view tests/test-encoding-func.py @ 40623:7c5a922be068

tests: document a known failing interaction between narrow and lfs

This is one of the two remaining aborts I found looking into issue5794.  I've
got no idea what's wrong with the hook, since the changes there fixed the other
two problems noted in that bug report.  It seems like it might go away when the
narrow issue is fixed, but let's make sure this doesn't get lost.

The stacktrace for the hook seems to indicate that the missing file *is* in ctx:

  remote: Traceback (most recent call last):
  remote:   File "c:\Users\Matt\projects\hg\hgext\lfs\__init__.py", line 253, in checkrequireslfs
  remote:     if any(f in ctx and match(f) and ctx[f].islfs() for f in ctx.files()):
  remote:   File "c:\Users\Matt\projects\hg\hgext\lfs\__init__.py", line 253, in <genexpr>
  remote:     if any(f in ctx and match(f) and ctx[f].islfs() for f in ctx.files()):
  remote:   File "c:\Users\Matt\projects\hg\hgext\lfs\wrapper.py", line 191, in filectxislfs
  remote:     return _islfs(self.filelog(), self.filenode())
  remote:   File "c:\Users\Matt\projects\hg\mercurial\context.py", line 631, in filenode
  remote:     return self._filenode
  remote:   File "c:\Users\Matt\projects\hg\mercurial\util.py", line 1528, in __get__
  remote:     result = self.func(obj)
  remote:   File "c:\Users\Matt\projects\hg\mercurial\context.py", line 579, in _filenode
  remote:     return self._filelog.lookup(self._fileid)
  remote:   File "c:\Users\Matt\projects\hg\mercurial\filelog.py", line 68, in lookup
  remote:     self._revlog.indexfile)
  remote:   File "c:\Users\Matt\projects\hg\mercurial\utils\storageutil.py", line 218, in fileidlookup
  remote:     raise error.LookupError(fileid, identifier, _('no match found'))
  remote: LookupError: data/inside2/f.i@f59b4e021835: no match found

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__)