view mercurial/pushkey.py @ 45020:697212a830fb stable

convert: bail out in Subversion source if encountering non-ASCII HTTP(S) URL

Before this patch, in the tested case, urllib raised `httplib.InvalidURL: URL
can't contain control characters. '/\xff/!svn/ver/0/.svn' (found at least
'\xff')`, which resulted in that the URL was never recognized as a Subversion
repository.

This patch adds a check that bails out if the URL contains non-ASCII characters.
The warning is not overly user-friendly, but giving the user something to type
into a search engine is definitively better than not explaining why the
repository was not recognized.

We could support non-ASCII chracters by quoting them before passing them to
urllib. However, we would want to be compatible with what the `svn` command
does, which converts the URL from the locale encoding to UTF-8, percent-encodes
it and sends it to the server. If the locale encoding is not UTF-8, the
behavior is IMHO not very intuitive, as the `svn` command may send different
(percent-encoded) octets than what was passed on the console. Instead of
copying this behavior, we better leave it forbidden.

# pushkey.py - dispatching for pushing and pulling keys
#
# Copyright 2010 Matt Mackall <[e-mail]>
#
# 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

from . import (
    bookmarks,
    encoding,
    obsolete,
    phases,
)


def _nslist(repo):
    n = {}
    for k in _namespaces:
        n[k] = b""
    if not obsolete.isenabled(repo, obsolete.exchangeopt):
        n.pop(b'obsolete')
    return n


_namespaces = {
    b"namespaces": (lambda *x: False, _nslist),
    b"bookmarks": (bookmarks.pushbookmark, bookmarks.listbookmarks),
    b"phases": (phases.pushphase, phases.listphases),
    b"obsolete": (obsolete.pushmarker, obsolete.listmarkers),
}


def register(namespace, pushkey, listkeys):
    _namespaces[namespace] = (pushkey, listkeys)


def _get(namespace):
    return _namespaces.get(namespace, (lambda *x: False, lambda *x: {}))


def push(repo, namespace, key, old, new):
    '''should succeed iff value was old'''
    pk = _get(namespace)[0]
    return pk(repo, key, old, new)


def list(repo, namespace):
    '''return a dict'''
    lk = _get(namespace)[1]
    return lk(repo)


encode = encoding.fromlocal

decode = encoding.tolocal


def encodekeys(keys):
    """encode the content of a pushkey namespace for exchange over the wire"""
    return b'\n'.join([b'%s\t%s' % (encode(k), encode(v)) for k, v in keys])


def decodekeys(data):
    """decode the content of a pushkey namespace from exchange over the wire"""
    result = {}
    for l in data.splitlines():
        k, v = l.split(b'\t')
        result[decode(k)] = decode(v)
    return result