view hgext/schemes.py @ 32572:377c74ef008d stable

win32mbcs: avoid unintentional failure at colorization

Since 176ed32dc159, pycompat.bytestr() wrapped by win32mbcs returns
unicode object, if an argument is not byte-str object. And this causes
unexpected failure at colorization.

pycompat.bytestr() is used to convert from color effect "int" value to
byte-str object in color module. Wrapped pycompat.bytestr() returns
unicode object for such "int" value, because it isn't byte-str.

If this returned unicode object is used to colorize non-ASCII byte-str
in cases below, UnicodeDecodeError is raised at an operation between
them.

  - colorization uses "ansi" color mode, or

    Even though this isn't default on Windows, user might use this
    color mode for third party pager.

  - ui.write() is buffered with labeled=True

    Buffering causes "ansi" color mode internally, regardless of
    actual color mode. With "win32" color mode, extra escape sequences
    are omitted at writing data out.

    For example, with "win32" color mode, "hg status" doesn't fail for
    non-ASCII filenames, but "hg log" does for non-ASCII text, because
    the latter implies buffered formatter.

There are many "color effect" value lines in color.py, and making them
byte-str objects isn't suitable for fixing on stable. In addition to
it, pycompat.bytestr will be used to get byte-str object from any
types other than int, too.

To resolve this issue, this patch does:

  - replace pycompat.bytestr in checkwinfilename() with newly added
    hook point util._filenamebytestr, and

  - make win32mbcs reverse-wrap util._filenamebytestr
    (this is a replacement of 176ed32dc159)

This patch does two things above at same time, because separately
applying the former change adds broken revision (from point of view of
win32mbcs) to stable branch.

"_" prefix is added to "filenamebytestr", because it is win32mbcs
specific hook point.

# Copyright 2009, Alexander Solovyov <[e-mail]>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

"""extend schemes with shortcuts to repository swarms

This extension allows you to specify shortcuts for parent URLs with a
lot of repositories to act like a scheme, for example::

  [schemes]
  py = http://code.python.org/hg/

After that you can use it like::

  hg clone py://trunk/

Additionally there is support for some more complex schemas, for
example used by Google Code::

  [schemes]
  gcode = http://{1}.googlecode.com/hg/

The syntax is taken from Mercurial templates, and you have unlimited
number of variables, starting with ``{1}`` and continuing with
``{2}``, ``{3}`` and so on. This variables will receive parts of URL
supplied, split by ``/``. Anything not specified as ``{part}`` will be
just appended to an URL.

For convenience, the extension adds these schemes by default::

  [schemes]
  py = http://hg.python.org/
  bb = https://bitbucket.org/
  bb+ssh = ssh://[e-mail]/
  gcode = https://{1}.googlecode.com/hg/
  kiln = https://{1}.kilnhg.com/Repo/

You can override a predefined scheme by defining a new scheme with the
same name.
"""
from __future__ import absolute_import

import os
import re

from mercurial.i18n import _
from mercurial import (
    cmdutil,
    error,
    extensions,
    hg,
    pycompat,
    templater,
    util,
)

cmdtable = {}
command = cmdutil.command(cmdtable)
# Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
# extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
# be specifying the version(s) of Mercurial they are tested with, or
# leave the attribute unspecified.
testedwith = 'ships-with-hg-core'

_partre = re.compile(br'\{(\d+)\}')

class ShortRepository(object):
    def __init__(self, url, scheme, templater):
        self.scheme = scheme
        self.templater = templater
        self.url = url
        try:
            self.parts = max(map(int, _partre.findall(self.url)))
        except ValueError:
            self.parts = 0

    def __repr__(self):
        return '<ShortRepository: %s>' % self.scheme

    def instance(self, ui, url, create):
        url = self.resolve(url)
        return hg._peerlookup(url).instance(ui, url, create)

    def resolve(self, url):
        # Should this use the util.url class, or is manual parsing better?
        try:
            url = url.split('://', 1)[1]
        except IndexError:
            raise error.Abort(_("no '://' in scheme url '%s'") % url)
        parts = url.split('/', self.parts)
        if len(parts) > self.parts:
            tail = parts[-1]
            parts = parts[:-1]
        else:
            tail = ''
        context = dict((str(i + 1), v) for i, v in enumerate(parts))
        return ''.join(self.templater.process(self.url, context)) + tail

def hasdriveletter(orig, path):
    if path:
        for scheme in schemes:
            if path.startswith(scheme + ':'):
                return False
    return orig(path)

schemes = {
    'py': 'http://hg.python.org/',
    'bb': 'https://bitbucket.org/',
    'bb+ssh': 'ssh://[e-mail]/',
    'gcode': 'https://{1}.googlecode.com/hg/',
    'kiln': 'https://{1}.kilnhg.com/Repo/'
    }

def extsetup(ui):
    schemes.update(dict(ui.configitems('schemes')))
    t = templater.engine(lambda x: x)
    for scheme, url in schemes.items():
        if (pycompat.osname == 'nt' and len(scheme) == 1 and scheme.isalpha()
            and os.path.exists('%s:\\' % scheme)):
            raise error.Abort(_('custom scheme %s:// conflicts with drive '
                               'letter %s:\\\n') % (scheme, scheme.upper()))
        hg.schemes[scheme] = ShortRepository(url, scheme, t)

    extensions.wrapfunction(util, 'hasdriveletter', hasdriveletter)

@command('debugexpandscheme', norepo=True)
def expandscheme(ui, url, **opts):
    """given a repo path, provide the scheme-expanded path
    """
    repo = hg._peerlookup(url)
    if isinstance(repo, ShortRepository):
        url = repo.resolve(url)
    ui.write(url + '\n')