view tests/test-encoding-func.py @ 39270:37e56607cbb9

lfs: add a progress bar when searching for blobs to upload

The search itself can take an extreme amount of time if there are a lot of
revisions involved.  I've got a local repo that took 6 minutes to push 1850
commits, and 60% of that time was spent here (there are ~70K files):

     \ 58.1%  wrapper.py:     extractpointers      line 297:  pointers = extractpointers(...
       | 57.7%  wrapper.py:     pointersfromctx    line 352:  for p in pointersfromctx(ct...
       | 57.4%  wrapper.py:     pointerfromctx     line 397:  p = pointerfromctx(ctx, f, ...
         \ 38.7%  context.py:     __contains__     line 368:  if f not in ctx:
           | 38.7%  util.py:        __get__        line 82:  return key in self._manifest
           | 38.7%  context.py:     _manifest      line 1416:  result = self.func(obj)
           | 38.7%  manifest.py:    read           line 472:  return self._manifestctx.re...
             \ 25.6%  revlog.py:      revision     line 1562:  text = rl.revision(self._node)
               \ 12.8%  revlog.py:      _chunks    line 2217:  bins = self._chunks(chain, ...
                 | 12.0%  revlog.py:      decompressline 2112:  ladd(decomp(buffer(data, ch...
               \  7.8%  revlog.py:      checkhash  line 2232:  self.checkhash(text, node, ...
                 |  7.8%  revlog.py:      hash     line 2315:  if node != self.hash(text, ...
                 |  7.8%  revlog.py:      hash     line 2242:  return hash(text, p1, p2)
             \ 12.0%  manifest.py:    __init__     line 1565:  self._data = manifestdict(t...
         \ 16.8%  context.py:     filenode         line 378:  if not _islfs(fctx.filelog(...
           | 15.7%  util.py:        __get__        line 706:  return self._filelog
           | 14.8%  context.py:     _filelog       line 1416:  result = self.func(obj)
           | 14.8%  localrepo.py:   file           line 629:  return self._repo.file(self...
           | 14.8%  filelog.py:     __init__       line 1134:  return filelog.filelog(self...
           | 14.5%  revlog.py:      __init__       line 24:  censorable=True)

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__)