lucene入门

最新推荐文章于 2024-03-11 21:30:51 发布

e就完事了

最新推荐文章于 2024-03-11 21:30:51 发布

阅读量241

点赞数

分类专栏：啦啦啦文章标签： lucene入门

本文链接：https://blog.csdn.net/qq_43588771/article/details/100579390

版权

啦啦啦专栏收录该内容

63 篇文章 0 订阅

订阅专栏

lucene入门

简介
导入pom依赖
生成索引
使用索引
构建索引
文档域加权
特定项搜索
指定数字范围查询
中文分词器和高亮效果
案例

简介

Lucene是当前非常流行的、免费的Java信息搜索(IR)库。Lucene是Apache下一个著名的开源搜索引擎内核，它基于Java技术，可以处理索引、拼写检查、点击爸爸好高亮和其他分词等技术。Lucene并不关心数据源、数据格式、甚至数据的语言，Lucene更不会关心搜索的界面会是怎样，因为这些工作都是由基于Lucene的程序来完成，因此Lucene使用于几乎所有以文本内容为主的数据检索功能。

导入pom依赖

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

在这里插入图片描述

生成索引

/**
 * 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 = "D:\\lucene\\demo1";
//		数据源地址
		String dataDir = "D:\\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.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
	 * @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
	 * @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;
	}
}

在这里插入图片描述
会自动在你设置的目录里生成索引文件

可以通过工具查看索引文件

使用索引

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

/**
 * 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();
	}
}

在这里插入图片描述

构建索引

/**
 * 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("D:\\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 {
//		https://blog.csdn.net/asdfsadfasdfsa/article/details/78820030
//		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();
	}
}

在这里插入图片描述

文档域加权

/**
 * 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("D:\\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，越大越排前
			}
			
			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"));
		}
	}
	
}

在这里插入图片描述

特定项搜索

/**
 * 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 = "D:\\lucene\\demo4";
		// 数据源地址
		String dataDir = "D:\\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 = "D:\\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 = "D:\\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();
		}
	}
	
}

testTermQuery：
在这里插入图片描述
testQueryParser：

指定数字范围查询

/**
 * 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("D:\\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.YES));
			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","n"));
		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"));
		}	
	}
}

testNumericRangeQuery：
在这里插入图片描述
testPrefixQuery：

testBooleanQuery：

中文分词器和高亮效果

public class Demo7 {
	private Integer ids[] = { 1, 2, 3 };
	private String citys[] = { "青岛", "南京", "上海" };
	// private String descs[]={
	// "青岛是个美丽的城市。",
	// "南京是个有文化的城市。",
	// "上海市个繁华的城市。"
	// };
	private String descs[] = { "青岛是个美丽的城市。",
			"南京是一个文化的城市南京，简称宁，是江苏省会，地处中国东部地区，长江下游，濒江近海。全市下辖11个区，总面积6597平方公里，2013年建成区面积752.83平方公里，常住人口818.78万，其中城镇人口659.1万人。[1-4] “江南佳丽地，金陵帝王州”，南京拥有着6000多年文明史、近2600年建城史和近500年的建都史，是中国四大古都之一，有“六朝古都”、“十朝都会”之称，是中华文明的重要发祥地，历史上曾数次庇佑华夏之正朔，长期是中国南方的政治、经济、文化中心，拥有厚重的文化底蕴和丰富的历史遗存。[5-7] 南京是国家重要的科教中心，自古以来就是一座崇文重教的城市，有“天下文枢”、“东南第一学”的美誉。截至2013年，南京有高等院校75所，其中211高校8所，仅次于北京上海；国家重点实验室25所、国家重点学科169个、两院院士83人，均居中国第三。[8-10]",
			"上海市个繁华的城市。" };

	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("D:\\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.YES));
			indexWriter.addDocument(doc);
		}
		indexWriter.close();
	}

	/**
	 * 获取索引输出流
	 * 
	 * @return
	 * @throws Exception
	 */
	private IndexWriter getIndexWriter() throws Exception {
//		Analyzer analyzer = new StandardAnalyzer();
		Analyzer analyzer = new SmartChineseAnalyzer();//中文分词器
		IndexWriterConfig conf = new IndexWriterConfig(analyzer);
		return new IndexWriter(dir, conf);
	}

	/**
	 * luke查看索引生成
	 * 
	 * @throws Exception
	 */
	@Test
	public void testIndexCreate() throws Exception {

	}

	/**
	 * 测试高亮
	 * 
	 * @throws Exception
	 */
	@Test
	public void testHeight() throws Exception {
		IndexReader reader = DirectoryReader.open(dir);
		IndexSearcher searcher = new IndexSearcher(reader);

		SmartChineseAnalyzer analyzer = new SmartChineseAnalyzer();
		QueryParser parser = new QueryParser("desc", analyzer);
		// Query query = parser.parse("南京文化");
		Query query = parser.parse("南京文明");
		TopDocs hits = searcher.search(query, 100);

		// 查询得分项
		QueryScorer queryScorer = new QueryScorer(query);
		// 得分项对应的内容片段
		SimpleSpanFragmenter fragmenter = new SimpleSpanFragmenter(queryScorer);
		// 高亮显示的样式
		SimpleHTMLFormatter htmlFormatter = new SimpleHTMLFormatter("<span color='red'><b>", "</b></span>");
		// 高亮显示对象
		Highlighter highlighter = new Highlighter(htmlFormatter, queryScorer);
		// 设置需要高亮显示对应的内容片段
		highlighter.setTextFragmenter(fragmenter);

		for (ScoreDoc scoreDoc : hits.scoreDocs) {
			Document doc = searcher.doc(scoreDoc.doc);
			String desc = doc.get("desc");
			if (desc != null) {
				// tokenstream是从doucment的域（field)中抽取的一个个分词而组成的一个数据流，用于分词。
				TokenStream tokenStream = analyzer.tokenStream("desc", new StringReader(desc));
				System.out.println("高亮显示的片段：" + highlighter.getBestFragment(tokenStream, desc));
			}
			System.out.println("所有内容：" + desc);
		}

	}

}

testHeight:
在这里插入图片描述

案例

BlogAction

/**
 * IndexReader
 * IndexSearcher
 * Highlighter
 * @author Administrator
 *
 */
public class BlogAction {
	private String title;
	private BlogDao blogDao = new BlogDao();

	public String getTitle() {
		return title;
	}

	public void setTitle(String title) {
		this.title = title;
	}

	public String list() {
		try {
			HttpServletRequest request = ServletActionContext.getRequest();
			if (StringUtils.isBlank(title)) {
				List<Map<String, Object>> blogList = this.blogDao.list(title, null);
				request.setAttribute("blogList", blogList);
			}else {
				Directory directory = LuceneUtil.getDirectory(PropertiesUtil.getValue("indexPath"));
				DirectoryReader reader = LuceneUtil.getDirectoryReader(directory);
				IndexSearcher searcher = LuceneUtil.getIndexSearcher(reader);
				SmartChineseAnalyzer analyzer = new SmartChineseAnalyzer();
//				拿一句话到索引目中的索引文件中的词库进行关键词碰撞
				Query query = new QueryParser("title", analyzer).parse(title);
				Highlighter highlighter = LuceneUtil.getHighlighter(query, "title");
				
				TopDocs topDocs = searcher.search(query , 100);
				//处理得分命中的文档
				List<Map<String, Object>> blogList = new ArrayList<>();
				Map<String, Object> map = null;
				ScoreDoc[] scoreDocs = topDocs.scoreDocs;
				for (ScoreDoc scoreDoc : scoreDocs) {
					map = new HashMap<>();
					Document doc = searcher.doc(scoreDoc.doc);
					map.put("id", doc.get("id"));
					String titleHighlighter = doc.get("title");
					if(StringUtils.isNotBlank(titleHighlighter)) {
						titleHighlighter = highlighter.getBestFragment(analyzer, "title", titleHighlighter);
					}
					map.put("title", titleHighlighter);
					map.put("url", doc.get("url"));
					blogList.add(map);
				}
				
				request.setAttribute("blogList", blogList);
			}
		} catch (Exception e) {
			e.printStackTrace();
		}
		return "blogList";
	}
}

BlogDao

public class BlogDao extends JsonBaseDao{
	public List<Map<String,Object>> list(String title, PageBean pageBean) throws InstantiationException, IllegalAccessException, SQLException{
		String sql = "select * from t_lucene_crawler_blog where 1=1";
		if(StringUtils.isNotBlank(title)) {
			sql += " and title like '%"+title+"%'";
		}
		return super.executeQuery(sql, pageBean);
	}
	
	public int save(Map<String,String[]> paMap) throws InstantiationException, IllegalAccessException, SQLException, NoSuchFieldException, SecurityException, IllegalArgumentException{
		String sql = "insert into t_lucene_crawler_blog values(?,?,?,?,0)";
		return super.executeUpdate(sql, new String[] {"id","title","content","url"}, paMap);
	}
	
}

BlogActionBak

/**
 * IndexReader
 * IndexSearcher
 * Highlighter
 * @author Administrator
 *
 */
public class BlogActionBak {
	private String title;
	private BlogDao blogDao = new BlogDao();

	public String getTitle() {
		return title;
	}

	public void setTitle(String title) {
		this.title = title;
	}

	public String execute() {
		try {
			HttpServletRequest request = ServletActionContext.getRequest();
			if (StringUtils.isBlank(title)) {
				List<Map<String, Object>> blogList = this.blogDao.list(title, null);
				request.setAttribute("blogList", blogList);
			}else {
				SmartChineseAnalyzer analyzer = new SmartChineseAnalyzer();
				IndexReader indexReader = DirectoryReader.open(FSDirectory.open(Paths.get(PropertiesUtil.getValue("indexPath"))));
				IndexSearcher searcher = new IndexSearcher(indexReader);
//				拿一句话到索引目中的索引文件中的词库进行关键词碰撞
				Query query = new QueryParser("title", analyzer).parse(title);
				TopDocs topDocs = searcher.search(query , 100);
				
//				将碰撞出来的关键词给点亮
				QueryScorer queryScorer = new QueryScorer(query);
//				以什么形式点亮关键词
				Formatter formatter = new SimpleHTMLFormatter("<span style='color:red;'><b>", "</span></b>");
				Highlighter highlighter = new Highlighter(formatter , queryScorer);
				
				List<Map<String, Object>> blogList = new ArrayList<>();
				Map<String, Object> map = null;
				ScoreDoc[] scoreDocs = topDocs.scoreDocs;
				for (ScoreDoc scoreDoc : scoreDocs) {
					map = new HashMap<>();
					Document doc = searcher.doc(scoreDoc.doc);
					map.put("id", doc.get("id"));
					String titleHighlighter = doc.get("title");
					if(StringUtils.isNotBlank(titleHighlighter)) {
						titleHighlighter = highlighter.getBestFragment(analyzer, "title", titleHighlighter);
					}
					map.put("title", titleHighlighter);
					map.put("url", doc.get("url"));
					blogList.add(map);
				}
				request.setAttribute("blogList", blogList);
			}
		} catch (Exception e) {
			e.printStackTrace();
		}
		return "blogList";
	}
}

<%@ page language="java" contentType="text/html; charset=UTF-8"
    pageEncoding="UTF-8"%>
    <%@ taglib uri="http://java.sun.com/jsp/jstl/core" prefix="c" %>
<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8">
<title>Insert title here</title>
</head>
<body>
<form action="${pageContext.request.contextPath}/sy/blog_list.action"
		method="post">
		博客标题：<input type="text" name="title"> <input type="submit"
			value="确定">
	</form>
	<button id="add">添加</button>
	<button id="refresh">刷新全局索引</button>
	<table border="1" width="100%">
		<tr>
			<td>编号</td>
			<td>名称</td>
			<td>价格</td>
			<td>操作</td>
		</tr>
		<c:forEach items="${blogList }" var="blog">
			<tr>
				<td>${blog.id }</td>
				<td>${blog.title }</td>
				<td><a href="${blog.url }">${blog.title }</a></td>
				<td>
					<a href="">修改</a>
					<a href="">删除</a>
				</td>
			</tr>
		</c:forEach>
	</table>
</body>
</html>

在这里插入图片描述

e就完事了

关注

0
点赞
踩
2

收藏

觉得还不错? 一键收藏
0
评论
lucene入门

lucene入门简介导入pom依赖生成索引使用索引构建索引文档域加权特定项搜索指定数字范围查询中文分词器和高亮效果案例简介Lucene是当前非常流行的、免费的Java信息搜索(IR)库。Lucene是Apache下一个著名的开源搜索引擎内核，它基于Java技术，可以处理索引、拼写检查、点击爸爸好高亮和其他分词等技术。Lucene并不关心数据源、数据格式、甚至数据的语言，Lucene更不会关心搜...
复制链接

扫一扫