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.meltmedia.cadmium.search.SearchService.java
License:Apache License
private Map<String, Object> buildSearchResults(final String query, final String path) throws Exception { logger.info("Running search for [{}]", query); final Map<String, Object> resultMap = new LinkedHashMap<String, Object>(); new SearchTemplate(provider) { public void doSearch(IndexSearcher index) throws IOException, ParseException { QueryParser parser = createParser(getAnalyzer()); resultMap.put("number-hits", 0); List<Map<String, Object>> resultList = new ArrayList<Map<String, Object>>(); resultMap.put("results", resultList); if (index != null && parser != null) { String literalQuery = query.replaceAll(ALLOWED_CHARS_PATTERN, "\\\\$1"); Query query1 = parser.parse(literalQuery); if (StringUtils.isNotBlank(path)) { Query pathPrefix = new PrefixQuery(new Term("path", path)); BooleanQuery boolQuery = new BooleanQuery(); boolQuery.add(pathPrefix, Occur.MUST); boolQuery.add(query1, Occur.MUST); query1 = boolQuery;//from w ww. jav a2 s. com } TopDocs results = index.search(query1, null, 100000); QueryScorer scorer = new QueryScorer(query1); Highlighter highlighter = new Highlighter(new SimpleHTMLFormatter(), new SimpleHTMLEncoder(), scorer); logger.info("Search returned {} hits.", results.totalHits); resultMap.put("number-hits", results.totalHits); for (ScoreDoc doc : results.scoreDocs) { Document document = index.doc(doc.doc); String content = document.get("content"); String title = document.get("title"); Map<String, Object> result = new LinkedHashMap<String, Object>(); String excerpt = ""; try { excerpt = highlighter.getBestFragments( parser.getAnalyzer().tokenStream(null, new StringReader(content)), content, 3, "..."); excerpt = fixExcerpt(excerpt); result.put("excerpt", excerpt); } catch (Exception e) { logger.debug("Failed to get search excerpt from content.", e); try { excerpt = highlighter.getBestFragments( parser.getAnalyzer().tokenStream(null, new StringReader(title)), title, 1, "..."); excerpt = fixExcerpt(excerpt); result.put("excerpt", excerpt); } catch (Exception e1) { logger.debug("Failed to get search excerpt from title.", e1); result.put("excerpt", ""); } } result.put("score", doc.score); result.put("title", title); result.put("path", document.get("path")); resultList.add(result); } } } }.search(); return resultMap; }
From source file:com.miliworks.virgo.test.LuceneIndexAndSearchDemo.java
License:Apache License
/** * /*from ww w . jav a 2 s .com*/ * ??? * @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(Version.LUCENE_40, 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(Version.LUCENE_40, 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.mycompany.lucenedemo.SearchFiles.java
/** * 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.//from ww w . j a v a 2 s.co 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 = Math.toIntExact(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++) { 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 (raw) { // output raw format System.out.println("doc=" + hits[i].doc + " score=" + hits[i].score); System.out.println(searcher.explain(query, hits[i].doc)); } } 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.mycompany.mavenproject1.Main.java
public static void main(String[] args) throws IOException, ParseException { StandardAnalyzer analyzer = new StandardAnalyzer(); // Directory index = new RAMDirectory(); Directory index = new SimpleFSDirectory(Paths.get( "C:\\Users\\slete\\Documents\\NetBeansProjects\\mavenproject1\\src\\main\\java\\com\\mycompany\\mavenproject1\\data")); IndexWriterConfig config = new IndexWriterConfig(analyzer); //config.setOpenMode(OpenMode.CREATE); IndexWriter w = new IndexWriter(index, config); try (ItemProvider provider = new ItemProvider( "C:\\Users\\slete\\Documents\\NetBeansProjects\\mavenproject1\\src\\main\\java\\com\\mycompany\\mavenproject1\\items.xml")) { while (provider.hasNext()) { Item item = provider.next(); addItem(w, item);/*from w w w. j av a 2 s. c o m*/ } } catch (XMLStreamException | IOException ex) { ex.getMessage(); } // w.commit(); w.close(); // String queryStr = "id:1* NOT id:19*"; String a = "id:1* NOT id:19*"; String b = "name:Dekielek AND description:(ty AND obiektywu)"; String c = "category:Dek*"; String ds = "id:1232~2"; String e = "price:[0.0 TO 100.0]"; Query q = new QueryParser("name", analyzer).parse(ds); int hitsPerPage = 10; IndexReader reader = DirectoryReader.open(index); IndexSearcher searcher = new IndexSearcher(reader); TopDocs docs = searcher.search(q, hitsPerPage); ScoreDoc[] hits = docs.scoreDocs; System.out.println("Found " + hits.length + " hits."); for (int i = 0; i < hits.length; ++i) { int docId = hits[i].doc; Document d = searcher.doc(docId); System.out .println(d.get("id") + "\t" + d.get("price") + "\t" + d.get("name") + "\t" + d.get("category"));//+"\t" + d.get("description")); } }
From source file:com.mycompany.restlet.search.sample.searcher.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.//from w w w. jav a 2 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.nearinfinity.blur.search.SuperQueryTest.java
License:Apache License
@Test public void testSimpleSuperQuery() throws CorruptIndexException, IOException, InterruptedException { BooleanQuery booleanQuery = new BooleanQuery(); booleanQuery.add(wrapSuper(new TermQuery(new Term(PERSON_NAME, NAME1))), Occur.MUST); booleanQuery.add(wrapSuper(new TermQuery(new Term(ADDRESS_STREET, STREET1))), Occur.MUST); Directory directory = createIndex(); IndexReader reader = IndexReader.open(directory); printAll(new Term(PERSON_NAME, NAME1), reader); printAll(new Term(ADDRESS_STREET, STREET1), reader); printAll(new Term(PRIME_DOC, PRIME_DOC_VALUE), reader); IndexSearcher searcher = new IndexSearcher(reader); TopDocs topDocs = searcher.search(booleanQuery, 10); assertEquals(2, topDocs.totalHits);/*w w w. j a v a2s . co m*/ assertEquals("1", searcher.doc(topDocs.scoreDocs[0].doc).get(ROW_ID)); assertEquals("3", searcher.doc(topDocs.scoreDocs[1].doc).get(ROW_ID)); }
From source file:com.nero.model.SearchFiles.java
License:Apache License
public static void testSearch() { String queryStr = "1"; //This is the directory that hosts the Lucene index IndexReader reader;/*from ww w . j av a2s. c o m*/ try { reader = IndexReader.open(FSDirectory.open(new File(index))); IndexSearcher searcher = new IndexSearcher(reader); Term term = new Term("contents", queryStr); TermQuery luceneQuery = new TermQuery(term); TopDocs results; results = searcher.search(luceneQuery, 100); ScoreDoc[] hits = results.scoreDocs; System.out.println(hits.length); for (int i = 0; i < hits.length; i++) { Document doc; doc = searcher.doc(hits[i].doc); System.out.println("File: " + doc.get("contents")); } searcher.close(); } catch (CorruptIndexException e) { // TODO Auto-generated catch block e.printStackTrace(); } catch (IOException e) { // TODO Auto-generated catch block e.printStackTrace(); } }
From source file:com.nero.model.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./*from w ww .j a va 2 s . c om*/ * * 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("zh_name"); if (path != null) { System.out .println((i + 1) + "!!!!!!!!!!!!!!! " + path + "!!!!!!!!!!!!!!! " + doc.get("summary")); 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.netcrest.pado.index.provider.lucene.LuceneSearch.java
License:Open Source License
protected Set<Object> getIdentityKeySet(String queryString, Directory dir) { Set<Object> identityKeySet = new HashSet<Object>(); DirectoryReader reader;//from w ww. j a v a2 s .com try { reader = DirectoryReader.open(dir); } catch (CorruptIndexException e1) { e1.printStackTrace(); throw new RuntimeException(e1); } catch (IOException e1) { e1.printStackTrace(); throw new RuntimeException(e1); } Query query; try { StandardQueryParser parser = new StandardQueryParser(new StandardAnalyzer(LUCENE_VERSION)); query = parser.parse(queryString.replaceAll("\\-", "\\\\-"), "__doc"); } catch (Exception ex) { // Lucene bug. Unable to serialize exception. Log the message and // throw a new exception with the string message. ex.printStackTrace(); throw new PadoException(ex.getMessage()); } IndexSearcher searcher = new IndexSearcher(reader); TopDocs results; try { results = searcher.search(query, null, Integer.MAX_VALUE); for (ScoreDoc hit : results.scoreDocs) { Document doc; try { doc = searcher.doc(hit.doc); } catch (CorruptIndexException e) { e.printStackTrace(); throw new RuntimeException(e); } catch (IOException e) { e.printStackTrace(); throw new RuntimeException(e); } // IndexableField field = doc.getField("IdentityKey"); // if (field == null) { // continue; // } // Object identityKey = field.stringValue(); // if (identityKey == null) { // identityKey = field.numericValue(); // } // if (identityKey == null) { // BytesRef br = field.binaryValue(); // if (br != null) { // byte[] blob = br.bytes; // try { // identityKey = BlobHelper.deserializeBlob(blob); // identityKeySet.add(identityKey); // } catch (Exception ex) { // Logger.warning("Identity key deserialization error", ex); // } // } else { // identityKey = field.toString(); // } // } LuceneField luceneField = new LuceneField(); ITemporalKey temporalKey = luceneField.getTemporalKey(doc); if (temporalKey != null) { identityKeySet.add(temporalKey.getIdentityKey()); } } } catch (IOException e1) { e1.printStackTrace(); throw new RuntimeException(e1); } return identityKeySet; }
From source file:com.netcrest.pado.index.provider.lucene.LuceneSearch.java
License:Open Source License
protected Set<ITemporalKey> getTemporalKeySet(String queryString, Directory dir) { Set<ITemporalKey> temporalKeySet = new HashSet<ITemporalKey>(); DirectoryReader reader;/* w w w.j a va 2s . c om*/ try { reader = DirectoryReader.open(dir); } catch (CorruptIndexException e1) { e1.printStackTrace(); throw new RuntimeException(e1); } catch (IOException e1) { e1.printStackTrace(); throw new RuntimeException(e1); } Query query; try { StandardQueryParser parser = new StandardQueryParser(new StandardAnalyzer(LUCENE_VERSION)); query = parser.parse(queryString.replaceAll("\\-", "\\\\-"), "__doc"); } catch (Exception ex) { // Lucene 4.7 bug, internal message not serializable // Send message instead of nesting the cause. throw new RuntimeException(ex.getMessage()); } IndexSearcher searcher = new IndexSearcher(reader); TopDocs results; try { results = searcher.search(query, null, Integer.MAX_VALUE); for (ScoreDoc hit : results.scoreDocs) { Document doc; try { doc = searcher.doc(hit.doc); } catch (CorruptIndexException e) { e.printStackTrace(); throw new RuntimeException(e); } catch (IOException e) { e.printStackTrace(); throw new RuntimeException(e); } LuceneField luceneField = new LuceneField(); ITemporalKey temporalKey = luceneField.getTemporalKey(doc); if (temporalKey != null) { temporalKeySet.add(temporalKey); } } } catch (IOException e1) { e1.printStackTrace(); throw new RuntimeException(e1); } return temporalKeySet; }