Mercurial > hg
view tests/test-encoding-func.py @ 40527:1b49b84d5ed5
pycompat: adding Linux detection and fixing Mac
Python 3 recommends detecting OSs with the prefix of the platform, but we were
comparing the full string for macOS. We also didn't have Linux detection, which
is convenient for extensions to use (rather than have some OSs detected by hg
and some by the extension).
Reference:
https://docs.python.org/3/library/sys.html#sys.platform
Differential Revision: https://phab.mercurial-scm.org/D5227
author | rdamazio@google.com |
---|---|
date | Mon, 05 Nov 2018 19:52:42 -0800 |
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__)