package cn.lucene.lesson1;

import java.io.BufferedReader;
import java.io.File;
import java.io.FileNotFoundException;
import java.io.FileReader;
import java.io.IOException;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field.Store;
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.IndexWriterConfig.OpenMode;
import org.apache.lucene.index.Term;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TermQuery;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.Version;

/**
 * Lucene 是一个基于 Java 的全文信息检索工具包，它不是一个完整的搜索应用程序，而是为你的应用程序提供索引和搜索功能。
 * 
 */
public class TxtFileIndex {
	/*索引目录*/
	private final static String INDEX_PATH = "d:/lucene/index";
	/*文件目录*/
	private final static String DATA_PATH = "d:/lucene/data";
	
	public static void main(String[] args) throws Exception{
		//创建索引
		//createTxtIndexs();
		//搜索索引
		searchTxtIndexs();
	}

	private static void searchTxtIndexs() throws IOException {
		File indexDir = new File(INDEX_PATH);
		//索引位置
		Directory directory = FSDirectory.open(indexDir);
		//索引读取
		IndexReader reader = DirectoryReader.open(directory);
		//索引搜索
		IndexSearcher searcher = new IndexSearcher(reader);
		//定义关键字
		Term term = new Term("contents", "he");
		//关键字搜索
		TermQuery query = new TermQuery(term);
		//
		TopDocs topDocs = searcher.search(query, 10);
		
		ScoreDoc[] scoreDocs = topDocs.scoreDocs;
		System.out.println("查询结果总数---" + topDocs.totalHits + ", 最大的评分--" + topDocs.getMaxScore());  
		for (int i = 0; i < scoreDocs.length; i++) {
			int doc = scoreDocs[i].doc;
			Document document = searcher.doc(doc);
			System.out.println("contents====" + document.get("contents"));  
			System.out.println("id--" + scoreDocs[i].doc + "---scors--" + scoreDocs[i].score+"---index--" + scoreDocs[i].shardIndex);  
		}
		reader.close();
	}
	
	/**
	 * 创建索引
	 * @throws IOException
	 * @throws FileNotFoundException
	 */
	private static void createTxtIndexs() throws IOException, FileNotFoundException {
		File indexDir = new File(INDEX_PATH);
		File dataDir = new File(DATA_PATH);
		//标准分析器
		Analyzer luceneAnalyzer = new StandardAnalyzer(Version.LUCENE_43);
		//获得文件目录
		File[] dataFiles = dataDir.listFiles();
		//索引的存储的位置
		Directory directory = FSDirectory.open(indexDir);
		//设置了存放索引的文件夹将以覆盖或者新建的方式建立
		IndexWriterConfig iwConfig = new IndexWriterConfig(Version.LUCENE_43, luceneAnalyzer);
		iwConfig.setOpenMode(OpenMode.CREATE_OR_APPEND);
		//创建索引， 作用是把一个个的 Document 对象加到索引中来
		IndexWriter indexWriter = new IndexWriter(directory, iwConfig);
		long startTime = System.currentTimeMillis();
		//遍历文件
		for(int i = 0; i < dataFiles.length; i++){ 
			if(dataFiles[i].isFile() && dataFiles[i].getName().endsWith(".txt")){
				 System.out.println("Indexing file " + dataFiles[i].getCanonicalPath()); 
				 //用来描述文档的
				 Document document = new Document();
				 BufferedReader reader = new BufferedReader(new FileReader(dataFiles[i]));
				 document.add(new StringField("id", dataFiles[i].getCanonicalPath(), Store.YES));
				 //document.add(new TextField("contents", reader));//此构造方法不进行存储,需要将reader内容读取出来
				 String line = reader.readLine();
				 StringBuffer sbf = new StringBuffer();
				 while(line != null){
					 sbf.append(line);
					 line = reader.readLine();
				 }
				 document.add(new TextField("contents", sbf.toString(), Store.YES));
				 reader.close();
				 indexWriter.addDocument(document);
			}
		}
		System.out.println("indexs created!");  
		indexWriter.close();
		long endTime = System.currentTimeMillis();
		System.out.println("创建索引耗时: " + (endTime - startTime) + " milliseconds. " + dataDir.getPath());        
	}
}