mfajri
/
dojo_app
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity
sample skeleton application with dojo toolkit & arcgis js api v 4.30
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
4 Commits
1 Branch
0 Tags
92 MiB
 
 
 
 
 
 
Branch: master
Branches Tags
${ item.name }
Create tag ${ searchTerm }
Create branch ${ searchTerm }
from 'master'
${ noResults }
dojo_app/js/library/dojox/editor/tests/PorterStemmer.php.disabled

474 lines
16 KiB
Raw Permalink Blame History

<?php
/**
*
* Present by Xinhao Chen in Dojo Team, IBM Shanghai
*
* Usage: $stem = PorterStemmer::getStem($word);
*
* Reference: "An algorithm for suffix stripping", M.F.Porter, http://tartarus.org/martin/PorterStemmer/def.txt
*
*/
class PorterStemmer{
/**
* String to store the original word
* @var string
*/
private static $word = "";
/**
* Regex for matching a consonant
* @var string
*/
private static $regexConsonant = "#([bcdfghjklmnpqrstvwxz])|([aeiou]y)|^y#";
/**
* Regex for matching a vowel
* @var string
*/
private static $regexVowel = "#([aeiou])|([bcdfghjklmnpqrstvwxz]y)#";
/**
* Regex for matching a VC set, in order to calculate m
* @var string
*/
private static $regexVC = "#((([aeiou])|([bcdfghjklmnpqrstvwxz]y))[bcdfghjklmnpqrstvwxyz])#";
/**
* Regex for matching a CVC set, in order to represent condition *o;
* @var string
*/
private static $regexCVC = "#((([bcdfghjklmnpqrstvwxz][aeiouy])|(y[aeiou]))[bcdfghjklmnpqrstvz])#";
/**
* Stems a word.
* @param string $word Word to stem
* @return string Stemmed word
*/
public static function getStem($word){
if (strlen($word) <= 2){
return $word;
}
self::$word = strtolower($word);
self::step1a();
self::step1b();
self::step1c();
self::step2();
self::step3();
self::step4();
self::step5();
return self::$word;
}
/**
* step 1a
*/
private static function step1a(){
if (substr(self::$word, -1, 1)!= "s"){
return;
}
switch (substr(self::$word, -2, 1)){
case 'e':
(self::matchLetter("sses")) && self::replaceLetter(4, "ss");
(self::matchLetter("ies")) && self::replaceLetter(3, "i");
(self::matchLetter("es")) && self::replaceLetter(2, "e");
break;
case 's':
//(self::matchLetter("ss")) && self::replaceLetter(2, "ss");
break;
default :
(self::matchLetter("s")) && self::replaceLetter(1, "");
}
}
/**
* step 1b
*/
private static function step1b(){
if (self::matchLetter("eed")){
(self::getStemM(3) > 0) && self::replaceLetter(3,"ee");
return;
}
if ((self::matchLetter("ed"))&&(self::stemContainVowel(2))){
self::replaceLetter(2,"");
self::step1b2();
return;
}
if ((self::matchLetter("ing"))&&(self::stemContainVowel(3))){
self::replaceLetter(3,"");
self::step1b2();
}
}
/**
* step 1b2
*/
private static function step1b2(){
(self::matchLetter("at")) && self::replaceLetter(2, "ate");
(self::matchLetter("bl")) && self::replaceLetter(2, "ble");
(self::matchLetter("iz")) && self::replaceLetter(2, "ize");
if (self::stemEndWithCC(0) && !(self::stemEndWithLetter(0,'l') || self::stemEndWithLetter(0,'s') || self::stemEndWithLetter(0,'z'))){
self::$word = substr(self::$word, 0 ,-1);
} else if ((self::getStemM(0) == 1) && self::stemEndWithCVC(0)){
self::$word = self::$word."e";
}
}
/**
* step 1c
*/
private static function step1c(){
(self::matchLetter("y")) && (self::stemContainVowel(1)) && self::replaceLetter(1,"i");
}
/**
* step 2
*/
private static function step2(){
switch (substr(self::$word, -2, 1)){
case 'a' :
if(self::matchLetter("ational")){
(self::getStemM(7)>0) && self::replaceLetter(7,"tion");
break;
} else if (self::matchLetter("tional")){
(self::getStemM(6)>0) && self::replaceLetter(6,"tion");
break;
}
break;
case 'c' :
if(self::matchLetter("enci")){
(self::getStemM(4)>0)&& self::replaceLetter(4,"ence");
break;
} else if (self::matchLetter("anci")){
(self::getStemM(4)>0) && self::replaceLetter(4,"ance");
break;
}
break;
case 'e' :
if(self::matchLetter("izer")){
(self::getStemM(4)>0) && self::replaceLetter(4,"ize");
break;
}
break;
case 'g' :
if(self::matchLetter("logi")){
(self::getStemM(4)>0) && self::replaceLetter(4,"log");
break;
}
break;
case 'l' :
if(self::matchLetter("bli")){
(self::getStemM(3)>0) && self::replaceLetter(3,"ble");
break;
} else if (self::matchLetter("alli")){
(self::getStemM(4)>0) && self::replaceLetter(4,"al");
break;
} else if (self::matchLetter("entli")){
(self::getStemM(5)>0) && self::replaceLetter(5,"ent");
break;
} else if (self::matchLetter("eli")){
(self::getStemM(3)>0) && self::replaceLetter(3,"e");
break;
} else if (self::matchLetter("ousli")){
(self::getStemM(5)>0) && self::replaceLetter(5,"ous");
break;
}
break;
case 'o':
if(self::matchLetter("ization")){
(self::getStemM(7)>0) && self::replaceLetter(7,"ize");
break;
} else if (self::matchLetter("ation")){
(self::getStemM(5)>0) && self::replaceLetter(5,"ate");
break;
} else if (self::matchLetter("ator")){
(self::getStemM(4)>0) && self::replaceLetter(4,"ate");
break;
}
break;
case 's':
if(self::matchLetter("alism")){
(self::getStemM(5)>0) && self::replaceLetter(5,"al");
break;
} else if (self::matchLetter("iveness")){
(self::getStemM(7)>0) && self::replaceLetter(7,"ive");
break;
} else if (self::matchLetter("fulness")){
(self::getStemM(7)>0) && self::replaceLetter(7,"ful");
break;
} else if (self::matchLetter("ousness")){
(self::getStemM(7)>0) && self::replaceLetter(7,"ous");
break;
}
break;
case 't':
if(self::matchLetter("aliti")){
(self::getStemM(5)>0) && self::replaceLetter(5,"al");
break;
} else if (self::matchLetter("iviti")){
(self::getStemM(5)>0) && self::replaceLetter(5,"ive");
break;
} else if (self::matchLetter("biliti")){
(self::getStemM(6)>0) && self::replaceLetter(6,"ble");
break;
}
break;
}
}
/**
* step 3
*/
private static function step3(){
switch (substr(self::$word, -1, 1)){
case 'e' :
if(self::matchLetter("icate")){
(self::getStemM(5)>0) && self::replaceLetter(5,"ic");
break;
} else if (self::matchLetter("ative")){
(self::getStemM(5)>0) && self::replaceLetter(5,"");
break;
} else if (self::matchLetter("alize")){
(self::getStemM(5)>0) && self::replaceLetter(5,"al");
break;
}
break;
case 'i' :
if(self::matchLetter("iciti")){
(self::getStemM(5)>0) && self::replaceLetter(5,"ic");
break;
}
break;
case 'l' :
if(self::matchLetter("ical")){
(self::getStemM(4)>0) && self::replaceLetter(4,"ic");
break;
} else if (self::matchLetter("ful")){
(self::getStemM(3)>0) && self::replaceLetter(3,"");
break;
}
break;
case 's' :
if(self::matchLetter("ness")){
(self::getStemM(4)>0) && self::replaceLetter(4,"");
break;
}
break;
}
}
/**
* step 4
*/
private static function step4(){
switch (substr(self::$word, -2, 1)){
case 'a' :
if(self::matchLetter("al")){
(self::getStemM(2)>1) && self::replaceLetter(2,"");
break;
}
break;
case 'c' :
if(self::matchLetter("ance")){
(self::getStemM(4)>1) && self::replaceLetter(4,"");
break;
} else if (self::matchLetter("ence")){
(self::getStemM(4)>1) && self::replaceLetter(4,"");
break;
}
break;
case 'e' :
if(self::matchLetter("er")){
(self::getStemM(2)>1) && self::replaceLetter(2,"");
break;
}
break;
case 'i' :
if(self::matchLetter("ic")){
(self::getStemM(2)>1) && self::replaceLetter(2,"");
break;
}
case 'l' :
if(self::matchLetter("able")){
(self::getStemM(4)>1) && self::replaceLetter(4,"");
break;
} else if (self::matchLetter("ible")){
(self::getStemM(4)>1) && self::replaceLetter(4,"");
break;
}
break;
case 'n' :
if(self::matchLetter("ant")){
(self::getStemM(3)>1) && self::replaceLetter(3,"");
break;
} else if (self::matchLetter("ement")){
(self::getStemM(5)>1) && self::replaceLetter(5,"");
break;
} else if (self::matchLetter("ment")){
(self::getStemM(4)>1) && self::replaceLetter(4,"");
break;
} else if (self::matchLetter("ent")){
(self::getStemM(3)>1) && self::replaceLetter(3,"");
break;
}
break;
case 'o' :
if(self::matchLetter("sion")){
(self::getStemM(3)>1) && self::replaceLetter(3,"");
break;
} else if (self::matchLetter("tion")){
(self::getStemM(3)>1) && self::replaceLetter(3,"");
break;
} else if (self::matchLetter("ou")){
(self::getStemM(2)>1) && self::replaceLetter(2,"");
break;
}
break;
case 's' :
if(self::matchLetter("ism")){
(self::getStemM(3)>1) && self::replaceLetter(3,"");
break;
}
break;
case 't' :
if(self::matchLetter("ate")){
(self::getStemM(3)>1) && self::replaceLetter(3,"");
break;
} else if (self::matchLetter("iti")){
(self::getStemM(3)>1) && self::replaceLetter(3,"");
break;
}
break;
case 'u' :
if(self::matchLetter("ous")){
(self::getStemM(3)>1) && self::replaceLetter(3,"");
break;
}
break;
case 'v' :
if(self::matchLetter("ive")){
(self::getStemM(3)>1) && self::replaceLetter(3,"");
break;
}
break;
case 'z' :
if(self::matchLetter("ize")){
(self::getStemM(3)>1) && self::replaceLetter(3,"");
break;
}
break;
}
}
/**
* step 5
*/
private static function step5(){
if (self::matchLetter("e")){
if (self::getStemM(1)>1){
self::replaceLetter(1,"");
}else if ((self::getStemM(1)==1) && !self::stemEndWithCVC(1)){
self::replaceLetter(1,"");
}
}
if (((self::matchLetter("dd"))||(self::matchLetter("ll")))&&(self::getStemM(0)>1)){
self::$word = substr(self::$word, 0 ,-1);
}
}
/**
* check whether the suffix of the word matches $strOld
* @param (string) $strOld String to check
* @return (bool) Result
*/
private static function matchLetter($strOld){
return (substr(self::$word, -strlen($strOld)) == $strOld);
}
/**
* replace the last ($offset) letters with $strNew
* @param (int) $offset offset intiger
* @param (string) $strNew String to replace with
*/
private static function replaceLetter($offset, $strNew){
self::$word = self::getSubString($offset).$strNew;
}
/**
* get the substring without the last ($offset) letters
* @param (int) $offset offset intiger
* @return (bool) Result
*/
private static function getSubString($offset){
return ($offset) ? substr(self::$word, 0, -$offset) : (self::$word);
}
/**
* get M of the substring without the last ($offset) letters
* @param (int) $offset offset intiger
* @return (bool) Result
*/
private static function getStemM($offset){
$stem = self::getSubString($offset);
preg_match_all(PorterStemmer::$regexVC, $stem, $matched);
return sizeOf($matched[1]);
}
/**
* check whether the last letters of the substring
* without the last ($offset) letters matches $chLetter
* @param (int) $offset offset intiger
* @param (string) $Letter String to check
* @return (bool) Result
*/
private static function stemEndWithLetter($offset, $Letter){
$stem = self::getSubString($offset);
return (substr($stem, -1 ,1) == $Letter);
}
/**
* check whether the substring without the last ($offset) letters
* contains a vowel
* @param (int) $offset offset intiger
* @return (bool) Result
*/
private static function stemContainVowel($offset){
$stem = self::getSubString($offset);
return preg_match(self::$regexVowel, $stem);
}
/**
* check whether the last letters of the substring
* without the last ($offset) letters matches double Consonant
* @param (int) $offset offset intiger
* @return (bool) Result
*/
private static function stemEndWithCC($offset){
$stem = self::getSubString($offset);
$temp1 = substr($stem, -1, 1);
$temp2 = substr($stem, -2, 1);
return (($temp1==$temp2) && (preg_match(self::$regexConsonant, $temp1)));
}
/**
* check whether the last letters of the substring
* without the last ($offset) letters matches CVC
* @param (int) $offset offset intiger
* @return (bool) Result
*/
private static function stemEndWithCVC($offset){
$stem = self::getSubString($offset);
$temp = substr($stem, -3, 3);
return (preg_match(self::$regexCVC, $temp));
}
}
?>