mercurial/statichttprepo.py

hgweb: support Content Security Policy

Content-Security-Policy (CSP) is a web security feature that allows
servers to declare what loaded content is allowed to do. For example,
a policy can prevent loading of images, JavaScript, CSS, etc unless
the source of that content is whitelisted (by hostname, URI scheme,
hashes of content, etc). It's a nifty security feature that provides
extra mitigation against some attacks, notably XSS.

Mitigation against these attacks is important for Mercurial because
hgweb renders repository data, which is commonly untrusted. While we
make attempts to escape things, etc, there's the possibility that
malicious data could be injected into the site content. If this happens
today, the full power of the web browser is available to that
malicious content. A restrictive CSP policy (defined by the server
operator and sent in an HTTP header which is outside the control of
malicious content), could restrict browser capabilities and mitigate
security problems posed by malicious data.

CSP works by emitting an HTTP header declaring the policy that browsers
should apply. Ideally, this header would be emitted by a layer above
Mercurial (likely the HTTP server doing the WSGI "proxying"). This
works for some CSP policies, but not all.

For example, policies to allow inline JavaScript may require setting
a "nonce" attribute on <script>. This attribute value must be unique
and non-guessable. And, the value must be present in the HTTP header
and the HTML body. This means that coordinating the value between
Mercurial and another HTTP server could be difficult: it is much
easier to generate and emit the nonce in a central location.

This commit introduces support for emitting a
Content-Security-Policy header from hgweb. A config option defines
the header value. If present, the header is emitted. A special
"%nonce%" syntax in the value triggers generation of a nonce and
inclusion in <script> elements in templates. The inclusion of a
nonce does not occur unless "%nonce%" is present. This makes this
commit completely backwards compatible and the feature opt-in.

The nonce is a type 4 UUID, which is the flavor that is randomly
generated. It has 122 random bits, which should be plenty to satisfy
the guarantees of a nonce.

# statichttprepo.py - simple http repository class for mercurial
#
# This provides read-only repo access to repositories exported via static http
#
# Copyright 2005-2007 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

import errno
import os

from .i18n import _
from . import (
    byterange,
    changelog,
    error,
    localrepo,
    manifest,
    namespaces,
    scmutil,
    store,
    url,
    util,
)

urlerr = util.urlerr
urlreq = util.urlreq

class httprangereader(object):
    def __init__(self, url, opener):
        # we assume opener has HTTPRangeHandler
        self.url = url
        self.pos = 0
        self.opener = opener
        self.name = url

    def __enter__(self):
        return self

    def __exit__(self, exc_type, exc_value, traceback):
        self.close()

    def seek(self, pos):
        self.pos = pos
    def read(self, bytes=None):
        req = urlreq.request(self.url)
        end = ''
        if bytes:
            end = self.pos + bytes - 1
        if self.pos or end:
            req.add_header('Range', 'bytes=%d-%s' % (self.pos, end))

        try:
            f = self.opener.open(req)
            data = f.read()
            code = f.code
        except urlerr.httperror as inst:
            num = inst.code == 404 and errno.ENOENT or None
            raise IOError(num, inst)
        except urlerr.urlerror as inst:
            raise IOError(None, inst.reason[1])

        if code == 200:
            # HTTPRangeHandler does nothing if remote does not support
            # Range headers and returns the full entity. Let's slice it.
            if bytes:
                data = data[self.pos:self.pos + bytes]
            else:
                data = data[self.pos:]
        elif bytes:
            data = data[:bytes]
        self.pos += len(data)
        return data
    def readlines(self):
        return self.read().splitlines(True)
    def __iter__(self):
        return iter(self.readlines())
    def close(self):
        pass

def build_opener(ui, authinfo):
    # urllib cannot handle URLs with embedded user or passwd
    urlopener = url.opener(ui, authinfo)
    urlopener.add_handler(byterange.HTTPRangeHandler())

    class statichttpvfs(scmutil.abstractvfs):
        def __init__(self, base):
            self.base = base

        def __call__(self, path, mode='r', *args, **kw):
            if mode not in ('r', 'rb'):
                raise IOError('Permission denied')
            f = "/".join((self.base, urlreq.quote(path)))
            return httprangereader(f, urlopener)

        def join(self, path):
            if path:
                return os.path.join(self.base, path)
            else:
                return self.base

    return statichttpvfs

class statichttppeer(localrepo.localpeer):
    def local(self):
        return None
    def canpush(self):
        return False

class statichttprepository(localrepo.localrepository):
    supported = localrepo.localrepository._basesupported

    def __init__(self, ui, path):
        self._url = path
        self.ui = ui

        self.root = path
        u = util.url(path.rstrip('/') + "/.hg")
        self.path, authinfo = u.authinfo()

        opener = build_opener(ui, authinfo)
        self.opener = opener(self.path)
        self.vfs = self.opener
        self._phasedefaults = []

        self.names = namespaces.namespaces()

        try:
            requirements = scmutil.readrequires(self.vfs, self.supported)
        except IOError as inst:
            if inst.errno != errno.ENOENT:
                raise
            requirements = set()

            # check if it is a non-empty old-style repository
            try:
                fp = self.vfs("00changelog.i")
                fp.read(1)
                fp.close()
            except IOError as inst:
                if inst.errno != errno.ENOENT:
                    raise
                # we do not care about empty old-style repositories here
                msg = _("'%s' does not appear to be an hg repository") % path
                raise error.RepoError(msg)

        # setup store
        self.store = store.store(requirements, self.path, opener)
        self.spath = self.store.path
        self.svfs = self.store.opener
        self.sjoin = self.store.join
        self._filecache = {}
        self.requirements = requirements

        self.manifestlog = manifest.manifestlog(self.svfs, self)
        self.changelog = changelog.changelog(self.svfs)
        self._tags = None
        self.nodetagscache = None
        self._branchcaches = {}
        self._revbranchcache = None
        self.encodepats = None
        self.decodepats = None
        self._transref = None

    def _restrictcapabilities(self, caps):
        caps = super(statichttprepository, self)._restrictcapabilities(caps)
        return caps.difference(["pushkey"])

    def url(self):
        return self._url

    def local(self):
        return False

    def peer(self):
        return statichttppeer(self)

    def lock(self, wait=True):
        raise error.Abort(_('cannot lock static-http repository'))

    def _writecaches(self):
        pass # statichttprepository are read only

def instance(ui, path, create):
    if create:
        raise error.Abort(_('cannot create new static-http repository'))
    return statichttprepository(ui, path[7:])