annotate mercurial/hgweb/server.py @ 27142:060f83d219b9

extensions: refuse to load extensions if minimum hg version not met

As the author of several 3rd party extensions, I frequently see bug
reports from users attempting to run my extension with an old version
of Mercurial that I no longer support in my extension. Oftentimes, the
extension will import just fine. But as soon as we run extsetup(),
reposetup(), or get into the guts of a wrapped function, we encounter
an exception and abort. Today, Mercurial will print a message about
extensions that don't have a "testedwith" declaring explicit
compatibility with the current version.

The existing mechanism is a good start. But it isn't as robust as I
would like. Specifically, Mercurial assumes compatibility by default.
This means extension authors must perform compatibility checking in
their extsetup() or we wait and see if we encounter an abort at
runtime. And, compatibility checking can involve a lot of code and
lots of error checking. It's a lot of effort for extension authors.

Oftentimes, extension authors know which versions of Mercurial there
extension works on and more importantly where it is broken.

This patch introduces a magic "minimumhgversion" attribute in
extensions. When found, the extension loading mechanism will compare
the declared version against the current Mercurial version. If the
extension explicitly states we require a newer Mercurial version, a
warning is printed and the extension isn't loaded beyond importing
the Python module. This causes a graceful failure while alerting
the user of the compatibility issue.

I would be receptive to the idea of making the failure more fatal.
However, care would need to be taken to not criple every hg command.
e.g. the user may use `hg config` to fix the hgrc and if we aborted
trying to run that, the user would effectively be locked out of `hg`!

A potential future improvement to this functionality would be to catch
ImportError for the extension/module and parse the source code for
"minimumhgversion = 'XXX'" and do similar checking. This way we could
give more information about why the extension failed to load.

# hgweb/server.py - The standalone hg web server.
#
# Copyright 21 May 2005 - (c) 2005 Jake Edge <[e-mail]>
# 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 BaseHTTPServer
import SocketServer
import errno
import os
import socket
import sys
import traceback
import urllib

from ..i18n import _

from .. import (
    error,
    util,
)

from . import (
    common,
)

def _splitURI(uri):
    """Return path and query that has been split from uri

    Just like CGI environment, the path is unquoted, the query is
    not.
    """
    if '?' in uri:
        path, query = uri.split('?', 1)
    else:
        path, query = uri, ''
    return urllib.unquote(path), query

class _error_logger(object):
    def __init__(self, handler):
        self.handler = handler
    def flush(self):
        pass
    def write(self, str):
        self.writelines(str.split('\n'))
    def writelines(self, seq):
        for msg in seq:
            self.handler.log_error("HG error:  %s", msg)

class _httprequesthandler(BaseHTTPServer.BaseHTTPRequestHandler):

    url_scheme = 'http'

    @staticmethod
    def preparehttpserver(httpserver, ssl_cert):
        """Prepare .socket of new HTTPServer instance"""
        pass

    def __init__(self, *args, **kargs):
        self.protocol_version = 'HTTP/1.1'
        BaseHTTPServer.BaseHTTPRequestHandler.__init__(self, *args, **kargs)

    def _log_any(self, fp, format, *args):
        fp.write("%s - - [%s] %s\n" % (self.client_address[0],
                                       self.log_date_time_string(),
                                       format % args))
        fp.flush()

    def log_error(self, format, *args):
        self._log_any(self.server.errorlog, format, *args)

    def log_message(self, format, *args):
        self._log_any(self.server.accesslog, format, *args)

    def log_request(self, code='-', size='-'):
        xheaders = []
        if util.safehasattr(self, 'headers'):
            xheaders = [h for h in self.headers.items()
                        if h[0].startswith('x-')]
        self.log_message('"%s" %s %s%s',
                         self.requestline, str(code), str(size),
                         ''.join([' %s:%s' % h for h in sorted(xheaders)]))

    def do_write(self):
        try:
            self.do_hgweb()
        except socket.error as inst:
            if inst[0] != errno.EPIPE:
                raise

    def do_POST(self):
        try:
            self.do_write()
        except Exception:
            self._start_response("500 Internal Server Error", [])
            self._write("Internal Server Error")
            self._done()
            tb = "".join(traceback.format_exception(*sys.exc_info()))
            self.log_error("Exception happened during processing "
                           "request '%s':\n%s", self.path, tb)

    def do_GET(self):
        self.do_POST()

    def do_hgweb(self):
        path, query = _splitURI(self.path)

        env = {}
        env['GATEWAY_INTERFACE'] = 'CGI/1.1'
        env['REQUEST_METHOD'] = self.command
        env['SERVER_NAME'] = self.server.server_name
        env['SERVER_PORT'] = str(self.server.server_port)
        env['REQUEST_URI'] = self.path
        env['SCRIPT_NAME'] = self.server.prefix
        env['PATH_INFO'] = path[len(self.server.prefix):]
        env['REMOTE_HOST'] = self.client_address[0]
        env['REMOTE_ADDR'] = self.client_address[0]
        if query:
            env['QUERY_STRING'] = query

        if self.headers.typeheader is None:
            env['CONTENT_TYPE'] = self.headers.type
        else:
            env['CONTENT_TYPE'] = self.headers.typeheader
        length = self.headers.getheader('content-length')
        if length:
            env['CONTENT_LENGTH'] = length
        for header in [h for h in self.headers.keys()
                       if h not in ('content-type', 'content-length')]:
            hkey = 'HTTP_' + header.replace('-', '_').upper()
            hval = self.headers.getheader(header)
            hval = hval.replace('\n', '').strip()
            if hval:
                env[hkey] = hval
        env['SERVER_PROTOCOL'] = self.request_version
        env['wsgi.version'] = (1, 0)
        env['wsgi.url_scheme'] = self.url_scheme
        if env.get('HTTP_EXPECT', '').lower() == '100-continue':
            self.rfile = common.continuereader(self.rfile, self.wfile.write)

        env['wsgi.input'] = self.rfile
        env['wsgi.errors'] = _error_logger(self)
        env['wsgi.multithread'] = isinstance(self.server,
                                             SocketServer.ThreadingMixIn)
        env['wsgi.multiprocess'] = isinstance(self.server,
                                              SocketServer.ForkingMixIn)
        env['wsgi.run_once'] = 0

        self.saved_status = None
        self.saved_headers = []
        self.sent_headers = False
        self.length = None
        self._chunked = None
        for chunk in self.server.application(env, self._start_response):
            self._write(chunk)
        if not self.sent_headers:
            self.send_headers()
        self._done()

    def send_headers(self):
        if not self.saved_status:
            raise AssertionError("Sending headers before "
                                 "start_response() called")
        saved_status = self.saved_status.split(None, 1)
        saved_status[0] = int(saved_status[0])
        self.send_response(*saved_status)
        self.length = None
        self._chunked = False
        for h in self.saved_headers:
            self.send_header(*h)
            if h[0].lower() == 'content-length':
                self.length = int(h[1])
        if (self.length is None and
            saved_status[0] != common.HTTP_NOT_MODIFIED):
            self._chunked = (not self.close_connection and
                             self.request_version == "HTTP/1.1")
            if self._chunked:
                self.send_header('Transfer-Encoding', 'chunked')
            else:
                self.send_header('Connection', 'close')
        self.end_headers()
        self.sent_headers = True

    def _start_response(self, http_status, headers, exc_info=None):
        code, msg = http_status.split(None, 1)
        code = int(code)
        self.saved_status = http_status
        bad_headers = ('connection', 'transfer-encoding')
        self.saved_headers = [h for h in headers
                              if h[0].lower() not in bad_headers]
        return self._write

    def _write(self, data):
        if not self.saved_status:
            raise AssertionError("data written before start_response() called")
        elif not self.sent_headers:
            self.send_headers()
        if self.length is not None:
            if len(data) > self.length:
                raise AssertionError("Content-length header sent, but more "
                                     "bytes than specified are being written.")
            self.length = self.length - len(data)
        elif self._chunked and data:
            data = '%x\r\n%s\r\n' % (len(data), data)
        self.wfile.write(data)
        self.wfile.flush()

    def _done(self):
        if self._chunked:
            self.wfile.write('0\r\n\r\n')
            self.wfile.flush()

class _httprequesthandlerssl(_httprequesthandler):
    """HTTPS handler based on Python's ssl module"""

    url_scheme = 'https'

    @staticmethod
    def preparehttpserver(httpserver, ssl_cert):
        try:
            import ssl
            ssl.wrap_socket
        except ImportError:
            raise error.Abort(_("SSL support is unavailable"))
        httpserver.socket = ssl.wrap_socket(
            httpserver.socket, server_side=True,
            certfile=ssl_cert, ssl_version=ssl.PROTOCOL_TLSv1)

    def setup(self):
        self.connection = self.request
        self.rfile = socket._fileobject(self.request, "rb", self.rbufsize)
        self.wfile = socket._fileobject(self.request, "wb", self.wbufsize)

try:
    import threading
    threading.activeCount() # silence pyflakes and bypass demandimport
    _mixin = SocketServer.ThreadingMixIn
except ImportError:
    if util.safehasattr(os, "fork"):
        _mixin = SocketServer.ForkingMixIn
    else:
        class _mixin(object):
            pass

def openlog(opt, default):
    if opt and opt != '-':
        return open(opt, 'a')
    return default

class MercurialHTTPServer(object, _mixin, BaseHTTPServer.HTTPServer):

    # SO_REUSEADDR has broken semantics on windows
    if os.name == 'nt':
        allow_reuse_address = 0

    def __init__(self, ui, app, addr, handler, **kwargs):
        BaseHTTPServer.HTTPServer.__init__(self, addr, handler, **kwargs)
        self.daemon_threads = True
        self.application = app

        handler.preparehttpserver(self, ui.config('web', 'certificate'))

        prefix = ui.config('web', 'prefix', '')
        if prefix:
            prefix = '/' + prefix.strip('/')
        self.prefix = prefix

        alog = openlog(ui.config('web', 'accesslog', '-'), sys.stdout)
        elog = openlog(ui.config('web', 'errorlog', '-'), sys.stderr)
        self.accesslog = alog
        self.errorlog = elog

        self.addr, self.port = self.socket.getsockname()[0:2]
        self.fqaddr = socket.getfqdn(addr[0])

class IPv6HTTPServer(MercurialHTTPServer):
    address_family = getattr(socket, 'AF_INET6', None)
    def __init__(self, *args, **kwargs):
        if self.address_family is None:
            raise error.RepoError(_('IPv6 is not available on this system'))
        super(IPv6HTTPServer, self).__init__(*args, **kwargs)

def create_server(ui, app):

    if ui.config('web', 'certificate'):
        handler = _httprequesthandlerssl
    else:
        handler = _httprequesthandler

    if ui.configbool('web', 'ipv6'):
        cls = IPv6HTTPServer
    else:
        cls = MercurialHTTPServer

    # ugly hack due to python issue5853 (for threaded use)
    try:
        import mimetypes
        mimetypes.init()
    except UnicodeDecodeError:
        # Python 2.x's mimetypes module attempts to decode strings
        # from Windows' ANSI APIs as ascii (fail), then re-encode them
        # as ascii (clown fail), because the default Python Unicode
        # codec is hardcoded as ascii.

        sys.argv # unwrap demand-loader so that reload() works
        reload(sys) # resurrect sys.setdefaultencoding()
        oldenc = sys.getdefaultencoding()
        sys.setdefaultencoding("latin1") # or any full 8-bit encoding
        mimetypes.init()
        sys.setdefaultencoding(oldenc)

    address = ui.config('web', 'address', '')
    port = util.getport(ui.config('web', 'port', 8000))
    try:
        return cls(ui, app, (address, port), handler)
    except socket.error as inst:
        raise error.Abort(_("cannot start server at '%s:%d': %s")
                         % (address, port, inst.args[1]))