view mercurial/hgweb/wsgicgi.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/wsgicgi.py - CGI->WSGI translator
#
# Copyright 2006 Eric Hopper <[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.
#
# This was originally copied from the public domain code at
# http://www.python.org/dev/peps/pep-0333/#the-server-gateway-side

from __future__ import absolute_import

import os

from .. import (
    pycompat,
)

from ..utils import (
    procutil,
)

from . import (
    common,
)

def launch(application):
    procutil.setbinary(procutil.stdin)
    procutil.setbinary(procutil.stdout)

    environ = dict(os.environ.iteritems()) # re-exports
    environ.setdefault(r'PATH_INFO', '')
    if environ.get(r'SERVER_SOFTWARE', r'').startswith(r'Microsoft-IIS'):
        # IIS includes script_name in PATH_INFO
        scriptname = environ[r'SCRIPT_NAME']
        if environ[r'PATH_INFO'].startswith(scriptname):
            environ[r'PATH_INFO'] = environ[r'PATH_INFO'][len(scriptname):]

    stdin = procutil.stdin
    if environ.get(r'HTTP_EXPECT', r'').lower() == r'100-continue':
        stdin = common.continuereader(stdin, procutil.stdout.write)

    environ[r'wsgi.input'] = stdin
    environ[r'wsgi.errors'] = procutil.stderr
    environ[r'wsgi.version'] = (1, 0)
    environ[r'wsgi.multithread'] = False
    environ[r'wsgi.multiprocess'] = True
    environ[r'wsgi.run_once'] = True

    if environ.get(r'HTTPS', r'off').lower() in (r'on', r'1', r'yes'):
        environ[r'wsgi.url_scheme'] = r'https'
    else:
        environ[r'wsgi.url_scheme'] = r'http'

    headers_set = []
    headers_sent = []
    out = procutil.stdout

    def write(data):
        if not headers_set:
            raise AssertionError("write() before start_response()")

        elif not headers_sent:
            # Before the first output, send the stored headers
            status, response_headers = headers_sent[:] = headers_set
            out.write('Status: %s\r\n' % pycompat.bytesurl(status))
            for hk, hv in response_headers:
                out.write('%s: %s\r\n' % (pycompat.bytesurl(hk),
                                          pycompat.bytesurl(hv)))
            out.write('\r\n')

        out.write(data)
        out.flush()

    def start_response(status, response_headers, exc_info=None):
        if exc_info:
            try:
                if headers_sent:
                    # Re-raise original exception if headers sent
                    raise exc_info[0](exc_info[1], exc_info[2])
            finally:
                exc_info = None     # avoid dangling circular ref
        elif headers_set:
            raise AssertionError("Headers already set!")

        headers_set[:] = [status, response_headers]
        return write

    content = application(environ, start_response)
    try:
        for chunk in content:
            write(chunk)
        if not headers_sent:
            write('')   # send headers now if body was empty
    finally:
        getattr(content, 'close', lambda: None)()