This is an archive of the discontinued Mercurial Phabricator instance.

Differential D3708

py3: replace `unicode` with pycompat.unicode
ClosedPublic

Authored by pulkit on Jun 10 2018, 6:32 AM.

Details

Reviewers
None
Group Reviewers
hg-reviewers
Commits
rHG79dd61a4554f: py3: replace `unicode` with pycompat.unicode
Summary

unicode() is not available on Python 3 and throws a NameError because unicodes
are now default str() on py3.

Diff Detail

Repository
rHG Mercurial
Lint
Automatic diff as part of commit; lint not applicable.
Unit
Automatic diff as part of commit; unit tests not applicable.

Event Timeline

pulkit created this revision.Jun 10 2018, 6:32 AM
yuja added a subscriber: yuja.Jun 10 2018, 11:01 AM
unicode() is not available on Python 3 and throws a NameError because unicodes
are now default str() on py3.

Appears that we need many type(u'')s, so I'd rather make pycompat.unicode
available on both Py2 and Py3. IMHO, type(u'') is just a temporary
workaround.

pulkit retitled this revision from py3: replace `unicode` with `type(u'')` in isinstance() calls to py3: replace `unicode` with pycompat.unicode.Jun 13 2018, 2:42 PM
pulkit updated this revision to Diff 9053.
Closed by commit rHG79dd61a4554f: py3: replace `unicode` with pycompat.unicode (authored by pulkit). · Explain WhyJun 15 2018, 8:48 AM
This revision was automatically updated to reflect the committed changes.

Revision Contents
Changeset List

Diff 9079

hgext/convert/common.py

Tag names must be UTF-8 strings. Tag names must be UTF-8 strings.
""" """
raise NotImplementedError raise NotImplementedError
def recode(self, s, encoding=None): def recode(self, s, encoding=None):
if not encoding: if not encoding:
encoding = self.encoding or 'utf-8' encoding = self.encoding or 'utf-8'
if isinstance(s, unicode): if isinstance(s, pycompat.unicode):
return s.encode("utf-8") return s.encode("utf-8")
try: try:
return s.decode(pycompat.sysstr(encoding)).encode("utf-8") return s.decode(pycompat.sysstr(encoding)).encode("utf-8")
except UnicodeError: except UnicodeError:
try: try:
return s.decode("latin-1").encode("utf-8") return s.decode("latin-1").encode("utf-8")
except UnicodeError: except UnicodeError:
return s.decode(pycompat.sysstr(encoding), return s.decode(pycompat.sysstr(encoding),

hgext/convert/convcmd.py

monotone_source = monotone.monotone_source monotone_source = monotone.monotone_source
p4_source = p4.p4_source p4_source = p4.p4_source
svn_sink = subversion.svn_sink svn_sink = subversion.svn_sink
svn_source = subversion.svn_source svn_source = subversion.svn_source
orig_encoding = 'ascii' orig_encoding = 'ascii'
def recode(s): def recode(s):
if isinstance(s, unicode): if isinstance(s, pycompat.unicode):
return s.encode(pycompat.sysstr(orig_encoding), 'replace') return s.encode(pycompat.sysstr(orig_encoding), 'replace')
else: else:
return s.decode('utf-8').encode( return s.decode('utf-8').encode(
pycompat.sysstr(orig_encoding), 'replace') pycompat.sysstr(orig_encoding), 'replace')
def mapbranch(branch, branchmap): def mapbranch(branch, branchmap):
''' '''
>>> bmap = {b'default': b'branch1'} >>> bmap = {b'default': b'branch1'}

hgext/convert/darcs.py

child = node child = node
self.parents[child] = [] self.parents[child] = []
def after(self): def after(self):
self.ui.debug('cleaning up %s\n' % self.tmppath) self.ui.debug('cleaning up %s\n' % self.tmppath)
shutil.rmtree(self.tmppath, ignore_errors=True) shutil.rmtree(self.tmppath, ignore_errors=True)
def recode(self, s, encoding=None): def recode(self, s, encoding=None):
if isinstance(s, unicode): if isinstance(s, pycompat.unicode):
# XMLParser returns unicode objects for anything it can't # XMLParser returns unicode objects for anything it can't
# encode into ASCII. We convert them back to str to get # encode into ASCII. We convert them back to str to get
# recode's normal conversion behavior. # recode's normal conversion behavior.
s = s.encode('latin-1') s = s.encode('latin-1')
return super(darcs_source, self).recode(s, encoding) return super(darcs_source, self).recode(s, encoding)
def xml(self, cmd, **kwargs): def xml(self, cmd, **kwargs):
# NOTE: darcs is currently encoding agnostic and will print # NOTE: darcs is currently encoding agnostic and will print

hgext/win32mbcs.py

elif isinstance(arg, list): elif isinstance(arg, list):
return map(decode, arg) return map(decode, arg)
elif isinstance(arg, dict): elif isinstance(arg, dict):
for k, v in arg.items(): for k, v in arg.items():
arg[k] = decode(v) arg[k] = decode(v)
return arg return arg
def encode(arg): def encode(arg):
if isinstance(arg, unicode): if isinstance(arg, pycompat.unicode):
return arg.encode(_encoding) return arg.encode(_encoding)
elif isinstance(arg, tuple): elif isinstance(arg, tuple):
return tuple(map(encode, arg)) return tuple(map(encode, arg))
elif isinstance(arg, list): elif isinstance(arg, list):
return map(encode, arg) return map(encode, arg)
elif isinstance(arg, dict): elif isinstance(arg, dict):
for k, v in arg.items(): for k, v in arg.items():
arg[k] = encode(v) arg[k] = encode(v)
# convert string arguments, call func, then convert back the # convert string arguments, call func, then convert back the
# return value. # return value.
return enc(func(*dec(args), **dec(kwds))) return enc(func(*dec(args), **dec(kwds)))
except UnicodeError: except UnicodeError:
raise error.Abort(_("[win32mbcs] filename conversion failed with" raise error.Abort(_("[win32mbcs] filename conversion failed with"
" %s encoding\n") % (_encoding)) " %s encoding\n") % (_encoding))
def wrapper(func, args, kwds): def wrapper(func, args, kwds):
return basewrapper(func, unicode, encode, decode, args, kwds) return basewrapper(func, pycompat.unicode, encode, decode, args, kwds)
def reversewrapper(func, args, kwds): def reversewrapper(func, args, kwds):
return basewrapper(func, str, decode, encode, args, kwds) return basewrapper(func, str, decode, encode, args, kwds)
def wrapperforlistdir(func, args, kwds): def wrapperforlistdir(func, args, kwds):
# Ensure 'path' argument ends with os.sep to avoids # Ensure 'path' argument ends with os.sep to avoids
# misinterpreting last 0x5c of MBCS 2nd byte as path separator. # misinterpreting last 0x5c of MBCS 2nd byte as path separator.

mercurial/i18n.py

) )
# modelled after templater.templatepath: # modelled after templater.templatepath:
if getattr(sys, 'frozen', None) is not None: if getattr(sys, 'frozen', None) is not None:
module = pycompat.sysexecutable module = pycompat.sysexecutable
else: else:
module = pycompat.fsencode(__file__) module = pycompat.fsencode(__file__)
try:
unicode
except NameError:
unicode = str
_languages = None _languages = None
if (pycompat.iswindows if (pycompat.iswindows
and 'LANGUAGE' not in encoding.environ and 'LANGUAGE' not in encoding.environ
and 'LC_ALL' not in encoding.environ and 'LC_ALL' not in encoding.environ
and 'LC_MESSAGES' not in encoding.environ and 'LC_MESSAGES' not in encoding.environ
and 'LANG' not in encoding.environ): and 'LANG' not in encoding.environ):
# Try to detect UI language by "User Interface Language Management" API # Try to detect UI language by "User Interface Language Management" API
# if no locale variables are set. Note that locale.getdefaultlocale() # if no locale variables are set. Note that locale.getdefaultlocale()
""" """
# If message is None, t.ugettext will return u'None' as the # If message is None, t.ugettext will return u'None' as the
# translation whereas our callers expect us to return None. # translation whereas our callers expect us to return None.
if message is None or not _ugettext: if message is None or not _ugettext:
return message return message
cache = _msgcache.setdefault(encoding.encoding, {}) cache = _msgcache.setdefault(encoding.encoding, {})
if message not in cache: if message not in cache:
if type(message) is unicode: if type(message) is pycompat.unicode:
# goofy unicode docstrings in test # goofy unicode docstrings in test
paragraphs = message.split(u'\n\n') paragraphs = message.split(u'\n\n')
else: else:
paragraphs = [p.decode("ascii") for p in message.split('\n\n')] paragraphs = [p.decode("ascii") for p in message.split('\n\n')]
# Be careful not to translate the empty string -- it holds the # Be careful not to translate the empty string -- it holds the
# meta data of the .po file. # meta data of the .po file.
u = u'\n\n'.join([p and _ugettext(p) or u'' for p in paragraphs]) u = u'\n\n'.join([p and _ugettext(p) or u'' for p in paragraphs])
try: try:

mercurial/pycompat.py

def emailparser(*args, **kwargs): def emailparser(*args, **kwargs):
import email.parser import email.parser
return email.parser.BytesParser(*args, **kwargs) return email.parser.BytesParser(*args, **kwargs)
else: else:
import cStringIO import cStringIO
unicode = unicode
bytechr = chr bytechr = chr
byterepr = repr byterepr = repr
bytestr = str bytestr = str
iterbytestr = iter iterbytestr = iter
maybebytestr = identity maybebytestr = identity
sysbytes = identity sysbytes = identity
sysstr = identity sysstr = identity
strurl = identity strurl = identity

mercurial/scmutil.py

if util.safehasattr(inst, "code"): if util.safehasattr(inst, "code"):
ui.warn(_("abort: %s\n") % stringutil.forcebytestr(inst)) ui.warn(_("abort: %s\n") % stringutil.forcebytestr(inst))
elif util.safehasattr(inst, "reason"): elif util.safehasattr(inst, "reason"):
try: # usually it is in the form (errno, strerror) try: # usually it is in the form (errno, strerror)
reason = inst.reason.args[1] reason = inst.reason.args[1]
except (AttributeError, IndexError): except (AttributeError, IndexError):
# it might be anything, for example a string # it might be anything, for example a string
reason = inst.reason reason = inst.reason
if isinstance(reason, unicode): if isinstance(reason, pycompat.unicode):
# SSLError of Python 2.7.9 contains a unicode # SSLError of Python 2.7.9 contains a unicode
reason = encoding.unitolocal(reason) reason = encoding.unitolocal(reason)
ui.warn(_("abort: error: %s\n") % reason) ui.warn(_("abort: error: %s\n") % reason)
elif (util.safehasattr(inst, "args") elif (util.safehasattr(inst, "args")
and inst.args and inst.args[0] == errno.EPIPE): and inst.args and inst.args[0] == errno.EPIPE):
pass pass
elif getattr(inst, "strerror", None): elif getattr(inst, "strerror", None):
if getattr(inst, "filename", None): if getattr(inst, "filename", None):