
116 // When mState is zero we expect either a US-ASCII character or a
117 // multi-octet sequence.
118 if (0 == (0x80 & ($in))) {
119 // US-ASCII, pass straight through.
122 } elseif (0xC0 == (0xE0 & ($in))) {
123 // First octet of 2 octet sequence
125 $mUcs4 = ($mUcs4 & 0x1F) << 6;
128 } elseif (0xE0 == (0xF0 & ($in))) {
129 // First octet of 3 octet sequence
131 $mUcs4 = ($mUcs4 & 0x0F) << 12;
134 } elseif (0xF0 == (0xF8 & ($in))) {
135 // First octet of 4 octet sequence
137 $mUcs4 = ($mUcs4 & 0x07) << 18;
140 } elseif (0xF8 == (0xFC & ($in))) {
141 /* First octet of 5 octet sequence.
143 * This is illegal because the encoded codepoint must be either
144 * (a) not the shortest form or
145 * (b) outside the Unicode range of 0-0x10FFFF.
146 * Rather than trying to resynchronize, we will carry on until the end
147 * of the sequence and let the later error handling code catch it.
150 $mUcs4 = ($mUcs4 & 0x03) << 24;
153 } elseif (0xFC == (0xFE & ($in))) {
154 // First octet of 6 octet sequence, see comments for 5 octet sequence.
156 $mUcs4 = ($mUcs4 & 1) << 30;
160 /* Current octet is neither in the US-ASCII range nor a legal first
161 * octet of a multi-octet sequence.
166 // When mState is non-zero, we expect a continuation of the multi-octet
168 if (0x80 == (0xC0 & ($in))) {
169 // Legal continuation.
170 $shift = ($mState - 1) * 6;
172 $tmp = ($tmp & 0x0000003F) << $shift;
174 if (0 == --$mState) {
175 /* End of the multi-octet sequence. mUcs4 now contains the final
176 * Unicode codepoint to be output
178 * Check for illegal sequences and codepoints.
180 // From Unicode 3.1, non-shortest form is illegal
182 ((2 == $mBytes) && ($mUcs4 < 0x0080)) ||
183 ((3 == $mBytes) && ($mUcs4 < 0x0800)) ||
184 ((4 == $mBytes) && ($mUcs4 < 0x10000)) ||
186 // From Unicode 3.2, surrogate characters are illegal
187 (($mUcs4 & 0xFFFFF800) == 0xD800) ||
188 // Codepoints outside the Unicode range are illegal
193 if (0xFEFF != $mUcs4) {
196 //initialize UTF8 cache
202 /* ((0xC0 & (*in) != 0x80) && (mState != 0))
204 * Incomplete multi-octet sequence.
216 function onPluginVersion(&$versions){
218 'name' => 'Direction detector',
219 'version' => DIRECTIONDETECTORPLUGIN_VERSION,
220 'author' => 'behrooz shabani',
221 'rawdescription' => _m('shows notices with right-to-left content in correct direction.')
229 var_dump(DirectionDetectorPlugin::isRTL('RT @everplays ♺: دادگاه به دليل عدم حضور وکلای متهمان بنا بر اصل ١٣٥ قانون اساسی غير قانونی است')); // true