DirectionDetector plugin: tabs to spaces
This commit is contained in:
Brion Vibber
parent
d055b63187
commit
a3de417ca5
@ -26,240 +26,240 @@
|
|||||||
*/
|
*/
|
||||||
|
|
||||||
if (!defined('STATUSNET')) {
|
if (!defined('STATUSNET')) {
|
||||||
exit(1);
|
exit(1);
|
||||||
}
|
}
|
||||||
|
|
||||||
define('DIRECTIONDETECTORPLUGIN_VERSION', '0.2.0');
|
define('DIRECTIONDETECTORPLUGIN_VERSION', '0.2.0');
|
||||||
|
|
||||||
class DirectionDetectorPlugin extends Plugin {
|
class DirectionDetectorPlugin extends Plugin {
|
||||||
/**
|
/**
|
||||||
* SN plugin API, here we will make changes on rendered column
|
* SN plugin API, here we will make changes on rendered column
|
||||||
*
|
*
|
||||||
* @param object $notice notice is going to be saved
|
* @param object $notice notice is going to be saved
|
||||||
*/
|
*/
|
||||||
public function onStartNoticeSave($notice){
|
public function onStartNoticeSave($notice){
|
||||||
if(!preg_match('/<span class="rtl">/', $notice->rendered) && self::isRTL($notice->content))
|
if(!preg_match('/<span class="rtl">/', $notice->rendered) && self::isRTL($notice->content))
|
||||||
$notice->rendered = '<span class="rtl">'.$notice->rendered.'</span>';
|
$notice->rendered = '<span class="rtl">'.$notice->rendered.'</span>';
|
||||||
return true;
|
return true;
|
||||||
}
|
}
|
||||||
|
|
||||||
/**
|
/**
|
||||||
* SN plugin API, here we will add css needed for modifiyed rendered
|
* SN plugin API, here we will add css needed for modifiyed rendered
|
||||||
*
|
*
|
||||||
* @param Action $xml
|
* @param Action $xml
|
||||||
*/
|
*/
|
||||||
public function onEndShowStatusNetStyles($xml){
|
public function onEndShowStatusNetStyles($xml){
|
||||||
$xml->element('style', array('type' => 'text/css'), 'span.rtl {display:block;direction:rtl;text-align:right;float:right;} .notice .author {float:left}');
|
$xml->element('style', array('type' => 'text/css'), 'span.rtl {display:block;direction:rtl;text-align:right;float:right;} .notice .author {float:left}');
|
||||||
}
|
}
|
||||||
|
|
||||||
/**
|
/**
|
||||||
* is passed string a rtl content or not
|
* is passed string a rtl content or not
|
||||||
*
|
*
|
||||||
* @param string $content
|
* @param string $content
|
||||||
* @return boolean
|
* @return boolean
|
||||||
*/
|
*/
|
||||||
public static function isRTL($content){
|
public static function isRTL($content){
|
||||||
$content = self::getClearText($content);
|
$content = self::getClearText($content);
|
||||||
$words = explode(' ', $content);
|
$words = explode(' ', $content);
|
||||||
$rtl = 0;
|
$rtl = 0;
|
||||||
foreach($words as $str)
|
foreach($words as $str)
|
||||||
if(self::startsWithRTLCharacter($str))
|
if(self::startsWithRTLCharacter($str))
|
||||||
$rtl++;
|
$rtl++;
|
||||||
else
|
else
|
||||||
$rtl--;
|
$rtl--;
|
||||||
if($rtl>0)// if number of rtl words is more than ltr words so it's a rtl content
|
if($rtl>0)// if number of rtl words is more than ltr words so it's a rtl content
|
||||||
return true;
|
return true;
|
||||||
elseif($rtl==0)
|
elseif($rtl==0)
|
||||||
// check first word again
|
// check first word again
|
||||||
return self::startsWithRTLCharacter($words[0]);
|
return self::startsWithRTLCharacter($words[0]);
|
||||||
return false;
|
return false;
|
||||||
}
|
}
|
||||||
|
|
||||||
/**
|
/**
|
||||||
* checks that passed string starts with a RTL language or not
|
* checks that passed string starts with a RTL language or not
|
||||||
*
|
*
|
||||||
* @param string $str
|
* @param string $str
|
||||||
* @return boolean
|
* @return boolean
|
||||||
*/
|
*/
|
||||||
public static function startsWithRTLCharacter($str){
|
public static function startsWithRTLCharacter($str){
|
||||||
if( is_array($cc = self::utf8ToUnicode(mb_substr($str, 0, 1, 'utf-8'))) )
|
if( is_array($cc = self::utf8ToUnicode(mb_substr($str, 0, 1, 'utf-8'))) )
|
||||||
$cc = $cc[0];
|
$cc = $cc[0];
|
||||||
else
|
else
|
||||||
return false;
|
return false;
|
||||||
if($cc>=1536 && $cc<=1791) // arabic, persian, urdu, kurdish, ...
|
if($cc>=1536 && $cc<=1791) // arabic, persian, urdu, kurdish, ...
|
||||||
return true;
|
return true;
|
||||||
if($cc>=65136 && $cc<=65279) // arabic peresent 2
|
if($cc>=65136 && $cc<=65279) // arabic peresent 2
|
||||||
return true;
|
return true;
|
||||||
if($cc>=64336 && $cc<=65023) // arabic peresent 1
|
if($cc>=64336 && $cc<=65023) // arabic peresent 1
|
||||||
return true;
|
return true;
|
||||||
if($cc>=1424 && $cc<=1535) // hebrew
|
if($cc>=1424 && $cc<=1535) // hebrew
|
||||||
return true;
|
return true;
|
||||||
if($cc>=64256 && $cc<=64335) // hebrew peresent
|
if($cc>=64256 && $cc<=64335) // hebrew peresent
|
||||||
return true;
|
return true;
|
||||||
if($cc>=1792 && $cc<=1871) // Syriac
|
if($cc>=1792 && $cc<=1871) // Syriac
|
||||||
return true;
|
return true;
|
||||||
if($cc>=1920 && $cc<=1983) // Thaana
|
if($cc>=1920 && $cc<=1983) // Thaana
|
||||||
return true;
|
return true;
|
||||||
if($cc>=1984 && $cc<=2047) // NKo
|
if($cc>=1984 && $cc<=2047) // NKo
|
||||||
return true;
|
return true;
|
||||||
if($cc>=11568 && $cc<=11647) // Tifinagh
|
if($cc>=11568 && $cc<=11647) // Tifinagh
|
||||||
return true;
|
return true;
|
||||||
return false;
|
return false;
|
||||||
}
|
}
|
||||||
|
|
||||||
/**
|
/**
|
||||||
* clears text from replys, tags, groups, reteets & whitespaces
|
* clears text from replys, tags, groups, reteets & whitespaces
|
||||||
*
|
*
|
||||||
* @param string $str
|
* @param string $str
|
||||||
* @return string
|
* @return string
|
||||||
*/
|
*/
|
||||||
private static function getClearText($str){
|
private static function getClearText($str){
|
||||||
$str = preg_replace('/@[^ ]+|![^ ]+|#[^ ]+/u', '', $str); // reply, tag, group
|
$str = preg_replace('/@[^ ]+|![^ ]+|#[^ ]+/u', '', $str); // reply, tag, group
|
||||||
$str = preg_replace('/^RT[: ]{1}| RT | RT: |^RD[: ]{1}| RD | RD: |[♺♻:]/u', '', $str); // redent, retweet
|
$str = preg_replace('/^RT[: ]{1}| RT | RT: |^RD[: ]{1}| RD | RD: |[♺♻:]/u', '', $str); // redent, retweet
|
||||||
$str = preg_replace("/[ \r\t\n]+/", ' ', trim($str)); // remove spaces
|
$str = preg_replace("/[ \r\t\n]+/", ' ', trim($str)); // remove spaces
|
||||||
return $str;
|
return $str;
|
||||||
}
|
}
|
||||||
|
|
||||||
/**
|
/**
|
||||||
* adds javascript to do same thing on input textarea
|
* adds javascript to do same thing on input textarea
|
||||||
*
|
*
|
||||||
* @param Action $action
|
* @param Action $action
|
||||||
*/
|
*/
|
||||||
function onEndShowScripts($action){
|
function onEndShowScripts($action){
|
||||||
if (common_logged_in()) {
|
if (common_logged_in()) {
|
||||||
$action->script('plugins/DirectionDetector/jquery.DirectionDetector.js');
|
$action->script('plugins/DirectionDetector/jquery.DirectionDetector.js');
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
/**
|
/**
|
||||||
* Takes an UTF-8 string and returns an array of ints representing the
|
* Takes an UTF-8 string and returns an array of ints representing the
|
||||||
* Unicode characters. Astral planes are supported ie. the ints in the
|
* Unicode characters. Astral planes are supported ie. the ints in the
|
||||||
* output can be > 0xFFFF. O$ccurrances of the BOM are ignored. Surrogates
|
* output can be > 0xFFFF. O$ccurrances of the BOM are ignored. Surrogates
|
||||||
* are not allowed.
|
* are not allowed.
|
||||||
*
|
*
|
||||||
* @param string $str
|
* @param string $str
|
||||||
* @return mixed array of ints, or false on invalid input
|
* @return mixed array of ints, or false on invalid input
|
||||||
*/
|
*/
|
||||||
private static function utf8ToUnicode($str){
|
private static function utf8ToUnicode($str){
|
||||||
$mState = 0; // cached expected number of octets after the current octet
|
$mState = 0; // cached expected number of octets after the current octet
|
||||||
// until the beginning of the next UTF8 character sequence
|
// until the beginning of the next UTF8 character sequence
|
||||||
$mUcs4 = 0; // cached Unicode character
|
$mUcs4 = 0; // cached Unicode character
|
||||||
$mBytes = 1; // cached expected number of octets in the current sequence
|
$mBytes = 1; // cached expected number of octets in the current sequence
|
||||||
$out = array();
|
$out = array();
|
||||||
$len = strlen($str);
|
$len = strlen($str);
|
||||||
|
|
||||||
for($i = 0; $i < $len; $i++) {
|
for($i = 0; $i < $len; $i++) {
|
||||||
$in = ord($str{$i});
|
$in = ord($str{$i});
|
||||||
if (0 == $mState) {
|
if (0 == $mState) {
|
||||||
// When mState is zero we expect either a US-ASCII character or a
|
// When mState is zero we expect either a US-ASCII character or a
|
||||||
// multi-octet sequence.
|
// multi-octet sequence.
|
||||||
if (0 == (0x80 & ($in))) {
|
if (0 == (0x80 & ($in))) {
|
||||||
// US-ASCII, pass straight through.
|
// US-ASCII, pass straight through.
|
||||||
$out[] = $in;
|
$out[] = $in;
|
||||||
$mBytes = 1;
|
$mBytes = 1;
|
||||||
} elseif (0xC0 == (0xE0 & ($in))) {
|
} elseif (0xC0 == (0xE0 & ($in))) {
|
||||||
// First octet of 2 octet sequence
|
// First octet of 2 octet sequence
|
||||||
$mUcs4 = ($in);
|
$mUcs4 = ($in);
|
||||||
$mUcs4 = ($mUcs4 & 0x1F) << 6;
|
$mUcs4 = ($mUcs4 & 0x1F) << 6;
|
||||||
$mState = 1;
|
$mState = 1;
|
||||||
$mBytes = 2;
|
$mBytes = 2;
|
||||||
} elseif (0xE0 == (0xF0 & ($in))) {
|
} elseif (0xE0 == (0xF0 & ($in))) {
|
||||||
// First octet of 3 octet sequence
|
// First octet of 3 octet sequence
|
||||||
$mUcs4 = ($in);
|
$mUcs4 = ($in);
|
||||||
$mUcs4 = ($mUcs4 & 0x0F) << 12;
|
$mUcs4 = ($mUcs4 & 0x0F) << 12;
|
||||||
$mState = 2;
|
$mState = 2;
|
||||||
$mBytes = 3;
|
$mBytes = 3;
|
||||||
} elseif (0xF0 == (0xF8 & ($in))) {
|
} elseif (0xF0 == (0xF8 & ($in))) {
|
||||||
// First octet of 4 octet sequence
|
// First octet of 4 octet sequence
|
||||||
$mUcs4 = ($in);
|
$mUcs4 = ($in);
|
||||||
$mUcs4 = ($mUcs4 & 0x07) << 18;
|
$mUcs4 = ($mUcs4 & 0x07) << 18;
|
||||||
$mState = 3;
|
$mState = 3;
|
||||||
$mBytes = 4;
|
$mBytes = 4;
|
||||||
} elseif (0xF8 == (0xFC & ($in))) {
|
} elseif (0xF8 == (0xFC & ($in))) {
|
||||||
/* First octet of 5 octet sequence.
|
/* First octet of 5 octet sequence.
|
||||||
*
|
*
|
||||||
* This is illegal because the encoded codepoint must be either
|
* This is illegal because the encoded codepoint must be either
|
||||||
* (a) not the shortest form or
|
* (a) not the shortest form or
|
||||||
* (b) outside the Unicode range of 0-0x10FFFF.
|
* (b) outside the Unicode range of 0-0x10FFFF.
|
||||||
* Rather than trying to resynchronize, we will carry on until the end
|
* Rather than trying to resynchronize, we will carry on until the end
|
||||||
* of the sequence and let the later error handling code catch it.
|
* of the sequence and let the later error handling code catch it.
|
||||||
*/
|
*/
|
||||||
$mUcs4 = ($in);
|
$mUcs4 = ($in);
|
||||||
$mUcs4 = ($mUcs4 & 0x03) << 24;
|
$mUcs4 = ($mUcs4 & 0x03) << 24;
|
||||||
$mState = 4;
|
$mState = 4;
|
||||||
$mBytes = 5;
|
$mBytes = 5;
|
||||||
} elseif (0xFC == (0xFE & ($in))) {
|
} elseif (0xFC == (0xFE & ($in))) {
|
||||||
// First octet of 6 octet sequence, see comments for 5 octet sequence.
|
// First octet of 6 octet sequence, see comments for 5 octet sequence.
|
||||||
$mUcs4 = ($in);
|
$mUcs4 = ($in);
|
||||||
$mUcs4 = ($mUcs4 & 1) << 30;
|
$mUcs4 = ($mUcs4 & 1) << 30;
|
||||||
$mState = 5;
|
$mState = 5;
|
||||||
$mBytes = 6;
|
$mBytes = 6;
|
||||||
} else {
|
} else {
|
||||||
/* Current octet is neither in the US-ASCII range nor a legal first
|
/* Current octet is neither in the US-ASCII range nor a legal first
|
||||||
* octet of a multi-octet sequence.
|
* octet of a multi-octet sequence.
|
||||||
*/
|
*/
|
||||||
return false;
|
return false;
|
||||||
}
|
}
|
||||||
} else {
|
} else {
|
||||||
// When mState is non-zero, we expect a continuation of the multi-octet
|
// When mState is non-zero, we expect a continuation of the multi-octet
|
||||||
// sequence
|
// sequence
|
||||||
if (0x80 == (0xC0 & ($in))) {
|
if (0x80 == (0xC0 & ($in))) {
|
||||||
// Legal continuation.
|
// Legal continuation.
|
||||||
$shift = ($mState - 1) * 6;
|
$shift = ($mState - 1) * 6;
|
||||||
$tmp = $in;
|
$tmp = $in;
|
||||||
$tmp = ($tmp & 0x0000003F) << $shift;
|
$tmp = ($tmp & 0x0000003F) << $shift;
|
||||||
$mUcs4 |= $tmp;
|
$mUcs4 |= $tmp;
|
||||||
if (0 == --$mState) {
|
if (0 == --$mState) {
|
||||||
/* End of the multi-octet sequence. mUcs4 now contains the final
|
/* End of the multi-octet sequence. mUcs4 now contains the final
|
||||||
* Unicode codepoint to be output
|
* Unicode codepoint to be output
|
||||||
*
|
*
|
||||||
* Check for illegal sequences and codepoints.
|
* Check for illegal sequences and codepoints.
|
||||||
*/
|
*/
|
||||||
// From Unicode 3.1, non-shortest form is illegal
|
// From Unicode 3.1, non-shortest form is illegal
|
||||||
if (
|
if (
|
||||||
((2 == $mBytes) && ($mUcs4 < 0x0080)) ||
|
((2 == $mBytes) && ($mUcs4 < 0x0080)) ||
|
||||||
((3 == $mBytes) && ($mUcs4 < 0x0800)) ||
|
((3 == $mBytes) && ($mUcs4 < 0x0800)) ||
|
||||||
((4 == $mBytes) && ($mUcs4 < 0x10000)) ||
|
((4 == $mBytes) && ($mUcs4 < 0x10000)) ||
|
||||||
(4 < $mBytes) ||
|
(4 < $mBytes) ||
|
||||||
// From Unicode 3.2, surrogate characters are illegal
|
// From Unicode 3.2, surrogate characters are illegal
|
||||||
(($mUcs4 & 0xFFFFF800) == 0xD800) ||
|
(($mUcs4 & 0xFFFFF800) == 0xD800) ||
|
||||||
// Codepoints outside the Unicode range are illegal
|
// Codepoints outside the Unicode range are illegal
|
||||||
($mUcs4 > 0x10FFFF)
|
($mUcs4 > 0x10FFFF)
|
||||||
){
|
){
|
||||||
return false;
|
return false;
|
||||||
}
|
}
|
||||||
if (0xFEFF != $mUcs4) {
|
if (0xFEFF != $mUcs4) {
|
||||||
$out[] = $mUcs4;
|
$out[] = $mUcs4;
|
||||||
}
|
}
|
||||||
//initialize UTF8 cache
|
//initialize UTF8 cache
|
||||||
$mState = 0;
|
$mState = 0;
|
||||||
$mUcs4 = 0;
|
$mUcs4 = 0;
|
||||||
$mBytes = 1;
|
$mBytes = 1;
|
||||||
}
|
}
|
||||||
} else {
|
} else {
|
||||||
/* ((0xC0 & (*in) != 0x80) && (mState != 0))
|
/* ((0xC0 & (*in) != 0x80) && (mState != 0))
|
||||||
*
|
*
|
||||||
* Incomplete multi-octet sequence.
|
* Incomplete multi-octet sequence.
|
||||||
*/
|
*/
|
||||||
return false;
|
return false;
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
return $out;
|
return $out;
|
||||||
}
|
}
|
||||||
|
|
||||||
/**
|
/**
|
||||||
* plugin details
|
* plugin details
|
||||||
*/
|
*/
|
||||||
function onPluginVersion(&$versions){
|
function onPluginVersion(&$versions){
|
||||||
$versions[] = array(
|
$versions[] = array(
|
||||||
'name' => 'Direction detector',
|
'name' => 'Direction detector',
|
||||||
'version' => DIRECTIONDETECTORPLUGIN_VERSION,
|
'version' => DIRECTIONDETECTORPLUGIN_VERSION,
|
||||||
'author' => 'Behrooz Shabani',
|
'author' => 'Behrooz Shabani',
|
||||||
'rawdescription' => _m('Shows notices with right-to-left content in correct direction.')
|
'rawdescription' => _m('Shows notices with right-to-left content in correct direction.')
|
||||||
);
|
);
|
||||||
return true;
|
return true;
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
/*
|
/*
|
||||||
|
|||||||
Loading…
Reference in New Issue
Block a user