comparison mercurial/url.py @ 13848:b2798c1defff

url: be stricter about detecting schemes

While the URL parser is very forgiving about what characters are
allowed in each component, it's useful to be strict about the scheme
so we don't accidentally interpret local paths with colons as URLs.

This restricts schemes to containing alphanumeric characters, dashes,
pluses, and dots (as specified in RFC 2396).

13845:ddcb57a2eaeb

# Copyright 2006 Vadim Gelfer <[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.

import urllib, urllib2, httplib, os, socket, cStringIO
import __builtin__
from i18n import _
import keepalive, util

class url(object):

    <url scheme: 'http', host: 'host', path: 'a?b#c'>
    """

    _safechars = "!~*'()+"
    _safepchars = "/!~*'()+"

    def __init__(self, path, parsequery=True, parsefragment=True):
        # We slowly chomp away at path until we have only the path left
        self.scheme = self.user = self.passwd = self.host = None
        self.port = self.path = self.query = self.fragment = None

            if path.startswith('//'):
                path = path[2:]
            self.path = path
            return

        if not path.startswith('/') and ':' in path:
            parts = path.split(':', 1)
            if parts[0]:
                self.scheme, path = parts
                self._localpath = False

13848:b2798c1defff

# Copyright 2006 Vadim Gelfer <[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.

import urllib, urllib2, httplib, os, socket, cStringIO, re
import __builtin__
from i18n import _
import keepalive, util

class url(object):

    <url scheme: 'http', host: 'host', path: 'a?b#c'>
    """

    _safechars = "!~*'()+"
    _safepchars = "/!~*'()+"
    _matchscheme = re.compile(r'^[a-zA-Z0-9+.\-]+:').match

    def __init__(self, path, parsequery=True, parsefragment=True):
        # We slowly chomp away at path until we have only the path left
        self.scheme = self.user = self.passwd = self.host = None
        self.port = self.path = self.query = self.fragment = None

            if path.startswith('//'):
                path = path[2:]
            self.path = path
            return

        if self._matchscheme(path):
            parts = path.split(':', 1)
            if parts[0]:
                self.scheme, path = parts
                self._localpath = False