lucene入門

擼了今年阿里、頭條和美團的面試，我有一個重要發現.......>>>

#lucene 對於從來沒有接觸過lucene的開發人員可能對lucene比較的恐懼，第一點，lucene的發展是相當快的，API在不斷的更新當中，第二點，lucene並不是一個完整的全文檢索引擎，而是一個全文檢索引擎的架構，lucene的目的只是爲軟件開發人員提供一個簡單易用的工具包。但是呢，如果只是想使用lucene，而不是專門做搜索引擎，使用lucene開發是非常簡單的，這是官網給的一個例子（lucene6.1.0）：

創建索引：

//創建一個標準的分析器（這個分析器不支持中文）
Analyzer analyzer = new StandardAnalyzer();

// 在內存中創建一個目錄
Directory directory = new RAMDirectory();
// 在磁盤中創建一個目錄（最常用）
//Directory directory = FSDirectory.open("/tmp/testindex");
//創建一個索引Writer配置
IndexWriterConfig config = new IndexWriterConfig(analyzer);
//創建一個索引Writer
IndexWriter iwriter = new IndexWriter(directory, config);
//創建一個文件
Document doc = new Document();
String text = "This is the text to be indexed.";
//向文件中添加字段
doc.add(new Field("fieldname", text, TextField.TYPE_STORED));
//向Writer中添加文件
iwriter.addDocument(doc);
//關閉
iwriter.close();

查詢：

//創建一個標準的分析器（這個分析器不支持中文）
Analyzer analyzer = new StandardAnalyzer();
// 在內存中創建一個目錄
Directory directory = new RAMDirectory();
// 在磁盤中創建一個目錄（最常用）
//Directory directory = FSDirectory.open("/tmp/testindex");
//創建一個Reader
DirectoryReader ireader = DirectoryReader.open(directory);
//創建一個索引搜索
IndexSearcher isearcher = new IndexSearcher(ireader);
//c創建一個查詢表達式
QueryParser parser = new QueryParser("fieldname", analyzer);
//我們搜索的關鍵字爲“test”
Query query = parser.parse("text");
//進行查詢
ScoreDoc[] hits = isearcher.search(query, null, 1000).scoreDocs;
assertEquals(1, hits.length);
// 遍歷結果
for (int i = 0; i < hits.length; i++) {
  Document hitDoc = isearcher.doc(hits[i].doc);
  assertEquals("This is the text to be indexed.", hitDoc.get("fieldname"));
}
ireader.close();
directory.close();

從官網給的例子中可以發現，想要用lucene做搜索就兩步：

1. 爲數據加上索引
2. 查詢索引，得到結果

例子：

添加lucene支持

<dependency>
	<groupId>org.apache.lucene</groupId>
	<artifactId>lucene-core</artifactId>
	<version>5.3.1</version>
  </dependency>
  
  <dependency>
	<groupId>org.apache.lucene</groupId>
	<artifactId>lucene-analyzers-common</artifactId>
	<version>5.3.1</version>
 </dependency>
 
 <dependency>
	<groupId>org.apache.lucene</groupId>
	<artifactId>lucene-analyzers-smartcn</artifactId>
	<version>5.3.1</version>
</dependency>
 
 
 <dependency>
	<groupId>org.apache.lucene</groupId>
	<artifactId>lucene-queryparser</artifactId>
	<version>5.3.1</version>
 </dependency>
 
 <dependency>
	<groupId>org.apache.lucene</groupId>
	<artifactId>lucene-highlighter</artifactId>
	<version>5.3.1</version>
</dependency>

博客索引類

package com.lucene;

import java.io.StringReader;
import java.nio.file.Paths;
import java.util.LinkedList;
import java.util.List;

import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.cn.smart.SmartChineseAnalyzer;
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.queryparser.classic.QueryParser;
import org.apache.lucene.search.BooleanClause;
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.TopDocs;
import org.apache.lucene.search.highlight.Fragmenter;
import org.apache.lucene.search.highlight.Highlighter;
import org.apache.lucene.search.highlight.QueryScorer;
import org.apache.lucene.search.highlight.SimpleHTMLFormatter;
import org.apache.lucene.search.highlight.SimpleSpanFragmenter;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;


/**
 * 博客索引類
 * @author Administrator
 *
 */
public class BlogIndex {

	private Directory dir=null;
	

	/**
	 * 獲取IndexWriter實例
	 * @return
	 * @throws Exception
	 */
	private IndexWriter getWriter()throws Exception{
		dir=FSDirectory.open(Paths.get("C://lucene"));
		SmartChineseAnalyzer analyzer=new SmartChineseAnalyzer();
		IndexWriterConfig iwc=new IndexWriterConfig(analyzer);
		IndexWriter writer=new IndexWriter(dir, iwc);
		return writer;
	}
	
	/**
	 * 添加博客索引
	 * @param blog
	 */
	public void addIndex(Blog blog)throws Exception{
		IndexWriter writer=getWriter();
		Document doc=new Document();
		doc.add(new StringField("id",String.valueOf(blog.getId()),Field.Store.YES));
		doc.add(new TextField("title",blog.getTitle(),Field.Store.YES));
		doc.add(new StringField("releaseDate",DateUtil.formatDate(blog.getReleaseDate(), "yyyy-MM-dd"),Field.Store.YES));
		doc.add(new TextField("content",blog.getContentNoTag(),Field.Store.YES));
		writer.addDocument(doc);
		writer.close();
	}
	
	/**
	 * 更新博客索引
	 * @param blog
	 * @throws Exception
	 */
	public void updateIndex(Blog blog)throws Exception{
		IndexWriter writer=getWriter();
		Document doc=new Document();
		doc.add(new StringField("id",String.valueOf(blog.getId()),Field.Store.YES));
		doc.add(new TextField("title",blog.getTitle(),Field.Store.YES));
		doc.add(new StringField("releaseDate",DateUtil.formatDate(blog.getReleaseDate(), "yyyy-MM-dd"),Field.Store.YES));
		doc.add(new TextField("content",blog.getContentNoTag(),Field.Store.YES));
		writer.updateDocument(new Term("id", String.valueOf(blog.getId())), doc);
		writer.close();
	}
	
	/**
	 * 刪除指定博客的索引
	 * @param blogId
	 * @throws Exception
	 */
	public void deleteIndex(String blogId)throws Exception{
		IndexWriter writer=getWriter();
		writer.deleteDocuments(new Term("id",blogId));
		writer.forceMergeDeletes(); // 強制刪除
		writer.commit();
		writer.close();
	}
	
	/**
	 * 查詢博客信息
	 * @param q 查詢關鍵字
	 * @return
	 * @throws Exception
	 */
	public List<Blog> searchBlog(String q)throws Exception{
		dir=FSDirectory.open(Paths.get("C://lucene"));
		IndexReader reader = DirectoryReader.open(dir);
		IndexSearcher is=new IndexSearcher(reader);
		BooleanQuery.Builder booleanQuery = new BooleanQuery.Builder();
		SmartChineseAnalyzer analyzer=new SmartChineseAnalyzer();
		QueryParser parser=new QueryParser("title",analyzer);
		Query query=parser.parse(q);
		QueryParser parser2=new QueryParser("content",analyzer);
		Query query2=parser2.parse(q);
		booleanQuery.add(query,BooleanClause.Occur.SHOULD);
		booleanQuery.add(query2,BooleanClause.Occur.SHOULD);
		TopDocs hits=is.search(booleanQuery.build(), 100);
		QueryScorer scorer=new QueryScorer(query);  
		Fragmenter fragmenter = new SimpleSpanFragmenter(scorer);  
		SimpleHTMLFormatter simpleHTMLFormatter=new SimpleHTMLFormatter("<b><font color='red'>","</font></b>");
		Highlighter highlighter=new Highlighter(simpleHTMLFormatter, scorer);
		highlighter.setTextFragmenter(fragmenter);  
		List<Blog> blogList=new LinkedList<Blog>();
		for(ScoreDoc scoreDoc:hits.scoreDocs){
			Document doc=is.doc(scoreDoc.doc);
			Blog blog=new Blog();
			blog.setId(Integer.parseInt(doc.get(("id"))));
			blog.setReleaseDateStr(doc.get(("releaseDate")));
			String title=doc.get("title");
			String content=doc.get("content");
			if(title!=null){
				TokenStream tokenStream = analyzer.tokenStream("title", new StringReader(title));
				String hTitle=highlighter.getBestFragment(tokenStream, title);
				if(StringUtil.isEmpty(hTitle)){
					blog.setTitle(title);
				}else{
					blog.setTitle(hTitle);					
				}
			}
			if(content!=null){
				TokenStream tokenStream = analyzer.tokenStream("content", new StringReader(content)); 
				String hContent=highlighter.getBestFragment(tokenStream, content);
				if(StringUtil.isEmpty(hContent)){
					if(content.length()<=200){
						blog.setContent(content);
					}else{
						blog.setContent(content.substring(0, 200));						
					}
				}else{
					blog.setContent(hContent);					
				}
			}
			blogList.add(blog);
		}
		return blogList;
	}
}