Mercurial > p > roundup > code
annotate test/test_indexer.py @ 5840:b68d3d8531d5 maint-1.6 1.6.1
Changes to prepare for 1.6.1 release.
| author | John Rouillard <rouilj@ieee.org> |
|---|---|
| date | Wed, 10 Jul 2019 10:35:29 -0400 |
| parents | 43a1f7fe39f5 |
| children | d26921b851c3 |
| rev | line source |
|---|---|
|
848
2a928d404af8
ehem, forgot to add
Richard Jones <richard@users.sourceforge.net>
parents:
diff
changeset
|
1 # Copyright (c) 2002 ekit.com Inc (http://www.ekit-inc.com/) |
|
2a928d404af8
ehem, forgot to add
Richard Jones <richard@users.sourceforge.net>
parents:
diff
changeset
|
2 # |
|
2a928d404af8
ehem, forgot to add
Richard Jones <richard@users.sourceforge.net>
parents:
diff
changeset
|
3 # Permission is hereby granted, free of charge, to any person obtaining a copy |
|
2a928d404af8
ehem, forgot to add
Richard Jones <richard@users.sourceforge.net>
parents:
diff
changeset
|
4 # of this software and associated documentation files (the "Software"), to deal |
|
2a928d404af8
ehem, forgot to add
Richard Jones <richard@users.sourceforge.net>
parents:
diff
changeset
|
5 # in the Software without restriction, including without limitation the rights |
|
2a928d404af8
ehem, forgot to add
Richard Jones <richard@users.sourceforge.net>
parents:
diff
changeset
|
6 # to use, copy, modify, merge, publish, distribute, sublicense, and/or sell |
|
2a928d404af8
ehem, forgot to add
Richard Jones <richard@users.sourceforge.net>
parents:
diff
changeset
|
7 # copies of the Software, and to permit persons to whom the Software is |
|
2a928d404af8
ehem, forgot to add
Richard Jones <richard@users.sourceforge.net>
parents:
diff
changeset
|
8 # furnished to do so, subject to the following conditions: |
|
2a928d404af8
ehem, forgot to add
Richard Jones <richard@users.sourceforge.net>
parents:
diff
changeset
|
9 # |
|
2a928d404af8
ehem, forgot to add
Richard Jones <richard@users.sourceforge.net>
parents:
diff
changeset
|
10 # The above copyright notice and this permission notice shall be included in |
|
2a928d404af8
ehem, forgot to add
Richard Jones <richard@users.sourceforge.net>
parents:
diff
changeset
|
11 # all copies or substantial portions of the Software. |
|
2a928d404af8
ehem, forgot to add
Richard Jones <richard@users.sourceforge.net>
parents:
diff
changeset
|
12 # |
|
2a928d404af8
ehem, forgot to add
Richard Jones <richard@users.sourceforge.net>
parents:
diff
changeset
|
13 # THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR |
|
2a928d404af8
ehem, forgot to add
Richard Jones <richard@users.sourceforge.net>
parents:
diff
changeset
|
14 # IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, |
|
2a928d404af8
ehem, forgot to add
Richard Jones <richard@users.sourceforge.net>
parents:
diff
changeset
|
15 # FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE |
|
2a928d404af8
ehem, forgot to add
Richard Jones <richard@users.sourceforge.net>
parents:
diff
changeset
|
16 # AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER |
|
2a928d404af8
ehem, forgot to add
Richard Jones <richard@users.sourceforge.net>
parents:
diff
changeset
|
17 # LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, |
|
2a928d404af8
ehem, forgot to add
Richard Jones <richard@users.sourceforge.net>
parents:
diff
changeset
|
18 # OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE |
|
2a928d404af8
ehem, forgot to add
Richard Jones <richard@users.sourceforge.net>
parents:
diff
changeset
|
19 # SOFTWARE. |
|
2a928d404af8
ehem, forgot to add
Richard Jones <richard@users.sourceforge.net>
parents:
diff
changeset
|
20 |
|
2a928d404af8
ehem, forgot to add
Richard Jones <richard@users.sourceforge.net>
parents:
diff
changeset
|
21 import os, unittest, shutil |
|
2a928d404af8
ehem, forgot to add
Richard Jones <richard@users.sourceforge.net>
parents:
diff
changeset
|
22 |
|
5036
380d8d8b30a3
Replace existing run_tests.py script with a pytest script
John Kristensen <john@jerrykan.com>
parents:
5033
diff
changeset
|
23 import pytest |
|
4008
0bf9f8ae7d1b
fix bug introduced in 1.4.5 in RDBMS full-text indexing;
Richard Jones <richard@users.sourceforge.net>
parents:
3547
diff
changeset
|
24 from roundup.backends import get_backend, have_backend |
|
0bf9f8ae7d1b
fix bug introduced in 1.4.5 in RDBMS full-text indexing;
Richard Jones <richard@users.sourceforge.net>
parents:
3547
diff
changeset
|
25 from roundup.backends.indexer_rdbms import Indexer |
|
0bf9f8ae7d1b
fix bug introduced in 1.4.5 in RDBMS full-text indexing;
Richard Jones <richard@users.sourceforge.net>
parents:
3547
diff
changeset
|
26 |
|
0bf9f8ae7d1b
fix bug introduced in 1.4.5 in RDBMS full-text indexing;
Richard Jones <richard@users.sourceforge.net>
parents:
3547
diff
changeset
|
27 # borrow from other tests |
|
0bf9f8ae7d1b
fix bug introduced in 1.4.5 in RDBMS full-text indexing;
Richard Jones <richard@users.sourceforge.net>
parents:
3547
diff
changeset
|
28 from db_test_base import setupSchema, config |
|
5036
380d8d8b30a3
Replace existing run_tests.py script with a pytest script
John Kristensen <john@jerrykan.com>
parents:
5033
diff
changeset
|
29 from .test_postgresql import postgresqlOpener, skip_postgresql |
|
380d8d8b30a3
Replace existing run_tests.py script with a pytest script
John Kristensen <john@jerrykan.com>
parents:
5033
diff
changeset
|
30 from .test_mysql import mysqlOpener, skip_mysql |
|
4008
0bf9f8ae7d1b
fix bug introduced in 1.4.5 in RDBMS full-text indexing;
Richard Jones <richard@users.sourceforge.net>
parents:
3547
diff
changeset
|
31 from test_sqlite import sqliteOpener |
|
0bf9f8ae7d1b
fix bug introduced in 1.4.5 in RDBMS full-text indexing;
Richard Jones <richard@users.sourceforge.net>
parents:
3547
diff
changeset
|
32 |
|
5036
380d8d8b30a3
Replace existing run_tests.py script with a pytest script
John Kristensen <john@jerrykan.com>
parents:
5033
diff
changeset
|
33 try: |
|
380d8d8b30a3
Replace existing run_tests.py script with a pytest script
John Kristensen <john@jerrykan.com>
parents:
5033
diff
changeset
|
34 import xapian |
|
5038
c977f3530944
Work-around for pytest.mark.skipif() bug
John Kristensen <john@jerrykan.com>
parents:
5037
diff
changeset
|
35 skip_xapian = lambda func, *args, **kwargs: func |
|
5036
380d8d8b30a3
Replace existing run_tests.py script with a pytest script
John Kristensen <john@jerrykan.com>
parents:
5033
diff
changeset
|
36 except ImportError: |
|
5109
43a1f7fe39f5
Improved work-around for pytest markers bug
John Kristensen <john@jerrykan.com>
parents:
5105
diff
changeset
|
37 # FIX: workaround for a bug in pytest.mark.skip(): |
|
43a1f7fe39f5
Improved work-around for pytest markers bug
John Kristensen <john@jerrykan.com>
parents:
5105
diff
changeset
|
38 # https://github.com/pytest-dev/pytest/issues/568 |
|
43a1f7fe39f5
Improved work-around for pytest markers bug
John Kristensen <john@jerrykan.com>
parents:
5105
diff
changeset
|
39 from .pytest_patcher import mark_class |
|
43a1f7fe39f5
Improved work-around for pytest markers bug
John Kristensen <john@jerrykan.com>
parents:
5105
diff
changeset
|
40 skip_xapian = mark_class(pytest.mark.skip( |
|
43a1f7fe39f5
Improved work-around for pytest markers bug
John Kristensen <john@jerrykan.com>
parents:
5105
diff
changeset
|
41 "Skipping Xapian indexer tests: 'xapian' not installed")) |
|
5036
380d8d8b30a3
Replace existing run_tests.py script with a pytest script
John Kristensen <john@jerrykan.com>
parents:
5033
diff
changeset
|
42 |
|
5096
e74c3611b138
- issue2550636, issue2550909: Added support for Whoosh indexer.
John Rouillard <rouilj@ieee.org>
parents:
5038
diff
changeset
|
43 try: |
|
e74c3611b138
- issue2550636, issue2550909: Added support for Whoosh indexer.
John Rouillard <rouilj@ieee.org>
parents:
5038
diff
changeset
|
44 import whoosh |
|
e74c3611b138
- issue2550636, issue2550909: Added support for Whoosh indexer.
John Rouillard <rouilj@ieee.org>
parents:
5038
diff
changeset
|
45 skip_whoosh = lambda func, *args, **kwargs: func |
|
e74c3611b138
- issue2550636, issue2550909: Added support for Whoosh indexer.
John Rouillard <rouilj@ieee.org>
parents:
5038
diff
changeset
|
46 except ImportError: |
|
5109
43a1f7fe39f5
Improved work-around for pytest markers bug
John Kristensen <john@jerrykan.com>
parents:
5105
diff
changeset
|
47 # FIX: workaround for a bug in pytest.mark.skip(): |
|
43a1f7fe39f5
Improved work-around for pytest markers bug
John Kristensen <john@jerrykan.com>
parents:
5105
diff
changeset
|
48 # https://github.com/pytest-dev/pytest/issues/568 |
|
43a1f7fe39f5
Improved work-around for pytest markers bug
John Kristensen <john@jerrykan.com>
parents:
5105
diff
changeset
|
49 from .pytest_patcher import mark_class |
|
43a1f7fe39f5
Improved work-around for pytest markers bug
John Kristensen <john@jerrykan.com>
parents:
5105
diff
changeset
|
50 skip_whoosh = mark_class(pytest.mark.skip( |
|
43a1f7fe39f5
Improved work-around for pytest markers bug
John Kristensen <john@jerrykan.com>
parents:
5105
diff
changeset
|
51 "Skipping Whoosh indexer tests: 'whoosh' not installed")) |
|
5036
380d8d8b30a3
Replace existing run_tests.py script with a pytest script
John Kristensen <john@jerrykan.com>
parents:
5033
diff
changeset
|
52 |
|
5105
37d1e24fb941
Fix work-around for pytest markers bug
John Kristensen <john@jerrykan.com>
parents:
5096
diff
changeset
|
53 |
|
3297
8f7dc283bfa5
some more Xapian stuff (doc, test fixes)
Richard Jones <richard@users.sourceforge.net>
parents:
3295
diff
changeset
|
54 class db: |
|
3546
a4edd24c32be
test fixes and checking of indexer overwrites (xapian currently fails)
Richard Jones <richard@users.sourceforge.net>
parents:
3297
diff
changeset
|
55 class config(dict): |
|
3297
8f7dc283bfa5
some more Xapian stuff (doc, test fixes)
Richard Jones <richard@users.sourceforge.net>
parents:
3295
diff
changeset
|
56 DATABASE = 'test-index' |
|
3546
a4edd24c32be
test fixes and checking of indexer overwrites (xapian currently fails)
Richard Jones <richard@users.sourceforge.net>
parents:
3297
diff
changeset
|
57 config = config() |
|
a4edd24c32be
test fixes and checking of indexer overwrites (xapian currently fails)
Richard Jones <richard@users.sourceforge.net>
parents:
3297
diff
changeset
|
58 config[('main', 'indexer_stopwords')] = [] |
|
3297
8f7dc283bfa5
some more Xapian stuff (doc, test fixes)
Richard Jones <richard@users.sourceforge.net>
parents:
3295
diff
changeset
|
59 |
|
848
2a928d404af8
ehem, forgot to add
Richard Jones <richard@users.sourceforge.net>
parents:
diff
changeset
|
60 class IndexerTest(unittest.TestCase): |
|
2a928d404af8
ehem, forgot to add
Richard Jones <richard@users.sourceforge.net>
parents:
diff
changeset
|
61 def setUp(self): |
|
2a928d404af8
ehem, forgot to add
Richard Jones <richard@users.sourceforge.net>
parents:
diff
changeset
|
62 if os.path.exists('test-index'): |
|
2a928d404af8
ehem, forgot to add
Richard Jones <richard@users.sourceforge.net>
parents:
diff
changeset
|
63 shutil.rmtree('test-index') |
|
2a928d404af8
ehem, forgot to add
Richard Jones <richard@users.sourceforge.net>
parents:
diff
changeset
|
64 os.mkdir('test-index') |
|
2a928d404af8
ehem, forgot to add
Richard Jones <richard@users.sourceforge.net>
parents:
diff
changeset
|
65 os.mkdir('test-index/files') |
|
3295
a615cc230160
added Xapian indexer; replaces standard indexers if Xapian is available
Richard Jones <richard@users.sourceforge.net>
parents:
3078
diff
changeset
|
66 from roundup.backends.indexer_dbm import Indexer |
|
3297
8f7dc283bfa5
some more Xapian stuff (doc, test fixes)
Richard Jones <richard@users.sourceforge.net>
parents:
3295
diff
changeset
|
67 self.dex = Indexer(db) |
|
848
2a928d404af8
ehem, forgot to add
Richard Jones <richard@users.sourceforge.net>
parents:
diff
changeset
|
68 self.dex.load_index() |
|
2a928d404af8
ehem, forgot to add
Richard Jones <richard@users.sourceforge.net>
parents:
diff
changeset
|
69 |
|
4008
0bf9f8ae7d1b
fix bug introduced in 1.4.5 in RDBMS full-text indexing;
Richard Jones <richard@users.sourceforge.net>
parents:
3547
diff
changeset
|
70 def assertSeqEqual(self, s1, s2): |
|
4102
dcca66d56815
fix unit test compatibility
Richard Jones <richard@users.sourceforge.net>
parents:
4016
diff
changeset
|
71 # First argument is the db result we're testing, second is the |
|
dcca66d56815
fix unit test compatibility
Richard Jones <richard@users.sourceforge.net>
parents:
4016
diff
changeset
|
72 # desired result. Some db results don't have iterable rows, so we |
|
dcca66d56815
fix unit test compatibility
Richard Jones <richard@users.sourceforge.net>
parents:
4016
diff
changeset
|
73 # have to work around that. |
|
4015
6eec11b197aa
fix for indexer-test:
Ralf Schlatterbeck <schlatterbeck@users.sourceforge.net>
parents:
4008
diff
changeset
|
74 # Also work around some dbs not returning items in the expected |
|
4102
dcca66d56815
fix unit test compatibility
Richard Jones <richard@users.sourceforge.net>
parents:
4016
diff
changeset
|
75 # order. |
|
dcca66d56815
fix unit test compatibility
Richard Jones <richard@users.sourceforge.net>
parents:
4016
diff
changeset
|
76 s1 = list([tuple([r[n] for n in range(len(r))]) for r in s1]) |
|
4015
6eec11b197aa
fix for indexer-test:
Ralf Schlatterbeck <schlatterbeck@users.sourceforge.net>
parents:
4008
diff
changeset
|
77 s1.sort() |
|
4102
dcca66d56815
fix unit test compatibility
Richard Jones <richard@users.sourceforge.net>
parents:
4016
diff
changeset
|
78 if s1 != s2: |
|
4008
0bf9f8ae7d1b
fix bug introduced in 1.4.5 in RDBMS full-text indexing;
Richard Jones <richard@users.sourceforge.net>
parents:
3547
diff
changeset
|
79 self.fail('contents of %r != %r'%(s1, s2)) |
|
0bf9f8ae7d1b
fix bug introduced in 1.4.5 in RDBMS full-text indexing;
Richard Jones <richard@users.sourceforge.net>
parents:
3547
diff
changeset
|
80 |
|
848
2a928d404af8
ehem, forgot to add
Richard Jones <richard@users.sourceforge.net>
parents:
diff
changeset
|
81 def test_basics(self): |
|
3295
a615cc230160
added Xapian indexer; replaces standard indexers if Xapian is available
Richard Jones <richard@users.sourceforge.net>
parents:
3078
diff
changeset
|
82 self.dex.add_text(('test', '1', 'foo'), 'a the hello world') |
|
a615cc230160
added Xapian indexer; replaces standard indexers if Xapian is available
Richard Jones <richard@users.sourceforge.net>
parents:
3078
diff
changeset
|
83 self.dex.add_text(('test', '2', 'foo'), 'blah blah the world') |
|
4008
0bf9f8ae7d1b
fix bug introduced in 1.4.5 in RDBMS full-text indexing;
Richard Jones <richard@users.sourceforge.net>
parents:
3547
diff
changeset
|
84 self.assertSeqEqual(self.dex.find(['world']), [('test', '1', 'foo'), |
|
3295
a615cc230160
added Xapian indexer; replaces standard indexers if Xapian is available
Richard Jones <richard@users.sourceforge.net>
parents:
3078
diff
changeset
|
85 ('test', '2', 'foo')]) |
|
4008
0bf9f8ae7d1b
fix bug introduced in 1.4.5 in RDBMS full-text indexing;
Richard Jones <richard@users.sourceforge.net>
parents:
3547
diff
changeset
|
86 self.assertSeqEqual(self.dex.find(['blah']), [('test', '2', 'foo')]) |
|
0bf9f8ae7d1b
fix bug introduced in 1.4.5 in RDBMS full-text indexing;
Richard Jones <richard@users.sourceforge.net>
parents:
3547
diff
changeset
|
87 self.assertSeqEqual(self.dex.find(['blah', 'hello']), []) |
|
848
2a928d404af8
ehem, forgot to add
Richard Jones <richard@users.sourceforge.net>
parents:
diff
changeset
|
88 |
|
3547
7728ee93efd2
fix reindexing in Xapian
Richard Jones <richard@users.sourceforge.net>
parents:
3546
diff
changeset
|
89 def test_change(self): |
|
7728ee93efd2
fix reindexing in Xapian
Richard Jones <richard@users.sourceforge.net>
parents:
3546
diff
changeset
|
90 self.dex.add_text(('test', '1', 'foo'), 'a the hello world') |
|
7728ee93efd2
fix reindexing in Xapian
Richard Jones <richard@users.sourceforge.net>
parents:
3546
diff
changeset
|
91 self.dex.add_text(('test', '2', 'foo'), 'blah blah the world') |
|
4008
0bf9f8ae7d1b
fix bug introduced in 1.4.5 in RDBMS full-text indexing;
Richard Jones <richard@users.sourceforge.net>
parents:
3547
diff
changeset
|
92 self.assertSeqEqual(self.dex.find(['world']), [('test', '1', 'foo'), |
|
3547
7728ee93efd2
fix reindexing in Xapian
Richard Jones <richard@users.sourceforge.net>
parents:
3546
diff
changeset
|
93 ('test', '2', 'foo')]) |
|
3546
a4edd24c32be
test fixes and checking of indexer overwrites (xapian currently fails)
Richard Jones <richard@users.sourceforge.net>
parents:
3297
diff
changeset
|
94 self.dex.add_text(('test', '1', 'foo'), 'a the hello') |
|
4008
0bf9f8ae7d1b
fix bug introduced in 1.4.5 in RDBMS full-text indexing;
Richard Jones <richard@users.sourceforge.net>
parents:
3547
diff
changeset
|
95 self.assertSeqEqual(self.dex.find(['world']), [('test', '2', 'foo')]) |
|
3546
a4edd24c32be
test fixes and checking of indexer overwrites (xapian currently fails)
Richard Jones <richard@users.sourceforge.net>
parents:
3297
diff
changeset
|
96 |
|
3547
7728ee93efd2
fix reindexing in Xapian
Richard Jones <richard@users.sourceforge.net>
parents:
3546
diff
changeset
|
97 def test_clear(self): |
|
7728ee93efd2
fix reindexing in Xapian
Richard Jones <richard@users.sourceforge.net>
parents:
3546
diff
changeset
|
98 self.dex.add_text(('test', '1', 'foo'), 'a the hello world') |
|
7728ee93efd2
fix reindexing in Xapian
Richard Jones <richard@users.sourceforge.net>
parents:
3546
diff
changeset
|
99 self.dex.add_text(('test', '2', 'foo'), 'blah blah the world') |
|
4008
0bf9f8ae7d1b
fix bug introduced in 1.4.5 in RDBMS full-text indexing;
Richard Jones <richard@users.sourceforge.net>
parents:
3547
diff
changeset
|
100 self.assertSeqEqual(self.dex.find(['world']), [('test', '1', 'foo'), |
|
3547
7728ee93efd2
fix reindexing in Xapian
Richard Jones <richard@users.sourceforge.net>
parents:
3546
diff
changeset
|
101 ('test', '2', 'foo')]) |
|
7728ee93efd2
fix reindexing in Xapian
Richard Jones <richard@users.sourceforge.net>
parents:
3546
diff
changeset
|
102 self.dex.add_text(('test', '1', 'foo'), '') |
|
4008
0bf9f8ae7d1b
fix bug introduced in 1.4.5 in RDBMS full-text indexing;
Richard Jones <richard@users.sourceforge.net>
parents:
3547
diff
changeset
|
103 self.assertSeqEqual(self.dex.find(['world']), [('test', '2', 'foo')]) |
|
3547
7728ee93efd2
fix reindexing in Xapian
Richard Jones <richard@users.sourceforge.net>
parents:
3546
diff
changeset
|
104 |
|
4251
2b1241daaa20
Added more indexer tests for stopwords, case-insensitity...
Bernhard Reiter <Bernhard.Reiter@intevation.de>
parents:
4102
diff
changeset
|
105 def test_stopwords(self): |
|
2b1241daaa20
Added more indexer tests for stopwords, case-insensitity...
Bernhard Reiter <Bernhard.Reiter@intevation.de>
parents:
4102
diff
changeset
|
106 """Test that we can find a text with a stopword in it.""" |
|
2b1241daaa20
Added more indexer tests for stopwords, case-insensitity...
Bernhard Reiter <Bernhard.Reiter@intevation.de>
parents:
4102
diff
changeset
|
107 stopword = "with" |
|
2b1241daaa20
Added more indexer tests for stopwords, case-insensitity...
Bernhard Reiter <Bernhard.Reiter@intevation.de>
parents:
4102
diff
changeset
|
108 self.assert_(self.dex.is_stopword(stopword.upper())) |
|
2b1241daaa20
Added more indexer tests for stopwords, case-insensitity...
Bernhard Reiter <Bernhard.Reiter@intevation.de>
parents:
4102
diff
changeset
|
109 self.dex.add_text(('test', '1', 'bar'), '%s hello world' % stopword) |
|
2b1241daaa20
Added more indexer tests for stopwords, case-insensitity...
Bernhard Reiter <Bernhard.Reiter@intevation.de>
parents:
4102
diff
changeset
|
110 self.dex.add_text(('test', '2', 'bar'), 'blah a %s world' % stopword) |
|
2b1241daaa20
Added more indexer tests for stopwords, case-insensitity...
Bernhard Reiter <Bernhard.Reiter@intevation.de>
parents:
4102
diff
changeset
|
111 self.dex.add_text(('test', '3', 'bar'), 'blah Blub river') |
|
2b1241daaa20
Added more indexer tests for stopwords, case-insensitity...
Bernhard Reiter <Bernhard.Reiter@intevation.de>
parents:
4102
diff
changeset
|
112 self.dex.add_text(('test', '4', 'bar'), 'blah river %s' % stopword) |
|
2b1241daaa20
Added more indexer tests for stopwords, case-insensitity...
Bernhard Reiter <Bernhard.Reiter@intevation.de>
parents:
4102
diff
changeset
|
113 self.assertSeqEqual(self.dex.find(['with','world']), |
|
2b1241daaa20
Added more indexer tests for stopwords, case-insensitity...
Bernhard Reiter <Bernhard.Reiter@intevation.de>
parents:
4102
diff
changeset
|
114 [('test', '1', 'bar'), |
|
2b1241daaa20
Added more indexer tests for stopwords, case-insensitity...
Bernhard Reiter <Bernhard.Reiter@intevation.de>
parents:
4102
diff
changeset
|
115 ('test', '2', 'bar')]) |
|
2b1241daaa20
Added more indexer tests for stopwords, case-insensitity...
Bernhard Reiter <Bernhard.Reiter@intevation.de>
parents:
4102
diff
changeset
|
116 def test_extremewords(self): |
|
2b1241daaa20
Added more indexer tests for stopwords, case-insensitity...
Bernhard Reiter <Bernhard.Reiter@intevation.de>
parents:
4102
diff
changeset
|
117 """Testing too short or too long words.""" |
|
2b1241daaa20
Added more indexer tests for stopwords, case-insensitity...
Bernhard Reiter <Bernhard.Reiter@intevation.de>
parents:
4102
diff
changeset
|
118 short = "b" |
|
2b1241daaa20
Added more indexer tests for stopwords, case-insensitity...
Bernhard Reiter <Bernhard.Reiter@intevation.de>
parents:
4102
diff
changeset
|
119 long = "abcdefghijklmnopqrstuvwxyz" |
|
2b1241daaa20
Added more indexer tests for stopwords, case-insensitity...
Bernhard Reiter <Bernhard.Reiter@intevation.de>
parents:
4102
diff
changeset
|
120 self.dex.add_text(('test', '1', 'a'), '%s hello world' % short) |
|
2b1241daaa20
Added more indexer tests for stopwords, case-insensitity...
Bernhard Reiter <Bernhard.Reiter@intevation.de>
parents:
4102
diff
changeset
|
121 self.dex.add_text(('test', '2', 'a'), 'blah a %s world' % short) |
|
2b1241daaa20
Added more indexer tests for stopwords, case-insensitity...
Bernhard Reiter <Bernhard.Reiter@intevation.de>
parents:
4102
diff
changeset
|
122 self.dex.add_text(('test', '3', 'a'), 'blah Blub river') |
|
2b1241daaa20
Added more indexer tests for stopwords, case-insensitity...
Bernhard Reiter <Bernhard.Reiter@intevation.de>
parents:
4102
diff
changeset
|
123 self.dex.add_text(('test', '4', 'a'), 'blah river %s %s' |
|
2b1241daaa20
Added more indexer tests for stopwords, case-insensitity...
Bernhard Reiter <Bernhard.Reiter@intevation.de>
parents:
4102
diff
changeset
|
124 % (short, long)) |
|
2b1241daaa20
Added more indexer tests for stopwords, case-insensitity...
Bernhard Reiter <Bernhard.Reiter@intevation.de>
parents:
4102
diff
changeset
|
125 self.assertSeqEqual(self.dex.find([short,'world', long, short]), |
|
2b1241daaa20
Added more indexer tests for stopwords, case-insensitity...
Bernhard Reiter <Bernhard.Reiter@intevation.de>
parents:
4102
diff
changeset
|
126 [('test', '1', 'a'), |
|
2b1241daaa20
Added more indexer tests for stopwords, case-insensitity...
Bernhard Reiter <Bernhard.Reiter@intevation.de>
parents:
4102
diff
changeset
|
127 ('test', '2', 'a')]) |
|
2b1241daaa20
Added more indexer tests for stopwords, case-insensitity...
Bernhard Reiter <Bernhard.Reiter@intevation.de>
parents:
4102
diff
changeset
|
128 self.assertSeqEqual(self.dex.find([long]),[]) |
|
2b1241daaa20
Added more indexer tests for stopwords, case-insensitity...
Bernhard Reiter <Bernhard.Reiter@intevation.de>
parents:
4102
diff
changeset
|
129 |
|
2b1241daaa20
Added more indexer tests for stopwords, case-insensitity...
Bernhard Reiter <Bernhard.Reiter@intevation.de>
parents:
4102
diff
changeset
|
130 # special test because some faulty code indexed length(word)>=2 |
|
2b1241daaa20
Added more indexer tests for stopwords, case-insensitity...
Bernhard Reiter <Bernhard.Reiter@intevation.de>
parents:
4102
diff
changeset
|
131 # but only considered length(word)>=3 to be significant |
|
2b1241daaa20
Added more indexer tests for stopwords, case-insensitity...
Bernhard Reiter <Bernhard.Reiter@intevation.de>
parents:
4102
diff
changeset
|
132 self.dex.add_text(('test', '5', 'a'), 'blah py %s %s' |
|
2b1241daaa20
Added more indexer tests for stopwords, case-insensitity...
Bernhard Reiter <Bernhard.Reiter@intevation.de>
parents:
4102
diff
changeset
|
133 % (short, long)) |
|
2b1241daaa20
Added more indexer tests for stopwords, case-insensitity...
Bernhard Reiter <Bernhard.Reiter@intevation.de>
parents:
4102
diff
changeset
|
134 self.assertSeqEqual(self.dex.find(["py"]), [('test', '5', 'a')]) |
|
2b1241daaa20
Added more indexer tests for stopwords, case-insensitity...
Bernhard Reiter <Bernhard.Reiter@intevation.de>
parents:
4102
diff
changeset
|
135 |
|
2b1241daaa20
Added more indexer tests for stopwords, case-insensitity...
Bernhard Reiter <Bernhard.Reiter@intevation.de>
parents:
4102
diff
changeset
|
136 def test_casesensitity(self): |
|
2b1241daaa20
Added more indexer tests for stopwords, case-insensitity...
Bernhard Reiter <Bernhard.Reiter@intevation.de>
parents:
4102
diff
changeset
|
137 """Test if searches are case-in-sensitive.""" |
|
2b1241daaa20
Added more indexer tests for stopwords, case-insensitity...
Bernhard Reiter <Bernhard.Reiter@intevation.de>
parents:
4102
diff
changeset
|
138 self.dex.add_text(('test', '1', 'a'), 'aaaa bbbb') |
|
2b1241daaa20
Added more indexer tests for stopwords, case-insensitity...
Bernhard Reiter <Bernhard.Reiter@intevation.de>
parents:
4102
diff
changeset
|
139 self.dex.add_text(('test', '2', 'a'), 'aAaa BBBB') |
|
2b1241daaa20
Added more indexer tests for stopwords, case-insensitity...
Bernhard Reiter <Bernhard.Reiter@intevation.de>
parents:
4102
diff
changeset
|
140 self.assertSeqEqual(self.dex.find(['aaaa']), |
|
2b1241daaa20
Added more indexer tests for stopwords, case-insensitity...
Bernhard Reiter <Bernhard.Reiter@intevation.de>
parents:
4102
diff
changeset
|
141 [('test', '1', 'a'), |
|
2b1241daaa20
Added more indexer tests for stopwords, case-insensitity...
Bernhard Reiter <Bernhard.Reiter@intevation.de>
parents:
4102
diff
changeset
|
142 ('test', '2', 'a')]) |
|
2b1241daaa20
Added more indexer tests for stopwords, case-insensitity...
Bernhard Reiter <Bernhard.Reiter@intevation.de>
parents:
4102
diff
changeset
|
143 self.assertSeqEqual(self.dex.find(['BBBB']), |
|
2b1241daaa20
Added more indexer tests for stopwords, case-insensitity...
Bernhard Reiter <Bernhard.Reiter@intevation.de>
parents:
4102
diff
changeset
|
144 [('test', '1', 'a'), |
|
2b1241daaa20
Added more indexer tests for stopwords, case-insensitity...
Bernhard Reiter <Bernhard.Reiter@intevation.de>
parents:
4102
diff
changeset
|
145 ('test', '2', 'a')]) |
|
2b1241daaa20
Added more indexer tests for stopwords, case-insensitity...
Bernhard Reiter <Bernhard.Reiter@intevation.de>
parents:
4102
diff
changeset
|
146 |
|
4314
b41a033bffcc
- add a small word-splitting test for the indexers...
Ralf Schlatterbeck <schlatterbeck@users.sourceforge.net>
parents:
4251
diff
changeset
|
147 def test_wordsplitting(self): |
|
b41a033bffcc
- add a small word-splitting test for the indexers...
Ralf Schlatterbeck <schlatterbeck@users.sourceforge.net>
parents:
4251
diff
changeset
|
148 """Test if word splitting works.""" |
|
b41a033bffcc
- add a small word-splitting test for the indexers...
Ralf Schlatterbeck <schlatterbeck@users.sourceforge.net>
parents:
4251
diff
changeset
|
149 self.dex.add_text(('test', '1', 'a'), 'aaaa-aaa bbbb*bbb') |
|
b41a033bffcc
- add a small word-splitting test for the indexers...
Ralf Schlatterbeck <schlatterbeck@users.sourceforge.net>
parents:
4251
diff
changeset
|
150 self.dex.add_text(('test', '2', 'a'), 'aaaA-aaa BBBB*BBB') |
|
b41a033bffcc
- add a small word-splitting test for the indexers...
Ralf Schlatterbeck <schlatterbeck@users.sourceforge.net>
parents:
4251
diff
changeset
|
151 for k in 'aaaa', 'aaa', 'bbbb', 'bbb': |
|
b41a033bffcc
- add a small word-splitting test for the indexers...
Ralf Schlatterbeck <schlatterbeck@users.sourceforge.net>
parents:
4251
diff
changeset
|
152 self.assertSeqEqual(self.dex.find([k]), |
|
b41a033bffcc
- add a small word-splitting test for the indexers...
Ralf Schlatterbeck <schlatterbeck@users.sourceforge.net>
parents:
4251
diff
changeset
|
153 [('test', '1', 'a'), ('test', '2', 'a')]) |
|
b41a033bffcc
- add a small word-splitting test for the indexers...
Ralf Schlatterbeck <schlatterbeck@users.sourceforge.net>
parents:
4251
diff
changeset
|
154 |
|
4841
3ff1a288fb9c
issue2550583, issue2550635 Do not limit results with Xapian indexer
Thomas Arendsen Hein <thomas@intevation.de>
parents:
4570
diff
changeset
|
155 def test_manyresults(self): |
|
3ff1a288fb9c
issue2550583, issue2550635 Do not limit results with Xapian indexer
Thomas Arendsen Hein <thomas@intevation.de>
parents:
4570
diff
changeset
|
156 """Test if searches find many results.""" |
|
3ff1a288fb9c
issue2550583, issue2550635 Do not limit results with Xapian indexer
Thomas Arendsen Hein <thomas@intevation.de>
parents:
4570
diff
changeset
|
157 for i in range(123): |
|
3ff1a288fb9c
issue2550583, issue2550635 Do not limit results with Xapian indexer
Thomas Arendsen Hein <thomas@intevation.de>
parents:
4570
diff
changeset
|
158 self.dex.add_text(('test', str(i), 'many'), 'many') |
|
3ff1a288fb9c
issue2550583, issue2550635 Do not limit results with Xapian indexer
Thomas Arendsen Hein <thomas@intevation.de>
parents:
4570
diff
changeset
|
159 self.assertEqual(len(self.dex.find(['many'])), 123) |
|
3ff1a288fb9c
issue2550583, issue2550635 Do not limit results with Xapian indexer
Thomas Arendsen Hein <thomas@intevation.de>
parents:
4570
diff
changeset
|
160 |
|
848
2a928d404af8
ehem, forgot to add
Richard Jones <richard@users.sourceforge.net>
parents:
diff
changeset
|
161 def tearDown(self): |
|
2a928d404af8
ehem, forgot to add
Richard Jones <richard@users.sourceforge.net>
parents:
diff
changeset
|
162 shutil.rmtree('test-index') |
|
2a928d404af8
ehem, forgot to add
Richard Jones <richard@users.sourceforge.net>
parents:
diff
changeset
|
163 |
|
5096
e74c3611b138
- issue2550636, issue2550909: Added support for Whoosh indexer.
John Rouillard <rouilj@ieee.org>
parents:
5038
diff
changeset
|
164 @skip_whoosh |
|
e74c3611b138
- issue2550636, issue2550909: Added support for Whoosh indexer.
John Rouillard <rouilj@ieee.org>
parents:
5038
diff
changeset
|
165 class WhooshIndexerTest(IndexerTest): |
|
e74c3611b138
- issue2550636, issue2550909: Added support for Whoosh indexer.
John Rouillard <rouilj@ieee.org>
parents:
5038
diff
changeset
|
166 def setUp(self): |
|
e74c3611b138
- issue2550636, issue2550909: Added support for Whoosh indexer.
John Rouillard <rouilj@ieee.org>
parents:
5038
diff
changeset
|
167 if os.path.exists('test-index'): |
|
e74c3611b138
- issue2550636, issue2550909: Added support for Whoosh indexer.
John Rouillard <rouilj@ieee.org>
parents:
5038
diff
changeset
|
168 shutil.rmtree('test-index') |
|
e74c3611b138
- issue2550636, issue2550909: Added support for Whoosh indexer.
John Rouillard <rouilj@ieee.org>
parents:
5038
diff
changeset
|
169 os.mkdir('test-index') |
|
e74c3611b138
- issue2550636, issue2550909: Added support for Whoosh indexer.
John Rouillard <rouilj@ieee.org>
parents:
5038
diff
changeset
|
170 from roundup.backends.indexer_whoosh import Indexer |
|
e74c3611b138
- issue2550636, issue2550909: Added support for Whoosh indexer.
John Rouillard <rouilj@ieee.org>
parents:
5038
diff
changeset
|
171 self.dex = Indexer(db) |
|
e74c3611b138
- issue2550636, issue2550909: Added support for Whoosh indexer.
John Rouillard <rouilj@ieee.org>
parents:
5038
diff
changeset
|
172 def tearDown(self): |
|
e74c3611b138
- issue2550636, issue2550909: Added support for Whoosh indexer.
John Rouillard <rouilj@ieee.org>
parents:
5038
diff
changeset
|
173 shutil.rmtree('test-index') |
|
5036
380d8d8b30a3
Replace existing run_tests.py script with a pytest script
John Kristensen <john@jerrykan.com>
parents:
5033
diff
changeset
|
174 |
|
380d8d8b30a3
Replace existing run_tests.py script with a pytest script
John Kristensen <john@jerrykan.com>
parents:
5033
diff
changeset
|
175 @skip_xapian |
|
3295
a615cc230160
added Xapian indexer; replaces standard indexers if Xapian is available
Richard Jones <richard@users.sourceforge.net>
parents:
3078
diff
changeset
|
176 class XapianIndexerTest(IndexerTest): |
|
a615cc230160
added Xapian indexer; replaces standard indexers if Xapian is available
Richard Jones <richard@users.sourceforge.net>
parents:
3078
diff
changeset
|
177 def setUp(self): |
|
3297
8f7dc283bfa5
some more Xapian stuff (doc, test fixes)
Richard Jones <richard@users.sourceforge.net>
parents:
3295
diff
changeset
|
178 if os.path.exists('test-index'): |
|
8f7dc283bfa5
some more Xapian stuff (doc, test fixes)
Richard Jones <richard@users.sourceforge.net>
parents:
3295
diff
changeset
|
179 shutil.rmtree('test-index') |
|
8f7dc283bfa5
some more Xapian stuff (doc, test fixes)
Richard Jones <richard@users.sourceforge.net>
parents:
3295
diff
changeset
|
180 os.mkdir('test-index') |
|
3295
a615cc230160
added Xapian indexer; replaces standard indexers if Xapian is available
Richard Jones <richard@users.sourceforge.net>
parents:
3078
diff
changeset
|
181 from roundup.backends.indexer_xapian import Indexer |
|
3297
8f7dc283bfa5
some more Xapian stuff (doc, test fixes)
Richard Jones <richard@users.sourceforge.net>
parents:
3295
diff
changeset
|
182 self.dex = Indexer(db) |
|
3295
a615cc230160
added Xapian indexer; replaces standard indexers if Xapian is available
Richard Jones <richard@users.sourceforge.net>
parents:
3078
diff
changeset
|
183 def tearDown(self): |
|
3297
8f7dc283bfa5
some more Xapian stuff (doc, test fixes)
Richard Jones <richard@users.sourceforge.net>
parents:
3295
diff
changeset
|
184 shutil.rmtree('test-index') |
|
3295
a615cc230160
added Xapian indexer; replaces standard indexers if Xapian is available
Richard Jones <richard@users.sourceforge.net>
parents:
3078
diff
changeset
|
185 |
|
5033
63c79c0992ae
Update tests to work with py.test
John Kristensen <john@jerrykan.com>
parents:
4841
diff
changeset
|
186 |
|
63c79c0992ae
Update tests to work with py.test
John Kristensen <john@jerrykan.com>
parents:
4841
diff
changeset
|
187 class RDBMSIndexerTest(object): |
|
4008
0bf9f8ae7d1b
fix bug introduced in 1.4.5 in RDBMS full-text indexing;
Richard Jones <richard@users.sourceforge.net>
parents:
3547
diff
changeset
|
188 def setUp(self): |
|
0bf9f8ae7d1b
fix bug introduced in 1.4.5 in RDBMS full-text indexing;
Richard Jones <richard@users.sourceforge.net>
parents:
3547
diff
changeset
|
189 # remove previous test, ignore errors |
|
0bf9f8ae7d1b
fix bug introduced in 1.4.5 in RDBMS full-text indexing;
Richard Jones <richard@users.sourceforge.net>
parents:
3547
diff
changeset
|
190 if os.path.exists(config.DATABASE): |
|
0bf9f8ae7d1b
fix bug introduced in 1.4.5 in RDBMS full-text indexing;
Richard Jones <richard@users.sourceforge.net>
parents:
3547
diff
changeset
|
191 shutil.rmtree(config.DATABASE) |
|
0bf9f8ae7d1b
fix bug introduced in 1.4.5 in RDBMS full-text indexing;
Richard Jones <richard@users.sourceforge.net>
parents:
3547
diff
changeset
|
192 self.db = self.module.Database(config, 'admin') |
|
0bf9f8ae7d1b
fix bug introduced in 1.4.5 in RDBMS full-text indexing;
Richard Jones <richard@users.sourceforge.net>
parents:
3547
diff
changeset
|
193 self.dex = Indexer(self.db) |
|
0bf9f8ae7d1b
fix bug introduced in 1.4.5 in RDBMS full-text indexing;
Richard Jones <richard@users.sourceforge.net>
parents:
3547
diff
changeset
|
194 def tearDown(self): |
|
0bf9f8ae7d1b
fix bug introduced in 1.4.5 in RDBMS full-text indexing;
Richard Jones <richard@users.sourceforge.net>
parents:
3547
diff
changeset
|
195 if hasattr(self, 'db'): |
|
0bf9f8ae7d1b
fix bug introduced in 1.4.5 in RDBMS full-text indexing;
Richard Jones <richard@users.sourceforge.net>
parents:
3547
diff
changeset
|
196 self.db.close() |
|
0bf9f8ae7d1b
fix bug introduced in 1.4.5 in RDBMS full-text indexing;
Richard Jones <richard@users.sourceforge.net>
parents:
3547
diff
changeset
|
197 if os.path.exists(config.DATABASE): |
|
0bf9f8ae7d1b
fix bug introduced in 1.4.5 in RDBMS full-text indexing;
Richard Jones <richard@users.sourceforge.net>
parents:
3547
diff
changeset
|
198 shutil.rmtree(config.DATABASE) |
|
0bf9f8ae7d1b
fix bug introduced in 1.4.5 in RDBMS full-text indexing;
Richard Jones <richard@users.sourceforge.net>
parents:
3547
diff
changeset
|
199 |
|
5033
63c79c0992ae
Update tests to work with py.test
John Kristensen <john@jerrykan.com>
parents:
4841
diff
changeset
|
200 |
|
5036
380d8d8b30a3
Replace existing run_tests.py script with a pytest script
John Kristensen <john@jerrykan.com>
parents:
5033
diff
changeset
|
201 @skip_postgresql |
|
5033
63c79c0992ae
Update tests to work with py.test
John Kristensen <john@jerrykan.com>
parents:
4841
diff
changeset
|
202 class postgresqlIndexerTest(postgresqlOpener, RDBMSIndexerTest, IndexerTest): |
|
4008
0bf9f8ae7d1b
fix bug introduced in 1.4.5 in RDBMS full-text indexing;
Richard Jones <richard@users.sourceforge.net>
parents:
3547
diff
changeset
|
203 def setUp(self): |
|
0bf9f8ae7d1b
fix bug introduced in 1.4.5 in RDBMS full-text indexing;
Richard Jones <richard@users.sourceforge.net>
parents:
3547
diff
changeset
|
204 postgresqlOpener.setUp(self) |
|
0bf9f8ae7d1b
fix bug introduced in 1.4.5 in RDBMS full-text indexing;
Richard Jones <richard@users.sourceforge.net>
parents:
3547
diff
changeset
|
205 RDBMSIndexerTest.setUp(self) |
|
0bf9f8ae7d1b
fix bug introduced in 1.4.5 in RDBMS full-text indexing;
Richard Jones <richard@users.sourceforge.net>
parents:
3547
diff
changeset
|
206 def tearDown(self): |
|
0bf9f8ae7d1b
fix bug introduced in 1.4.5 in RDBMS full-text indexing;
Richard Jones <richard@users.sourceforge.net>
parents:
3547
diff
changeset
|
207 RDBMSIndexerTest.tearDown(self) |
|
0bf9f8ae7d1b
fix bug introduced in 1.4.5 in RDBMS full-text indexing;
Richard Jones <richard@users.sourceforge.net>
parents:
3547
diff
changeset
|
208 postgresqlOpener.tearDown(self) |
|
0bf9f8ae7d1b
fix bug introduced in 1.4.5 in RDBMS full-text indexing;
Richard Jones <richard@users.sourceforge.net>
parents:
3547
diff
changeset
|
209 |
|
5033
63c79c0992ae
Update tests to work with py.test
John Kristensen <john@jerrykan.com>
parents:
4841
diff
changeset
|
210 |
|
5036
380d8d8b30a3
Replace existing run_tests.py script with a pytest script
John Kristensen <john@jerrykan.com>
parents:
5033
diff
changeset
|
211 @skip_mysql |
|
5033
63c79c0992ae
Update tests to work with py.test
John Kristensen <john@jerrykan.com>
parents:
4841
diff
changeset
|
212 class mysqlIndexerTest(mysqlOpener, RDBMSIndexerTest, IndexerTest): |
|
4008
0bf9f8ae7d1b
fix bug introduced in 1.4.5 in RDBMS full-text indexing;
Richard Jones <richard@users.sourceforge.net>
parents:
3547
diff
changeset
|
213 def setUp(self): |
|
0bf9f8ae7d1b
fix bug introduced in 1.4.5 in RDBMS full-text indexing;
Richard Jones <richard@users.sourceforge.net>
parents:
3547
diff
changeset
|
214 mysqlOpener.setUp(self) |
|
0bf9f8ae7d1b
fix bug introduced in 1.4.5 in RDBMS full-text indexing;
Richard Jones <richard@users.sourceforge.net>
parents:
3547
diff
changeset
|
215 RDBMSIndexerTest.setUp(self) |
|
0bf9f8ae7d1b
fix bug introduced in 1.4.5 in RDBMS full-text indexing;
Richard Jones <richard@users.sourceforge.net>
parents:
3547
diff
changeset
|
216 def tearDown(self): |
|
0bf9f8ae7d1b
fix bug introduced in 1.4.5 in RDBMS full-text indexing;
Richard Jones <richard@users.sourceforge.net>
parents:
3547
diff
changeset
|
217 RDBMSIndexerTest.tearDown(self) |
|
0bf9f8ae7d1b
fix bug introduced in 1.4.5 in RDBMS full-text indexing;
Richard Jones <richard@users.sourceforge.net>
parents:
3547
diff
changeset
|
218 mysqlOpener.tearDown(self) |
|
0bf9f8ae7d1b
fix bug introduced in 1.4.5 in RDBMS full-text indexing;
Richard Jones <richard@users.sourceforge.net>
parents:
3547
diff
changeset
|
219 |
|
5033
63c79c0992ae
Update tests to work with py.test
John Kristensen <john@jerrykan.com>
parents:
4841
diff
changeset
|
220 |
|
63c79c0992ae
Update tests to work with py.test
John Kristensen <john@jerrykan.com>
parents:
4841
diff
changeset
|
221 class sqliteIndexerTest(sqliteOpener, RDBMSIndexerTest, IndexerTest): |
|
4008
0bf9f8ae7d1b
fix bug introduced in 1.4.5 in RDBMS full-text indexing;
Richard Jones <richard@users.sourceforge.net>
parents:
3547
diff
changeset
|
222 pass |
|
0bf9f8ae7d1b
fix bug introduced in 1.4.5 in RDBMS full-text indexing;
Richard Jones <richard@users.sourceforge.net>
parents:
3547
diff
changeset
|
223 |
|
848
2a928d404af8
ehem, forgot to add
Richard Jones <richard@users.sourceforge.net>
parents:
diff
changeset
|
224 # vim: set filetype=python ts=4 sw=4 et si |
