lucene4.7学习总结

private String filePath = "F:/myEclipse10/workspace/luceneTest/src/resource.txt";// 源文件所在位置
	private String indexDir = "F:/myEclipse10/workspace/luceneTest/src/index";// 索引目录
	private static final Version VERSION = Version.LUCENE_47;// lucene版本

/**
	 * 创建索引
	 * 
	 * @throws IOException
	 */
	@Test
	public void createIndex() throws IOException {
		Directory director = FSDirectory.open(new File(indexDir));// 创建Directory关联源文件
		Analyzer analyzer = new StandardAnalyzer(VERSION);// 创建一个分词器
		IndexWriterConfig indexWriterConfig = new IndexWriterConfig(VERSION, analyzer);// 创建索引的配置信息
		IndexWriter indexWriter = new IndexWriter(director, indexWriterConfig);
		Document doc = new Document();// 创建文档
		String str = fileToString();// 读取txt中内容
		Field field1 = new StringField("title", "lucene测试", Store.YES);// 标题 StringField索引存储不分词
		Field field2 = new TextField("content", str, Store.NO);// 内容 TextField索引分词不存储
		Field field3 = new DoubleField("version", 1.2, Store.YES);// 版本 DoubleField类型
		Field field4 = new IntField("score", 90, Store.YES);// 评分 IntField类型
		doc.add(field1);// 添加field域到文档中
		doc.add(field2);
		doc.add(field3);
		doc.add(field4);
		indexWriter.addDocument(doc);// 添加文本到索引中
		indexWriter.close();// 关闭索引
	}

/**
	 * 查询搜索
	 * 
	 * @throws IOException
	 * @throws ParseException
	 */
	@Test
	public void query() throws IOException, ParseException {
		IndexReader reader = DirectoryReader.open(FSDirectory.open(new File(indexDir)));// 索引读取类
		IndexSearcher search = new IndexSearcher(reader);// 搜索入口工具类
		String queryStr = "life";// 搜索关键字
		QueryParser queryParser = new QueryParser(VERSION, "content", new StandardAnalyzer(VERSION));// 实例查询条件类
		Query query = queryParser.parse(queryStr);
		TopDocs topdocs = search.search(query, 100);// 查询前100条
		System.out.println("查询结果总数---" + topdocs.totalHits);
		ScoreDoc scores[] = topdocs.scoreDocs;// 得到所有结果集
		for (int i = 0; i < scores.length; i++) {
			int num = scores[i].doc;// 得到文档id
			Document document = search.doc(num);// 拿到指定的文档
			System.out.println("内容====" + document.get("content"));// 由于内容没有存储所以执行结果为null
			System.out.println("标题====" + document.get("title"));
			System.out.println("版本====" + document.get("version"));
			System.out.println("评分====" + document.get("score"));
			System.out.println("id--" + num + "---scors--" + scores[i].score + "---index--" + scores[i].shardIndex);
		}
	}

/**
	 * 读取文件的内容
	 * 
	 * @return
	 * @throws IOException
	 */
	public String fileToString() throws IOException {
		StringBuffer sb = new StringBuffer();
		InputStream inputStream = new FileInputStream(new File(filePath));
		InputStreamReader inputStreamReader = new InputStreamReader(inputStream);
		BufferedReader br = new BufferedReader(inputStreamReader);
		String line = null;
		while ((line = br.readLine()) != null) {
			sb.append(line);
		}
		br.close();
		inputStreamReader.close();
		inputStream.close();
		return sb.toString();
	}

public class AnalyzerTest {
	private static final Version VERSION = Version.LUCENE_47;// lucene版本

	@Test
	public void test() throws IOException {
		String txt = "我是中国人";
		Analyzer analyzer1 = new StandardAnalyzer(VERSION);// 标准分词器
		// Analyzer analyzer2 = new SimpleAnalyzer(VERSION);// 简单分词器
		// Analyzer analyzer3 = new CJKAnalyzer(VERSION);// 二元切分
		// Analyzer analyzer4 = new IKAnalyzer(false);// 语意分词
		TokenStream tokenstream = analyzer1.tokenStream("content", new StringReader(txt));// 生成一个分词流
		// TokenStream tokenstream = analyzer2.tokenStream("content", new StringReader(txt));
		// TokenStream tokenstream = analyzer3.tokenStream("content", new StringReader(txt));
		// TokenStream tokenstream = analyzer4.tokenStream("content", new StringReader(txt));
		CharTermAttribute termAttribute = tokenstream.addAttribute(CharTermAttribute.class);// 为token设置属性类
		tokenstream.reset();// 重新设置
		while (tokenstream.incrementToken()) {// 遍历得到token
			System.out.print(new String(termAttribute.buffer(), 0, termAttribute.length()) + "  ");
		}
	}
}

public class MultiseQueryTest {
	private String indexDir = "F:/myEclipse10/workspace/luceneTest/src/index";// 索引目录
	private static final Version VERSION = Version.LUCENE_47;// lucene版本

	/**
	 * 多条件查询 查询内容必须包含life内容和评分大于等于80分的结果
	 * 
	 * @throws IOException
	 * @throws ParseException
	 */
	@Test
	public void query() throws IOException, ParseException {
		IndexReader reader = DirectoryReader.open(FSDirectory.open(new File(indexDir)));// 索引读取类
		IndexSearcher search = new IndexSearcher(reader);// 搜索入口工具类
		String queryStr1 = "life";// 搜索关键字
		BooleanQuery booleanQuery = new BooleanQuery();
		// 条件一内容中必须要有life内容
		QueryParser queryParser = new QueryParser(VERSION, "content", new StandardAnalyzer(VERSION));// 实例查询条件类
		Query query1 = queryParser.parse(queryStr1);
		// 条件二评分大于等于80
		Query query2 = NumericRangeQuery.newIntRange("score", 80, null, true, false);
		booleanQuery.add(query1, BooleanClause.Occur.MUST);
		booleanQuery.add(query2, BooleanClause.Occur.MUST);
		TopDocs topdocs = search.search(booleanQuery, 100);// 查询前100条
		System.out.println("查询结果总数---" + topdocs.totalHits);
		ScoreDoc scores[] = topdocs.scoreDocs;// 得到所有结果集
		for (int i = 0; i < scores.length; i++) {
			int num = scores[i].doc;// 得到文档id
			Document document = search.doc(num);// 拿到指定的文档
			System.out.println("内容====" + document.get("content"));// 由于内容没有存储所以执行结果为null
			System.out.println("标题====" + document.get("title"));
			System.out.println("版本====" + document.get("version"));
			System.out.println("评分====" + document.get("score"));
			System.out.println("id--" + num + "---scors--" + scores[i].score + "---index--" + scores[i].shardIndex);
		}
	}
}

六、修改删除索引

/**
	 * 修改索引
	 * 
	 * @throws IOException
	 */
	@Test
	public void updateIndex() throws IOException {
		Directory director = FSDirectory.open(new File(indexDir));// 创建Directory关联源文件
		Analyzer analyzer = new StandardAnalyzer(VERSION);// 创建一个分词器
		IndexWriterConfig indexWriterConfig = new IndexWriterConfig(VERSION, analyzer);// 创建索引的配置信息
		IndexWriter indexWriter = new IndexWriter(director, indexWriterConfig);
		Document doc = new Document();// 创建文档
		Field field1 = new StringField("title", "lucene", Store.YES);// 标题 StringField索引存储不分词
		Field field2 = new TextField("content", "Is there life on Mars", Store.NO);// 内容 TextField索引分词不存储
		Field field3 = new DoubleField("version", 2.0, Store.YES);// 版本 DoubleField类型
		Field field4 = new IntField("score", 90, Store.YES);// 评分 IntField类型
		doc.add(field1);// 添加field域到文档中
		doc.add(field2);
		doc.add(field3);
		doc.add(field4);
		indexWriter.updateDocument(new Term("title", "lucene测试"), doc);
		indexWriter.commit();
		indexWriter.close();
	}

运行结果：前后对比
注意：（1）所谓的更新索引是分两步进行的：先删除然后再添加索引，添加的索引占用删除前索引的位置；如果在删除索引时lucene在索引文件中找不到相应的数据，就会在索引文件的最后面添加新的索引。

/**
	 * 删除索引
	 * 
	 * @throws IOException
	 */
	@Test
	public void deleteIndex() throws IOException {
		Directory director = FSDirectory.open(new File(indexDir));// 创建Directory关联源文件
		Analyzer analyzer = new StandardAnalyzer(VERSION);// 创建一个分词器
		IndexWriterConfig indexWriterConfig = new IndexWriterConfig(VERSION, analyzer);// 创建索引的配置信息
		IndexWriter indexWriter = new IndexWriter(director, indexWriterConfig);
		indexWriter.deleteDocuments(new Term("title", "lucene"));
		indexWriter.commit();
		// indexWriter.rollback();
		indexWriter.close();
	}

七、lucene优化、排序

	/**
	 * 优化
	 * 
	 * @throws IOException
	 */
	@Test
	public void optimize() throws IOException {
		Directory director = FSDirectory.open(new File(indexDir));// 创建Directory关联源文件
		Analyzer analyzer = new StandardAnalyzer(VERSION);// 创建一个分词器
		IndexWriterConfig indexWriterConfig = new IndexWriterConfig(VERSION, analyzer);// 创建索引的配置信息
		IndexWriter indexWriter = new IndexWriter(director, indexWriterConfig);
		indexWriter.forceMerge(1);// 当小文件达到多少个时，就自动合并多个小文件为一个大文件
		indexWriter.close();
	}

/**
	 * 创建索引
	 * 
	 * @throws IOException
	 */
	@Test
	public void createIndex() throws IOException {
		Directory director = FSDirectory.open(new File(indexDir));// 创建Directory关联源文件
		Analyzer analyzer = new StandardAnalyzer(VERSION);// 创建一个分词器
		IndexWriterConfig indexWriterConfig = new IndexWriterConfig(VERSION, analyzer);// 创建索引的配置信息
		IndexWriter indexWriter = new IndexWriter(director, indexWriterConfig);
		for (int i = 1; i <= 5; i++) {
			Document doc = new Document();// 创建文档
			Field field1 = new StringField("title", "标题" + i, Store.YES);// 标题 StringField索引存储不分词
			Field field2 = new TextField("content", "201" + i + "文章内容", Store.NO);// 内容 TextField索引分词不存储
			Field field3 = new DoubleField("version", 1.2, Store.YES);// 版本 DoubleField类型
			Field field4 = new IntField("score", 90 + i, Store.YES);// 评分 IntField类型
			Field field5 = new StringField("date", "2014-07-0" + i, Store.YES);// 评分 IntField类型
			doc.add(field1);// 添加field域到文档中
			doc.add(field2);
			doc.add(field3);
			doc.add(field4);
			doc.add(field5);
			indexWriter.addDocument(doc);// 添加文本到索引中
		}
		indexWriter.close();// 关闭索引
	}

/**
	 * 排序
	 * 
	 * @throws IOException
	 * @throws ParseException
	 */
	@Test
	public void defaultSortTest() throws IOException, ParseException {
		IndexReader reader = DirectoryReader.open(FSDirectory.open(new File(indexDir)));// 索引读取类
		IndexSearcher search = new IndexSearcher(reader);// 搜索入口工具类
		String queryStr = "文章";// 搜索关键字
		QueryParser queryParser = new QueryParser(VERSION, "content", new StandardAnalyzer(VERSION));// 实例查询条件类
		Query query = queryParser.parse(queryStr);
		TopDocs topdocs = search.search(query, 100);// 查询前100条
		System.out.println("查询结果总数---" + topdocs.totalHits);
		ScoreDoc scores[] = topdocs.scoreDocs;// 得到所有结果集
		for (int i = 0; i < scores.length; i++) {
			int num = scores[i].doc;// 得到文档id
			Document document = search.doc(num);// 拿到指定的文档
			System.out.println("内容====" + document.get("content"));// 由于内容没有存储所以执行结果为null
			System.out.println("标题====" + document.get("title"));
			System.out.println("版本====" + document.get("version"));
			System.out.println("评分====" + document.get("score"));
			System.out.println("日期====" + document.get("date"));
			System.out.println("id--" + num + "---scors--" + scores[i].score + "---index--" + scores[i].shardIndex);
		}
	}
}

Sort sort = new Sort(new SortField("score", SortField.Type.INT, true));// false升序true降序
		TopDocs topdocs = search.search(query, 100, sort);// 查询前100条

八、lucene高亮显示

/**
	 * 高亮
	 * 
	 * @throws IOException
	 * @throws ParseException
	 * @throws InvalidTokenOffsetsException
	 */
	@Test
	public void highlighter() throws IOException, ParseException, InvalidTokenOffsetsException {
		IndexReader reader = DirectoryReader.open(FSDirectory.open(new File(indexDir)));// 索引读取类
		IndexSearcher search = new IndexSearcher(reader);// 搜索入口工具类
		Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_47);// 分词器
		QueryParser qp = new QueryParser(Version.LUCENE_47, "content", analyzer);// 实例查询条件类
		Query query = qp.parse("文章");
		TopDocs topDocs = search.search(query, 100);// 查询前100条
		System.out.println("共查询出:" + topDocs.totalHits + "条数据");
		ScoreDoc scoreDoc[] = topDocs.scoreDocs;// 结果集
		// 高亮
		Formatter formatter = new SimpleHTMLFormatter("<font color='red'>", "</font>");// 高亮html格式
		Scorer score = new QueryScorer(query);// 检索评份
		Fragmenter fragmenter = new SimpleFragmenter(100);// 设置最大片断为100
		Highlighter highlighter = new Highlighter(formatter, score);// 高亮显示类
		highlighter.setTextFragmenter(fragmenter);// 设置格式
		for (int i = 0; i < scoreDoc.length; i++) {// 遍历结果集
			int docnum = scoreDoc[i].doc;
			Document doc = search.doc(docnum);
			String content = doc.get("content");
			System.out.println(content);// 原内容
			if (content != null) {
				TokenStream tokenStream = analyzer.tokenStream("content", new StringReader(content));
				String str = highlighter.getBestFragment(tokenStream, content);// 得到高亮显示后的内容
				System.out.println(str);
			}
		}
	}

选择结果：

九、lucene分页

/**
	 * 分页
	 * 
	 * @throws IOException
	 * @throws ParseException
	 */
	@Test
	public void pageTest() throws IOException, ParseException {
		IndexReader reader = DirectoryReader.open(FSDirectory.open(new File(indexDir)));// 索引读取类
		IndexSearcher search = new IndexSearcher(reader);// 搜索入口工具类
		String queryStr = "文章";// 搜索关键字
		QueryParser queryParser = new QueryParser(VERSION, "content", new StandardAnalyzer(VERSION));// 实例查询条件类
		Query query = queryParser.parse(queryStr);// 查询
		TopScoreDocCollector results = TopScoreDocCollector.create(100, false);// 结果集
		search.search(query, results);// 查询前100条
		TopDocs topdocs = results.topDocs(1, 2);// 从结果集中第1条开始取2条
		ScoreDoc scores[] = topdocs.scoreDocs;// 得到所有结果集
		for (int i = 0; i < scores.length; i++) {
			int num = scores[i].doc;// 得到文档id
			Document document = search.doc(num);// 拿到指定的文档
			System.out.println("内容====" + document.get("content"));// 由于内容没有存储所以执行结果为null
			System.out.println("标题====" + document.get("title"));
			System.out.println("版本====" + document.get("version"));
			System.out.println("评分====" + document.get("score"));
			System.out.println("id--" + num + "---scors--" + scores[i].score + "---index--" + scores[i].shardIndex);
		}
	}

十、lucene注意几点