tests/test-wsgirequest.py
author Gregory Szorc <gregory.szorc@gmail.com>
Tue, 10 Apr 2018 14:29:15 -0700
changeset 37557 734515aca84d
parent 36917 f0a851542a05
child 37715 1859b9a7ddef
permissions -rw-r--r--
wireproto: define and implement HTTP handshake to upgrade protocol When clients connect to repositories over HTTP, they issue a request to the well-known URL "?cmd=capabilities" to fetch the repository capabilities. This is the handshake portion of the HTTP protocol. This commit defines a mechanism to use that HTTP request to return information about modern server features. If a client sends an X-HgUpgrade-* header containing a list of client-supported API names, the server responds with a response containing information about available services. This includes the normal capabilities string. So if the server doesn't support any newer services, the client can easily fall back. By advertising supported services from clients, server operators can see and log what client support exists in the wild. This will also help with debugging. The response contains the base path to API services. We know there are potential issues with the <repo>/api/ URL space conflicting with hgwebdir and subrepos. By making the API URL dynamic from the perspective of the client, the URL for APIs is not subject to backwards compatibility concerns - at least as long as a ?cmd=capabilities request is made. We've also defined the ``cbor`` client capability for the X-HgProto-* header. This MUST be sent in order to get the modern response from "?cmd=capabilities". During implementation, I initially always sent an application/mercurial-cbor response. However, the handshake mechanism will be more future compatible if the client is in charge of which formats to request. We already perform content negotiation from X-HgProto-*, so keying off this for the capabilities response feels appropriate. In addition, I initially used application/cbor. However, it is conceivable that a non-Mercurial server could serve application/cbor. To rule out this possibility, I've invented a new media type that is Mercurial specific and can't be confused for generic CBOR. Differential Revision: https://phab.mercurial-scm.org/D3242

from __future__ import absolute_import, print_function

import unittest

from mercurial.hgweb import (
    request as requestmod,
)
from mercurial import (
    error,
)

DEFAULT_ENV = {
    r'REQUEST_METHOD': r'GET',
    r'SERVER_NAME': r'testserver',
    r'SERVER_PORT': r'80',
    r'SERVER_PROTOCOL': r'http',
    r'wsgi.version': (1, 0),
    r'wsgi.url_scheme': r'http',
    r'wsgi.input': None,
    r'wsgi.errors': None,
    r'wsgi.multithread': False,
    r'wsgi.multiprocess': True,
    r'wsgi.run_once': False,
}

def parse(env, reponame=None, altbaseurl=None, extra=None):
    env = dict(env)
    env.update(extra or {})

    return requestmod.parserequestfromenv(env, reponame=reponame,
                                          altbaseurl=altbaseurl)

class ParseRequestTests(unittest.TestCase):
    def testdefault(self):
        r = parse(DEFAULT_ENV)
        self.assertEqual(r.url, b'http://testserver')
        self.assertEqual(r.baseurl, b'http://testserver')
        self.assertEqual(r.advertisedurl, b'http://testserver')
        self.assertEqual(r.advertisedbaseurl, b'http://testserver')
        self.assertEqual(r.urlscheme, b'http')
        self.assertEqual(r.method, b'GET')
        self.assertIsNone(r.remoteuser)
        self.assertIsNone(r.remotehost)
        self.assertEqual(r.apppath, b'')
        self.assertEqual(r.dispatchparts, [])
        self.assertIsNone(r.dispatchpath)
        self.assertIsNone(r.reponame)
        self.assertEqual(r.querystring, b'')
        self.assertEqual(len(r.qsparams), 0)
        self.assertEqual(len(r.headers), 0)

    def testcustomport(self):
        r = parse(DEFAULT_ENV, extra={
            r'SERVER_PORT': r'8000',
        })

        self.assertEqual(r.url, b'http://testserver:8000')
        self.assertEqual(r.baseurl, b'http://testserver:8000')
        self.assertEqual(r.advertisedurl, b'http://testserver:8000')
        self.assertEqual(r.advertisedbaseurl, b'http://testserver:8000')

        r = parse(DEFAULT_ENV, extra={
            r'SERVER_PORT': r'4000',
            r'wsgi.url_scheme': r'https',
        })

        self.assertEqual(r.url, b'https://testserver:4000')
        self.assertEqual(r.baseurl, b'https://testserver:4000')
        self.assertEqual(r.advertisedurl, b'https://testserver:4000')
        self.assertEqual(r.advertisedbaseurl, b'https://testserver:4000')

    def testhttphost(self):
        r = parse(DEFAULT_ENV, extra={
            r'HTTP_HOST': r'altserver',
        })

        self.assertEqual(r.url, b'http://altserver')
        self.assertEqual(r.baseurl, b'http://altserver')
        self.assertEqual(r.advertisedurl, b'http://testserver')
        self.assertEqual(r.advertisedbaseurl, b'http://testserver')

    def testscriptname(self):
        r = parse(DEFAULT_ENV, extra={
            r'SCRIPT_NAME': r'',
        })

        self.assertEqual(r.url, b'http://testserver')
        self.assertEqual(r.baseurl, b'http://testserver')
        self.assertEqual(r.advertisedurl, b'http://testserver')
        self.assertEqual(r.advertisedbaseurl, b'http://testserver')
        self.assertEqual(r.apppath, b'')
        self.assertEqual(r.dispatchparts, [])
        self.assertIsNone(r.dispatchpath)

        r = parse(DEFAULT_ENV, extra={
            r'SCRIPT_NAME': r'/script',
        })

        self.assertEqual(r.url, b'http://testserver/script')
        self.assertEqual(r.baseurl, b'http://testserver')
        self.assertEqual(r.advertisedurl, b'http://testserver/script')
        self.assertEqual(r.advertisedbaseurl, b'http://testserver')
        self.assertEqual(r.apppath, b'/script')
        self.assertEqual(r.dispatchparts, [])
        self.assertIsNone(r.dispatchpath)

        r = parse(DEFAULT_ENV, extra={
            r'SCRIPT_NAME': r'/multiple words',
        })

        self.assertEqual(r.url, b'http://testserver/multiple%20words')
        self.assertEqual(r.baseurl, b'http://testserver')
        self.assertEqual(r.advertisedurl, b'http://testserver/multiple%20words')
        self.assertEqual(r.advertisedbaseurl, b'http://testserver')
        self.assertEqual(r.apppath, b'/multiple words')
        self.assertEqual(r.dispatchparts, [])
        self.assertIsNone(r.dispatchpath)

    def testpathinfo(self):
        r = parse(DEFAULT_ENV, extra={
            r'PATH_INFO': r'',
        })

        self.assertEqual(r.url, b'http://testserver')
        self.assertEqual(r.baseurl, b'http://testserver')
        self.assertEqual(r.advertisedurl, b'http://testserver')
        self.assertEqual(r.advertisedbaseurl, b'http://testserver')
        self.assertEqual(r.apppath, b'')
        self.assertEqual(r.dispatchparts, [])
        self.assertEqual(r.dispatchpath, b'')

        r = parse(DEFAULT_ENV, extra={
            r'PATH_INFO': r'/pathinfo',
        })

        self.assertEqual(r.url, b'http://testserver/pathinfo')
        self.assertEqual(r.baseurl, b'http://testserver')
        self.assertEqual(r.advertisedurl, b'http://testserver/pathinfo')
        self.assertEqual(r.advertisedbaseurl, b'http://testserver')
        self.assertEqual(r.apppath, b'')
        self.assertEqual(r.dispatchparts, [b'pathinfo'])
        self.assertEqual(r.dispatchpath, b'pathinfo')

        r = parse(DEFAULT_ENV, extra={
            r'PATH_INFO': r'/one/two/',
        })

        self.assertEqual(r.url, b'http://testserver/one/two/')
        self.assertEqual(r.baseurl, b'http://testserver')
        self.assertEqual(r.advertisedurl, b'http://testserver/one/two/')
        self.assertEqual(r.advertisedbaseurl, b'http://testserver')
        self.assertEqual(r.apppath, b'')
        self.assertEqual(r.dispatchparts, [b'one', b'two'])
        self.assertEqual(r.dispatchpath, b'one/two')

    def testscriptandpathinfo(self):
        r = parse(DEFAULT_ENV, extra={
            r'SCRIPT_NAME': r'/script',
            r'PATH_INFO': r'/pathinfo',
        })

        self.assertEqual(r.url, b'http://testserver/script/pathinfo')
        self.assertEqual(r.baseurl, b'http://testserver')
        self.assertEqual(r.advertisedurl, b'http://testserver/script/pathinfo')
        self.assertEqual(r.advertisedbaseurl, b'http://testserver')
        self.assertEqual(r.apppath, b'/script')
        self.assertEqual(r.dispatchparts, [b'pathinfo'])
        self.assertEqual(r.dispatchpath, b'pathinfo')

        r = parse(DEFAULT_ENV, extra={
            r'SCRIPT_NAME': r'/script1/script2',
            r'PATH_INFO': r'/path1/path2',
        })

        self.assertEqual(r.url,
                         b'http://testserver/script1/script2/path1/path2')
        self.assertEqual(r.baseurl, b'http://testserver')
        self.assertEqual(r.advertisedurl,
                         b'http://testserver/script1/script2/path1/path2')
        self.assertEqual(r.advertisedbaseurl, b'http://testserver')
        self.assertEqual(r.apppath, b'/script1/script2')
        self.assertEqual(r.dispatchparts, [b'path1', b'path2'])
        self.assertEqual(r.dispatchpath, b'path1/path2')

        r = parse(DEFAULT_ENV, extra={
            r'HTTP_HOST': r'hostserver',
            r'SCRIPT_NAME': r'/script',
            r'PATH_INFO': r'/pathinfo',
        })

        self.assertEqual(r.url, b'http://hostserver/script/pathinfo')
        self.assertEqual(r.baseurl, b'http://hostserver')
        self.assertEqual(r.advertisedurl, b'http://testserver/script/pathinfo')
        self.assertEqual(r.advertisedbaseurl, b'http://testserver')
        self.assertEqual(r.apppath, b'/script')
        self.assertEqual(r.dispatchparts, [b'pathinfo'])
        self.assertEqual(r.dispatchpath, b'pathinfo')

    def testreponame(self):
        """repository path components get stripped from URL."""

        with self.assertRaisesRegexp(error.ProgrammingError,
                                     b'reponame requires PATH_INFO'):
            parse(DEFAULT_ENV, reponame=b'repo')

        with self.assertRaisesRegexp(error.ProgrammingError,
                                     b'PATH_INFO does not begin with repo '
                                     b'name'):
            parse(DEFAULT_ENV, reponame=b'repo', extra={
                r'PATH_INFO': r'/pathinfo',
            })

        with self.assertRaisesRegexp(error.ProgrammingError,
                                     b'reponame prefix of PATH_INFO'):
            parse(DEFAULT_ENV, reponame=b'repo', extra={
                r'PATH_INFO': r'/repoextra/path',
            })

        r = parse(DEFAULT_ENV, reponame=b'repo', extra={
            r'PATH_INFO': r'/repo/path1/path2',
        })

        self.assertEqual(r.url, b'http://testserver/repo/path1/path2')
        self.assertEqual(r.baseurl, b'http://testserver')
        self.assertEqual(r.advertisedurl, b'http://testserver/repo/path1/path2')
        self.assertEqual(r.advertisedbaseurl, b'http://testserver')
        self.assertEqual(r.apppath, b'/repo')
        self.assertEqual(r.dispatchparts, [b'path1', b'path2'])
        self.assertEqual(r.dispatchpath, b'path1/path2')
        self.assertEqual(r.reponame, b'repo')

        r = parse(DEFAULT_ENV, reponame=b'prefix/repo', extra={
            r'PATH_INFO': r'/prefix/repo/path1/path2',
        })

        self.assertEqual(r.url, b'http://testserver/prefix/repo/path1/path2')
        self.assertEqual(r.baseurl, b'http://testserver')
        self.assertEqual(r.advertisedurl,
                         b'http://testserver/prefix/repo/path1/path2')
        self.assertEqual(r.advertisedbaseurl, b'http://testserver')
        self.assertEqual(r.apppath, b'/prefix/repo')
        self.assertEqual(r.dispatchparts, [b'path1', b'path2'])
        self.assertEqual(r.dispatchpath, b'path1/path2')
        self.assertEqual(r.reponame, b'prefix/repo')

    def testaltbaseurl(self):
        # Simple hostname remap.
        r = parse(DEFAULT_ENV, altbaseurl='http://altserver')

        self.assertEqual(r.url, b'http://testserver')
        self.assertEqual(r.baseurl, b'http://testserver')
        self.assertEqual(r.advertisedurl, b'http://altserver')
        self.assertEqual(r.advertisedbaseurl, b'http://altserver')
        self.assertEqual(r.urlscheme, b'http')
        self.assertEqual(r.apppath, b'')
        self.assertEqual(r.dispatchparts, [])
        self.assertIsNone(r.dispatchpath)
        self.assertIsNone(r.reponame)

        # With a custom port.
        r = parse(DEFAULT_ENV, altbaseurl='http://altserver:8000')
        self.assertEqual(r.url, b'http://testserver')
        self.assertEqual(r.baseurl, b'http://testserver')
        self.assertEqual(r.advertisedurl, b'http://altserver:8000')
        self.assertEqual(r.advertisedbaseurl, b'http://altserver:8000')
        self.assertEqual(r.urlscheme, b'http')
        self.assertEqual(r.apppath, b'')
        self.assertEqual(r.dispatchparts, [])
        self.assertIsNone(r.dispatchpath)
        self.assertIsNone(r.reponame)

        # With a changed protocol.
        r = parse(DEFAULT_ENV, altbaseurl='https://altserver')
        self.assertEqual(r.url, b'http://testserver')
        self.assertEqual(r.baseurl, b'http://testserver')
        self.assertEqual(r.advertisedurl, b'https://altserver')
        self.assertEqual(r.advertisedbaseurl, b'https://altserver')
        # URL scheme is defined as the actual scheme, not advertised.
        self.assertEqual(r.urlscheme, b'http')
        self.assertEqual(r.apppath, b'')
        self.assertEqual(r.dispatchparts, [])
        self.assertIsNone(r.dispatchpath)
        self.assertIsNone(r.reponame)

        # Need to specify explicit port number for proper https:// alt URLs.
        r = parse(DEFAULT_ENV, altbaseurl='https://altserver:443')
        self.assertEqual(r.url, b'http://testserver')
        self.assertEqual(r.baseurl, b'http://testserver')
        self.assertEqual(r.advertisedurl, b'https://altserver')
        self.assertEqual(r.advertisedbaseurl, b'https://altserver')
        self.assertEqual(r.urlscheme, b'http')
        self.assertEqual(r.apppath, b'')
        self.assertEqual(r.dispatchparts, [])
        self.assertIsNone(r.dispatchpath)
        self.assertIsNone(r.reponame)

        # With only PATH_INFO defined.
        r = parse(DEFAULT_ENV, altbaseurl='http://altserver', extra={
            r'PATH_INFO': r'/path1/path2',
        })
        self.assertEqual(r.url, b'http://testserver/path1/path2')
        self.assertEqual(r.baseurl, b'http://testserver')
        self.assertEqual(r.advertisedurl, b'http://altserver/path1/path2')
        self.assertEqual(r.advertisedbaseurl, b'http://altserver')
        self.assertEqual(r.urlscheme, b'http')
        self.assertEqual(r.apppath, b'')
        self.assertEqual(r.dispatchparts, [b'path1', b'path2'])
        self.assertEqual(r.dispatchpath, b'path1/path2')
        self.assertIsNone(r.reponame)

        # Path on alt URL.
        r = parse(DEFAULT_ENV, altbaseurl='http://altserver/altpath')
        self.assertEqual(r.url, b'http://testserver')
        self.assertEqual(r.baseurl, b'http://testserver')
        self.assertEqual(r.advertisedurl, b'http://altserver/altpath')
        self.assertEqual(r.advertisedbaseurl, b'http://altserver')
        self.assertEqual(r.urlscheme, b'http')
        self.assertEqual(r.apppath, b'/altpath')
        self.assertEqual(r.dispatchparts, [])
        self.assertIsNone(r.dispatchpath)
        self.assertIsNone(r.reponame)

        # With a trailing slash.
        r = parse(DEFAULT_ENV, altbaseurl='http://altserver/altpath/')
        self.assertEqual(r.url, b'http://testserver')
        self.assertEqual(r.baseurl, b'http://testserver')
        self.assertEqual(r.advertisedurl, b'http://altserver/altpath/')
        self.assertEqual(r.advertisedbaseurl, b'http://altserver')
        self.assertEqual(r.urlscheme, b'http')
        self.assertEqual(r.apppath, b'/altpath/')
        self.assertEqual(r.dispatchparts, [])
        self.assertIsNone(r.dispatchpath)
        self.assertIsNone(r.reponame)

        # PATH_INFO + path on alt URL.
        r = parse(DEFAULT_ENV, altbaseurl='http://altserver/altpath', extra={
            r'PATH_INFO': r'/path1/path2',
        })
        self.assertEqual(r.url, b'http://testserver/path1/path2')
        self.assertEqual(r.baseurl, b'http://testserver')
        self.assertEqual(r.advertisedurl,
                         b'http://altserver/altpath/path1/path2')
        self.assertEqual(r.advertisedbaseurl, b'http://altserver')
        self.assertEqual(r.urlscheme, b'http')
        self.assertEqual(r.apppath, b'/altpath')
        self.assertEqual(r.dispatchparts, [b'path1', b'path2'])
        self.assertEqual(r.dispatchpath, b'path1/path2')
        self.assertIsNone(r.reponame)

        # PATH_INFO + path on alt URL with trailing slash.
        r = parse(DEFAULT_ENV, altbaseurl='http://altserver/altpath/', extra={
            r'PATH_INFO': r'/path1/path2',
        })
        self.assertEqual(r.url, b'http://testserver/path1/path2')
        self.assertEqual(r.baseurl, b'http://testserver')
        self.assertEqual(r.advertisedurl,
                         b'http://altserver/altpath//path1/path2')
        self.assertEqual(r.advertisedbaseurl, b'http://altserver')
        self.assertEqual(r.urlscheme, b'http')
        self.assertEqual(r.apppath, b'/altpath/')
        self.assertEqual(r.dispatchparts, [b'path1', b'path2'])
        self.assertEqual(r.dispatchpath, b'path1/path2')
        self.assertIsNone(r.reponame)

        # Local SCRIPT_NAME is ignored.
        r = parse(DEFAULT_ENV, altbaseurl='http://altserver', extra={
            r'SCRIPT_NAME': r'/script',
            r'PATH_INFO': r'/path1/path2',
        })
        self.assertEqual(r.url, b'http://testserver/script/path1/path2')
        self.assertEqual(r.baseurl, b'http://testserver')
        self.assertEqual(r.advertisedurl, b'http://altserver/path1/path2')
        self.assertEqual(r.advertisedbaseurl, b'http://altserver')
        self.assertEqual(r.urlscheme, b'http')
        self.assertEqual(r.apppath, b'')
        self.assertEqual(r.dispatchparts, [b'path1', b'path2'])
        self.assertEqual(r.dispatchpath, b'path1/path2')
        self.assertIsNone(r.reponame)

        # Use remote's path for script name, app path
        r = parse(DEFAULT_ENV, altbaseurl='http://altserver/altroot', extra={
            r'SCRIPT_NAME': r'/script',
            r'PATH_INFO': r'/path1/path2',
        })
        self.assertEqual(r.url, b'http://testserver/script/path1/path2')
        self.assertEqual(r.baseurl, b'http://testserver')
        self.assertEqual(r.advertisedurl,
                         b'http://altserver/altroot/path1/path2')
        self.assertEqual(r.advertisedbaseurl, b'http://altserver')
        self.assertEqual(r.urlscheme, b'http')
        self.assertEqual(r.apppath, b'/altroot')
        self.assertEqual(r.dispatchparts, [b'path1', b'path2'])
        self.assertEqual(r.dispatchpath, b'path1/path2')
        self.assertIsNone(r.reponame)

        # reponame is factored in properly.
        r = parse(DEFAULT_ENV, reponame=b'repo',
                  altbaseurl='http://altserver/altroot',
                  extra={
                r'SCRIPT_NAME': r'/script',
                r'PATH_INFO': r'/repo/path1/path2',
            })

        self.assertEqual(r.url, b'http://testserver/script/repo/path1/path2')
        self.assertEqual(r.baseurl, b'http://testserver')
        self.assertEqual(r.advertisedurl,
                         b'http://altserver/altroot/repo/path1/path2')
        self.assertEqual(r.advertisedbaseurl, b'http://altserver')
        self.assertEqual(r.apppath, b'/altroot/repo')
        self.assertEqual(r.dispatchparts, [b'path1', b'path2'])
        self.assertEqual(r.dispatchpath, b'path1/path2')
        self.assertEqual(r.reponame, b'repo')

if __name__ == '__main__':
    import silenttestrunner
    silenttestrunner.main(__name__)