Compare commits
14 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| 95ba364090 | |||
| 0c8992fd80 | |||
| 356d9d9ae9 | |||
| cd43d4b9ee | |||
| 5068a58e0f | |||
| 107b4ced30 | |||
| e6817ecba5 | |||
| 0916f3f8bd | |||
| a3705f5753 | |||
| cc9f0d7bea | |||
| 7a2515a134 | |||
| 2ebf31fed5 | |||
| fd35153cce | |||
| 48a0234bb6 |
+2
-1
@@ -1,3 +1,4 @@
|
||||
language: java
|
||||
|
||||
jdk:
|
||||
- oraclejdk8
|
||||
- openjdk8
|
||||
@@ -6,6 +6,7 @@ ik-analyzer for solr 7.x-8.x
|
||||
[](https://github.com/magese/ik-analyzer-solr/releases)
|
||||
[](./LICENSE)
|
||||
[](https://travis-ci.org/magese/ik-analyzer-solr)
|
||||
[](http://hits.dwyl.io/magese/ik-analyzer-solr)
|
||||
|
||||
[](https://github.com/magese/ik-analyzer-solr/network/members)
|
||||
[](https://github.com/magese/ik-analyzer-solr/stargazers)
|
||||
@@ -21,15 +22,15 @@ ik-analyzer for solr 7.x-8.x
|
||||
| word | 64.2万 | 2014年 |
|
||||
| jieba | 58.4万 | 2012年 |
|
||||
| jcesg | 16.6万 | 2018年 |
|
||||
| sougou词库 | 115.2万 | 2018年 |
|
||||
#### 将以上词库进行整理后约188.5万条词汇;
|
||||
| sougou词库 | 115.2万 | 2019年 |
|
||||
#### 将以上词库进行整理后约187.1万条词汇;
|
||||
#### 添加动态加载词典表功能,在不需要重启solr服务的情况下加载新增的词典。
|
||||
* IKAnalyzer的原作者为林良益<linliangyi2007@gmail.com>,项目网站为<http://code.google.com/p/ik-analyzer>
|
||||
* 该项目动态加载功能根据博主[@星火燎原智勇](http://www.cnblogs.com/liang1101/articles/6395016.html)的博客进行修改,其GITHUB地址为[@liang68](https://github.com/liang68)
|
||||
|
||||
|
||||
## 使用说明
|
||||
* jar包下载地址:[](https://search.maven.org/remotecontent?filepath=com/github/magese/ik-analyzer/8.0.0/ik-analyzer-8.0.0.jar)
|
||||
* jar包下载地址:[](https://search.maven.org/remotecontent?filepath=com/github/magese/ik-analyzer/8.3.0/ik-analyzer-8.3.0.jar)
|
||||
* 历史版本:[](https://search.maven.org/search?q=g:com.github.magese%20AND%20a:ik-analyzer&core=gav)
|
||||
|
||||
```console
|
||||
@@ -37,7 +38,7 @@ ik-analyzer for solr 7.x-8.x
|
||||
<dependency>
|
||||
<groupId>com.github.magese</groupId>
|
||||
<artifactId>ik-analyzer</artifactId>
|
||||
<version>8.0.0</version>
|
||||
<version>8.3.0</version>
|
||||
</dependency>
|
||||
```
|
||||
|
||||
@@ -75,7 +76,15 @@ ik-analyzer for solr 7.x-8.x
|
||||
|
||||

|
||||
|
||||
5. `ik.conf`文件说明:
|
||||
5. `IKAnalyzer.cfg.xml`配置文件说明:
|
||||
|
||||
| 名称 | 类型 | 描述 | 默认 |
|
||||
| :------: | :------: | :------: | :------: |
|
||||
| use_main_dict | boolean | 是否使用默认主词典 | true |
|
||||
| ext_dict | String | 扩展词典文件名称,多个用分号隔开 | ext.dic; |
|
||||
| ext_stopwords | String | 停用词典文件名称,多个用分号隔开 | stopword.dic; |
|
||||
|
||||
6. `ik.conf`文件说明:
|
||||
```console
|
||||
files=dynamicdic.txt
|
||||
lastupdate=0
|
||||
@@ -84,13 +93,22 @@ ik-analyzer for solr 7.x-8.x
|
||||
1. `files`为动态词典列表,可以设置多个词典表,用逗号进行分隔,默认动态词典表为`dynamicdic.txt`;
|
||||
2. `lastupdate`默认值为`0`,每次对动态词典表修改后请+1,不然不会将词典表中新的词语添加到内存中。<s>`lastupdate`采用的是`int`类型,不支持时间戳,如果使用时间戳的朋友可以把源码中的`int`改成`long`即可;</s> `2018-08-23` 已将源码中`lastUpdate`改为`long`类型,现可以用时间戳了。
|
||||
|
||||
6. `dynamicdic.txt` 为动态词典
|
||||
7. `dynamicdic.txt` 为动态词典
|
||||
|
||||
在此文件配置的词语不需重启服务即可加载进内存中。
|
||||
以`#`开头的词语视为注释,将不会加载到内存中。
|
||||
|
||||
|
||||
## 更新说明
|
||||
- `2019-11-12:`
|
||||
- 升级lucene版本为`8.3.0`
|
||||
- `IKAnalyzer.cfg.xml`增加配置项`use_main_dict`,用于配置是否启用默认主词典
|
||||
- `2019-09-27:` 升级lucene版本为`8.2.0`
|
||||
- `2019-07-11:` 升级lucene版本为`8.1.1`
|
||||
- `2019-05-27:`
|
||||
- 升级lucene版本为`8.1.0`
|
||||
- 优化原词典部分重复词语
|
||||
- 更新搜狗2019最新流行词汇词典,约20k词汇量
|
||||
- `2019-05-15:` 升级lucene版本为`8.0.0`,并支持Solr8使用
|
||||
- `2019-03-01:` 升级lucene版本为`7.7.1`
|
||||
- `2019-02-15:` 升级lucene版本为`7.7.0`
|
||||
|
||||
@@ -4,7 +4,7 @@
|
||||
|
||||
<groupId>com.github.magese</groupId>
|
||||
<artifactId>ik-analyzer</artifactId>
|
||||
<version>8.0.0</version>
|
||||
<version>8.3.0</version>
|
||||
<packaging>jar</packaging>
|
||||
|
||||
<name>ik-analyzer-solr</name>
|
||||
@@ -13,7 +13,7 @@
|
||||
|
||||
<properties>
|
||||
<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
|
||||
<lucene.version>8.0.0</lucene.version>
|
||||
<lucene.version>8.3.0</lucene.version>
|
||||
<javac.src.version>1.8</javac.src.version>
|
||||
<javac.target.version>1.8</javac.target.version>
|
||||
<maven.compiler.plugin.version>3.3</maven.compiler.plugin.version>
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
/*
|
||||
* IK 中文分词 版本 8.0.0
|
||||
* IK Analyzer release 8.0.0
|
||||
* IK 中文分词 版本 8.3.0
|
||||
* IK Analyzer release 8.3.0
|
||||
*
|
||||
* Licensed to the Apache Software Foundation (ASF) under one or more
|
||||
* contributor license agreements. See the NOTICE file distributed with
|
||||
@@ -21,8 +21,8 @@
|
||||
* 版权声明 2012,乌龙茶工作室
|
||||
* provided by Linliangyi and copyright 2012 by Oolong studio
|
||||
*
|
||||
* 8.0.0版本 由 Magese (magese@live.cn) 更新
|
||||
* release 8.0.0 update by Magese(magese@live.cn)
|
||||
* 8.3.0版本 由 Magese (magese@live.cn) 更新
|
||||
* release 8.3.0 update by Magese(magese@live.cn)
|
||||
*
|
||||
*/
|
||||
package org.wltea.analyzer.cfg;
|
||||
@@ -50,6 +50,19 @@ public interface Configuration {
|
||||
*/
|
||||
void setUseSmart(boolean useSmart);
|
||||
|
||||
/**
|
||||
* 获取是否使用主词典
|
||||
*
|
||||
* @return = true 默认加载主词典, = false 不加载主词典
|
||||
*/
|
||||
boolean useMainDict();
|
||||
|
||||
/**
|
||||
* 设置是否使用主词典
|
||||
*
|
||||
* @param useMainDic = true 默认加载主词典, = false 不加载主词典
|
||||
*/
|
||||
void setUseMainDict(boolean useMainDic);
|
||||
|
||||
/**
|
||||
* 获取主词典路径
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
/*
|
||||
* IK 中文分词 版本 8.0.0
|
||||
* IK Analyzer release 8.0.0
|
||||
* IK 中文分词 版本 8.3.0
|
||||
* IK Analyzer release 8.3.0
|
||||
*
|
||||
* Licensed to the Apache Software Foundation (ASF) under one or more
|
||||
* contributor license agreements. See the NOTICE file distributed with
|
||||
@@ -21,8 +21,8 @@
|
||||
* 版权声明 2012,乌龙茶工作室
|
||||
* provided by Linliangyi and copyright 2012 by Oolong studio
|
||||
*
|
||||
* 8.0.0版本 由 Magese (magese@live.cn) 更新
|
||||
* release 8.0.0 update by Magese(magese@live.cn)
|
||||
* 8.3.0版本 由 Magese (magese@live.cn) 更新
|
||||
* release 8.3.0 update by Magese(magese@live.cn)
|
||||
*
|
||||
*/
|
||||
package org.wltea.analyzer.cfg;
|
||||
@@ -48,17 +48,21 @@ public class DefaultConfig implements Configuration {
|
||||
* 分词器配置文件路径
|
||||
*/
|
||||
private static final String FILE_NAME = "IKAnalyzer.cfg.xml";
|
||||
// 配置属性——是否使用主词典
|
||||
private static final String USE_MAIN = "use_main_dict";
|
||||
// 配置属性——扩展字典
|
||||
private static final String EXT_DICT = "ext_dict";
|
||||
// 配置属性——扩展停止词典
|
||||
private static final String EXT_STOP = "ext_stopwords";
|
||||
|
||||
private Properties props;
|
||||
/*
|
||||
* 是否使用smart方式分词
|
||||
*/
|
||||
|
||||
// 是否使用smart方式分词
|
||||
private boolean useSmart;
|
||||
|
||||
// 是否加载主词典
|
||||
private boolean useMainDict = true;
|
||||
|
||||
/**
|
||||
* 返回单例
|
||||
*
|
||||
@@ -100,10 +104,33 @@ public class DefaultConfig implements Configuration {
|
||||
*
|
||||
* @param useSmart =true ,分词器使用智能切分策略, =false则使用细粒度切分
|
||||
*/
|
||||
@Override
|
||||
public void setUseSmart(boolean useSmart) {
|
||||
this.useSmart = useSmart;
|
||||
}
|
||||
|
||||
/**
|
||||
* 获取是否使用主词典
|
||||
*
|
||||
* @return = true 默认加载主词典, = false 不加载主词典
|
||||
*/
|
||||
public boolean useMainDict() {
|
||||
String useMainDictCfg = props.getProperty(USE_MAIN);
|
||||
if (useMainDictCfg != null && useMainDictCfg.trim().length() > 0)
|
||||
setUseMainDict(Boolean.parseBoolean(useMainDictCfg));
|
||||
return useMainDict;
|
||||
}
|
||||
|
||||
/**
|
||||
* 设置是否使用主词典
|
||||
*
|
||||
* @param useMainDict = true 默认加载主词典, = false 不加载主词典
|
||||
*/
|
||||
@Override
|
||||
public void setUseMainDict(boolean useMainDict) {
|
||||
this.useMainDict = useMainDict;
|
||||
}
|
||||
|
||||
/**
|
||||
* 获取主词典路径
|
||||
*
|
||||
@@ -142,7 +169,6 @@ public class DefaultConfig implements Configuration {
|
||||
return extDictFiles;
|
||||
}
|
||||
|
||||
|
||||
/**
|
||||
* 获取扩展停止词典配置路径
|
||||
*
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
/*
|
||||
* IK 中文分词 版本 8.0.0
|
||||
* IK Analyzer release 8.0.0
|
||||
* IK 中文分词 版本 8.3.0
|
||||
* IK Analyzer release 8.3.0
|
||||
*
|
||||
* Licensed to the Apache Software Foundation (ASF) under one or more
|
||||
* contributor license agreements. See the NOTICE file distributed with
|
||||
@@ -21,8 +21,8 @@
|
||||
* 版权声明 2012,乌龙茶工作室
|
||||
* provided by Linliangyi and copyright 2012 by Oolong studio
|
||||
*
|
||||
* 8.0.0版本 由 Magese (magese@live.cn) 更新
|
||||
* release 8.0.0 update by Magese(magese@live.cn)
|
||||
* 8.3.0版本 由 Magese (magese@live.cn) 更新
|
||||
* release 8.3.0 update by Magese(magese@live.cn)
|
||||
*
|
||||
*/
|
||||
package org.wltea.analyzer.core;
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
/*
|
||||
* IK 中文分词 版本 8.0.0
|
||||
* IK Analyzer release 8.0.0
|
||||
* IK 中文分词 版本 8.3.0
|
||||
* IK Analyzer release 8.3.0
|
||||
*
|
||||
* Licensed to the Apache Software Foundation (ASF) under one or more
|
||||
* contributor license agreements. See the NOTICE file distributed with
|
||||
@@ -21,8 +21,8 @@
|
||||
* 版权声明 2012,乌龙茶工作室
|
||||
* provided by Linliangyi and copyright 2012 by Oolong studio
|
||||
*
|
||||
* 8.0.0版本 由 Magese (magese@live.cn) 更新
|
||||
* release 8.0.0 update by Magese(magese@live.cn)
|
||||
* 8.3.0版本 由 Magese (magese@live.cn) 更新
|
||||
* release 8.3.0 update by Magese(magese@live.cn)
|
||||
*
|
||||
*/
|
||||
package org.wltea.analyzer.core;
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
/*
|
||||
* IK 中文分词 版本 8.0.0
|
||||
* IK Analyzer release 8.0.0
|
||||
* IK 中文分词 版本 8.3.0
|
||||
* IK Analyzer release 8.3.0
|
||||
*
|
||||
* Licensed to the Apache Software Foundation (ASF) under one or more
|
||||
* contributor license agreements. See the NOTICE file distributed with
|
||||
@@ -21,8 +21,8 @@
|
||||
* 版权声明 2012,乌龙茶工作室
|
||||
* provided by Linliangyi and copyright 2012 by Oolong studio
|
||||
*
|
||||
* 8.0.0版本 由 Magese (magese@live.cn) 更新
|
||||
* release 8.0.0 update by Magese(magese@live.cn)
|
||||
* 8.3.0版本 由 Magese (magese@live.cn) 更新
|
||||
* release 8.3.0 update by Magese(magese@live.cn)
|
||||
*
|
||||
*/
|
||||
package org.wltea.analyzer.core;
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
/*
|
||||
* IK 中文分词 版本 8.0.0
|
||||
* IK Analyzer release 8.0.0
|
||||
* IK 中文分词 版本 8.3.0
|
||||
* IK Analyzer release 8.3.0
|
||||
*
|
||||
* Licensed to the Apache Software Foundation (ASF) under one or more
|
||||
* contributor license agreements. See the NOTICE file distributed with
|
||||
@@ -21,8 +21,8 @@
|
||||
* 版权声明 2012,乌龙茶工作室
|
||||
* provided by Linliangyi and copyright 2012 by Oolong studio
|
||||
*
|
||||
* 8.0.0版本 由 Magese (magese@live.cn) 更新
|
||||
* release 8.0.0 update by Magese(magese@live.cn)
|
||||
* 8.3.0版本 由 Magese (magese@live.cn) 更新
|
||||
* release 8.3.0 update by Magese(magese@live.cn)
|
||||
*
|
||||
*/
|
||||
package org.wltea.analyzer.core;
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
/*
|
||||
* IK 中文分词 版本 8.0.0
|
||||
* IK Analyzer release 8.0.0
|
||||
* IK 中文分词 版本 8.3.0
|
||||
* IK Analyzer release 8.3.0
|
||||
*
|
||||
* Licensed to the Apache Software Foundation (ASF) under one or more
|
||||
* contributor license agreements. See the NOTICE file distributed with
|
||||
@@ -21,8 +21,8 @@
|
||||
* 版权声明 2012,乌龙茶工作室
|
||||
* provided by Linliangyi and copyright 2012 by Oolong studio
|
||||
*
|
||||
* 8.0.0版本 由 Magese (magese@live.cn) 更新
|
||||
* release 8.0.0 update by Magese(magese@live.cn)
|
||||
* 8.3.0版本 由 Magese (magese@live.cn) 更新
|
||||
* release 8.3.0 update by Magese(magese@live.cn)
|
||||
*
|
||||
*/
|
||||
package org.wltea.analyzer.core;
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
/*
|
||||
* IK 中文分词 版本 8.0.0
|
||||
* IK Analyzer release 8.0.0
|
||||
* IK 中文分词 版本 8.3.0
|
||||
* IK Analyzer release 8.3.0
|
||||
*
|
||||
* Licensed to the Apache Software Foundation (ASF) under one or more
|
||||
* contributor license agreements. See the NOTICE file distributed with
|
||||
@@ -21,21 +21,21 @@
|
||||
* 版权声明 2012,乌龙茶工作室
|
||||
* provided by Linliangyi and copyright 2012 by Oolong studio
|
||||
*
|
||||
* 8.0.0版本 由 Magese (magese@live.cn) 更新
|
||||
* release 8.0.0 update by Magese(magese@live.cn)
|
||||
* 8.3.0版本 由 Magese (magese@live.cn) 更新
|
||||
* release 8.3.0 update by Magese(magese@live.cn)
|
||||
*
|
||||
*/
|
||||
package org.wltea.analyzer.core;
|
||||
|
||||
import org.wltea.analyzer.cfg.Configuration;
|
||||
import org.wltea.analyzer.cfg.DefaultConfig;
|
||||
import org.wltea.analyzer.dic.Dictionary;
|
||||
|
||||
import java.io.IOException;
|
||||
import java.io.Reader;
|
||||
import java.util.ArrayList;
|
||||
import java.util.List;
|
||||
|
||||
import org.wltea.analyzer.cfg.Configuration;
|
||||
import org.wltea.analyzer.cfg.DefaultConfig;
|
||||
import org.wltea.analyzer.dic.Dictionary;
|
||||
|
||||
/**
|
||||
* IK分词器主类
|
||||
*/
|
||||
@@ -58,7 +58,6 @@ public final class IKSegmenter {
|
||||
*
|
||||
* @param input 读取流
|
||||
* @param useSmart 为true,使用智能分词策略
|
||||
* <p>
|
||||
* 非智能分词:细粒度输出所有可能的切分结果
|
||||
* 智能分词: 合并数词和量词,对分词结果进行歧义判断
|
||||
*/
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
/*
|
||||
* IK 中文分词 版本 8.0.0
|
||||
* IK Analyzer release 8.0.0
|
||||
* IK 中文分词 版本 8.3.0
|
||||
* IK Analyzer release 8.3.0
|
||||
*
|
||||
* Licensed to the Apache Software Foundation (ASF) under one or more
|
||||
* contributor license agreements. See the NOTICE file distributed with
|
||||
@@ -21,8 +21,8 @@
|
||||
* 版权声明 2012,乌龙茶工作室
|
||||
* provided by Linliangyi and copyright 2012 by Oolong studio
|
||||
*
|
||||
* 8.0.0版本 由 Magese (magese@live.cn) 更新
|
||||
* release 8.0.0 update by Magese(magese@live.cn)
|
||||
* 8.3.0版本 由 Magese (magese@live.cn) 更新
|
||||
* release 8.3.0 update by Magese(magese@live.cn)
|
||||
*
|
||||
*/
|
||||
package org.wltea.analyzer.core;
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
/*
|
||||
* IK 中文分词 版本 8.0.0
|
||||
* IK Analyzer release 8.0.0
|
||||
* IK 中文分词 版本 8.3.0
|
||||
* IK Analyzer release 8.3.0
|
||||
*
|
||||
* Licensed to the Apache Software Foundation (ASF) under one or more
|
||||
* contributor license agreements. See the NOTICE file distributed with
|
||||
@@ -21,8 +21,8 @@
|
||||
* 版权声明 2012,乌龙茶工作室
|
||||
* provided by Linliangyi and copyright 2012 by Oolong studio
|
||||
*
|
||||
* 8.0.0版本 由 Magese (magese@live.cn) 更新
|
||||
* release 8.0.0 update by Magese(magese@live.cn)
|
||||
* 8.3.0版本 由 Magese (magese@live.cn) 更新
|
||||
* release 8.3.0 update by Magese(magese@live.cn)
|
||||
*
|
||||
*/
|
||||
package org.wltea.analyzer.core;
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
/*
|
||||
* IK 中文分词 版本 8.0.0
|
||||
* IK Analyzer release 8.0.0
|
||||
* IK 中文分词 版本 8.3.0
|
||||
* IK Analyzer release 8.3.0
|
||||
*
|
||||
* Licensed to the Apache Software Foundation (ASF) under one or more
|
||||
* contributor license agreements. See the NOTICE file distributed with
|
||||
@@ -21,8 +21,8 @@
|
||||
* 版权声明 2012,乌龙茶工作室
|
||||
* provided by Linliangyi and copyright 2012 by Oolong studio
|
||||
*
|
||||
* 8.0.0版本 由 Magese (magese@live.cn) 更新
|
||||
* release 8.0.0 update by Magese(magese@live.cn)
|
||||
* 8.3.0版本 由 Magese (magese@live.cn) 更新
|
||||
* release 8.3.0 update by Magese(magese@live.cn)
|
||||
*
|
||||
*/
|
||||
package org.wltea.analyzer.core;
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
/*
|
||||
* IK 中文分词 版本 8.0.0
|
||||
* IK Analyzer release 8.0.0
|
||||
* IK 中文分词 版本 8.3.0
|
||||
* IK Analyzer release 8.3.0
|
||||
*
|
||||
* Licensed to the Apache Software Foundation (ASF) under one or more
|
||||
* contributor license agreements. See the NOTICE file distributed with
|
||||
@@ -21,8 +21,8 @@
|
||||
* 版权声明 2012,乌龙茶工作室
|
||||
* provided by Linliangyi and copyright 2012 by Oolong studio
|
||||
*
|
||||
* 8.0.0版本 由 Magese (magese@live.cn) 更新
|
||||
* release 8.0.0 update by Magese(magese@live.cn)
|
||||
* 8.3.0版本 由 Magese (magese@live.cn) 更新
|
||||
* release 8.3.0 update by Magese(magese@live.cn)
|
||||
*
|
||||
*/
|
||||
package org.wltea.analyzer.core;
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
/*
|
||||
* IK 中文分词 版本 8.0.0
|
||||
* IK Analyzer release 8.0.0
|
||||
* IK 中文分词 版本 8.3.0
|
||||
* IK Analyzer release 8.2.0
|
||||
*
|
||||
* Licensed to the Apache Software Foundation (ASF) under one or more
|
||||
* contributor license agreements. See the NOTICE file distributed with
|
||||
@@ -21,8 +21,8 @@
|
||||
* 版权声明 2012,乌龙茶工作室
|
||||
* provided by Linliangyi and copyright 2012 by Oolong studio
|
||||
*
|
||||
* 8.0.0版本 由 Magese (magese@live.cn) 更新
|
||||
* release 8.0.0 update by Magese(magese@live.cn)
|
||||
* 8.2.0版本 由 Magese (magese@live.cn) 更新
|
||||
* release 8.2.0 update by Magese(magese@live.cn)
|
||||
*
|
||||
*/
|
||||
package org.wltea.analyzer.core;
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
/*
|
||||
* IK 中文分词 版本 8.0.0
|
||||
* IK Analyzer release 8.0.0
|
||||
* IK 中文分词 版本 8.3.0
|
||||
* IK Analyzer release 8.3.0
|
||||
*
|
||||
* Licensed to the Apache Software Foundation (ASF) under one or more
|
||||
* contributor license agreements. See the NOTICE file distributed with
|
||||
@@ -21,8 +21,8 @@
|
||||
* 版权声明 2012,乌龙茶工作室
|
||||
* provided by Linliangyi and copyright 2012 by Oolong studio
|
||||
*
|
||||
* 8.0.0版本 由 Magese (magese@live.cn) 更新
|
||||
* release 8.0.0 update by Magese(magese@live.cn)
|
||||
* 8.3.0版本 由 Magese (magese@live.cn) 更新
|
||||
* release 8.3.0 update by Magese(magese@live.cn)
|
||||
*
|
||||
*/
|
||||
package org.wltea.analyzer.dic;
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
/*
|
||||
* IK 中文分词 版本 8.0.0
|
||||
* IK Analyzer release 8.0.0
|
||||
* IK 中文分词 版本 8.3.0
|
||||
* IK Analyzer release 8.3.0
|
||||
*
|
||||
* Licensed to the Apache Software Foundation (ASF) under one or more
|
||||
* contributor license agreements. See the NOTICE file distributed with
|
||||
@@ -21,8 +21,8 @@
|
||||
* 版权声明 2012,乌龙茶工作室
|
||||
* provided by Linliangyi and copyright 2012 by Oolong studio
|
||||
*
|
||||
* 8.0.0版本 由 Magese (magese@live.cn) 更新
|
||||
* release 8.0.0 update by Magese(magese@live.cn)
|
||||
* 8.3.0版本 由 Magese (magese@live.cn) 更新
|
||||
* release 8.3.0 update by Magese(magese@live.cn)
|
||||
*
|
||||
*/
|
||||
package org.wltea.analyzer.dic;
|
||||
@@ -226,31 +226,25 @@ public class Dictionary {
|
||||
private void loadMainDict() {
|
||||
// 建立一个主词典实例
|
||||
_MainDict = new DictSegment((char) 0);
|
||||
// 读取主词典文件
|
||||
InputStream is = this.getClass().getClassLoader().getResourceAsStream(cfg.getMainDictionary());
|
||||
if (is == null) {
|
||||
throw new RuntimeException("Main Dictionary not found!!!");
|
||||
}
|
||||
|
||||
try {
|
||||
BufferedReader br = new BufferedReader(new InputStreamReader(is, StandardCharsets.UTF_8), 512);
|
||||
String theWord;
|
||||
do {
|
||||
theWord = br.readLine();
|
||||
if (theWord != null && !"".equals(theWord.trim())) {
|
||||
_MainDict.fillSegment(theWord.trim().toLowerCase().toCharArray());
|
||||
}
|
||||
} while (theWord != null);
|
||||
|
||||
} catch (IOException ioe) {
|
||||
System.err.println("Main Dictionary loading exception.");
|
||||
ioe.printStackTrace();
|
||||
|
||||
} finally {
|
||||
// 获取是否加载主词典
|
||||
if (cfg.useMainDict()) {
|
||||
// 读取主词典文件
|
||||
InputStream is = this.getClass().getClassLoader().getResourceAsStream(cfg.getMainDictionary());
|
||||
if (is == null) {
|
||||
throw new RuntimeException("Main Dictionary not found!!!");
|
||||
}
|
||||
try {
|
||||
is.close();
|
||||
} catch (IOException e) {
|
||||
e.printStackTrace();
|
||||
readDict(is, _MainDict);
|
||||
} catch (IOException ioe) {
|
||||
System.err.println("Main Dictionary loading exception.");
|
||||
ioe.printStackTrace();
|
||||
|
||||
} finally {
|
||||
try {
|
||||
is.close();
|
||||
} catch (IOException e) {
|
||||
e.printStackTrace();
|
||||
}
|
||||
}
|
||||
}
|
||||
// 加载扩展词典
|
||||
@@ -274,17 +268,7 @@ public class Dictionary {
|
||||
continue;
|
||||
}
|
||||
try {
|
||||
BufferedReader br = new BufferedReader(new InputStreamReader(is, StandardCharsets.UTF_8), 512);
|
||||
String theWord;
|
||||
do {
|
||||
theWord = br.readLine();
|
||||
if (theWord != null && !"".equals(theWord.trim())) {
|
||||
// 加载扩展词典数据到主内存词典中
|
||||
// System.out.println(theWord);
|
||||
_MainDict.fillSegment(theWord.trim().toLowerCase().toCharArray());
|
||||
}
|
||||
} while (theWord != null);
|
||||
|
||||
readDict(is, _MainDict);
|
||||
} catch (IOException ioe) {
|
||||
System.err.println("Extension Dictionary loading exception.");
|
||||
ioe.printStackTrace();
|
||||
@@ -319,17 +303,7 @@ public class Dictionary {
|
||||
continue;
|
||||
}
|
||||
try {
|
||||
BufferedReader br = new BufferedReader(new InputStreamReader(is, StandardCharsets.UTF_8), 512);
|
||||
String theWord;
|
||||
do {
|
||||
theWord = br.readLine();
|
||||
if (theWord != null && !"".equals(theWord.trim())) {
|
||||
// System.out.println(theWord);
|
||||
// 加载扩展停止词典数据到内存中
|
||||
_StopWordDict.fillSegment(theWord.trim().toLowerCase().toCharArray());
|
||||
}
|
||||
} while (theWord != null);
|
||||
|
||||
readDict(is, _StopWordDict);
|
||||
} catch (IOException ioe) {
|
||||
System.err.println("Extension Stop word Dictionary loading exception.");
|
||||
ioe.printStackTrace();
|
||||
@@ -357,15 +331,7 @@ public class Dictionary {
|
||||
throw new RuntimeException("Quantifier Dictionary not found!!!");
|
||||
}
|
||||
try {
|
||||
BufferedReader br = new BufferedReader(new InputStreamReader(is, StandardCharsets.UTF_8), 512);
|
||||
String theWord;
|
||||
do {
|
||||
theWord = br.readLine();
|
||||
if (theWord != null && !"".equals(theWord.trim())) {
|
||||
_QuantifierDict.fillSegment(theWord.trim().toLowerCase().toCharArray());
|
||||
}
|
||||
} while (theWord != null);
|
||||
|
||||
readDict(is, _QuantifierDict);
|
||||
} catch (IOException ioe) {
|
||||
System.err.println("Quantifier Dictionary loading exception.");
|
||||
ioe.printStackTrace();
|
||||
@@ -379,4 +345,21 @@ public class Dictionary {
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* 读取词典文件到词典树中
|
||||
*
|
||||
* @param is 文件输入流
|
||||
* @param dictSegment 词典树分段
|
||||
* @throws IOException 读取异常
|
||||
*/
|
||||
private void readDict(InputStream is, DictSegment dictSegment) throws IOException {
|
||||
BufferedReader br = new BufferedReader(new InputStreamReader(is, StandardCharsets.UTF_8), 512);
|
||||
String theWord;
|
||||
do {
|
||||
theWord = br.readLine();
|
||||
if (theWord != null && !"".equals(theWord.trim())) {
|
||||
dictSegment.fillSegment(theWord.trim().toLowerCase().toCharArray());
|
||||
}
|
||||
} while (theWord != null);
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
/*
|
||||
* IK 中文分词 版本 8.0.0
|
||||
* IK Analyzer release 8.0.0
|
||||
* IK 中文分词 版本 8.3.0
|
||||
* IK Analyzer release 8.3.0
|
||||
*
|
||||
* Licensed to the Apache Software Foundation (ASF) under one or more
|
||||
* contributor license agreements. See the NOTICE file distributed with
|
||||
@@ -21,8 +21,8 @@
|
||||
* 版权声明 2012,乌龙茶工作室
|
||||
* provided by Linliangyi and copyright 2012 by Oolong studio
|
||||
*
|
||||
* 8.0.0版本 由 Magese (magese@live.cn) 更新
|
||||
* release 8.0.0 update by Magese(magese@live.cn)
|
||||
* 8.3.0版本 由 Magese (magese@live.cn) 更新
|
||||
* release 8.3.0 update by Magese(magese@live.cn)
|
||||
*
|
||||
*/
|
||||
package org.wltea.analyzer.dic;
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
/*
|
||||
* IK 中文分词 版本 8.0.0
|
||||
* IK Analyzer release 8.0.0
|
||||
* IK 中文分词 版本 8.3.0
|
||||
* IK Analyzer release 8.3.0
|
||||
*
|
||||
* Licensed to the Apache Software Foundation (ASF) under one or more
|
||||
* contributor license agreements. See the NOTICE file distributed with
|
||||
@@ -21,8 +21,8 @@
|
||||
* 版权声明 2012,乌龙茶工作室
|
||||
* provided by Linliangyi and copyright 2012 by Oolong studio
|
||||
*
|
||||
* 8.0.0版本 由 Magese (magese@live.cn) 更新
|
||||
* release 8.0.0 update by Magese(magese@live.cn)
|
||||
* 8.3.0版本 由 Magese (magese@live.cn) 更新
|
||||
* release 8.3.0 update by Magese(magese@live.cn)
|
||||
*
|
||||
*/
|
||||
package org.wltea.analyzer.lucene;
|
||||
@@ -34,44 +34,40 @@ import org.apache.lucene.analysis.Tokenizer;
|
||||
* IK分词器,Lucene Analyzer接口实现
|
||||
*/
|
||||
@SuppressWarnings("unused")
|
||||
public final class IKAnalyzer extends Analyzer{
|
||||
|
||||
private boolean useSmart;
|
||||
|
||||
private boolean useSmart() {
|
||||
return useSmart;
|
||||
}
|
||||
public final class IKAnalyzer extends Analyzer {
|
||||
|
||||
public void setUseSmart(boolean useSmart) {
|
||||
this.useSmart = useSmart;
|
||||
}
|
||||
private boolean useSmart;
|
||||
|
||||
/**
|
||||
* IK分词器Lucene Analyzer接口实现类
|
||||
*
|
||||
* 默认细粒度切分算法
|
||||
*/
|
||||
public IKAnalyzer(){
|
||||
this(false);
|
||||
}
|
||||
|
||||
/**
|
||||
* IK分词器Lucene Analyzer接口实现类
|
||||
*
|
||||
* @param useSmart 当为true时,分词器进行智能切分
|
||||
*/
|
||||
public IKAnalyzer(boolean useSmart){
|
||||
super();
|
||||
this.useSmart = useSmart;
|
||||
}
|
||||
private boolean useSmart() {
|
||||
return useSmart;
|
||||
}
|
||||
|
||||
/**
|
||||
* 重载Analyzer接口,构造分词组件
|
||||
*/
|
||||
@Override
|
||||
protected TokenStreamComponents createComponents(String fieldName) {
|
||||
Tokenizer _IKTokenizer = new IKTokenizer(this.useSmart());
|
||||
return new TokenStreamComponents(_IKTokenizer);
|
||||
}
|
||||
|
||||
/**
|
||||
* IK分词器Lucene Analyzer接口实现类
|
||||
* 默认细粒度切分算法
|
||||
*/
|
||||
public IKAnalyzer() {
|
||||
this(false);
|
||||
}
|
||||
|
||||
/**
|
||||
* IK分词器Lucene Analyzer接口实现类
|
||||
*
|
||||
* @param useSmart 当为true时,分词器进行智能切分
|
||||
*/
|
||||
public IKAnalyzer(boolean useSmart) {
|
||||
super();
|
||||
this.useSmart = useSmart;
|
||||
}
|
||||
|
||||
/**
|
||||
* 重载Analyzer接口,构造分词组件
|
||||
*/
|
||||
@Override
|
||||
protected TokenStreamComponents createComponents(String fieldName) {
|
||||
Tokenizer _IKTokenizer = new IKTokenizer(this.useSmart());
|
||||
return new TokenStreamComponents(_IKTokenizer);
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
/*
|
||||
* IK 中文分词 版本 8.0.0
|
||||
* IK Analyzer release 8.0.0
|
||||
* IK 中文分词 版本 8.3.0
|
||||
* IK Analyzer release 8.3.0
|
||||
*
|
||||
* Licensed to the Apache Software Foundation (ASF) under one or more
|
||||
* contributor license agreements. See the NOTICE file distributed with
|
||||
@@ -21,8 +21,8 @@
|
||||
* 版权声明 2012,乌龙茶工作室
|
||||
* provided by Linliangyi and copyright 2012 by Oolong studio
|
||||
*
|
||||
* 8.0.0版本 由 Magese (magese@live.cn) 更新
|
||||
* release 8.0.0 update by Magese(magese@live.cn)
|
||||
* 8.3.0版本 由 Magese (magese@live.cn) 更新
|
||||
* release 8.3.0 update by Magese(magese@live.cn)
|
||||
*
|
||||
*/
|
||||
package org.wltea.analyzer.lucene;
|
||||
@@ -43,88 +43,88 @@ import java.io.IOException;
|
||||
*/
|
||||
@SuppressWarnings("unused")
|
||||
public final class IKTokenizer extends Tokenizer {
|
||||
|
||||
//IK分词器实现
|
||||
private IKSegmenter _IKImplement;
|
||||
|
||||
//词元文本属性
|
||||
private CharTermAttribute termAtt;
|
||||
//词元位移属性
|
||||
private OffsetAttribute offsetAtt;
|
||||
//词元分类属性(该属性分类参考org.wltea.analyzer.core.Lexeme中的分类常量)
|
||||
private TypeAttribute typeAtt;
|
||||
//记录最后一个词元的结束位置
|
||||
private int endPosition;
|
||||
|
||||
/**
|
||||
* Lucene 7.6 Tokenizer适配器类构造函数
|
||||
*/
|
||||
public IKTokenizer() {
|
||||
this(false);
|
||||
}
|
||||
|
||||
IKTokenizer(boolean useSmart) {
|
||||
super();
|
||||
init(useSmart);
|
||||
}
|
||||
//IK分词器实现
|
||||
private IKSegmenter _IKImplement;
|
||||
|
||||
public IKTokenizer(AttributeFactory factory) {
|
||||
this(factory, false);
|
||||
}
|
||||
//词元文本属性
|
||||
private CharTermAttribute termAtt;
|
||||
//词元位移属性
|
||||
private OffsetAttribute offsetAtt;
|
||||
//词元分类属性(该属性分类参考org.wltea.analyzer.core.Lexeme中的分类常量)
|
||||
private TypeAttribute typeAtt;
|
||||
//记录最后一个词元的结束位置
|
||||
private int endPosition;
|
||||
|
||||
IKTokenizer(AttributeFactory factory, boolean useSmart) {
|
||||
super(factory);
|
||||
init(useSmart);
|
||||
}
|
||||
/**
|
||||
* Lucene 7.6 Tokenizer适配器类构造函数
|
||||
*/
|
||||
public IKTokenizer() {
|
||||
this(false);
|
||||
}
|
||||
|
||||
private void init(boolean useSmart) {
|
||||
offsetAtt = addAttribute(OffsetAttribute.class);
|
||||
termAtt = addAttribute(CharTermAttribute.class);
|
||||
typeAtt = addAttribute(TypeAttribute.class);
|
||||
_IKImplement = new IKSegmenter(input , useSmart);
|
||||
}
|
||||
IKTokenizer(boolean useSmart) {
|
||||
super();
|
||||
init(useSmart);
|
||||
}
|
||||
|
||||
/* (non-Javadoc)
|
||||
* @see org.apache.lucene.analysis.TokenStream#incrementToken()
|
||||
*/
|
||||
@Override
|
||||
public boolean incrementToken() throws IOException {
|
||||
//清除所有的词元属性
|
||||
clearAttributes();
|
||||
Lexeme nextLexeme = _IKImplement.next();
|
||||
if(nextLexeme != null){
|
||||
//将Lexeme转成Attributes
|
||||
//设置词元文本
|
||||
termAtt.append(nextLexeme.getLexemeText());
|
||||
//设置词元长度
|
||||
termAtt.setLength(nextLexeme.getLength());
|
||||
//设置词元位移
|
||||
offsetAtt.setOffset(nextLexeme.getBeginPosition(), nextLexeme.getEndPosition());
|
||||
//记录分词的最后位置
|
||||
endPosition = nextLexeme.getEndPosition();
|
||||
//记录词元分类
|
||||
typeAtt.setType(nextLexeme.getLexemeTypeString());
|
||||
//返会true告知还有下个词元
|
||||
return true;
|
||||
}
|
||||
//返会false告知词元输出完毕
|
||||
return false;
|
||||
}
|
||||
|
||||
/*
|
||||
* (non-Javadoc)
|
||||
* @see org.apache.lucene.analysis.Tokenizer#reset(java.io.Reader)
|
||||
*/
|
||||
@Override
|
||||
public void reset() throws IOException {
|
||||
super.reset();
|
||||
_IKImplement.reset(input);
|
||||
}
|
||||
|
||||
@Override
|
||||
public final void end() {
|
||||
// set final offset
|
||||
int finalOffset = correctOffset(this.endPosition);
|
||||
offsetAtt.setOffset(finalOffset, finalOffset);
|
||||
}
|
||||
public IKTokenizer(AttributeFactory factory) {
|
||||
this(factory, false);
|
||||
}
|
||||
|
||||
IKTokenizer(AttributeFactory factory, boolean useSmart) {
|
||||
super(factory);
|
||||
init(useSmart);
|
||||
}
|
||||
|
||||
private void init(boolean useSmart) {
|
||||
offsetAtt = addAttribute(OffsetAttribute.class);
|
||||
termAtt = addAttribute(CharTermAttribute.class);
|
||||
typeAtt = addAttribute(TypeAttribute.class);
|
||||
_IKImplement = new IKSegmenter(input, useSmart);
|
||||
}
|
||||
|
||||
/* (non-Javadoc)
|
||||
* @see org.apache.lucene.analysis.TokenStream#incrementToken()
|
||||
*/
|
||||
@Override
|
||||
public boolean incrementToken() throws IOException {
|
||||
//清除所有的词元属性
|
||||
clearAttributes();
|
||||
Lexeme nextLexeme = _IKImplement.next();
|
||||
if (nextLexeme != null) {
|
||||
//将Lexeme转成Attributes
|
||||
//设置词元文本
|
||||
termAtt.append(nextLexeme.getLexemeText());
|
||||
//设置词元长度
|
||||
termAtt.setLength(nextLexeme.getLength());
|
||||
//设置词元位移
|
||||
offsetAtt.setOffset(nextLexeme.getBeginPosition(), nextLexeme.getEndPosition());
|
||||
//记录分词的最后位置
|
||||
endPosition = nextLexeme.getEndPosition();
|
||||
//记录词元分类
|
||||
typeAtt.setType(nextLexeme.getLexemeTypeString());
|
||||
//返会true告知还有下个词元
|
||||
return true;
|
||||
}
|
||||
//返会false告知词元输出完毕
|
||||
return false;
|
||||
}
|
||||
|
||||
/*
|
||||
* (non-Javadoc)
|
||||
* @see org.apache.lucene.analysis.Tokenizer#reset(java.io.Reader)
|
||||
*/
|
||||
@Override
|
||||
public void reset() throws IOException {
|
||||
super.reset();
|
||||
_IKImplement.reset(input);
|
||||
}
|
||||
|
||||
@Override
|
||||
public final void end() {
|
||||
// set final offset
|
||||
int finalOffset = correctOffset(this.endPosition);
|
||||
offsetAtt.setOffset(finalOffset, finalOffset);
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
/*
|
||||
* IK 中文分词 版本 8.0.0
|
||||
* IK Analyzer release 8.0.0
|
||||
* IK 中文分词 版本 8.3.0
|
||||
* IK Analyzer release 8.3.0
|
||||
*
|
||||
* Licensed to the Apache Software Foundation (ASF) under one or more
|
||||
* contributor license agreements. See the NOTICE file distributed with
|
||||
@@ -21,8 +21,8 @@
|
||||
* 版权声明 2012,乌龙茶工作室
|
||||
* provided by Linliangyi and copyright 2012 by Oolong studio
|
||||
*
|
||||
* 8.0.0版本 由 Magese (magese@live.cn) 更新
|
||||
* release 8.0.0 update by Magese(magese@live.cn)
|
||||
* 8.3.0版本 由 Magese (magese@live.cn) 更新
|
||||
* release 8.3.0 update by Magese(magese@live.cn)
|
||||
*
|
||||
*/
|
||||
package org.wltea.analyzer.lucene;
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
/*
|
||||
* IK 中文分词 版本 8.0.0
|
||||
* IK Analyzer release 8.0.0
|
||||
* IK 中文分词 版本 8.3.0
|
||||
* IK Analyzer release 8.3.0
|
||||
*
|
||||
* Licensed to the Apache Software Foundation (ASF) under one or more
|
||||
* contributor license agreements. See the NOTICE file distributed with
|
||||
@@ -21,8 +21,8 @@
|
||||
* 版权声明 2012,乌龙茶工作室
|
||||
* provided by Linliangyi and copyright 2012 by Oolong studio
|
||||
*
|
||||
* 8.0.0版本 由 Magese (magese@live.cn) 更新
|
||||
* release 8.0.0 update by Magese(magese@live.cn)
|
||||
* 8.3.0版本 由 Magese (magese@live.cn) 更新
|
||||
* release 8.3.0 update by Magese(magese@live.cn)
|
||||
*
|
||||
*/
|
||||
package org.wltea.analyzer.lucene;
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
/*
|
||||
* IK 中文分词 版本 8.0.0
|
||||
* IK Analyzer release 8.0.0
|
||||
* IK 中文分词 版本 8.3.0
|
||||
* IK Analyzer release 8.3.0
|
||||
*
|
||||
* Licensed to the Apache Software Foundation (ASF) under one or more
|
||||
* contributor license agreements. See the NOTICE file distributed with
|
||||
@@ -21,8 +21,8 @@
|
||||
* 版权声明 2012,乌龙茶工作室
|
||||
* provided by Linliangyi and copyright 2012 by Oolong studio
|
||||
*
|
||||
* 8.0.0版本 由 Magese (magese@live.cn) 更新
|
||||
* release 8.0.0 update by Magese(magese@live.cn)
|
||||
* 8.3.0版本 由 Magese (magese@live.cn) 更新
|
||||
* release 8.3.0 update by Magese(magese@live.cn)
|
||||
*
|
||||
*/
|
||||
package org.wltea.analyzer.query;
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
/*
|
||||
* IK 中文分词 版本 8.0.0
|
||||
* IK Analyzer release 8.0.0
|
||||
* IK 中文分词 版本 8.3.0
|
||||
* IK Analyzer release 8.3.0
|
||||
*
|
||||
* Licensed to the Apache Software Foundation (ASF) under one or more
|
||||
* contributor license agreements. See the NOTICE file distributed with
|
||||
@@ -21,8 +21,8 @@
|
||||
* 版权声明 2012,乌龙茶工作室
|
||||
* provided by Linliangyi and copyright 2012 by Oolong studio
|
||||
*
|
||||
* 8.0.0版本 由 Magese (magese@live.cn) 更新
|
||||
* release 8.0.0 update by Magese(magese@live.cn)
|
||||
* 8.3.0版本 由 Magese (magese@live.cn) 更新
|
||||
* release 8.3.0 update by Magese(magese@live.cn)
|
||||
*
|
||||
*/
|
||||
package org.wltea.analyzer.query;
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
/*
|
||||
* IK 中文分词 版本 8.0.0
|
||||
* IK Analyzer release 8.0.0
|
||||
* IK 中文分词 版本 8.3.0
|
||||
* IK Analyzer release 8.3.0
|
||||
*
|
||||
* Licensed to the Apache Software Foundation (ASF) under one or more
|
||||
* contributor license agreements. See the NOTICE file distributed with
|
||||
@@ -21,8 +21,8 @@
|
||||
* 版权声明 2012,乌龙茶工作室
|
||||
* provided by Linliangyi and copyright 2012 by Oolong studio
|
||||
*
|
||||
* 8.0.0版本 由 Magese (magese@live.cn) 更新
|
||||
* release 8.0.0 update by Magese(magese@live.cn)
|
||||
* 8.3.0版本 由 Magese (magese@live.cn) 更新
|
||||
* release 8.3.0 update by Magese(magese@live.cn)
|
||||
*
|
||||
*/
|
||||
package org.wltea.analyzer.sample;
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
/*
|
||||
* IK 中文分词 版本 8.0.0
|
||||
* IK Analyzer release 8.0.0
|
||||
* IK 中文分词 版本 8.3.0
|
||||
* IK Analyzer release 8.3.0
|
||||
*
|
||||
* Licensed to the Apache Software Foundation (ASF) under one or more
|
||||
* contributor license agreements. See the NOTICE file distributed with
|
||||
@@ -21,8 +21,8 @@
|
||||
* 版权声明 2012,乌龙茶工作室
|
||||
* provided by Linliangyi and copyright 2012 by Oolong studio
|
||||
*
|
||||
* 8.0.0版本 由 Magese (magese@live.cn) 更新
|
||||
* release 8.0.0 update by Magese(magese@live.cn)
|
||||
* 8.3.0版本 由 Magese (magese@live.cn) 更新
|
||||
* release 8.3.0 update by Magese(magese@live.cn)
|
||||
*
|
||||
*/
|
||||
package org.wltea.analyzer.sample;
|
||||
|
||||
@@ -1,11 +1,11 @@
|
||||
<?xml version="1.0" encoding="UTF-8"?>
|
||||
<!DOCTYPE properties SYSTEM "http://java.sun.com/dtd/properties.dtd">
|
||||
<properties>
|
||||
<comment>IK Analyzer 扩展配置</comment>
|
||||
<!--用户可以在这里配置自己的扩展字典 -->
|
||||
<entry key="ext_dict">ext.dic;</entry>
|
||||
|
||||
<!--用户可以在这里配置自己的扩展停止词字典-->
|
||||
<entry key="ext_stopwords">stopword.dic;</entry>
|
||||
|
||||
<!DOCTYPE properties SYSTEM "http://java.sun.com/dtd/properties.dtd">
|
||||
<properties>
|
||||
<comment>IK Analyzer 扩展配置</comment>
|
||||
<!-- 配置是否加载默认词典 -->
|
||||
<entry key="use_main_dict">true</entry>
|
||||
<!-- 配置自己的扩展字典,多个用分号分隔 -->
|
||||
<entry key="ext_dict">ext.dic;</entry>
|
||||
<!-- 配置自己的扩展停止词字典,多个用分号分隔 -->
|
||||
<entry key="ext_stopwords">stopword.dic;</entry>
|
||||
</properties>
|
||||
+15452
-1
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user