Back | WordLists

CzechStemmerAgressive - CzechStemmerAgressive.txt

Download Complete Wordlist (18.92 K)
Download Complete Wordlist bzip2 Compressed (2.61 K)
Showing 67 Randomly Sampled Lines...
buffer.substring( len-3 ,len).equals("ost")||
buffer.substring( len-2 ,len).equals("\u00e9\u0159")){ //-é
buffer.substring( len-2,len).equals("mi")||
buffer.substring( len-4,len).equals("onek")||
buffer.substring( len-4,len).equa
}
buffer.substring( len-3 ,len).equals("ist")||
buffer.substring( len-2 ,len).equals("a\u010d")|| //
buffer.substring( len- 2 ,len).equals("\u017ee")){ //-že
buffer.substring( len-4,len).equals("a\u010
buffer.substring( len-2 ,len).equals("a\u010d")|| //-ač
removeDiminutive(sb);
* -removes case endings form nouns and adjectives, possesive adj. endings from names,
buffer.substring( len-2,len).equals("os")||
buffer.substring( len- 2 ,len).equals("ce")||
return result;
buffer.substring( len-3,len).equals("\u00fdmi")){ //-ými
buffer.substring( len- 2 ,len).equals("\u017ei")|| //-ži
//removes derivational sufixes from nouns
//
buffer.charAt(buffer.length()-1)=='n'||
buffer.substring( len-3,len).equals("o\u010dk")|| //-očk
return;
buffer.substring( len-4,len).equals("unek")||
buffer.substring( len-1,len).equals("y")||
return;
buffer.substring( len-3,len).equals("ich")||
buffer.substring( len-3,len).equals("emi")||
buffer.substring( len- 3 ,len).equals("isk"))){
buffer.substring( len-4,len).equals("a\u010dek")|| //aček
return;
return;
}
}
buffer.substring( len-2 ,len).equals("in")||
buffer.substring( len- 2 ,len).equals("\u0161t\u00ed")){ //-ští
buffer.substring( len-3 ,len).equals("isk")||
buffer.substring( len-3 ,len).equals("itb")||
int len=buffer.length();
buffer.substring( len-2 ,len).equals("ov")||
buffer.substring( len-3 ,len).equals("n\u00edk")|| //-ník
}
buffer.substring( len- 3 ,len).equals("\u010dt\u
buffer.substring( len-3 ,len).equals("oun")||
return;
palatalise(buffer);
return;
buffer.substring( len-5 ,len).equals("ovstv")||
buffer.substring( len-2 ,len).equals("\u00e1\u0159")|| //-ář
buffer.substring( len-4,len).equals("\u00ednek")){ //-ínek
buffer.substring( len-4 ,len).equals("teln")||
buffer.substring( len-2,len).equals("\u00e1m")|| //-ám
buffer.substring( len-3,len).equals("\u00ed\u010dk")|| //-íčk
buffer.substring( len-2,len).equals("\u00e1m")|
buffer.substring( len-1,len).equals("\u00fd")){ //-ý
buffer.substring( len-3,len).equals("\u00e9\u010dk")|| /
if(buffer.substring( len-3 ,len).equals("kyn")||
}//len>6
buffer.substring( len-4 ,len).equals("loun")||
buffer.charAt(buffer.length()-1)=='k'||
buffer.substring( len-4,len).equals("\u00e9\u010dek")|| //-éček
buffer.substring( len-5 ,len).equals("ovi\u0161t")|| //-ovišt
}
//removes augmentatives endings
buffer.substring( len-4,len).equ
buffer.substring( len-2 ,len).equals("\u00e9\u0159")){ //-éř
buffer.substring( len-2 ,len).equals("en")||


Back | WordLists