QueryParserTest.py :  » Search » PyLucence » pylucene-3.0.1-1 » samples » LuceneInAction » lia » searching » Python Open Source

Home
Python Open Source
1.3.1.2 Python
2.Ajax
3.Aspect Oriented
4.Blog
5.Build
6.Business Application
7.Chart Report
8.Content Management Systems
9.Cryptographic
10.Database
11.Development
12.Editor
13.Email
14.ERP
15.Game 2D 3D
16.GIS
17.GUI
18.IDE
19.Installer
20.IRC
21.Issue Tracker
22.Language Interface
23.Log
24.Math
25.Media Sound Audio
26.Mobile
27.Network
28.Parser
29.PDF
30.Project Management
31.RSS
32.Search
33.Security
34.Template Engines
35.Test
36.UML
37.USB Serial
38.Web Frameworks
39.Web Server
40.Web Services
41.Web Unit
42.Wiki
43.Windows
44.XML
Python Open Source » Search » PyLucence 
PyLucence » pylucene 3.0.1 1 » samples » LuceneInAction » lia » searching » QueryParserTest.py
# ====================================================================
#   Licensed under the Apache License, Version 2.0 (the "License");
#   you may not use this file except in compliance with the License.
#   You may obtain a copy of the License at
#
#       http://www.apache.org/licenses/LICENSE-2.0
#
#   Unless required by applicable law or agreed to in writing, software
#   distributed under the License is distributed on an "AS IS" BASIS,
#   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
#   See the License for the specific language governing permissions and
#   limitations under the License.
# ====================================================================

from lia.common.LiaTestCase import LiaTestCase

from lucene import \
     WhitespaceAnalyzer, StandardAnalyzer, Term, QueryParser, Locale, \
     BooleanQuery, FuzzyQuery, IndexSearcher, TermRangeQuery, TermQuery, \
     BooleanClause, Version


class QueryParserTest(LiaTestCase):

    def setUp(self):

        super(QueryParserTest, self).setUp()
        self.analyzer = WhitespaceAnalyzer()
        self.searcher = IndexSearcher(self.directory, True)

    def testToString(self):

        query = BooleanQuery()
        query.add(FuzzyQuery(Term("field", "kountry")),
                  BooleanClause.Occur.MUST)
        query.add(TermQuery(Term("title", "western")),
                  BooleanClause.Occur.SHOULD)

        self.assertEqual("+kountry~0.5 title:western",
                         query.toString("field"), "both kinds")

    def testPrefixQuery(self):

        parser = QueryParser(Version.LUCENE_CURRENT, "category",
                             StandardAnalyzer(Version.LUCENE_CURRENT))
        parser.setLowercaseExpandedTerms(False)

        print parser.parse("/Computers/technology*").toString("category")

    def testGrouping(self):

        query = QueryParser(Version.LUCENE_CURRENT, "subject",
                            self.analyzer).parse("(agile OR extreme) AND methodology")
        scoreDocs = self.searcher.search(query, 50).scoreDocs

        self.assertHitsIncludeTitle(self.searcher, scoreDocs,
                                    "Extreme Programming Explained")
        self.assertHitsIncludeTitle(self.searcher, scoreDocs,
                                    "The Pragmatic Programmer")

    def testTermRangeQuery(self):

        query = QueryParser(Version.LUCENE_CURRENT, "subject",
                            self.analyzer).parse("title2:[K TO N]")
        self.assert_(TermRangeQuery.instance_(query))

        scoreDocs = self.searcher.search(query, 10).scoreDocs
        self.assertHitsIncludeTitle(self.searcher, scoreDocs, "Mindstorms")

        query = QueryParser(Version.LUCENE_CURRENT, "subject",
                            self.analyzer).parse("title2:{K TO Mindstorms}")
        scoreDocs = self.searcher.search(query, 10).scoreDocs
        self.assertHitsIncludeTitle(self.searcher, scoreDocs, "Mindstorms",
                                    True)

    def testDateRangeQuery(self):

        # locale diff between jre and gcj 1/1/04 -> 01/01/04
        # expression = "modified:[1/1/04 TO 12/31/04]"
        
        expression = "modified:[01/01/04 TO 12/31/04]"
        parser = QueryParser(Version.LUCENE_CURRENT, "subject", self.analyzer)
        parser.setLocale(Locale.US)
        query = parser.parse(expression)
        print expression, "parsed to", query

        topDocs = self.searcher.search(query, 50)
        self.assert_(topDocs.totalHits > 0)

    def testSlop(self):

        q = QueryParser(Version.LUCENE_CURRENT, "field",
                        self.analyzer).parse('"exact phrase"')
        self.assertEqual("\"exact phrase\"", q.toString("field"),
                         "zero slop")

        qp = QueryParser(Version.LUCENE_CURRENT, "field", self.analyzer)
        qp.setPhraseSlop(5)
        q = qp.parse('"sloppy phrase"')
        self.assertEqual("\"sloppy phrase\"~5", q.toString("field"),
                         "sloppy, implicitly")

    def testPhraseQuery(self):

        analyzer = StandardAnalyzer(Version.LUCENE_24)
        q = QueryParser(Version.LUCENE_24, "field",
                        analyzer).parse('"This is Some Phrase*"')
        self.assertEqual("\"some phrase\"", q.toString("field"), "analyzed")

        q = QueryParser(Version.LUCENE_CURRENT, "field",
                        self.analyzer).parse('"term"')
        self.assert_(TermQuery.instance_(q), "reduced to TermQuery")

    def testLowercasing(self):

        q = QueryParser(Version.LUCENE_CURRENT, "field",
                        self.analyzer).parse("PrefixQuery*")
        self.assertEqual("prefixquery*", q.toString("field"), "lowercased")

        qp = QueryParser(Version.LUCENE_CURRENT, "field", self.analyzer)
        qp.setLowercaseExpandedTerms(False)
        q = qp.parse("PrefixQuery*")
        self.assertEqual("PrefixQuery*", q.toString("field"), "not lowercased")

    def testWildcard(self):

        try:
            QueryParser(Version.LUCENE_CURRENT, "field",
                        self.analyzer).parse("*xyz")
            self.fail("Leading wildcard character should not be allowed")
        except:
            self.assert_(True)

    def testBoost(self):

         q = QueryParser(Version.LUCENE_CURRENT, "field",
                         self.analyzer).parse("term^2")
         self.assertEqual("term^2.0", q.toString("field"))

    def testParseException(self):

        try:
            QueryParser(Version.LUCENE_CURRENT, "contents",
                        self.analyzer).parse("^&#")
        except:
            # expression is invalid, as expected
            self.assert_(True)
        else:
            self.fail("ParseException expected, but not thrown")
www.java2java.com | Contact Us
Copyright 2009 - 12 Demo Source and Support. All rights reserved.
All other trademarks are property of their respective owners.