Lucene使用项向量进行模糊查询

TermVector是Lucene 1.4新增的 它提供一种向量机制来进行模糊查询,TermVector保存Token.getPositionIncrement() 和Token.startOffset() 以及Token.endOffset() 信息.

 

Field.TermVector.NO:不保存term vectors
Field.TermVector.YES:保存term vectors
Field.TermVector.WITH_POSITIONS:保存term vectors.(保存值和token位置信息)
Field.TermVector.WITH_OFFSETS:保存term vectors.(保存值和Token的offset)
Field.TermVector.WITH_POSITIONS_OFFSETS:保存term vectors.(保存值和token位置信息和Token的offset)

 

下面是个简单的例子:

                Analyzer analyzer = new StandardAnalyzer();
	
	RAMDirectory directory = new RAMDirectory();
	
	/** 
	 * 创建索引
	 * 
	 * @throws IOException
	 */
	public void index() throws IOException{
		
		IndexWriter indexWriter = new IndexWriter(directory,analyzer,true);
		
		Document doc1 = new Document();
		
		doc1.add(new Field("title","java",Store.YES,Index.TOKENIZED));
		
		doc1.add(new Field("author","callan",Store.YES,Index.TOKENIZED));
		
		doc1.add(new Field("subject", "java一门编程语言",
				Store.YES, Index.TOKENIZED,TermVector.WITH_POSITIONS_OFFSETS));
		
		indexWriter.addDocument(doc1);
		
		Document doc2 = new Document();
		
		doc2.add(new Field("title","english",Store.YES,Index.TOKENIZED));
		
		doc2.add(new Field("author","wcq",Store.YES,Index.TOKENIZED));
		
		doc2.add(new Field("subject", "英语用的人很多",
				Store.YES, Index.TOKENIZED,TermVector.WITH_POSITIONS_OFFSETS));
		
		indexWriter.addDocument(doc2);
		
		Document doc3 = new Document();
				
		doc3.add(new Field("title","asp",Store.YES,Index.TOKENIZED));
				
		doc3.add(new Field("author","ca",Store.YES,Index.TOKENIZED));
				
		doc3.add(new Field("subject", "asp很多人用",
				Store.YES, Index.TOKENIZED,TermVector.WITH_POSITIONS_OFFSETS));
		
		indexWriter.addDocument(doc3);
		
		indexWriter.optimize();
		
		indexWriter.close();
	}
	
	// 进行搜索
	public void searcher() throws IOException{
		
		IndexSearcher searcher = new IndexSearcher(directory);
		
		// 搜索书名为java的索引
		TermQuery query = new TermQuery(new Term("title","java"));
		
		Hits hits = searcher.search(query);
		
		// 能找到一条记录
		for(int i = 0; i < hits.length(); i++){
			
			Document doc = hits.doc(i);
			
			System.out.println("书名:" + doc.get("title") + "  " + "作者:" + doc.get("author") + "简介:" + doc.get("subject"));
			
			System.out.println("相关的书:");
			
			docsLike(hits.id(i));
			
		}
		
	}
	
	// 在subject中模糊搜索与doc相进的索引
	public void docsLike(int id) throws IOException {
		
		IndexReader reader = IndexReader.open(directory);
		
		TermFreqVector  vector = reader.getTermFreqVector(id, "subject");
	
		BooleanQuery query = new BooleanQuery();
		
		for (int j = 0; j < vector.size(); j++) {
			
			TermQuery tq = new TermQuery(new Term("subject",
					vector.getTerms()[j]));
			
			 query.add(tq, BooleanClause.Occur.SHOULD);
		}
		
		IndexSearcher searcher = new IndexSearcher(directory);
		
		Hits hits = searcher.search(query);
		
		printResult(hits);
		
	}
	
	// 显示结果
	public void printResult(Hits hits) throws IOException{
		
		for(int i = 0; i < hits.length(); i++){
			
			Document d = hits.doc(i);
			
			System.out.println("书名:" + d.get("title")+"  " + "作者:" + d.get("author") +"  " + "简介:" + d.get("subject"));
			
		}
	}
	

	public static void main(String[] args) throws IOException {
		
		TermFreqVectorTest3 test = new TermFreqVectorTest3();
		
		test.index();
		
		test.searcher();
	}

搜索结果:

书名:java  作者:callan简介:java一门编程语言
相关的书:
书名:java  作者:callan  简介:java一门编程语言
书名:english  作者:wcq  简介:英语用的人很多

搜索书名为java 的索引,并且搜索与java的简介相关的索引.
将书<<java>>的subject分词为java/一/门/编/程/语/言/

在subject中搜索包含java/一/门/编/程/语/言/的索引

<<english>>包含语