Index: Lib/wsgiref/simple_server.py =================================================================== --- Lib/wsgiref/simple_server.py (revision 85567) +++ Lib/wsgiref/simple_server.py (working copy) @@ -1,4 +1,4 @@ -"""BaseHTTPServer that implements the Python WSGI protocol (PEP 333, rev 1.21) +"""BaseHTTPServer that implements the Python WSGI protocol (PEP 3333, v.85294) This is both an example of how WSGI can be implemented, and a basis for running simple web applications on a local machine, such as might be done when testing @@ -15,7 +15,7 @@ import urllib.parse from wsgiref.handlers import SimpleHandler -__version__ = "0.1" +__version__ = "0.2" __all__ = ['WSGIServer', 'WSGIRequestHandler', 'demo_app', 'make_server'] @@ -74,13 +74,14 @@ def get_environ(self): env = self.server.base_environ.copy() env['SERVER_PROTOCOL'] = self.request_version + env['SERVER_SOFTWARE'] = self.server_version env['REQUEST_METHOD'] = self.command if '?' in self.path: path,query = self.path.split('?',1) else: path,query = self.path,'' - env['PATH_INFO'] = urllib.parse.unquote(path) + env['PATH_INFO'] = urllib.parse.unquote_to_bytes(path).decode('iso-8859-1') env['QUERY_STRING'] = query host = self.address_string() @@ -133,7 +134,7 @@ h = sorted(environ.items()) for k,v in h: print(k,'=',repr(v), file=stdout) - start_response(b"200 OK", [(b'Content-Type',b'text/plain; charset=utf-8')]) + start_response('200 OK', [('Content-Type', 'text/plain; charset=utf-8')]) return [stdout.getvalue().encode("utf-8")] Index: Lib/wsgiref/handlers.py =================================================================== --- Lib/wsgiref/handlers.py (revision 85567) +++ Lib/wsgiref/handlers.py (working copy) @@ -5,7 +5,7 @@ import sys, os, time -__all__ = ['BaseHandler', 'SimpleHandler', 'BaseCGIHandler', 'CGIHandler'] +__all__ = ['BaseHandler', 'SimpleHandler', 'BaseCGIHandler', 'CGIHandler', 'IISCGIHandler'] # Weekday and month names for HTTP date/time formatting; always English! _weekdayname = ["Mon", "Tue", "Wed", "Thu", "Fri", "Sat", "Sun"] @@ -19,7 +19,74 @@ _weekdayname[wd], day, _monthname[month], year, hh, mm, ss ) +def read_environ(): + """Read environment, fixing HTTP variables""" + enc = sys.getfilesystemencoding() + esc = 'surrogateescape' + try: + ''.encode('utf-8', esc) + except LookupError: + esc = 'replace' + environ = {} + # If a native byte-oriented environ is available, use it (Python 3.2 on + # posix) + if sys.platform != 'win32' and hasattr(os, 'environb') and False: + for k, v in os.environb.items(): + environ[k.decode('iso-8859-1')] = v.decode('iso-8859-1') + return environ + + # Otherwise, take the basic environment from native-unicode os.environ. + # Attempt to fix up the variables that come from the HTTP request to + # compensate for the bytes->unicode decoding step that will already hav + # taken place. + for k, v in os.environ.items(): + if k in ('SCRIPT_NAME', 'PATH_INFO') or k.startswith('HTTP_'): + + # On win32, the os.environ is natively Unicode. Different servers + # decode the request bytes using different encodings. + if sys.platform == 'win32': + software = os.environ.get('SERVER_SOFTWARE', '').lower() + + # On IIS, the HTTP request will be decoded as UTF-8 as long + # as the input is a valid UTF-8 sequence. Otherwise it is + # decoded using the system code page (mbcs), with no way to + # detect this has happened. Because UTF-8 is the more likely + # encoding, and mbcs is inherently unreliable (an mbcs string + # that happens to be valid UTF-8 will not be decoded as mbcs) + # always recreate the original bytes as UTF-8. + if software.startswith('microsoft-iis/'): + v = v.encode('utf-8').decode('iso-8859-1') + + # Apache mod_cgi writes bytes-as-unicode (as if ISO-8859-1) direct + # to the Unicode environ. No modification needed. + elif software.startswith('apache/'): + pass + + # Python 3's http.server.CGIHTTPRequestHandler decodes + # using the urllib.unquote default of UTF-8, amongst other + # issues. + elif ( + software.startswith('simplehttp/') + and 'python/3' in software + ): + v = v.encode('utf-8').decode('iso-8859-1') + + # For other servers, guess that they have written bytes to + # the environ using stdio byte-oriented interfaces, ending up + # with the system code page. + else: + v = v.encode(enc, 'replace').decode('iso-8859-1') + + # Recover bytes from unicode environ, using surrogate escapes + # where available (Python 3.1). + else: + v = v.encode(enc, esc).decode('iso-8859-1') + + environ[k] = v + return environ + + class BaseHandler: """Manage the invocation of a WSGI application""" @@ -36,7 +103,7 @@ # os_environ is used to supply configuration from the OS environment: # by default it's a copy of 'os.environ' as of import time, but you can # override this in e.g. your __init__ method. - os_environ = dict(os.environ.items()) + os_environ= read_environ() # Collaborator classes wsgi_file_wrapper = FileWrapper # set to None to disable @@ -438,6 +505,43 @@ def __init__(self): BaseCGIHandler.__init__( - self, sys.stdin, sys.stdout, sys.stderr, dict(os.environ.items()), - multithread=False, multiprocess=True + self, sys.stdin.buffer, sys.stdout.buffer, sys.stderr, + read_environ(), multithread=False, multiprocess=True ) + + +class IISCGIHandler(BaseCGIHandler): + """CGI-based invocation with workaround for IIS path bug + + This handler should be used in preference to CGIHandler when deploying on + Microsoft IIS without having set the config allowPathInfo option (IIS>=7) + or metabase allowPathInfoForScriptMappings (IIS<7). + """ + wsgi_run_once = True + os_environ = {} + + # By default, IIS gives a PATH_INFO that duplicates the SCRIPT_NAME at + # the front, causing problems for WSGI applications that wish to implement + # routing. This handler strips any such duplicated path. + + # IIS can be configured to pass the correct PATH_INFO, but this causes + # another bug where PATH_TRANSLATED is wrong. Luckily this variable is + # rarely used and is not guaranteed by WSGI. On IIS<7, though, the + # setting can only be made on a vhost level, affecting all other script + # mappings, many of which break when exposed to the PATH_TRANSLATED bug. + # For this reason IIS<7 is almost never deployed with the fix. (Even IIS7 + # rarely uses it because there is still no UI for it.) + + # There is no way for CGI code to tell whether the option was set, so a + # separate handler class is provided. + def __init__(self): + environ= read_environ() + path = environ.get('PATH_INFO', '') + script = environ.get('SCRIPT_NAME', '') + if (path+'/').startswith(script+'/'): + environ['PATH_INFO'] = path[len(script):] + BaseCGIHandler.__init__( + self, sys.stdin.buffer, sys.stdout.buffer, sys.stderr, + environ, multithread=False, multiprocess=True + ) + Index: Lib/test/test_wsgiref.py =================================================================== --- Lib/test/test_wsgiref.py (revision 85567) +++ Lib/test/test_wsgiref.py (working copy) @@ -131,7 +131,7 @@ def check_hello(self, out, has_length=True): self.assertEqual(out, ("HTTP/1.0 200 OK\r\n" - "Server: WSGIServer/0.1 Python/"+sys.version.split()[0]+"\r\n" + "Server: WSGIServer/0.2 Python/"+sys.version.split()[0]+"\r\n" "Content-Type: text/plain\r\n" "Date: Mon, 05 Jun 2006 18:49:54 GMT\r\n" + (has_length and "Content-Length: 13\r\n" or "") + @@ -175,28 +175,7 @@ err.splitlines()[-2], "AssertionError" ) - def test_bytes_validation(self): - def app(e, s): - s(b"200 OK", [ - (b"Content-Type", b"text/plain; charset=utf-8"), - ("Date", "Wed, 24 Dec 2008 13:29:32 GMT"), - ]) - return [b"data"] - out, err = run_amock(validator(app)) - self.assertTrue(err.endswith('"GET / HTTP/1.0" 200 4\n')) - ver = sys.version.split()[0].encode('ascii') - self.assertEqual( - b"HTTP/1.0 200 OK\r\n" - b"Server: WSGIServer/0.1 Python/" + ver + b"\r\n" - b"Content-Type: text/plain; charset=utf-8\r\n" - b"Date: Wed, 24 Dec 2008 13:29:32 GMT\r\n" - b"\r\n" - b"data", - out) - - - class UtilityTests(TestCase): def checkShift(self,sn_in,pi_in,part,sn_out,pi_out):