Mercurial > public > mercurial-scm > hg-stable
diff mercurial/hgweb/request.py @ 36906:219b23359f4c
hgweb: support constructing URLs from an alternate base URL
The web.baseurl config option allows server operators to define a
custom URL for hosted content.
The way it works today is that hgwebdir parses this config
option into URL components then updates the appropriate
WSGI environment variables so the request "lies" about its
details. For example, SERVER_NAME is updated to reflect the
alternate base URL's hostname.
The WSGI environment should not be modified because WSGI
applications may want to know the original request details (for
debugging, etc).
This commit teaches our request parser about the existence of
an alternate base URL. If defined, the advertised URL and other
self-reflected paths will take the alternate base URL into account.
The hgweb WSGI application didn't use web.baseurl. But hgwebdir
did. We update hgwebdir to alter the environment parsing
accordingly. The old code around environment manipulation
has been removed.
With this change, parserequestfromenv() has grown to a bit
unwieldy. Now that practically everyone is using it, it is
obvious that there is some unused features that can be trimmed.
So look for this in follow-up commits.
Differential Revision: https://phab.mercurial-scm.org/D2822
author | Gregory Szorc <gregory.szorc@gmail.com> |
---|---|
date | Sun, 11 Mar 2018 15:33:56 -0700 |
parents | e67a2e05fa8a |
children | cd6ae9ab7bd8 |
line wrap: on
line diff
--- a/mercurial/hgweb/request.py Sun Mar 11 13:55:13 2018 -0700 +++ b/mercurial/hgweb/request.py Sun Mar 11 15:33:56 2018 -0700 @@ -157,7 +157,7 @@ # Request body input stream. bodyfh = attr.ib() -def parserequestfromenv(env, bodyfh, reponame=None): +def parserequestfromenv(env, bodyfh, reponame=None, altbaseurl=None): """Parse URL components from environment variables. WSGI defines request attributes via environment variables. This function @@ -167,8 +167,18 @@ string are effectively shifted from ``PATH_INFO`` to ``SCRIPT_NAME``. This simulates the world view of a WSGI application that processes requests from the base URL of a repo. + + If ``altbaseurl`` (typically comes from ``web.baseurl`` config option) + is defined, it is used - instead of the WSGI environment variables - for + constructing URL components up to and including the WSGI application path. + For example, if the current WSGI application is at ``/repo`` and a request + is made to ``/rev/@`` with this argument set to + ``http://myserver:9000/prefix``, the URL and path components will resolve as + if the request were to ``http://myserver:9000/prefix/rev/@``. In other + words, ``wsgi.url_scheme``, ``SERVER_NAME``, ``SERVER_PORT``, and + ``SCRIPT_NAME`` are all effectively replaced by components from this URL. """ - # PEP-0333 defines the WSGI spec and is a useful reference for this code. + # PEP 3333 defines the WSGI spec and is a useful reference for this code. # We first validate that the incoming object conforms with the WSGI spec. # We only want to be dealing with spec-conforming WSGI implementations. @@ -184,20 +194,27 @@ env = {k: v.encode('latin-1') if isinstance(v, str) else v for k, v in env.iteritems()} + if altbaseurl: + altbaseurl = util.url(altbaseurl) + # https://www.python.org/dev/peps/pep-0333/#environ-variables defines # the environment variables. # https://www.python.org/dev/peps/pep-0333/#url-reconstruction defines # how URLs are reconstructed. fullurl = env['wsgi.url_scheme'] + '://' - advertisedfullurl = fullurl + + if altbaseurl and altbaseurl.scheme: + advertisedfullurl = altbaseurl.scheme + '://' + else: + advertisedfullurl = fullurl - def addport(s): - if env['wsgi.url_scheme'] == 'https': - if env['SERVER_PORT'] != '443': - s += ':' + env['SERVER_PORT'] + def addport(s, port): + if s.startswith('https://'): + if port != '443': + s += ':' + port else: - if env['SERVER_PORT'] != '80': - s += ':' + env['SERVER_PORT'] + if port != '80': + s += ':' + port return s @@ -205,17 +222,39 @@ fullurl += env['HTTP_HOST'] else: fullurl += env['SERVER_NAME'] - fullurl = addport(fullurl) + fullurl = addport(fullurl, env['SERVER_PORT']) + + if altbaseurl and altbaseurl.host: + advertisedfullurl += altbaseurl.host - advertisedfullurl += env['SERVER_NAME'] - advertisedfullurl = addport(advertisedfullurl) + if altbaseurl.port: + port = altbaseurl.port + elif altbaseurl.scheme == 'http' and not altbaseurl.port: + port = '80' + elif altbaseurl.scheme == 'https' and not altbaseurl.port: + port = '443' + else: + port = env['SERVER_PORT'] + + advertisedfullurl = addport(advertisedfullurl, port) + else: + advertisedfullurl += env['SERVER_NAME'] + advertisedfullurl = addport(advertisedfullurl, env['SERVER_PORT']) baseurl = fullurl advertisedbaseurl = advertisedfullurl fullurl += util.urlreq.quote(env.get('SCRIPT_NAME', '')) - advertisedfullurl += util.urlreq.quote(env.get('SCRIPT_NAME', '')) fullurl += util.urlreq.quote(env.get('PATH_INFO', '')) + + if altbaseurl: + path = altbaseurl.path or '' + if path and not path.startswith('/'): + path = '/' + path + advertisedfullurl += util.urlreq.quote(path) + else: + advertisedfullurl += util.urlreq.quote(env.get('SCRIPT_NAME', '')) + advertisedfullurl += util.urlreq.quote(env.get('PATH_INFO', '')) if env.get('QUERY_STRING'): @@ -226,7 +265,12 @@ # that represents the repository being dispatched to. When computing # the dispatch info, we ignore these leading path components. - apppath = env.get('SCRIPT_NAME', '') + if altbaseurl: + apppath = altbaseurl.path or '' + if apppath and not apppath.startswith('/'): + apppath = '/' + apppath + else: + apppath = env.get('SCRIPT_NAME', '') if reponame: repoprefix = '/' + reponame.strip('/') @@ -545,7 +589,7 @@ instantiate instances of this class, which provides higher-level APIs for obtaining request parameters, writing HTTP output, etc. """ - def __init__(self, wsgienv, start_response): + def __init__(self, wsgienv, start_response, altbaseurl=None): version = wsgienv[r'wsgi.version'] if (version < (1, 0)) or (version >= (2, 0)): raise RuntimeError("Unknown and unsupported WSGI version %d.%d" @@ -563,7 +607,7 @@ self.multiprocess = wsgienv[r'wsgi.multiprocess'] self.run_once = wsgienv[r'wsgi.run_once'] self.env = wsgienv - self.req = parserequestfromenv(wsgienv, inp) + self.req = parserequestfromenv(wsgienv, inp, altbaseurl=altbaseurl) self.res = wsgiresponse(self.req, start_response) self._start_response = start_response self.server_write = None