java鬼混筆記：lucene 5、index基本的增刪查改__lucene

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));// 更新一下目錄d.add(new TextField("content", readTxt(needIndex.listFiles()[0]), Store.YES));iw.updateDocument(new Term("id", "1"), d);// 更新ID等於1的索引iw.commit();iw.close();}// 刪除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) {// 刪除全部iw.deleteAll();}else {iw.deleteDocuments(new Term("id", "1"));// 根據索引ID=1來刪除}iw.commit();iw.close();}// 查詢// 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、關鍵字查詢 TermQuerypublic 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+"條記錄");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、首碼查詢 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+"條記錄");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、萬用字元查詢 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+"條記錄");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、模糊查詢 FuzzyQuery 用百分比符號，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+"條記錄");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、正則查詢 RegexpQuerypublic 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+"條記錄");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查詢 BooleanQuerypublic 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);// 這個查詢條件必須滿足bool.add(new FuzzyQuery(new Term("content",keyword)), Occur.MUST_NOT);// 這個查詢條件必須無bool.add(new WildcardQuery(new Term("content",keyword)), Occur.SHOULD);// 這個查詢條件可能有TopDocs top = searcher.search(bool, 12);System.out.println("得到"+top.totalHits+"條記錄");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、短語查詢 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);// 設定多個term之前的間隔pq.add(new Term("content","我們"));// 有序，符合才有記錄pq.add(new Term("content","你們"));TopDocs top = searcher.search(pq, 12);System.out.println("得到"+top.totalHits+"條記錄");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、多短語查詢 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","我們"));multiPhraseQuery.add(new Term("title","你們"));TopDocs top = searcher.search(multiPhraseQuery, 12);System.out.println("得到"+top.totalHits+"條記錄");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轉文字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 "";}}/** * 設定搜尋結果高亮 用【】包著 * @param query 查詢方法 * @param d 查出的文檔 * @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);// 高亮字串長度highlight.setTextFragmenter(fragmenter);TokenStream tokenStream = analyzer.tokenStream("content", new StringReader(d.get("content")));String highlightStr = highlight.getBestFragment(tokenStream, d.get("content"));System.out.println("【顯示搜尋結果位置】");System.out.println(highlightStr);}}