hanlp好处的,就是它的data字典比较齐全.
github上有国人写hanlp支持es的插件
https://github.com/pengcong90/elasticsearch-analysis-hanlp
1
下载它的安装release包
下载发现解压按它的安装要求总找不到hanlp.properties文件
将源码git下来,发现路径有问题.
package org.elasticsearch.index.analysis;
import com.hankcs.hanlp.HanLP;
import com.hankcs.hanlp.utility.Predefine;
import com.hankcs.lucene4.HanLPIndexAnalyzer;
import org.elasticsearch.common.inject.Inject;
import org.elasticsearch.common.inject.assistedinject.Assisted;
import org.elasticsearch.common.settings.Settings;
import org.elasticsearch.env.Environment;
import org.elasticsearch.index.IndexSettings;
/**
*/
public class HanLPAnalyzerProvider extends AbstractIndexAnalyzerProvider
private final HanLPIndexAnalyzer analyzer;
private static String sysPath = String.valueOf(System.getProperties().get("user.dir"));
@Inject
public HanLPAnalyzerProvider(IndexSettings indexSettings, Environment env, @Assisted String name, @Assisted Settings settings) {
super(indexSettings, name, settings);
//原来路径
//Predefine.HANLP_PROPERTIES_PATH = sysPath.substring(0, sysPath.length()-4) + "/plugins/analysis-hanlp/hanlp.properties";
//修改后正确路径
Predefine.HANLP_PROPERTIES_PATH = sysPath + "/plugins/analysis-hanlp/hanlp.properties";
analyzer = new HanLPIndexAnalyzer(true);
}
public static HanLPAnalyzerProvider getIndexAnalyzerProvider(IndexSettings indexSettings, Environment env, String name, Settings settings) {
return new HanLPAnalyzerProvider(indexSettings, env, name, settings);
}
public static HanLPAnalyzerProvider getSmartAnalyzerProvider(IndexSettings indexSettings, Environment env, String name, Settings settings) {
return new HanLPAnalyzerProvider(indexSettings, env, name, settings);
}
@Override
public HanLPIndexAnalyzer get() {
return this.analyzer;
}
}
因为它的hanlp版本是1.2.8,最新版本是1.5.4
修改pom.xml为
打包编译
在$ES_HOME下/plugins建立analysis-hanlp文件
目录下结构为
hanlp.properties属性(可以直接从https://github.com/hankcs/HanLP 的realease下载修改root路径就行了)
#本配置文件中的路径的根目录，根目录+其他路径=完整路径（支持相对路径，请参考：https://github.com/hankcs/HanLP/pull/254）
#Windows用户请注意，路径分隔符统一使用/
root=/opt/elasticsearch-5.5.1/plugins/analysis-hanlp
#核心词典路径
CoreDictionaryPath=data/dictionary/CoreNatureDictionary.txt
#2元语法词典路径
BiGramDictionaryPath=data/dictionary/CoreNatureDictionary.ngram.txt
#停用词词典路径
CoreStopWordDictionaryPath=data/dictionary/stopwords.txt
#同义词词典路径
CoreSynonymDictionaryDictionaryPath=data/dictionary/synonym/CoreSynonym.txt
#人名词典路径
PersonDictionaryPath=data/dictionary/person/nr.txt
#人名词典转移矩阵路径
PersonDictionaryTrPath=data/dictionary/person/nr.tr.txt
#繁简词典根目录
tcDictionaryRoot=data/dictionary/tc
#自定义词典路径，用;隔开多个自定义词典，空格开头表示在同一个目录，使用“文件名 词性”形式则表示这个词典的词性默认是该词性。优先级递减。
#另外data/dictionary/custom/CustomDictionary.txt是个高质量的词库，请不要删除。所有词典统一使用UTF-8编码。
CustomDictionaryPath=data/dictionary/custom/CustomDictionary.txt; 现代汉语补充词库.txt; 全国地名大全.txt ns; 人名词典.txt; 机构名词典.txt; 上海地名.txt ns;data/dictionary/person/nrf.txt nrf;
#CRF分词模型路径
CRFSegmentModelPath=data/model/segment/CRFSegmentModel.txt
#HMM分词模型
HMMSegmentModelPath=data/model/segment/HMMSegmentModel.bin
#分词结果是否展示词性
ShowTermNature=true
#IO适配器，实现com.hankcs.hanlp.corpus.io.IIOAdapter接口以在不同的平台（Hadoop、Redis等）上运行HanLP
#默认的IO适配器如下，该适配器是基于普通文件系统的。
#IOAdapter=com.hankcs.hanlp.corpus.io.FileIOAdapter
plugin-descriptor.properties和plugin-security.policy属性按 elasticsearch-analysis-hanlp的release包属性修改.
修改ES启动,并启动
vim /opt/elasticsearch-5.5.1config/jvm.options
#新增
-Djava.security.policy=/opt/elasticsearch-5.5.1/plugins/analysis-hanlp/plugin-security.policy
测试安装成功否命令
GET /_analyze?analyzer=hanlp-index&pretty=true
{
"text":"公安部：各地校车将享最高路权"
}
data字典文件从https://github.com/hankcs/HanLP/releases 下载,解压就行了.
文章来源于小白鸽的博客