view tests/test-byteify-strings.t @ 44651:00e0c5c06ed5

pycompat: change argv conversion semantics Use of os.fsencode() to convert Python's sys.argv back to bytes was not correct because it isn't the logically inverse operation from what CPython was doing under the hood. This commit changes the logic for doing the str -> bytes conversion. This required a separate implementation for POSIX and Windows. The Windows behavior is arguably not ideal. The previous behavior on Windows was leading to failing tests, such as test-http-branchmap.t, which defines a utf-8 branch name via a command argument. Previously, Mercurial's argument parser looked to be receiving wchar_t bytes in some cases. After this commit, behavior on Windows is compatible with Python 2, where CPython did not implement `int wmain()` and Windows was performing a Unicode to ANSI conversion on the wchar_t native command line. Arguably better behavior on Windows would be for Mercurial to preserve the original Unicode sequence coming from Python and to wrap this in a bytes-like type so we can round trip safely. But, this would be new, backwards incompatible behavior. My goal for this commit was to converge Mercurial behavior on Python 3 on Windows to fix busted tests. And I believe I was successful, as this commit fixes 9 tests on my Windows machine and 14 tests in the AWS CI environment! Differential Revision: https://phab.mercurial-scm.org/D8337
author Gregory Szorc <gregory.szorc@gmail.com>
date Sat, 28 Mar 2020 12:18:58 -0700
parents 3a463e5e470b
children 8250ecb53f30
line wrap: on
line source

#require py37

  $ byteify_strings () {
  >   "$PYTHON" "$TESTDIR/../contrib/byteify-strings.py" "$@"
  > }

Test version

  $ byteify_strings --version
  Byteify strings * (glob)

Test in-place

  $ cat > testfile.py <<EOF
  > obj['test'] = b"1234"
  > mydict.iteritems()
  > EOF
  $ byteify_strings testfile.py -i
  $ cat testfile.py
  obj[b'test'] = b"1234"
  mydict.iteritems()

Test with dictiter

  $ cat > testfile.py <<EOF
  > obj['test'] = b"1234"
  > mydict.iteritems()
  > EOF
  $ byteify_strings testfile.py --dictiter
  obj[b'test'] = b"1234"
  mydict.items()

Test kwargs-like objects

  $ cat > testfile.py <<EOF
  > kwargs['test'] = "123"
  > kwargs[test['testing']]
  > kwargs[test[[['testing']]]]
  > kwargs[kwargs['testing']]
  > kwargs.get('test')
  > kwargs.pop('test')
  > kwargs.get('test', 'testing')
  > kwargs.pop('test', 'testing')
  > kwargs.setdefault('test', 'testing')
  > 
  > opts['test'] = "123"
  > opts[test['testing']]
  > opts[test[[['testing']]]]
  > opts[opts['testing']]
  > opts.get('test')
  > opts.pop('test')
  > opts.get('test', 'testing')
  > opts.pop('test', 'testing')
  > opts.setdefault('test', 'testing')
  > 
  > commitopts['test'] = "123"
  > commitopts[test['testing']]
  > commitopts[test[[['testing']]]]
  > commitopts[commitopts['testing']]
  > commitopts.get('test')
  > commitopts.pop('test')
  > commitopts.get('test', 'testing')
  > commitopts.pop('test', 'testing')
  > commitopts.setdefault('test', 'testing')
  > EOF
  $ byteify_strings testfile.py --treat-as-kwargs kwargs opts commitopts
  kwargs['test'] = b"123"
  kwargs[test[b'testing']]
  kwargs[test[[[b'testing']]]]
  kwargs[kwargs['testing']]
  kwargs.get('test')
  kwargs.pop('test')
  kwargs.get('test', b'testing')
  kwargs.pop('test', b'testing')
  kwargs.setdefault('test', b'testing')
  
  opts['test'] = b"123"
  opts[test[b'testing']]
  opts[test[[[b'testing']]]]
  opts[opts['testing']]
  opts.get('test')
  opts.pop('test')
  opts.get('test', b'testing')
  opts.pop('test', b'testing')
  opts.setdefault('test', b'testing')
  
  commitopts['test'] = b"123"
  commitopts[test[b'testing']]
  commitopts[test[[[b'testing']]]]
  commitopts[commitopts['testing']]
  commitopts.get('test')
  commitopts.pop('test')
  commitopts.get('test', b'testing')
  commitopts.pop('test', b'testing')
  commitopts.setdefault('test', b'testing')

Test attr*() as methods

  $ cat > testfile.py <<EOF
  > setattr(o, 'a', 1)
  > util.setattr(o, 'ae', 1)
  > util.getattr(o, 'alksjdf', 'default')
  > util.addattr(o, 'asdf')
  > util.hasattr(o, 'lksjdf', 'default')
  > util.safehasattr(o, 'lksjdf', 'default')
  > @eh.wrapfunction(func, 'lksjdf')
  > def f():
  >     pass
  > @eh.wrapclass(klass, 'lksjdf')
  > def f():
  >     pass
  > EOF
  $ byteify_strings testfile.py --allow-attr-methods
  setattr(o, 'a', 1)
  util.setattr(o, 'ae', 1)
  util.getattr(o, 'alksjdf', b'default')
  util.addattr(o, 'asdf')
  util.hasattr(o, 'lksjdf', b'default')
  util.safehasattr(o, 'lksjdf', b'default')
  @eh.wrapfunction(func, 'lksjdf')
  def f():
      pass
  @eh.wrapclass(klass, 'lksjdf')
  def f():
      pass

Test without attr*() as methods

  $ cat > testfile.py <<EOF
  > setattr(o, 'a', 1)
  > util.setattr(o, 'ae', 1)
  > util.getattr(o, 'alksjdf', 'default')
  > util.addattr(o, 'asdf')
  > util.hasattr(o, 'lksjdf', 'default')
  > util.safehasattr(o, 'lksjdf', 'default')
  > @eh.wrapfunction(func, 'lksjdf')
  > def f():
  >     pass
  > @eh.wrapclass(klass, 'lksjdf')
  > def f():
  >     pass
  > EOF
  $ byteify_strings testfile.py
  setattr(o, 'a', 1)
  util.setattr(o, b'ae', 1)
  util.getattr(o, b'alksjdf', b'default')
  util.addattr(o, b'asdf')
  util.hasattr(o, b'lksjdf', b'default')
  util.safehasattr(o, b'lksjdf', b'default')
  @eh.wrapfunction(func, b'lksjdf')
  def f():
      pass
  @eh.wrapclass(klass, b'lksjdf')
  def f():
      pass

Test ignore comments

  $ cat > testfile.py <<EOF
  > # py3-transform: off
  > "none"
  > "of"
  > 'these'
  > s = """should"""
  > d = '''be'''
  > # py3-transform: on
  > "this should"
  > 'and this also'
  > 
  > # no-py3-transform
  > l = "this should be ignored"
  > l2 = "this shouldn't"
  > 
  > EOF
  $ byteify_strings testfile.py
  # py3-transform: off
  "none"
  "of"
  'these'
  s = """should"""
  d = '''be'''
  # py3-transform: on
  b"this should"
  b'and this also'
  
  # no-py3-transform
  l = "this should be ignored"
  l2 = b"this shouldn't"
  
Test triple-quoted strings

  $ cat > testfile.py <<EOF
  > """This is ignored
  > """
  > 
  > line = """
  >   This should not be
  > """
  > line = '''
  > Neither should this
  > '''
  > EOF
  $ byteify_strings testfile.py
  """This is ignored
  """
  
  line = b"""
    This should not be
  """
  line = b'''
  Neither should this
  '''

Test prefixed strings

  $ cat > testfile.py <<EOF
  > obj['test'] = b"1234"
  > obj[r'test'] = u"1234"
  > EOF
  $ byteify_strings testfile.py
  obj[b'test'] = b"1234"
  obj[r'test'] = u"1234"

Test multi-line alignment

  $ cat > testfile.py <<'EOF'
  > def foo():
  >     error.Abort(_("foo"
  >                  "bar"
  >                  "%s")
  >                % parameter)
  > {
  >     'test': dict,
  >     'test2': dict,
  > }
  > [
  >    "thing",
  >    "thing2"
  > ]
  > (
  >    "tuple",
  >    "tuple2",
  > )
  > {"thing",
  >  }
  > EOF
  $ byteify_strings testfile.py
  def foo():
      error.Abort(_(b"foo"
                    b"bar"
                    b"%s")
                  % parameter)
  {
      b'test': dict,
      b'test2': dict,
  }
  [
     b"thing",
     b"thing2"
  ]
  (
     b"tuple",
     b"tuple2",
  )
  {b"thing",
   }