File	Doc	Category	Size	Date	Package
RussianAnalyzer.java	API Doc	Apache Lucene 1.9	7146	Mon Feb 20 09:18:52 GMT 2006	org.apache.lucene.analysis.ru

RussianAnalyzer

• java.lang.Object
  • org.apache.lucene.analysis.Analyzer

(Omit source code)

Fields Summary
private static final char	A
private static final char	B
private static final char	V
private static final char	G
private static final char	D
private static final char	E
private static final char	ZH
private static final char	Z
private static final char	I
private static final char	I_
private static final char	K
private static final char	L
private static final char	M
private static final char	N
private static final char	O
private static final char	P
private static final char	R
private static final char	S
private static final char	T
private static final char	U
private static final char	X
private static final char	CH
private static final char	SH
private static final char	SHCH
private static final char	Y
private static final char	SOFT
private static final char	AE
private static final char	IU
private static final char	IA
private static char[]	RUSSIAN_STOP_WORDS List of typical Russian stopwords.
private Set	stopSet Contains the stopwords used with the StopFilter.
private char[]	charset Charset for Russian letters. Represents encoding for 32 lowercase Russian letters. Predefined charsets can be taken from RussianCharSets class

Constructors Summary
public RussianAnalyzer() charset = RussianCharsets.UnicodeRussian; stopSet = StopFilter.makeStopSet( makeStopWords(RussianCharsets.UnicodeRussian));
public RussianAnalyzer(char[] charset) Builds an analyzer. this.charset = charset; stopSet = StopFilter.makeStopSet(makeStopWords(charset));
public RussianAnalyzer(char[] charset, String[] stopwords) Builds an analyzer with the given stop words. this.charset = charset; stopSet = StopFilter.makeStopSet(stopwords);
public RussianAnalyzer(char[] charset, Hashtable stopwords) Builds an analyzer with the given stop words. todo create a Set version of this ctor this.charset = charset; stopSet = new HashSet(stopwords.keySet());

Methods Summary
private static java.lang.String[]	makeStopWords(char[] charset) String[] res = new String[RUSSIAN_STOP_WORDS.length]; for (int i = 0; i < res.length; i++) { char[] theStopWord = RUSSIAN_STOP_WORDS[i]; // translate the word, using the charset StringBuffer theWord = new StringBuffer(); for (int j = 0; j < theStopWord.length; j++) { theWord.append(charset[theStopWord[j]]); } res[i] = theWord.toString(); } return res;
public org.apache.lucene.analysis.TokenStream	tokenStream(java.lang.String fieldName, java.io.Reader reader) Creates a TokenStream which tokenizes all the text in the provided Reader. return A TokenStream build from a RussianLetterTokenizer filtered with RussianLowerCaseFilter, StopFilter, and RussianStemFilter TokenStream result = new RussianLetterTokenizer(reader, charset); result = new RussianLowerCaseFilter(result, charset); result = new StopFilter(result, stopSet); result = new RussianStemFilter(result, charset); return result;