( )⚙ D2742 hgweb: parse and store HTTP request headers

This is an archive of the discontinued Mercurial Phabricator instance.

Differential D2742

hgweb: parse and store HTTP request headers
ClosedPublic

Authored by indygreg on Mar 8 2018, 8:06 PM.

Details

Reviewers
durin42
Group Reviewers
hg-reviewers
Commits
rHGf9078c6caeb6: hgweb: parse and store HTTP request headers
rHG29b477d7f334: hgweb: parse and store HTTP request headers
Summary

WSGI transmits HTTP request headers as HTTP_* environment variables.
We teach our parser about these and hook up a dict-like data
structure that supports case insensitive header manipulation.

Diff Detail

Repository
rHG Mercurial
Lint
Lint Skipped
Unit
Unit Tests Skipped

Event Timeline

indygreg created this revision.Mar 8 2018, 8:06 PM
durin42 accepted this revision.Mar 9 2018, 2:25 PM
This revision is now accepted and ready to land.Mar 9 2018, 2:25 PM
Closed by commit rHG29b477d7f334: hgweb: parse and store HTTP request headers (authored by indygreg). · Explain WhyMar 9 2018, 2:30 PM
This revision was automatically updated to reflect the committed changes.

Revision Contents
Changeset List

Diff 6748

mercurial/hgweb/hgweb_mod.py

wsgireq.form['file'] = ['/'.join(args)] wsgireq.form['file'] = ['/'.join(args)]
else: else:
if args and args[0]: if args and args[0]:
node = args.pop(0).replace('%2F', '/') node = args.pop(0).replace('%2F', '/')
wsgireq.form['node'] = [node] wsgireq.form['node'] = [node]
if args: if args:
wsgireq.form['file'] = args wsgireq.form['file'] = args
ua = wsgireq.env.get('HTTP_USER_AGENT', '') ua = req.headers.get('User-Agent', '')
if cmd == 'rev' and 'mercurial' in ua: if cmd == 'rev' and 'mercurial' in ua:
wsgireq.form['style'] = ['raw'] wsgireq.form['style'] = ['raw']
if cmd == 'archive': if cmd == 'archive':
fn = wsgireq.form['node'][0] fn = wsgireq.form['node'][0]
for type_, spec in rctx.archivespecs.iteritems(): for type_, spec in rctx.archivespecs.iteritems():
ext = spec[2] ext = spec[2]
if fn.endswith(ext): if fn.endswith(ext):

mercurial/hgweb/request.py

# hgweb/request.py - An http request from either CGI or the standalone server. # hgweb/request.py - An http request from either CGI or the standalone server.
# #
# Copyright 21 May 2005 - (c) 2005 Jake Edge <jake@edge2.net> # Copyright 21 May 2005 - (c) 2005 Jake Edge <jake@edge2.net>
# Copyright 2005, 2006 Matt Mackall <mpm@selenic.com> # Copyright 2005, 2006 Matt Mackall <mpm@selenic.com>
# #
# This software may be used and distributed according to the terms of the # This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version. # GNU General Public License version 2 or any later version.
from __future__ import absolute_import from __future__ import absolute_import
import cgi import cgi
import errno import errno
import socket import socket
import wsgiref.headers as wsgiheaders
#import wsgiref.validate #import wsgiref.validate
from .common import ( from .common import (
ErrorResponse, ErrorResponse,
HTTP_NOT_MODIFIED, HTTP_NOT_MODIFIED,
statusmessage, statusmessage,
) )
# when ``dispatchpath`` is empty due to REPO_NAME muckery. # when ``dispatchpath`` is empty due to REPO_NAME muckery.
havepathinfo = attr.ib() havepathinfo = attr.ib()
# Raw query string (part after "?" in URL). # Raw query string (part after "?" in URL).
querystring = attr.ib() querystring = attr.ib()
# List of 2-tuples of query string arguments. # List of 2-tuples of query string arguments.
querystringlist = attr.ib() querystringlist = attr.ib()
# Dict of query string arguments. Values are lists with at least 1 item. # Dict of query string arguments. Values are lists with at least 1 item.
querystringdict = attr.ib() querystringdict = attr.ib()
# wsgiref.headers.Headers instance. Operates like a dict with case
# insensitive keys.
headers = attr.ib()
def parserequestfromenv(env): def parserequestfromenv(env):
"""Parse URL components from environment variables. """Parse URL components from environment variables.
WSGI defines request attributes via environment variables. This function WSGI defines request attributes via environment variables. This function
parses the environment variables into a data structure. parses the environment variables into a data structure.
""" """
# PEP-0333 defines the WSGI spec and is a useful reference for this code. # PEP-0333 defines the WSGI spec and is a useful reference for this code.
querystringdict = {} querystringdict = {}
for k, v in querystringlist: for k, v in querystringlist:
if k in querystringdict: if k in querystringdict:
querystringdict[k].append(v) querystringdict[k].append(v)
else: else:
querystringdict[k] = [v] querystringdict[k] = [v]
# 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)
return parsedrequest(url=fullurl, baseurl=baseurl, return parsedrequest(url=fullurl, baseurl=baseurl,
advertisedurl=advertisedfullurl, advertisedurl=advertisedfullurl,
advertisedbaseurl=advertisedbaseurl, advertisedbaseurl=advertisedbaseurl,
apppath=apppath, apppath=apppath,
dispatchparts=dispatchparts, dispatchpath=dispatchpath, dispatchparts=dispatchparts, dispatchpath=dispatchpath,
havepathinfo='PATH_INFO' in env, havepathinfo='PATH_INFO' in env,
querystring=querystring, querystring=querystring,
querystringlist=querystringlist, querystringlist=querystringlist,
querystringdict=querystringdict) querystringdict=querystringdict,
headers=headers)
class wsgirequest(object): class wsgirequest(object):
"""Higher-level API for a WSGI request. """Higher-level API for a WSGI request.
WSGI applications are invoked with 2 arguments. They are used to WSGI applications are invoked with 2 arguments. They are used to
instantiate instances of this class, which provides higher-level APIs instantiate instances of this class, which provides higher-level APIs
for obtaining request parameters, writing HTTP output, etc. for obtaining request parameters, writing HTTP output, etc.
""" """