Lucene全文检索

Lucene 是一个基于 Java 的全文信息检索工具包,目前主流的搜索系统 Elasticsearch 和 solr 都是基于 lucene 的索引和搜索能力进行。

Solr与Lucene的区别:

Solr和Lucene的本质区别三点:搜索服务器,企业级和管理。

Lucene本质上是搜索库,不是独立的应用程序,而Solr是。

Lucene专注于搜索底层的建设,而Solr专注与企业应用。

Lucene不负责支撑搜索服务所必须的管理,而Slor负责

所以说,一句话概括solr是Lucene面向企业搜索应用的扩展,如果Lucene数据量超过10万就会有点力不从心了

ES:
ES是对apache lucene的封装。
ES是elasticSearch的缩写,它是一个实时的分布式的查询和分析引擎。它是基于apache lucene开发的。
2:ES的目标是让全文搜索变得简单
3:ES可以支持横向的扩展,支持pb级别的结构和非机构化的数据处理。
4:使用ES可以以前所未有的速度来处理大数据。

今天的主题是Lucene:

Lucene生成索引:

package com.zking.test.lucene;

/**
 * 生成索引测试
 * @author Administrator
 *
 */
public class Demo1 {
	public static void main(String[] args) {
//		索引文件将要存放的位置
		String indexDir = "E:\\temp\\test\\lucene\\demo1";
//		数据源地址
		String dataDir = "E:\\temp\\test\\lucene\\demo1\\data";
		IndexCreate ic = null; 
		try {
			ic = new IndexCreate(indexDir);
			long start = System.currentTimeMillis();
			int num = ic.index(dataDir);
			long end = System.currentTimeMillis();
			System.out.println("检索指定路径下"+num+"个文件,一共花费了"+(end-start)+"毫秒");
		} catch (Exception e) {
			e.printStackTrace();
		}finally {
			try {
				ic.closeIndexWriter();
			} catch (Exception e) {
				e.printStackTrace();
			}
		}
	}
}

配合Demo1的实现:

package com.zking.test.lucene;

import java.io.File;
import java.io.FileReader;
import java.nio.file.Paths;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.TextField;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.store.FSDirectory;

/**
 * 配合Demo1.java进行lucene的helloword实现
 * @author Administrator
 *
 */
public class IndexCreate {
	private IndexWriter indexWriter;
	
	/**
	 * 1、构造方法 实例化IndexWriter
	 * @param indexDir 索引文件存放的地址
	 * @throws Exception
	 */
	public IndexCreate(String indexDir) throws Exception{
//		获取索引文件的存放地址对象
		FSDirectory dir = FSDirectory.open(Paths.get(indexDir));
//		标准分词器(针对英文)
		Analyzer analyzer = new StandardAnalyzer();
//		索引输出流配置对象
		IndexWriterConfig conf = new IndexWriterConfig(analyzer); 
		indexWriter = new IndexWriter(dir, conf);
	}
	
	/**
	 * 2、关闭索引输出流
	 * @throws Exception
	 */
	public void closeIndexWriter()  throws Exception{
		indexWriter.close();
	}
	
	/**
	 * 3、索引指定路径下的所有文件
	 * @param dataDir 数据源
	 * @return
	 * @throws Exception
	 */
	public int index(String dataDir) throws Exception{
		File[] files = new File(dataDir).listFiles();
		for (File file : files) {
			indexFile(file);
		}
		return indexWriter.numDocs();
	}
	
	/**
	 * 4、索引指定的文件
	 * @param file
	 * @throws Exception
	 */
	private void indexFile(File file) throws Exception{
		System.out.println("被索引文件的全路径:"+file.getCanonicalPath());
		Document doc = getDocument(file);
		indexWriter.addDocument(doc);
	}
	
	/**
	 * 5、获取文档(索引文件中包含的重要信息,key-value的形式)
	 * @param file
	 * @return
	 * @throws Exception
	 */
	private Document getDocument(File file) throws Exception{
		Document doc = new Document();
		doc.add(new TextField("contents", new FileReader(file)));
//		Field.Store.YES是否存储到硬盘
		doc.add(new TextField("fullPath", file.getCanonicalPath(),Field.Store.YES));
		doc.add(new TextField("fileName", file.getName(),Field.Store.YES));
		return doc;
	}
}

Lucene查询索引:

package com.zking.test.lucene;

/**
 * 查询索引测试
 * @author Administrator
 *
 */
public class Demo2 {
	public static void main(String[] args) {
		String indexDir = "E:\\temp\\test\\lucene\\demo1";
		String q = "EarlyTerminating-Collector";
		try {
			IndexUse.search(indexDir, q);
		} catch (Exception e) {
			e.printStackTrace();
		}
	}
}

配合Demo2的实现:

package com.zking.test.lucene;

import java.nio.file.Paths;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.queryparser.classic.QueryParser;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.store.FSDirectory;

/**
 * 配合Demo2.java进行lucene的helloword实现
 * @author Administrator
 *
 */
public class IndexUse {
	/**
	 * 通过关键字在索引目录中查询
	 * @param indexDir	索引文件所在目录
	 * @param q	关键字
	 */
	public static void search(String indexDir, String q) throws Exception{
		FSDirectory indexDirectory = FSDirectory.open(Paths.get(indexDir));
//		注意:索引输入流不是new出来的,是通过目录读取工具类打开的
		IndexReader indexReader = DirectoryReader.open(indexDirectory);
//		获取索引搜索对象
		IndexSearcher indexSearcher = new IndexSearcher(indexReader);
		Analyzer analyzer = new StandardAnalyzer();
		QueryParser queryParser = new QueryParser("contents", analyzer);
//		获取符合关键字的查询对象
		Query query = queryParser.parse(q);
		
		long start=System.currentTimeMillis();
//		获取关键字出现的前十次
		TopDocs topDocs = indexSearcher.search(query , 10);
		long end=System.currentTimeMillis();
		System.out.println("匹配 "+q+" ,总共花费"+(end-start)+"毫秒"+"查询到"+topDocs.totalHits+"个记录");
		
		for (ScoreDoc scoreDoc : topDocs.scoreDocs) {
			int docID = scoreDoc.doc;
//			索引搜索对象通过文档下标获取文档
			Document doc = indexSearcher.doc(docID);
			System.out.println("通过索引文件:"+doc.get("fullPath")+"拿数据");
		}
		
		indexReader.close();
	}
}

对索引的增删改:

package com.zking.test.lucene;

import java.nio.file.Paths;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.StringField;
import org.apache.lucene.document.TextField;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.index.Term;
import org.apache.lucene.store.FSDirectory;
import org.junit.Before;
import org.junit.Test;

/**
 * 构建索引
 * 	对索引的增删改
 * @author Administrator
 *
 */
public class Demo3 {
	private String ids[]={"1","2","3"};
	private String citys[]={"qingdao","nanjing","shanghai"};
	private String descs[]={
			"Qingdao is a beautiful city.",
			"Nanjing is a city of culture.",
			"Shanghai is a bustling city."
	};
	private FSDirectory dir;
	
	/**
	 * 每次都生成索引文件
	 * @throws Exception
	 */
	@Before
	public void setUp() throws Exception {
		dir  = FSDirectory.open(Paths.get("E:\\temp\\test\\lucene\\demo2\\indexDir"));
		IndexWriter indexWriter = getIndexWriter();
		for (int i = 0; i < ids.length; i++) {
			Document doc = new Document();
			doc.add(new StringField("id", ids[i], Field.Store.YES));
			doc.add(new StringField("city", citys[i], Field.Store.YES));
			doc.add(new TextField("desc", descs[i], Field.Store.NO));
			indexWriter.addDocument(doc);
		}
		indexWriter.close();
	}

	/**
	 * 获取索引输出流
	 * @return
	 * @throws Exception
	 */
	private IndexWriter getIndexWriter()  throws Exception{
		Analyzer analyzer = new StandardAnalyzer();
		IndexWriterConfig conf = new IndexWriterConfig(analyzer);
		return new IndexWriter(dir, conf );
	}
	
	/**
	 * 测试写了几个索引文件
	 * @throws Exception
	 */
	@Test
	public void getWriteDocNum() throws Exception {
		IndexWriter indexWriter = getIndexWriter();
		System.out.println("索引目录下生成"+indexWriter.numDocs()+"个索引文件");
	}
	
	/**
	 * 打上标记,该索引实际并未删除
	 * @throws Exception
	 */
	@Test
	public void deleteDocBeforeMerge() throws Exception {
		IndexWriter indexWriter = getIndexWriter();
		System.out.println("最大文档数:"+indexWriter.maxDoc());
		indexWriter.deleteDocuments(new Term("id", "1"));
		indexWriter.commit();
		
		System.out.println("最大文档数:"+indexWriter.maxDoc());
		System.out.println("实际文档数:"+indexWriter.numDocs());
		indexWriter.close();
	}
	
	/**
	 * 对应索引文件已经删除,但是该版本的分词会保留
	 * @throws Exception
	 */
	@Test
	public void deleteDocAfterMerge() throws Exception {	
//		org.apache.lucene.store.LockObtainFailedException: Lock held by this virtual machine:indexWriter是单例的、线程安全的,不允许打开多个。
		IndexWriter indexWriter = getIndexWriter();
		System.out.println("最大文档数:"+indexWriter.maxDoc());
		indexWriter.deleteDocuments(new Term("id", "1"));
		indexWriter.forceMergeDeletes(); //强制删除
		indexWriter.commit();
		
		System.out.println("最大文档数:"+indexWriter.maxDoc());
		System.out.println("实际文档数:"+indexWriter.numDocs());
		indexWriter.close();
	}
	
	/**
	 * 测试更新索引
	 * @throws Exception
	 */
	@Test
	public void testUpdate()throws Exception{
		IndexWriter writer=getIndexWriter();
		Document doc=new Document();
		doc.add(new StringField("id", "1", Field.Store.YES));
		doc.add(new StringField("city","qingdao",Field.Store.YES));
		doc.add(new TextField("desc", "dsss is a city.", Field.Store.NO));
		writer.updateDocument(new Term("id","1"), doc);
		writer.close();
	}
}

文档域加权:

package com.zking.test.lucene;

import java.nio.file.Paths;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.StringField;
import org.apache.lucene.document.TextField;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.index.Term;
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.junit.Before;
import org.junit.Test;

/**
 * 文档域加权
 * @author Administrator
 *
 */
public class Demo4 {
	private String ids[]={"1","2","3","4"};
	private String authors[]={"Jack","Marry","John","Json"};
	private String positions[]={"accounting","technician","salesperson","boss"};
	private String titles[]={"Java is a good language.","Java is a cross platform language","Java powerful","You should learn java"};
	private String contents[]={
			"If possible, use the same JRE major version at both index and search time.",
			"When upgrading to a different JRE major version, consider re-indexing. ",
			"Different JRE major versions may implement different versions of Unicode,",
			"For example: with Java 1.4, `LetterTokenizer` will split around the character U+02C6,"
	};
	
	private Directory dir;//索引文件目录

	@Before
	public void setUp()throws Exception {
		dir = FSDirectory.open(Paths.get("E:\\temp\\test\\lucene\\demo3\\indexDir"));
		IndexWriter writer = getIndexWriter();
		for (int i = 0; i < authors.length; i++) {
			Document doc = new Document();
			doc.add(new StringField("id", ids[i], Field.Store.YES));
			doc.add(new StringField("author", authors[i], Field.Store.YES));
			doc.add(new StringField("position", positions[i], Field.Store.YES));
			
			TextField textField = new TextField("title", titles[i], Field.Store.YES);
			
//			Json投钱做广告,把排名刷到第一了
			if("boss".equals(positions[i])) {
				textField.setBoost(2f);//设置权重,默认为1
			}
			
			doc.add(textField);
//			TextField会分词,StringField不会分词
			doc.add(new TextField("content", contents[i], Field.Store.NO));
			writer.addDocument(doc);
		}
		writer.close();
		
	}

	private IndexWriter getIndexWriter() throws Exception{
		Analyzer analyzer = new StandardAnalyzer();
		IndexWriterConfig conf = new IndexWriterConfig(analyzer);
		return new IndexWriter(dir, conf);
	}
	
	@Test
	public void index() throws Exception{
		IndexReader reader = DirectoryReader.open(dir);
		IndexSearcher searcher = new IndexSearcher(reader);
		String fieldName = "title";
		String keyWord = "java";
		Term t = new Term(fieldName, keyWord);
		Query query = new TermQuery(t);
		TopDocs hits = searcher.search(query, 10);
		System.out.println("关键字:‘"+keyWord+"’命中了"+hits.totalHits+"次");
		for (ScoreDoc scoreDoc : hits.scoreDocs) {
			Document doc = searcher.doc(scoreDoc.doc);
			System.out.println(doc.get("author"));
		}
	}
	
}

特定项搜索和查询表达式(queryParser):

package com.zking.test.lucene;

import java.io.IOException;
import java.nio.file.Paths;

import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.Term;
import org.apache.lucene.queryparser.classic.ParseException;
import org.apache.lucene.queryparser.classic.QueryParser;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.NumericRangeQuery;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TermQuery;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.store.FSDirectory;
import org.junit.Before;
import org.junit.Test;

/**
 * 特定项搜索
 * 查询表达式(queryParser)
 * @author Administrator
 *
 */
public class Demo5 {
	@Before
	public void setUp() {
		// 索引文件将要存放的位置
		String indexDir = "E:\\temp\\test\\lucene\\demo4";
		// 数据源地址
		String dataDir = "E:\\temp\\test\\lucene\\demo4\\data";
		IndexCreate ic = null;
		try {
			ic = new IndexCreate(indexDir);
			long start = System.currentTimeMillis();
			int num = ic.index(dataDir);
			long end = System.currentTimeMillis();
			System.out.println("检索指定路径下" + num + "个文件,一共花费了" + (end - start) + "毫秒");
			
			
		} catch (Exception e) {
			e.printStackTrace();
		} finally {
			try {
				ic.closeIndexWriter();
			} catch (Exception e) {
				e.printStackTrace();
			}
		}
	}
	
	/**
	 * 特定项搜索
	 */
	@Test
	public void testTermQuery() {
		String indexDir = "E:\\temp\\test\\lucene\\demo4";
		
		String fld = "contents";
		String text = "indexformattoooldexception";
//		特定项片段名和关键字
		Term t  = new Term(fld , text);
		TermQuery tq = new TermQuery(t  );
		try {
			FSDirectory indexDirectory = FSDirectory.open(Paths.get(indexDir));
//			注意:索引输入流不是new出来的,是通过目录读取工具类打开的
			IndexReader indexReader = DirectoryReader.open(indexDirectory);
//			获取索引搜索对象
			IndexSearcher is = new IndexSearcher(indexReader);
			
			
			TopDocs hits = is.search(tq, 100);
//			System.out.println(hits.totalHits);
			for(ScoreDoc scoreDoc: hits.scoreDocs) {
				Document doc = is.doc(scoreDoc.doc);
				System.out.println("文件"+doc.get("fullPath")+"中含有该关键字");
				
			}
		} catch (IOException e) {
			e.printStackTrace();
		}
	}
	
	/**
	 * 查询表达式(queryParser)
	 */
	@Test
	public void testQueryParser() {
		String indexDir = "E:\\temp\\test\\lucene\\demo4";
//		获取查询解析器(通过哪种分词器去解析哪种片段)
		QueryParser queryParser = new QueryParser("contents", new StandardAnalyzer());
		try {
			FSDirectory indexDirectory = FSDirectory.open(Paths.get(indexDir));
//			注意:索引输入流不是new出来的,是通过目录读取工具类打开的
			IndexReader indexReader = DirectoryReader.open(indexDirectory);
//			获取索引搜索对象
			IndexSearcher is = new IndexSearcher(indexReader);
			
//			由解析器去解析对应的关键字
			TopDocs hits = is.search(queryParser.parse("indexformattoooldexception") , 100);
			for(ScoreDoc scoreDoc: hits.scoreDocs) {
				Document doc = is.doc(scoreDoc.doc);
				System.out.println("文件"+doc.get("fullPath")+"中含有该关键字");
				
			}
		} catch (IOException e) {
			e.printStackTrace();
		} catch (ParseException e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
		}
	}
	
}

指定数字范围查询和指定字符串开头字母查询(prefixQuery):

package com.zking.test.lucene;

import java.nio.file.Paths;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.IntField;
import org.apache.lucene.document.StringField;
import org.apache.lucene.document.TextField;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.index.Term;
import org.apache.lucene.search.BooleanClause;
import org.apache.lucene.search.BooleanQuery;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.NumericRangeQuery;
import org.apache.lucene.search.PrefixQuery;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.store.FSDirectory;
import org.junit.Before;
import org.junit.Test;

/**
 * 指定数字范围查询
 * 指定字符串开头字母查询(prefixQuery)
 * @author Administrator
 *
 */
public class Demo6 {
	private int ids[]={1,2,3};
	private String citys[]={"qingdao","nanjing","shanghai"};
	private String descs[]={
			"Qingdao is a beautiful city.",
			"Nanjing is a city of culture.",
			"Shanghai is a bustling city."
	};
	private FSDirectory dir;
	
	/**
	 * 每次都生成索引文件
	 * @throws Exception
	 */
	@Before
	public void setUp() throws Exception {
		dir  = FSDirectory.open(Paths.get("E:\\temp\\test\\lucene\\demo2\\indexDir"));
		IndexWriter indexWriter = getIndexWriter();
		for (int i = 0; i < ids.length; i++) {
			Document doc = new Document();
			doc.add(new IntField("id", ids[i], Field.Store.YES));
			doc.add(new StringField("city", citys[i], Field.Store.YES));
			doc.add(new TextField("desc", descs[i], Field.Store.NO));
			indexWriter.addDocument(doc);
		}
		indexWriter.close();
	}
	
	/**
	 * 获取索引输出流
	 * @return
	 * @throws Exception
	 */
	private IndexWriter getIndexWriter()  throws Exception{
		Analyzer analyzer = new StandardAnalyzer();
		IndexWriterConfig conf = new IndexWriterConfig(analyzer);
		return new IndexWriter(dir, conf );
	}
	
	/**
	 * 指定数字范围查询
	 * @throws Exception
	 */
	@Test
	public void testNumericRangeQuery()throws Exception{
		IndexReader reader = DirectoryReader.open(dir);
		IndexSearcher is = new IndexSearcher(reader);
		
		NumericRangeQuery<Integer> query=NumericRangeQuery.newIntRange("id", 1, 2, true, true);
		TopDocs hits=is.search(query, 10);
		for(ScoreDoc scoreDoc:hits.scoreDocs){
			Document doc=is.doc(scoreDoc.doc);
			System.out.println(doc.get("id"));
			System.out.println(doc.get("city"));
			System.out.println(doc.get("desc"));
		}		
	}
	
	/**
	 * 指定字符串开头字母查询(prefixQuery)
	 * @throws Exception
	 */
	@Test
	public void testPrefixQuery()throws Exception{
		IndexReader reader = DirectoryReader.open(dir);
		IndexSearcher is = new IndexSearcher(reader);
		
		PrefixQuery query=new PrefixQuery(new Term("city","n"));
		TopDocs hits=is.search(query, 10);
		for(ScoreDoc scoreDoc:hits.scoreDocs){
			Document doc=is.doc(scoreDoc.doc);
			System.out.println(doc.get("id"));
			System.out.println(doc.get("city"));
			System.out.println(doc.get("desc"));
		}	
	}
	
	@Test
	public void testBooleanQuery()throws Exception{
		IndexReader reader = DirectoryReader.open(dir);
		IndexSearcher is = new IndexSearcher(reader);
		
		NumericRangeQuery<Integer> query1=NumericRangeQuery.newIntRange("id", 1, 2, true, true);
		PrefixQuery query2=new PrefixQuery(new Term("city","s"));
		BooleanQuery.Builder booleanQuery=new BooleanQuery.Builder();
		booleanQuery.add(query1,BooleanClause.Occur.MUST);
		booleanQuery.add(query2,BooleanClause.Occur.MUST);
		TopDocs hits=is.search(booleanQuery.build(), 10);
		for(ScoreDoc scoreDoc:hits.scoreDocs){
			Document doc=is.doc(scoreDoc.doc);
			System.out.println(doc.get("id"));
			System.out.println(doc.get("city"));
			System.out.println(doc.get("desc"));
		}	
	}
}