Mercurial > hg
view mercurial/pathutil.py @ 25561:50a6c3c55db1 stable
parsers: do not cache RevlogError type (issue4451)
Index lookups raise RevlogError when the lookup fails. The previous
implementation was caching a reference to the RevlogError type in a
static variable. This assumed that the "mercurial.error" module was
only loaded once and there was only a single copy of it floating
around in memory. Unfortunately, in some situations - including
certain mod_wsgi configurations - this was not the case: the
"mercurial.error" module could be reloaded. It was possible for a
"RevlogError" reference from the first interpreter to be used by
a second interpreter. While the underlying thing was a
"mercurial.error.RevlogError," the object IDs were different, so
the Python code in revlog.py was failing to catch the exception! This
error has existed since the C index lookup code was implemented in
changeset e8d37b78acfb, which was first released in Mercurial 2.2 in
2012.
http://emptysqua.re/blog/python-c-extensions-and-mod-wsgi/#static-variables-are-shared
contains more details.
This patch removes the caching of the RevlogError type from the
function.
Since pretty much the entire function was refactored and the return
value of the function wasn't used, I changed the function signature
to not return anything.
For reasons unknown to me, we were calling PyErr_SetObject()
with the type of RevlogError and an instance of RevlogError. This
was equivalent to the Python code "raise RevlogError(RevlogError)".
This seemed wonky and completely unnecessary. The Python code only
cares about the type of the exception, not its contents. So I got
rid of this complexity.
This is my first Python C extension patch. Please give extra scrutiny
to it during review.
author | Gregory Szorc <gregory.szorc@gmail.com> |
---|---|
date | Fri, 12 Jun 2015 14:43:59 -0700 |
parents | a4679a74df14 |
children | 7d6a507a4c53 |
line wrap: on
line source
import os, errno, stat import encoding import util from i18n import _ def _lowerclean(s): return encoding.hfsignoreclean(s.lower()) class pathauditor(object): '''ensure that a filesystem path contains no banned components. the following properties of a path are checked: - ends with a directory separator - under top-level .hg - starts at the root of a windows drive - contains ".." - traverses a symlink (e.g. a/symlink_here/b) - inside a nested repository (a callback can be used to approve some nested repositories, e.g., subrepositories) ''' def __init__(self, root, callback=None): self.audited = set() self.auditeddir = set() self.root = root self.callback = callback if os.path.lexists(root) and not util.checkcase(root): self.normcase = util.normcase else: self.normcase = lambda x: x def __call__(self, path): '''Check the relative path. path may contain a pattern (e.g. foodir/**.txt)''' path = util.localpath(path) normpath = self.normcase(path) if normpath in self.audited: return # AIX ignores "/" at end of path, others raise EISDIR. if util.endswithsep(path): raise util.Abort(_("path ends in directory separator: %s") % path) parts = util.splitpath(path) if (os.path.splitdrive(path)[0] or _lowerclean(parts[0]) in ('.hg', '.hg.', '') or os.pardir in parts): raise util.Abort(_("path contains illegal component: %s") % path) # Windows shortname aliases for p in parts: if "~" in p: first, last = p.split("~", 1) if last.isdigit() and first.upper() in ["HG", "HG8B6C"]: raise util.Abort(_("path contains illegal component: %s") % path) if '.hg' in _lowerclean(path): lparts = [_lowerclean(p.lower()) for p in parts] for p in '.hg', '.hg.': if p in lparts[1:]: pos = lparts.index(p) base = os.path.join(*parts[:pos]) raise util.Abort(_("path '%s' is inside nested repo %r") % (path, base)) normparts = util.splitpath(normpath) assert len(parts) == len(normparts) parts.pop() normparts.pop() prefixes = [] while parts: prefix = os.sep.join(parts) normprefix = os.sep.join(normparts) if normprefix in self.auditeddir: break curpath = os.path.join(self.root, prefix) try: st = os.lstat(curpath) except OSError, err: # EINVAL can be raised as invalid path syntax under win32. # They must be ignored for patterns can be checked too. if err.errno not in (errno.ENOENT, errno.ENOTDIR, errno.EINVAL): raise else: if stat.S_ISLNK(st.st_mode): raise util.Abort( _('path %r traverses symbolic link %r') % (path, prefix)) elif (stat.S_ISDIR(st.st_mode) and os.path.isdir(os.path.join(curpath, '.hg'))): if not self.callback or not self.callback(curpath): raise util.Abort(_("path '%s' is inside nested " "repo %r") % (path, prefix)) prefixes.append(normprefix) parts.pop() normparts.pop() self.audited.add(normpath) # only add prefixes to the cache after checking everything: we don't # want to add "foo/bar/baz" before checking if there's a "foo/.hg" self.auditeddir.update(prefixes) def check(self, path): try: self(path) return True except (OSError, util.Abort): return False def canonpath(root, cwd, myname, auditor=None): '''return the canonical path of myname, given cwd and root''' if util.endswithsep(root): rootsep = root else: rootsep = root + os.sep name = myname if not os.path.isabs(name): name = os.path.join(root, cwd, name) name = os.path.normpath(name) if auditor is None: auditor = pathauditor(root) if name != rootsep and name.startswith(rootsep): name = name[len(rootsep):] auditor(name) return util.pconvert(name) elif name == root: return '' else: # Determine whether `name' is in the hierarchy at or beneath `root', # by iterating name=dirname(name) until that causes no change (can't # check name == '/', because that doesn't work on windows). The list # `rel' holds the reversed list of components making up the relative # file name we want. rel = [] while True: try: s = util.samefile(name, root) except OSError: s = False if s: if not rel: # name was actually the same as root (maybe a symlink) return '' rel.reverse() name = os.path.join(*rel) auditor(name) return util.pconvert(name) dirname, basename = util.split(name) rel.append(basename) if dirname == name: break name = dirname raise util.Abort(_("%s not under root '%s'") % (myname, root)) def normasprefix(path): '''normalize the specified path as path prefix Returned value can be used safely for "p.startswith(prefix)", "p[len(prefix):]", and so on. For efficiency, this expects "path" argument to be already normalized by "os.path.normpath", "os.path.realpath", and so on. See also issue3033 for detail about need of this function. >>> normasprefix('/foo/bar').replace(os.sep, '/') '/foo/bar/' >>> normasprefix('/').replace(os.sep, '/') '/' ''' d, p = os.path.splitdrive(path) if len(p) != len(os.sep): return path + os.sep else: return path