org.wltea.analyzer.core.Lexeme Maven / Gradle / Ivy
/*
* IK 中文分词 版本 7.7.1
* IK Analyzer release 7.7.1
*
* Licensed to the Apache Software Foundation (ASF) under one or more
* contributor license agreements. See the NOTICE file distributed with
* this work for additional information regarding copyright ownership.
* The ASF licenses this file to You under the Apache License, Version 2.0
* (the "License"); you may not use this file except in compliance with
* the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*
* 源代码由林良益([email protected])提供
* 版权声明 2012，乌龙茶工作室
* provided by Linliangyi and copyright 2012 by Oolong studio
*
* 7.7.1版本 由 Magese ([email protected]) 更新
* release 7.7.1 update by Magese([email protected])
*
*/
package org.wltea.analyzer.core;
/**
* IK词元对象
*/
@SuppressWarnings("unused")
public class Lexeme implements Comparable{
//英文
static final int TYPE_ENGLISH = 1;
//数字
static final int TYPE_ARABIC = 2;
//英文数字混合
static final int TYPE_LETTER = 3;
//中文词元
static final int TYPE_CNWORD = 4;
//中文单字
static final int TYPE_CNCHAR = 64;
//日韩文字
static final int TYPE_OTHER_CJK = 8;
//中文数词
static final int TYPE_CNUM = 16;
//中文量词
static final int TYPE_COUNT = 32;
//中文数量词
static final int TYPE_CQUAN = 48;
//词元的起始位移
private int offset;
//词元的相对起始位置
private int begin;
//词元的长度
private int length;
//词元文本
private String lexemeText;
//词元类型
private int lexemeType;
public Lexeme(int offset , int begin , int length , int lexemeType){
this.offset = offset;
this.begin = begin;
if(length < 0){
throw new IllegalArgumentException("length < 0");
}
this.length = length;
this.lexemeType = lexemeType;
}
/*
* 判断词元相等算法
* 起始位置偏移、起始位置、终止位置相同
* @see java.lang.Object#equals(Object o)
*/
public boolean equals(Object o){
if(o == null){
return false;
}
if(this == o){
return true;
}
if(o instanceof Lexeme){
Lexeme other = (Lexeme)o;
return this.offset == other.getOffset()
&& this.begin == other.getBegin()
&& this.length == other.getLength();
}else{
return false;
}
}
/*
* 词元哈希编码算法
* @see java.lang.Object#hashCode()
*/
public int hashCode(){
int absBegin = getBeginPosition();
int absEnd = getEndPosition();
return (absBegin * 37) + (absEnd * 31) + ((absBegin * absEnd) % getLength()) * 11;
}
/*
* 词元在排序集合中的比较算法
* @see java.lang.Comparable#compareTo(java.lang.Object)
*/
public int compareTo(Lexeme other) {
//起始位置优先
if(this.begin < other.getBegin()){
return -1;
}else if(this.begin == other.getBegin()){
//词元长度优先
//this.length < other.getLength()
return Integer.compare(other.getLength(), this.length);
}else{//this.begin > other.getBegin()
return 1;
}
}
private int getOffset() {
return offset;
}
public void setOffset(int offset) {
this.offset = offset;
}
int getBegin() {
return begin;
}
/**
* 获取词元在文本中的起始位置
* @return int
*/
public int getBeginPosition(){
return offset + begin;
}
public void setBegin(int begin) {
this.begin = begin;
}
/**
* 获取词元在文本中的结束位置
* @return int
*/
public int getEndPosition(){
return offset + begin + length;
}
/**
* 获取词元的字符长度
* @return int
*/
public int getLength(){
return this.length;
}
public void setLength(int length) {
if(this.length < 0){
throw new IllegalArgumentException("length < 0");
}
this.length = length;
}
/**
* 获取词元的文本内容
* @return String
*/
public String getLexemeText() {
if(lexemeText == null){
return "";
}
return lexemeText;
}
void setLexemeText(String lexemeText) {
if(lexemeText == null){
this.lexemeText = "";
this.length = 0;
}else{
this.lexemeText = lexemeText;
this.length = lexemeText.length();
}
}
/**
* 获取词元类型
* @return int
*/
int getLexemeType() {
return lexemeType;
}
/**
* 获取词元类型标示字符串
* @return String
*/
public String getLexemeTypeString(){
switch(lexemeType) {
case TYPE_ENGLISH :
return "ENGLISH";
case TYPE_ARABIC :
return "ARABIC";
case TYPE_LETTER :
return "LETTER";
case TYPE_CNWORD :
return "CN_WORD";
case TYPE_CNCHAR :
return "CN_CHAR";
case TYPE_OTHER_CJK :
return "OTHER_CJK";
case TYPE_COUNT :
return "COUNT";
case TYPE_CNUM :
return "TYPE_CNUM";
case TYPE_CQUAN:
return "TYPE_CQUAN";
default :
return "UNKONW";
}
}
public void setLexemeType(int lexemeType) {
this.lexemeType = lexemeType;
}
/**
* 合并两个相邻的词元
* @return boolean 词元是否成功合并
*/
boolean append(Lexeme l, int lexemeType){
if(l != null && this.getEndPosition() == l.getBeginPosition()){
this.length += l.getLength();
this.lexemeType = lexemeType;
return true;
}else {
return false;
}
}
/**
*
*/
public String toString(){
return this.getBeginPosition() + "-" + this.getEndPosition() +
" : " + this.lexemeText + " : \t" +
this.getLexemeTypeString();
}
}