public abstract class HebrewAnalyzer
extends org.apache.lucene.analysis.Analyzer
| Modifier and Type | Class and Description |
|---|---|
static class |
HebrewAnalyzer.WordType |
org.apache.lucene.analysis.Analyzer.GlobalReuseStrategy, org.apache.lucene.analysis.Analyzer.PerFieldReuseStrategy, org.apache.lucene.analysis.Analyzer.ReuseStrategy, org.apache.lucene.analysis.Analyzer.TokenStreamComponents| Modifier and Type | Field and Description |
|---|---|
protected org.apache.lucene.analysis.util.CharArraySet |
commonWords |
protected static com.code972.hebmorph.datastructures.DictRadix<com.code972.hebmorph.MorphData> |
customWords |
protected static com.code972.hebmorph.datastructures.DictRadix<com.code972.hebmorph.MorphData> |
dictRadix |
protected com.code972.hebmorph.lemmafilters.LemmaFilterBase |
lemmaFilter |
protected static org.apache.lucene.util.Version |
matchVersion |
protected char |
originalTermSuffix |
static com.code972.hebmorph.datastructures.DictRadix<Integer> |
prefixesTree |
protected static com.code972.hebmorph.datastructures.DictRadix<Byte> |
SPECIAL_TOKENIZATION_CASES |
| Modifier | Constructor and Description |
|---|---|
protected |
HebrewAnalyzer() |
| Modifier and Type | Method and Description |
|---|---|
static boolean |
isHebrewWord(CharSequence word) |
static HebrewAnalyzer.WordType |
isRecognizedWord(String word,
boolean tolerate) |
static com.code972.hebmorph.datastructures.DictRadix<Byte> |
setCustomTokenizationCases(InputStream input) |
static com.code972.hebmorph.datastructures.DictRadix<com.code972.hebmorph.MorphData> |
setCustomWords(InputStream input) |
static void |
setDictRadix(com.code972.hebmorph.datastructures.DictRadix<com.code972.hebmorph.MorphData> radix) |
protected static final org.apache.lucene.util.Version matchVersion
public static final com.code972.hebmorph.datastructures.DictRadix<Integer> prefixesTree
protected static com.code972.hebmorph.datastructures.DictRadix<com.code972.hebmorph.MorphData> dictRadix
protected static com.code972.hebmorph.datastructures.DictRadix<com.code972.hebmorph.MorphData> customWords
protected final com.code972.hebmorph.lemmafilters.LemmaFilterBase lemmaFilter
protected final char originalTermSuffix
protected static com.code972.hebmorph.datastructures.DictRadix<Byte> SPECIAL_TOKENIZATION_CASES
protected org.apache.lucene.analysis.util.CharArraySet commonWords
protected HebrewAnalyzer()
throws IOException
IOExceptionpublic static com.code972.hebmorph.datastructures.DictRadix<Byte> setCustomTokenizationCases(InputStream input) throws IOException
IOExceptionpublic static void setDictRadix(com.code972.hebmorph.datastructures.DictRadix<com.code972.hebmorph.MorphData> radix)
public static com.code972.hebmorph.datastructures.DictRadix<com.code972.hebmorph.MorphData> setCustomWords(InputStream input) throws IOException
IOExceptionpublic static boolean isHebrewWord(CharSequence word)
public static HebrewAnalyzer.WordType isRecognizedWord(String word, boolean tolerate)
Copyright © 2014. All Rights Reserved.