Patchwork D2771: hgweb: expose input stream on parsed WSGI request object

login
register
mail settings
Submitter phabricator
Date March 10, 2018, 1:23 a.m.
Message ID <differential-rev-PHID-DREV-vxwqqyiv3mc7u2m2csrq-req@phab.mercurial-scm.org>
Download mbox | patch
Permalink /patch/29228/
State Superseded
Headers show

Comments

phabricator - March 10, 2018, 1:23 a.m.
indygreg created this revision.
Herald added a subscriber: mercurial-devel.
Herald added a reviewer: hg-reviewers.

REVISION SUMMARY
  Our next step towards moving away from wsgirequest to our newer,
  friendlier parsedrequest type is input stream access.
  
  This commit exposes the input stream on the instance. Consumers
  in the HTTP protocol server switch to it.
  
  Because there were very few consumers of the input stream, we stopped
  storing a reference to the input stream on wsgirequest directly. All
  access now goes through parsedrequest. However, wsgirequest still
  may read from this stream as part of cgi.parse(). So we still need to
  create the stream from wsgirequest.

REPOSITORY
  rHG Mercurial

REVISION DETAIL
  https://phab.mercurial-scm.org/D2771

AFFECTED FILES
  mercurial/hgweb/hgwebdir_mod.py
  mercurial/hgweb/request.py
  mercurial/wireprotoserver.py

CHANGE DETAILS




To: indygreg, #hg-reviewers
Cc: mercurial-devel

Patch

diff --git a/mercurial/wireprotoserver.py b/mercurial/wireprotoserver.py
--- a/mercurial/wireprotoserver.py
+++ b/mercurial/wireprotoserver.py
@@ -83,7 +83,7 @@ 
         postlen = int(self._req.headers.get(b'X-HgArgs-Post', 0))
         if postlen:
             args.update(urlreq.parseqs(
-                self._wsgireq.inp.read(postlen), keep_blank_values=True))
+                self._req.bodyfh.read(postlen), keep_blank_values=True))
             return args
 
         argvalue = decodevaluefromheaders(self._req, b'X-HgArg')
@@ -97,7 +97,7 @@ 
         # If httppostargs is used, we need to read Content-Length
         # minus the amount that was consumed by args.
         length -= int(self._req.headers.get(b'X-HgArgs-Post', 0))
-        for s in util.filechunkiter(self._wsgireq.inp, limit=length):
+        for s in util.filechunkiter(self._req.bodyfh, limit=length):
             fp.write(s)
 
     @contextlib.contextmanager
diff --git a/mercurial/hgweb/request.py b/mercurial/hgweb/request.py
--- a/mercurial/hgweb/request.py
+++ b/mercurial/hgweb/request.py
@@ -61,7 +61,10 @@ 
 
 @attr.s(frozen=True)
 class parsedrequest(object):
-    """Represents a parsed WSGI request / static HTTP request parameters."""
+    """Represents a parsed WSGI request.
+
+    Contains both parsed parameters as well as a handle on the input stream.
+    """
 
     # Request method.
     method = attr.ib()
@@ -91,8 +94,10 @@ 
     # wsgiref.headers.Headers instance. Operates like a dict with case
     # insensitive keys.
     headers = attr.ib()
+    # Request body input stream.
+    bodyfh = attr.ib()
 
-def parserequestfromenv(env):
+def parserequestfromenv(env, bodyfh):
     """Parse URL components from environment variables.
 
     WSGI defines request attributes via environment variables. This function
@@ -209,6 +214,12 @@ 
     if 'CONTENT_LENGTH' in env and 'HTTP_CONTENT_LENGTH' not in env:
         headers['Content-Length'] = env['CONTENT_LENGTH']
 
+    # 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']))
+
     return parsedrequest(method=env['REQUEST_METHOD'],
                          url=fullurl, baseurl=baseurl,
                          advertisedurl=advertisedfullurl,
@@ -219,7 +230,8 @@ 
                          querystring=querystring,
                          querystringlist=querystringlist,
                          querystringdict=querystringdict,
-                         headers=headers)
+                         headers=headers,
+                         bodyfh=bodyfh)
 
 class wsgirequest(object):
     """Higher-level API for a WSGI request.
@@ -233,28 +245,27 @@ 
         if (version < (1, 0)) or (version >= (2, 0)):
             raise RuntimeError("Unknown and unsupported WSGI version %d.%d"
                                % version)
-        self.inp = wsgienv[r'wsgi.input']
+
+        inp = wsgienv[r'wsgi.input']
 
         if r'HTTP_CONTENT_LENGTH' in wsgienv:
-            self.inp = util.cappedreader(self.inp,
-                                         int(wsgienv[r'HTTP_CONTENT_LENGTH']))
+            inp = util.cappedreader(inp, int(wsgienv[r'HTTP_CONTENT_LENGTH']))
         elif r'CONTENT_LENGTH' in wsgienv:
-            self.inp = util.cappedreader(self.inp,
-                                         int(wsgienv[r'CONTENT_LENGTH']))
+            inp = util.cappedreader(inp, int(wsgienv[r'CONTENT_LENGTH']))
 
         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']
         self.env = wsgienv
-        self.form = normalize(cgi.parse(self.inp,
+        self.form = normalize(cgi.parse(inp,
                                         self.env,
                                         keep_blank_values=1))
         self._start_response = start_response
         self.server_write = None
         self.headers = []
 
-        self.req = parserequestfromenv(wsgienv)
+        self.req = parserequestfromenv(wsgienv, inp)
 
     def respond(self, status, type, filename=None, body=None):
         if not isinstance(type, str):
@@ -301,7 +312,7 @@ 
             if self.env[r'REQUEST_METHOD'] in (r'POST', r'PUT'):
                 # If we can't guarantee the end of stream, close the connection
                 # because any reading may be unsafe.
-                if not isinstance(self.inp, util.cappedreader):
+                if not isinstance(self.req.bodyfh, util.cappedreader):
                     close = True
                 else:
                     # We know the length of the input. So draining is possible.
@@ -325,9 +336,9 @@ 
                 self.headers.append((r'Connection', r'Close'))
 
             if drain:
-                assert isinstance(self.inp, util.cappedreader)
+                assert isinstance(self.req.bodyfh, util.cappedreader)
                 while True:
-                    chunk = self.inp.read(32768)
+                    chunk = self.req.bodyfh.read(32768)
                     if not chunk:
                         break
 
diff --git a/mercurial/hgweb/hgwebdir_mod.py b/mercurial/hgweb/hgwebdir_mod.py
--- a/mercurial/hgweb/hgwebdir_mod.py
+++ b/mercurial/hgweb/hgwebdir_mod.py
@@ -293,7 +293,8 @@ 
                     # variable.
                     # TODO this is kind of hacky and we should have a better
                     # way of doing this than with REPO_NAME side-effects.
-                    wsgireq.req = requestmod.parserequestfromenv(wsgireq.env)
+                    wsgireq.req = requestmod.parserequestfromenv(
+                        wsgireq.env, wsgireq.req.bodyfh)
                     try:
                         # ensure caller gets private copy of ui
                         repo = hg.repository(self.ui.copy(), real)