List of usage examples for org.apache.lucene.search IndexSearcher doc
public Document doc(int docID) throws IOException
.getIndexReader().document(docID) From source file:com.knowgate.lucene.NewsMessageSearcher.java
License:Open Source License
/** * Compose a Lucene query based on given parameters * @param sLuceneIndexPath String Base path for Lucene indexes excluding WorkArea and table name * @param sWorkArea String GUID of WorkArea to be searched, cannot be null * @param sGroup sNewsGroupCategoryName String GUID or Category Name of NewsGroup to which message belongs (optional, may be null) * @param sAuthor String//from ww w . j ava 2s .c o m * @param sTitle String * @param sText String * @param iLimit int * @param oSortBy Comparator * @return NewsMessageRecord[] An Array of NewsMessageRecord objects or <b>null</b> if no messages where found matching the given criteria * @throws ParseException * @throws IOException * @throws NullPointerException */ public static NewsMessageRecord[] search(String sLuceneIndexPath, String sWorkArea, String sNewsGroupCategoryName, String sAuthor, String sTitle, Date dtFromDate, Date dtToDate, String sText, int iLimit, Comparator oSortBy) throws ParseException, IOException, NullPointerException { if (null == sLuceneIndexPath) throw new NullPointerException("NewsMessageSearcher.search() luceneindex parameter cannot be null"); if (null == sWorkArea) throw new NullPointerException("NewsMessageSearcher.search() workarea parameter cannot be null"); if (DebugFile.trace) { DebugFile.writeln("Begin NewsMessageSearcher.search(" + sLuceneIndexPath + "," + sWorkArea + "," + sNewsGroupCategoryName + "," + sAuthor + "," + sTitle + "," + dtFromDate + "," + dtToDate + "," + sText + "," + String.valueOf(iLimit) + ")"); DebugFile.incIdent(); } NewsMessageRecord[] aRetArr; BooleanQuery oQrx = new BooleanQuery(); oQrx.add(new TermQuery(new Term("workarea", sWorkArea)), BooleanClause.Occur.MUST); if (null != sNewsGroupCategoryName) oQrx.add(new TermQuery(new Term("container", sNewsGroupCategoryName)), BooleanClause.Occur.MUST); if (dtFromDate != null && dtToDate != null) oQrx.add( new TermRangeQuery("created", DateTools.dateToString(dtFromDate, DateTools.Resolution.DAY), DateTools.dateToString(dtToDate, DateTools.Resolution.DAY), true, true), BooleanClause.Occur.MUST); else if (dtFromDate != null) oQrx.add(new TermRangeQuery("created", DateTools.dateToString(dtFromDate, DateTools.Resolution.DAY), null, true, false), BooleanClause.Occur.MUST); else if (dtToDate != null) oQrx.add(new TermRangeQuery("created", null, DateTools.dateToString(dtToDate, DateTools.Resolution.DAY), false, true), BooleanClause.Occur.MUST); BooleanQuery oQry = new BooleanQuery(); if (null != sAuthor) oQry.add(new TermQuery(new Term("author", sAuthor)), BooleanClause.Occur.SHOULD); if (null != sTitle) oQry.add(new TermQuery(new Term("title", sTitle)), BooleanClause.Occur.SHOULD); if (null != sText) oQry.add(new TermQuery(new Term("text", escape(Gadgets.ASCIIEncode(sText).toLowerCase()))), BooleanClause.Occur.SHOULD); oQrx.add(oQry, BooleanClause.Occur.MUST); String sSegments = Gadgets.chomp(sLuceneIndexPath, File.separator) + "k_newsmsgs" + File.separator + sWorkArea; if (DebugFile.trace) DebugFile.writeln("new IndexSearcher(" + sSegments + ")"); Directory oDir = Indexer.openDirectory(sSegments); IndexSearcher oSearch = new IndexSearcher(oDir); Document oDoc; if (DebugFile.trace) DebugFile.writeln("IndexSearcher.search(" + oQrx.toString() + ")"); TopDocs oTopSet = oSearch.search(oQrx, null, iLimit > 0 ? iLimit : 2147483647); if (oTopSet.scoreDocs != null) { ScoreDoc[] oTopDoc = oTopSet.scoreDocs; final int iDocCount = oTopDoc.length <= iLimit ? oTopDoc.length : iLimit; aRetArr = new NewsMessageRecord[iDocCount]; for (int d = 0; d < iDocCount; d++) { oDoc = oSearch.doc(oTopDoc[d].doc); try { aRetArr[d] = new NewsMessageRecord(oTopDoc[d].score, oDoc.get("workarea"), oDoc.get("guid"), oDoc.get("thread"), oDoc.get("container"), oDoc.get("title"), oDoc.get("author"), DateTools.stringToDate(oDoc.get("created")), oDoc.get("abstract")); } catch (java.text.ParseException neverthrown) { throw new ParseException("NewsMessageSearcher.search() Error parsing date " + oDoc.get("created") + " of document " + oDoc.get("guid")); } } // next } else { aRetArr = null; } oSearch.close(); oDir.close(); if (oSortBy != null) { Arrays.sort(aRetArr, oSortBy); } if (DebugFile.trace) { DebugFile.decIdent(); if (null == aRetArr) DebugFile.writeln("End NewsMessageSearcher.search() : no records found"); else DebugFile.writeln("End NewsMessageSearcher.search() : " + String.valueOf(aRetArr.length)); } return aRetArr; }
From source file:com.leavesfly.lia.advsearching.SortingExample.java
License:Apache License
public void displayResults(Query query, Sort sort) // #1 throws IOException { IndexSearcher searcher = new IndexSearcher(directory); searcher.setDefaultFieldSortScoring(true, false); // #2 TopDocs results = searcher.search(query, null, // #3 20, sort); // #3 System.out.println("\nResults for: " + // #4 query.toString() + " sorted by " + sort); System.out.println(StringUtils.rightPad("Title", 30) + StringUtils.rightPad("pubmonth", 10) + StringUtils.center("id", 4) + StringUtils.center("score", 15)); PrintStream out = new PrintStream(System.out, true, "UTF-8"); // #5 DecimalFormat scoreFormatter = new DecimalFormat("0.######"); for (ScoreDoc sd : results.scoreDocs) { int docID = sd.doc; float score = sd.score; Document doc = searcher.doc(docID); out.println(StringUtils.rightPad( // #6 StringUtils.abbreviate(doc.get("title"), 29), 30) + // #6 StringUtils.rightPad(doc.get("pubmonth"), 10) + // #6 StringUtils.center("" + docID, 4) + // #6 StringUtils.leftPad( // #6 scoreFormatter.format(score), 12)); // #6 out.println(" " + doc.get("category")); // out.println(searcher.explain(query, docID)); // #7 }//from www . jav a 2s .c om searcher.close(); }
From source file:com.leavesfly.lia.commom.TestUtil.java
License:Apache License
public static boolean hitsIncludeTitle(IndexSearcher searcher, TopDocs hits, String title) throws IOException { for (ScoreDoc match : hits.scoreDocs) { Document doc = searcher.doc(match.doc); if (title.equals(doc.get("title"))) { return true; }//from w w w . jav a 2 s.co m } System.out.println("title '" + title + "' not found"); return false; }
From source file:com.leavesfly.lia.commom.TestUtil.java
License:Apache License
public static void dumpHits(IndexSearcher searcher, TopDocs hits) throws IOException { if (hits.totalHits == 0) { System.out.println("No hits"); }/*from w w w .j av a 2s. c om*/ for (ScoreDoc match : hits.scoreDocs) { Document doc = searcher.doc(match.doc); System.out.println(match.score + ":" + doc.get("title")); } }
From source file:com.leavesfly.lia.extsearch.payloads.PayloadsTest.java
License:Apache License
public void testPayloadTermQuery() throws Throwable { addDoc("Hurricane warning", "Bulletin: A hurricane warning was issued at " + "6 AM for the outer great banks"); addDoc("Warning label maker", "The warning label maker is a delightful toy for " + "your precocious seven year old's warning needs"); addDoc("Tornado warning", "Bulletin: There is a tornado warning for " + "Worcester county until 6 PM today"); IndexReader r = writer.getReader();/*from w ww .j av a 2 s . c o m*/ writer.close(); IndexSearcher searcher = new IndexSearcher(r); searcher.setSimilarity(new BoostingSimilarity()); Term warning = new Term("contents", "warning"); Query query1 = new TermQuery(warning); System.out.println("\nTermQuery results:"); TopDocs hits = searcher.search(query1, 10); TestUtil.dumpHits(searcher, hits); assertEquals("Warning label maker", // #B searcher.doc(hits.scoreDocs[0].doc).get("title")); // #B Query query2 = new PayloadTermQuery(warning, new AveragePayloadFunction()); System.out.println("\nPayloadTermQuery results:"); hits = searcher.search(query2, 10); TestUtil.dumpHits(searcher, hits); assertEquals("Warning label maker", // #C searcher.doc(hits.scoreDocs[2].doc).get("title")); // #C r.close(); searcher.close(); }
From source file:com.leavesfly.lia.meetlucene.Searcher.java
License:Apache License
public static void search(String indexDir, String q) throws IOException, ParseException { Directory dir = FSDirectory.open(new File(indexDir)); //3 IndexSearcher is = new IndexSearcher(dir); //3 QueryParser parser = new QueryParser(Version.LUCENE_30, // 4 "contents", //4 new StandardAnalyzer( //4 Version.LUCENE_30)); //4 Query query = parser.parse(q); //4 long start = System.currentTimeMillis(); TopDocs hits = is.search(query, 10); //5 long end = System.currentTimeMillis(); System.err.println("Found " + hits.totalHits + //6 " document(s) (in " + (end - start) + // 6 " milliseconds) that matched query '" + // 6 q + "':"); // 6 for (ScoreDoc scoreDoc : hits.scoreDocs) { Document doc = is.doc(scoreDoc.doc); //7 System.out.println(doc.get("fullpath")); //8 }//from ww w .j av a2s. com is.close(); //9 }
From source file:com.leavesfly.lia.searching.BasicSearchingTest.java
License:Apache License
public void testQueryParser() throws Exception { Directory dir = TestUtil.getBookIndexDirectory(); IndexSearcher searcher = new IndexSearcher(dir); QueryParser parser = new QueryParser(Version.LUCENE_30, //A "contents", //A new SimpleAnalyzer()); //A Query query = parser.parse("+JUNIT +ANT -MOCK"); //B TopDocs docs = searcher.search(query, 10); assertEquals(1, docs.totalHits);/*from w ww . j a v a 2 s. c om*/ Document d = searcher.doc(docs.scoreDocs[0].doc); assertEquals("Ant in Action", d.get("title")); query = parser.parse("mock OR junit"); //B docs = searcher.search(query, 10); assertEquals("Ant in Action, " + "JUnit in Action, Second Edition", 2, docs.totalHits); searcher.close(); dir.close(); }
From source file:com.leavesfly.lia.searching.Explainer.java
License:Apache License
public static void main(String[] args) throws Exception { if (args.length != 2) { System.err.println("Usage: Explainer <index dir> <query>"); System.exit(1);//w w w. j a v a 2 s . co m } String indexDir = args[0]; String queryExpression = args[1]; Directory directory = FSDirectory.open(new File(indexDir)); QueryParser parser = new QueryParser(Version.LUCENE_30, "contents", new SimpleAnalyzer()); Query query = parser.parse(queryExpression); System.out.println("Query: " + queryExpression); IndexSearcher searcher = new IndexSearcher(directory); TopDocs topDocs = searcher.search(query, 10); for (ScoreDoc match : topDocs.scoreDocs) { Explanation explanation = searcher.explain(query, match.doc); //#A System.out.println("----------"); Document doc = searcher.doc(match.doc); System.out.println(doc.get("title")); System.out.println(explanation.toString()); //#B } searcher.close(); directory.close(); }
From source file:com.leavesfly.lia.tool.HighlightTest.java
License:Apache License
public void testHits() throws Exception { IndexSearcher searcher = new IndexSearcher(TestUtil.getBookIndexDirectory()); TermQuery query = new TermQuery(new Term("title", "action")); TopDocs hits = searcher.search(query, 10); QueryScorer scorer = new QueryScorer(query, "title"); Highlighter highlighter = new Highlighter(scorer); highlighter.setTextFragmenter(new SimpleSpanFragmenter(scorer)); Analyzer analyzer = new SimpleAnalyzer(); for (ScoreDoc sd : hits.scoreDocs) { Document doc = searcher.doc(sd.doc); String title = doc.get("title"); TokenStream stream = TokenSources.getAnyTokenStream(searcher.getIndexReader(), sd.doc, "title", doc, analyzer);//ww w . j a v a2 s . co m String fragment = highlighter.getBestFragment(stream, title); System.out.println(fragment); } }
From source file:com.leavesfly.lia.tool.SpatialLuceneExample.java
License:Apache License
public void findNear(String what, double latitude, double longitude, double radius) throws CorruptIndexException, IOException { IndexSearcher searcher = new IndexSearcher(directory); DistanceQueryBuilder dq;/* w ww .ja v a 2 s. co m*/ dq = new DistanceQueryBuilder(latitude, // #A longitude, // #A radius, // #A latField, // #A lngField, // #A tierPrefix, // #A true); // #A Query tq; if (what == null) tq = new TermQuery(new Term("metafile", "doc")); // #B else tq = new TermQuery(new Term("name", what)); DistanceFieldComparatorSource dsort; // #C dsort = new DistanceFieldComparatorSource( // #C dq.getDistanceFilter()); // #C Sort sort = new Sort(new SortField("foo", dsort)); // #C TopDocs hits = searcher.search(tq, dq.getFilter(), 10, sort); Map<Integer, Double> distances = // #D dq.getDistanceFilter().getDistances(); // #D System.out.println("Number of results: " + hits.totalHits); System.out.println("Found:"); for (ScoreDoc sd : hits.scoreDocs) { int docID = sd.doc; Document d = searcher.doc(docID); String name = d.get("name"); double rsLat = NumericUtils.prefixCodedToDouble(d.get(latField)); double rsLng = NumericUtils.prefixCodedToDouble(d.get(lngField)); Double geo_distance = distances.get(docID); System.out.printf(name + ": %.2f Miles\n", geo_distance); System.out.println("\t\t(" + rsLat + "," + rsLng + ")"); } }