List of usage examples for org.apache.lucene.search IndexSearcher doc
public Document doc(int docID) throws IOException
.getIndexReader().document(docID) From source file:com.liang.minisearch.domain.search.Engine.java
public List<QueryDocument> search(String queryString) throws ParseException, IOException { List<QueryDocument> results = new ArrayList<>(); IndexSearcher searcher = new IndexSearcher(this.getReader()); // Parse user input query Query query = new QueryParser(FIELD_CONTENT, new StandardAnalyzer()).parse(queryString); // Get top n matching documents TopDocs topDocs = searcher.search(query, NUM_TOP_RESULT); ScoreDoc[] hits = topDocs.scoreDocs; for (ScoreDoc hit : hits) { Document doc = searcher.doc(hit.doc); QueryDocument result = new QueryDocument(); result.setUrl(doc.get(FIELD_URL)); result.setScore(hit.score);//from ww w . ja v a2s .co m results.add(result); } return results; }
From source file:com.lin.studytest.lucene.SearchFiles.java
License:Apache License
/** * This demonstrates a typical paging search scenario, where the search engine presents * pages of size n to the user. The user can then go to the next page if interested in * the next hits./*ww w . ja v a2 s. c o m*/ * * When the query is executed for the first time, then only enough results are collected * to fill 5 result pages. If the user wants to page beyond this limit, then the query * is executed another time and all hits are collected. * */ public static void doPagingSearch(BufferedReader in, IndexSearcher searcher, Query query, int hitsPerPage, boolean raw, boolean interactive) throws IOException { // Collect enough docs to show 5 pages TopDocs results = searcher.search(query, 5 * hitsPerPage); ScoreDoc[] hits = results.scoreDocs; int numTotalHits = results.totalHits; System.out.println(numTotalHits + " total matching documents"); int start = 0; int end = Math.min(numTotalHits, hitsPerPage); while (true) { if (end > hits.length) { System.out.println("Only results 1 - " + hits.length + " of " + numTotalHits + " total matching documents collected."); System.out.println("Collect more (y/n) ?"); String line = in.readLine(); if (line.length() == 0 || line.charAt(0) == 'n') { break; } hits = searcher.search(query, numTotalHits).scoreDocs; } end = Math.min(hits.length, start + hitsPerPage); for (int i = start; i < end; i++) { if (raw) { // output raw format System.out.println("doc=" + hits[i].doc + " score=" + hits[i].score); continue; } Document doc = searcher.doc(hits[i].doc); String path = doc.get("path"); if (path != null) { System.out.println((i + 1) + ". " + path); String title = doc.get("title"); if (title != null) { System.out.println(" Title: " + doc.get("title")); } } else { System.out.println((i + 1) + ". " + "No path for this document"); } } if (!interactive || end == 0) { break; } if (numTotalHits >= end) { boolean quit = false; while (true) { System.out.print("Press "); if (start - hitsPerPage >= 0) { System.out.print("(p)revious page, "); } if (start + hitsPerPage < numTotalHits) { System.out.print("(n)ext page, "); } System.out.println("(q)uit or enter number to jump to a page."); String line = in.readLine(); if (line.length() == 0 || line.charAt(0) == 'q') { quit = true; break; } if (line.charAt(0) == 'p') { start = Math.max(0, start - hitsPerPage); break; } else if (line.charAt(0) == 'n') { if (start + hitsPerPage < numTotalHits) { start += hitsPerPage; } break; } else { int page = Integer.parseInt(line); if ((page - 1) * hitsPerPage < numTotalHits) { start = (page - 1) * hitsPerPage; break; } else { System.out.println("No such page"); } } } if (quit) break; end = Math.min(numTotalHits, start + hitsPerPage); } } }
From source file:com.lithium.flow.filer.lucene.LuceneFiler.java
License:Apache License
@Nullable private List<Record> search(@Nonnull Term term) throws IOException { long time = System.currentTimeMillis(); manager.maybeRefresh();//from w w w.j a v a 2 s .c om IndexSearcher searcher = manager.acquire(); try { TopDocs topDocs = searcher.search(new TermQuery(term), Integer.MAX_VALUE); if (topDocs.totalHits > 0) { List<Record> records = Lists.newArrayList(); for (ScoreDoc scoreDoc : topDocs.scoreDocs) { Document doc = searcher.doc(scoreDoc.doc); RecordDoc recordDoc = RecordDoc.create(doc); records.add(recordDoc.getRecord()); if (maxAge > -1 && time > recordDoc.getIndexTime() + maxAge) { return null; } } return records; } } finally { manager.release(searcher); } return null; }
From source file:com.lorelib.analyzer.sample.LuceneIndexAndSearchDemo.java
License:Apache License
/** * //from www . j a v a 2s . c o m * ??? * @param args */ public static void main(String[] args) { //Lucene Document?? String fieldName = "text"; // String text = "IK Analyzer???????"; //IKAnalyzer? Analyzer analyzer = new IKAnalyzer(true); Directory directory = null; IndexWriter iwriter = null; IndexReader ireader = null; IndexSearcher isearcher = null; try { // directory = new RAMDirectory(); //?IndexWriterConfig IndexWriterConfig iwConfig = new IndexWriterConfig(analyzer); iwConfig.setOpenMode(OpenMode.CREATE_OR_APPEND); iwriter = new IndexWriter(directory, iwConfig); // Document doc = new Document(); doc.add(new StringField("ID", "10000", Field.Store.YES)); doc.add(new TextField(fieldName, text, Field.Store.YES)); iwriter.addDocument(doc); iwriter.close(); //?********************************** //? ireader = DirectoryReader.open(directory); isearcher = new IndexSearcher(ireader); String keyword = "?"; //QueryParser?Query QueryParser qp = new QueryParser(fieldName, analyzer); qp.setDefaultOperator(QueryParser.AND_OPERATOR); Query query = qp.parse(keyword); System.out.println("Query = " + query); //?5? TopDocs topDocs = isearcher.search(query, 5); System.out.println("" + topDocs.totalHits); // ScoreDoc[] scoreDocs = topDocs.scoreDocs; for (int i = 0; i < topDocs.totalHits; i++) { Document targetDoc = isearcher.doc(scoreDocs[i].doc); System.out.println("" + targetDoc.toString()); } } catch (CorruptIndexException e) { e.printStackTrace(); } catch (LockObtainFailedException e) { e.printStackTrace(); } catch (IOException e) { e.printStackTrace(); } catch (ParseException e) { e.printStackTrace(); } finally { if (ireader != null) { try { ireader.close(); } catch (IOException e) { e.printStackTrace(); } } if (directory != null) { try { directory.close(); } catch (IOException e) { e.printStackTrace(); } } } }
From source file:com.lucene.index.test.IKAnalyzerdemo.java
License:Apache License
/** * /* w w w.ja va2 s . c om*/ * ??? * @param args */ public static void main(String[] args) { //Lucene Document?? String fieldName = "text"; // String text1 = "oracle,?"; String text2 = "?"; String text3 = "?"; //IKAnalyzer? Analyzer analyzer = new IKAnalyzer(); Directory directory1 = null; Directory directory2 = null; IndexWriter iwriter1 = null; IndexWriter iwriter2 = null; IndexReader ireader1 = null; IndexReader ireader2 = null; IndexSearcher isearcher = null; try { // directory1 = new RAMDirectory(); directory2 = new RAMDirectory(); //?IndexWriterConfig IndexWriterConfig iwConfig1 = new IndexWriterConfig(analyzer); iwConfig1.setOpenMode(OpenMode.CREATE); IndexWriterConfig iwConfig2 = new IndexWriterConfig(analyzer); iwConfig2.setOpenMode(OpenMode.CREATE); iwriter1 = new IndexWriter(directory1, iwConfig1); iwriter2 = new IndexWriter(directory2, iwConfig2); // Document doc1 = new Document(); doc1.add(new StringField("ID", "10000", Field.Store.YES)); doc1.add(new TextField("text1", text1, Field.Store.YES)); iwriter1.addDocument(doc1); Document doc2 = new Document(); doc2.add(new StringField("ID", "10001", Field.Store.YES)); doc2.add(new TextField("text2", text2, Field.Store.YES)); iwriter2.addDocument(doc2); iwriter1.close(); iwriter2.close(); //?********************************** //? ireader1 = DirectoryReader.open(directory1); ireader2 = DirectoryReader.open(directory2); IndexReader[] mreader = { ireader1, ireader2 }; MultiReader multiReader = new MultiReader(mreader); isearcher = new IndexSearcher(multiReader); String keyword = "?"; //QueryParser?Query String[] fields = { "text1", "text2" }; Map<String, Float> boosts = new HashMap<String, Float>(); boosts.put("text1", 5.0f); boosts.put("text2", 2.0f); /**MultiFieldQueryParser??? * */ MultiFieldQueryParser parser = new MultiFieldQueryParser(fields, analyzer, boosts); Query query = parser.parse(keyword); System.out.println("Query = " + query); //?5? TopDocs topDocs = isearcher.search(query, 5); System.out.println("" + topDocs.totalHits); // ScoreDoc[] scoreDocs = topDocs.scoreDocs; for (int i = 0; i < topDocs.totalHits; i++) { Document targetDoc = isearcher.doc(scoreDocs[i].doc); System.out.println("" + targetDoc.toString()); } } catch (CorruptIndexException e) { e.printStackTrace(); } catch (LockObtainFailedException e) { e.printStackTrace(); } catch (IOException e) { e.printStackTrace(); } catch (ParseException e) { e.printStackTrace(); } finally { if (ireader1 != null) { try { ireader1.close(); ireader2.close(); } catch (IOException e) { e.printStackTrace(); } } if (directory1 != null) { try { directory1.close(); directory2.close(); } catch (IOException e) { e.printStackTrace(); } } } }
From source file:com.lucene.index.test.IKAnalyzerdemoMutilField.java
License:Apache License
/** * //from w w w . j av a2 s .co m * ??? * @param args */ public static void main(String[] args) { //Lucene Document?? String fieldName = "text"; // String text1 = "oracle?"; String text2 = "?"; String text3 = "?"; //IKAnalyzer? Analyzer analyzer = new IKAnalyzer(); Directory directory = null; IndexWriter iwriter = null; IndexReader ireader = null; IndexSearcher isearcher = null; try { // directory = new RAMDirectory(); //?IndexWriterConfig IndexWriterConfig iwConfig = new IndexWriterConfig(analyzer); iwConfig.setOpenMode(OpenMode.CREATE_OR_APPEND); iwriter = new IndexWriter(directory, iwConfig); // Document doc1 = new Document(); doc1.add(new StringField("ID", "10000", Field.Store.YES)); doc1.add(new TextField(fieldName, text1, Field.Store.YES)); iwriter.addDocument(doc1); Document doc2 = new Document(); doc2.add(new StringField("ID", "10000", Field.Store.YES)); doc2.add(new TextField(fieldName, text2, Field.Store.YES)); iwriter.addDocument(doc2); Document doc3 = new Document(); doc3.add(new StringField("ID", "10000", Field.Store.YES)); doc3.add(new TextField(fieldName, text3, Field.Store.YES)); iwriter.addDocument(doc3); iwriter.close(); //?********************************** //? ireader = DirectoryReader.open(directory); isearcher = new IndexSearcher(ireader); String keyword = "?"; //QueryParser?Query QueryParser qp = new QueryParser(fieldName, analyzer); qp.setDefaultOperator(QueryParser.AND_OPERATOR); Query query = qp.parse(keyword); System.out.println("Query = " + query); //?5? TopDocs topDocs = isearcher.search(query, 5); System.out.println("" + topDocs.totalHits); // ScoreDoc[] scoreDocs = topDocs.scoreDocs; for (int i = 0; i < topDocs.totalHits; i++) { Document targetDoc = isearcher.doc(scoreDocs[i].doc); System.out.println("" + targetDoc.toString()); } } catch (CorruptIndexException e) { e.printStackTrace(); } catch (LockObtainFailedException e) { e.printStackTrace(); } catch (IOException e) { e.printStackTrace(); } catch (ParseException e) { e.printStackTrace(); } finally { if (ireader != null) { try { ireader.close(); } catch (IOException e) { e.printStackTrace(); } } if (directory != null) { try { directory.close(); } catch (IOException e) { e.printStackTrace(); } } } }
From source file:com.m3958.apps.pcms.lucene.SearchFiles.java
License:Apache License
/** * This demonstrates a typical paging search scenario, where the search engine presents * pages of size n to the user. The user can then go to the next page if interested in * the next hits./* w w w. j av a 2s. com*/ * * When the query is executed for the first time, then only enough results are collected * to fill 5 result pages. If the user wants to page beyond this limit, then the query * is executed another time and all hits are collected. * */ public static void doPagingSearch(BufferedReader in, IndexSearcher searcher, Query query, int hitsPerPage, boolean raw, boolean interactive) throws IOException { // Collect enough docs to show 5 pages TopDocs results = searcher.search(query, 5 * hitsPerPage); ScoreDoc[] hits = results.scoreDocs;// // DBObject queryCondition = new BasicDBObject(); // //age in [13, 47] // queryCondition = new BasicDBObject(); // BasicDBList values = new BasicDBList(); // values.add(13); // values.add(47); // queryCondition.put("age", new BasicDBObject("$in", values)); // DBCursor dbCursor = coll.find(queryCondition); int numTotalHits = results.totalHits;// System.out.println(numTotalHits + " total matching documents"); int start = 0; int end = Math.min(numTotalHits, hitsPerPage); while (true) { if (end > hits.length) { System.out.println("Only results 1 - " + hits.length + " of " + numTotalHits + " total matching documents collected."); System.out.println("Collect more (y/n) ?"); String line = in.readLine(); if (line.length() == 0 || line.charAt(0) == 'n') { break; } hits = searcher.search(query, numTotalHits).scoreDocs; } end = Math.min(hits.length, start + hitsPerPage); for (int i = start; i < end; i++) { if (raw) {// output raw format System.out.println("doc=" + hits[i].doc + " score=" + hits[i].score); continue; } Document doc = searcher.doc(hits[i].doc); String path = doc.get("path"); if (path != null) { System.out.println((i + 1) + ". " + path); String title = doc.get("title"); if (title != null) { System.out.println(" Title: " + doc.get("title")); } } else { System.out.println((i + 1) + ". " + "No path for this document"); } } if (!interactive || end == 0) { break; } if (numTotalHits >= end) { boolean quit = false; while (true) { System.out.print("Press "); if (start - hitsPerPage >= 0) { System.out.print("(p)revious page, "); } if (start + hitsPerPage < numTotalHits) { System.out.print("(n)ext page, "); } System.out.println("(q)uit or enter number to jump to a page."); String line = in.readLine(); if (line.length() == 0 || line.charAt(0) == 'q') { quit = true; break; } if (line.charAt(0) == 'p') { start = Math.max(0, start - hitsPerPage); break; } else if (line.charAt(0) == 'n') { if (start + hitsPerPage < numTotalHits) { start += hitsPerPage; } break; } else { int page = Integer.parseInt(line); if ((page - 1) * hitsPerPage < numTotalHits) { start = (page - 1) * hitsPerPage; break; } else { System.out.println("No such page"); } } } if (quit) break; end = Math.min(numTotalHits, start + hitsPerPage); } } }
From source file:com.main.Searcher.java
public List<Bean> searching(String s1, String s2, String radioBtn) throws IOException, ParseException, InvalidTokenOffsetsException { //getting reference of directory Directory dir = FSDirectory.open(Paths.get(Index_Dir)); //Index reader - an interface for accessing a point-in-time view of a lucene index IndexReader reader = DirectoryReader.open(dir); IndexSearcher searcher = new IndexSearcher(reader); //analyzer with the default stop words, takes out the stop words Analyzer analyzer = new StandardAnalyzer(); String contents = "contents"; QueryParser parser = new QueryParser(contents, analyzer); int numOfDoc = reader.numDocs(); for (int i = 0; i < numOfDoc; i++) { Document d = reader.document(i); }//from w ww . j av a2 s. com Query q1 = parser.parse(s1); Query q2 = parser.parse(s2); //conjuction, disjunction and negation BooleanQuery.Builder bq = new BooleanQuery.Builder(); //occur.must : both queries required in a doc if (radioBtn.equals("conjunction")) { bq.add(q1, BooleanClause.Occur.MUST); bq.add(q2, BooleanClause.Occur.MUST); bq.build(); } //occur.should: one of the q1 should be presen t in doc else if (radioBtn.equals("disjunction")) { bq.add(q1, BooleanClause.Occur.SHOULD); bq.add(q2, BooleanClause.Occur.SHOULD); bq.build(); } //negation: first should present , second should not else { bq.add(q1, BooleanClause.Occur.MUST); bq.add(q2, BooleanClause.Occur.MUST_NOT); bq.build(); } TopDocs hits = searcher.search(bq.build(), 10); Formatter formatter = new SimpleHTMLFormatter(); QueryScorer scorer = new QueryScorer(bq.build()); //used to markup highlighted terms found in the best sections of a cont Highlighter highlighter = new Highlighter(formatter, scorer); //It breaks cont up into same-size texts but does not split up spans Fragmenter fragmenter = new SimpleSpanFragmenter(scorer, 10); //breaks cont up into same-size fragments with no concerns over spotting sentence boundaries. //set fragmenter to highlighter highlighter.setTextFragmenter(fragmenter); for (int i = 0; i < hits.scoreDocs.length; i++) { Bean bean = new Bean(); int outResult = hits.scoreDocs.length; bean.setNumFile(outResult); int docid = hits.scoreDocs[i].doc; double rank = hits.scoreDocs[i].score; bean.setRankSc(rank); Document doc = searcher.doc(docid); String name = doc.get("name"); String title = doc.get("title"); bean.setTitle(name); String path = doc.get("path"); bean.setPath(path); String cont = doc.get("contents"); //Create token stream TokenStream stream = TokenSources.getAnyTokenStream(reader, docid, "contents", analyzer); //Get highlighted cont fragments String[] frags = highlighter.getBestFragments(stream, cont, 10); ArrayList<String> dummy = new ArrayList<>(); for (String frag : frags) { dummy.add(frag); } bean.setContent(dummy); beanList.add(bean); } dir.close(); // } return beanList; }
From source file:com.main.Searcher.java
public List<Bean> searching(String s1) throws IOException, ParseException, InvalidTokenOffsetsException { //Get directory reference Directory dir = FSDirectory.open(Paths.get(Index_Dir)); //Index reader - an interface for accessing a point-in-time view of a lucene index IndexReader reader = DirectoryReader.open(dir); //CreateIndexReader reader = DirectoryReader.open(dir); lucene searcher. It search over a single IndexReader. IndexSearcher searcher = new IndexSearcher(reader); //analyzer with the default stop words Analyzer analyzer = new StandardAnalyzer(); //Query parser to be used for creating TermQuery String queries = null;/*w w w . j av a2 s. com*/ String queryString = null; //regular search String contents = "contents"; BufferedReader in = null; if (queries != null) { in = Files.newBufferedReader(Paths.get(queries), StandardCharsets.UTF_8); } else { in = new BufferedReader(new InputStreamReader(System.in, StandardCharsets.UTF_8)); } QueryParser parser = new QueryParser(contents, analyzer); int numOfDoc = reader.numDocs(); for (int i = 0; i < numOfDoc; i++) { Document d = reader.document(i); } Query q1 = parser.parse(s1); BooleanQuery.Builder bq = new BooleanQuery.Builder(); bq.add(q1, BooleanClause.Occur.MUST); //Search the lucene documents TopDocs hits = searcher.search(bq.build(), 10); // TopScoreDocCollector collector = TopScoreDocCollector.create(5); /** * Highlighter Code Start *** */ //Uses HTML <B></B> tag to highlight the searched terms Formatter formatter = new SimpleHTMLFormatter(); //It scores cont fragments by the number of unique q1 terms found //Basically the matching score in layman terms QueryScorer scorer = new QueryScorer(bq.build()); //used to markup highlighted terms found in the best sections of a cont Highlighter highlighter = new Highlighter(formatter, scorer); //It breaks cont up into same-size texts but does not split up spans Fragmenter fragmenter = new SimpleSpanFragmenter(scorer, 10); //breaks cont up into same-size fragments with no concerns over spotting sentence boundaries. //set fragmenter to highlighter highlighter.setTextFragmenter(fragmenter); //Iterate over found results for (int i = 0; i < hits.scoreDocs.length; i++) { Bean bean = new Bean(); //int rank = hits.scoreDocs.length; int outResult = hits.scoreDocs.length; bean.setNumFile(outResult); int docid = hits.scoreDocs[i].doc; double rank = hits.scoreDocs[i].score; bean.setRankSc(rank); Document doc = searcher.doc(docid); // String title = doc.get("title"); String name = doc.get("name"); String title = doc.get("title"); bean.setTitle(name); String path = doc.get("path"); bean.setPath(path); String cont = doc.get("contents"); //Create token stream TokenStream stream = TokenSources.getAnyTokenStream(reader, docid, "contents", analyzer); //Get highlighted cont fragments String[] frags = highlighter.getBestFragments(stream, cont, 10); ArrayList<String> dummy = new ArrayList<>(); for (String frag : frags) { dummy.add(frag); } bean.setContent(dummy); beanList.add(bean); } dir.close(); // } return beanList; }
From source file:com.mathworks.xzheng.advsearching.SortingExample.java
License:Apache License
public void displayResults(Query query, Sort sort) // #1 throws IOException { IndexSearcher searcher = new IndexSearcher(DirectoryReader.open(directory)); searcher.setDefaultFieldSortScoring(true, false); // #2 TopDocs results = searcher.search(query, null, // #3 20, sort); // #3 System.out.println("\nResults for: " + // #4 query.toString() + " sorted by " + sort); System.out.println(StringUtils.rightPad("Title", 30) + StringUtils.rightPad("pubmonth", 10) + StringUtils.center("id", 4) + StringUtils.center("score", 15)); PrintStream out = new PrintStream(System.out, true, "UTF-8"); // #5 DecimalFormat scoreFormatter = new DecimalFormat("0.######"); for (ScoreDoc sd : results.scoreDocs) { int docID = sd.doc; float score = sd.score; Document doc = searcher.doc(docID); out.println(StringUtils.rightPad( // #6 StringUtils.abbreviate(doc.get("title"), 29), 30) + // #6 StringUtils.rightPad(doc.get("pubmonth"), 10) + // #6 StringUtils.center("" + docID, 4) + // #6 StringUtils.leftPad( // #6 scoreFormatter.format(score), 12)); // #6 out.println(" " + doc.get("category")); //out.println(searcher.explain(query, docID)); // #7 }//from ww w . j a v a 2 s. c o m }