tests/get-with-headers.py

wireproto: config options to disable bundle1

bundle2 is the new and preferred wire protocol format. For various
reasons, server operators may wish to force clients to use it.

One reason is performance. If a repository is stored in generaldelta,
the server must recompute deltas in order to produce the bundle1
changegroup. This can be extremely expensive. For mozilla-central,
bundle generation typically takes a few minutes. However, generating
a non-gd bundle from a generaldelta encoded mozilla-central requires
over 30 minutes of CPU! If a large repository like mozilla-central
were encoded in generaldelta and non-gd clients connected, they could
easily flood a server by cloning.

This patch gives server operators config knobs to control whether
bundle1 is allowed for push and pull operations. The default is to
support legacy bundle1 clients, making this patch backwards compatible.

#!/usr/bin/env python

"""This does HTTP GET requests given a host:port and path and returns
a subset of the headers plus the body of the result."""

import httplib, sys

try:
    import json
except ImportError:
    try:
        import simplejson as json
    except ImportError:
        json = None

try:
    import msvcrt, os
    msvcrt.setmode(sys.stdout.fileno(), os.O_BINARY)
    msvcrt.setmode(sys.stderr.fileno(), os.O_BINARY)
except ImportError:
    pass

twice = False
if '--twice' in sys.argv:
    sys.argv.remove('--twice')
    twice = True
headeronly = False
if '--headeronly' in sys.argv:
    sys.argv.remove('--headeronly')
    headeronly = True
formatjson = False
if '--json' in sys.argv:
    sys.argv.remove('--json')
    formatjson = True

tag = None
def request(host, path, show):
    assert not path.startswith('/'), path
    global tag
    headers = {}
    if tag:
        headers['If-None-Match'] = tag

    conn = httplib.HTTPConnection(host)
    conn.request("GET", '/' + path, None, headers)
    response = conn.getresponse()
    print response.status, response.reason
    if show[:1] == ['-']:
        show = sorted(h for h, v in response.getheaders()
                      if h.lower() not in show)
    for h in [h.lower() for h in show]:
        if response.getheader(h, None) is not None:
            print "%s: %s" % (h, response.getheader(h))
    if not headeronly:
        print
        data = response.read()

        # Pretty print JSON. This also has the beneficial side-effect
        # of verifying emitted JSON is well-formed.
        if formatjson:
            if not json:
                print 'no json module not available'
                print 'did you forget a #require json?'
                sys.exit(1)

            # json.dumps() will print trailing newlines. Eliminate them
            # to make tests easier to write.
            data = json.loads(data)
            lines = json.dumps(data, sort_keys=True, indent=2).splitlines()
            for line in lines:
                print line.rstrip()
        else:
            sys.stdout.write(data)

        if twice and response.getheader('ETag', None):
            tag = response.getheader('ETag')

    return response.status

status = request(sys.argv[1], sys.argv[2], sys.argv[3:])
if twice:
    status = request(sys.argv[1], sys.argv[2], sys.argv[3:])

if 200 <= status <= 305:
    sys.exit(0)
sys.exit(1)