view hgext/schemes.py @ 42377:0546ead39a7e stable

manifest: avoid corruption by dropping removed files with pure (issue5801)

Previously, removed files would simply be marked by overwriting the first byte
with NUL and dropping their entry in `self.position`.  But no effort was made to
ignore them when compacting the dictionary into text form.  This allowed them to
slip into the manifest revision, since the code seems to be trying to minimize
the string operations by copying as large a chunk as possible.  As part of this,
compact() walks the existing text based on entries in the `positions` list, and
consumed everything up to the next position entry.   This typically resulted in
a ValueError complaining about unsorted manifest entries.

Sometimes it seems that files do get dropped in large repos- it seems to
correspond to there being a new entry that would take the same slot.  A much
more trivial problem is that if the only changes were removals, `_compact()`
didn't even run because `__delitem__` doesn't add anything to `self.extradata`.
Now there's an explicit variable to flag this, both to allow `_compact()` to
run, and to avoid searching the manifest in cases where there are no removals.

In practice, this behavior was mostly obscured by the check in fastdelta() which
takes a different path that explicitly drops removed files if there are fewer
than 1000 changes.  However, timeless has a repo where after rebasing tens of
commits, a totally different path[1] is taken that bypasses the change count
check and hits this problem.

[1] https://www.mercurial-scm.org/repo/hg/file/2338bdea4474/mercurial/manifest.py#l1511

# 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 (
    error,
    extensions,
    hg,
    pycompat,
    registrar,
    templater,
    util,
)

cmdtable = {}
command = registrar.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, intents=None, createopts=None):
        url = self.resolve(url)
        return hg._peerlookup(url).instance(ui, url, create, intents=intents,
                                            createopts=createopts)

    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(('%d' % (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(templater.parse)
    for scheme, url in schemes.items():
        if (pycompat.iswindows 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')