view mercurial/hgweb/__init__.py @ 40626:87a872555e90

revlog: detect incomplete revlog reads

_readsegment() is supposed to return N bytes of revlog revision
data starting at a file offset. Surprisingly, its behavior before
this patch never verified that it actually read and returned N
bytes! Instead, it would perform the read(), then return whatever
data was available. And even more surprisingly, nothing in the
call chain appears to have been validating that it received all
the data it was expecting.

This behavior could lead to partial or incomplete revision chunks
being operated on. This could result in e.g. cached deltas being
applied against incomplete base revisions. The delta application
process would happily perform this operation. Only hash
verification would detect the corruption and save us.

This commit changes the behavior of raw revlog reading to validate
that we actually read() the number of bytes that were requested.
We will raise a more specific error faster, rather than possibly
have it go undetected or manifest later in the call stack, at
delta application or hash verification.

Differential Revision: https://phab.mercurial-scm.org/D5266

# hgweb/__init__.py - web interface to a mercurial repository
#
# Copyright 21 May 2005 - (c) 2005 Jake Edge <[e-mail]>
# Copyright 2005 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 os

from ..i18n import _

from .. import (
    error,
    pycompat,
)

from ..utils import (
    procutil,
)

from . import (
    hgweb_mod,
    hgwebdir_mod,
    server,
)

def hgweb(config, name=None, baseui=None):
    '''create an hgweb wsgi object

    config can be one of:
    - repo object (single repo view)
    - path to repo (single repo view)
    - path to config file (multi-repo view)
    - dict of virtual:real pairs (multi-repo view)
    - list of virtual:real tuples (multi-repo view)
    '''

    if ((isinstance(config, bytes) and not os.path.isdir(config)) or
        isinstance(config, dict) or isinstance(config, list)):
        # create a multi-dir interface
        return hgwebdir_mod.hgwebdir(config, baseui=baseui)
    return hgweb_mod.hgweb(config, name=name, baseui=baseui)

def hgwebdir(config, baseui=None):
    return hgwebdir_mod.hgwebdir(config, baseui=baseui)

class httpservice(object):
    def __init__(self, ui, app, opts):
        self.ui = ui
        self.app = app
        self.opts = opts

    def init(self):
        procutil.setsignalhandler()
        self.httpd = server.create_server(self.ui, self.app)

        if (self.opts['port'] and
            not self.ui.verbose and
            not self.opts['print_url']):
            return

        if self.httpd.prefix:
            prefix = self.httpd.prefix.strip('/') + '/'
        else:
            prefix = ''

        port = r':%d' % self.httpd.port
        if port == r':80':
            port = r''

        bindaddr = self.httpd.addr
        if bindaddr == r'0.0.0.0':
            bindaddr = r'*'
        elif r':' in bindaddr: # IPv6
            bindaddr = r'[%s]' % bindaddr

        fqaddr = self.httpd.fqaddr
        if r':' in fqaddr:
            fqaddr = r'[%s]' % fqaddr

        url = 'http://%s%s/%s' % (
            pycompat.sysbytes(fqaddr), pycompat.sysbytes(port), prefix)
        if self.opts['print_url']:
            self.ui.write('%s\n' % url)
        else:
            if self.opts['port']:
                write = self.ui.status
            else:
                write = self.ui.write
            write(_('listening at %s (bound to %s:%d)\n') %
                  (url, pycompat.sysbytes(bindaddr), self.httpd.port))
        self.ui.flush()  # avoid buffering of status message

    def run(self):
        self.httpd.serve_forever()

def createapp(baseui, repo, webconf):
    if webconf:
        return hgwebdir_mod.hgwebdir(webconf, baseui=baseui)
    else:
        if not repo:
            raise error.RepoError(_("there is no Mercurial repository"
                                    " here (.hg not found)"))
        return hgweb_mod.hgweb(repo, baseui=baseui)