Mercurial > hg
view tests/test-encoding-func.py @ 42753:fce6dc93a510
rust-dirstate: rust implementation of dirstatemap
The `dirstatemap` is one of the last building blocks needed to get to a
`dirstate.walk` Rust implementation.
Disclaimer: This change is part of a big (10) series of patches, all of which
started as one big changeset that took a long time to write.
This `dirstatemap` implementation is a compromise in terms of complexity both
for me and for the reviewers. I chose to submit this patch right now because
while it is not perfect, it works and is simple enough (IMHO) to be reviewed.
The Python implementation uses a lot of lazy propertycaches, breaks
encapsulation and is used as an iterator in a lot of places, all of which
dictated the somewhat unidiomatic patterns in this change.
Like written in the comments, rewriting this struct to use the typestate
pattern might be a good idea, but this is a good first step.
Differential Revision: https://phab.mercurial-scm.org/D6632
author | Raphaël Gomès <rgomes@octobus.net> |
---|---|
date | Wed, 10 Jul 2019 09:56:23 +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__)