java鬼混笔记：lucene 5、index基本的增删查改

package cn;

import java.io.BufferedReader;
import java.io.File;
import java.io.FileInputStream;
import java.io.InputStreamReader;
import java.io.StringReader;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field.Store;
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.BooleanClause.Occur;
import org.apache.lucene.search.BooleanQuery;
import org.apache.lucene.search.FuzzyQuery;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.MultiPhraseQuery;
import org.apache.lucene.search.PhraseQuery;
import org.apache.lucene.search.PrefixQuery;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.RegexpQuery;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TermQuery;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.search.WildcardQuery;
import org.apache.lucene.search.highlight.Formatter;
import org.apache.lucene.search.highlight.Fragmenter;
import org.apache.lucene.search.highlight.Highlighter;
import org.apache.lucene.search.highlight.InvalidTokenOffsetsException;
import org.apache.lucene.search.highlight.QueryScorer;
import org.apache.lucene.search.highlight.SimpleFragmenter;
import org.apache.lucene.search.highlight.SimpleHTMLFormatter;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.Version;
import org.wltea.analyzer.lucene.IKAnalyzer;

public class CURDIndex {

	public static void main(String[] args) throws Exception {
		
		//add();
		//update();
		delete(0);
		//showAll();
		//queryByPrefixQuery("寂寞");
		//queryByRegexpQuery("寂寞");
	}
	
	// 添加
	public static void add() throws Exception {

		Directory directory = FSDirectory.open(new File(System.getProperty("user.dir")+File.separator+"dir"));
		Analyzer analyzer = new IKAnalyzer();
		IndexWriterConfig config = new IndexWriterConfig(Version.LUCENE_40, analyzer);
		config.setOpenMode(OpenMode.CREATE_OR_APPEND);
		IndexWriter iw = new IndexWriter(directory, config);
		File needIndex = new File(System.getProperty("user.dir")+File.separator+"src"+File.separator+"txt");
		int id = 1;
		for(File f : needIndex.listFiles()) {
			Document d = new Document();
			d.add(new TextField("id", id+"", Store.YES));
			d.add(new TextField("title", f.getName(), Store.YES));
			d.add(new TextField("content", readTxt(f), Store.YES));
			iw.addDocument(d);
			iw.commit();
			id ++;
		}
		iw.close();
	}
	
	// 更新
	public static void update() throws Exception {

		Directory directory = FSDirectory.open(new File(System.getProperty("user.dir")+File.separator+"dir"));
		Analyzer analyzer = new IKAnalyzer();
		IndexWriterConfig config = new IndexWriterConfig(Version.LUCENE_40, analyzer);
		config.setOpenMode(OpenMode.CREATE_OR_APPEND);
		IndexWriter iw = new IndexWriter(directory, config);
		File needIndex = new File(System.getProperty("user.dir")+File.separator+"src"+File.separator+"txt");
		Document d = new Document();
		d.add(new TextField("id", "1", Store.YES));
		d.add(new TextField("title", "2_"+needIndex.listFiles()[0].getName(), Store.YES));// 更新一下目录
		d.add(new TextField("content", readTxt(needIndex.listFiles()[0]), Store.YES));
		iw.updateDocument(new Term("id", "1"), d);// 更新ID等于1的索引
		iw.commit();
		iw.close();
	}
	
	// 删除
	public static void delete(int type) throws Exception {

		Directory directory = FSDirectory.open(new File(System.getProperty("user.dir")+File.separator+"dir"));
		Analyzer analyzer = new IKAnalyzer();
		IndexWriterConfig config = new IndexWriterConfig(Version.LUCENE_40, analyzer);
		config.setOpenMode(OpenMode.CREATE_OR_APPEND);
		IndexWriter iw = new IndexWriter(directory, config);
		if(type == 0) {
			// 删除全部
			iw.deleteAll();
		}else {
			iw.deleteDocuments(new Term("id", "1"));// 根据索引ID=1来删除
		}
		iw.commit();
		iw.close();
	}

	// 查询
	// 1、列出全部
	public static void showAll() throws Exception {

		Directory directory = FSDirectory.open(new File(System.getProperty("user.dir")+File.separator+"dir"));
		IndexReader reader = DirectoryReader.open(directory);
		for(int i = 0; i < reader.numDocs(); i ++) {
			Document d = reader.document(i);
			System.out.println("i:"+i);
			System.out.println("id:"+d.get("id"));
			System.out.println("title:"+d.get("title"));
			System.out.println("content:"+d.get("content"));
			
		}
	}
	
	// 2、关键字查询 TermQuery
	public static void queryByKeyword(String keyword) throws Exception {

		Directory directory = FSDirectory.open(new File("G:\\eclipseworkspace\\lucence\\dir"));
		IndexReader read = DirectoryReader.open(directory);
		IndexSearcher searcher = new IndexSearcher(read);
		Query query = new TermQuery(new Term("content",keyword));
		TopDocs top = searcher.search(query, 12);
		System.out.println("得到"+top.totalHits+"条记录");
		ScoreDoc[] scoreDocs = top.scoreDocs;
		for (ScoreDoc scoreDoc :scoreDocs){
			Document doc = searcher.doc(scoreDoc.doc);
			System.out.println(doc.get("id"));
			System.out.println(doc.get("title"));
			System.out.println(doc.get("content"));
		}
		read.close();
	}
	
	// 3、前缀查询 PrefixQuery 比如：寂寞**
	public static void queryByPrefixQuery(String keyword) throws Exception {

		Directory directory = FSDirectory.open(new File("G:\\eclipseworkspace\\lucence\\dir"));
		IndexReader read = DirectoryReader.open(directory);
		IndexSearcher searcher = new IndexSearcher(read);
		Query query = new PrefixQuery(new Term("content",keyword));
		TopDocs top = searcher.search(query, 12);
		System.out.println("得到"+top.totalHits+"条记录");
		ScoreDoc[] scoreDocs = top.scoreDocs;
		for (ScoreDoc scoreDoc :scoreDocs){
			Document doc = searcher.doc(scoreDoc.doc);
			System.out.println(doc.get("id"));
			System.out.println(doc.get("title"));
			System.out.println(doc.get("content"));
			markKeyWord(query, doc);
		}
		read.close();
	}
	
	// 4、通配符查询 WildcardQuery 比如：*寂寞*
	public static void queryByWildcardQuery(String keyword) throws Exception {

		Directory directory = FSDirectory.open(new File("G:\\eclipseworkspace\\lucence\\dir"));
		IndexReader read = DirectoryReader.open(directory);
		IndexSearcher searcher = new IndexSearcher(read);
		Query query = new WildcardQuery(new Term("content",keyword));
		TopDocs top = searcher.search(query, 12);
		System.out.println("得到"+top.totalHits+"条记录");
		ScoreDoc[] scoreDocs = top.scoreDocs;
		for (ScoreDoc scoreDoc :scoreDocs){
			Document doc = searcher.doc(scoreDoc.doc);
			System.out.println(doc.get("id"));
			System.out.println(doc.get("title"));
			System.out.println(doc.get("content"));
			markKeyWord(query, doc);
		}
		read.close();
	}
	
	// 5、模糊查询 FuzzyQuery 用百分号，如：%渺
	public static void queryByFuzzyQuery(String keyword) throws Exception {

		Directory directory = FSDirectory.open(new File("G:\\eclipseworkspace\\lucence\\dir"));
		IndexReader read = DirectoryReader.open(directory);
		IndexSearcher searcher = new IndexSearcher(read);
		Query query = new FuzzyQuery(new Term("content",keyword));
		TopDocs top = searcher.search(query, 12);
		System.out.println("得到"+top.totalHits+"条记录");
		ScoreDoc[] scoreDocs = top.scoreDocs;
		for (ScoreDoc scoreDoc :scoreDocs){
			Document doc = searcher.doc(scoreDoc.doc);
			System.out.println(doc.get("id"));
			System.out.println(doc.get("title"));
			System.out.println(doc.get("content"));
			markKeyWord(query, doc);
		}
		read.close();
	}
	
	// 6、正则查询 RegexpQuery
	public static void queryByRegexpQuery(String keyword) throws Exception {

		Directory directory = FSDirectory.open(new File("G:\\eclipseworkspace\\lucence\\dir"));
		IndexReader read = DirectoryReader.open(directory);
		IndexSearcher searcher = new IndexSearcher(read);
		Query query = new RegexpQuery(new Term("content",keyword));
		TopDocs top = searcher.search(query, 12);
		System.out.println("得到"+top.totalHits+"条记录");
		ScoreDoc[] scoreDocs = top.scoreDocs;
		for (ScoreDoc scoreDoc :scoreDocs){
			Document doc = searcher.doc(scoreDoc.doc);
			System.out.println(doc.get("id"));
			System.out.println(doc.get("title"));
			System.out.println(doc.get("content"));
			markKeyWord(query, doc);
		}
		read.close();
	}
	
	// 7、boolean查询 BooleanQuery
	public static void queryByBooleanQuery(String keyword) throws Exception {

		Directory directory = FSDirectory.open(new File("G:\\eclipseworkspace\\lucence\\dir"));
		IndexReader read = DirectoryReader.open(directory);
		IndexSearcher searcher = new IndexSearcher(read);
		BooleanQuery bool = new BooleanQuery();
		bool.add(new RegexpQuery(new Term("content",keyword)), Occur.MUST);// 这个查询条件必须满足
		bool.add(new FuzzyQuery(new Term("content",keyword)), Occur.MUST_NOT);// 这个查询条件必须无
		bool.add(new WildcardQuery(new Term("content",keyword)), Occur.SHOULD);// 这个查询条件可能有
		
		TopDocs top = searcher.search(bool, 12);
		System.out.println("得到"+top.totalHits+"条记录");
		ScoreDoc[] scoreDocs = top.scoreDocs;
		for (ScoreDoc scoreDoc :scoreDocs){
			Document doc = searcher.doc(scoreDoc.doc);
			System.out.println(doc.get("id"));
			System.out.println(doc.get("title"));
			System.out.println(doc.get("content"));
			markKeyWord(bool, doc);
		}
		read.close();
	}
	
	// 8、短语查询 
	public static void queryByPhraseQuery() throws Exception {

		Directory directory = FSDirectory.open(new File("G:\\eclipseworkspace\\lucence\\dir"));
		IndexReader read = DirectoryReader.open(directory);
		IndexSearcher searcher = new IndexSearcher(read);
		PhraseQuery pq = new PhraseQuery();
		//pq.setSlop(2);// 设置多个term之前的间隔
		pq.add(new Term("content","我们"));// 有序，符合才有记录
		pq.add(new Term("content","你们"));
		TopDocs top = searcher.search(pq, 12);
		System.out.println("得到"+top.totalHits+"条记录");
		ScoreDoc[] scoreDocs = top.scoreDocs;
		for (ScoreDoc scoreDoc :scoreDocs){
			Document doc = searcher.doc(scoreDoc.doc);
			System.out.println(doc.get("id"));
			System.out.println(doc.get("title"));
			System.out.println(doc.get("content"));
			markKeyWord(pq, doc);
		}
		read.close();
	}
	
	// 9、多短语查询 
	public static void queryByMultiPhraseQuery() throws Exception {

		Directory directory = FSDirectory.open(new File("G:\\eclipseworkspace\\lucence\\dir"));
		IndexReader read = DirectoryReader.open(directory);
		IndexSearcher searcher = new IndexSearcher(read);
		MultiPhraseQuery multiPhraseQuery = new MultiPhraseQuery();
		multiPhraseQuery.add(new Term("content","我们"));
		multiPhraseQuery.add(new Term("title","你们"));
		TopDocs top = searcher.search(multiPhraseQuery, 12);
		System.out.println("得到"+top.totalHits+"条记录");
		ScoreDoc[] scoreDocs = top.scoreDocs;
		for (ScoreDoc scoreDoc :scoreDocs){
			Document doc = searcher.doc(scoreDoc.doc);
			System.out.println(doc.get("id"));
			System.out.println(doc.get("title"));
			System.out.println(doc.get("content"));
			markKeyWord(multiPhraseQuery, doc);
		}
		read.close();
	}
	
	// txt转文字
	public static String readTxt(File file) {
		try {
			BufferedReader br = new BufferedReader(new InputStreamReader(new FileInputStream(file), "UTF-8"));
			String str = null;
			StringBuffer sbf = new StringBuffer();
			while((str = br.readLine()) != null){
				sbf.append(str);
			}
			br.close();
			return sbf.toString();
		} catch (Exception e) {
			e.printStackTrace();
			return "";
		}
	}
	
	/**
	 * 设置搜索结果高亮 用【】包着
	 * @param query 查询方法
	 * @param d 查出的文档
	 * @throws InvalidTokenOffsetsException 
	 * @throws Exception 
	 */
	public static void markKeyWord(Query query, Document d) throws Exception{
		
		Analyzer analyzer = new IKAnalyzer();
		QueryScorer scorer = new QueryScorer(query);  
	    Formatter formatter = new SimpleHTMLFormatter("   【", "】   ");  
		Highlighter highlight = new Highlighter(formatter,scorer);  
		Fragmenter fragmenter = new SimpleFragmenter(888);// 高亮字符串长度
		highlight.setTextFragmenter(fragmenter);
		TokenStream tokenStream = analyzer.tokenStream("content", new StringReader(d.get("content")));
		String highlightStr = highlight.getBestFragment(tokenStream, d.get("content"));
		System.out.println("【显示搜索结果位置】");
		System.out.println(highlightStr);
	}
}