List of usage examples for org.apache.lucene.search.highlight Highlighter Highlighter
public Highlighter(Formatter formatter, Scorer fragmentScorer)
From source file:com.taobao.common.tedis.support.lucene.analysis.xanalyzer.TestHighLight.java
License:Open Source License
/** * @param args//from w ww . j ava2 s .co m */ public static void main(String[] args) { Directory ramDir = new RAMDirectory(); try { IndexWriter writer = new IndexWriter(ramDir, /* * new * StandardAnalyzer()/ */XFactory.getWriterAnalyzer()); Document doc = new Document(); Field fd = new Field(FIELD_NAME, CONTENT, Field.Store.YES, Field.Index.TOKENIZED, Field.TermVector.WITH_POSITIONS_OFFSETS); doc.add(fd); writer.addDocument(doc); writer.optimize(); writer.close(); IndexReader reader = IndexReader.open(ramDir); String queryString = QUERY; QueryParser parser = new QueryParser(FIELD_NAME, /* * new * StandardAnalyzer * ()/ */XFactory.getWriterAnalyzer()); Query query = parser.parse(queryString); System.out.println(query); Searcher searcher = new IndexSearcher(ramDir); query = query.rewrite(reader); System.out.println(query); System.out.println("Searching for: " + query.toString(FIELD_NAME)); Hits hits = searcher.search(query); BoldFormatter formatter = new BoldFormatter(); Highlighter highlighter = new Highlighter(formatter, new QueryScorer(query)); highlighter.setTextFragmenter(new SimpleFragmenter(50)); for (int i = 0; i < hits.length(); i++) { String text = hits.doc(i).get(FIELD_NAME); int maxNumFragmentsRequired = 5; String fragmentSeparator = "..."; TermPositionVector tpv = (TermPositionVector) reader.getTermFreqVector(hits.id(i), FIELD_NAME); TokenStream tokenStream = TokenSources.getTokenStream(tpv); /* * TokenStream tokenStream2= (new StandardAnalyzer()) * //XFactory.getWriterAnalyzer() .tokenStream(FIELD_NAME,new * StringReader(text)); * * do { Token t = tokenStream2.next(); if(t==null)break; * System.out.println("\t" + t.startOffset() + "," + * t.endOffset() + "\t" + t.termText()); }while(true); */ String result = highlighter.getBestFragments(tokenStream, text, maxNumFragmentsRequired, fragmentSeparator); System.out.println("\n" + result); } reader.close(); } catch (Exception e) { e.printStackTrace(); } }
From source file:com.thinkgem.jeesite.common.persistence.BaseDaoImpl.java
License:Open Source License
/** * //from w ww. ja v a 2 s. c o m * * @param query * * @param list * * @param fields * ?? */ public List<T> keywordsHighlight(BooleanQuery query, List<T> list, String... fields) { Analyzer analyzer = new IKAnalyzer(); Formatter formatter = new SimpleHTMLFormatter("<span class=\"highlight\">", "</span>"); Highlighter highlighter = new Highlighter(formatter, new QueryScorer(query)); highlighter.setTextFragmenter(new SimpleFragmenter(100)); for (T entity : list) { try { for (String field : fields) { String text = StringUtils.replaceHtml((String) Reflections.invokeGetter(entity, field)); String desciption = highlighter.getBestFragment(analyzer, field, text); if (desciption != null) { Reflections.invokeSetter(entity, fields[0], desciption); break; } Reflections.invokeSetter(entity, fields[0], StringUtils.abbreviate(text, 100)); } // Reflections.invokeSetter(entity, fields[1], // "sdfkjsdlkfjklsdjf"); } catch (IOException e) { e.printStackTrace(); } catch (InvalidTokenOffsetsException e) { e.printStackTrace(); } } return list; }
From source file:de.blizzy.documentr.search.GetSearchHitTask.java
License:Open Source License
@Override public SearchHit call() throws IOException { Formatter formatter = new SimpleHTMLFormatter("<strong>", "</strong>"); //$NON-NLS-1$ //$NON-NLS-2$ Scorer scorer = new QueryScorer(query); Highlighter highlighter = new Highlighter(formatter, scorer); highlighter.setTextFragmenter(new SimpleFragmenter(FRAGMENT_SIZE)); highlighter.setEncoder(new SimpleHTMLEncoder()); Document doc = reader.document(docId); String projectName = doc.get(PageIndex.PROJECT); String branchName = doc.get(PageIndex.BRANCH); String path = doc.get(PageIndex.PATH); String title = doc.get(PageIndex.TITLE); String text = doc.get(PageIndex.TEXT); String[] tagsArray = doc.getValues(PageIndex.TAG); List<String> tags = Lists.newArrayList(tagsArray); Collections.sort(tags);/* ww w. j av a 2s .co m*/ TokenStream tokenStream = null; String highlightedText = StringUtils.EMPTY; try { tokenStream = TokenSources.getAnyTokenStream(reader, docId, PageIndex.TEXT, doc, analyzer); String[] fragments = highlighter.getBestFragments(tokenStream, text, NUM_FRAGMENTS); cleanupFragments(fragments); highlightedText = Util.join(fragments, " <strong>...</strong> "); //$NON-NLS-1$ } catch (InvalidTokenOffsetsException e) { // ignore } finally { Closeables.closeQuietly(tokenStream); } return new SearchHit(projectName, branchName, path, title, highlightedText, tags); }
From source file:de.elbe5.cms.search.ContentSearchData.java
License:Open Source License
public void setContexts(Query query, Analyzer analyzer) { Highlighter highlighter = new Highlighter(new SearchContextFormatter(), new QueryScorer(query)); String context = getContext(highlighter, analyzer, "name", CONTEXT_LENGTH_NAME); setNameContext(context == null || context.length() == 0 ? getName() : context); context = getContext(highlighter, analyzer, "description", CONTEXT_LENGTH_DESCRIPTION); setDescriptionContext(context);/* w ww .j a va 2 s .c om*/ context = getContext(highlighter, analyzer, "keywords", CONTEXT_LENGTH_KEYWORDS); setKeywordsContext(context); context = getContext(highlighter, analyzer, "authorName", CONTEXT_LENGTH_AUTHOR); setAuthorContext(context); context = getContext(highlighter, analyzer, "content", CONTEXT_LENGTH_CONTENT); setContentContext(context); }
From source file:de.elbe5.cms.search.UserSearchData.java
License:Open Source License
public void setContexts(Query query, Analyzer analyzer) { Highlighter highlighter = new Highlighter(new SearchContextFormatter(), new QueryScorer(query)); String context = getContext(highlighter, analyzer, "name", CONTEXT_LENGTH_NAME); setNameContext(context == null || context.length() == 0 ? getName() : context); }
From source file:de.fhg.iais.cortex.search.highlight.SolrTermRememberingHighlighter.java
License:Apache License
private Highlighter createNewHighlighter(String fieldName, SolrQueryRequest request, Highlighter originalHighlighter) { Formatter localDecoratedFormatter = createDecoratedFormatter(fieldName, request); Highlighter newHighlighter = new Highlighter(localDecoratedFormatter, originalHighlighter.getFragmentScorer()); newHighlighter.setTextFragmenter(originalHighlighter.getTextFragmenter()); return newHighlighter; }
From source file:de.ilias.services.lucene.search.highlight.HitHighlighter.java
License:Open Source License
/** * @throws ConfigurationException //from w w w. j a va2 s .c o m * @throws IOException * @throws SQLException * */ private void init() throws ConfigurationException, IOException, SQLException { // init lucene settings luceneSettings = LuceneSettings.getInstance(); // init highlighter QueryScorer queryScorer = new QueryScorer(query); SimpleHTMLFormatter formatter = new SimpleHTMLFormatter(HIGHLIGHT_BEGIN_TAG, HIGHLIGHT_END_TAG); // Default highlighter highlighter = new Highlighter(formatter, queryScorer); Fragmenter fragmenter = new SimpleFragmenter(luceneSettings.getFragmentSize()); highlighter.setTextFragmenter(fragmenter); highlighter.setMaxDocCharsToAnalyze(Integer.MAX_VALUE); // Title description highlighter -> bigger FRAGMENT SIZE titleHighlighter = new Highlighter(formatter, queryScorer); Fragmenter titleFragmenter = new SimpleFragmenter(FRAGMENT_TITLE_SIZE); titleHighlighter.setTextFragmenter(titleFragmenter); // init fieldinfo fieldInfo = FieldInfo.getInstance(LocalSettings.getClientKey()); // init searcher searcher = SearchHolder.getInstance().getSearcher(); return; }
From source file:de.innovationgate.wgpublisher.lucene.LuceneManager.java
License:Open Source License
public Highlighter createHighlighter(String itemOrMeta, Query query, Formatter formatter) { if (itemOrMeta == null) { return null; }/*w w w .jav a2 s.c o m*/ if (query == null) { return null; } // create scorer // use only terms for this item and terms for allcontent for scoring List terms = new ArrayList(); WeightedTerm[] termsForThisItem = QueryTermExtractor.getTerms(query, false, itemOrMeta); if (termsForThisItem != null) { for (int i = 0; i < termsForThisItem.length; i++) { terms.add(termsForThisItem[i]); } } WeightedTerm[] termsForAllContent = QueryTermExtractor.getTerms(query, false, LuceneManager.INDEXFIELD_ALLCONTENT); if (termsForAllContent != null) { for (int i = 0; i < termsForAllContent.length; i++) { terms.add(termsForAllContent[i]); } } WeightedTerm[] termsArray = new WeightedTerm[terms.size()]; for (int i = 0; i < terms.size(); i++) { WeightedTerm term = (WeightedTerm) terms.get(i); termsArray[i] = term; } QueryTermScorer scorer = new QueryTermScorer(termsArray); // create highlighter Highlighter highlighter = new Highlighter(formatter, scorer); return highlighter; }
From source file:de.iteratec.iteraplan.businesslogic.service.SearchServiceImpl.java
License:Open Source License
/** * Execute the hibernate search//from w w w. j av a2s .co m * * @param searchMap * Multimap of SearhRowDTOs contains the results * @param queryString * the query string which the user entered */ private void executeSearchQuery(Multimap<String, SearchRowDTO> searchMap, String queryString, String buildingBlockTypeFilter) { // reader provider is required to close the reader after search has finished ReaderProvider readerProvider = searchDAO.getReaderProvider(); IndexReader reader = searchDAO.openReader(readerProvider, getClassArray()); // if the reader is null (i.e. the user has no functional permissions to search any one of the // building blocks) return without executing a search if (reader == null) { return; } try { // index fields that will be searched String[] productFields = { "attributeValueAssignments.attributeValue.valueString", "name", "version", "description", "informationSystem.name", "technicalComponent.name", "runtimePeriod.start", "runtimePeriod.end", "informationSystemReleaseA.informationSystem.name", "informationSystemReleaseA.version", "informationSystemReleaseB.informationSystem.name", "informationSystemReleaseB.version" }; QueryParser parser = new MultiFieldQueryParser(Version.LUCENE_31, productFields, new StandardAnalyzer(Version.LUCENE_31)); // allow wildcard * at the beginning of a query string parser.setAllowLeadingWildcard(true); // automatically put quotes around the search term for phrase search, because that's what most people expect parser.setAutoGeneratePhraseQueries(true); // workaround for known issue with highlighter and wildcard queries parser.setMultiTermRewriteMethod(MultiTermQuery.SCORING_BOOLEAN_QUERY_REWRITE); Query luceneQuery = null; try { // parse the query string luceneQuery = parser.parse(queryString); // rewrite luceneQuery for highlighting luceneQuery = luceneQuery.rewrite(reader); } catch (TooManyClauses tmcEx) { throw new IteraplanBusinessException(IteraplanErrorMessages.LUCENE_QUERY_TOO_COMPLEX, tmcEx); } catch (ParseException e) { throw new IteraplanBusinessException(IteraplanErrorMessages.LUCENE_QUERY_PARSE_FAILED, e); } catch (IOException e) { throw new IteraplanTechnicalException(IteraplanErrorMessages.LUCENE_QUERY_REWRITE_FAILED, e); } // the found content is being highlighted SimpleHTMLFormatter sHtmlF = new SimpleHTMLFormatter("<span class=\"highlighted\">", "</span>"); Highlighter highlighter = new Highlighter(sHtmlF, new QueryScorer(luceneQuery)); highlighter.setTextFragmenter(new SimpleFragmenter(40)); // sorted by Building block types SortField sortField = new SortField("buildingBlockType.name", SortField.STRING); Sort sort = new Sort(sortField); String[] projections = { "id", "buildingBlockType.name", FullTextQuery.DOCUMENT, "name", "informationSystem.name", "technicalComponent.name", "version", "description", "runtimePeriod.start", "runtimePeriod.end", "informationSystemReleaseA.informationSystem.name", "informationSystemReleaseA.version", "informationSystemReleaseB.informationSystem.name", "informationSystemReleaseB.version" }; List<Object[]> results = searchDAO.search(luceneQuery, sort, getClassArray(), projections); addResultsToSearchMap(searchMap, results, buildingBlockTypeFilter, highlighter); } finally { readerProvider.closeReader(reader); } }
From source file:de.joergjahnke.jdesktopsearch.SearchPanel.java
License:Open Source License
/** * Get HTML representation of search results * * @param documents found result documents * @param query query which was executed and which contains the search terms * @param maxResults maximum number of results to display, 0 for unlimited search * @return StringBuffer containing HTML to display *///w w w.ja va 2 s . com private StringBuffer getSearchResultHTML(final Collection<Document> documents, final Query query, final int maxResults) { // create result string with HTML content final StringBuffer result = new StringBuffer("<html><body>"); result.append("<i>Searching for "" + query.toString() + ""</i><br><br>"); // get query strings to mark in result final Set<String> searchTerms = QueryUtils.getSearchTerms(query, "contents"); // add hits to result string int found = 0; // prepare highlighter final Formatter formatter = new SimpleHTMLFormatter(MARK_START, MARK_END); final Highlighter highlighter; if (IS_USE_HIGHLIGHTER) { //QueryScorer q = new QueryScorer(query); highlighter = new Highlighter(formatter, new QueryScorer(query)); } for (Document doc : documents) { final String path = doc.get("path"); // add title if one exists String[] values = doc.getValues("title"); if (null != values) { result.append("<b>"); for (int j = 0; j < values.length; ++j) { result.append(values[j]); if (j != values.length - 1) { result.append(' '); } } result.append("</b><br>"); } // add part of the document values = doc.getValues("contents"); if (null != values) { final StringBuffer contents = new StringBuffer(); for (int j = 0; j < values.length && contents.length() < MAX_LENGTH; ++j) { final String value = values[j]; String newContents = null; if (IS_USE_HIGHLIGHTER) { final TokenStream tokenStream = new StandardAnalyzer().tokenStream("contents", new StringReader(value)); try { // get 3 best fragments and seperate with a "..." newContents = highlighter.getBestFragments(tokenStream, value, 3, "<br>...<br>"); } catch (IOException e) { System.err.println("why here " + e.getMessage()); } } else { newContents = highlightSearchTerms(value, searchTerms, contents.toString().replaceAll(MARK_START, "").replaceAll(MARK_END, "").length()); } if (null != newContents && newContents.length() > 0) { contents.append(newContents); contents.append(' '); } } if (contents.length() > 0) { result.append(contents.toString()); result.append("<br>"); } } else { System.err.println("why no contents"); } // add url to document result.append("<a href='" + new File(path).toURI() + "'>" + path + "</a><br><br>"); ++found; } result.append("<br>" + found + " documents found."); // show link to get more results if the maximum result number was reached if (maxResults > 0 && documents.size() >= maxResults) { result.append("<br><br>The maximum of " + maxResults + " documents to display was reached. More results might be available. Click <a href='special://searchAgain'>here</a> to search again without a result number limitation. Please note that such a search might take a considerable amount of time depending on the number of documents found."); } result.append("</body></html>"); return result; }