|
||||||||||
PREV CLASS NEXT CLASS | FRAMES NO FRAMES | |||||||||
SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD |
java.lang.Object org.apache.lucene.util.AttributeSource org.apache.lucene.analysis.TokenStream org.apache.lucene.analysis.TokenFilter org.apache.lucene.analysis.compound.CompoundWordTokenFilterBase
public abstract class CompoundWordTokenFilterBase
Base class for decomposition token filters.
You must specify the required Version
compatibility when creating
CompoundWordTokenFilterBase:
If you pass in a CharArraySet
as dictionary,
it should be case-insensitive unless it contains only lowercased entries and you
have LowerCaseFilter
before this filter in your analysis chain.
For optional performance (as this filter does lots of lookups to the dictionary,
you should use the latter analysis chain/CharArraySet). Be aware: If you supply arbitrary
Sets
to the ctors or String[]
dictionaries, they will be automatically
transformed to case-insensitive!
Nested Class Summary | |
---|---|
protected class |
CompoundWordTokenFilterBase.CompoundToken
Helper class to hold decompounded token information |
Nested classes/interfaces inherited from class org.apache.lucene.util.AttributeSource |
---|
org.apache.lucene.util.AttributeSource.AttributeFactory, org.apache.lucene.util.AttributeSource.State |
Field Summary | |
---|---|
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 org.apache.lucene.analysis.tokenattributes.OffsetAttribute |
offsetAtt
|
protected boolean |
onlyLongestMatch
|
protected org.apache.lucene.analysis.tokenattributes.CharTermAttribute |
termAtt
|
protected LinkedList<CompoundWordTokenFilterBase.CompoundToken> |
tokens
|
Fields inherited from class org.apache.lucene.analysis.TokenFilter |
---|
input |
Constructor Summary | |
---|---|
protected |
CompoundWordTokenFilterBase(org.apache.lucene.analysis.TokenStream input,
Set<?> dictionary)
Deprecated. use CompoundWordTokenFilterBase(Version, TokenStream, Set) instead |
protected |
CompoundWordTokenFilterBase(org.apache.lucene.analysis.TokenStream input,
Set<?> dictionary,
boolean onlyLongestMatch)
Deprecated. use CompoundWordTokenFilterBase(Version, TokenStream, Set, boolean) instead |
protected |
CompoundWordTokenFilterBase(org.apache.lucene.analysis.TokenStream input,
Set<?> dictionary,
int minWordSize,
int minSubwordSize,
int maxSubwordSize,
boolean onlyLongestMatch)
Deprecated. use CompoundWordTokenFilterBase(Version, TokenStream, Set, int, int, int, boolean) instead |
protected |
CompoundWordTokenFilterBase(org.apache.lucene.analysis.TokenStream input,
String[] dictionary)
Deprecated. use CompoundWordTokenFilterBase(Version, TokenStream, String[]) instead |
protected |
CompoundWordTokenFilterBase(org.apache.lucene.analysis.TokenStream input,
String[] dictionary,
boolean onlyLongestMatch)
Deprecated. use CompoundWordTokenFilterBase(Version, TokenStream, String[], boolean) instead |
protected |
CompoundWordTokenFilterBase(org.apache.lucene.analysis.TokenStream input,
String[] dictionary,
int minWordSize,
int minSubwordSize,
int maxSubwordSize,
boolean onlyLongestMatch)
Deprecated. use CompoundWordTokenFilterBase(Version, TokenStream, String[], int, int, int, boolean) instead |
protected |
CompoundWordTokenFilterBase(org.apache.lucene.util.Version matchVersion,
org.apache.lucene.analysis.TokenStream input,
Set<?> dictionary)
|
protected |
CompoundWordTokenFilterBase(org.apache.lucene.util.Version matchVersion,
org.apache.lucene.analysis.TokenStream input,
Set<?> dictionary,
boolean onlyLongestMatch)
|
protected |
CompoundWordTokenFilterBase(org.apache.lucene.util.Version matchVersion,
org.apache.lucene.analysis.TokenStream input,
Set<?> dictionary,
int minWordSize,
int minSubwordSize,
int maxSubwordSize,
boolean onlyLongestMatch)
|
protected |
CompoundWordTokenFilterBase(org.apache.lucene.util.Version matchVersion,
org.apache.lucene.analysis.TokenStream input,
String[] dictionary)
|
protected |
CompoundWordTokenFilterBase(org.apache.lucene.util.Version matchVersion,
org.apache.lucene.analysis.TokenStream input,
String[] dictionary,
boolean onlyLongestMatch)
|
protected |
CompoundWordTokenFilterBase(org.apache.lucene.util.Version matchVersion,
org.apache.lucene.analysis.TokenStream input,
String[] dictionary,
int minWordSize,
int minSubwordSize,
int maxSubwordSize,
boolean onlyLongestMatch)
|
Method Summary | |
---|---|
protected abstract void |
decompose()
Decomposes the current termAtt and places CompoundWordTokenFilterBase.CompoundToken instances in the tokens list. |
boolean |
incrementToken()
|
static org.apache.lucene.analysis.CharArraySet |
makeDictionary(org.apache.lucene.util.Version matchVersion,
String[] dictionary)
Deprecated. Only available for backwards compatibility. |
void |
reset()
|
Methods inherited from class org.apache.lucene.analysis.TokenFilter |
---|
close, end |
Methods inherited from class org.apache.lucene.util.AttributeSource |
---|
addAttribute, addAttributeImpl, captureState, clearAttributes, cloneAttributes, copyTo, equals, getAttribute, getAttributeClassesIterator, getAttributeFactory, getAttributeImplsIterator, hasAttribute, hasAttributes, hashCode, reflectAsString, reflectWith, restoreState, toString |
Methods inherited from class java.lang.Object |
---|
clone, finalize, getClass, notify, notifyAll, wait, wait, wait |
Field Detail |
---|
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<CompoundWordTokenFilterBase.CompoundToken> tokens
protected final int minWordSize
protected final int minSubwordSize
protected final int maxSubwordSize
protected final boolean onlyLongestMatch
protected final org.apache.lucene.analysis.tokenattributes.CharTermAttribute termAtt
protected final org.apache.lucene.analysis.tokenattributes.OffsetAttribute offsetAtt
Constructor Detail |
---|
@Deprecated protected CompoundWordTokenFilterBase(org.apache.lucene.analysis.TokenStream input, String[] dictionary, int minWordSize, int minSubwordSize, int maxSubwordSize, boolean onlyLongestMatch)
CompoundWordTokenFilterBase(Version, TokenStream, String[], int, int, int, boolean)
instead
@Deprecated protected CompoundWordTokenFilterBase(org.apache.lucene.analysis.TokenStream input, String[] dictionary, boolean onlyLongestMatch)
CompoundWordTokenFilterBase(Version, TokenStream, String[], boolean)
instead
@Deprecated protected CompoundWordTokenFilterBase(org.apache.lucene.analysis.TokenStream input, Set<?> dictionary, boolean onlyLongestMatch)
CompoundWordTokenFilterBase(Version, TokenStream, Set, boolean)
instead
@Deprecated protected CompoundWordTokenFilterBase(org.apache.lucene.analysis.TokenStream input, String[] dictionary)
CompoundWordTokenFilterBase(Version, TokenStream, String[])
instead
@Deprecated protected CompoundWordTokenFilterBase(org.apache.lucene.analysis.TokenStream input, Set<?> dictionary)
CompoundWordTokenFilterBase(Version, TokenStream, Set)
instead
@Deprecated protected CompoundWordTokenFilterBase(org.apache.lucene.analysis.TokenStream input, Set<?> dictionary, int minWordSize, int minSubwordSize, int maxSubwordSize, boolean onlyLongestMatch)
CompoundWordTokenFilterBase(Version, TokenStream, Set, int, int, int, boolean)
instead
protected CompoundWordTokenFilterBase(org.apache.lucene.util.Version matchVersion, org.apache.lucene.analysis.TokenStream input, String[] dictionary, int minWordSize, int minSubwordSize, int maxSubwordSize, boolean onlyLongestMatch)
protected CompoundWordTokenFilterBase(org.apache.lucene.util.Version matchVersion, org.apache.lucene.analysis.TokenStream input, String[] dictionary, boolean onlyLongestMatch)
protected CompoundWordTokenFilterBase(org.apache.lucene.util.Version matchVersion, org.apache.lucene.analysis.TokenStream input, Set<?> dictionary, boolean onlyLongestMatch)
protected CompoundWordTokenFilterBase(org.apache.lucene.util.Version matchVersion, org.apache.lucene.analysis.TokenStream input, String[] dictionary)
protected CompoundWordTokenFilterBase(org.apache.lucene.util.Version matchVersion, org.apache.lucene.analysis.TokenStream input, Set<?> dictionary)
protected CompoundWordTokenFilterBase(org.apache.lucene.util.Version matchVersion, org.apache.lucene.analysis.TokenStream input, Set<?> dictionary, int minWordSize, int minSubwordSize, int maxSubwordSize, boolean onlyLongestMatch)
Method Detail |
---|
@Deprecated public static org.apache.lucene.analysis.CharArraySet makeDictionary(org.apache.lucene.util.Version matchVersion, String[] dictionary)
public final boolean incrementToken() throws IOException
incrementToken
in class org.apache.lucene.analysis.TokenStream
IOException
protected abstract void decompose()
termAtt
and places CompoundWordTokenFilterBase.CompoundToken
instances in the tokens
list.
The original token may not be placed in the list, as it is automatically passed through this filter.
public void reset() throws IOException
reset
in class org.apache.lucene.analysis.TokenFilter
IOException
|
||||||||||
PREV CLASS NEXT CLASS | FRAMES NO FRAMES | |||||||||
SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD |