view tests/test-encoding-func.py @ 39548:7ce9dea3a14a

localrepo: move repo creation logic out of localrepository.__init__ (API) It has long bothered me that local repository creation is handled as part of localrepository.__init__. Upcoming changes I want to make around how repositories are initialized and instantiated will make the continued existence of repository creation code in localrepository.__init__ even more awkward. localrepository instances are almost never constructed directly: instead, callers are supposed to go through hg.repository() to obtain a handle on a repository. And hg.repository() calls localrepo.instance() to return a new repo instance. This commit teaches localrepo.instance() to handle the create=True logic. Most of the code for repo construction has been moved to a standalone function. This allows extensions to monkeypatch the function to further customize freshly-created repositories. A few calls to localrepo.localrepository.__init__ that were passing create=True were converted to call localrepo.instance(). .. api:: local repo creation moved out of constructor ``localrepo.localrepository.__init__`` no longer accepts a ``create`` argument to create a new repository. New repository creation is now performed as part of ``localrepo.instance()`` and the bulk of the work is performed by ``localrepo.createrepository()``. Differential Revision: https://phab.mercurial-scm.org/D4534
author Gregory Szorc <gregory.szorc@gmail.com>
date Tue, 11 Sep 2018 13:46:59 -0700
parents 3ea3c96ada54
children 2372284d9457
line wrap: on
line source

from __future__ import absolute_import

import unittest

from mercurial import (
    encoding,
)

class IsasciistrTest(unittest.TestCase):
    asciistrs = [
        b'a',
        b'ab',
        b'abc',
        b'abcd',
        b'abcde',
        b'abcdefghi',
        b'abcd\0fghi',
    ]

    def testascii(self):
        for s in self.asciistrs:
            self.assertTrue(encoding.isasciistr(s))

    def testnonasciichar(self):
        for s in self.asciistrs:
            for i in range(len(s)):
                t = bytearray(s)
                t[i] |= 0x80
                self.assertFalse(encoding.isasciistr(bytes(t)))

class LocalEncodingTest(unittest.TestCase):
    def testasciifastpath(self):
        s = b'\0' * 100
        self.assertTrue(s is encoding.tolocal(s))
        self.assertTrue(s is encoding.fromlocal(s))

class Utf8bEncodingTest(unittest.TestCase):
    def setUp(self):
        self.origencoding = encoding.encoding

    def tearDown(self):
        encoding.encoding = self.origencoding

    def testasciifastpath(self):
        s = b'\0' * 100
        self.assertTrue(s is encoding.toutf8b(s))
        self.assertTrue(s is encoding.fromutf8b(s))

    def testlossylatin(self):
        encoding.encoding = b'ascii'
        s = u'\xc0'.encode('utf-8')
        l = encoding.tolocal(s)
        self.assertEqual(l, b'?')  # lossy
        self.assertEqual(s, encoding.toutf8b(l))  # utf8 sequence preserved

    def testlosslesslatin(self):
        encoding.encoding = b'latin-1'
        s = u'\xc0'.encode('utf-8')
        l = encoding.tolocal(s)
        self.assertEqual(l, b'\xc0')  # lossless
        self.assertEqual(s, encoding.toutf8b(l))  # convert back to utf-8

    def testlossy0xed(self):
        encoding.encoding = b'euc-kr'  # U+Dxxx Hangul
        s = u'\ud1bc\xc0'.encode('utf-8')
        l = encoding.tolocal(s)
        self.assertIn(b'\xed', l)
        self.assertTrue(l.endswith(b'?'))  # lossy
        self.assertEqual(s, encoding.toutf8b(l))  # utf8 sequence preserved

    def testlossless0xed(self):
        encoding.encoding = b'euc-kr'  # U+Dxxx Hangul
        s = u'\ud1bc'.encode('utf-8')
        l = encoding.tolocal(s)
        self.assertEqual(l, b'\xc5\xed')  # lossless
        self.assertEqual(s, encoding.toutf8b(l))  # convert back to utf-8

if __name__ == '__main__':
    import silenttestrunner
    silenttestrunner.main(__name__)