view test/test_token.py @ 5543:bc3e00a3d24b

MySQL backend fixes for Python 3. With Python 2, text sent to and from MySQL is treated as bytes in Python. The database may be recorded by MySQL as having some other encoding (latin1 being the default in some MySQL versions - Roundup does not set an encoding explicitly, unlike in back_postgresql), but as long as MySQL's notion of the connection encoding agrees with its notion of the database encoding, no conversions actually take place and the bytes are stored and returned as-is. With Python 3, text sent to and from MySQL is treated as Python Unicode strings. When the database and connection encoding is latin1, that means the bytes stored in the database under Python 2 are interpreted as latin1 and converted from that to Unicode, producing incorrect results for any non-ASCII characters; furthermore, if trying to store new non-ASCII data in the database under Python 3, any non-latin1 characters produce errors. This patch arranges for both the connection and database character sets to be UTF-8 when using Python 3, and documents a need to export and import the database when moving from Python 2 to Python 3 with this backend.
author Joseph Myers <jsm@polyomino.org.uk>
date Sun, 16 Sep 2018 16:19:20 +0000
parents 364c54991861
children 6971c9249c6d
line wrap: on
line source

#
# Copyright (c) 2001 Richard Jones
# This module is free software, and you may redistribute it and/or modify
# under the same terms as Python, so long as this copyright message and
# disclaimer are retained in their original form.
#
# This module is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.

import unittest, time

from roundup.token import token_split

class TokenTestCase(unittest.TestCase):
    def testValid(self):
        l = token_split('hello world')
        self.assertEqual(l, ['hello', 'world'])

    def testIgnoreExtraSpace(self):
        l = token_split('hello  world ')
        self.assertEqual(l, ['hello', 'world'])

    def testQuoting(self):
        l = token_split('"hello world"')
        self.assertEqual(l, ['hello world'])
        l = token_split("'hello world'")
        self.assertEqual(l, ['hello world'])

    def testEmbedQuote(self):
        l = token_split(r'Roch\'e Compaan')
        self.assertEqual(l, ["Roch'e", "Compaan"])
        l = token_split('address="1 2 3"')
        self.assertEqual(l, ['address=1 2 3'])

    def testEscaping(self):
        l = token_split('"Roch\'e" Compaan')
        self.assertEqual(l, ["Roch'e", "Compaan"])
        l = token_split(r'hello\ world')
        self.assertEqual(l, ['hello world'])
        l = token_split(r'\\')
        self.assertEqual(l, ['\\'])
        l = token_split(r'\n')
        self.assertEqual(l, ['\n'])

    def testBadQuote(self):
        self.assertRaises(ValueError, token_split, '"hello world')
        self.assertRaises(ValueError, token_split, "Roch'e Compaan")

# vim: set filetype=python ts=4 sw=4 et si

Roundup Issue Tracker: http://roundup-tracker.org/