changeset 36809:3c15b84ab66c

hgweb: teach WSGI parser about query strings

Currently, req.form uses cgi.parse() to populate form data. Depending
on the request, form data can come from POST multipart/form-data,
application/x-www-form-urlencoded, or the URL query string.

Putting all these things into one data structure makes it difficult
to reason about how exactly parameters got to the request. It can
lead to wonkiness such as pulling parameters from both the URL and
POST data.

This commit teaches our WSGI request parser about argument data
in query strings. We populate fields containing the query string
data and only the query string data so it can't be confused with
POST data.

Differential Revision: https://phab.mercurial-scm.org/D2737

--- a/mercurial/hgweb/request.py	Thu Mar 08 15:08:20 2018 -0800
+++ b/mercurial/hgweb/request.py	Thu Mar 08 11:21:46 2018 -0800
@@ -78,6 +78,10 @@
     dispatchpath = attr.ib()
     # Raw query string (part after "?" in URL).
     querystring = attr.ib()
+    # List of 2-tuples of query string arguments.
+    querystringlist = attr.ib()
+    # Dict of query string arguments. Values are lists with at least 1 item.
+    querystringdict = attr.ib()
 
 def parserequestfromenv(env):
     """Parse URL components from environment variables.
@@ -168,12 +172,25 @@
 
     querystring = env.get('QUERY_STRING', '')
 
+    # We store as a list so we have ordering information. We also store as
+    # a dict to facilitate fast lookup.
+    querystringlist = util.urlreq.parseqsl(querystring, keep_blank_values=True)
+
+    querystringdict = {}
+    for k, v in querystringlist:
+        if k in querystringdict:
+            querystringdict[k].append(v)
+        else:
+            querystringdict[k] = [v]
+
     return parsedrequest(url=fullurl, baseurl=baseurl,
                          advertisedurl=advertisedfullurl,
                          advertisedbaseurl=advertisedbaseurl,
                          apppath=apppath,
                          dispatchparts=dispatchparts, dispatchpath=dispatchpath,
-                         querystring=querystring)
+                         querystring=querystring,
+                         querystringlist=querystringlist,
+                         querystringdict=querystringdict)
 
 class wsgirequest(object):
     """Higher-level API for a WSGI request.

--- a/mercurial/urllibcompat.py	Thu Mar 08 15:08:20 2018 -0800
+++ b/mercurial/urllibcompat.py	Thu Mar 08 11:21:46 2018 -0800
@@ -48,6 +48,7 @@
         "urlunparse",
     ))
     urlreq._registeralias(urllib.parse, "parse_qs", "parseqs")
+    urlreq._registeralias(urllib.parse, "parse_qsl", "parseqsl")
     urlreq._registeralias(urllib.parse, "unquote_to_bytes", "unquote")
     import urllib.request
     urlreq._registeraliases(urllib.request, (
@@ -159,6 +160,7 @@
         "urlunparse",
     ))
     urlreq._registeralias(urlparse, "parse_qs", "parseqs")
+    urlreq._registeralias(urlparse, "parse_qsl", "parseqsl")
     urlerr._registeraliases(urllib2, (
         "HTTPError",
         "URLError",