Mercurial > p > roundup > code
view test/test_indexer.py @ 5542:29346d92d80c
Fix email interfaces with Python 3 (issue 2550974, issue 2551000).
This patch fixes various issues handling incoming email with
roundup-mailgw with Python 3.
Incoming email must always be handled as bytes, not strings, because
it may contain 8-bit-encoded MIME parts with different encodings in
each part. When handling piped input, that means using
sys.stdin.buffer in Python 3 for binary input, along with
message_from_binary_file, not sys.stdin which is text input and may be
for the wrong encoding and not message_from_file. (In turn, tests
that use MailGW.main with text input are affected so an s2b call is
inserted in the test code and it is made to use BytesIO not StringIO.
Properly all the test messages in test_mailgw.py ought to use b''
explicitly rather than having such an s2b conversion, and there ought
to be test messages using 8-bit encodings with non-ASCII characters to
verify that that case works.)
imaplib and poplib return bytes not strings with Python 3 (from
inspection of the code, not tested), as is necessary for the above
reasons. Thus, the handling of IMAP and POP messages must expect
bytes and handle the data accordingly.
For messages from mailboxes, I saw the same problem described in issue
2551000 for a multipart message with a single (non-ASCII) part. The
Roundup code requires RoundupMessage not email.message.Message to be
used recursively for all MIME parts of a message. Because the mailbox
module uses email.message_from_* directly without passing the _class
argument to them, fixing this requires temporarily patching the email
module to ensure _class=RoundupMessage gets passed to those methods.
| author | Joseph Myers <jsm@polyomino.org.uk> |
|---|---|
| date | Sun, 16 Sep 2018 13:55:53 +0000 |
| parents | d26921b851c3 |
| children | f8893e1cde0d |
line wrap: on
line source
# Copyright (c) 2002 ekit.com Inc (http://www.ekit-inc.com/) # # Permission is hereby granted, free of charge, to any person obtaining a copy # of this software and associated documentation files (the "Software"), to deal # in the Software without restriction, including without limitation the rights # to use, copy, modify, merge, publish, distribute, sublicense, and/or sell # copies of the Software, and to permit persons to whom the Software is # furnished to do so, subject to the following conditions: # # The above copyright notice and this permission notice shall be included in # all copies or substantial portions of the Software. # # THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR # IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, # FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE # AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER # LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, # OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE # SOFTWARE. import os, unittest, shutil import pytest from roundup.backends import get_backend, have_backend from roundup.backends.indexer_rdbms import Indexer # borrow from other tests from .db_test_base import setupSchema, config from .test_postgresql import postgresqlOpener, skip_postgresql from .test_mysql import mysqlOpener, skip_mysql from .test_sqlite import sqliteOpener try: import xapian skip_xapian = lambda func, *args, **kwargs: func except ImportError: # FIX: workaround for a bug in pytest.mark.skip(): # https://github.com/pytest-dev/pytest/issues/568 from .pytest_patcher import mark_class skip_xapian = mark_class(pytest.mark.skip( "Skipping Xapian indexer tests: 'xapian' not installed")) try: import whoosh skip_whoosh = lambda func, *args, **kwargs: func except ImportError: # FIX: workaround for a bug in pytest.mark.skip(): # https://github.com/pytest-dev/pytest/issues/568 from .pytest_patcher import mark_class skip_whoosh = mark_class(pytest.mark.skip( "Skipping Whoosh indexer tests: 'whoosh' not installed")) class db: class config(dict): DATABASE = 'test-index' config = config() config[('main', 'indexer_stopwords')] = [] class IndexerTest(unittest.TestCase): def setUp(self): if os.path.exists('test-index'): shutil.rmtree('test-index') os.mkdir('test-index') os.mkdir('test-index/files') from roundup.backends.indexer_dbm import Indexer self.dex = Indexer(db) self.dex.load_index() def assertSeqEqual(self, s1, s2): # First argument is the db result we're testing, second is the # desired result. Some db results don't have iterable rows, so we # have to work around that. # Also work around some dbs not returning items in the expected # order. s1 = list([tuple([r[n] for n in range(len(r))]) for r in s1]) s1.sort() if s1 != s2: self.fail('contents of %r != %r'%(s1, s2)) def test_basics(self): self.dex.add_text(('test', '1', 'foo'), 'a the hello world') self.dex.add_text(('test', '2', 'foo'), 'blah blah the world') self.assertSeqEqual(self.dex.find(['world']), [('test', '1', 'foo'), ('test', '2', 'foo')]) self.assertSeqEqual(self.dex.find(['blah']), [('test', '2', 'foo')]) self.assertSeqEqual(self.dex.find(['blah', 'hello']), []) def test_change(self): self.dex.add_text(('test', '1', 'foo'), 'a the hello world') self.dex.add_text(('test', '2', 'foo'), 'blah blah the world') self.assertSeqEqual(self.dex.find(['world']), [('test', '1', 'foo'), ('test', '2', 'foo')]) self.dex.add_text(('test', '1', 'foo'), 'a the hello') self.assertSeqEqual(self.dex.find(['world']), [('test', '2', 'foo')]) def test_clear(self): self.dex.add_text(('test', '1', 'foo'), 'a the hello world') self.dex.add_text(('test', '2', 'foo'), 'blah blah the world') self.assertSeqEqual(self.dex.find(['world']), [('test', '1', 'foo'), ('test', '2', 'foo')]) self.dex.add_text(('test', '1', 'foo'), '') self.assertSeqEqual(self.dex.find(['world']), [('test', '2', 'foo')]) def test_stopwords(self): """Test that we can find a text with a stopword in it.""" stopword = "with" self.assert_(self.dex.is_stopword(stopword.upper())) self.dex.add_text(('test', '1', 'bar'), '%s hello world' % stopword) self.dex.add_text(('test', '2', 'bar'), 'blah a %s world' % stopword) self.dex.add_text(('test', '3', 'bar'), 'blah Blub river') self.dex.add_text(('test', '4', 'bar'), 'blah river %s' % stopword) self.assertSeqEqual(self.dex.find(['with','world']), [('test', '1', 'bar'), ('test', '2', 'bar')]) def test_extremewords(self): """Testing too short or too long words.""" short = "b" long = "abcdefghijklmnopqrstuvwxyz" self.dex.add_text(('test', '1', 'a'), '%s hello world' % short) self.dex.add_text(('test', '2', 'a'), 'blah a %s world' % short) self.dex.add_text(('test', '3', 'a'), 'blah Blub river') self.dex.add_text(('test', '4', 'a'), 'blah river %s %s' % (short, long)) self.assertSeqEqual(self.dex.find([short,'world', long, short]), [('test', '1', 'a'), ('test', '2', 'a')]) self.assertSeqEqual(self.dex.find([long]),[]) # special test because some faulty code indexed length(word)>=2 # but only considered length(word)>=3 to be significant self.dex.add_text(('test', '5', 'a'), 'blah py %s %s' % (short, long)) self.assertSeqEqual(self.dex.find(["py"]), [('test', '5', 'a')]) def test_casesensitity(self): """Test if searches are case-in-sensitive.""" self.dex.add_text(('test', '1', 'a'), 'aaaa bbbb') self.dex.add_text(('test', '2', 'a'), 'aAaa BBBB') self.assertSeqEqual(self.dex.find(['aaaa']), [('test', '1', 'a'), ('test', '2', 'a')]) self.assertSeqEqual(self.dex.find(['BBBB']), [('test', '1', 'a'), ('test', '2', 'a')]) def test_wordsplitting(self): """Test if word splitting works.""" self.dex.add_text(('test', '1', 'a'), 'aaaa-aaa bbbb*bbb') self.dex.add_text(('test', '2', 'a'), 'aaaA-aaa BBBB*BBB') for k in 'aaaa', 'aaa', 'bbbb', 'bbb': self.assertSeqEqual(self.dex.find([k]), [('test', '1', 'a'), ('test', '2', 'a')]) def test_manyresults(self): """Test if searches find many results.""" for i in range(123): self.dex.add_text(('test', str(i), 'many'), 'many') self.assertEqual(len(self.dex.find(['many'])), 123) def tearDown(self): shutil.rmtree('test-index') @skip_whoosh class WhooshIndexerTest(IndexerTest): def setUp(self): if os.path.exists('test-index'): shutil.rmtree('test-index') os.mkdir('test-index') from roundup.backends.indexer_whoosh import Indexer self.dex = Indexer(db) def tearDown(self): shutil.rmtree('test-index') @skip_xapian class XapianIndexerTest(IndexerTest): def setUp(self): if os.path.exists('test-index'): shutil.rmtree('test-index') os.mkdir('test-index') from roundup.backends.indexer_xapian import Indexer self.dex = Indexer(db) def tearDown(self): shutil.rmtree('test-index') class RDBMSIndexerTest(object): def setUp(self): # remove previous test, ignore errors if os.path.exists(config.DATABASE): shutil.rmtree(config.DATABASE) self.db = self.module.Database(config, 'admin') self.dex = Indexer(self.db) def tearDown(self): if hasattr(self, 'db'): self.db.close() if os.path.exists(config.DATABASE): shutil.rmtree(config.DATABASE) @skip_postgresql class postgresqlIndexerTest(postgresqlOpener, RDBMSIndexerTest, IndexerTest): def setUp(self): postgresqlOpener.setUp(self) RDBMSIndexerTest.setUp(self) def tearDown(self): RDBMSIndexerTest.tearDown(self) postgresqlOpener.tearDown(self) @skip_mysql class mysqlIndexerTest(mysqlOpener, RDBMSIndexerTest, IndexerTest): def setUp(self): mysqlOpener.setUp(self) RDBMSIndexerTest.setUp(self) def tearDown(self): RDBMSIndexerTest.tearDown(self) mysqlOpener.tearDown(self) class sqliteIndexerTest(sqliteOpener, RDBMSIndexerTest, IndexerTest): pass # vim: set filetype=python ts=4 sw=4 et si
