samples/LuceneInAction/lia/extsearch/queryparser/AdvancedQueryParserTest.py

   1 # ====================================================================
   2 #   Licensed under the Apache License, Version 2.0 (the "License");
   3 #   you may not use this file except in compliance with the License.
   4 #   You may obtain a copy of the License at
   5 #
   6 #       http://www.apache.org/licenses/LICENSE-2.0
   7 #
   8 #   Unless required by applicable law or agreed to in writing, software
   9 #   distributed under the License is distributed on an "AS IS" BASIS,
  10 #   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
  11 #   See the License for the specific language governing permissions and
  12 #   limitations under the License.
  13 # ====================================================================
  14
  15 from unittest import TestCase
  16
  17 from lucene import \
  18      WhitespaceAnalyzer, IndexSearcher, RAMDirectory, \
  19      Document, Field, IndexWriter, TermQuery, SpanNearQuery
  20
  21 from lia.extsearch.queryparser.NumberUtils import NumberUtils
  22 from lia.extsearch.queryparser.CustomQueryParser import \
  23     MultiFieldCustomQueryParser, CustomQueryParser
  24
  25
  26 class AdvancedQueryParserTest(TestCase):
  27
  28     def setUp(self):
  29
  30         self.analyzer = WhitespaceAnalyzer()
  31         self.directory = RAMDirectory()
  32
  33         writer = IndexWriter(self.directory, self.analyzer, True,
  34                              IndexWriter.MaxFieldLength.LIMITED)
  35
  36         for i in xrange(1, 501):
  37             doc = Document()
  38             doc.add(Field("id", NumberUtils.pad(i),
  39                           Field.Store.YES, Field.Index.NOT_ANALYZED))
  40             writer.addDocument(doc)
  41
  42         writer.close()
  43
  44     def testCustomQueryParser(self):
  45
  46         parser = CustomQueryParser("field", self.analyzer)
  47
  48         try:
  49             parser.parse("a?t")
  50             self.fail("Wildcard queries should not be allowed")
  51         except:
  52             # expected
  53             self.assert_(True)
  54
  55         try:
  56             parser.parse("xunit~")
  57             self.fail("Fuzzy queries should not be allowed")
  58         except:
  59             # expected
  60             self.assert_(True)
  61
  62     def testCustomMultiFieldQueryParser(self):
  63
  64         parser = MultiFieldCustomQueryParser(["field"], self.analyzer)
  65
  66         try:
  67             parser.parse("a?t")
  68             self.fail("Wildcard queries should not be allowed")
  69         except:
  70             # expected
  71             self.assert_(True)
  72
  73         try:
  74             parser.parse("xunit~")
  75             self.fail("Fuzzy queries should not be allowed")
  76         except:
  77             # expected
  78             self.assert_(True)
  79
  80     def testIdRangeQuery(self):
  81
  82         parser = CustomQueryParser("field", self.analyzer)
  83
  84         query = parser.parse("id:[37 TO 346]")
  85         self.assertEqual("id:[0000000037 TO 0000000346]",
  86                          query.toString("field"), "padded")
  87
  88         searcher = IndexSearcher(self.directory, True)
  89         scoreDocs = searcher.search(query, 1000).scoreDocs
  90         self.assertEqual(310, len(scoreDocs))
  91
  92         print parser.parse("special:[term TO *]")
  93         print parser.parse("special:[* TO term]")
  94
  95     def testPhraseQuery(self):
  96
  97         parser = CustomQueryParser("field", self.analyzer)
  98
  99         query = parser.parse("singleTerm")
 100         self.assert_(TermQuery.instance_(query), "TermQuery")
 101
 102         query = parser.parse("\"a phrase\"")
 103         self.assert_(SpanNearQuery.instance_(query), "SpanNearQuery")