Mercurial > public > mercurial-scm > hg-stable

comparison tests/test-encoding-func.py @ 52682:62546ee1f56b

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
pyupgrade: drop redundant `''.encode("utf-8")` Again, I'd prefer explicit. But without a way to selectively choose what fixes are applied by `_fix_tokens()`, I'll accept this for the sake of reducing the nuisance output when running `pyupgrade`.
author Matt Harbison <matt_harbison@yahoo.com>
date Tue, 07 Jan 2025 17:36:13 -0500
parents 9db77d46de79
children
comparison
equal deleted inserted replaced
52681:3e84e001b6c1 52682:62546ee1f56b
45 self.assertTrue(s is encoding.toutf8b(s)) 45 self.assertTrue(s is encoding.toutf8b(s))
46 self.assertTrue(s is encoding.fromutf8b(s)) 46 self.assertTrue(s is encoding.fromutf8b(s))
47 47
48 def testlossylatin(self): 48 def testlossylatin(self):
49 encoding.encoding = b'ascii' 49 encoding.encoding = b'ascii'
50 s = '\xc0'.encode('utf-8') 50 s = '\xc0'.encode()
51 l = encoding.tolocal(s) 51 l = encoding.tolocal(s)
52 self.assertEqual(l, b'?') # lossy 52 self.assertEqual(l, b'?') # lossy
53 self.assertEqual(s, encoding.toutf8b(l)) # utf8 sequence preserved 53 self.assertEqual(s, encoding.toutf8b(l)) # utf8 sequence preserved
54 54
55 def testlosslesslatin(self): 55 def testlosslesslatin(self):
56 encoding.encoding = b'latin-1' 56 encoding.encoding = b'latin-1'
57 s = '\xc0'.encode('utf-8') 57 s = '\xc0'.encode()
58 l = encoding.tolocal(s) 58 l = encoding.tolocal(s)
59 self.assertEqual(l, b'\xc0') # lossless 59 self.assertEqual(l, b'\xc0') # lossless
60 self.assertEqual(s, encoding.toutf8b(l)) # convert back to utf-8 60 self.assertEqual(s, encoding.toutf8b(l)) # convert back to utf-8
61 61
62 def testlossy0xed(self): 62 def testlossy0xed(self):
63 encoding.encoding = b'euc-kr' # U+Dxxx Hangul 63 encoding.encoding = b'euc-kr' # U+Dxxx Hangul
64 s = '\ud1bc\xc0'.encode('utf-8') 64 s = '\ud1bc\xc0'.encode()
65 l = encoding.tolocal(s) 65 l = encoding.tolocal(s)
66 self.assertIn(b'\xed', l) 66 self.assertIn(b'\xed', l)
67 self.assertTrue(l.endswith(b'?')) # lossy 67 self.assertTrue(l.endswith(b'?')) # lossy
68 self.assertEqual(s, encoding.toutf8b(l)) # utf8 sequence preserved 68 self.assertEqual(s, encoding.toutf8b(l)) # utf8 sequence preserved
69 69
70 def testlossless0xed(self): 70 def testlossless0xed(self):
71 encoding.encoding = b'euc-kr' # U+Dxxx Hangul 71 encoding.encoding = b'euc-kr' # U+Dxxx Hangul
72 s = '\ud1bc'.encode('utf-8') 72 s = '\ud1bc'.encode()
73 l = encoding.tolocal(s) 73 l = encoding.tolocal(s)
74 self.assertEqual(l, b'\xc5\xed') # lossless 74 self.assertEqual(l, b'\xc5\xed') # lossless
75 self.assertEqual(s, encoding.toutf8b(l)) # convert back to utf-8 75 self.assertEqual(s, encoding.toutf8b(l)) # convert back to utf-8
76 76
77 77