List of usage examples for org.apache.lucene.search.highlight Highlighter setTextFragmenter
public void setTextFragmenter(Fragmenter fragmenter)
From source file:org.mskcc.pathdb.tool.QueryFullText.java
License:Open Source License
/** * Executes Full Text Query.// ww w .j a va2s.c om * * @param term Search Term * @throws QueryException Lucene Query Error * @throws IOException I/O Error * @throws ParseException Lucene Parsing Error */ public static void queryFullText(String term) throws QueryException, IOException, ParseException { System.out.println("Using search term: " + term); LuceneReader luceneReader = new LuceneReader(); Hits hits = luceneReader.executeQuery(term); int num = Math.min(10, hits.length()); System.out.println("Total Number of Hits: " + hits.length()); if (hits.length() > 0) { // Standard Analyzer to extract words using a list of English stop words. StandardAnalyzer analyzer = new StandardAnalyzer(); // Standard Query Parser QueryParser queryParser = new QueryParser(LuceneConfig.FIELD_ALL, analyzer); // for the usage of highlighting with wildcards // Necessary to expand search terms IndexReader reader = IndexReader.open(new File(LuceneConfig.getLuceneDirectory())); Query luceneQuery = queryParser.parse(term); luceneQuery = luceneQuery.rewrite(reader); // Scorer implementation which scores text fragments by the number of // unique query terms found. QueryScorer queryScorer = new QueryScorer(luceneQuery); // HTML Formatted surrounds matching text with <B></B> tags. SimpleHTMLFormatter htmlFormatter = new SimpleHTMLFormatter(); // Highligher Class Highlighter highLighter = new Highlighter(htmlFormatter, queryScorer); // XXX Characters Max in Each Fragment Fragmenter fragmenter = new SimpleFragmenter(100); highLighter.setTextFragmenter(fragmenter); System.out.println("Showing hits: 0-" + (num - 1)); for (int i = 0; i < num; i++) { System.out.print("Hit " + i + ": "); // Get the Matching Hit Document doc = hits.doc(i); // Get the Field of Interest Field field = doc.getField(LuceneConfig.FIELD_ALL); // Create the Token Stream TokenStream tokenStream = new StandardAnalyzer().tokenStream(LuceneConfig.FIELD_ALL, new StringReader(field.stringValue())); // Get the Best Fragment String formattedText = highLighter.getBestFragments(tokenStream, field.stringValue(), 5, "..."); System.out.println(formattedText); } } }
From source file:org.riotfamily.search.ResultHighlighter.java
License:Apache License
public HighlightingContext createContext(IndexSearcher indexSearcher, Query query) throws IOException { Scorer scorer = new QueryScorer(indexSearcher.rewrite(query)); if (formatter == null) { formatter = new SimpleHTMLFormatter("<" + highlightPreTag + ">", "</" + highlightPostTag + ">"); }//from www .j a va2 s. c om if (fragmenter == null) { fragmenter = new SimpleFragmenter(fragmentSize); } Highlighter highlighter = new Highlighter(formatter, encoder, scorer); highlighter.setTextFragmenter(fragmenter); return new HighlightingContext(highlighter); }
From source file:org.shredzone.cilla.service.search.strategy.LuceneSearchStrategy.java
License:Open Source License
/** * Creates a list of highlights for a search result. * * @param pq// w w w . j av a 2 s . co m * {@link Query} that was used * @param result * List of {@link Page} results * @return matching list of text extracts with highlights */ private List<String> createHighlights(Query pq, List<Page> result) { QueryScorer scorer = new QueryScorer(pq, "text"); Fragmenter fragmenter = searchResultRenderer.createFragmenter(scorer); Formatter formatter = searchResultRenderer.createFormatter(); Highlighter hilighter = new Highlighter(formatter, scorer); hilighter.setTextFragmenter(fragmenter); PageBridge bridge = new PageBridge(); return result.stream().parallel().map(bridge::objectToString).map(plain -> highlight(plain, hilighter)) .collect(Collectors.toList()); }
From source file:searchEngine.SearchFiles.java
License:Apache License
public static QueryResult doPagingSearch(BufferedReader in, IndexSearcher searcher, Query query, int hitsPerPage, int pageNumber, boolean raw, boolean interactive) throws IOException, InvalidTokenOffsetsException { QueryResult queryResults = new QueryResult(); TopDocs results = searcher.search(query, pageNumber * hitsPerPage); ScoreDoc[] hits = results.scoreDocs; int numTotalHits = results.totalHits; System.out.println(numTotalHits + " total matching documents"); Highlighter highlighter = new Highlighter(new SimpleHTMLFormatter("<font color=\"red\">", "</font>"), new QueryScorer(query)); highlighter.setTextFragmenter(new SimpleFragmenter(20)); int start = 0; int end = Math.min(numTotalHits, pageNumber * hitsPerPage); for (int i = start; i < end; i++) { if (raw) { System.out.println("doc=" + hits[i].doc + " score=" + hits[i].score); continue; }//from ww w . jav a 2 s. co m Document doc = searcher.doc(hits[i].doc); Analyzer analyzer = new SmartChineseAnalyzer(); String text = doc.get("contents"); TokenStream tokenStream = analyzer.tokenStream("contents", new StringReader(text)); String highlighterResult = highlighter.getBestFragments(tokenStream, text, 2, ""); System.out.println("########### " + highlighterResult); String path = doc.get("path"); if (path != null) { System.out.println((i + 1) + ". " + path + " Score: " + hits[i].score); //System.out.println(results[i].) queryResults.addUrl(path); String title = doc.get("title"); queryResults.addTitle(title); queryResults.addContent(highlighterResult); } else { System.out.println((i + 1) + ". " + "No path for this document"); } } return queryResults; }
From source file:top.sj.lucene.LuceneSearchUtil.java
License:Open Source License
/** * ???/* www. ja v a2s . c o m*/ * * @param primaryKeyByHibernateEntity * Hibernate?? * @param analysisTarget * ????? * @param analysisCondition * ???? * @return ???? * @throws IOException * @throws ParseException * @throws InvalidTokenOffsetsException */ public static List<LuceneSearchDTO> searchOfSingleAreaAndSingleCondition(String primaryKeyByHibernateEntity, String analysisTarget, String analysisCondition) throws IOException, ParseException, InvalidTokenOffsetsException { String configPath = PropertiesTool.getPropertiesFileAsObject("lucene_config.properties") .getProperty("index_location"); Directory dir = null; try { dir = FSDirectory.open(new File(configPath)); } catch (Exception e) { e.printStackTrace(); } // Directory dir = FSDirectory.open(new File("D:\\lucene")); IndexSearcher searcher = new IndexSearcher(dir); QueryParser parser = new QueryParser(Version.LUCENE_30, analysisTarget, new StandardAnalyzer(Version.LUCENE_30)); // ?? Query query = parser.parse(analysisCondition); TopDocs topDocs = searcher.search(query, MAX_SEARCH_RESULT); /** * */ QueryScorer queryScorer = new QueryScorer(query); Fragmenter fragmenter = new SimpleSpanFragmenter(queryScorer); Formatter formatter = new SimpleHTMLFormatter("<b>", "<b/>"); Highlighter highlighter = new Highlighter(formatter, queryScorer); highlighter.setTextFragmenter(fragmenter); List<LuceneSearchDTO> analysisResults = new ArrayList<LuceneSearchDTO>(); for (int i = 0; i < topDocs.scoreDocs.length; i++) { int docId = topDocs.scoreDocs[i].doc; Document doc = searcher.doc(docId); String attr = highlighter.getBestFragment(new StandardAnalyzer(Version.LUCENE_30), analysisTarget, doc.get(analysisTarget)); analysisResults.add(new LuceneSearchDTO(Integer.valueOf(doc.get(primaryKeyByHibernateEntity)), attr)); } return analysisResults; }
From source file:top.sj.lucene.LuceneSearchUtil.java
License:Open Source License
/** * ??/*w w w.jav a2 s . c o m*/ * * @param primaryKeyByHibernateEntity * Hibernate?? * @param analysisTarget * ????? * @param analysisConditions * ????????????? * @return ???? * @throws IOException * @throws ParseException * @throws InvalidTokenOffsetsException */ public static List<LuceneSearchDTO> searchOfSingleAreaAndMultiCondition(String primaryKeyByHibernateEntity, String analysisTarget, String... analysisConditions) throws IOException, ParseException, InvalidTokenOffsetsException { String configPath = PropertiesTool.getPropertiesFileAsObject("lucene_config.properties") .getProperty("index_location"); Directory dir = FSDirectory.open(new File(configPath)); // Directory dir = FSDirectory.open(new File("D://lucene")); IndexSearcher searcher = new IndexSearcher(dir); QueryParser parser = new QueryParser(Version.LUCENE_30, analysisTarget, new StandardAnalyzer(Version.LUCENE_30)); BooleanQuery query = new BooleanQuery(); for (int i = 0; i < analysisConditions.length; i++) { Query query1 = parser.parse(analysisConditions[i]); query.add(query1, i == 0 ? Occur.MUST : Occur.SHOULD); } TopDocs topDocs = searcher.search(query, MAX_SEARCH_RESULT); /** * */ QueryScorer queryScorer = new QueryScorer(query); Fragmenter fragmenter = new SimpleSpanFragmenter(queryScorer); Formatter formatter = new SimpleHTMLFormatter("<b>", "<b/>"); Highlighter highlighter = new Highlighter(formatter, queryScorer); highlighter.setTextFragmenter(fragmenter); List<LuceneSearchDTO> analysisResults = new ArrayList<LuceneSearchDTO>(); for (int i = 0; i < topDocs.scoreDocs.length; i++) { int docId = topDocs.scoreDocs[i].doc; Document doc = searcher.doc(docId); String attr = highlighter.getBestFragment(new StandardAnalyzer(Version.LUCENE_30), analysisTarget, doc.get(analysisTarget)); analysisResults.add(new LuceneSearchDTO(Integer.valueOf(doc.get(primaryKeyByHibernateEntity)), attr)); } return analysisResults; }
From source file:uk.ac.ebi.arrayexpress.utils.saxon.search.QueryHighlighter.java
License:Apache License
public String highlightQuery(QueryInfo queryInfo, String fieldName, String text) { try {/*from www . j a va 2 s . c o m*/ SimpleHTMLFormatter htmlFormatter = new SimpleHTMLFormatter(HIT_OPEN_MARK, HIT_CLOSE_MARK); Highlighter highlighter = new Highlighter(htmlFormatter, new QueryScorer(queryInfo.getQuery(), fieldName, this.env.defaultField)); highlighter.setTextFragmenter(new NullFragmenter()); String str = highlighter.getBestFragment(this.env.indexAnalyzer, "".equals(fieldName) ? this.env.defaultField : fieldName, text); return null != str ? str : text; } catch (Exception x) { logger.error("Caught an exception:", x); } return text; }
From source file:uk.ac.ebi.arrayexpress.utils.search.EFOExpandedHighlighter.java
License:Apache License
private String doHighlightQuery(Query query, String fieldName, String text, String openMark, String closeMark) { try {/*from w w w .ja va2 s .c o m*/ SimpleHTMLFormatter htmlFormatter = new SimpleHTMLFormatter(openMark, closeMark); Highlighter highlighter = new Highlighter(htmlFormatter, new QueryScorer(query, fieldName, this.env.defaultField)); highlighter.setTextFragmenter(new NullFragmenter()); String str = highlighter.getBestFragment(this.env.indexAnalyzer, "".equals(fieldName) ? this.env.defaultField : fieldName, text); return null != str ? str : text; } catch (Exception x) { logger.error("Caught an exception:", x); } return text; }
From source file:uk.ac.ebi.biostudies.efo.EFOExpandedHighlighter.java
License:Apache License
private String doHighlightQuery(Query query, String fieldName, String text, String openMark, String closeMark, boolean fragmentOnly) { try {/* w ww .j a v a 2 s . com*/ SimpleHTMLFormatter htmlFormatter = new SimpleHTMLFormatter(openMark, closeMark); QueryScorer scorer = new QueryScorer(query, fieldName, indexConfig.getDefaultField()); Highlighter highlighter = new Highlighter(htmlFormatter, scorer); highlighter.setTextFragmenter( fragmentOnly ? new SimpleSpanFragmenter(scorer, indexConfig.getSearchSnippetFragmentSize()) : new NullFragmenter()); String str = highlighter.getBestFragment(new ExperimentTextAnalyzer(), "".equals(fieldName) ? indexConfig.getDefaultField() : fieldName, text); return str; } catch (Exception x) { logger.error("Caught an exception:", x); } return text; }