（2）认识Lucene：检索数据

参考官网：//http://lucene.apache.org/core/5_3_1/demo/overview-summary.html#overview_description

package example;

import java.nio.file.Files;
import java.nio.file.Path;
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.index.Term;
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.TermQuery;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.store.FSDirectory;

//http://lucene.apache.org/core/5_3_1/demo/overview-summary.html#overview_description
public class FileSearch {
	
	public static void main(String[] args) throws Exception
	{
		String indexPath="E:\\LuceneIndex";//This is the directory that hosts the Lucene index
		final Path indexDir = Paths.get(indexPath);
		if (!Files.isReadable(indexDir)) 
		{
			System.out.println("Lucene index directory '" +indexDir.toAbsolutePath()+ "' does not exist or is not readable");
			System.exit(1);
		}
		String queryField="contents";
		String queryStr="mao yang a the other Michael Jordan";
		
		FSDirectory directory=FSDirectory.open(Paths.get(indexPath));
		IndexReader reader = DirectoryReader.open(directory);
		/*
		IndexSearcher是用来在建立好的索引上进行搜索的。它只能以只读的方式打开一个索引，所以可以有多个 IndexSearcher的实例在一个索引上进行操作。
		*/
		IndexSearcher searcher=new IndexSearcher(reader);
		Analyzer analyzer = new StandardAnalyzer();
		/*
		The query parser is constructed with an analyzer used to interpret your query text in the same way the documents are interpreted: 
		finding word boundaries, downcasing, and removing useless words like 'a', 'an' and 'the'.
		It's also possible to programmatically construct a rich Query object without using the query parser. 
		The query parser just enables decoding the Lucene query syntax into the corresponding Query object.		
		*/
		QueryParser parser = new QueryParser(queryField, analyzer);
		/*
		Query是一个抽象类，他有多个实现，比如 TermQuery, BooleanQuery, PrefixQuery. 
		这个类的目的是把用户输入的查询字符串封装成 Lucene能够识别的 Query。
		The Query object contains the results from the QueryParser which is passed to the searcher
		*/
		Query query = parser.parse(queryStr);
		//Searching for: mao yang other ==>truely removes the stop words like 'a', 'an' and 'the'.
		System.out.println("Searching for: " + query.toString(queryField));
		//The IndexSearcher.search(query,n) method returns TopDocs with max n hits
		TopDocs results=searcher.search(query, 5);
		ScoreDoc[] hits=results.scoreDocs;
		for(int i=0;i<hits.length;i++)
		{
			Document doc=searcher.doc(hits[i].doc);
			System.out.println("File path: " + doc.get("path"));
			System.out.println("File lastModified: " + doc.get("modified"));//output is "null", because FileIndex.java use "Field.Store.NO"
		}
		
		
		System.out.println("\n\nanother case:");
		queryStr="morning";
		/*
		Term是搜索的基本单位，一个 Term对象有两个 String类型的域组成。
		生成一个 Term对象可以有如下一条语句来完成：Term term = new Term(“fieldName”,”queryWord”); 
		其中第一个参数代表了要在文档的哪一个 Field上进行查找，第二个参数代表了要查询的关键词。
		注意，如果不是用QueryParser，则不对”queryWord”进行任何解析，如果令queryStr="MAO Hang"，则查不出任何结果
		*/
		Term term = new Term("contents", queryStr.toLowerCase());
		/*
		TermQuery 是抽象类 Query 的一个子类，它同时也是 Lucene支持的最为基本的一个查询类。
		生成一个 TermQuery对象由如下语句完成： TermQuery termQuery = new TermQuery(new Term(“fieldName”,”queryWord”)); 
		它的构造函数只接受一个参数，那就是一个 Term对象。
		*/
        TermQuery termQuery = new TermQuery(term);
        results=searcher.search(termQuery, 2);
		hits=results.scoreDocs;
		for(int i=0;i<hits.length;i++)
		{
			Document doc=searcher.doc(hits[i].doc);
			System.out.println("File path: " + doc.get("path"));
			System.out.println("File lastModified: " + doc.get("modified"));//output is "null", because FileIndex.java use "Field.Store.NO"
		}
		
		reader.close();
	}
}

参考文献：

[1] Mendes, Pablo N, Jakob, Max, Garc&#, et al. DBpedia spotlight: Shedding light on the web of documents[C]// Proceedings of the 7th International Conference on Semantic Systems. ACM, 2011:1-8.

[2] Han X, Sun L. A Generative Entity-Mention Model for Linking Entities with Knowledge Base.[J]. Proceeding of Acl, 2011:945-954.

[3] http://lucene.apache.org/

[4] http://alias-i.com/lingpipe/demos/tutorial/ne/read-me.html

[5] http://wiki.dbpedia.org/Downloads2014

[6] http://www.oschina.net/p/jieba（结巴分词）