目录
1、com.xiong.bean.LuceneBean.java
2、package com.xiong.lucene.OperateLucene.java
3、com.xiong.utils.DocementUtil.java
一、项目需求
将文章作文Lucene的仓库和索引库，当输入一段话如“孙悟空很厉害”自动进行分词，并全文索引，返回其id号和文章内容,其中由于给多家银行，所以bean有银行号
二、项目开发所需基本知识
https://blog.youkuaiyun.com/qq_27339781/article/details/82814360
三、项目结构
四、代码
1、com.xiong.bean.LuceneBean.java
package com.xiong.bean;
import java.io.Serializable;
public class LuceneBean implements Serializable{
private static final long serialVersionUID = 1L;
private String id;
private String content;
private String bankId;
public String getId() {
return id;
}
public void setId(String id) {
this.id = id;
}
public String getContent() {
return content;
}
public void setContent(String content) {
this.content = content;
}
public String getBankId() {
return bankId;
}
public void setBankId(String bankId) {
this.bankId = bankId;
}
}
2、package com.xiong.lucene.OperateLucene.java
package com.xiong.lucene;
import java.io.File;
import java.io.IOException;
import java.io.StringReader;
import java.util.ArrayList;
import java.util.List;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.tokenattributes.TermAttribute;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriter.MaxFieldLength;
import org.apache.lucene.index.Term;
import org.apache.lucene.queryParser.MultiFieldQueryParser;
import org.apache.lucene.queryParser.QueryParser;
import org.apache.lucene.search.BooleanClause.Occur;
import org.apache.lucene.search.BooleanQuery;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TermQuery;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.Version;
import org.junit.Test;
import org.wltea.analyzer.lucene.IKAnalyzer;
import com.xiong.bean.LuceneBean;
import com.xiong.utils.DocumentUtils;
public class OperateLucene {
private String dirPath;
public String getDirPath() {
return dirPath;
}
public void setDirPath(String dirPath) {
this.dirPath = dirPath;
}
public OperateLucene(String dirPath) {
super();
this.dirPath = dirPath;
}
/*-----------------------------------------------------------------------------------------------------------*/
/**
* 添加到Lucene的List数据库中
* @param luceneBeans lucene的List
* @param dirPath
*/
public void writeLucene(List<LuceneBean> luceneBeans){
IndexWriter indexWriter = null;
try {
/**
* 第一个参数 :索引库的位置
*/
Directory directory = FSDirectory.open(new File(dirPath));
/**
* 第二个参数:分词器
*/
Analyzer analyzer = new IKAnalyzer();
/**
* 第三个参数:限制索引库中字段的大小
*/
indexWriter = new IndexWriter(directory, analyzer, MaxFieldLength.LIMITED);
for (int i = 0; i < luceneBeans.size(); i++) {
LuceneBean luceneBean = luceneBeans.get(i);
//把article转化成document
Document document = DocumentUtils.bean2Document(luceneBean);
//把document加入到索引库中
indexWriter.addDocument(document);
}
} catch (IOException e) {
e.printStackTrace();
}finally{
try {
indexWriter.close();
} catch (Exception e) {
e.printStackTrace();
}
}
}
/*-----------------------------------------------------------------------------------------------------------*/
/**
* 添加到Lucene数据库中,单个
* @param luceneBeans lucene
* @param dirPath
*/
public boolean writeLucene(LuceneBean luceneBean){
IndexWriter indexWriter = null;
try {
/**
* 第一个参数 :索引库的位置
*/
Directory directory = FSDirectory.open(new File(dirPath));
/**
* 第二个参数:分词器
*/
Analyzer analyzer = new IKAnalyzer();
/**
* 第三个参数:限制索引库中字段的大小
*/
indexWriter = new IndexWriter(directory, analyzer, MaxFieldLength.LIMITED);
//把lucene转化成document
Document document = DocumentUtils.bean2Document(luceneBean);
//把document加入到索引库中
indexWriter.addDocument(document);
return true;
} catch (IOException e) {
e.printStackTrace();
return false;
}finally{
try {
indexWriter.close();
} catch (Exception e) {
e.printStackTrace();
}
}
}
/*-----------------------------------------------------------------------------------------------------------*/
/**
* 删除
* 不是把原来的cfs文件删除掉了，而是多了一个del文件
*/
@Test
public boolean delete(String id){
IndexWriter indexWriter = null;
try {
/**
* 第一个参数 :索引库的位置
*/
Directory directory = FSDirectory.open(new File(dirPath));
/**
* 第二个参数:分词器
*/
Analyzer analyzer = new IKAnalyzer();
/**
* 第三个参数:限制索引库中字段的大小
*/
indexWriter = new IndexWriter(directory, analyzer, MaxFieldLength.LIMITED);
Term term = new Term("id",id);
indexWriter.deleteDocuments(term);
return true;
} catch (IOException e) {
e.printStackTrace();
return false;
}finally{
try {
indexWriter.close();
} catch (Exception e) {
e.printStackTrace();
}
}
}
/*-----------------------------------------------------------------------------------------------------------*/
/**
* 修改
* 先删除后增加
*/
@Test
public boolean update(LuceneBean luceneBean){
IndexWriter indexWriter = null;
try {
/**
* 第一个参数 :索引库的位置
*/
Directory directory = FSDirectory.open(new File(dirPath));
/**
* 第二个参数:分词器
*/
Analyzer analyzer = new IKAnalyzer();
/**
* 第三个参数:限制索引库中字段的大小
*/
indexWriter = new IndexWriter(directory, analyzer, MaxFieldLength.LIMITED);
Term term = new Term("id",luceneBean.getId());
//把lucene转化成document
Document document = DocumentUtils.bean2Document(luceneBean);
indexWriter.updateDocument(term, document);
return true;
} catch (IOException e) {
e.printStackTrace();
return false;
}finally{
try {
indexWriter.close();
} catch (Exception e) {
e.printStackTrace();
}
}
}
/*-----------------------------------------------------------------------------------------------------------*/
/**
* 查找
* @throws Exception
*/
@Test
public boolean search(String content,String bankId){
try {
Directory directory = FSDirectory.open(new File(dirPath));
IndexSearcher indexSearcher = new IndexSearcher(directory);
BooleanQuery booleanQuery = new BooleanQuery();
Query query1 = new TermQuery(new Term("bankId", bankId));
booleanQuery.add(query1, Occur.MUST);
List<String> queryList = getQueryList(content);
for (int i = 0; i < queryList.size(); i++) {
String str = queryList.get(i);
Query query2 = new TermQuery(new Term("content", str));
booleanQuery.add(query2, Occur.SHOULD);
}
TopDocs topDocs = indexSearcher.search(booleanQuery, 5);
ScoreDoc[] scoreDocs = topDocs.scoreDocs;
List<LuceneBean> LuceneBeans = new ArrayList<LuceneBean>();
for (ScoreDoc scoreDoc : scoreDocs) {
int index = scoreDoc.doc;
Document document = indexSearcher.doc(index);
LuceneBean LuceneBean = DocumentUtils.document2Bean(document);
LuceneBeans.add(LuceneBean);
}
for (LuceneBean lucene : LuceneBeans) {
System.out.println(lucene.getId());
System.out.println(lucene.getContent());
System.out.println(lucene.getBankId());
}
return true;
} catch (Exception e) {
e.printStackTrace();
return false;
}finally{
}
}
/*-----------------------------------------------------------------------------------------------------------*/
/**
* 获取查询的组件
* @param content
* @return
* @throws IOException
*/
public List<String> getQueryList(String content) throws IOException{
Analyzer analyzer = new IKAnalyzer();
TokenStream tokenStream = analyzer.tokenStream("", new StringReader(content));
tokenStream.addAttribute(TermAttribute.class);
List<String> list = new ArrayList<String>();
while (tokenStream.incrementToken()) {
TermAttribute termAttribute = tokenStream.getAttribute(TermAttribute.class);
list.add(termAttribute.term());
System.out.println(termAttribute.term());
}
System.out.println("-------------------------------------------------");
tokenStream.end();
tokenStream.close();
return list;
}
/*-----------------------------------------------------------------------------------------------------------*/
}
3、com.xiong.utils.DocementUtil.java
package com.xiong.utils;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.Field.Index;
import org.apache.lucene.document.Field.Store;
import com.xiong.bean.LuceneBean;
public class DocumentUtils {
public static Document bean2Document(LuceneBean luceneBean){
Document document = new Document();
Field id = new Field("id", luceneBean.getId(), Store.YES, Index.NOT_ANALYZED);
Field content = new Field("content", luceneBean.getContent(), Store.YES, Index.ANALYZED);
Field bankId = new Field("bankId", luceneBean.getBankId(), Store.YES, Index.NOT_ANALYZED);
//把上面的field放入到document中
document.add(id);
document.add(content);
document.add(bankId);
return document;
}
public static LuceneBean document2Bean(Document document){
LuceneBean luceneBean = new LuceneBean();
luceneBean.setId(document.get("id"));
luceneBean.setContent(document.get("content"));
luceneBean.setBankId(document.get("bankId"));
return luceneBean;
}
}
4.com.xiong.Test.java
package com.xiong;
import java.io.IOException;
import com.xiong.lucene.OperateLucene;
public class Test {
public static void main(String[] args) throws IOException {
// List<LuceneBean> list = new ArrayList<LuceneBean>();
// for (int i = 0; i < 20; i++) {
// LuceneBean luceneBean = new LuceneBean();
// luceneBean.setId("2018"+i);
// luceneBean.setContent("我是银行的记录");
// luceneBean.setBankId(i+"");
// list.add(luceneBean);
// }
OperateLucene operateLucene = new OperateLucene("./DirIndex");
// operateLucene.writeLucene(list);
// operateLucene.delete("20182");
// LuceneBean luceneBean = new LuceneBean();
// luceneBean.setId("20183");
// luceneBean.setContent("我是银行的记录哈哈哈");
// luceneBean.setBankId("3");
// operateLucene.update(luceneBean);
operateLucene.search("记录","3");
// List<String> list = operateLucene.getQueryList("山西省太原市晋源区姚村镇枣园头关道街555号");
// for (int i = 0; i < list.size(); i++) {
// System.out.println(list.get(i));
// }
}
}
5.IKAnalyzer.cfg.xml
<?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">/mydict.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">/ext_stopword.dic</entry>
-->
</properties>
扫一扫
866
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
