view mercurial/hgweb/request.py @ 26755:bb0b955d050d

streamclone: support for producing and consuming stream clone bundles

Up to this point, stream clones only existed as a dynamically generated
data format produced and consumed during streaming clones. In order to
support this efficient cloning format with the clone bundles feature, we
need a more formal, on disk representation of the streaming clone data.

This patch introduces a new "bundle" type for streaming clones. Unlike
existing bundles, it does not contain changegroup data. It does,
however, share the same concepts like the 4 byte header which identifies
the type of data that follows and the 2 byte abbreviation for
compression types (of which only "UN" is currently supported).

The new bundle format is essentially the existing stream clone version 1
data format with some headers at the beginning.

Content negotiation at stream clone request time checked for repository
format/requirements compatibility before initiating a stream clone. We
can't do active content negotiation when using clone bundles. So, we put
this set of requirements inside the payload so consumers have a built-in
mechanism for checking compatibility before reading and applying lots of
data. Of course, we will also advertise this requirements set in clone
bundles. But that's for another patch.

We currently don't have a mechanism to produce and consume this new
bundle format. This will be implemented in upcoming patches.

It's worth noting that if a legacy client attempts to `hg unbundle` a
stream clone bundle (with the "HGS1" header), it will abort with:
"unknown bundle version S1," which seems appropriate.

# hgweb/request.py - An http request from either CGI or the standalone server.
#
# Copyright 21 May 2005 - (c) 2005 Jake Edge <[e-mail]>
# Copyright 2005, 2006 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.

import socket, cgi, errno
from mercurial import util
from common import ErrorResponse, statusmessage, HTTP_NOT_MODIFIED

shortcuts = {
    'cl': [('cmd', ['changelog']), ('rev', None)],
    'sl': [('cmd', ['shortlog']), ('rev', None)],
    'cs': [('cmd', ['changeset']), ('node', None)],
    'f': [('cmd', ['file']), ('filenode', None)],
    'fl': [('cmd', ['filelog']), ('filenode', None)],
    'fd': [('cmd', ['filediff']), ('node', None)],
    'fa': [('cmd', ['annotate']), ('filenode', None)],
    'mf': [('cmd', ['manifest']), ('manifest', None)],
    'ca': [('cmd', ['archive']), ('node', None)],
    'tags': [('cmd', ['tags'])],
    'tip': [('cmd', ['changeset']), ('node', ['tip'])],
    'static': [('cmd', ['static']), ('file', None)]
}

def normalize(form):
    # first expand the shortcuts
    for k in shortcuts.iterkeys():
        if k in form:
            for name, value in shortcuts[k]:
                if value is None:
                    value = form[k]
                form[name] = value
            del form[k]
    # And strip the values
    for k, v in form.iteritems():
        form[k] = [i.strip() for i in v]
    return form

class wsgirequest(object):
    """Higher-level API for a WSGI request.

    WSGI applications are invoked with 2 arguments. They are used to
    instantiate instances of this class, which provides higher-level APIs
    for obtaining request parameters, writing HTTP output, etc.
    """
    def __init__(self, wsgienv, start_response):
        version = wsgienv['wsgi.version']
        if (version < (1, 0)) or (version >= (2, 0)):
            raise RuntimeError("Unknown and unsupported WSGI version %d.%d"
                               % version)
        self.inp = wsgienv['wsgi.input']
        self.err = wsgienv['wsgi.errors']
        self.threaded = wsgienv['wsgi.multithread']
        self.multiprocess = wsgienv['wsgi.multiprocess']
        self.run_once = wsgienv['wsgi.run_once']
        self.env = wsgienv
        self.form = normalize(cgi.parse(self.inp,
                                        self.env,
                                        keep_blank_values=1))
        self._start_response = start_response
        self.server_write = None
        self.headers = []

    def __iter__(self):
        return iter([])

    def read(self, count=-1):
        return self.inp.read(count)

    def drain(self):
        '''need to read all data from request, httplib is half-duplex'''
        length = int(self.env.get('CONTENT_LENGTH') or 0)
        for s in util.filechunkiter(self.inp, limit=length):
            pass

    def respond(self, status, type, filename=None, body=None):
        if self._start_response is not None:
            self.headers.append(('Content-Type', type))
            if filename:
                filename = (filename.split('/')[-1]
                            .replace('\\', '\\\\').replace('"', '\\"'))
                self.headers.append(('Content-Disposition',
                                     'inline; filename="%s"' % filename))
            if body is not None:
                self.headers.append(('Content-Length', str(len(body))))

            for k, v in self.headers:
                if not isinstance(v, str):
                    raise TypeError('header value must be string: %r' % (v,))

            if isinstance(status, ErrorResponse):
                self.headers.extend(status.headers)
                if status.code == HTTP_NOT_MODIFIED:
                    # RFC 2616 Section 10.3.5: 304 Not Modified has cases where
                    # it MUST NOT include any headers other than these and no
                    # body
                    self.headers = [(k, v) for (k, v) in self.headers if
                                    k in ('Date', 'ETag', 'Expires',
                                          'Cache-Control', 'Vary')]
                status = statusmessage(status.code, str(status))
            elif status == 200:
                status = '200 Script output follows'
            elif isinstance(status, int):
                status = statusmessage(status)

            self.server_write = self._start_response(status, self.headers)
            self._start_response = None
            self.headers = []
        if body is not None:
            self.write(body)
            self.server_write = None

    def write(self, thing):
        if thing:
            try:
                self.server_write(thing)
            except socket.error as inst:
                if inst[0] != errno.ECONNRESET:
                    raise

    def writelines(self, lines):
        for line in lines:
            self.write(line)

    def flush(self):
        return None

    def close(self):
        return None

def wsgiapplication(app_maker):
    '''For compatibility with old CGI scripts. A plain hgweb() or hgwebdir()
    can and should now be used as a WSGI application.'''
    application = app_maker()
    def run_wsgi(env, respond):
        return application(env, respond)
    return run_wsgi