3 * DirectionDetector plugin, detects notices with RTL content & sets RTL
6 * This program is free software: you can redistribute it and/or modify
7 * it under the terms of the GNU General Public License as published by
8 * the Free Software Foundation, either version 3 of the License, or
9 * (at your option) any later version.
11 * This program is distributed in the hope that it will be useful,
12 * but WITHOUT ANY WARRANTY; without even the implied warranty of
13 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
14 * GNU General Public License for more details.
16 * You should have received a copy of the GNU General Public License
17 * along with this program. If not, see <http://www.gnu.org/licenses/>.
21 * @author Behrooz shabani (everplays) - <behrooz@rock.com>
22 * @copyright 2009-2010 Behrooz shabani
23 * @license http://www.fsf.org/licensing/licenses/agpl-3.0.html AGPL 3.0
27 if (!defined('STATUSNET')) {
31 define('DIRECTIONDETECTORPLUGIN_VERSION', '0.1.2');
33 class DirectionDetectorPlugin extends Plugin {
35 * SN plugin API, here we will make changes on rendered column
37 * @param object $notice notice is going to be saved
39 public function onStartNoticeSave(&$notice){
40 if(!preg_match('/<span class="rtl">/', $notice->rendered) && self::isRTL($notice->content))
41 $notice->rendered = '<span class="rtl">'.$notice->rendered.'</span>';
46 * SN plugin API, here we will add css needed for modifiyed rendered
50 public function onEndShowStatusNetStyles($xml){
51 $xml->element('style', array('type' => 'text/css'), 'span.rtl {display:block;direction:rtl;text-align:right;float:right;width:490px;} .notice .author {float:left}');
54 * checks that passed string is a RTL language or not
56 * @param string $str String to be checked
58 public static function isRTL($str){
59 self::getClearText($str);
60 if( is_array($cc = self::utf8ToUnicode(mb_substr($str, 0, 1, 'utf-8'))) )
64 if($cc>=1536 && $cc<=1791) // Arabic, Persian, Urdu, Kurdish, ...
66 if($cc>=65136 && $cc<=65279) // Arabic peresent 2
68 if($cc>=64336 && $cc<=65023) // Arabic peresent 1
70 if($cc>=1424 && $cc<=1535) // Hebrew
72 if($cc>=64256 && $cc<=64335) // Hebrew peresent
74 if($cc>=1792 && $cc<=1871) // Syriac
76 if($cc>=1920 && $cc<=1983) // Thaana
78 if($cc>=1984 && $cc<=2047) // NKo
80 if($cc>=11568 && $cc<=11647) // Tifinagh
86 * clears text from replies, tags, groups, repeats & whitespaces
88 * @param string &$str string to be cleared
90 private static function getClearText(&$str){
91 $str = preg_replace('/@[^ ]+|![^ ]+|#[^ ]+/u', '', $str); // reply, tag, group
92 $str = preg_replace('/^RT[: ]{1}| RT | RT: |^RD[: ]{1}| RD | RD: |[♺♻:]/u', '', $str); // redent, retweet
93 $str = preg_replace("/[ \r\t\n]+/", ' ', trim($str)); // remove spaces
97 * Takes a UTF-8 string and returns an array of ints representing the
98 * Unicode characters. Astral planes are supported i.e. the ints in the
99 * output can be > 0xFFFF. Occurrances of the BOM are ignored. Surrogates
100 * are not allowed. ### modified ### returns first character code
102 * Returns false if the input string isn't a valid UTF-8 octet sequence.
104 private static function utf8ToUnicode($str){
105 $mState = 0; // cached expected number of octets after the current octet
106 // until the beginning of the next UTF8 character sequence
107 $mUcs4 = 0; // cached Unicode character
108 $mBytes = 1; // cached expected number of octets in the current sequence
112 for($i = 0; $i < $len; $i++) {
115 // When mState is zero we expect either a US-ASCII character or a
116 // multi-octet sequence.
117 if (0 == (0x80 & ($in))) {
118 // US-ASCII, pass straight through.
121 } elseif (0xC0 == (0xE0 & ($in))) {
122 // First octet of 2 octet sequence
124 $mUcs4 = ($mUcs4 & 0x1F) << 6;
127 } elseif (0xE0 == (0xF0 & ($in))) {
128 // First octet of 3 octet sequence
130 $mUcs4 = ($mUcs4 & 0x0F) << 12;
133 } elseif (0xF0 == (0xF8 & ($in))) {
134 // First octet of 4 octet sequence
136 $mUcs4 = ($mUcs4 & 0x07) << 18;
139 } elseif (0xF8 == (0xFC & ($in))) {
140 /* First octet of 5 octet sequence.
142 * This is illegal because the encoded codepoint must be either
143 * (a) not the shortest form or
144 * (b) outside the Unicode range of 0-0x10FFFF.
145 * Rather than trying to resynchronize, we will carry on until the end
146 * of the sequence and let the later error handling code catch it.
149 $mUcs4 = ($mUcs4 & 0x03) << 24;
152 } elseif (0xFC == (0xFE & ($in))) {
153 // First octet of 6 octet sequence, see comments for 5 octet sequence.
155 $mUcs4 = ($mUcs4 & 1) << 30;
159 /* Current octet is neither in the US-ASCII range nor a legal first
160 * octet of a multi-octet sequence.
165 // When mState is non-zero, we expect a continuation of the multi-octet
167 if (0x80 == (0xC0 & ($in))) {
168 // Legal continuation.
169 $shift = ($mState - 1) * 6;
171 $tmp = ($tmp & 0x0000003F) << $shift;
173 if (0 == --$mState) {
174 /* End of the multi-octet sequence. mUcs4 now contains the final
175 * Unicode codepoint to be output
177 * Check for illegal sequences and codepoints.
179 // From Unicode 3.1, non-shortest form is illegal
181 ((2 == $mBytes) && ($mUcs4 < 0x0080)) ||
182 ((3 == $mBytes) && ($mUcs4 < 0x0800)) ||
183 ((4 == $mBytes) && ($mUcs4 < 0x10000)) ||
185 // From Unicode 3.2, surrogate characters are illegal
186 (($mUcs4 & 0xFFFFF800) == 0xD800) ||
187 // Codepoints outside the Unicode range are illegal
192 if (0xFEFF != $mUcs4) {
195 //initialize UTF8 cache
201 /* ((0xC0 & (*in) != 0x80) && (mState != 0))
203 * Incomplete multi-octet sequence.
215 function onPluginVersion(&$versions){
217 'name' => 'Direction detector',
218 'version' => DIRECTIONDETECTORPLUGIN_VERSION,
219 'author' => 'Behrooz Shabani',
220 // TRANS: Direction detector plugin description.
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