py3: use bytes os.sep in doctest of pathutil.py

mercurial/pathutil.py

@@ -1,221 +1,221 b''
 from __future__ import absolute_import
 
 import errno
 import os
 import posixpath
 import stat
 
 from .i18n import _
 from . import (
     encoding,
     error,
     pycompat,
     util,
 )
 
 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 ".."
 
     More check are also done about the file system states:
     - 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)
 
     The file system checks are only done when 'realfs' is set to True (the
     default). They should be disable then we are auditing path for operation on
     stored history.
 
     If 'cached' is set to True, audited paths and sub-directories are cached.
     Be careful to not keep the cache of unmanaged directories for long because
     audited paths may be replaced with symlinks.
     '''
 
     def __init__(self, root, callback=None, realfs=True, cached=False):
         self.audited = set()
         self.auditeddir = set()
         self.root = root
         self._realfs = realfs
         self._cached = cached
         self.callback = callback
         if os.path.lexists(root) and not util.fscasesensitive(root):
             self.normcase = util.normcase
         else:
             self.normcase = lambda x: x
 
     def __call__(self, path, mode=None):
         '''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 error.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 error.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 error.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 error.Abort(_("path '%s' is inside nested repo %r")
                                      % (path, base))
 
         normparts = util.splitpath(normpath)
         assert len(parts) == len(normparts)
 
         parts.pop()
         normparts.pop()
         prefixes = []
         # It's important that we check the path parts starting from the root.
         # This means we won't accidentally traverse a symlink into some other
         # filesystem (which is potentially expensive to access).
         for i in range(len(parts)):
             prefix = pycompat.ossep.join(parts[:i + 1])
             normprefix = pycompat.ossep.join(normparts[:i + 1])
             if normprefix in self.auditeddir:
                 continue
             if self._realfs:
                 self._checkfs(prefix, path)
             prefixes.append(normprefix)
 
         if self._cached:
             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 _checkfs(self, prefix, path):
         """raise exception if a file system backed check fails"""
         curpath = os.path.join(self.root, prefix)
         try:
             st = os.lstat(curpath)
         except OSError as 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):
                 msg = _('path %r traverses symbolic link %r') % (path, prefix)
                 raise error.Abort(msg)
             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):
                     msg = _("path '%s' is inside nested repo %r")
                     raise error.Abort(msg % (path, prefix))
 
     def check(self, path):
         try:
             self(path)
             return True
         except (OSError, error.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 + pycompat.ossep
     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
 
         # A common mistake is to use -R, but specify a file relative to the repo
         # instead of cwd.  Detect that case, and provide a hint to the user.
         hint = None
         try:
             if cwd != root:
                 canonpath(root, root, myname, auditor)
                 hint = (_("consider using '--cwd %s'")
                         % os.path.relpath(root, cwd))
         except error.Abort:
             pass
 
         raise error.Abort(_("%s not under root '%s'") % (myname, root),
                          hint=hint)
 
 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(b'/foo/bar').replace(os.sep, b'/')
+    >>> normasprefix(b'/foo/bar').replace(pycompat.ossep, b'/')
     '/foo/bar/'
-    >>> normasprefix(b'/').replace(os.sep, b'/')
+    >>> normasprefix(b'/').replace(pycompat.ossep, b'/')
     '/'
     '''
     d, p = os.path.splitdrive(path)
     if len(p) != len(pycompat.ossep):
         return path + pycompat.ossep
     else:
         return path
 
 # forward two methods from posixpath that do what we need, but we'd
 # rather not let our internals know that we're thinking in posix terms
 # - instead we'll let them be oblivious.
 join = posixpath.join
 dirname = posixpath.dirname

tests/test-doctest.py

@@ -1,81 +1,81 b''
 # this is hack to make sure no escape characters are inserted into the output
 
 from __future__ import absolute_import
 
 import doctest
 import os
 import re
 import sys
 
 ispy3 = (sys.version_info[0] >= 3)
 
 if 'TERM' in os.environ:
     del os.environ['TERM']
 
 class py3docchecker(doctest.OutputChecker):
     def check_output(self, want, got, optionflags):
         want2 = re.sub(r'''\bu(['"])(.*?)\1''', r'\1\2\1', want)  # py2: u''
         got2 = re.sub(r'''\bb(['"])(.*?)\1''', r'\1\2\1', got)  # py3: b''
         # py3: <exc.name>: b'<msg>' -> <name>: <msg>
         #      <exc.name>: <others> -> <name>: <others>
         got2 = re.sub(r'''^mercurial\.\w+\.(\w+): (['"])(.*?)\2''', r'\1: \3',
                       got2, re.MULTILINE)
         got2 = re.sub(r'^mercurial\.\w+\.(\w+): ', r'\1: ', got2, re.MULTILINE)
         return any(doctest.OutputChecker.check_output(self, w, g, optionflags)
                    for w, g in [(want, got), (want2, got2)])
 
 # TODO: migrate doctests to py3 and enable them on both versions
 def testmod(name, optionflags=0, testtarget=None, py2=True, py3=True):
     if not (not ispy3 and py2 or ispy3 and py3):
         return
     __import__(name)
     mod = sys.modules[name]
     if testtarget is not None:
         mod = getattr(mod, testtarget)
 
     # minimal copy of doctest.testmod()
     finder = doctest.DocTestFinder()
     checker = None
     if ispy3:
         checker = py3docchecker()
     runner = doctest.DocTestRunner(checker=checker, optionflags=optionflags)
     for test in finder.find(mod, name):
         runner.run(test)
     runner.summarize()
 
 testmod('mercurial.changegroup')
 testmod('mercurial.changelog')
 testmod('mercurial.color')
 testmod('mercurial.config')
 testmod('mercurial.context')
 testmod('mercurial.dagparser', optionflags=doctest.NORMALIZE_WHITESPACE)
 testmod('mercurial.dispatch')
 testmod('mercurial.encoding')
 testmod('mercurial.formatter', py3=False)  # py3: write bytes to stdout
 testmod('mercurial.hg')
 testmod('mercurial.hgweb.hgwebdir_mod', py3=False)  # py3: repr(bytes) ?
 testmod('mercurial.match')
 testmod('mercurial.mdiff')
 testmod('mercurial.minirst')
 testmod('mercurial.patch')
-testmod('mercurial.pathutil', py3=False)  # py3: os.sep
+testmod('mercurial.pathutil')
 testmod('mercurial.parser')
 testmod('mercurial.pycompat')
 testmod('mercurial.revsetlang')
 testmod('mercurial.smartset')
 testmod('mercurial.store')
 testmod('mercurial.subrepo')
 testmod('mercurial.templatefilters')
 testmod('mercurial.templater')
 testmod('mercurial.ui')
 testmod('mercurial.url')
 testmod('mercurial.util', py3=False)  # py3: multiple bytes/unicode issues
 testmod('mercurial.util', testtarget='platform')
 testmod('hgext.convert.convcmd', py3=False)  # py3: use of str() ?
 testmod('hgext.convert.cvsps')
 testmod('hgext.convert.filemap')
 testmod('hgext.convert.p4')
 testmod('hgext.convert.subversion')
 testmod('hgext.mq')
 # Helper scripts in tests/ that have doctests:
 testmod('drawdag')