Mercurial > hg
view tests/test-encoding-func.py @ 42353:f22131315791
tests: make the grep pattern in remotefilelog-gcrepack portable (issue6122)
test-remotefilelog-gcrepack was using "\" to escape "|" in the grep pattern.
The most of implementations ignore "\" when it is followed by "|", so the regex
works. However, OpenBSD doesn't ignore "\" and considers "|" part of the text
instead of create two branches. Neither of both behaviors violate POSIX.
This change removes the unnecessary escape character and changes grep to egrep,
so the extended regular expression works on every unix.
This is part of the bug 6122. Tested on OpenBSD, GNU, FreeBSD, NetBSD, Solaris
11 and BusyBox.
Credits to Todd C. Miller, Paul de Weerd and Ingo Schwarze for helping me with
it.
author | Juan Francisco Cantero Hurtado <iam@juanfra.info> |
---|---|
date | Tue, 21 May 2019 19:23:14 +0200 |
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__)