1、添加maven
<!--tika抽取文件內容 -->
<dependency>
<groupId>org.apache.tika</groupId>
<artifactId>tika-core</artifactId>
<version>1.12</version>
</dependency>
<dependency>
<groupId>org.apache.tika</groupId>
<artifactId>tika-parsers</artifactId>
<version>1.12</version>
</dependency>
<!--tika end-->
<!--bboss操作elasticsearch-->
<dependency>
<groupId>com.bbossgroups.plugins</groupId>
<artifactId>bboss-elasticsearch-rest-jdbc</artifactId>
<version>5.5.7</version>
</dependency>
<!--Hanlp自然語言分詞-->
<dependency>
<groupId>com.hankcs</groupId>
<artifactId>hanlp</artifactId>
<version>portable-1.7.1</version>
</dependency>
<!-- httpclient -->
<dependency>
<groupId>org.apache.httpcomponents</groupId>
<artifactId>httpclient</artifactId>
<version>4.5.5</version>
</dependency>
注意：與spring集成時需要注意版本號，版本太高會造成jar包沖突，tika-parsers 依賴poi.jar包,所以項目中不需要單獨添加poi.jar，會造成沖突。
完整的項目elasticsearch-common
pom.xml內容
<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
<modelVersion>4.0.0</modelVersion>
<groupId>com.hd</groupId>
<artifactId>elasticsearch-common</artifactId>
<version>1.0-SNAPSHOT</version>
<packaging>war</packaging>
<name>elasticsearch-common Maven Webapp</name>
<url>http://www.example.com</url>
<properties>
<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
<maven.compiler.source>1.7</maven.compiler.source>
<maven.compiler.target>1.7</maven.compiler.target>
<mysql.version>5.1.40</mysql.version>
<druid.version>1.0.29</druid.version>
<spring.version>4.2.3.RELEASE</spring.version>
<servlet.version>3.0.1</servlet.version>
<jackson.version>2.8.8</jackson.version>
<commons-io.version>2.5</commons-io.version>
<log4j2.version>2.8.2</log4j2.version>
<hibernate-validator.version>5.3.5.Final</hibernate-validator.version>
<hibernate.version>4.3.11.Final</hibernate.version>
<shiro.version>1.3.2</shiro.version>
<ehcache.version>2.6.11</ehcache.version>
</properties>
<dependencies>
<dependency>
<groupId>junit</groupId>
<artifactId>junit</artifactId>
<version>4.11</version>
<scope>test</scope>
</dependency>
<dependency>
<groupId>javax.el</groupId>
<artifactId>javax.el-api</artifactId>
<version>3.0.0</version>
<scope>test</scope>
</dependency>
<dependency>
<groupId>org.glassfish</groupId>
<artifactId>javax.el</artifactId>
<version>3.0.0</version>
<scope>test</scope>
</dependency>
<!--test end-->
<!--web begin -->
<dependency>
<groupId>javax.servlet</groupId>
<artifactId>javax.servlet-api</artifactId>
<version>${servlet.version}</version>
<scope>provided</scope>
</dependency>
<dependency>
<groupId>javax.servlet</groupId>
<artifactId>jsp-api</artifactId>
<version>2.0</version>
<scope>provided</scope>
</dependency>
<dependency>
<groupId>javax.servlet</groupId>
<artifactId>jstl</artifactId>
<version>1.2</version>
</dependency>
<!-- web end -->
<!-- log4j2 begin -->
<dependency>
<groupId>org.apache.logging.log4j</groupId>
<artifactId>log4j-core</artifactId>
<version>${log4j2.version}</version>
</dependency>
<dependency>
<groupId>org.apache.logging.log4j</groupId>
<artifactId>log4j-jcl</artifactId>
<version>${log4j2.version}</version>
</dependency>
<dependency>
<groupId>org.apache.logging.log4j</groupId>
<artifactId>log4j-slf4j-impl</artifactId>
<version>${log4j2.version}</version>
</dependency>
<!-- log4j2 end -->
<!-- spring核心包 -->
<dependency>
<groupId>org.springframework</groupId>
<artifactId>spring-core</artifactId>
</dependency>
<dependency>
<groupId>org.springframework</groupId>
<artifactId>spring-context</artifactId>
</dependency>
<dependency>
<groupId>org.springframework</groupId>
<artifactId>spring-beans</artifactId>
</dependency>
<dependency>
<groupId>org.springframework</groupId>
<artifactId>spring-expression</artifactId>
</dependency>
<dependency>
<groupId>org.springframework</groupId>
<artifactId>spring-jdbc</artifactId>
</dependency>
<dependency>
<groupId>org.springframework</groupId>
<artifactId>spring-orm</artifactId>
<version>${spring.version}</version>
</dependency>
<dependency>
<groupId>org.springframework</groupId>
<artifactId>spring-tx</artifactId>
</dependency>
<dependency>
<groupId>org.springframework</groupId>
<artifactId>spring-aop</artifactId>
</dependency>
<dependency>
<groupId>org.springframework</groupId>
<artifactId>spring-web</artifactId>
</dependency>
<dependency>
<groupId>org.springframework</groupId>
<artifactId>spring-webmvc</artifactId>
</dependency>
<dependency>
<groupId>org.springframework</groupId>
<artifactId>spring-test</artifactId>
</dependency>
<dependency>
<groupId>org.springframework</groupId>
<artifactId>spring-aspects</artifactId>
</dependency>
<dependency>
<groupId>org.springframework</groupId>
<artifactId>spring-context-support</artifactId>
</dependency>
<!--上傳組件-->
<dependency>
<groupId>commons-io</groupId>
<artifactId>commons-io</artifactId>
<version>${commons-io.version}</version>
</dependency>
<dependency>
<groupId>commons-fileupload</groupId>
<artifactId>commons-fileupload</artifactId>
<version>1.3.1</version>
</dependency>
<dependency>
<groupId>org.hibernate</groupId>
<artifactId>hibernate-core</artifactId>
<version>${hibernate.version}</version>
</dependency>
<!--數據庫-->
<dependency>
<groupId>mysql</groupId>
<artifactId>mysql-connector-java</artifactId>
<version>${mysql.version}</version>
</dependency>
<dependency>
<groupId>com.alibaba</groupId>
<artifactId>druid</artifactId>
<version>${druid.version}</version>
</dependency>
<!-- jackson begin -->
<dependency>
<groupId>com.fasterxml.jackson.core</groupId>
<artifactId>jackson-databind</artifactId>
<version>${jackson.version}</version>
</dependency>
<!--fastjson-->
<dependency>
<groupId>com.alibaba</groupId>
<artifactId>fastjson</artifactId>
<version>1.2.54</version>
</dependency>
<!-- httpclient -->
<dependency>
<groupId>org.apache.httpcomponents</groupId>
<artifactId>httpclient</artifactId>
<version>4.5.5</version>
</dependency>
<!--tika抽取文件內容 -->
<dependency>
<groupId>org.apache.tika</groupId>
<artifactId>tika-core</artifactId>
<version>1.12</version>
</dependency>
<dependency>
<groupId>org.apache.tika</groupId>
<artifactId>tika-parsers</artifactId>
<version>1.12</version>
</dependency>
<!--tika end-->
<!--bboss操作elasticsearch-->
<dependency>
<groupId>com.bbossgroups.plugins</groupId>
<artifactId>bboss-elasticsearch-rest-jdbc</artifactId>
<version>5.5.7</version>
</dependency>
<!--Hanlp自然語言分詞-->
<dependency>
<groupId>com.hankcs</groupId>
<artifactId>hanlp</artifactId>
<version>portable-1.7.1</version>
</dependency>
<!-- shiro begin -->
<dependency>
<groupId>org.apache.shiro</groupId>
<artifactId>shiro-spring</artifactId>
<version>${shiro.version}</version>
<exclusions>
<exclusion>
<artifactId>slf4j-api</artifactId>
<groupId>org.slf4j</groupId>
</exclusion>
</exclusions>
</dependency>
<!-- hibernate-validator -->
<dependency>
<groupId>org.hibernate</groupId>
<artifactId>hibernate-validator</artifactId>
<version>${hibernate-validator.version}</version>
</dependency>
<dependency>
<groupId>net.sf.ehcache</groupId>
<artifactId>ehcache-core</artifactId>
<version>${ehcache.version}</version>
</dependency>
<dependency>
<groupId>com.googlecode.ehcache-spring-annotations</groupId>
<artifactId>ehcache-spring-annotations</artifactId>
<version>1.2.0</version>
</dependency>
</dependencies>
<build>
<finalName>elasticsearch-common</finalName>
<plugins>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-compiler-plugin</artifactId>
<version>3.5.1</version>
<configuration>
<source>${maven.compiler.source}</source>
<target>${maven.compiler.target}</target>
<encoding>${project.build.sourceEncoding}</encoding>
</configuration>
</plugin>
<!--跳過test begin-->
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-surefire-plugin</artifactId>
<version>2.4.2</version>
<configuration>
<skip>true</skip>
</configuration>
</plugin>
<!-- jetty:run 添加jetty插件以便啟動 -->
<plugin>
<groupId>org.eclipse.jetty</groupId>
<artifactId>jetty-maven-plugin</artifactId>
<!-- <version>9.2.12.M0</version> -->
<version>9.3.10.v20160621</version>
<configuration>
<stopPort>9967</stopPort>
<stopKey>stop</stopKey>
<scanIntervalSeconds>0</scanIntervalSeconds>
<httpConnector>
<port>8878</port>
</httpConnector>
<webApp>
<contextPath>/</contextPath>
</webApp>
</configuration>
</plugin>
<!-- tomcat7:run -->
<plugin>
<groupId>org.apache.tomcat.maven</groupId>
<artifactId>tomcat7-maven-plugin</artifactId>
<version>2.2</version>
<configuration>
<port>8878</port>
<path>/</path>
<uriEncoding>UTF-8</uriEncoding>
<server>tomcat7</server>
</configuration>
<!-- 配置tomcat熱部署 -->
<!--<configuration>-->
<!--<uriEncoding>UTF-8</uriEncoding>-->
<!--<url>http://localhost:8080/manager/text</url>-->
<!--<path>/${project.build.finalName}</path>-->
<!--<!–<server>tomcat7</server>–>-->
<!--<username>tomcat</username>-->
<!--<password>123456</password>-->
<!--</configuration>-->
</plugin>
<!-- <plugin>
<groupId>org.zeroturnaround</groupId>
<artifactId>javarebel-maven-plugin</artifactId>
<version>1.0.5</version>
<executions>
<execution>
<id>generate-rebel-xml</id>
<phase>process-resources</phase>
<goals>
<goal>generate</goal>
</goals>
</execution>
</executions>
</plugin> -->
</plugins>
</build>
<!-- 使用aliyun鏡像 -->
<repositories>
<repository>
<id>aliyun</id>
<name>aliyun</name>
<url>http://maven.aliyun.com/nexus/content/groups/public</url>
</repository>
</repositories>
<!-- spring-framework-bom -->
<dependencyManagement>
<dependencies>
<dependency>
<groupId>org.springframework</groupId>
<artifactId>spring-framework-bom</artifactId>
<version>${spring.version}</version>
<type>pom</type>
<scope>import</scope>
</dependency>
</dependencies>
</dependencyManagement>
</project>
2、配置文件
elasticsearch.properties文件內容
#elasticUser=elastic
#elasticPassword=hzhh123
elasticsearch.rest.hostNames=127.0.0.1:9200
#elasticsearch.rest.hostNames=192.168.200.82:9200,192.168.200.83:9200,192.168.200.85:9200
elasticsearch.dateFormat=yyyy.MM.dd
elasticsearch.timeZone=Asia/Shanghai
elasticsearch.ttl=2d
#在控制台輸出腳本調試開關showTemplate,false關閉，true打開，同時log4j至少是info級別
elasticsearch.showTemplate=true
#elasticsearch.discoverHost=true
http.timeoutConnection = 400000
http.timeoutSocket = 400000
http.connectionRequestTimeout=400000
http.retryTime = 1
http.maxLineLength = -1
http.maxHeaderCount = 200
http.maxTotal = 400
http.defaultMaxPerRoute = 200
elasticsearch.xml
<properties>
<config file="conf/elasticsearch.properties"/>
<property name="elasticsearchPropes">
<propes>
<property name="elasticsearch.client" value="${elasticsearch.client:restful}">
<description> <![CDATA[ 客戶端類型:transport，restful ]]></description>
</property>
<!--<property name="elasticUser" value="${elasticUser:}">-->
<!--<description> <![CDATA[ 認證用戶 ]]></description>-->
<!--</property>-->
<!--<property name="elasticPassword" value="${elasticPassword:}">-->
<!--<description> <![CDATA[ 認證口令 ]]></description>-->
<!--</property>-->
<!--<property name="elasticsearch.hostNames" value="${elasticsearch.hostNames}">
<description> <![CDATA[ 指定序列化處理類，默認為kafka.serializer.DefaultEncoder,即byte[] ]]></description>
</property>-->
<property name="elasticsearch.rest.hostNames" value="${elasticsearch.rest.hostNames}">
<description> <![CDATA[ rest協議地址 ]]></description>
</property>
<property name="elasticsearch.dateFormat" value="${elasticsearch.dateFormat}">
<description> <![CDATA[ 索引日期格式]]></description>
</property>
<property name="elasticsearch.timeZone" value="${elasticsearch.timeZone}">
<description> <![CDATA[ 時區信息]]></description>
</property>
<property name="elasticsearch.ttl" value="${elasticsearch.ttl}">
<description> <![CDATA[ ms(毫秒) s(秒) m(分鍾) h(小時) d(天) w(星期)]]></description>
</property>
<property name="elasticsearch.showTemplate" value="${elasticsearch.showTemplate:false}">
<description> <![CDATA[ query dsl腳本日志調試開關，與log info級別日志結合使用]]></description>
</property>
<property name="elasticsearch.httpPool" value="${elasticsearch.httpPool:default}">
<description> <![CDATA[ http連接池邏輯名稱，在conf/httpclient.xml中配置]]></description>
</property>
<property name="elasticsearch.discoverHost" value="${elasticsearch.discoverHost:false}">
<description> <![CDATA[ 是否啟動節點自動發現功能，默認關閉，開啟后每隔10秒探測新加或者移除的es節點，實時更新本地地址清單]]></description>
</property>
</propes>
</property>
<!--默認的elasticsearch-->
<property name="elasticSearch"
class="org.frameworkset.elasticsearch.ElasticSearch"
init-method="configure"
destroy-method="stop"
f:elasticsearchPropes="attr:elasticsearchPropes"/>
</properties>
httpclient.xml
<properties>
<config file="conf/elasticsearch.properties"/>
<property name="default"
f:timeoutConnection = "${http.timeoutConnection}"
f:timeoutSocket = "${http.timeoutSocket}"
f:connectionRequestTimeout="${http.connectionRequestTimeout}"
f:retryTime = "${http.retryTime}"
f:maxLineLength = "${http.maxLineLength}"
f:maxHeaderCount = "${http.maxHeaderCount}"
f:maxTotal = "${http.maxTotal}"
f:defaultMaxPerRoute = "${http.defaultMaxPerRoute}"
class="org.frameworkset.spi.remote.http.ClientConfiguration">
</property>
</properties>
search.xml
<properties>
<!--
創建document需要的索引表結構
-->
<property name="document">
<![CDATA[{
"settings": {
"number_of_shards": 6,
"index.refresh_interval": "5s"
},
"mappings": {
"document": {
"properties": {
"title": {
"type": "text",
"analyzer": "ik_max_word"
},
"contentbody": {
"type": "text",
"analyzer": "ik_max_word"
},
"fileId": {
"type": "text"
},
"description": {
"type": "text",
"analyzer": "ik_max_word"
},
"tags": {
"type": "text"
},
"typeId": {
"type": "text"
},
"classicId": {
"type": "text"
},
"url": {
"type": "text"
},
"agentStarttime": {
"type": "date"
## ,"format":"yyyy-MM-dd HH:mm:ss.SSS||yyyy-MM-dd'T'HH:mm:ss.SSS||yyyy-MM-dd HH:mm:ss||epoch_millis"
},
"name": {
"type": "keyword"
}
}
}
}
}]]>
</property>
<!--
一個簡單的檢索dsl,中有四個變量
applicationName1
applicationName2
startTime
endTime
通過map傳遞變量參數值
變量語法參考文檔：
-->
<property name="searchDatas">
<![CDATA[{
"query": {
"bool": {
"filter": [
{ ## 多值檢索，查找多個應用名稱對應的文檔記錄
"terms": {
"applicationName.keyword": [#[applicationName1],#[applicationName2]]
}
},
{ ## 時間范圍檢索，返回對應時間范圍內的記錄，接受long型的值
"range": {
"agentStarttime": {
"gte": #[startTime],##統計開始時間
"lt": #[endTime] ##統計截止時間
}
}
}
]
}
},
## 最多返回1000條記錄
"size":1000
}]]>
</property>
<!--
一個簡單的檢索dsl,中有四個變量
applicationName1
applicationName2
startTime
endTime
通過map傳遞變量參數值
變量語法參考文檔：
-->
<property name="searchPagineDatas">
<![CDATA[{
"query": {
"bool": {
"filter": [
{
"term": {
"classicId": #[classicId]
}
}],
"must": [
{
"multi_match": {
"query": #[keywords],
"fields": ["contentbody","title","description"]
}
}
]
}
},
## 分頁起點
"from":#[from] ,
## 最多返回size條記錄
"size":#[size],
"highlight": {
"pre_tags": [
"<mark>"
],
"post_tags": [
"</mark>"
],
"fields": {
"*": {}
},
"fragment_size": 2147483647
}
}]]>
</property>
<property name="searchPagineDatas2">
<![CDATA[{
"query": {
"bool": {
"filter": [
{
"term": {
"classicId": #[classicId]
}
}]
}
},
## 分頁起點
"from":#[from] ,
## 最多返回size條記錄
"size":#[size],
"highlight": {
"pre_tags": [
"<mark>"
],
"post_tags": [
"</mark>"
],
"fields": {
"*": {}
},
"fragment_size": 2147483647
}
}]]>
</property>
<property name="searchPagineDatas3">
<![CDATA[{
"query": {
"bool": {
"filter": [
{
"term": {
"typeId": #[typeId]
}
}],
"must": [
{
"multi_match": {
"query": #[keywords],
"fields": ["contentbody","title","description"]
}
}
]
}
},
## 分頁起點
"from":#[from] ,
## 最多返回size條記錄
"size":#[size],
"highlight": {
"pre_tags": [
"<mark>"
],
"post_tags": [
"</mark>"
],
"fields": {
"*": {}
},
"fragment_size": 2147483647
}
}]]>
</property>
<property name="searchPagineDatas4">
<![CDATA[{
"query": {
"bool": {
"filter": [
{
"term": {
"typeId": #[typeId]
}
}]
}
},
## 分頁起點
"from":#[from] ,
## 最多返回size條記錄
"size":#[size],
"highlight": {
"pre_tags": [
"<mark>"
],
"post_tags": [
"</mark>"
],
"fields": {
"*": {}
},
"fragment_size": 2147483647
}
}]]>
</property>
<!--
一個簡單的檢索dsl,中有四個變量
applicationName1
applicationName2
startTime
endTime
通過map傳遞變量參數值
變量語法參考文檔：
-->
<property name="searchDatasArray">
<![CDATA[{
"query": {
"bool": {
"filter": [
{ ## 多值檢索，查找多個應用名稱對應的文檔記錄
"terms": {
"applicationName.keyword":[
#if($applicationNames && $applicationNames.size() > 0)
#foreach($applicationName in $applicationNames)
#if($velocityCount > 0),#end "$applicationName"
#end
#end
]
}
},
{ ## 時間范圍檢索，返回對應時間范圍內的記錄，接受long型的值
"range": {
"agentStarttime": {
"gte": #[startTime],##統計開始時間
"lt": #[endTime] ##統計截止時間
}
}
}
]
}
},
## 最多返回1000條記錄
"size":1000
}]]>
</property>
<!--部分更新,注意：dsl不能換行-->
<property name="updatePartDocument">
<![CDATA[{"applicationName" : #[applicationName],"agentStarttime" : #[agentStarttime],"contentbody" : #[contentbody]}]]>
</property>
</properties>
hanlp.properties
#本配置文件中的路徑的根目錄，根目錄+其他路徑=完整路徑（支持相對路徑，請參考：https://github.com/hankcs/HanLP/pull/254）
#Windows用戶請注意，路徑分隔符統一使用/
root=H:/doc/java/hzhh123
#root=/home/data/software/devsoft/java/hanlp
#好了，以上為唯一需要修改的部分，以下配置項按需反注釋編輯。
#核心詞典路徑
CoreDictionaryPath=data/dictionary/CoreNatureDictionary.txt
#2元語法詞典路徑
BiGramDictionaryPath=data/dictionary/CoreNatureDictionary.ngram.txt
#自定義詞典路徑，用;隔開多個自定義詞典，空格開頭表示在同一個目錄，使用“文件名 詞性”形式則表示這個詞典的詞性默認是該詞性。優先級遞減。
#所有詞典統一使用UTF-8編碼，每一行代表一個單詞，格式遵從[單詞] [詞性A] [A的頻次] [詞性B] [B的頻次] ... 如果不填詞性則表示采用詞典的默認詞性。
CustomDictionaryPath=data/dictionary/custom/CustomDictionary.txt; 現代漢語補充詞庫.txt; 全國地名大全.txt ns; 人名詞典.txt; 機構名詞典.txt; 上海地名.txt ns;data/dictionary/person/nrf.txt nrf;
#停用詞詞典路徑
CoreStopWordDictionaryPath=data/dictionary/stopwords.txt
#同義詞詞典路徑
CoreSynonymDictionaryDictionaryPath=data/dictionary/synonym/CoreSynonym.txt
#人名詞典路徑
PersonDictionaryPath=data/dictionary/person/nr.txt
#人名詞典轉移矩陣路徑
PersonDictionaryTrPath=data/dictionary/person/nr.tr.txt
#繁簡詞典根目錄
tcDictionaryRoot=data/dictionary/tc
#HMM分詞模型
HMMSegmentModelPath=data/model/segment/HMMSegmentModel.bin
#分詞結果是否展示詞性
ShowTermNature=true
#IO適配器，實現com.hankcs.hanlp.corpus.io.IIOAdapter接口以在不同的平台（Hadoop、Redis等）上運行HanLP
#默認的IO適配器如下，該適配器是基於普通文件系統的。
#IOAdapter=com.hankcs.hanlp.corpus.io.FileIOAdapter
#感知機詞法分析器
PerceptronCWSModelPath=data/model/perceptron/pku199801/cws.bin
PerceptronPOSModelPath=data/model/perceptron/pku199801/pos.bin
PerceptronNERModelPath=data/model/perceptron/pku199801/ner.bin
#CRF詞法分析器
CRFCWSModelPath=data/model/crf/pku199801/cws.txt
CRFPOSModelPath=data/model/crf/pku199801/pos.txt
CRFNERModelPath=data/model/crf/pku199801/ner.txt
#更多配置項請參考 https://github.com/hankcs/HanLP/blob/master/src/main/java/com/hankcs/hanlp/HanLP.java#L59 自行添加
注意：參考https://github.com/hankcs/HanLP，下載data.zip文件，解壓到H:/doc/java/hzhh123下
3、java代碼
Hanlp.java
package com.hd.util;
import com.hankcs.hanlp.HanLP;
import com.hankcs.hanlp.corpus.document.sentence.Sentence;
import com.hankcs.hanlp.corpus.document.sentence.word.IWord;
import com.hankcs.hanlp.model.crf.CRFLexicalAnalyzer;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
/**
* hzhh123
* 2019/3/25 14:05
*
* @desciption 自然語言處理 中文分詞 詞性標注 命名實體識別 依存句法分析
* 新詞發現 關鍵詞短語提取 自動摘要 文本分類聚類 拼音簡繁
* @link https://github.com/hankcs/HanLP
*/
public class HanlpUtil {
/**
* @param content
* @return
* @description 提取摘要
*/
public static List<String> summary(String content) {
List<String> summary = HanLP.extractSummary(content, 3);
return summary;
}
/**
* @param content
* @return
* @desciption 提取短語
*/
public static List<String> phrase(String content) {
return HanLP.extractPhrase(content, 5);
}
/**
* @param document
* @return
* @throws IOException
* @desciption 找出相關詞性聚合成一個list
*/
public static List<String> findWordsAndCollectByLabel(List<String> document) throws IOException {
/* 對詞性進行分析，找出合適的詞性 */
CRFLexicalAnalyzer analyzer = new CRFLexicalAnalyzer();
Sentence analyzeWords = analyzer.analyze(String.valueOf(document));
List<IWord> wordsByLabell = analyzeWords.findWordsByLabel("n");
List<IWord> wordsByLabel2 = analyzeWords.findWordsByLabel("ns");
List<IWord> wordsByLabel3 = analyzeWords.findWordsByLabel("t");
List<IWord> wordsByLabel4 = analyzeWords.findWordsByLabel("j");
List<IWord> wordsByLabel5 = analyzeWords.findWordsByLabel("vn");
List<IWord> wordsByLabel6 = analyzeWords.findWordsByLabel("nr");
List<IWord> wordsByLabel7 = analyzeWords.findWordsByLabel("nt");
List<IWord> wordsByLabel8 = analyzeWords.findWordsByLabel("nz");
wordsByLabell.addAll(wordsByLabel2);
wordsByLabell.addAll(wordsByLabel3);
wordsByLabell.addAll(wordsByLabel4);
wordsByLabell.addAll(wordsByLabel5);
wordsByLabell.addAll(wordsByLabel6);
wordsByLabell.addAll(wordsByLabel7);
wordsByLabell.addAll(wordsByLabel8);
List<String> words = new ArrayList<>();
for (IWord word : wordsByLabell) {
words.add(word.getValue());
}
return words;
}
public static void main(String[] args) {
String document = "算法可大致分為基本算法、數據結構的算法、數論算法、計算幾何的算法、圖的算法、動態規划以及數值分析、加密算法、排序算法、檢索算法、隨機化算法、並行算法、厄米變形模型、隨機森林算法。\n" +
"算法可以寬泛的分為三類，\n" +
"一，有限的確定性算法，這類算法在有限的一段時間內終止。他們可能要花很長時間來執行指定的任務，但仍將在一定的時間內終止。這類算法得出的結果常取決於輸入值。\n" +
"二，有限的非確定算法，這類算法在有限的時間內終止。然而，對於一個（或一些）給定的數值，算法的結果並不是唯一的或確定的。\n" +
"三，無限的算法，是那些由於沒有定義終止定義條件，或定義的條件無法由輸入的數據滿足而不終止運行的算法。通常，無限算法的產生是由於未能確定的定義終止條件。";
List<String> sentenceList = phrase(document);
// List<String> sentenceList = summary(document);
System.out.println(sentenceList);
}
}
ElasticsearchResponseEntity.java
package com.hd.util;
import java.util.List;
/**
* hzhh123
* 2019/3/22 11:51
* @descript elasticsearch分頁查詢查詢返回結果內容
*/
public class ElasticsearchResponseEntity<T> {
private int from=0;
private int size=10;
private Long total;
private List<T> records;
public ElasticsearchResponseEntity(int from, int size) {
this.from = from;
this.size = size;
}
public int getFrom() {
return from;
}
public void setFrom(int from) {
this.from = from;
}
public int getSize() {
return size;
}
public void setSize(int size) {
this.size = size;
}
public Long getTotal() {
return total;
}
public void setTotal(Long total) {
this.total = total;
}
public List<T> getRecords() {
return records;
}
public void setRecords(List<T> records) {
this.records = records;
}
}
ElasticsearchClentUtil.java
package com.hd.util;
import org.frameworkset.elasticsearch.ElasticSearchException;
import org.frameworkset.elasticsearch.ElasticSearchHelper;
import org.frameworkset.elasticsearch.client.ClientInterface;
import org.frameworkset.elasticsearch.entity.ESBaseData;
import org.frameworkset.elasticsearch.entity.ESDatas;
import java.util.HashMap;
import java.util.Iterator;
import java.util.List;
import java.util.Map;
/**
* hzhh123
* <p>
* ES 增刪改查實現
* @link https://gitee.com/bboss/bboss-elastic
* </p>
*/
public class ElasticsearchClentUtil<T extends ESBaseData> {
private String mappath;
public ElasticsearchClentUtil(String mappath) {
this.mappath = mappath;
}
/**
* @param indexName 索引名稱
* @param indexMapping 表結構名稱
* @return
* @description 創建索引庫
*/
public String createIndex(String indexName, String indexMapping) throws Exception {
//加載配置文件，單實例多線程安全的
ClientInterface clientUtil = ElasticSearchHelper.getConfigRestClientUtil(mappath);
//判斷索引表是否存在
boolean exist = clientUtil.existIndice(indexName);
if (exist) {
//創建一個mapping之前先刪除
clientUtil.dropIndice(indexName);
}
//創建mapping
return clientUtil.createIndiceMapping(indexName, indexMapping);
}
/**
* @desciption 刪除索引
* @param indexName
* @return
*/
public String dropIndex(String indexName){
//加載配置文件，單實例多線程安全的
ClientInterface clientUtil = ElasticSearchHelper.getConfigRestClientUtil(mappath);
return clientUtil.dropIndice(indexName);
}
/**
* @param indexName 索引庫名稱
* @param indexType 索引類型
* @param id 索引id
* @return
* @description 刪除文檔索引
*/
public String deleteDocment(String indexName, String indexType, String id) throws ElasticSearchException {
//加載配置文件，單實例多線程安全的
ClientInterface clientUtil = ElasticSearchHelper.getConfigRestClientUtil(mappath);
return clientUtil.deleteDocument(indexName, indexType, id);
}
/**
* @param indexName 索引庫名稱
* @param indexType 索引類型
* @param bean
* @return
* @description 添加文檔
*/
public String addDocument(String indexName, String indexType,T bean){
//創建創建/修改/獲取/刪除文檔的客戶端對象，單實例多線程安全
ClientInterface clientUtil = ElasticSearchHelper.getConfigRestClientUtil(mappath);
return clientUtil.addDocument(indexName,indexType,bean);
}
/**
*
* @param path _search為檢索操作action
* @param templateName esmapper/search.xml中定義的dsl語句
* @param queryFiled 查詢參數
* @param keywords 查詢參數值
* @param from 分頁查詢的起始記錄,默認為0
* @param size 分頁大小，默認為10
* @return
*/
public ElasticsearchResponseEntity<T> searchDocumentByKeywords(String path, String templateName, String queryFiled, String keywords,
String from, String size, Class <T> beanClass) {
//加載配置文件，單實例多線程安全的
ClientInterface clientUtil = ElasticSearchHelper.getConfigRestClientUtil(mappath);
Map<String,Object> params = new HashMap<String,Object>();
params.put(queryFiled, keywords);
//設置分頁參數
params.put("from",from);
params.put("size",size);
ElasticsearchResponseEntity<T> responseEntity = new ElasticsearchResponseEntity<T>(Integer.parseInt(from),Integer.parseInt(size));
//執行查詢，search為索引表，_search為檢索操作action
ESDatas<T> esDatas = //ESDatas包含當前檢索的記錄集合，最多1000條記錄，由dsl中的size屬性指定
clientUtil.searchList(path,//search為索引表，_search為檢索操作action
templateName,//esmapper/search.xml中定義的dsl語句
params,//變量參數
beanClass);//返回的文檔封裝對象類型
//獲取結果對象列表，最多返回1000條記錄
List<T> documentList = esDatas.getDatas();
System.out.println(documentList==null);
//獲取總記錄數
long totalSize = esDatas.getTotalSize();
responseEntity.setTotal(totalSize);
for(int i = 0; documentList != null && i < documentList.size(); i ++) {//遍歷檢索結果列表
T doc = documentList.get(i);
//記錄中匹配上檢索條件的所有字段的高亮內容
Map<String, List<Object>> highLights = doc.getHighlight();
Iterator<Map.Entry<String, List<Object>>> entries = highLights.entrySet().iterator();
while (entries.hasNext()) {
Map.Entry<String, List<Object>> entry = entries.next();
String fieldName = entry.getKey();
System.out.print(fieldName + ":");
List<Object> fieldHighLightSegments = entry.getValue();
for (Object highLightSegment : fieldHighLightSegments) {
/**
* 在dsl中通過<mark></mark>來標識需要高亮顯示的內容，然后傳到web ui前端的時候，通過為mark元素添加css樣式來設置高亮的顏色背景樣式
* 例如：
* <style type="text/css">
* .mark,mark{background-color:#f39c12;padding:.2em}
* </style>
*/
System.out.println(highLightSegment);
}
}
}
responseEntity.setRecords(documentList);
return responseEntity;
}
/**
*
* @param path _search為檢索操作action
* @param templateName esmapper/search.xml中定義的dsl語句
* @param paramsMap 包含from和size,還有其他要查詢的key-value
* @return
*/
public ElasticsearchResponseEntity<T> searchDocumentByKeywords(String path, String templateName, Map<String,String> paramsMap,
Class <T> beanClass) {
//加載配置文件，單實例多線程安全的
ClientInterface clientUtil = ElasticSearchHelper.getConfigRestClientUtil(mappath);
ElasticsearchResponseEntity<T> responseEntity = new ElasticsearchResponseEntity<T>(Integer.parseInt(paramsMap.get("from")),Integer.parseInt(paramsMap.get("size")));
//執行查詢，search為索引表，_search為檢索操作action
ESDatas<T> esDatas = //ESDatas包含當前檢索的記錄集合，最多1000條記錄，由dsl中的size屬性指定
clientUtil.searchList(path,//search為索引表，_search為檢索操作action
templateName,//esmapper/search.xml中定義的dsl語句
paramsMap,//變量參數
beanClass);//返回的文檔封裝對象類型
//獲取結果對象列表，最多返回1000條記錄
List<T> documentList = esDatas.getDatas();
System.out.println(documentList==null);
//獲取總記錄數
long totalSize = esDatas.getTotalSize();
responseEntity.setTotal(totalSize);
for(int i = 0; documentList != null && i < documentList.size(); i ++) {//遍歷檢索結果列表
T doc = documentList.get(i);
//記錄中匹配上檢索條件的所有字段的高亮內容
Map<String, List<Object>> highLights = doc.getHighlight();
Iterator<Map.Entry<String, List<Object>>> entries = highLights.entrySet().iterator();
while (entries.hasNext()) {
Map.Entry<String, List<Object>> entry = entries.next();
String fieldName = entry.getKey();
System.out.print(fieldName + ":");
List<Object> fieldHighLightSegments = entry.getValue();
for (Object highLightSegment : fieldHighLightSegments) {
/**
* 在dsl中通過<mark></mark>來標識需要高亮顯示的內容，然后傳到web ui前端的時候，通過為mark元素添加css樣式來設置高亮的顏色背景樣式
* 例如：
* <style type="text/css">
* .mark,mark{background-color:#f39c12;padding:.2em}
* </style>
*/
System.out.println(highLightSegment);
}
}
}
responseEntity.setRecords(documentList);
return responseEntity;
}
}