List of usage examples for org.apache.lucene.search.highlight Highlighter Highlighter
public Highlighter(Formatter formatter, Scorer fragmentScorer)
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// ww w .j a v a 2s. c om * {@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:org.zilverline.service.SearchServiceImpl.java
License:Open Source License
/** * Searches the given Collections for the query. Sending an empty or null array of names will betreated as if all collections * need to be searched, which is handy for external queries, that can't know the names of collections. * /*from w w w .j a v a2s . com*/ * @param names array of collection names * @param queryString the query * @param startAt the first result to return (start counting from 0) * @param numberOfResults the (maximum) number of results to return * @return Object containing the results, and number of hits and the possibly changed startAt and endAt * * @throws SearchException if query can't be executed */ public SearchResult doSearch(final String[] names, final String queryString, int startAt, final int numberOfResults) throws SearchException { try { MultiSearcher ms = null; try { // for given collections create a List of IndexSearchers IndexSearcher[] allSearchers = createSearchersForCollectionsByName(names); // prepare the query // TODO: which analyzer to use? Different collections may have different Analyers Analyzer analyzer = getCollectionManager().createAnalyzer(); log.debug("Using Analyzer " + analyzer.getClass()); // for each occurence of contents, add a boost for fields specified in BoostFactor BoostingParser zp = new BoostingParser("contents", analyzer); zp.setFactors(factors); Query localquery = zp.parse(queryString); log.debug("the Query: " + query); // and search in all collections ms = new MultiSearcher(allSearchers); Hits hits = ms.search(localquery); log.debug("Query " + queryString + ", with " + hits.length() + " hits"); // if we're changing the query, and we've paged too far if (startAt >= hits.length() || startAt < 0) { startAt = 0; } // only get the number of results we're interested in that is from startAt to endAt, or last int endAt = startAt + numberOfResults; // set the max index to maxpage or last if (endAt > hits.length()) { endAt = hits.length(); } log.debug("Returning hits " + startAt + " to " + (endAt - 1)); // get all the hits into results array Result[] results = new Result[endAt - startAt]; Highlighter highlighter = new Highlighter( new SimpleHTMLFormatter("<span class=\"highlight\">", "</span>"), new QueryScorer(localquery)); // get all the hits into Result for (int j = startAt; j < endAt; j++) { Document doc = hits.doc(j); float score = hits.score(j); results[j - startAt] = doc2ResultHelper(doc, score, highlighter, analyzer); } log.info("The query '" + queryString + "', has " + hits.length() + " hits, returning " + maxResults + " results: " + (startAt + 1) + " to " + endAt); return new SearchResult(results, hits.length(), startAt, endAt); } catch (org.apache.lucene.queryParser.ParseException pe) { throw new SearchException("Error executing query '" + queryString + "'", pe); } catch (TooManyClauses e) { throw new SearchException("Error executing query '" + queryString + ". Too complex, possibly spanning more than 1024 days'", e); } finally { if (ms != null) { ms.close(); } } } catch (Exception e) { log.error("Error executing query '" + queryString + "', " + e); throw new SearchException("Error executing query '" + queryString + "'", e); } }
From source file:perf.SearchTask.java
License:Apache License
@Override public void go(IndexState state) throws IOException { //System.out.println("go group=" + this.group + " single=" + singlePassGroup + " xxx=" + xxx + " this=" + this); final IndexSearcher searcher = state.mgr.acquire(); //System.out.println("GO query=" + q); try {/* w w w . j a v a 2 s. c o m*/ if (doHilite) { if (state.fastHighlighter != null) { fieldQuery = state.fastHighlighter.getFieldQuery(q, searcher.getIndexReader()); } else if (state.useHighlighter) { highlighter = new Highlighter(new SimpleHTMLFormatter(), new QueryScorer(q)); } else { // no setup for postingshighlighter } } if (group != null) { if (singlePassGroup) { final BlockGroupingCollector c = new BlockGroupingCollector(Sort.RELEVANCE, 10, true, searcher.createNormalizedWeight(state.groupEndQuery, false)); searcher.search(q, c); groupsResultBlock = c.getTopGroups(Sort.RELEVANCE, 0, 0, 10, true); if (doHilite) { hilite(groupsResultBlock, state, searcher); } } else { //System.out.println("GB: " + group); final TermFirstPassGroupingCollector c1 = new TermFirstPassGroupingCollector(group, Sort.RELEVANCE, 10); final Collector c; final TermAllGroupsCollector allGroupsCollector; // Turn off AllGroupsCollector for now -- it's very slow: if (false && doCountGroups) { allGroupsCollector = new TermAllGroupsCollector(group); //c = MultiCollector.wrap(allGroupsCollector, c1); c = c1; } else { allGroupsCollector = null; c = c1; } searcher.search(q, c); final Collection<SearchGroup<BytesRef>> topGroups = c1.getTopGroups(0, true); if (topGroups != null) { final TermSecondPassGroupingCollector c2 = new TermSecondPassGroupingCollector(group, topGroups, Sort.RELEVANCE, Sort.RELEVANCE, 10, true, true, true); searcher.search(q, c2); groupsResultTerms = c2.getTopGroups(0); if (allGroupsCollector != null) { groupsResultTerms = new TopGroups<BytesRef>(groupsResultTerms, allGroupsCollector.getGroupCount()); } if (doHilite) { hilite(groupsResultTerms, state, searcher); } } } } else if (!facetRequests.isEmpty()) { // TODO: support sort, filter too!! // TODO: support other facet methods if (doDrillSideways) { // nocommit todo hits = null; facetResults = null; } else { facetResults = new ArrayList<FacetResult>(); FacetsCollector fc = new FacetsCollector(); hits = FacetsCollector.search(searcher, q, 10, fc); long t0 = System.nanoTime(); Facets mainFacets = null; for (String request : facetRequests) { if (request.startsWith("range:")) { int i = request.indexOf(':', 6); if (i == -1) { throw new IllegalArgumentException("range facets request \"" + request + "\" is missing field; should be range:field:0-10,10-20"); } String field = request.substring(6, i); String[] rangeStrings = request.substring(i + 1, request.length()).split(","); LongRange[] ranges = new LongRange[rangeStrings.length]; for (int rangeIDX = 0; rangeIDX < ranges.length; rangeIDX++) { String rangeString = rangeStrings[rangeIDX]; int j = rangeString.indexOf('-'); if (j == -1) { throw new IllegalArgumentException( "range facets request should be X-Y; got: " + rangeString); } long start = Long.parseLong(rangeString.substring(0, j)); long end = Long.parseLong(rangeString.substring(j + 1)); ranges[rangeIDX] = new LongRange(rangeString, start, true, end, true); } LongRangeFacetCounts facets = new LongRangeFacetCounts(field, fc, ranges); facetResults.add(facets.getTopChildren(ranges.length, field)); } else { Facets facets = new FastTaxonomyFacetCounts(state.taxoReader, state.facetsConfig, fc); facetResults.add(facets.getTopChildren(10, request)); } } getFacetResultsMsec = (System.nanoTime() - t0) / 1000000.0; } } else if (s == null) { hits = searcher.search(q, topN); if (doHilite) { hilite(hits, state, searcher, q); } } else { hits = searcher.search(q, topN, s); if (doHilite) { hilite(hits, state, searcher, q); } /* final boolean fillFields = true; final boolean fieldSortDoTrackScores = true; final boolean fieldSortDoMaxScore = true; final TopFieldCollector c = TopFieldCollector.create(s, topN, fillFields, fieldSortDoTrackScores, fieldSortDoMaxScore, false); searcher.search(q, c); hits = c.topDocs(); */ } if (hits != null) { totalHitCount = hits.totalHits; if (doStoredLoads) { for (int i = 0; i < hits.scoreDocs.length; i++) { ScoreDoc scoreDoc = hits.scoreDocs[i]; searcher.doc(scoreDoc.doc); } } } else if (groupsResultBlock != null) { totalHitCount = groupsResultBlock.totalHitCount; } } catch (Throwable t) { System.out.println("EXC: " + q); throw new RuntimeException(t); //System.out.println("TE: " + TermsEnum.getStats()); } finally { state.mgr.release(searcher); fieldQuery = null; highlighter = null; } }
From source file:Search.SearchExecutor.java
License:Educational Community License
/** * Search user generated transcriptions. Results contain embedded images. Results are restricted to those the user usrID has * permissing to view the transcription/* ww w . j av a 2 s.co m*/ * @param searchWord * @param language * @param order * @param paged * @param pageNumber * @param usrID * @return * @throws Exception */ public Stack<Transcription> transcriptionSearch(String searchWord, String language, int order, Boolean paged, int pageNumber, String usrID) throws Exception { Boolean wildcard = true; final int pageSize = 20; //Number of results per page, could be made a parm one day final int maxResults = 1000; //No matter what dont return more than this many results from Lucene. This is ok because result filtering occurs before this limitation is applied String returnStringArray = ""; //we dont currently worry about language filtering, but ENAP did, so we could do it if we wanted to if (language != null && language.length() > 1) { //searchWord=searchWord+" AND lang:"+language; } /**@TODO the location should be a param*/ IndexSearcher is = new IndexSearcher("/usr/indexTranscriptions"); QueryParser parser = new QueryParser("text", analyser); Sort newsort; Query query = parser.parse(searchWord); is.rewrite(parser.parse(searchWord)); QueryScorer queryScorer = new QueryScorer(query); ScoreDoc[] hits; //If the person wasnt logged in, give them only public comments. comment owner if (usrID.compareTo("") == 0) { usrID = "0"; } Query secQuery = parser.parse("security:private OR creator:" + usrID); //This will filter search results so only comments owned by the user and public comments will be returned QueryFilter secFilter = new QueryFilter(query); //If a sort was specified, use it, otherwise use the default sorting which is by hit quality if (order > 0) { //order=1 means sort by line number, first line of the text is first. //order=2 means inverse sort by line number, last line of the text is first. //Java, the Nanny language, doesn't want to let me use newsort even if I ensure its not a null pointer //So if were going to use a filter, set the filter to type 1, then check to see if it should be something else. try { hits = is.search(query, secFilter, maxResults).scoreDocs; } catch (org.apache.lucene.search.BooleanQuery.TooManyClauses e) { return null; } } else { try { newsort = new Sort("creator", false); hits = is.search(query, secFilter, maxResults, newsort).scoreDocs; } catch (org.apache.lucene.search.BooleanQuery.TooManyClauses e) { return null; } } //Start at the hit that belongs at the top of the page they requested. For page 2, that is 19 //Ensure we do not print more than pageNumber hits, or go beyond the end of the hit list String link = ""; int ctr = 1; Stack<Transcription> results = new Stack(); SimpleHTMLFormatter formatter = new SimpleHTMLFormatter("<span class=\"highlight\">", "</span>"); Highlighter highlighter = new Highlighter(formatter, queryScorer); if (pageSize * (pageNumber - 1) < hits.length) { returnStringArray += "Your search for \"<b>" + searchWord + "</b>\" returned " + hits.length + " results.<br/>"; for (int i = pageSize * (pageNumber - 1); i < hits.length && i - (pageSize * (pageNumber - 1)) < pageSize; i++) { Document hitDoc = is.doc(hits[i].doc); field = hitDoc.getField("line"); Transcription t = new Transcription(Integer.parseInt(hitDoc.getField("id").stringValue())); results.add(t); String paragraph = field.stringValue(); String pageno = ""; String creator = hitDoc.getField("creator").stringValue(); user.User u = new User(Integer.parseInt(creator)); creator = "" + u.getLname() + " " + u.getFname(); if (isInteger(paragraph)) { field = hitDoc.getField("page"); pageno = field.stringValue(); if (pageno == null) { pageno = "hi null"; } if (paragraph == null) { paragraph = "hola null"; } } else { String folio = ""; Folio f = new Folio(Integer.parseInt(folio)); link = " <a href=transcriptionImageTest.jsp?p=" + folio + ">" + field.stringValue() + "(Archive:" + f.getArchive() + " Shelfmark:" + f.getCollectionName() + " page:" + folio + ")</a>"; } returnStringArray = returnStringArray + (ctr + ". " + link + "<br/>"); ctr++; } } else /*we dont have any results for the page/search they gave us*/ { returnStringArray = "No results to display."; } totalHits = hits.length; totalPages = hits.length / pageSize; if (hits.length % pageSize > 0) { totalPages++; } if (!wildcard) { return results; } else { return results; } }
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; }/* w ww .ja va 2 s . c om*/ 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:searcher.CollStat.java
String getSnippet(Query q, Document doc, int docid) throws Exception { StringBuffer buff = new StringBuffer(); SimpleHTMLFormatter htmlFormatter = new SimpleHTMLFormatter(); Highlighter highlighter = new Highlighter(htmlFormatter, new QueryScorer(q)); System.out.println("enterEd"); // Get the decompressed html String html = IndexHtmlToText.decompress(doc.getBinaryValue(WTDocument.WTDOC_FIELD_HTML).bytes); // Generate snippet... InputStream input = new ByteArrayInputStream(html.getBytes(StandardCharsets.UTF_8)); ContentHandler handler = new BodyContentHandler(-1); Metadata metadata = new Metadata(); new HtmlParser().parse(input, handler, metadata, new ParseContext()); String text = handler.toString(); TokenStream tokenStream = analyzer.tokenStream("dummy", new StringReader(text)); TextFragment[] frag = highlighter.getBestTextFragments(tokenStream, text, false, 5); for (int j = 0; j < frag.length; j++) { if ((frag[j] != null) && (frag[j].getScore() > 0)) { buff.append((frag[j].toString())); }//from w w w . java 2s .co m } String snippet = buff.toString(); String modifiedText = snippet; String pattern = "<(\\s*)[a-zA-Z0-9]+[^>]+$"; Pattern r = Pattern.compile(pattern); Matcher m = r.matcher(snippet); if (m.find()) { modifiedText = m.replaceAll(""); } snippet = modifiedText; return snippet; //byte[] encodedBytes = Base64.encodeBase64(snippet.getBytes()); //return new String(encodedBytes); }
From source file:servlet.Checkcopy.java
/** * Processes requests for both HTTP <code>GET</code> and <code>POST</code> * methods.//from w w w . jav a2 s .co m * * @param request servlet request * @param response servlet response * @throws ServletException if a servlet-specific error occurs * @throws IOException if an I/O error occurs */ protected void processRequest(HttpServletRequest request, HttpServletResponse response) throws ServletException, IOException { HttpSession ss = request.getSession(); Assignment a = (Assignment) ss.getAttribute("curAm"); int safv_id = Integer.parseInt(request.getParameter("safv_id")); String studentAmPath = getServletContext().getRealPath("/") + "/file/student_assignment_file/"; if (a.getAss_type().equalsIgnoreCase("file")) { StAssignmentFile sa = (StAssignmentFile) ss.getAttribute("sa"); StAmFileList f = StAmFileList.getSafvByListIdSafv(safv_id, sa.getList_id()); String filename = f.getPath_file(); String fileExtension = filename.substring(filename.lastIndexOf(".") + 1); String keyword = ""; if (fileExtension.equalsIgnoreCase("docx")) { keyword = DocumentFunction.readDocxFile(studentAmPath + filename); } else if (fileExtension.equalsIgnoreCase("doc")) { keyword = DocumentFunction.readDocFile(studentAmPath + filename); } else if (fileExtension.equalsIgnoreCase("xls")) { keyword = DocumentFunction.readXlsFile(studentAmPath + filename); } else if (fileExtension.equalsIgnoreCase("xlsx")) { keyword = DocumentFunction.readXlsxFile(studentAmPath + filename); } else if (fileExtension.equalsIgnoreCase("pdf")) { keyword = DocumentFunction.readPdfFile(studentAmPath + filename); } if (!keyword.equals("")) { System.out.println("----------------------search..."); Directory directory = null; IndexReader indexReader; ArrayList<String[]> indexsetList = null; try { directory = FSDirectory.open( new File(studentAmPath + "//" + a.getCourse().getCourse_id() + "//" + sa.getAm_id())); indexReader = DirectoryReader.open(directory); IndexSearcher searcher = new IndexSearcher(indexReader); BooleanQuery.setMaxClauseCount(20000); QueryParser parser = new QueryParser(Version.LUCENE_47, "student_assignment", new ThaiAnalyzer(Version.LUCENE_47)); Query query = parser.parse(QueryParser.escape(keyword)); int hitsPerPage = 10; Sort sort = new Sort(new SortField[] { SortField.FIELD_SCORE, new SortField("student_assignment", SortField.Type.STRING) }); TopFieldCollector topField = TopFieldCollector.create(sort, hitsPerPage, true, true, true, false); searcher.search(query, topField); TopDocs docs = topField.topDocs(); SimpleHTMLFormatter htmlFormatter = new SimpleHTMLFormatter("<font color=red>", "</font>"); Highlighter highlighter = new Highlighter(htmlFormatter, new QueryScorer(query)); indexsetList = new ArrayList<>(); for (int i = 0; i < docs.totalHits; i++) { String[] indexset = new String[5]; int id = docs.scoreDocs[i].doc; float score = docs.scoreDocs[i].score; Document doc = searcher.doc(id); String text = doc.get("student_assignment"); String st_am_id = doc.get("st_am_id"); String owner_safv_id = doc.get("safv_id"); // System.out.println(text); // System.out.println(st_am_id); // System.out.println(owner_safv_id); // System.out.println("-----------"); TokenStream tokenStream = TokenSources.getAnyTokenStream(searcher.getIndexReader(), id, "student_assignment", new ThaiAnalyzer(Version.LUCENE_47)); String[] hltextArr = highlighter.getBestFragments(tokenStream, text, hitsPerPage); String hltext = ""; for (String string : hltextArr) { hltext += string.toString() + "<br/>"; } indexset[0] = st_am_id; indexset[1] = hltext; //getting owner of StAmFileList file = StAmFileList.getSafvBySafv(Integer.parseInt(owner_safv_id)); if (file != null) { System.out.println((a.getAm_id() + " /" + file.getList_id())); StAssignmentFile stam = StAssignmentFile.getStAmBbyAmIDAndList(a.getAm_id(), file.getList_id()); String html = ""; //add ??? boolean add = true; if (stam.getG_id() == 0) { //if no group that mean it's a individual work if (sa.getAcc_id() != stam.getAcc_id()) { Account owneracc = Account.getNameByID(stam.getAcc_id()); html = "<img style=\"width:30px\" src=\"" + owneracc.getProfile_pic() + "\" data-toggle=\"tooltip\" data-placement=\"top\" title=\"\" class=\"img-circle\" data-original-title=\"" + owneracc.getFirstname() + "\">"; } else { add = false; } } else { if (sa.getG_id() != stam.getG_id()) { List<Account> ownerlist = Account.getNameByGIDandAmID(stam.getG_id(), stam.getAm_id()); html = "<a class=\"showGroup\" data-toggle=\"popover\" data-html=\"true\" data-content=\"" + Util.createPopoverGroup(ownerlist) + "\">Group no. " + Group_member.getGNOById(stam.getG_id()) + "</a>"; } else { add = false; } } indexset[2] = html; indexset[3] = score + ""; indexset[4] = owner_safv_id; if (add) { indexsetList.add(indexset); } } } } catch (IOException ex) { Logger.getLogger(TestDriver.class.getName()).log(Level.SEVERE, null, ex); } catch (ParseException ex) { Logger.getLogger(TestDriver.class.getName()).log(Level.SEVERE, null, ex); } catch (InvalidTokenOffsetsException ex) { Logger.getLogger(TestDriver.class.getName()).log(Level.SEVERE, null, ex); } // for (String[] strings : indexsetList) { // System.out.println(strings[0] + " : "+ strings[2] +" : " + strings[1] ); // } request.setAttribute("nowUUid", f.getUuid()); request.setAttribute("keyword", keyword); request.setAttribute("indexsetList", indexsetList); } else { request.setAttribute("error_msg", "This assignment cannot use for check copy."); } // System.out.println(keyword); getServletContext().getRequestDispatcher("/Checkcopy.jsp?tab=AllAssignment").forward(request, response); } }
From source file:suneido.runtime.builtin.Lucene.java
License:Open Source License
@Params("dir, query, limit, block") public static Object Search(Object self, Object a, Object b, Object c, Object d) { Path path = getPath(a);// w w w . ja v a 2 s. c om if (!path.toFile().exists()) throw dirNotFound("Search", path); String queryStr = Ops.toStr(b); int limit = Ops.toInt(c); try (FSDirectory dir = FSDirectory.open(getPath(a)); IndexReader ir = DirectoryReader.open(dir)) { IndexSearcher searcher = new IndexSearcher(ir); Analyzer analyzer = analyzer(); QueryParser parser = new QueryParser("content", analyzer); Query query = parser.parse(queryStr); TopDocs results = searcher.search(query, limit); SimpleHTMLFormatter htmlFormatter = new SimpleHTMLFormatter(); Highlighter highlighter = new Highlighter(htmlFormatter, new QueryScorer(query)); ScoreDoc[] hits = results.scoreDocs; for (ScoreDoc hit : hits) { int id = hit.doc; Document doc = ir.document(id); String key = doc.get("key"); String content = doc.get("content"); TokenStream tokenStream = analyzer.tokenStream("content", content); TextFragment[] frag = highlighter.getBestTextFragments(tokenStream, content, false, 4); SuObject fragments = new SuObject(); for (int j = 0; j < frag.length; j++) { if ((frag[j] != null) && (frag[j].getScore() > 0)) { fragments.add(frag[j].toString()); } } Ops.call2(d, key, fragments); } return null; } catch (Exception e) { throw new SuException("Lucene.Search: failed", e); } }
From source file:top.sj.lucene.LuceneSearchUtil.java
License:Open Source License
/** * ???//w ww . j a v a 2 s .com * * @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
/** * ??/*from ww w. j a v a 2s . 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; }