List of usage examples for org.apache.lucene.search.highlight Highlighter Highlighter
public Highlighter(Formatter formatter, Scorer fragmentScorer)
From source file:com.liferay.portal.search.lucene.LuceneHelperImpl.java
License:Open Source License
public String getSnippet(Query query, String field, String s, int maxNumFragments, int fragmentLength, String fragmentSuffix, String preTag, String postTag) throws IOException { SimpleHTMLFormatter simpleHTMLFormatter = new SimpleHTMLFormatter(preTag, postTag); QueryScorer queryScorer = new QueryScorer(query, field); Highlighter highlighter = new Highlighter(simpleHTMLFormatter, queryScorer); highlighter.setTextFragmenter(new SimpleFragmenter(fragmentLength)); TokenStream tokenStream = getAnalyzer().tokenStream(field, new UnsyncStringReader(s)); try {//from w w w. j a v a 2 s . c o m String snippet = highlighter.getBestFragments(tokenStream, s, maxNumFragments, fragmentSuffix); if (Validator.isNotNull(snippet) && !StringUtil.endsWith(snippet, fragmentSuffix)) { snippet = snippet.concat(fragmentSuffix); } return snippet; } catch (InvalidTokenOffsetsException itoe) { throw new IOException(itoe.getMessage()); } }
From source file:com.liferay.portal.search.lucene31.LuceneHelperImpl.java
License:Open Source License
public String getSnippet(Query query, String field, String s, int maxNumFragments, int fragmentLength, String fragmentSuffix, String preTag, String postTag) throws IOException { SimpleHTMLFormatter simpleHTMLFormatter = new SimpleHTMLFormatter(preTag, postTag); QueryScorer queryScorer = new QueryScorer(query, field); Highlighter highlighter = new Highlighter(simpleHTMLFormatter, queryScorer); highlighter.setTextFragmenter(new SimpleFragmenter(fragmentLength)); TokenStream tokenStream = getAnalyzer().tokenStream(field, new UnsyncStringReader(s)); try {/*from w w w.ja v a 2 s . c o m*/ String snippet = highlighter.getBestFragments(tokenStream, s, maxNumFragments, fragmentSuffix); if (Validator.isNotNull(snippet) && !StringUtil.endsWith(snippet, fragmentSuffix)) { snippet = snippet + fragmentSuffix; } return snippet; } catch (InvalidTokenOffsetsException itoe) { throw new IOException(itoe.getMessage()); } }
From source file:com.main.Searcher.java
public List<Bean> searching(String s1, String s2, String radioBtn) throws IOException, ParseException, InvalidTokenOffsetsException { //getting reference of directory Directory dir = FSDirectory.open(Paths.get(Index_Dir)); //Index reader - an interface for accessing a point-in-time view of a lucene index IndexReader reader = DirectoryReader.open(dir); IndexSearcher searcher = new IndexSearcher(reader); //analyzer with the default stop words, takes out the stop words Analyzer analyzer = new StandardAnalyzer(); String contents = "contents"; QueryParser parser = new QueryParser(contents, analyzer); int numOfDoc = reader.numDocs(); for (int i = 0; i < numOfDoc; i++) { Document d = reader.document(i); }/*from w w w . j ava2 s . co m*/ Query q1 = parser.parse(s1); Query q2 = parser.parse(s2); //conjuction, disjunction and negation BooleanQuery.Builder bq = new BooleanQuery.Builder(); //occur.must : both queries required in a doc if (radioBtn.equals("conjunction")) { bq.add(q1, BooleanClause.Occur.MUST); bq.add(q2, BooleanClause.Occur.MUST); bq.build(); } //occur.should: one of the q1 should be presen t in doc else if (radioBtn.equals("disjunction")) { bq.add(q1, BooleanClause.Occur.SHOULD); bq.add(q2, BooleanClause.Occur.SHOULD); bq.build(); } //negation: first should present , second should not else { bq.add(q1, BooleanClause.Occur.MUST); bq.add(q2, BooleanClause.Occur.MUST_NOT); bq.build(); } TopDocs hits = searcher.search(bq.build(), 10); Formatter formatter = new SimpleHTMLFormatter(); QueryScorer scorer = new QueryScorer(bq.build()); //used to markup highlighted terms found in the best sections of a cont Highlighter highlighter = new Highlighter(formatter, scorer); //It breaks cont up into same-size texts but does not split up spans Fragmenter fragmenter = new SimpleSpanFragmenter(scorer, 10); //breaks cont up into same-size fragments with no concerns over spotting sentence boundaries. //set fragmenter to highlighter highlighter.setTextFragmenter(fragmenter); for (int i = 0; i < hits.scoreDocs.length; i++) { Bean bean = new Bean(); int outResult = hits.scoreDocs.length; bean.setNumFile(outResult); int docid = hits.scoreDocs[i].doc; double rank = hits.scoreDocs[i].score; bean.setRankSc(rank); Document doc = searcher.doc(docid); String name = doc.get("name"); String title = doc.get("title"); bean.setTitle(name); String path = doc.get("path"); bean.setPath(path); String cont = doc.get("contents"); //Create token stream TokenStream stream = TokenSources.getAnyTokenStream(reader, docid, "contents", analyzer); //Get highlighted cont fragments String[] frags = highlighter.getBestFragments(stream, cont, 10); ArrayList<String> dummy = new ArrayList<>(); for (String frag : frags) { dummy.add(frag); } bean.setContent(dummy); beanList.add(bean); } dir.close(); // } return beanList; }
From source file:com.main.Searcher.java
public List<Bean> searching(String s1) throws IOException, ParseException, InvalidTokenOffsetsException { //Get directory reference Directory dir = FSDirectory.open(Paths.get(Index_Dir)); //Index reader - an interface for accessing a point-in-time view of a lucene index IndexReader reader = DirectoryReader.open(dir); //CreateIndexReader reader = DirectoryReader.open(dir); lucene searcher. It search over a single IndexReader. IndexSearcher searcher = new IndexSearcher(reader); //analyzer with the default stop words Analyzer analyzer = new StandardAnalyzer(); //Query parser to be used for creating TermQuery String queries = null;/*from ww w . j a va2 s . c o m*/ String queryString = null; //regular search String contents = "contents"; BufferedReader in = null; if (queries != null) { in = Files.newBufferedReader(Paths.get(queries), StandardCharsets.UTF_8); } else { in = new BufferedReader(new InputStreamReader(System.in, StandardCharsets.UTF_8)); } QueryParser parser = new QueryParser(contents, analyzer); int numOfDoc = reader.numDocs(); for (int i = 0; i < numOfDoc; i++) { Document d = reader.document(i); } Query q1 = parser.parse(s1); BooleanQuery.Builder bq = new BooleanQuery.Builder(); bq.add(q1, BooleanClause.Occur.MUST); //Search the lucene documents TopDocs hits = searcher.search(bq.build(), 10); // TopScoreDocCollector collector = TopScoreDocCollector.create(5); /** * Highlighter Code Start *** */ //Uses HTML <B></B> tag to highlight the searched terms Formatter formatter = new SimpleHTMLFormatter(); //It scores cont fragments by the number of unique q1 terms found //Basically the matching score in layman terms QueryScorer scorer = new QueryScorer(bq.build()); //used to markup highlighted terms found in the best sections of a cont Highlighter highlighter = new Highlighter(formatter, scorer); //It breaks cont up into same-size texts but does not split up spans Fragmenter fragmenter = new SimpleSpanFragmenter(scorer, 10); //breaks cont up into same-size fragments with no concerns over spotting sentence boundaries. //set fragmenter to highlighter highlighter.setTextFragmenter(fragmenter); //Iterate over found results for (int i = 0; i < hits.scoreDocs.length; i++) { Bean bean = new Bean(); //int rank = hits.scoreDocs.length; int outResult = hits.scoreDocs.length; bean.setNumFile(outResult); int docid = hits.scoreDocs[i].doc; double rank = hits.scoreDocs[i].score; bean.setRankSc(rank); Document doc = searcher.doc(docid); // String title = doc.get("title"); String name = doc.get("name"); String title = doc.get("title"); bean.setTitle(name); String path = doc.get("path"); bean.setPath(path); String cont = doc.get("contents"); //Create token stream TokenStream stream = TokenSources.getAnyTokenStream(reader, docid, "contents", analyzer); //Get highlighted cont fragments String[] frags = highlighter.getBestFragments(stream, cont, 10); ArrayList<String> dummy = new ArrayList<>(); for (String frag : frags) { dummy.add(frag); } bean.setContent(dummy); beanList.add(bean); } dir.close(); // } return beanList; }
From source file:com.mathworks.xzheng.tools.HighlightIt.java
License:Apache License
public static void main(String[] args) throws Exception { if (args.length != 1) { System.err.println("Usage: HighlightIt <filename-out>"); System.exit(-1);//from w w w . ja v a 2 s . co m } String filename = args[0]; String searchText = "term"; // #1 QueryParser parser = new QueryParser(Version.LUCENE_46, // #1 "f", // #1 new StandardAnalyzer(Version.LUCENE_46));// #1 Query query = parser.parse(searchText); // #1 SimpleHTMLFormatter formatter = // #2 new SimpleHTMLFormatter("<span class=\"highlight\">", // #2 "</span>"); // #2 TokenStream tokens = new StandardAnalyzer(Version.LUCENE_46) // #3 .tokenStream("f", new StringReader(text)); // #3 QueryScorer scorer = new QueryScorer(query, "f"); // #4 Highlighter highlighter = new Highlighter(formatter, scorer); // #5 highlighter.setTextFragmenter( // #6 new SimpleSpanFragmenter(scorer)); // #6 String result = // #7 highlighter.getBestFragments(tokens, text, 3, "..."); // #7 FileWriter writer = new FileWriter(filename); // #8 writer.write("<html>"); // #8 writer.write("<style>\n" + // #8 ".highlight {\n" + // #8 " background: yellow;\n" + // #8 "}\n" + // #8 "</style>"); // #8 writer.write("<body>"); // #8 writer.write(result); // #8 writer.write("</body></html>"); // #8 writer.close(); // #8 }
From source file:com.oneis.app.SearchResultExcerptHighlighter.java
License:Mozilla Public License
static public String[] bestHighlightedExcerpts(String escapedText, String searchTerms, int maxExcerptLength) { try {/*from w w w . jav a2 s.c om*/ // Scorer selects the terms which need highlighting. Created from a 'query' based on the extracted search terms. Scorer scorer; Fragmenter fragmenter; if (searchTerms != null && searchTerms.length() > 0) { QueryParser queryParser = new QueryParser("FIELD", new StandardAnalyzer()); Query query = queryParser.parse(searchTerms); scorer = new QueryScorer(query); fragmenter = new SimpleSpanFragmenter((QueryScorer) scorer, maxExcerptLength); } else { scorer = new NoHighlightingScorer(); fragmenter = new SimpleFragmenter(maxExcerptLength); } // Parse the escaped text into tokens, which retain the positions in the text StandardAnalyzer analyser = new StandardAnalyzer(); TokenStream tokenStream = analyser.tokenStream("FIELD", new StringReader(escapedText)); // Finally, do the highlighting! Highlighter highlighter = new Highlighter(new SimpleHTMLFormatter("<b>", "</b>"), scorer); highlighter.setTextFragmenter(fragmenter); return highlighter.getBestFragments(tokenStream, escapedText, NUMBER_OF_FRAGMENTS); } catch (Exception e) { Logger.getLogger("com.oneis.app").info("Exception in SearchResultExcerptHighlighter: ", e); return null; } }
From source file:com.paladin.common.Tools.java
License:Apache License
/** * ? /* ww w . j a va 2 s . c o m*/ * * @param _query * @param _field * @param _content * @return */ public static String highlight(final Query _query, final String _field, final String _content) { // Scorer scorer = new QueryScorer(_query); SimpleHTMLFormatter formatter = new SimpleHTMLFormatter(Constants.HIGHLIGHT_STYLE, "</span>"); Highlighter hl = new Highlighter(formatter, scorer); TokenStream tokens = new IKAnalyzer().tokenStream(_field, new StringReader(_content)); try { return hl.getBestFragment(tokens, _content); } catch (IOException e) { e.printStackTrace(); } catch (InvalidTokenOffsetsException e) { e.printStackTrace(); } return null; }
From source file:com.rapidminer.search.GlobalSearchHandler.java
License:Open Source License
/** * Creates the search result for search methods. * * @param searchTerm//from ww w .j a va 2s.c o m * the search string * @param searcher * the index searcher instance which was used to search * @param result * the result of the search * @param highlightResult * if {@code true}, the {@link GlobalSearchResult#getBestFragments()} will be created * @return the search result instance, never {@code null} * @throws IOException * if something goes wrong */ private GlobalSearchResult createSearchResult(final String searchTerm, final Query parsedQuery, final IndexSearcher searcher, final TopDocs result, final boolean highlightResult) throws IOException { int resultNumber = result.scoreDocs.length; List<Document> resultList = new ArrayList<>(resultNumber); List<String[]> highlights = highlightResult ? new LinkedList<>() : null; ScoreDoc lastResult = resultNumber > 0 ? result.scoreDocs[result.scoreDocs.length - 1] : null; for (ScoreDoc scoreDoc : result.scoreDocs) { Document doc = searcher.doc(scoreDoc.doc); resultList.add(doc); if (highlightResult) { // search result highlighting best match on name field QueryScorer scorer = new QueryScorer(parsedQuery); Highlighter highlighter = new Highlighter(HIGHLIGHT_FORMATTER, scorer); Fragmenter fragmenter = new SimpleSpanFragmenter(scorer, FRAGMENT_SIZE); highlighter.setTextFragmenter(fragmenter); try { TokenStream stream = TokenSources.getTokenStream(GlobalSearchUtilities.FIELD_NAME, searcher.getIndexReader().getTermVectors(scoreDoc.doc), doc.get(GlobalSearchUtilities.FIELD_NAME), GlobalSearchUtilities.ANALYZER, Highlighter.DEFAULT_MAX_CHARS_TO_ANALYZE - 1); if (stream != null) { highlights.add(highlighter.getBestFragments(stream, doc.get(GlobalSearchUtilities.FIELD_NAME), MAX_NUMBER_OF_FRAGMENTS)); } else { highlights.add(null); } } catch (InvalidTokenOffsetsException e) { highlights.add(null); } } } return new GlobalSearchResult(resultList, searchTerm, lastResult, result.totalHits, highlights); }
From source file:com.recomdata.search.Finder.java
License:Open Source License
private void display(Document doc, int id, float score, Query query, Analyzer analyzer) { System.out.println("repository = " + doc.get("repository")); System.out.println("path = " + doc.get("path")); System.out.println("extension = " + doc.get("extension")); System.out.println("title = " + doc.get("title")); Highlighter highlighter = new Highlighter(new SimpleHTMLFormatter("<b>", "</b>"), new QueryScorer(query, "contents")); highlighter.setTextFragmenter(new SimpleFragmenter(50)); String summary = doc.get("contents"); TokenStream tokenStream = analyzer.tokenStream("contents", new StringReader(summary)); try {// w ww. java2s . c o m System.out.println("contents = " + highlighter.getBestFragments(tokenStream, summary, 5, "...")); } catch (IOException e) { System.out.println("exception: " + e.getMessage()); } System.out.println(); }
From source file:com.searchlocal.lucene.ContentSearcher.java
License:Open Source License
/** * ? /*from w ww . jav a2 s .c om*/ * * @param param ? * @param indexlocal ? * @return list */ public static List<ResultBean> query(SearchParam param) throws IOException, LogicException { // ? String indexPath = param.getIndexPath(); // if (null == fsd) { fsd = SimpleFSDirectory.open(new File(indexPath)); } List<ResultBean> beanList = new ArrayList<ResultBean>(); try { // ?KeyWord Analyzer analyzer = new PaodingAnalyzer(); QueryParser parser = new QueryParser(Version.LUCENE_CURRENT, "content", analyzer); Query query; query = parser.parse(param.getKeyWord()); TopScoreDocCollector collector = TopScoreDocCollector.create(100, true); // ? if (null == is) { is = new IndexSearcher(fsd, true); } is.search(query, collector); ScoreDoc[] scoreDoc = collector.topDocs().scoreDocs; SimpleHTMLFormatter simpleHTMLFormatter = new SimpleHTMLFormatter("<font color=\"red\">", "</font>"); Highlighter highlighter = new Highlighter(simpleHTMLFormatter, new QueryScorer(query)); highlighter.setTextFragmenter(new SimpleFragmenter(CONTENTS_SHOW_LENGTH)); if (scoreDoc.length == 0) { return beanList; } int startRow = param.getStartRow(); int endRow = param.getEndRow(); endRow = scoreDoc.length > endRow ? endRow : scoreDoc.length; for (int i = startRow; i < endRow; i++) { Document doc = is.doc(scoreDoc[i].doc); String content = doc.get("content"); // TokenStream tokenStream = analyzer.tokenStream("content", new StringReader(content)); content = highlighter.getBestFragment(tokenStream, content); ResultBean bean = BeanUtil.getBean(doc, content); beanList.add(bean); } } catch (IOException e) { // TODO Auto-generated catch block e.printStackTrace(); } catch (InvalidTokenOffsetsException e) { // TODO Auto-generated catch block e.printStackTrace(); } catch (ParseException e) { e.printStackTrace(); } return beanList; }