org.lionsoul.jcseg.tokenizer.core

Class ADictionary

java.lang.Object

org.lionsoul.jcseg.tokenizer.core.ADictionary

Direct Known Subclasses:

Dictionary

public abstract class ADictionary
extends Object

Dictionary abstract super class

Author:

chenxin

Field Summary

Fields

Modifier and Type	Field and Description
static String	AL_TODO_FILE the default auto load task file name
protected JcsegTaskConfig	config
int	mixPrefixLength
int	mixSuffixLength maximum length for the Chinese words after the LATIN word or the one before it used to match Chinese and English mix word, like 'B超,AA制...' or style compose style like '卡拉ok'.
protected boolean	sync

Constructor Summary

Constructors

Constructor and Description
ADictionary(JcsegTaskConfig config, Boolean sync) initialize the ADictionary

Method Summary

Modifier and Type	Method and Description
abstract IWord	add(int t, IWord word) directly add a IWord item to the dictionary
abstract IWord	add(int t, String key, int type) add a new word to the dictionary
abstract IWord	add(int t, String key, int fre, int type) add a new word to the dictionary
abstract IWord	add(int t, String key, int fre, int type, String entity) add a new word to the dictionary with its statistics frequency
abstract IWord	add(int t, String key, int type, String entity) add a new word to the dictionary
abstract IWord	get(int t, String key) return the IWord associate with the given key.
JcsegTaskConfig	getConfig()
static int	getIndex(String key) get the key's type index located in ILexicon interface
boolean	isSync()
void	load(File file) load all the words from a specified lexicon file
void	load(InputStream is) load all the words from a specified lexicon input stream
void	load(String file) load all the words from a specified lexicon path
void	loadClassPath() load all the words from all the files under the specified class path.
void	loadDirectory(String lexDir) load the all the words form all the files under a specified lexicon directory
static void	loadWords(JcsegTaskConfig config, ADictionary dic, File file) load all the words in the specified lexicon file into the dictionary
static void	loadWords(JcsegTaskConfig config, ADictionary dic, InputStream is) load words from a InputStream
static void	loadWords(JcsegTaskConfig config, ADictionary dic, String file) load all the words from a specified lexicon file path
abstract boolean	match(int t, String key) loop up the dictionary, check the given key is in the dictionary or not
abstract void	remove(int t, String key) remove the mapping associate with the given key
static boolean	resetPrefixLength(JcsegTaskConfig config, ADictionary dic, int mixLength) check and reset the value of mixPrefixLength
static boolean	resetSuffixLength(JcsegTaskConfig config, ADictionary dic, int mixLength) check and reset the value of the mixSuffixLength
void	setConfig(JcsegTaskConfig config)
abstract int	size(int t) return the size of the dictionary
void	startAutoload() start the lexicon autoload thread
void	stopAutoload()

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Field Detail

AL_TODO_FILE

public static final String AL_TODO_FILE

the default auto load task file name

See Also:

Constant Field Values

config

protected JcsegTaskConfig config

sync

protected boolean sync

mixSuffixLength

public volatile int mixSuffixLength

maximum length for the Chinese words after the LATIN word or the one before it used to match Chinese and English mix word, like 'B超,AA制...' or style compose style like '卡拉ok'. since 2.0.1 the value will be reset during the lexicon load process

mixPrefixLength

public volatile int mixPrefixLength

Constructor Detail

ADictionary

public ADictionary(JcsegTaskConfig config,
                   Boolean sync)

initialize the ADictionary

Parameters:

config -

sync -

Method Detail

load

public void load(File file)
          throws NumberFormatException,
                 FileNotFoundException,
                 IOException

load all the words from a specified lexicon file

Parameters:

file -

Throws:

IOException

FileNotFoundException

NumberFormatException

load

public void load(String file)
          throws NumberFormatException,
                 FileNotFoundException,
                 IOException

load all the words from a specified lexicon path

Parameters:

file -

Throws:

IOException

FileNotFoundException

NumberFormatException

load

public void load(InputStream is)
          throws NumberFormatException,
                 IOException

load all the words from a specified lexicon input stream

Parameters:

is -

Throws:

IOException

NumberFormatException

loadDirectory

public void loadDirectory(String lexDir)
                   throws IOException

load the all the words form all the files under a specified lexicon directory

Parameters:

lexDir -

Throws:

IOException

loadClassPath

public void loadClassPath()
                   throws IOException

load all the words from all the files under the specified class path. added at 2016/07/12: only in the jar file could the ZipInputStream available add IDE classpath supported here

Parameters:

lexDir -

Throws:

IOException

Since:

1.9.9

startAutoload

public void startAutoload()

start the lexicon autoload thread

stopAutoload

public void stopAutoload()

isSync

public boolean isSync()

match

public abstract boolean match(int t,
                              String key)

loop up the dictionary, check the given key is in the dictionary or not

Parameters:

t -

key -

Returns:

true for matched false for not match.

add

public abstract IWord add(int t,
                          IWord word)

directly add a IWord item to the dictionary

Parameters:

t -

word -

IWord -

add

public abstract IWord add(int t,
                          String key,
                          int fre,
                          int type,
                          String entity)

add a new word to the dictionary with its statistics frequency

Parameters:

t -

key -

fre -

type -

entity -

Returns:

IWord

add

public abstract IWord add(int t,
                          String key,
                          int fre,
                          int type)

add a new word to the dictionary

Parameters:

t -

key -

fre -

type -

IWord -

add

public abstract IWord add(int t,
                          String key,
                          int type)

add a new word to the dictionary

Parameters:

t -

key -

type -

IWord -

add

public abstract IWord add(int t,
                          String key,
                          int type,
                          String entity)

add a new word to the dictionary

Parameters:

t -

key -

type -

entity -

IWord -

get

public abstract IWord get(int t,
                          String key)

return the IWord associate with the given key. if there is not mapping for the key null will be return

Parameters:

t -

key -

remove

public abstract void remove(int t,
                            String key)

remove the mapping associate with the given key

Parameters:

t -

key -

size

public abstract int size(int t)

return the size of the dictionary

Parameters:

t -

Returns:

int

getIndex

public static int getIndex(String key)

get the key's type index located in ILexicon interface

Parameters:

key -

Returns:

int

getConfig

public JcsegTaskConfig getConfig()

setConfig

public void setConfig(JcsegTaskConfig config)

loadWords

public static void loadWords(JcsegTaskConfig config,
                             ADictionary dic,
                             File file)
                      throws NumberFormatException,
                             FileNotFoundException,
                             IOException

load all the words in the specified lexicon file into the dictionary

Parameters:

config -

dic -

file -

Throws:

IOException

FileNotFoundException

NumberFormatException

loadWords

public static void loadWords(JcsegTaskConfig config,
                             ADictionary dic,
                             String file)
                      throws NumberFormatException,
                             FileNotFoundException,
                             IOException

load all the words from a specified lexicon file path

Parameters:

config -

dic -

file -

Throws:

IOException

FileNotFoundException

NumberFormatException

loadWords

public static void loadWords(JcsegTaskConfig config,
                             ADictionary dic,
                             InputStream is)
                      throws NumberFormatException,
                             IOException

load words from a InputStream

Parameters:

config -

dic -

is -

Throws:

IOException

NumberFormatException

resetPrefixLength

public static boolean resetPrefixLength(JcsegTaskConfig config,
                                        ADictionary dic,
                                        int mixLength)

check and reset the value of mixPrefixLength

Parameters:

config -

dic -

mixLength -

Returns:

boolean

resetSuffixLength

public static boolean resetSuffixLength(JcsegTaskConfig config,
                                        ADictionary dic,
                                        int mixLength)

check and reset the value of the mixSuffixLength

Parameters:

config -

dic -

mixLength -

Returns:

boolean