annotate tests/test-encoding-func.py @ 50195:11e6eee4b063

transaction: use the standard transaction mechanism to backup branch

Branch is a bit special :
- It currently does not collaborate with the transaction (or any scoping) for
  writing (this is bad)
- It can change without the lock being taken (it is protected by `wlock`)

So we rely on the same mechanism as for the backup of the other dirstate file:
- we only do a backup if we hold the wlock
- we force a backup though the transaction


Since "branch" write does not collaborate with the transaction, we cannot back
it up "at the last minute" as we do for the dirstate. We have to back it up
"upfront". Since we have a backup, the transaction is no longer doing its
"quick_abort" and get noisy. Which is quite annoying. To work around this, and
to avoid jumping in yet-another-rabbit-hole of "getting branch written
properly", I am doing horrible things to the transaction in the meantime.
We should be able to get this code go away during the next cycle.

In the meantime, I prefer to take this small stop so that we stop abusing the
"journal" and "undo" mechanism instead of the proper backup mechanism of the
transaction.


Also note that this change regress the warning message for the legacy fallback
introduced in 2008 when issue902 got fixed in dd5a501cb97f (Mercurial 1.0).

I feel like this is fine as issue 902 remains fixed, and this would only affect
people deploying a mix of 15 year old Mercurial and modern mercurial, and using
branch and rollback extensively.

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__)