public override TokenStream create(TokenStream input)
{
return(new LowerCaseFilter(input));
}
public SnowballPorterFilter(TokenStream source, SnowballProgram stemmer, CharArraySet protWords) : base(source)
{
this.protWords = protWords;
this.stemmer = stemmer;
this.termAtt = (TermAttribute)addAttribute(typeof(TermAttribute));
}
public EnglishPorterFilter(TokenStream source, CharArraySet protWords) :
base(source, new org.tartarus.snowball.ext.EnglishStemmer(), protWords)
{
}
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: private void assertCollatesToSame(org.apache.lucene.analysis.TokenStream stream1, org.apache.lucene.analysis.TokenStream stream2) throws java.io.IOException
private void assertCollatesToSame(TokenStream stream1, TokenStream stream2)
{
stream1.reset();
stream2.reset();
CharTermAttribute term1 = stream1.addAttribute(typeof(CharTermAttribute));
CharTermAttribute term2 = stream2.addAttribute(typeof(CharTermAttribute));
assertTrue(stream1.incrementToken());
assertTrue(stream2.incrementToken());
assertEquals(term1.ToString(), term2.ToString());
assertFalse(stream1.incrementToken());
assertFalse(stream2.incrementToken());
stream1.end();
stream2.end();
stream1.close();
stream2.close();
}
public WordDelimiterFilter(TokenStream input, int generateWordParts, int generateNumberParts, int catenateWords, int catenateNumbers, int catenateAll) :
this(input, defaultWordDelimTable, generateWordParts, generateNumberParts, catenateWords, catenateNumbers, catenateAll, 1, 0, 1, null)
{
}
public override TokenStream create(TokenStream input)
{
return(new EnglishPorterFilter(input, protectedWords));
}
public WordDelimiterFilter(TokenStream input, byte[] charTypeTable, int generateWordParts, int generateNumberParts, int catenateWords, int catenateNumbers, int catenateAll) :
this(input, charTypeTable, generateWordParts, generateNumberParts, catenateWords, catenateNumbers, catenateAll, 1, 0, 1, null)
{
}
public WordDelimiterFilter(TokenStream input, int generateWordParts, int generateNumberParts, int catenateWords, int catenateNumbers, int catenateAll, int splitOnCaseChange, int preserveOriginal) :
this(input, defaultWordDelimTable, generateWordParts, generateNumberParts, catenateWords, catenateNumbers, catenateAll, splitOnCaseChange, preserveOriginal)
{
}
/**
* @param in Token stream to be filtered.
* @param generateWordParts If 1, causes parts of words to be generated: "PowerShot", "Power-Shot" => "Power" "Shot"
* @param generateNumberParts If 1, causes number subwords to be generated: "500-42" => "500" "42"
* @param catenateWords 1, causes maximum runs of word parts to be catenated: "wi-fi" => "wifi"
* @param catenateNumbers If 1, causes maximum runs of number parts to be catenated: "500-42" => "50042"
* @param catenateAll If 1, causes all subword parts to be catenated: "wi-fi-4000" => "wifi4000"
* @param splitOnCaseChange 1, causes "PowerShot" to be two tokens; ("Power-Shot" remains two parts regards)
* @param preserveOriginal If 1, includes original words in subwords: "500-42" => "500" "42" "500-42"
* @param splitOnNumerics 1, causes "j2se" to be three tokens; "j" "2" "se"
* @param stemEnglishPossessive If 1, causes trailing "'s" to be removed for each subword: "O'Neil's" => "O", "Neil"
* @param protWords If not null is the set of tokens to protect from being delimited
*/
public WordDelimiterFilter(TokenStream input, int generateWordParts, int generateNumberParts, int catenateWords, int catenateNumbers, int catenateAll, int splitOnCaseChange, int preserveOriginal, int splitOnNumerics, int stemEnglishPossessive, CharArraySet protWords) :
this(input, defaultWordDelimTable, generateWordParts, generateNumberParts, catenateWords, catenateNumbers, catenateAll, splitOnCaseChange, preserveOriginal, splitOnNumerics, stemEnglishPossessive, protWords)
{
}
public WordDelimiterFilter(TokenStream input, byte[] charTypeTable, int generateWordParts, int generateNumberParts, int catenateWords, int catenateNumbers, int catenateAll, int splitOnCaseChange, int preserveOriginal) :
this(input, charTypeTable, generateWordParts, generateNumberParts, catenateWords, catenateNumbers, catenateAll, splitOnCaseChange, preserveOriginal, 1, null)
{
}
public override TokenStream create(TokenStream input)
{
return(new LucidKStemFilter(input, protectedWords));
}