List of usage examples for org.apache.lucene.search.highlight Highlighter Highlighter
public Highlighter(Formatter formatter, Scorer fragmentScorer)
From source file:fr.mael.microrss.dao.impl.UserArticleDaoImpl.java
License:Open Source License
public List<UserArticle> search(String queryStr, User user, int start, int nb) throws ParseException, IOException, InvalidTokenOffsetsException { FullTextSession searchSession = Search.getFullTextSession(getSessionFactory().getCurrentSession()); QueryParser parser = new MultiFieldQueryParser(Version.LUCENE_31, new String[] { "article.content", "article.title" }, new StandardAnalyzer(Version.LUCENE_31)); org.apache.lucene.search.Query query = parser.parse(queryStr); FullTextQuery hibQuery = searchSession.createFullTextQuery(query, UserArticle.class); Criteria fetchingStrategy = searchSession.createCriteria(UserArticle.class); fetchingStrategy.setFetchMode("article.feed", FetchMode.JOIN); fetchingStrategy.setFetchMode("userLabels", FetchMode.JOIN); fetchingStrategy.add(Property.forName("user").eq(user)); hibQuery.setCriteriaQuery(fetchingStrategy); hibQuery.setFirstResult(start);/* www. ja va 2 s . c om*/ hibQuery.setMaxResults(nb); QueryScorer scorer = new QueryScorer(query); SimpleHTMLFormatter formatter = new SimpleHTMLFormatter("[highlight]", "[/highlight]"); Highlighter highlighter = new Highlighter(formatter, scorer); highlighter.setTextFragmenter(new SimpleSpanFragmenter(scorer, 200)); List<UserArticle> userArticles = (List<UserArticle>) hibQuery.list(); for (UserArticle userArticle : userArticles) { String highlight = highlighter.getBestFragment(new StandardAnalyzer(Version.LUCENE_32), "content", userArticle.getArticle().getContent()); if (highlight != null) { highlight = highlight.replaceAll("\\<.*?>", "").replace("\n", " "); userArticle.getArticle().setHighlight(highlight); } } return userArticles; }
From source file:framework.retrieval.engine.query.formatter.impl.HighlighterMaker.java
License:Apache License
public String getHighlighter(Query query, String fieldName, String keyWord, int resumeLength) { QueryScorer scorer = new QueryScorer(query); Highlighter highlighter = new Highlighter(getFormatter(), scorer); Fragmenter fragmenter = new SimpleFragmenter(resumeLength); highlighter.setTextFragmenter(fragmenter); String result = ""; try {/* w w w . jav a 2 s.com*/ result = highlighter.getBestFragment(analyzer, fieldName, keyWord); } catch (Exception e) { throw new RetrievalQueryException(e); } return result; }
From source file:index.IndexUtils.java
public static List highlight(IndexSearcher indexSearcher, String key) throws ClassNotFoundException { try {//from ww w . j a va 2s . c o m QueryParser queryParser = new QueryParser("name", new StandardAnalyzer()); Query query = queryParser.parse(key); TopDocCollector collector = new TopDocCollector(800); indexSearcher.search(query, collector); ScoreDoc[] hits = collector.topDocs().scoreDocs; Highlighter highlighter = null; SimpleHTMLFormatter simpleHTMLFormatter = new SimpleHTMLFormatter("<font color='red'>", "</font>"); highlighter = new Highlighter(simpleHTMLFormatter, new QueryScorer(query)); highlighter.setTextFragmenter(new SimpleFragmenter(200)); List list = new ArrayList(); Document doc; for (int i = 0; i < hits.length; i++) { //System.out.println(hits[i].score); doc = indexSearcher.doc(hits[i].doc); TokenStream tokenStream = new StandardAnalyzer().tokenStream("name", new StringReader(doc.get("name"))); // IndexResult ir = getIndexResult(doc,"index.IndexResult"); // ir.setName(highlighter.getBestFragment(tokenStream, doc.get("name"))); // list.add(ir); } return list; } catch (ParseException e) { e.printStackTrace(); } catch (IOException e) { e.printStackTrace(); } return null; }
From source file:io.bdrc.lucene.bo.TibetanAnalyzerTest.java
License:Apache License
@Test public void ewtsOffsetBug2() throws IOException, ParseException, InvalidTokenOffsetsException { String input = "(cha) bka' bkan gnyis kyi lung"; String queryLucene = "test:\"bka'\""; Analyzer indexingAnalyzer = new TibetanAnalyzer(false, true, false, "ewts", ""); Analyzer queryAnalyzer = new TibetanAnalyzer(false, true, false, "ewts", ""); TokenStream indexTk = indexingAnalyzer.tokenStream("", input); QueryParser queryParser = new QueryParser("test", queryAnalyzer); Query query = queryParser.parse(queryLucene); SimpleHTMLFormatter formatter = new SimpleHTMLFormatter("->", "<-"); Highlighter highlighter = new Highlighter(formatter, new QueryScorer(query)); highlighter.setTextFragmenter(new SimpleFragmenter(10)); TextFragment[] frags = highlighter.getBestTextFragments(indexTk, input, true, 128); final String firstFrag = frags[0].toString(); System.out.println(firstFrag); assert (firstFrag.equals("(cha) ->bka'<- bkan gnyis kyi lung")); indexingAnalyzer.close();/*from w w w.j ava 2s . c o m*/ queryAnalyzer.close(); }
From source file:io.jpress.module.article.searcher.LuceneSearcher.java
License:LGPL
@Override public Page<Article> search(String keyword, int pageNum, int pageSize) { IndexReader indexReader = null;// w ww . jav a 2 s .c om try { //Bug fix , QueryParser.escape(keyword),keyword=I/O,?buildQuery keyword = QueryParser.escape(keyword); indexReader = DirectoryReader.open(directory); IndexSearcher indexSearcher = new IndexSearcher(indexReader); Query query = buildQuery(keyword); ScoreDoc lastScoreDoc = getLastScoreDoc(pageNum, pageSize, query, indexSearcher); TopDocs topDocs = indexSearcher.searchAfter(lastScoreDoc, query, pageSize); SimpleHTMLFormatter formatter = new SimpleHTMLFormatter("<font class=\"" + HIGH_LIGHT_CLASS + "\">", "</font>"); Highlighter highlighter = new Highlighter(formatter, new QueryScorer(query)); highlighter.setTextFragmenter(new SimpleFragmenter(100)); List<Article> articles = toArticleList(indexSearcher, topDocs, highlighter, keyword); int totalRow = getTotalRow(indexSearcher, query); return newPage(pageNum, pageSize, totalRow, articles); } catch (IOException e) { e.printStackTrace(); } finally { CommonsUtils.quietlyClose(indexReader); } return null; }
From source file:it.eng.spagobi.commons.utilities.indexing.LuceneSearcher.java
License:Mozilla Public License
public static HashMap<String, Object> searchIndex(IndexSearcher searcher, String queryString, String index, String[] fields, String metaDataToSearch) throws IOException, ParseException { logger.debug("IN"); HashMap<String, Object> objectsToReturn = new HashMap<String, Object>(); Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_CURRENT); BooleanQuery andQuery = new BooleanQuery(); if (metaDataToSearch != null) { //search for query string on metadata name field and content //where metadata name = metaDataToSearch Query queryMetadata = new TermQuery(new Term(IndexingConstants.METADATA, metaDataToSearch)); andQuery.add(queryMetadata, BooleanClause.Occur.MUST); }//from ww w . j a v a 2s . c o m Query query = new MultiFieldQueryParser(Version.LUCENE_CURRENT, fields, analyzer).parse(queryString); andQuery.add(query, BooleanClause.Occur.MUST); Query tenantQuery = new TermQuery(new Term(IndexingConstants.TENANT, getTenant())); andQuery.add(tenantQuery, BooleanClause.Occur.MUST); logger.debug("Searching for: " + andQuery.toString()); int hitsPerPage = 50; // Collect enough docs to show 5 pages TopScoreDocCollector collector = TopScoreDocCollector.create(5 * hitsPerPage, false); searcher.search(andQuery, collector); ScoreDoc[] hits = collector.topDocs().scoreDocs; //setsback to action objectsToReturn.put("hits", hits); //highlighter Highlighter highlighter = new Highlighter(new SimpleHTMLFormatter(), new QueryScorer(andQuery)); if (hits != null) { logger.debug("hits size: " + hits.length); for (int i = 0; i < hits.length; i++) { ScoreDoc hit = hits[i]; Document doc = searcher.doc(hit.doc); String biobjId = doc.get(IndexingConstants.BIOBJ_ID); String[] subobjNames = doc.getValues(IndexingConstants.SUBOBJ_NAME); if (subobjNames != null && subobjNames.length != 0) { String views = ""; for (int k = 0; k < subobjNames.length; k++) { views += subobjNames[k] + " "; } objectsToReturn.put(biobjId + "-views", views); } String summary = ""; if (highlighter != null) { String[] summaries; try { Integer idobj = (Integer.valueOf(biobjId)); String contentToSearchOn = fillSummaryText(idobj); summaries = highlighter.getBestFragments(new StandardAnalyzer(Version.LUCENE_CURRENT), IndexingConstants.CONTENTS, contentToSearchOn, 3); StringBuffer summaryBuffer = new StringBuffer(); if (summaries.length > 0) { summaryBuffer.append(summaries[0]); } for (int j = 1; j < summaries.length; j++) { summaryBuffer.append(" ... "); summaryBuffer.append(summaries[j]); } summary = summaryBuffer.toString(); //get only a portion of summary if (summary.length() > 101) { summary = summary.substring(0, 100); summary += "..."; } objectsToReturn.put(biobjId, summary); } catch (InvalidTokenOffsetsException e) { logger.error(e.getMessage(), e); } catch (NumberFormatException e) { logger.error(e.getMessage(), e); } catch (Exception e) { logger.error(e.getMessage(), e); } } } } int numTotalHits = collector.getTotalHits(); logger.info(numTotalHits + " total matching documents"); logger.debug("OUT"); return objectsToReturn; }
From source file:it.eng.spagobi.commons.utilities.indexing.LuceneSearcher.java
License:Mozilla Public License
public static HashMap<String, Object> searchIndexFuzzy(IndexSearcher searcher, String queryString, String index, String[] fields, String metaDataToSearch) throws IOException, ParseException { logger.debug("IN"); HashMap<String, Object> objectsToReturn = new HashMap<String, Object>(); Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_CURRENT); BooleanQuery orQuery = new BooleanQuery(); BooleanQuery andQuery = new BooleanQuery(); for (int i = 0; i < fields.length; i++) { Query query = new FuzzyQuery(new Term(fields[i], queryString)); query = query.rewrite(searcher.getIndexReader()); orQuery.add(query, BooleanClause.Occur.SHOULD); }/*from w w w . j a v a2 s .c o m*/ andQuery.add(orQuery, BooleanClause.Occur.MUST); if (metaDataToSearch != null) { //search for query string on metadata name field and content //where metadata name = metaDataToSearch Query queryMetadata = new TermQuery(new Term(IndexingConstants.METADATA, metaDataToSearch)); andQuery.add(queryMetadata, BooleanClause.Occur.MUST); } Query tenantQuery = new TermQuery(new Term(IndexingConstants.TENANT, getTenant())); andQuery.add(tenantQuery, BooleanClause.Occur.MUST); logger.debug("Searching for: " + andQuery.toString()); int hitsPerPage = 50; // Collect enough docs to show 5 pages TopScoreDocCollector collector = TopScoreDocCollector.create(5 * hitsPerPage, false); searcher.search(andQuery, collector); ScoreDoc[] hits = collector.topDocs().scoreDocs; objectsToReturn.put("hits", hits); //highlighter //orQuery = orQuery.rewrite(searcher.getIndexReader()); //andQuery = andQuery.rewrite(searcher.getIndexReader()); Highlighter highlighter = new Highlighter(new SimpleHTMLFormatter(), new QueryScorer(andQuery)); if (hits != null) { for (int i = 0; i < hits.length; i++) { ScoreDoc hit = hits[i]; Document doc = searcher.doc(hit.doc); String biobjId = doc.get(IndexingConstants.BIOBJ_ID); String summary = " "; if (highlighter != null) { String[] summaries; try { Integer idobj = (Integer.valueOf(biobjId)); String contentToSearchOn = fillSummaryText(idobj); summaries = highlighter.getBestFragments(new StandardAnalyzer(Version.LUCENE_CURRENT), IndexingConstants.CONTENTS, contentToSearchOn, 3); StringBuffer summaryBuffer = new StringBuffer(); if (summaries.length > 0) { summaryBuffer.append(summaries[0]); } for (int j = 1; j < summaries.length; j++) { summaryBuffer.append(" ... "); summaryBuffer.append(summaries[j]); } summary = summaryBuffer.toString(); //get only a portion of summary if (summary.length() > 101) { summary = summary.substring(0, 100); summary += "..."; } objectsToReturn.put(biobjId, summary); } catch (InvalidTokenOffsetsException e) { logger.error(e.getMessage(), e); } catch (Exception e) { logger.error(e.getMessage(), e); } } } } int numTotalHits = collector.getTotalHits(); logger.info(numTotalHits + " total matching documents"); logger.debug("OUT"); return objectsToReturn; }
From source file:lius.search.LiusHitList.java
License:Apache License
private LiusHit buildLiusHit(int index) throws IOException { LiusHit liusHit = new LiusHit(); liusHit.setScore(luceneHits.score(index)); liusHit.setDocId(luceneHits.id(index)); Document luceneDocument = luceneHits.doc(index); Map liusHitFieldsMap = new HashMap(); List liusFieldsList = new ArrayList(); Highlighter luceneHighlighter = null; if (liusConfig.getHighlighter() == true) { IndexReader luceneIndexReader = IndexReader.open(indexDirectory); Query rewrittenLuceneQuery = luceneQuery.rewrite(luceneIndexReader); QueryScorer luceneScorer = new QueryScorer(rewrittenLuceneQuery); SimpleHTMLFormatter luceneFormatter = new SimpleHTMLFormatter("<span class=\"liusHit\">", "</span>"); luceneHighlighter = new Highlighter(luceneFormatter, luceneScorer); }// w ww .java 2s. c o m for (int j = 0; j < liusConfig.getDisplayFields().size(); j++) { LiusField configLiusField = (LiusField) liusConfig.getDisplayFields().get(j); LiusField hitLiusField = new LiusField(); String fieldName = configLiusField.getName(); hitLiusField.setName(fieldName); hitLiusField.setLabel(configLiusField.getLabel()); if (luceneHighlighter != null) { Fragmenter luceneFragmenter; if (configLiusField.getFragmenter() != null) { luceneFragmenter = new SimpleFragmenter(Integer.parseInt(configLiusField.getFragmenter())); } else { luceneFragmenter = new SimpleFragmenter(Integer.MAX_VALUE); } luceneHighlighter.setTextFragmenter(luceneFragmenter); } String[] luceneDocumentValues = luceneDocument.getValues(configLiusField.getName()); if (luceneDocumentValues != null) { if (luceneHighlighter != null) { for (int k = 0; k < luceneDocumentValues.length; k++) { Analyzer luceneAnalyzer = AnalyzerFactory.getAnalyzer(liusConfig); TokenStream luceneTokenStream = luceneAnalyzer.tokenStream(configLiusField.getName(), new StringReader(luceneDocumentValues[k])); String fragment = null; if (configLiusField.getFragmenter() != null) fragment = luceneHighlighter.getBestFragments(luceneTokenStream, luceneDocumentValues[k], 5, "..."); else { fragment = luceneHighlighter.getBestFragment(luceneTokenStream, luceneDocumentValues[k]); } if (fragment == null) { } else { luceneDocumentValues[k] = fragment; } } } hitLiusField.setValue(luceneDocumentValues[0]); hitLiusField.setValues(luceneDocumentValues); liusHitFieldsMap.put(configLiusField.getName(), hitLiusField); liusFieldsList.add(hitLiusField); } } liusHit.setLiusFieldsMap(liusHitFieldsMap); liusHit.setLiusFields(liusFieldsList); return liusHit; }
From source file:lucandra.LucandraTests.java
License:Apache License
public void testHighlight() throws Exception { // This tests the TermPositionVector classes IndexReader indexReader = new IndexReader(indexName, client); IndexSearcher searcher = new IndexSearcher(indexReader); QueryParser qp = new QueryParser(Version.LUCENE_CURRENT, "key", analyzer); // check exact Query q = qp.parse("+key:\"foobar foobar\""); TopDocs docs = searcher.search(q, 10); assertEquals(1, docs.totalHits);//from w ww.j av a 2s . c o m SimpleHTMLFormatter formatter = new SimpleHTMLFormatter(); QueryScorer scorer = new QueryScorer(q, "key", text); Highlighter highlighter = new Highlighter(formatter, scorer); highlighter.setTextFragmenter(new SimpleFragmenter(Integer.MAX_VALUE)); TokenStream tvStream = TokenSources.getTokenStream(indexReader, docs.scoreDocs[0].doc, "key"); String rv = highlighter.getBestFragment(tvStream, text); assertNotNull(rv); assertEquals(rv, highlightedText); }
From source file:lucee.runtime.search.lucene2.highlight._Highlight.java
License:Open Source License
public static Object createHighlighter(Query query, String highlightBegin, String highlightEnd) { return new Highlighter( //new SimpleHTMLFormatter("<span class=\"matching-term\">","</span>"), new SimpleHTMLFormatter(highlightBegin, highlightEnd), new QueryScorer(query)); }