Package org.apache.lucene.search.spans

Examples of org.apache.lucene.search.spans.SpanQuery

260
261
262
263
264
265
266
267
268
269
270
      clauses[1] = q2;
      return clauses;
  }
  private SpanNearQuery spanNearQuery(String fieldName, String words) {
    String[] wordList = words.split("[\\s]+");
    SpanQuery clauses[] = new SpanQuery[wordList.length];
    for (int i=0;i<clauses.length;i++) {
      clauses[i] = new PayloadTermQuery(new Term(fieldName, wordList[i]), new AveragePayloadFunction()); 
    }
    return new SpanNearQuery(clauses, 10000, false);
  }
View Full Code Here
287
288
289
290
291
292
293
294
295
296
297
298
299
300
    PayloadNearQuery query;
    TopDocs hits;

    // combine ordered and unordered spans with some nesting to make sure all payloads are counted

    SpanQuery q1 = newPhraseQuery("field", "nine hundred", true, new AveragePayloadFunction());
    SpanQuery q2 = newPhraseQuery("field", "ninety nine", true, new AveragePayloadFunction());
    SpanQuery q3 = newPhraseQuery("field", "nine ninety", false, new AveragePayloadFunction());
    SpanQuery q4 = newPhraseQuery("field", "hundred nine", false, new AveragePayloadFunction());
    SpanQuery[]clauses = new SpanQuery[] {new PayloadNearQuery(new SpanQuery[] {q1,q2}, 0, true), new PayloadNearQuery(new SpanQuery[] {q3,q4}, 0, false)};
    query = new PayloadNearQuery(clauses, 0, false);
    hits = searcher.search(query, null, 100);
    assertTrue("hits is null and it shouldn't be", hits != null);
    // should be only 1 hit - doc 999
View Full Code Here
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
    Set<Term> nonWeightedTerms = new HashSet<Term>();
    final boolean mustRewriteQuery = mustRewriteQuery(spanQuery);
    if (mustRewriteQuery) {
      for (final String field : fieldNames) {
        final SpanQuery rewrittenQuery = (SpanQuery) spanQuery.rewrite(getLeafContext().reader());
        queries.put(field, rewrittenQuery);
        rewrittenQuery.extractTerms(nonWeightedTerms);
      }
    } else {
      spanQuery.extractTerms(nonWeightedTerms);
    }

    List<PositionSpan> spanPositions = new ArrayList<PositionSpan>();

    for (final String field : fieldNames) {
      final SpanQuery q;
      if (mustRewriteQuery) {
        q = queries.get(field);
      } else {
        q = spanQuery;
      }
      AtomicReaderContext context = getLeafContext();
      Map<Term,TermContext> termContexts = new HashMap<Term,TermContext>();
      TreeSet<Term> extractedTerms = new TreeSet<Term>();
      q.extractTerms(extractedTerms);
      for (Term term : extractedTerms) {
        termContexts.put(term, TermContext.build(context, term, true));
      }
      Bits acceptDocs = context.reader().getLiveDocs();
      final Spans spans = q.getSpans(context, acceptDocs, termContexts);

      // collect span positions
      while (spans.next()) {
        spanPositions.add(new PositionSpan(spans.start(), spans.end() - 1));
      }
View Full Code Here
337
338
339
340
341
342
343
344
345
346
347
  }

  // LUCENE-3831
  public void testNullPointerException() throws IOException {
    RegexpQuery regex = new RegexpQuery(new Term("field", "worl."));
    SpanQuery wrappedquery = new SpanMultiTermQueryWrapper<RegexpQuery>(regex);
       
    MemoryIndex mindex = new MemoryIndex(random().nextBoolean(),  random().nextInt(50) * 1024 * 1024);
    mindex.addField("field", new MockAnalyzer(random()).tokenStream("field", new StringReader("hello there")));

    // This throws an NPE
View Full Code Here
349
350
351
352
353
354
355
356
357
358
359
  }
   
  // LUCENE-3831
  public void testPassesIfWrapped() throws IOException {
    RegexpQuery regex = new RegexpQuery(new Term("field", "worl."));
    SpanQuery wrappedquery = new SpanOrQuery(new SpanMultiTermQueryWrapper<RegexpQuery>(regex));

    MemoryIndex mindex = new MemoryIndex(random().nextBoolean(),  random().nextInt(50) * 1024 * 1024);
    mindex.addField("field", new MockAnalyzer(random()).tokenStream("field", new StringReader("hello there")));

    // This passes though
View Full Code Here
293
294
295
296
297
298
299
300
301
302
303
      }

      SpanQuery[] includeClauses = positiveClauses
          .toArray(new SpanQuery[positiveClauses.size()]);

      SpanQuery include = null;
      if (includeClauses.length == 1) {
        include = includeClauses[0]; // only one positive clause
      } else {
        // need to increase slop factor based on gaps introduced by
        // negatives
View Full Code Here
308
309
310
311
312
313
314
315
316
317
318
319
    IndexReader indexReader = DirectoryReader.open(directory);
    IndexSearcher searcher = new IndexSearcher(indexReader);

    BooleanQuery query = new BooleanQuery();
    SpanQuery sq1 = new SpanTermQuery(new Term(FIELD, "clockwork"));
    SpanQuery sq2 = new SpanTermQuery(new Term(FIELD, "clckwork"));
    query.add(sq1, BooleanClause.Occur.SHOULD);
    query.add(sq2, BooleanClause.Occur.SHOULD);
    TopScoreDocCollector collector = TopScoreDocCollector.create(1000, true);
    searcher.search(query, collector);
    hits = collector.topDocs().scoreDocs.length;
View Full Code Here
68
69
70
71
72
73
74
75
76
77
78
    writer.forceMerge(1);
    writer.close();

    IndexReader reader = DirectoryReader.open(directory);
    IndexSearcher searcher = new IndexSearcher(reader);
    SpanQuery srq = new SpanMultiTermQueryWrapper<RegexQuery>(new RegexQuery(new Term("field", "aut.*")));
    SpanFirstQuery sfq = new SpanFirstQuery(srq, 1);
    // SpanNearQuery query = new SpanNearQuery(new SpanQuery[] {srq, stq}, 6,
    // true);
    int numHits = searcher.search(sfq, null, 1000).totalHits;
    assertEquals(1, numHits);
View Full Code Here
637
638
639
640
641
642
643
644
645
646
647
      @Override
      protected Analyzer getIndexAnalyzer(String field) {
        return analyzer;
      }
    };
    SpanQuery childQuery = new SpanMultiTermQueryWrapper<>(new WildcardQuery(new Term("body", "te*")));
    Query query = new SpanOrQuery(new SpanQuery[] { childQuery });
    TopDocs topDocs = searcher.search(query, null, 10, Sort.INDEXORDER);
    assertEquals(2, topDocs.totalHits);
    String snippets[] = highlighter.highlight("body", query, searcher, topDocs);
    assertEquals(2, snippets.length);
View Full Code Here
679
680
681
682
683
684
685
686
687
688
689
      @Override
      protected Analyzer getIndexAnalyzer(String field) {
        return analyzer;
      }
    };
    SpanQuery childQuery = new SpanMultiTermQueryWrapper<>(new WildcardQuery(new Term("body", "te*")));
    Query query = new SpanNearQuery(new SpanQuery[] { childQuery }, 0, true);
    TopDocs topDocs = searcher.search(query, null, 10, Sort.INDEXORDER);
    assertEquals(2, topDocs.totalHits);
    String snippets[] = highlighter.highlight("body", query, searcher, topDocs);
    assertEquals(2, snippets.length);
View Full Code Here
TOP

Related Classes of org.apache.lucene.search.spans.SpanQuery

  • com.senseidb.search.query.SpanFirstQueryConstructor
  • com.senseidb.search.query.SpanNotQueryConstructor
  • com.tamingtext.qa.PassageRankingComponent
  • org.apache.lucene.index.memory.MemoryIndexTest
  • org.apache.lucene.queryparser.complexPhrase.ComplexPhraseQueryParser$ComplexPhraseQuery
  • org.apache.lucene.queryParser.complexPhrase.ComplexPhraseQueryParser$ComplexPhraseQuery
  • org.apache.lucene.queryparser.flexible.spans.TestSpanQueryParserSimpleSample
  • org.apache.lucene.queryParser.spans.TestSpanQueryParserSimpleSample
  • org.apache.lucene.queryParser.surround.query.SpanNearClauseFactory
  • org.apache.lucene.queryparser.surround.query.SpanNearClauseFactory
    • Copyright © 2018 www.massapicom. All rights reserved.
    All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.