Package org.apache.lucene.search

Examples of org.apache.lucene.search.RegexpQuery

The supported syntax is documented in the {@link RegExp} class.Note this might be different than other regular expression implementations. For some alternatives with different syntax, look under the sandbox.

Note this query can be slow, as it needs to iterate over many terms. In order to prevent extremely slow RegexpQueries, a Regexp term should not start with the expression .* @see RegExp @lucene.experimental

371
372
373
374
375
376
377
378
379
380
381
    }
  }

  // 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", "hello there"));

View Full Code Here
383
384
385
386
387
388
389
390
391
392
393
    assertEquals(0, mindex.search(wrappedquery), 0.00001f);
  }
   
  // 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", "hello there"));

View Full Code Here
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
  }
 
  public void testRegexps() throws Exception {
    StandardQueryParser qp = new StandardQueryParser();
    final String df = "field" ;
    RegexpQuery q = new RegexpQuery(new Term("field", "[a-z][123]"));
    assertEquals(q, qp.parse("/[a-z][123]/", df));
    qp.setLowercaseExpandedTerms(true);
    assertEquals(q, qp.parse("/[A-Z][123]/", df));
    q.setBoost(0.5f);
    assertEquals(q, qp.parse("/[A-Z][123]/^0.5", df));
    qp.setMultiTermRewriteMethod(MultiTermQuery.SCORING_BOOLEAN_QUERY_REWRITE);
    q.setRewriteMethod(MultiTermQuery.SCORING_BOOLEAN_QUERY_REWRITE);
    assertTrue(qp.parse("/[A-Z][123]/^0.5", df) instanceof RegexpQuery);
    assertEquals(q, qp.parse("/[A-Z][123]/^0.5", df));
    assertEquals(MultiTermQuery.SCORING_BOOLEAN_QUERY_REWRITE, ((RegexpQuery)qp.parse("/[A-Z][123]/^0.5", df)).getRewriteMethod());
    qp.setMultiTermRewriteMethod(MultiTermQuery.CONSTANT_SCORE_AUTO_REWRITE_DEFAULT);
   
    Query escaped = new RegexpQuery(new Term("field", "[a-z]\\/[123]"));
    assertEquals(escaped, qp.parse("/[a-z]\\/[123]/", df));
    Query escaped2 = new RegexpQuery(new Term("field", "[a-z]\\*[123]"));
    assertEquals(escaped2, qp.parse("/[a-z]\\*[123]/", df));
   
    BooleanQuery complex = new BooleanQuery();
    complex.add(new RegexpQuery(new Term("field", "[a-z]\\/[123]")), Occur.MUST);
    complex.add(new TermQuery(new Term("path", "/etc/init.d/")), Occur.MUST);
    complex.add(new TermQuery(new Term("field", "/etc/init[.]d/lucene/")), Occur.SHOULD);
    assertEquals(complex, qp.parse("/[a-z]\\/[123]/ AND path:\"/etc/init.d/\" OR \"/etc\\/init\\[.\\]d/lucene/\" ", df));
   
    Query re = new RegexpQuery(new Term("field", "http.*"));
    assertEquals(re, qp.parse("field:/http.*/", df));
    assertEquals(re, qp.parse("/http.*/", df));
   
    re = new RegexpQuery(new Term("field", "http~0.5"));
    assertEquals(re, qp.parse("field:/http~0.5/", df));
    assertEquals(re, qp.parse("/http~0.5/", df));
   
    re = new RegexpQuery(new Term("field", "boo"));
    assertEquals(re, qp.parse("field:/boo/", df));
    assertEquals(re, qp.parse("/boo/", df));
   
    assertEquals(new TermQuery(new Term("field", "/boo/")), qp.parse("\"/boo/\"", df));
    assertEquals(new TermQuery(new Term("field", "/boo/")), qp.parse("\\/boo\\/", df));
   
    BooleanQuery two = new BooleanQuery();
    two.add(new RegexpQuery(new Term("field", "foo")), Occur.SHOULD);
    two.add(new RegexpQuery(new Term("field", "bar")), Occur.SHOULD);
    assertEquals(two, qp.parse("field:/foo/ field:/bar/", df));
    assertEquals(two, qp.parse("/foo/ /bar/", df));
  }
View Full Code Here
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
    parser.setMultiFields(fields);
    parser.setDefaultOperator(StandardQueryConfigHandler.Operator.AND);
    parser.setAnalyzer(new MockAnalyzer(random()));

    BooleanQuery exp = new BooleanQuery();
    exp.add(new BooleanClause(new RegexpQuery(new Term("b", "ab.+")), BooleanClause.Occur.SHOULD));//TODO spezification? was "MUST"
    exp.add(new BooleanClause(new RegexpQuery(new Term("t", "ab.+")), BooleanClause.Occur.SHOULD));//TODO spezification? was "MUST"

    assertEquals(exp, parser.parse("/ab.+/", null));

    RegexpQuery regexpQueryexp = new RegexpQuery(new Term("test", "[abc]?[0-9]"));

    assertEquals(regexpQueryexp, parser.parse("test:/[abc]?[0-9]/", null));

  }
View Full Code Here
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
  }
 
  public void testRegexps() throws Exception {
    StandardQueryParser qp = new StandardQueryParser();
    final String df = "field" ;
    RegexpQuery q = new RegexpQuery(new Term("field", "[a-z][123]"));
    assertEquals(q, qp.parse("/[a-z][123]/", df));
    qp.setLowercaseExpandedTerms(true);
    assertEquals(q, qp.parse("/[A-Z][123]/", df));
    q.setBoost(0.5f);
    assertEquals(q, qp.parse("/[A-Z][123]/^0.5", df));
    qp.setMultiTermRewriteMethod(MultiTermQuery.SCORING_BOOLEAN_QUERY_REWRITE);
    q.setRewriteMethod(MultiTermQuery.SCORING_BOOLEAN_QUERY_REWRITE);
    assertTrue(qp.parse("/[A-Z][123]/^0.5", df) instanceof RegexpQuery);
    assertEquals(q, qp.parse("/[A-Z][123]/^0.5", df));
    assertEquals(MultiTermQuery.SCORING_BOOLEAN_QUERY_REWRITE, ((RegexpQuery)qp.parse("/[A-Z][123]/^0.5", df)).getRewriteMethod());
    qp.setMultiTermRewriteMethod(MultiTermQuery.CONSTANT_SCORE_AUTO_REWRITE_DEFAULT);
   
    Query escaped = new RegexpQuery(new Term("field", "[a-z]\\/[123]"));
    assertEquals(escaped, qp.parse("/[a-z]\\/[123]/", df));
    Query escaped2 = new RegexpQuery(new Term("field", "[a-z]\\*[123]"));
    assertEquals(escaped2, qp.parse("/[a-z]\\*[123]/", df));
   
    BooleanQuery complex = new BooleanQuery();
    complex.add(new RegexpQuery(new Term("field", "[a-z]\\/[123]")), Occur.MUST);
    complex.add(new TermQuery(new Term("path", "/etc/init.d/")), Occur.MUST);
    complex.add(new TermQuery(new Term("field", "/etc/init[.]d/lucene/")), Occur.SHOULD);
    assertEquals(complex, qp.parse("/[a-z]\\/[123]/ AND path:\"/etc/init.d/\" OR \"/etc\\/init\\[.\\]d/lucene/\" ", df));
   
    Query re = new RegexpQuery(new Term("field", "http.*"));
    assertEquals(re, qp.parse("field:/http.*/", df));
    assertEquals(re, qp.parse("/http.*/", df));
   
    re = new RegexpQuery(new Term("field", "http~0.5"));
    assertEquals(re, qp.parse("field:/http~0.5/", df));
    assertEquals(re, qp.parse("/http~0.5/", df));
   
    re = new RegexpQuery(new Term("field", "boo"));
    assertEquals(re, qp.parse("field:/boo/", df));
    assertEquals(re, qp.parse("/boo/", df));
   
    assertEquals(new TermQuery(new Term("field", "/boo/")), qp.parse("\"/boo/\"", df));
    assertEquals(new TermQuery(new Term("field", "/boo/")), qp.parse("\\/boo\\/", df));
   
    BooleanQuery two = new BooleanQuery();
    two.add(new RegexpQuery(new Term("field", "foo")), Occur.SHOULD);
    two.add(new RegexpQuery(new Term("field", "bar")), Occur.SHOULD);
    assertEquals(two, qp.parse("field:/foo/ field:/bar/", df));
    assertEquals(two, qp.parse("/foo/ /bar/", df));
  }
View Full Code Here
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
    parser.setMultiFields(fields);
    parser.setDefaultOperator(StandardQueryConfigHandler.Operator.AND);
    parser.setAnalyzer(new MockAnalyzer(random()));

    BooleanQuery exp = new BooleanQuery();
    exp.add(new BooleanClause(new RegexpQuery(new Term("b", "ab.+")), BooleanClause.Occur.SHOULD));//TODO spezification? was "MUST"
    exp.add(new BooleanClause(new RegexpQuery(new Term("t", "ab.+")), BooleanClause.Occur.SHOULD));//TODO spezification? was "MUST"

    assertEquals(exp, parser.parse("/ab.+/", null));

    RegexpQuery regexpQueryexp = new RegexpQuery(new Term("test", "[abc]?[0-9]"));

    assertEquals(regexpQueryexp, parser.parse("test:/[abc]?[0-9]/", null));

  }
View Full Code Here
372
373
374
375
376
377
378
379
380
381
382
    }
  }

  // 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")));

View Full Code Here
384
385
386
387
388
389
390
391
392
393
394
    assertEquals(0, mindex.search(wrappedquery), 0.00001f);
  }
   
  // 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")));

View Full Code Here
335
336
337
338
339
340
341
342
343
  public void testSimpleRegex() throws ParseException {
    String[] fields = new String[] {"a", "b"};
    MultiFieldQueryParser mfqp = new MultiFieldQueryParser(TEST_VERSION_CURRENT, fields, new MockAnalyzer(random()));

    BooleanQuery bq = new BooleanQuery(true);
    bq.add(new RegexpQuery(new Term("a", "[a-z][123]")), Occur.SHOULD);
    bq.add(new RegexpQuery(new Term("b", "[a-z][123]")), Occur.SHOULD);
    assertEquals(bq, mfqp.parse("/[a-z][123]/"));
  }
View Full Code Here
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
  @Override
  public RegexpQuery build(QueryNode queryNode) throws QueryNodeException {
    RegexpQueryNode regexpNode = (RegexpQueryNode) queryNode;

    RegexpQuery q = new RegexpQuery(new Term(regexpNode.getFieldAsString(),
        regexpNode.textToBytesRef()));

    MultiTermQuery.RewriteMethod method = (MultiTermQuery.RewriteMethod) queryNode
        .getTag(MultiTermRewriteMethodProcessor.TAG_ID);
    if (method != null) {
      q.setRewriteMethod(method);
    }

    return q;
  }
View Full Code Here
TOP

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

  • com.stratio.cassandra.index.query.RegexpCondition
  • org.apache.lucene.index.memory.MemoryIndexTest
  • org.apache.lucene.queryparser.classic.TestMultiFieldQueryParser
  • org.apache.lucene.queryparser.flexible.standard.builders.RegexpQueryNodeBuilder
  • org.apache.lucene.queryparser.flexible.standard.TestQPHelper
  • org.apache.lucene.search.postingshighlight.TestMultiTermHighlighting
  • org.apache.lucene.search.spans.TestSpanMultiTermQueryWrapper
  • org.apache.lucene.search.vectorhighlight.FieldQueryTest
  • org.apache.lucene.util.automaton.RegExp
  • org.elasticsearch.common.lucene.search.RegexpFilter$InternalFilter
    • 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.