py: error out if a "skip" character was given with non-dict to util.dirs()
util.dirs() keeps track of the directories in its input collection. If
a "skip" character is given to it, it will assume the input is a
dirstate map and it will skip entries that are in the given "skip"
state. I think this is used only for skipping removed entries ("r") in
the dirtate. The C implementation of util.dirs() errors out if it was
given a skip character and a non-dict was passed. The pure
implementation simply ignored the request skip state. Let's make it
easier to discover bugs here by erroring out in the pure
implementation too. Let's also switch to checking for the dict-ness,
to make the C implementation (since that's clearly been sufficient for
many years). This last change makes test-
issue660.t pass on py3 in
pure mode, since the old check was for existence of iteritems(), which
doesn't exist on py3.
Differential Revision: https://phab.mercurial-scm.org/D6669
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__)