|
||||||||||
PREV CLASS NEXT CLASS | FRAMES NO FRAMES | |||||||||
SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD |
java.lang.Object org.apache.lucene.analysis.ja.dict.BinaryDictionary
public abstract class BinaryDictionary
Base class for a binary-encoded in-memory dictionary.
Field Summary | |
---|---|
static String |
DICT_FILENAME_SUFFIX
|
static String |
DICT_HEADER
|
static int |
HAS_BASEFORM
flag that the entry has baseform data. |
static int |
HAS_PRONUNCIATION
flag that the entry has pronunciation data. |
static int |
HAS_READING
flag that the entry has reading data. |
static String |
POSDICT_FILENAME_SUFFIX
|
static String |
POSDICT_HEADER
|
static String |
TARGETMAP_FILENAME_SUFFIX
|
static String |
TARGETMAP_HEADER
|
static int |
VERSION
|
Fields inherited from interface org.apache.lucene.analysis.ja.dict.Dictionary |
---|
INTERNAL_SEPARATOR |
Constructor Summary | |
---|---|
protected |
BinaryDictionary()
|
Method Summary | |
---|---|
String |
getBaseForm(int wordId,
char[] surfaceForm,
int off,
int len)
Get base form of word |
static InputStream |
getClassResource(Class<?> clazz,
String suffix)
|
String |
getInflectionForm(int wordId)
Get inflection form of tokens |
String |
getInflectionType(int wordId)
Get inflection type of tokens |
int |
getLeftId(int wordId)
Get left id of specified word |
String |
getPartOfSpeech(int wordId)
Get Part-Of-Speech of tokens |
String |
getPronunciation(int wordId,
char[] surface,
int off,
int len)
Get pronunciation of tokens |
String |
getReading(int wordId,
char[] surface,
int off,
int len)
Get reading of tokens |
protected InputStream |
getResource(String suffix)
|
int |
getRightId(int wordId)
Get right id of specified word |
int |
getWordCost(int wordId)
Get word cost of specified word |
void |
lookupWordIds(int sourceId,
IntsRef ref)
|
Methods inherited from class java.lang.Object |
---|
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait |
Field Detail |
---|
public static final String DICT_FILENAME_SUFFIX
public static final String TARGETMAP_FILENAME_SUFFIX
public static final String POSDICT_FILENAME_SUFFIX
public static final String DICT_HEADER
public static final String TARGETMAP_HEADER
public static final String POSDICT_HEADER
public static final int VERSION
public static final int HAS_BASEFORM
public static final int HAS_READING
public static final int HAS_PRONUNCIATION
Constructor Detail |
---|
protected BinaryDictionary() throws IOException
IOException
Method Detail |
---|
protected final InputStream getResource(String suffix) throws IOException
IOException
public static final InputStream getClassResource(Class<?> clazz, String suffix) throws IOException
IOException
public void lookupWordIds(int sourceId, IntsRef ref)
public int getLeftId(int wordId)
Dictionary
getLeftId
in interface Dictionary
public int getRightId(int wordId)
Dictionary
getRightId
in interface Dictionary
public int getWordCost(int wordId)
Dictionary
getWordCost
in interface Dictionary
public String getBaseForm(int wordId, char[] surfaceForm, int off, int len)
Dictionary
getBaseForm
in interface Dictionary
wordId
- word ID of token
public String getReading(int wordId, char[] surface, int off, int len)
Dictionary
getReading
in interface Dictionary
wordId
- word ID of token
public String getPartOfSpeech(int wordId)
Dictionary
getPartOfSpeech
in interface Dictionary
wordId
- word ID of token
public String getPronunciation(int wordId, char[] surface, int off, int len)
Dictionary
getPronunciation
in interface Dictionary
wordId
- word ID of token
public String getInflectionType(int wordId)
Dictionary
getInflectionType
in interface Dictionary
wordId
- word ID of token
public String getInflectionForm(int wordId)
Dictionary
getInflectionForm
in interface Dictionary
wordId
- word ID of token
|
||||||||||
PREV CLASS NEXT CLASS | FRAMES NO FRAMES | |||||||||
SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD |