public abstract class CompoundWordTokenFilterBase
extends org.apache.lucene.analysis.TokenFilter
Modifier and Type | Field and Description |
---|---|
static int |
DEFAULT_MAX_SUBWORD_SIZE
The default for maximal length of subwords that get propagated to the output of this filter
|
static int |
DEFAULT_MIN_SUBWORD_SIZE
The default for minimal length of subwords that get propagated to the output of this filter
|
static int |
DEFAULT_MIN_WORD_SIZE
The default for minimal word length that gets decomposed
|
protected org.apache.lucene.analysis.CharArraySet |
dictionary |
protected int |
maxSubwordSize |
protected int |
minSubwordSize |
protected int |
minWordSize |
protected boolean |
onlyLongestMatch |
protected LinkedList |
tokens |
Modifier | Constructor and Description |
---|---|
protected |
CompoundWordTokenFilterBase(org.apache.lucene.analysis.TokenStream input,
Set dictionary) |
protected |
CompoundWordTokenFilterBase(org.apache.lucene.analysis.TokenStream input,
Set dictionary,
boolean onlyLongestMatch) |
protected |
CompoundWordTokenFilterBase(org.apache.lucene.analysis.TokenStream input,
Set dictionary,
int minWordSize,
int minSubwordSize,
int maxSubwordSize,
boolean onlyLongestMatch) |
protected |
CompoundWordTokenFilterBase(org.apache.lucene.analysis.TokenStream input,
String[] dictionary) |
protected |
CompoundWordTokenFilterBase(org.apache.lucene.analysis.TokenStream input,
String[] dictionary,
boolean onlyLongestMatch) |
protected |
CompoundWordTokenFilterBase(org.apache.lucene.analysis.TokenStream input,
String[] dictionary,
int minWordSize,
int minSubwordSize,
int maxSubwordSize,
boolean onlyLongestMatch) |
Modifier and Type | Method and Description |
---|---|
protected static void |
addAllLowerCase(Set target,
Collection col) |
protected org.apache.lucene.analysis.Token |
createToken(int offset,
int length,
org.apache.lucene.analysis.Token prototype) |
protected void |
decompose(org.apache.lucene.analysis.Token token) |
protected abstract void |
decomposeInternal(org.apache.lucene.analysis.Token token) |
boolean |
incrementToken() |
static Set |
makeDictionary(String[] dictionary)
Create a set of words from an array
The resulting Set does case insensitive matching
TODO We should look for a faster dictionary lookup approach.
|
protected static char[] |
makeLowerCaseCopy(char[] buffer) |
org.apache.lucene.analysis.Token |
next()
Deprecated.
Will be removed in Lucene 3.0. This method is final, as it should
not be overridden. Delegates to the backwards compatibility layer.
|
org.apache.lucene.analysis.Token |
next(org.apache.lucene.analysis.Token reusableToken)
Deprecated.
Will be removed in Lucene 3.0. This method is final, as it should
not be overridden. Delegates to the backwards compatibility layer.
|
void |
reset() |
getOnlyUseNewAPI, setOnlyUseNewAPI
addAttribute, addAttributeImpl, captureState, clearAttributes, cloneAttributes, equals, getAttribute, getAttributeClassesIterator, getAttributeFactory, getAttributeImplsIterator, hasAttribute, hasAttributes, hashCode, restoreState, toString
public static final int DEFAULT_MIN_WORD_SIZE
public static final int DEFAULT_MIN_SUBWORD_SIZE
public static final int DEFAULT_MAX_SUBWORD_SIZE
protected final org.apache.lucene.analysis.CharArraySet dictionary
protected final LinkedList tokens
protected final int minWordSize
protected final int minSubwordSize
protected final int maxSubwordSize
protected final boolean onlyLongestMatch
protected CompoundWordTokenFilterBase(org.apache.lucene.analysis.TokenStream input, String[] dictionary, int minWordSize, int minSubwordSize, int maxSubwordSize, boolean onlyLongestMatch)
protected CompoundWordTokenFilterBase(org.apache.lucene.analysis.TokenStream input, String[] dictionary, boolean onlyLongestMatch)
protected CompoundWordTokenFilterBase(org.apache.lucene.analysis.TokenStream input, Set dictionary, boolean onlyLongestMatch)
protected CompoundWordTokenFilterBase(org.apache.lucene.analysis.TokenStream input, String[] dictionary)
protected CompoundWordTokenFilterBase(org.apache.lucene.analysis.TokenStream input, Set dictionary)
protected CompoundWordTokenFilterBase(org.apache.lucene.analysis.TokenStream input, Set dictionary, int minWordSize, int minSubwordSize, int maxSubwordSize, boolean onlyLongestMatch)
public static final Set makeDictionary(String[] dictionary)
dictionary
- Set
of lowercased termspublic final boolean incrementToken() throws IOException
incrementToken
in class org.apache.lucene.analysis.TokenStream
IOException
public final org.apache.lucene.analysis.Token next(org.apache.lucene.analysis.Token reusableToken) throws IOException
next
in class org.apache.lucene.analysis.TokenStream
IOException
public final org.apache.lucene.analysis.Token next() throws IOException
next
in class org.apache.lucene.analysis.TokenStream
IOException
protected static final void addAllLowerCase(Set target, Collection col)
protected static char[] makeLowerCaseCopy(char[] buffer)
protected final org.apache.lucene.analysis.Token createToken(int offset, int length, org.apache.lucene.analysis.Token prototype)
protected void decompose(org.apache.lucene.analysis.Token token)
protected abstract void decomposeInternal(org.apache.lucene.analysis.Token token)
public void reset() throws IOException
reset
in class org.apache.lucene.analysis.TokenFilter
IOException
Copyright © 2000-2012 Apache Software Foundation. All Rights Reserved.