view mercurial/pathutil.py @ 28029:72072cfc7e91

update: warn about other topological heads on bare update

A concern around the user experience of Mercurial is user getting stuck on there
own topological branch forever. For example, someone pulling another topological
branch, missing that message in pull asking them to merge and getting stuck on
there own local branch.

The current way to "address" this concern was for bare 'hg update' to target the
tipmost (also latest pulled) changesets and complain when the update was not
linear. That way, failure to merge newly pulled changesets would result in some
kind of failure.

Yet the failure was quite obscure, not working in all cases (eg: commit right
after pull) and the behavior was very impractical in the common case
(eg: issue4673).

To be able to change that behavior, we need to provide other ways to alert a
user stucks on one of many topological head. We do so with an extra message after
bare update:

  1 other heads for branch "default"

Bookmark get its own special version:

  1 other divergent bookmarks for "foobar"

There is significant room to improve the message itself, and we should augment
it with hint about how to see theses other heads or handle the situation (see
in-line comment). But having "a" message is already a significant improvement
compared to the existing situation. Once we have it we can iterate on a better
version of it. As having such message is an important step toward changing the
default destination for update and other nicety, I would like to move forward
quickly on getting such message.

This was discussed during London - October 2015 Sprint.

from __future__ import absolute_import

import errno
import os
import posixpath
import stat

from .i18n import _
from . import (
    encoding,
    error,
    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.
    '''

    def __init__(self, root, callback=None, realfs=True):
        self.audited = set()
        self.auditeddir = set()
        self.root = root
        self._realfs = realfs
        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 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 = []
        while parts:
            prefix = os.sep.join(parts)
            normprefix = os.sep.join(normparts)
            if normprefix in self.auditeddir:
                break
            if self._realfs:
                self._checkfs(prefix, path)
            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 _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 + 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

        # 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('/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

# 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