Mercurial > hg
view mercurial/httpconnection.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
author | Matt Harbison <matt_harbison@yahoo.com> |
---|---|
date | Thu, 23 May 2019 21:54:24 -0400 |
parents | aaad36b88298 |
children | 57875cf423c9 |
line wrap: on
line source
# httpconnection.py - urllib2 handler for new http support # # Copyright 2005, 2006, 2007, 2008 Matt Mackall <mpm@selenic.com> # Copyright 2006, 2007 Alexis S. L. Carvalho <alexis@cecm.usp.br> # Copyright 2006 Vadim Gelfer <vadim.gelfer@gmail.com> # Copyright 2011 Google, Inc. # # This software may be used and distributed according to the terms of the # GNU General Public License version 2 or any later version. from __future__ import absolute_import import os from .i18n import _ from . import ( pycompat, util, ) urlerr = util.urlerr urlreq = util.urlreq # moved here from url.py to avoid a cycle class httpsendfile(object): """This is a wrapper around the objects returned by python's "open". Its purpose is to send file-like objects via HTTP. It do however not define a __len__ attribute because the length might be more than Py_ssize_t can handle. """ def __init__(self, ui, *args, **kwargs): self.ui = ui self._data = open(*args, **kwargs) self.seek = self._data.seek self.close = self._data.close self.write = self._data.write self.length = os.fstat(self._data.fileno()).st_size self._pos = 0 # We pass double the max for total because we currently have # to send the bundle twice in the case of a server that # requires authentication. Since we can't know until we try # once whether authentication will be required, just lie to # the user and maybe the push succeeds suddenly at 50%. self._progress = ui.makeprogress(_('sending'), unit=_('kb'), total=(self.length // 1024 * 2)) def read(self, *args, **kwargs): ret = self._data.read(*args, **kwargs) if not ret: self._progress.complete() return ret self._pos += len(ret) self._progress.update(self._pos // 1024) return ret def __enter__(self): return self def __exit__(self, exc_type, exc_val, exc_tb): self.close() # moved here from url.py to avoid a cycle def readauthforuri(ui, uri, user): uri = pycompat.bytesurl(uri) # Read configuration groups = {} for key, val in ui.configitems('auth'): if key in ('cookiefile',): continue if '.' not in key: ui.warn(_("ignoring invalid [auth] key '%s'\n") % key) continue group, setting = key.rsplit('.', 1) gdict = groups.setdefault(group, {}) if setting in ('username', 'cert', 'key'): val = util.expandpath(val) gdict[setting] = val # Find the best match scheme, hostpath = uri.split('://', 1) bestuser = None bestlen = 0 bestauth = None for group, auth in groups.iteritems(): if user and user != auth.get('username', user): # If a username was set in the URI, the entry username # must either match it or be unset continue prefix = auth.get('prefix') if not prefix: continue prefixurl = util.url(prefix) if prefixurl.user and prefixurl.user != user: # If a username was set in the prefix, it must match the username in # the URI. continue # The URI passed in has been stripped of credentials, so erase the user # here to allow simpler matching. prefixurl.user = None prefix = bytes(prefixurl) p = prefix.split('://', 1) if len(p) > 1: schemes, prefix = [p[0]], p[1] else: schemes = (auth.get('schemes') or 'https').split() if ((prefix == '*' or hostpath.startswith(prefix)) and (len(prefix) > bestlen or (len(prefix) == bestlen and not bestuser and 'username' in auth)) and scheme in schemes): bestlen = len(prefix) bestauth = group, auth bestuser = auth.get('username') if user and not bestuser: auth['username'] = user return bestauth