Package org.apache.lucene.search

Examples of org.apache.lucene.search.TopDocs

133
134
135
136
137
138
139
140
141
142
143
    flt.addTerms("fernando smith", "name", 0.3f, 1);
    Query q = flt.rewrite(searcher.getIndexReader());
    HashSet<Term> queryTerms = new HashSet<Term>();
    q.extractTerms(queryTerms);
    assertTrue("Should have variant smith", queryTerms.contains(new Term("name", "smith")));
    TopDocs topDocs = searcher.search(flt, 1);
    ScoreDoc[] sd = topDocs.scoreDocs;
    assertTrue("score docs must match 1 doc", (sd != null) && (sd.length > 0));
    Document doc = searcher.doc(sd[0].doc);
    assertEquals("Should match most similar when using 2 words", "2", doc.get("id"));
  }
View Full Code Here
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
          Math.min(BooleanQuery.getMaxClauseCount(), terms.size()));
      BooleanQuery bq = new BooleanQuery();
      for (int j = 0; j < numTerms; j++) {
        bq.add(new BooleanClause(new TermQuery(terms.get(j)), Occur.SHOULD));
      }
      TopDocs queryResult = searcher.search(new ConstantScoreQuery(bq), reader.maxDoc());
     
      MatchAllDocsQuery matchAll = new MatchAllDocsQuery();
      final TermsFilter filter = termsFilter(singleField, terms.subList(0, numTerms));;
      TopDocs filterResult = searcher.search(matchAll, filter, reader.maxDoc());
      assertEquals(filterResult.totalHits, queryResult.totalHits);
      ScoreDoc[] scoreDocs = filterResult.scoreDocs;
      for (int j = 0; j < scoreDocs.length; j++) {
        assertEquals(scoreDocs[j].doc, queryResult.scoreDocs[j].doc);
      }
View Full Code Here
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
        for(ScoreDoc sd : shardGroupDocs.scoreDocs) {
          System.out.println("      doc=" + sd.doc);
        }
        */

        shardTopDocs[shardIDX] = new TopDocs(shardGroupDocs.totalHits,
                                             shardGroupDocs.scoreDocs,
                                             shardGroupDocs.maxScore);
        maxScore = Math.max(maxScore, shardGroupDocs.maxScore);
        totalHits += shardGroupDocs.totalHits;
        scoreSum += shardGroupDocs.score;
      }

      final TopDocs mergedTopDocs = TopDocs.merge(docSort, docOffset + docTopN, shardTopDocs);

      // Slice;
      final ScoreDoc[] mergedScoreDocs;
      if (docOffset == 0) {
        mergedScoreDocs = mergedTopDocs.scoreDocs;
View Full Code Here
118
119
120
121
122
123
124
125
126
127
128
      int pqSize = Integer.parseInt(params[2]);
      float minScore = Float.parseFloat(params[3]);
      SlowFuzzyQuery q = new SlowFuzzyQuery(new Term("field", query), minScore, prefix);
      q.setRewriteMethod(new MultiTermQuery.TopTermsBoostOnlyBooleanQueryRewrite(pqSize));
      int expectedResults = Integer.parseInt(reader.readLine());
      TopDocs docs = searcher.search(q, expectedResults);
      assertEquals(expectedResults, docs.totalHits);
      for (int i = 0; i < expectedResults; i++) {
        String scoreDoc[] = reader.readLine().split(",");
        assertEquals(Integer.parseInt(scoreDoc[0]), docs.scoreDocs[i].doc);
        assertEquals(Float.parseFloat(scoreDoc[1]), docs.scoreDocs[i].score, epsilon);
View Full Code Here
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
      query.add(new Term("field", "this"));
      query.add(new Term("field", "end"));
      query.add(new Term("field", "world"));
      query.add(new Term("field", "universe"));
      query.add(new Term("field", "right"));
      TopDocs search = s.search(query, 10);
      assertEquals(search.totalHits, 3);
      assertEquals("0", r.document(search.scoreDocs[0].doc).get("id"));
      assertEquals("2", r.document(search.scoreDocs[1].doc).get("id"));
      assertEquals("3", r.document(search.scoreDocs[2].doc).get("id"));
    }
   
    { // only high freq
      CommonTermsQuery query = new CommonTermsQuery(Occur.SHOULD, Occur.SHOULD,
          random().nextBoolean() ? 2.0f : 0.5f);
      query.add(new Term("field", "is"));
      query.add(new Term("field", "this"));
      query.add(new Term("field", "end"));
      TopDocs search = s.search(query, 10);
      assertEquals(search.totalHits, 2);
      assertEquals("0", r.document(search.scoreDocs[0].doc).get("id"));
      assertEquals("2", r.document(search.scoreDocs[1].doc).get("id"));
    }
   
    { // low freq is mandatory
      CommonTermsQuery query = new CommonTermsQuery(Occur.SHOULD, Occur.MUST,
          random().nextBoolean() ? 2.0f : 0.5f);
      query.add(new Term("field", "is"));
      query.add(new Term("field", "this"));
      query.add(new Term("field", "end"));
      query.add(new Term("field", "world"));
     
      TopDocs search = s.search(query, 10);
      assertEquals(search.totalHits, 1);
      assertEquals("0", r.document(search.scoreDocs[0].doc).get("id"));
    }
   
    { // low freq is mandatory
      CommonTermsQuery query = new CommonTermsQuery(Occur.SHOULD, Occur.MUST,
          random().nextBoolean() ? 2.0f : 0.5f);
      query.add(new Term("field", "restaurant"));
      query.add(new Term("field", "universe"));
     
      TopDocs search = s.search(query, 10);
      assertEquals(search.totalHits, 1);
      assertEquals("3", r.document(search.scoreDocs[0].doc).get("id"));
     
    }
    r.close();
View Full Code Here
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
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
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
      query.add(new Term("field", "end"));
      query.add(new Term("field", "world"));
      query.add(new Term("field", "universe"));
      query.add(new Term("field", "right"));
      query.setLowFreqMinimumNumberShouldMatch(0.5f);
      TopDocs search = s.search(query, 10);
      assertEquals(search.totalHits, 1);
      assertEquals("0", r.document(search.scoreDocs[0].doc).get("id"));
    }
    {
      CommonTermsQuery query = new CommonTermsQuery(Occur.SHOULD, Occur.SHOULD,
          random().nextBoolean() ? 2.0f : 0.5f);
      query.add(new Term("field", "is"));
      query.add(new Term("field", "this"));
      query.add(new Term("field", "end"));
      query.add(new Term("field", "world"));
      query.add(new Term("field", "universe"));
      query.add(new Term("field", "right"));
      query.setLowFreqMinimumNumberShouldMatch(2.0f);
      TopDocs search = s.search(query, 10);
      assertEquals(search.totalHits, 1);
      assertEquals("0", r.document(search.scoreDocs[0].doc).get("id"));
    }
   
    {
      CommonTermsQuery query = new CommonTermsQuery(Occur.SHOULD, Occur.SHOULD,
          random().nextBoolean() ? 2.0f : 0.5f);
      query.add(new Term("field", "is"));
      query.add(new Term("field", "this"));
      query.add(new Term("field", "end"));
      query.add(new Term("field", "world"));
      query.add(new Term("field", "universe"));
      query.add(new Term("field", "right"));
      query.setLowFreqMinimumNumberShouldMatch(0.49f);
      TopDocs search = s.search(query, 10);
      assertEquals(search.totalHits, 3);
      assertEquals("0", r.document(search.scoreDocs[0].doc).get("id"));
      assertEquals("2", r.document(search.scoreDocs[1].doc).get("id"));
      assertEquals("3", r.document(search.scoreDocs[2].doc).get("id"));
    }
   
    {
      CommonTermsQuery query = new CommonTermsQuery(Occur.SHOULD, Occur.SHOULD,
          random().nextBoolean() ? 2.0f : 0.5f);
      query.add(new Term("field", "is"));
      query.add(new Term("field", "this"));
      query.add(new Term("field", "end"));
      query.add(new Term("field", "world"));
      query.add(new Term("field", "universe"));
      query.add(new Term("field", "right"));
      query.setLowFreqMinimumNumberShouldMatch(1.0f);
      TopDocs search = s.search(query, 10);
      assertEquals(search.totalHits, 3);
      assertEquals("0", r.document(search.scoreDocs[0].doc).get("id"));
      assertEquals("2", r.document(search.scoreDocs[1].doc).get("id"));
      assertEquals("3", r.document(search.scoreDocs[2].doc).get("id"));
      assertTrue(search.scoreDocs[1].score > search.scoreDocs[2].score);
    }
   
    {
      CommonTermsQuery query = new CommonTermsQuery(Occur.SHOULD, Occur.SHOULD,
          random().nextBoolean() ? 2.0f : 0.5f);
      query.add(new Term("field", "is"));
      query.add(new Term("field", "this"));
      query.add(new Term("field", "end"));
      query.add(new Term("field", "world"));
      query.add(new Term("field", "universe"));
      query.add(new Term("field", "right"));
      query.setLowFreqMinimumNumberShouldMatch(1.0f);
      query.setHighFreqMinimumNumberShouldMatch(4.0f);
      TopDocs search = s.search(query, 10);
      assertEquals(search.totalHits, 3);
      assertEquals(search.scoreDocs[1].score, search.scoreDocs[2].score, 0.0f);
      assertEquals("0", r.document(search.scoreDocs[0].doc).get("id"));
      // doc 2 and 3 only get a score from low freq terms
      assertEquals(
          new HashSet<String>(Arrays.asList("2", "3")),
          new HashSet<String>(Arrays.asList(
              r.document(search.scoreDocs[1].doc).get("id"),
              r.document(search.scoreDocs[2].doc).get("id"))));
    }
   
    {
      // only high freq terms around - check that min should match is applied
      CommonTermsQuery query = new CommonTermsQuery(Occur.SHOULD, Occur.SHOULD,
          random().nextBoolean() ? 2.0f : 0.5f);
      query.add(new Term("field", "is"));
      query.add(new Term("field", "this"));
      query.add(new Term("field", "the"));
      query.setLowFreqMinimumNumberShouldMatch(1.0f);
      query.setHighFreqMinimumNumberShouldMatch(2.0f);
      TopDocs search = s.search(query, 10);
      assertEquals(search.totalHits, 4);
    }
   
    {
      // only high freq terms around - check that min should match is applied
      CommonTermsQuery query = new CommonTermsQuery(Occur.MUST, Occur.SHOULD,
          random().nextBoolean() ? 2.0f : 0.5f);
      query.add(new Term("field", "is"));
      query.add(new Term("field", "this"));
      query.add(new Term("field", "the"));
      query.setLowFreqMinimumNumberShouldMatch(1.0f);
      query.setHighFreqMinimumNumberShouldMatch(2.0f);
      TopDocs search = s.search(query, 10);
      assertEquals(search.totalHits, 2);
      assertEquals(
          new HashSet<String>(Arrays.asList("0", "2")),
          new HashSet<String>(Arrays.asList(
              r.document(search.scoreDocs[0].doc).get("id"),
View Full Code Here
404
405
406
407
408
409
410
411
412
413
414
415
416
      }
      for (TermAndFreq termAndFreq : highTerms) {
        cq.add(new Term(field, termAndFreq.term));
      }
     
      TopDocs cqSearch = searcher.search(cq, reader.maxDoc());
     
      TopDocs verifySearch = searcher.search(verifyQuery, reader.maxDoc());
      assertEquals(verifySearch.totalHits, cqSearch.totalHits);
      Set<Integer> hits = new HashSet<Integer>();
      for (ScoreDoc doc : verifySearch.scoreDocs) {
        hits.add(doc.doc);
      }
View Full Code Here
899
900
901
902
903
904
905
906
907
908
909
    w.setMaxBufferedDocs(2);
    w.getReader().close();
    w.setMergedSegmentWarmer(new IndexWriter.IndexReaderWarmer() {
        public void warm(IndexReader r) throws IOException {
          final IndexSearcher s = new IndexSearcher(r);
          final TopDocs hits = s.search(new TermQuery(new Term("foo", "bar")), 10);
          assertEquals(20, hits.totalHits);
        }
      });
   
    Document doc = new Document();
View Full Code Here
150
151
152
153
154
155
156
157
158
159
160
        tasks.close();
      }
     
      reader = DirectoryReader.open(runData.getDirectory());
      searcher = newSearcher(reader);
      TopDocs td = searcher.search(new TermQuery(new Term("body", "body")), 10);
      assertEquals(numAdds, td.totalHits);
      assertNotNull(td.scoreDocs[0]);
     
      if (storedField==null) {
        storedField = DocMaker.BODY_FIELD; // added to all docs and satisfies field-name == value
View Full Code Here
89
90
91
92
93
94
95
96
97
    tasks.addTask(new CloseIndexTask(runData));
    tasks.doLogic();
   
    IndexReader reader = DirectoryReader.open(runData.getDirectory());
    IndexSearcher searcher = newSearcher(reader);
    TopDocs td = searcher.search(new TermQuery(new Term("key", "value")), 10);
    assertEquals(numExpectedResults, td.totalHits);
    reader.close();
  }
View Full Code Here
TOP

Related Classes of org.apache.lucene.search.TopDocs

  • cc.twittertools.search.api.TrecSearchHandler
  • cc.twittertools.search.local.RunQueries
  • cc.twittertools.search.local.SearchStatuses
  • com.bericotech.clavin.gazetteer.query.LuceneGazetteer
  • com.esri.gpt.server.assertion.index.AsnIndexAdapter
  • com.googlecode.lucene.gae.blobstore.BlobStoreReaderTest
  • com.googlecode.lucene.gae.datastore.DataStoreReaderTest
  • com.jeecms.cms.lucene.LuceneContentSvcImpl
  • com.tistory.devyongsik.crescent.search.highlight.CrescentHighlighterTest
  • edu.isi.karma.semantictypes.tfIdf.Searcher
    • 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.