##// END OF EJS Templates
hgweb: support constructing URLs from an alternate base URL...
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

File last commit:

r36916:219b2335 default
r36916:219b2335 default
Show More
request.py
713 lines | 26.9 KiB | text/x-python | PythonLexer
Eric Hopper
Fixing up comment headers for split up code.
r2391 # hgweb/request.py - An http request from either CGI or the standalone server.
Eric Hopper
Splitting up hgweb so it's easier to change.
r2355 #
# Copyright 21 May 2005 - (c) 2005 Jake Edge <jake@edge2.net>
Vadim Gelfer
update copyrights.
r2859 # Copyright 2005, 2006 Matt Mackall <mpm@selenic.com>
Eric Hopper
Splitting up hgweb so it's easier to change.
r2355 #
Martin Geisler
updated license to be explicit about GPL version 2
r8225 # This software may be used and distributed according to the terms of the
Matt Mackall
Update license to GPLv2+
r10263 # GNU General Public License version 2 or any later version.
Eric Hopper
Splitting up hgweb so it's easier to change.
r2355
Yuya Nishihara
hgweb: use absolute_import
r27046 from __future__ import absolute_import
import errno
import socket
Gregory Szorc
hgweb: parse and store HTTP request headers...
r36832 import wsgiref.headers as wsgiheaders
Gregory Szorc
hgweb: parse WSGI request into a data structure...
r36824 #import wsgiref.validate
Yuya Nishihara
hgweb: use absolute_import
r27046
from .common import (
ErrorResponse,
statusmessage,
)
Gregory Szorc
hgweb: parse WSGI request into a data structure...
r36824 from ..thirdparty import (
attr,
)
Yuya Nishihara
hgweb: use absolute_import
r27046 from .. import (
Gregory Szorc
hgweb: create dedicated type for WSGI responses...
r36877 error,
Augie Fackler
request: coerce content-type to native str...
r34515 pycompat,
Yuya Nishihara
hgweb: use absolute_import
r27046 util,
)
Eric Hopper
Splitting up hgweb so it's easier to change.
r2355
Gregory Szorc
hgweb: use a multidict for holding query string parameters...
r36878 class multidict(object):
"""A dict like object that can store multiple values for a key.
Used to store parsed request parameters.
This is inspired by WebOb's class of the same name.
"""
def __init__(self):
# Stores (key, value) 2-tuples. This isn't the most efficient. But we
# don't rely on parameters that much, so it shouldn't be a perf issue.
# we can always add dict for fast lookups.
self._items = []
def __getitem__(self, key):
"""Returns the last set value for a key."""
for k, v in reversed(self._items):
if k == key:
return v
raise KeyError(key)
def __setitem__(self, key, value):
"""Replace a values for a key with a new value."""
try:
del self[key]
except KeyError:
pass
self._items.append((key, value))
def __delitem__(self, key):
"""Delete all values for a key."""
oldlen = len(self._items)
self._items[:] = [(k, v) for k, v in self._items if k != key]
if oldlen == len(self._items):
raise KeyError(key)
def __contains__(self, key):
return any(k == key for k, v in self._items)
def __len__(self):
return len(self._items)
def get(self, key, default=None):
try:
return self.__getitem__(key)
except KeyError:
return default
def add(self, key, value):
"""Add a new value for a key. Does not replace existing values."""
self._items.append((key, value))
def getall(self, key):
"""Obtains all values for a key."""
return [v for k, v in self._items if k == key]
def getone(self, key):
"""Obtain a single value for a key.
Raises KeyError if key not defined or it has multiple values set.
"""
vals = self.getall(key)
if not vals:
raise KeyError(key)
if len(vals) > 1:
raise KeyError('multiple values for %r' % key)
return vals[0]
def asdictoflists(self):
d = {}
for k, v in self._items:
if k in d:
d[k].append(v)
else:
d[k] = [v]
return d
Gregory Szorc
hgweb: parse WSGI request into a data structure...
r36824 @attr.s(frozen=True)
class parsedrequest(object):
Gregory Szorc
hgweb: expose input stream on parsed WSGI request object...
r36873 """Represents a parsed WSGI request.
Contains both parsed parameters as well as a handle on the input stream.
"""
Gregory Szorc
hgweb: parse WSGI request into a data structure...
r36824
Gregory Szorc
hgweb: store and use request method on parsed request...
r36864 # Request method.
method = attr.ib()
Gregory Szorc
hgweb: parse WSGI request into a data structure...
r36824 # Full URL for this request.
url = attr.ib()
# URL without any path components. Just <proto>://<host><port>.
baseurl = attr.ib()
# Advertised URL. Like ``url`` and ``baseurl`` but uses SERVER_NAME instead
# of HTTP: Host header for hostname. This is likely what clients used.
advertisedurl = attr.ib()
advertisedbaseurl = attr.ib()
Gregory Szorc
hgweb: expose URL scheme and REMOTE_* attributes...
r36883 # URL scheme (part before ``://``). e.g. ``http`` or ``https``.
urlscheme = attr.ib()
# Value of REMOTE_USER, if set, or None.
remoteuser = attr.ib()
# Value of REMOTE_HOST, if set, or None.
remotehost = attr.ib()
Gregory Szorc
hgweb: clarify that apppath begins with a forward slash...
r36915 # Relative WSGI application path. If defined, will begin with a
# ``/``.
Gregory Szorc
hgweb: parse WSGI request into a data structure...
r36824 apppath = attr.ib()
# List of path parts to be used for dispatch.
dispatchparts = attr.ib()
Gregory Szorc
hgweb: change how dispatch path is reported...
r36914 # URL path component (no query string) used for dispatch. Can be
# ``None`` to signal no path component given to the request, an
# empty string to signal a request to the application's root URL,
# or a string not beginning with ``/`` containing the requested
# path under the application.
Gregory Szorc
hgweb: parse WSGI request into a data structure...
r36824 dispatchpath = attr.ib()
Gregory Szorc
hgweb: expose repo name on parsedrequest...
r36884 # The name of the repository being accessed.
reponame = attr.ib()
Gregory Szorc
hgweb: parse WSGI request into a data structure...
r36824 # Raw query string (part after "?" in URL).
querystring = attr.ib()
Gregory Szorc
hgweb: use a multidict for holding query string parameters...
r36878 # multidict of query string parameters.
qsparams = attr.ib()
Gregory Szorc
hgweb: parse and store HTTP request headers...
r36832 # wsgiref.headers.Headers instance. Operates like a dict with case
# insensitive keys.
headers = attr.ib()
Gregory Szorc
hgweb: expose input stream on parsed WSGI request object...
r36873 # Request body input stream.
bodyfh = attr.ib()
Gregory Szorc
hgweb: parse WSGI request into a data structure...
r36824
Gregory Szorc
hgweb: support constructing URLs from an alternate base URL...
r36916 def parserequestfromenv(env, bodyfh, reponame=None, altbaseurl=None):
Gregory Szorc
hgweb: parse WSGI request into a data structure...
r36824 """Parse URL components from environment variables.
WSGI defines request attributes via environment variables. This function
parses the environment variables into a data structure.
Gregory Szorc
hgweb: refactor repository name URL parsing...
r36913
If ``reponame`` is defined, the leading path components matching that
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.
Gregory Szorc
hgweb: support constructing URLs from an alternate base URL...
r36916
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.
Gregory Szorc
hgweb: parse WSGI request into a data structure...
r36824 """
Gregory Szorc
hgweb: support constructing URLs from an alternate base URL...
r36916 # PEP 3333 defines the WSGI spec and is a useful reference for this code.
Gregory Szorc
hgweb: parse WSGI request into a data structure...
r36824
# We first validate that the incoming object conforms with the WSGI spec.
# We only want to be dealing with spec-conforming WSGI implementations.
# TODO enable this once we fix internal violations.
#wsgiref.validate.check_environ(env)
# PEP-0333 states that environment keys and values are native strings
# (bytes on Python 2 and str on Python 3). The code points for the Unicode
# strings on Python 3 must be between \00000-\000FF. We deal with bytes
# in Mercurial, so mass convert string keys and values to bytes.
if pycompat.ispy3:
env = {k.encode('latin-1'): v for k, v in env.iteritems()}
env = {k: v.encode('latin-1') if isinstance(v, str) else v
for k, v in env.iteritems()}
Gregory Szorc
hgweb: support constructing URLs from an alternate base URL...
r36916 if altbaseurl:
altbaseurl = util.url(altbaseurl)
Gregory Szorc
hgweb: parse WSGI request into a data structure...
r36824 # 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'] + '://'
Gregory Szorc
hgweb: support constructing URLs from an alternate base URL...
r36916
if altbaseurl and altbaseurl.scheme:
advertisedfullurl = altbaseurl.scheme + '://'
else:
advertisedfullurl = fullurl
Gregory Szorc
hgweb: parse WSGI request into a data structure...
r36824
Gregory Szorc
hgweb: support constructing URLs from an alternate base URL...
r36916 def addport(s, port):
if s.startswith('https://'):
if port != '443':
s += ':' + port
Gregory Szorc
hgweb: parse WSGI request into a data structure...
r36824 else:
Gregory Szorc
hgweb: support constructing URLs from an alternate base URL...
r36916 if port != '80':
s += ':' + port
Gregory Szorc
hgweb: parse WSGI request into a data structure...
r36824
return s
if env.get('HTTP_HOST'):
fullurl += env['HTTP_HOST']
else:
fullurl += env['SERVER_NAME']
Gregory Szorc
hgweb: support constructing URLs from an alternate base URL...
r36916 fullurl = addport(fullurl, env['SERVER_PORT'])
if altbaseurl and altbaseurl.host:
advertisedfullurl += altbaseurl.host
Gregory Szorc
hgweb: parse WSGI request into a data structure...
r36824
Gregory Szorc
hgweb: support constructing URLs from an alternate base URL...
r36916 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'])
Gregory Szorc
hgweb: parse WSGI request into a data structure...
r36824
baseurl = fullurl
advertisedbaseurl = advertisedfullurl
fullurl += util.urlreq.quote(env.get('SCRIPT_NAME', ''))
fullurl += util.urlreq.quote(env.get('PATH_INFO', ''))
Gregory Szorc
hgweb: support constructing URLs from an alternate base URL...
r36916
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', ''))
Gregory Szorc
hgweb: parse WSGI request into a data structure...
r36824 advertisedfullurl += util.urlreq.quote(env.get('PATH_INFO', ''))
if env.get('QUERY_STRING'):
fullurl += '?' + env['QUERY_STRING']
advertisedfullurl += '?' + env['QUERY_STRING']
Gregory Szorc
hgweb: refactor repository name URL parsing...
r36913 # If ``reponame`` is defined, that must be a prefix on PATH_INFO
# that represents the repository being dispatched to. When computing
# the dispatch info, we ignore these leading path components.
Gregory Szorc
hgweb: parse WSGI request into a data structure...
r36824
Gregory Szorc
hgweb: support constructing URLs from an alternate base URL...
r36916 if altbaseurl:
apppath = altbaseurl.path or ''
if apppath and not apppath.startswith('/'):
apppath = '/' + apppath
else:
apppath = env.get('SCRIPT_NAME', '')
Gregory Szorc
hgweb: parse WSGI request into a data structure...
r36824
Gregory Szorc
hgweb: refactor repository name URL parsing...
r36913 if reponame:
repoprefix = '/' + reponame.strip('/')
Gregory Szorc
hgweb: use the parsed application path directly...
r36826
Gregory Szorc
hgweb: refactor repository name URL parsing...
r36913 if not env.get('PATH_INFO'):
raise error.ProgrammingError('reponame requires PATH_INFO')
if not env['PATH_INFO'].startswith(repoprefix):
raise error.ProgrammingError('PATH_INFO does not begin with repo '
'name: %s (%s)' % (env['PATH_INFO'],
reponame))
Gregory Szorc
hgweb: parse WSGI request into a data structure...
r36824
Gregory Szorc
hgweb: refactor repository name URL parsing...
r36913 dispatchpath = env['PATH_INFO'][len(repoprefix):]
Gregory Szorc
hgweb: parse WSGI request into a data structure...
r36824
Gregory Szorc
hgweb: refactor repository name URL parsing...
r36913 if dispatchpath and not dispatchpath.startswith('/'):
raise error.ProgrammingError('reponame prefix of PATH_INFO does '
'not end at path delimiter: %s (%s)' %
(env['PATH_INFO'], reponame))
apppath = apppath.rstrip('/') + repoprefix
dispatchparts = dispatchpath.strip('/').split('/')
Gregory Szorc
hgweb: change how dispatch path is reported...
r36914 dispatchpath = '/'.join(dispatchparts)
elif 'PATH_INFO' in env:
if env['PATH_INFO'].strip('/'):
dispatchparts = env['PATH_INFO'].strip('/').split('/')
dispatchpath = '/'.join(dispatchparts)
else:
dispatchparts = []
dispatchpath = ''
Gregory Szorc
hgweb: parse WSGI request into a data structure...
r36824 else:
dispatchparts = []
Gregory Szorc
hgweb: change how dispatch path is reported...
r36914 dispatchpath = None
Gregory Szorc
hgweb: parse WSGI request into a data structure...
r36824
querystring = env.get('QUERY_STRING', '')
Gregory Szorc
hgweb: teach WSGI parser about query strings...
r36827 # We store as a list so we have ordering information. We also store as
# a dict to facilitate fast lookup.
Gregory Szorc
hgweb: use a multidict for holding query string parameters...
r36878 qsparams = multidict()
for k, v in util.urlreq.parseqsl(querystring, keep_blank_values=True):
qsparams.add(k, v)
Gregory Szorc
hgweb: teach WSGI parser about query strings...
r36827
Gregory Szorc
hgweb: parse and store HTTP request headers...
r36832 # HTTP_* keys contain HTTP request headers. The Headers structure should
# perform case normalization for us. We just rewrite underscore to dash
# so keys match what likely went over the wire.
headers = []
for k, v in env.iteritems():
if k.startswith('HTTP_'):
headers.append((k[len('HTTP_'):].replace('_', '-'), v))
headers = wsgiheaders.Headers(headers)
Gregory Szorc
hgweb: handle CONTENT_LENGTH...
r36863 # This is kind of a lie because the HTTP header wasn't explicitly
# sent. But for all intents and purposes it should be OK to lie about
# this, since a consumer will either either value to determine how many
# bytes are available to read.
if 'CONTENT_LENGTH' in env and 'HTTP_CONTENT_LENGTH' not in env:
headers['Content-Length'] = env['CONTENT_LENGTH']
Gregory Szorc
hgweb: expose input stream on parsed WSGI request object...
r36873 # TODO do this once we remove wsgirequest.inp, otherwise we could have
# multiple readers from the underlying input stream.
#bodyfh = env['wsgi.input']
#if 'Content-Length' in headers:
# bodyfh = util.cappedreader(bodyfh, int(headers['Content-Length']))
Gregory Szorc
hgweb: store and use request method on parsed request...
r36864 return parsedrequest(method=env['REQUEST_METHOD'],
url=fullurl, baseurl=baseurl,
Gregory Szorc
hgweb: parse WSGI request into a data structure...
r36824 advertisedurl=advertisedfullurl,
advertisedbaseurl=advertisedbaseurl,
Gregory Szorc
hgweb: expose URL scheme and REMOTE_* attributes...
r36883 urlscheme=env['wsgi.url_scheme'],
remoteuser=env.get('REMOTE_USER'),
remotehost=env.get('REMOTE_HOST'),
Gregory Szorc
hgweb: parse WSGI request into a data structure...
r36824 apppath=apppath,
dispatchparts=dispatchparts, dispatchpath=dispatchpath,
Gregory Szorc
hgweb: refactor repository name URL parsing...
r36913 reponame=reponame,
Gregory Szorc
hgweb: teach WSGI parser about query strings...
r36827 querystring=querystring,
Gregory Szorc
hgweb: use a multidict for holding query string parameters...
r36878 qsparams=qsparams,
Gregory Szorc
hgweb: expose input stream on parsed WSGI request object...
r36873 headers=headers,
bodyfh=bodyfh)
Gregory Szorc
hgweb: parse WSGI request into a data structure...
r36824
Gregory Szorc
hgweb: refactor fake file object proxy for archiving...
r36891 class offsettrackingwriter(object):
"""A file object like object that is append only and tracks write count.
Instances are bound to a callable. This callable is called with data
whenever a ``write()`` is attempted.
Instances track the amount of written data so they can answer ``tell()``
requests.
The intent of this class is to wrap the ``write()`` function returned by
a WSGI ``start_response()`` function. Since ``write()`` is a callable and
not a file object, it doesn't implement other file object methods.
"""
def __init__(self, writefn):
self._write = writefn
self._offset = 0
def write(self, s):
res = self._write(s)
# Some Python objects don't report the number of bytes written.
if res is None:
self._offset += len(s)
else:
self._offset += res
def flush(self):
pass
def tell(self):
return self._offset
Gregory Szorc
hgweb: create dedicated type for WSGI responses...
r36877 class wsgiresponse(object):
"""Represents a response to a WSGI request.
A response consists of a status line, headers, and a body.
Consumers must populate the ``status`` and ``headers`` fields and
make a call to a ``setbody*()`` method before the response can be
issued.
When it is time to start sending the response over the wire,
``sendresponse()`` is called. It handles emitting the header portion
of the response message. It then yields chunks of body data to be
written to the peer. Typically, the WSGI application itself calls
and returns the value from ``sendresponse()``.
"""
def __init__(self, req, startresponse):
"""Create an empty response tied to a specific request.
``req`` is a ``parsedrequest``. ``startresponse`` is the
``start_response`` function passed to the WSGI application.
"""
self._req = req
self._startresponse = startresponse
self.status = None
self.headers = wsgiheaders.Headers([])
self._bodybytes = None
self._bodygen = None
Gregory Szorc
hgweb: port archive command to modern response API...
r36892 self._bodywillwrite = False
Gregory Szorc
hgweb: create dedicated type for WSGI responses...
r36877 self._started = False
Gregory Szorc
hgweb: port archive command to modern response API...
r36892 self._bodywritefn = None
def _verifybody(self):
if (self._bodybytes is not None or self._bodygen is not None
or self._bodywillwrite):
raise error.ProgrammingError('cannot define body multiple times')
Gregory Szorc
hgweb: create dedicated type for WSGI responses...
r36877
def setbodybytes(self, b):
Gregory Szorc
hgweb: refactor 304 handling code...
r36894 """Define the response body as static bytes.
The empty string signals that there is no response body.
"""
Gregory Szorc
hgweb: port archive command to modern response API...
r36892 self._verifybody()
Gregory Szorc
hgweb: create dedicated type for WSGI responses...
r36877 self._bodybytes = b
self.headers['Content-Length'] = '%d' % len(b)
def setbodygen(self, gen):
"""Define the response body as a generator of bytes."""
Gregory Szorc
hgweb: port archive command to modern response API...
r36892 self._verifybody()
self._bodygen = gen
def setbodywillwrite(self):
"""Signal an intent to use write() to emit the response body.
**This is the least preferred way to send a body.**
Gregory Szorc
hgweb: create dedicated type for WSGI responses...
r36877
Gregory Szorc
hgweb: port archive command to modern response API...
r36892 It is preferred for WSGI applications to emit a generator of chunks
constituting the response body. However, some consumers can't emit
data this way. So, WSGI provides a way to obtain a ``write(data)``
function that can be used to synchronously perform an unbuffered
write.
Calling this function signals an intent to produce the body in this
manner.
"""
self._verifybody()
self._bodywillwrite = True
Gregory Szorc
hgweb: create dedicated type for WSGI responses...
r36877
def sendresponse(self):
"""Send the generated response to the client.
Before this is called, ``status`` must be set and one of
``setbodybytes()`` or ``setbodygen()`` must be called.
Calling this method multiple times is not allowed.
"""
if self._started:
raise error.ProgrammingError('sendresponse() called multiple times')
self._started = True
if not self.status:
raise error.ProgrammingError('status line not defined')
Gregory Szorc
hgweb: port archive command to modern response API...
r36892 if (self._bodybytes is None and self._bodygen is None
and not self._bodywillwrite):
Gregory Szorc
hgweb: create dedicated type for WSGI responses...
r36877 raise error.ProgrammingError('response body not defined')
Gregory Szorc
hgweb: refactor 304 handling code...
r36894 # RFC 7232 Section 4.1 states that a 304 MUST generate one of
# {Cache-Control, Content-Location, Date, ETag, Expires, Vary}
# and SHOULD NOT generate other headers unless they could be used
# to guide cache updates. Furthermore, RFC 7230 Section 3.3.2
# states that no response body can be issued. Content-Length can
# be sent. But if it is present, it should be the size of the response
# that wasn't transferred.
if self.status.startswith('304 '):
# setbodybytes('') will set C-L to 0. This doesn't conform with the
# spec. So remove it.
if self.headers.get('Content-Length') == '0':
del self.headers['Content-Length']
# Strictly speaking, this is too strict. But until it causes
# problems, let's be strict.
badheaders = {k for k in self.headers.keys()
if k.lower() not in ('date', 'etag', 'expires',
'cache-control',
'content-location',
'vary')}
if badheaders:
raise error.ProgrammingError(
'illegal header on 304 response: %s' %
', '.join(sorted(badheaders)))
if self._bodygen is not None or self._bodywillwrite:
raise error.ProgrammingError("must use setbodybytes('') with "
"304 responses")
Gregory Szorc
hgweb: create dedicated type for WSGI responses...
r36877 # Various HTTP clients (notably httplib) won't read the HTTP response
# until the HTTP request has been sent in full. If servers (us) send a
# response before the HTTP request has been fully sent, the connection
# may deadlock because neither end is reading.
#
# We work around this by "draining" the request data before
# sending any response in some conditions.
drain = False
close = False
# If the client sent Expect: 100-continue, we assume it is smart enough
# to deal with the server sending a response before reading the request.
# (httplib doesn't do this.)
if self._req.headers.get('Expect', '').lower() == '100-continue':
pass
# Only tend to request methods that have bodies. Strictly speaking,
# we should sniff for a body. But this is fine for our existing
# WSGI applications.
elif self._req.method not in ('POST', 'PUT'):
pass
else:
# If we don't know how much data to read, there's no guarantee
# that we can drain the request responsibly. The WSGI
# specification only says that servers *should* ensure the
# input stream doesn't overrun the actual request. So there's
# no guarantee that reading until EOF won't corrupt the stream
# state.
if not isinstance(self._req.bodyfh, util.cappedreader):
close = True
else:
# We /could/ only drain certain HTTP response codes. But 200 and
# non-200 wire protocol responses both require draining. Since
# we have a capped reader in place for all situations where we
# drain, it is safe to read from that stream. We'll either do
# a drain or no-op if we're already at EOF.
drain = True
if close:
self.headers['Connection'] = 'Close'
if drain:
assert isinstance(self._req.bodyfh, util.cappedreader)
while True:
chunk = self._req.bodyfh.read(32768)
if not chunk:
break
Gregory Szorc
hgweb: port archive command to modern response API...
r36892 write = self._startresponse(pycompat.sysstr(self.status),
self.headers.items())
Gregory Szorc
hgweb: create dedicated type for WSGI responses...
r36877 if self._bodybytes:
yield self._bodybytes
elif self._bodygen:
for chunk in self._bodygen:
yield chunk
Gregory Szorc
hgweb: port archive command to modern response API...
r36892 elif self._bodywillwrite:
self._bodywritefn = write
Gregory Szorc
hgweb: create dedicated type for WSGI responses...
r36877 else:
error.ProgrammingError('do not know how to send body')
Gregory Szorc
hgweb: port archive command to modern response API...
r36892 def getbodyfile(self):
"""Obtain a file object like object representing the response body.
For this to work, you must call ``setbodywillwrite()`` and then
``sendresponse()`` first. ``sendresponse()`` is a generator and the
function won't run to completion unless the generator is advanced. The
generator yields not items. The easiest way to consume it is with
``list(res.sendresponse())``, which should resolve to an empty list -
``[]``.
"""
if not self._bodywillwrite:
raise error.ProgrammingError('must call setbodywillwrite() first')
if not self._started:
raise error.ProgrammingError('must call sendresponse() first; did '
'you remember to consume it since it '
'is a generator?')
assert self._bodywritefn
return offsettrackingwriter(self._bodywritefn)
Dirkjan Ochtman
Less indirection in the WSGI web interface. This simplifies some code, and makes it more compliant with WSGI.
r5566 class wsgirequest(object):
Gregory Szorc
hgweb: add some documentation...
r26132 """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.
"""
Gregory Szorc
hgweb: support constructing URLs from an alternate base URL...
r36916 def __init__(self, wsgienv, start_response, altbaseurl=None):
Augie Fackler
hgweb: when constructing or adding to a wsgi environ dict, use native strs...
r34513 version = wsgienv[r'wsgi.version']
Thomas Arendsen Hein
white space and line break cleanups
r3673 if (version < (1, 0)) or (version >= (2, 0)):
Thomas Arendsen Hein
Cleanup of whitespace, indentation and line continuation.
r4633 raise RuntimeError("Unknown and unsupported WSGI version %d.%d"
Eric Hopper
This patch make several WSGI related alterations....
r2506 % version)
Gregory Szorc
hgweb: expose input stream on parsed WSGI request object...
r36873
inp = wsgienv[r'wsgi.input']
Gregory Szorc
hgweb: use a capped reader for WSGI input stream...
r36870
if r'HTTP_CONTENT_LENGTH' in wsgienv:
Gregory Szorc
hgweb: expose input stream on parsed WSGI request object...
r36873 inp = util.cappedreader(inp, int(wsgienv[r'HTTP_CONTENT_LENGTH']))
Gregory Szorc
hgweb: use a capped reader for WSGI input stream...
r36870 elif r'CONTENT_LENGTH' in wsgienv:
Gregory Szorc
hgweb: expose input stream on parsed WSGI request object...
r36873 inp = util.cappedreader(inp, int(wsgienv[r'CONTENT_LENGTH']))
Gregory Szorc
hgweb: use a capped reader for WSGI input stream...
r36870
Augie Fackler
hgweb: when constructing or adding to a wsgi environ dict, use native strs...
r34513 self.err = wsgienv[r'wsgi.errors']
self.threaded = wsgienv[r'wsgi.multithread']
self.multiprocess = wsgienv[r'wsgi.multiprocess']
self.run_once = wsgienv[r'wsgi.run_once']
Eric Hopper
This patch make several WSGI related alterations....
r2506 self.env = wsgienv
Gregory Szorc
hgweb: support constructing URLs from an alternate base URL...
r36916 self.req = parserequestfromenv(wsgienv, inp, altbaseurl=altbaseurl)
Gregory Szorc
hgweb: create dedicated type for WSGI responses...
r36877 self.res = wsgiresponse(self.req, start_response)
Dirkjan Ochtman
hgweb: separate out start_response() calling
r5888 self._start_response = start_response
Dirkjan Ochtman
hgweb: explicit response status
r5993 self.server_write = None
Eric Hopper
This patch make several WSGI related alterations....
r2506 self.headers = []
Mads Kiilerich
hgweb: pass the actual response body to request.response, not just the length...
r18352 def respond(self, status, type, filename=None, body=None):
Augie Fackler
request: coerce content-type to native str...
r34515 if not isinstance(type, str):
type = pycompat.sysstr(type)
Dirkjan Ochtman
hgweb: separate out start_response() calling
r5888 if self._start_response is not None:
Augie Fackler
hgweb: fill in content-type and content-length as native strings...
r34723 self.headers.append((r'Content-Type', type))
Mads Kiilerich
hgweb: simplify wsgirequest header handling...
r18348 if filename:
av6
hgweb: replace some str.split() calls by str.partition() or str.rpartition()...
r26846 filename = (filename.rpartition('/')[-1]
Mads Kiilerich
hgweb: simplify wsgirequest header handling...
r18348 .replace('\\', '\\\\').replace('"', '\\"'))
self.headers.append(('Content-Disposition',
'inline; filename="%s"' % filename))
Mads Kiilerich
hgweb: pass the actual response body to request.response, not just the length...
r18352 if body is not None:
Augie Fackler
hgweb: fill in content-type and content-length as native strings...
r34723 self.headers.append((r'Content-Length', str(len(body))))
Dirkjan Ochtman
hgweb: separate out start_response() calling
r5888
Dirkjan Ochtman
hgweb: be sure to send a valid content-type for raw files
r5926 for k, v in self.headers:
if not isinstance(v, str):
Mads Kiilerich
hgweb: simplify wsgirequest header handling...
r18348 raise TypeError('header value must be string: %r' % (v,))
Dirkjan Ochtman
hgweb: be sure to send a valid content-type for raw files
r5926
Dirkjan Ochtman
hgweb: separate out start_response() calling
r5888 if isinstance(status, ErrorResponse):
Mads Kiilerich
hgweb: simplify wsgirequest header handling...
r18348 self.headers.extend(status.headers)
Augie Fackler
hgweb: correctly bytes-ify status, not string-ify...
r36269 status = statusmessage(status.code, pycompat.bytestr(status))
Dirkjan Ochtman
hgweb: explicit response status
r5993 elif status == 200:
status = '200 Script output follows'
Dirkjan Ochtman
hgweb: separate out start_response() calling
r5888 elif isinstance(status, int):
status = statusmessage(status)
Gregory Szorc
hgweb: refactor the request draining code...
r36871 # Various HTTP clients (notably httplib) won't read the HTTP
# response until the HTTP request has been sent in full. If servers
# (us) send a response before the HTTP request has been fully sent,
# the connection may deadlock because neither end is reading.
#
# We work around this by "draining" the request data before
# sending any response in some conditions.
drain = False
close = False
# If the client sent Expect: 100-continue, we assume it is smart
# enough to deal with the server sending a response before reading
# the request. (httplib doesn't do this.)
if self.env.get(r'HTTP_EXPECT', r'').lower() == r'100-continue':
pass
# Only tend to request methods that have bodies. Strictly speaking,
# we should sniff for a body. But this is fine for our existing
# WSGI applications.
elif self.env[r'REQUEST_METHOD'] not in (r'POST', r'PUT'):
pass
else:
# If we don't know how much data to read, there's no guarantee
# that we can drain the request responsibly. The WSGI
# specification only says that servers *should* ensure the
# input stream doesn't overrun the actual request. So there's
# no guarantee that reading until EOF won't corrupt the stream
# state.
Gregory Szorc
hgweb: expose input stream on parsed WSGI request object...
r36873 if not isinstance(self.req.bodyfh, util.cappedreader):
Gregory Szorc
hgweb: refactor the request draining code...
r36871 close = True
else:
# We /could/ only drain certain HTTP response codes. But 200
# and non-200 wire protocol responses both require draining.
# Since we have a capped reader in place for all situations
# where we drain, it is safe to read from that stream. We'll
# either do a drain or no-op if we're already at EOF.
drain = True
if close:
self.headers.append((r'Connection', r'Close'))
if drain:
Gregory Szorc
hgweb: expose input stream on parsed WSGI request object...
r36873 assert isinstance(self.req.bodyfh, util.cappedreader)
Gregory Szorc
hgweb: refactor the request draining code...
r36871 while True:
Gregory Szorc
hgweb: expose input stream on parsed WSGI request object...
r36873 chunk = self.req.bodyfh.read(32768)
Gregory Szorc
hgweb: refactor the request draining code...
r36871 if not chunk:
break
Augie Fackler
py3: get bytes-repr of network errors portably...
r36272 self.server_write = self._start_response(
pycompat.sysstr(status), self.headers)
Dirkjan Ochtman
hgweb: separate out start_response() calling
r5888 self._start_response = None
self.headers = []
Mads Kiilerich
hgweb: pass the actual response body to request.response, not just the length...
r18352 if body is not None:
self.write(body)
self.server_write = None
Dirkjan Ochtman
hgweb: separate out start_response() calling
r5888
Dirkjan Ochtman
hgweb: explicit response status
r5993 def write(self, thing):
Mads Kiilerich
hgweb: don't pass empty response chunks on...
r18351 if thing:
try:
self.server_write(thing)
Gregory Szorc
global: mass rewrite to use modern exception syntax...
r25660 except socket.error as inst:
Mads Kiilerich
hgweb: don't pass empty response chunks on...
r18351 if inst[0] != errno.ECONNRESET:
raise
Eric Hopper
Splitting up hgweb so it's easier to change.
r2355
Alexis S. L. Carvalho
avoid _wsgioutputfile <-> _wsgirequest circular reference...
r4246 def flush(self):
return None
Dirkjan Ochtman
Less indirection in the WSGI web interface. This simplifies some code, and makes it more compliant with WSGI.
r5566 def wsgiapplication(app_maker):
Dirkjan Ochtman
hgweb: return iterable, add deprecation note
r5887 '''For compatibility with old CGI scripts. A plain hgweb() or hgwebdir()
can and should now be used as a WSGI application.'''
Thomas Arendsen Hein
Removed tabs and trailing whitespace in python files
r5760 application = app_maker()
def run_wsgi(env, respond):
Dirkjan Ochtman
hgweb: return iterable, add deprecation note
r5887 return application(env, respond)
Thomas Arendsen Hein
Removed tabs and trailing whitespace in python files
r5760 return run_wsgi