pathutil: tease out a new library to break an import cycle from canonpath use

mercurial/pathutil.py

@@ -0,0 +1,144 b''
+import os, errno, stat
+
+import util
+from i18n import _
+
+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 parts[0].lower() in ('.hg', '.hg.', '')
+            or os.pardir in parts):
+            raise util.Abort(_("path contains illegal component: %s") % path)
+        if '.hg' in path.lower():
+            lparts = [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))

hgext/keyword.py

@@ -84,7 +84,7 b" like CVS' $Log$, are not supported. A ke"
 
 from mercurial import commands, context, cmdutil, dispatch, filelog, extensions
 from mercurial import localrepo, match, patch, templatefilters, templater, util
-from mercurial import scmutil
+from mercurial import scmutil, pathutil
 from mercurial.hgweb import webcommands
 from mercurial.i18n import _
 import os, re, shutil, tempfile
@@ -673,7 +673,7 b' def reposetup(ui, repo):'
                 expansion. '''
                 source = repo.dirstate.copied(dest)
                 if 'l' in wctx.flags(source):
-                    source = scmutil.canonpath(repo.root, cwd,
+                    source = pathutil.canonpath(repo.root, cwd,
                                                os.path.realpath(source))
                 return kwt.match(source)
 

hgext/largefiles/overrides.py

@@ -12,7 +12,7 b' import os'
 import copy
 
 from mercurial import hg, commands, util, cmdutil, scmutil, match as match_, \
-    node, archival, error, merge, discovery
+    node, archival, error, merge, discovery, pathutil
 from mercurial.i18n import _
 from mercurial.node import hex
 from hgext import rebase
@@ -469,7 +469,7 b' def overridecopy(orig, ui, repo, pats, o'
         return orig(ui, repo, pats, opts, rename)
 
     def makestandin(relpath):
-        path = scmutil.canonpath(repo.root, repo.getcwd(), relpath)
+        path = pathutil.canonpath(repo.root, repo.getcwd(), relpath)
         return os.path.join(repo.wjoin(lfutil.standin(path)))
 
     fullpats = scmutil.expandpats(pats)

mercurial/cmdutil.py

@@ -10,7 +10,7 b' from i18n import _'
 import os, sys, errno, re, tempfile
 import util, scmutil, templater, patch, error, templatekw, revlog, copies
 import match as matchmod
-import subrepo, context, repair, graphmod, revset, phases, obsolete
+import subrepo, context, repair, graphmod, revset, phases, obsolete, pathutil
 import changelog
 import bookmarks
 import lock as lockmod
@@ -274,7 +274,7 b' def copy(ui, repo, pats, opts, rename=Fa'
     # relsrc: ossep
     # otarget: ossep
     def copyfile(abssrc, relsrc, otarget, exact):
-        abstarget = scmutil.canonpath(repo.root, cwd, otarget)
+        abstarget = pathutil.canonpath(repo.root, cwd, otarget)
         if '/' in abstarget:
             # We cannot normalize abstarget itself, this would prevent
             # case only renames, like a => A.
@@ -367,7 +367,7 b' def copy(ui, repo, pats, opts, rename=Fa'
     # return: function that takes hgsep and returns ossep
     def targetpathfn(pat, dest, srcs):
         if os.path.isdir(pat):
-            abspfx = scmutil.canonpath(repo.root, cwd, pat)
+            abspfx = pathutil.canonpath(repo.root, cwd, pat)
             abspfx = util.localpath(abspfx)
             if destdirexists:
                 striplen = len(os.path.split(abspfx)[0])
@@ -393,7 +393,7 b' def copy(ui, repo, pats, opts, rename=Fa'
             res = lambda p: os.path.join(dest,
                                          os.path.basename(util.localpath(p)))
         else:
-            abspfx = scmutil.canonpath(repo.root, cwd, pat)
+            abspfx = pathutil.canonpath(repo.root, cwd, pat)
             if len(abspfx) < len(srcs[0][0]):
                 # A directory. Either the target path contains the last
                 # component of the source path or it does not.
@@ -2065,7 +2065,7 b' def revert(ui, repo, ctx, parents, *pats'
                 fc = ctx[f]
                 repo.wwrite(f, fc.data(), fc.flags())
 
-            audit_path = scmutil.pathauditor(repo.root)
+            audit_path = pathutil.pathauditor(repo.root)
             for f in remove[0]:
                 if repo.dirstate[f] == 'a':
                     repo.dirstate.drop(f)

mercurial/dirstate.py

@@ -8,7 +8,7 b' import errno'
 
 from node import nullid
 from i18n import _
-import scmutil, util, ignore, osutil, parsers, encoding
+import scmutil, util, ignore, osutil, parsers, encoding, pathutil
 import os, stat, errno, gc
 
 propertycache = util.propertycache
@@ -736,7 +736,7 b' class dirstate(object):'
                 # unknown == True means we walked the full directory tree above.
                 # So if a file is not seen it was either a) not matching matchfn
                 # b) ignored, c) missing, or d) under a symlink directory.
-                audit_path = scmutil.pathauditor(self._root)
+                audit_path = pathutil.pathauditor(self._root)
 
                 for nf in iter(visit):
                     # Report ignored items in the dmap as long as they are not

mercurial/hgweb/webutil.py

@@ -7,7 +7,7 b''
 # GNU General Public License version 2 or any later version.
 
 import os, copy
-from mercurial import match, patch, scmutil, error, ui, util
+from mercurial import match, patch, error, ui, util, pathutil
 from mercurial.i18n import _
 from mercurial.node import hex, nullid
 from common import ErrorResponse
@@ -196,7 +196,7 b' def showbookmark(repo, tmpl, t1, node=nu'
 
 def cleanpath(repo, path):
     path = path.lstrip('/')
-    return scmutil.canonpath(repo.root, '', path)
+    return pathutil.canonpath(repo.root, '', path)
 
 def changeidctx (repo, changeid):
     try:

mercurial/localrepo.py

@@ -15,7 +15,7 b' import merge as mergemod'
 import tags as tagsmod
 from lock import release
 import weakref, errno, os, time, inspect
-import branchmap
+import branchmap, pathutil
 propertycache = util.propertycache
 filecache = scmutil.filecache
 
@@ -166,7 +166,7 b' class localrepository(object):'
         self.root = self.wvfs.base
         self.path = self.wvfs.join(".hg")
         self.origroot = path
-        self.auditor = scmutil.pathauditor(self.root, self._checknested)
+        self.auditor = pathutil.pathauditor(self.root, self._checknested)
         self.vfs = scmutil.vfs(self.path)
         self.opener = self.vfs
         self.baseui = baseui

mercurial/match.py

@@ -6,7 +6,7 b''
 # GNU General Public License version 2 or any later version.
 
 import re
-import scmutil, util, fileset
+import util, fileset, pathutil
 from i18n import _
 
 def _rematcher(pat):
@@ -317,7 +317,7 b' def _normalize(names, default, root, cwd'
     pats = []
     for kind, name in [_patsplit(p, default) for p in names]:
         if kind in ('glob', 'relpath'):
-            name = scmutil.canonpath(root, cwd, name, auditor)
+            name = pathutil.canonpath(root, cwd, name, auditor)
         elif kind in ('relglob', 'path'):
             name = util.normpath(name)
         elif kind in ('listfile', 'listfile0'):

mercurial/scmutil.py

@@ -8,8 +8,9 b''
 from i18n import _
 from mercurial.node import nullrev
 import util, error, osutil, revset, similar, encoding, phases, parsers
+import pathutil
 import match as matchmod
-import os, errno, re, stat, glob
+import os, errno, re, glob
 
 if os.name == 'nt':
     import scmwindows as scmplatform
@@ -108,100 +109,6 b' class casecollisionauditor(object):'
         self._loweredfiles.add(fl)
         self._newfiles.add(f)
 
-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 parts[0].lower() in ('.hg', '.hg.', '')
-            or os.pardir in parts):
-            raise util.Abort(_("path contains illegal component: %s") % path)
-        if '.hg' in path.lower():
-            lparts = [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
-
 class abstractvfs(object):
     """Abstract base class; cannot be instantiated"""
 
@@ -310,7 +217,7 b' class vfs(abstractvfs):'
     def _setmustaudit(self, onoff):
         self._audit = onoff
         if onoff:
-            self.audit = pathauditor(self.base)
+            self.audit = pathutil.pathauditor(self.base)
         else:
             self.audit = util.always
 
@@ -445,52 +352,6 b' class readonlyvfs(abstractvfs, auditvfs)'
         return self.vfs(path, mode, *args, **kw)
 
 
-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 walkrepos(path, followsym=False, seen_dirs=None, recurse=False):
     '''yield every hg repository under path, always recursively.
     The recurse flag will only control recursion into repo working dirs'''
@@ -768,7 +629,7 b' def _interestingfiles(repo, matcher):'
     This is different from dirstate.status because it doesn't care about
     whether files are modified or clean.'''
     added, unknown, deleted, removed = [], [], [], []
-    audit_path = pathauditor(repo.root)
+    audit_path = pathutil.pathauditor(repo.root)
 
     ctx = repo[None]
     dirstate = repo.dirstate

mercurial/subrepo.py

@@ -9,7 +9,8 b' import errno, os, re, shutil, posixpath,'
 import xml.dom.minidom
 import stat, subprocess, tarfile
 from i18n import _
-import config, scmutil, util, node, error, cmdutil, bookmarks, match as matchmod
+import config, util, node, error, cmdutil, bookmarks, match as matchmod
+import pathutil
 hg = None
 propertycache = util.propertycache
 
@@ -332,7 +333,7 b' def subrepo(ctx, path):'
     import hg as h
     hg = h
 
-    scmutil.pathauditor(ctx._repo.root)(path)
+    pathutil.pathauditor(ctx._repo.root)(path)
     state = ctx.substate[path]
     if state[2] not in types:
         raise util.Abort(_('unknown subrepo type %s') % state[2])