2000-08-19 10:01:19 -03:00
|
|
|
#!/usr/bin/env python
|
|
|
|
#
|
|
|
|
|
|
|
|
####
|
|
|
|
# Copyright 2000 by Timothy O'Malley <timo@alum.mit.edu>
|
2001-01-14 19:36:06 -04:00
|
|
|
#
|
2000-08-19 10:01:19 -03:00
|
|
|
# All Rights Reserved
|
2001-01-14 19:36:06 -04:00
|
|
|
#
|
2000-08-19 10:01:19 -03:00
|
|
|
# Permission to use, copy, modify, and distribute this software
|
|
|
|
# and its documentation for any purpose and without fee is hereby
|
|
|
|
# granted, provided that the above copyright notice appear in all
|
|
|
|
# copies and that both that copyright notice and this permission
|
|
|
|
# notice appear in supporting documentation, and that the name of
|
|
|
|
# Timothy O'Malley not be used in advertising or publicity
|
|
|
|
# pertaining to distribution of the software without specific, written
|
2001-01-14 19:36:06 -04:00
|
|
|
# prior permission.
|
|
|
|
#
|
2000-08-19 10:01:19 -03:00
|
|
|
# Timothy O'Malley DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS
|
|
|
|
# SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY
|
|
|
|
# AND FITNESS, IN NO EVENT SHALL Timothy O'Malley BE LIABLE FOR
|
|
|
|
# ANY SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
|
|
|
|
# WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS,
|
|
|
|
# WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS
|
|
|
|
# ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR
|
2001-01-14 19:36:06 -04:00
|
|
|
# PERFORMANCE OF THIS SOFTWARE.
|
2000-08-19 10:01:19 -03:00
|
|
|
#
|
|
|
|
####
|
2001-01-14 19:36:06 -04:00
|
|
|
#
|
|
|
|
# Id: Cookie.py,v 2.29 2000/08/23 05:28:49 timo Exp
|
2000-08-19 10:01:19 -03:00
|
|
|
# by Timothy O'Malley <timo@alum.mit.edu>
|
|
|
|
#
|
|
|
|
# Cookie.py is a Python module for the handling of HTTP
|
|
|
|
# cookies as a Python dictionary. See RFC 2109 for more
|
|
|
|
# information on cookies.
|
|
|
|
#
|
|
|
|
# The original idea to treat Cookies as a dictionary came from
|
2000-08-24 08:52:33 -03:00
|
|
|
# Dave Mitchell (davem@magnet.com) in 1995, when he released the
|
2000-08-19 10:01:19 -03:00
|
|
|
# first version of nscookie.py.
|
|
|
|
#
|
|
|
|
####
|
|
|
|
|
2001-04-06 16:39:11 -03:00
|
|
|
r"""
|
2000-08-19 10:01:19 -03:00
|
|
|
Here's a sample session to show how to use this module.
|
|
|
|
At the moment, this is the only documentation.
|
|
|
|
|
|
|
|
The Basics
|
|
|
|
----------
|
|
|
|
|
|
|
|
Importing is easy..
|
|
|
|
|
|
|
|
>>> import Cookie
|
|
|
|
|
|
|
|
Most of the time you start by creating a cookie. Cookies come in
|
2002-12-17 14:56:26 -04:00
|
|
|
three flavors, each with slightly different encoding semantics, but
|
2000-08-19 10:01:19 -03:00
|
|
|
more on that later.
|
|
|
|
|
|
|
|
>>> C = Cookie.SimpleCookie()
|
|
|
|
>>> C = Cookie.SerialCookie()
|
|
|
|
>>> C = Cookie.SmartCookie()
|
|
|
|
|
|
|
|
[Note: Long-time users of Cookie.py will remember using
|
|
|
|
Cookie.Cookie() to create an Cookie object. Although deprecated, it
|
|
|
|
is still supported by the code. See the Backward Compatibility notes
|
|
|
|
for more information.]
|
|
|
|
|
|
|
|
Once you've created your Cookie, you can add values just as if it were
|
|
|
|
a dictionary.
|
|
|
|
|
|
|
|
>>> C = Cookie.SmartCookie()
|
|
|
|
>>> C["fig"] = "newton"
|
|
|
|
>>> C["sugar"] = "wafer"
|
2005-08-24 19:34:21 -03:00
|
|
|
>>> C.output()
|
|
|
|
'Set-Cookie: fig=newton\r\nSet-Cookie: sugar=wafer'
|
2000-08-19 10:01:19 -03:00
|
|
|
|
|
|
|
Notice that the printable representation of a Cookie is the
|
|
|
|
appropriate format for a Set-Cookie: header. This is the
|
|
|
|
default behavior. You can change the header and printed
|
2003-10-20 11:01:56 -03:00
|
|
|
attributes by using the .output() function
|
2000-08-19 10:01:19 -03:00
|
|
|
|
|
|
|
>>> C = Cookie.SmartCookie()
|
|
|
|
>>> C["rocky"] = "road"
|
|
|
|
>>> C["rocky"]["path"] = "/cookie"
|
2007-02-09 16:33:44 -04:00
|
|
|
>>> print(C.output(header="Cookie:"))
|
2005-08-24 19:34:21 -03:00
|
|
|
Cookie: rocky=road; Path=/cookie
|
2007-02-09 16:33:44 -04:00
|
|
|
>>> print(C.output(attrs=[], header="Cookie:"))
|
2005-08-24 19:34:21 -03:00
|
|
|
Cookie: rocky=road
|
2000-08-19 10:01:19 -03:00
|
|
|
|
|
|
|
The load() method of a Cookie extracts cookies from a string. In a
|
|
|
|
CGI script, you would use this method to extract the cookies from the
|
|
|
|
HTTP_COOKIE environment variable.
|
|
|
|
|
|
|
|
>>> C = Cookie.SmartCookie()
|
|
|
|
>>> C.load("chips=ahoy; vienna=finger")
|
2005-08-24 19:34:21 -03:00
|
|
|
>>> C.output()
|
|
|
|
'Set-Cookie: chips=ahoy\r\nSet-Cookie: vienna=finger'
|
2000-08-19 10:01:19 -03:00
|
|
|
|
|
|
|
The load() method is darn-tootin smart about identifying cookies
|
|
|
|
within a string. Escaped quotation marks, nested semicolons, and other
|
|
|
|
such trickeries do not confuse it.
|
|
|
|
|
|
|
|
>>> C = Cookie.SmartCookie()
|
|
|
|
>>> C.load('keebler="E=everybody; L=\\"Loves\\"; fudge=\\012;";')
|
2007-02-09 16:33:44 -04:00
|
|
|
>>> print(C)
|
2005-08-24 19:34:21 -03:00
|
|
|
Set-Cookie: keebler="E=everybody; L=\"Loves\"; fudge=\012;"
|
2000-08-19 10:01:19 -03:00
|
|
|
|
|
|
|
Each element of the Cookie also supports all of the RFC 2109
|
|
|
|
Cookie attributes. Here's an example which sets the Path
|
|
|
|
attribute.
|
|
|
|
|
|
|
|
>>> C = Cookie.SmartCookie()
|
|
|
|
>>> C["oreo"] = "doublestuff"
|
|
|
|
>>> C["oreo"]["path"] = "/"
|
2007-02-09 16:33:44 -04:00
|
|
|
>>> print(C)
|
2005-08-24 19:34:21 -03:00
|
|
|
Set-Cookie: oreo=doublestuff; Path=/
|
2000-08-19 10:01:19 -03:00
|
|
|
|
|
|
|
Each dictionary element has a 'value' attribute, which gives you
|
2001-01-14 19:36:06 -04:00
|
|
|
back the value associated with the key.
|
2000-08-19 10:01:19 -03:00
|
|
|
|
|
|
|
>>> C = Cookie.SmartCookie()
|
|
|
|
>>> C["twix"] = "none for you"
|
|
|
|
>>> C["twix"].value
|
|
|
|
'none for you'
|
|
|
|
|
|
|
|
|
|
|
|
A Bit More Advanced
|
|
|
|
-------------------
|
|
|
|
|
|
|
|
As mentioned before, there are three different flavors of Cookie
|
|
|
|
objects, each with different encoding/decoding semantics. This
|
|
|
|
section briefly discusses the differences.
|
|
|
|
|
|
|
|
SimpleCookie
|
|
|
|
|
|
|
|
The SimpleCookie expects that all values should be standard strings.
|
|
|
|
Just to be sure, SimpleCookie invokes the str() builtin to convert
|
|
|
|
the value to a string, when the values are set dictionary-style.
|
|
|
|
|
|
|
|
>>> C = Cookie.SimpleCookie()
|
|
|
|
>>> C["number"] = 7
|
|
|
|
>>> C["string"] = "seven"
|
|
|
|
>>> C["number"].value
|
|
|
|
'7'
|
|
|
|
>>> C["string"].value
|
|
|
|
'seven'
|
2005-08-24 19:34:21 -03:00
|
|
|
>>> C.output()
|
|
|
|
'Set-Cookie: number=7\r\nSet-Cookie: string=seven'
|
2000-08-19 10:01:19 -03:00
|
|
|
|
2001-01-14 19:36:06 -04:00
|
|
|
|
2000-08-19 10:01:19 -03:00
|
|
|
SerialCookie
|
|
|
|
|
|
|
|
The SerialCookie expects that all values should be serialized using
|
|
|
|
cPickle (or pickle, if cPickle isn't available). As a result of
|
|
|
|
serializing, SerialCookie can save almost any Python object to a
|
|
|
|
value, and recover the exact same object when the cookie has been
|
|
|
|
returned. (SerialCookie can yield some strange-looking cookie
|
|
|
|
values, however.)
|
|
|
|
|
|
|
|
>>> C = Cookie.SerialCookie()
|
|
|
|
>>> C["number"] = 7
|
|
|
|
>>> C["string"] = "seven"
|
|
|
|
>>> C["number"].value
|
|
|
|
7
|
|
|
|
>>> C["string"].value
|
|
|
|
'seven'
|
2006-08-17 17:24:18 -03:00
|
|
|
>>> C.output().replace('p0', 'p1') # Hack for cPickle/pickle differences
|
2005-08-24 19:34:21 -03:00
|
|
|
'Set-Cookie: number="I7\\012."\r\nSet-Cookie: string="S\'seven\'\\012p1\\012."'
|
2000-08-19 10:01:19 -03:00
|
|
|
|
|
|
|
Be warned, however, if SerialCookie cannot de-serialize a value (because
|
|
|
|
it isn't a valid pickle'd object), IT WILL RAISE AN EXCEPTION.
|
|
|
|
|
|
|
|
|
|
|
|
SmartCookie
|
|
|
|
|
|
|
|
The SmartCookie combines aspects of each of the other two flavors.
|
|
|
|
When setting a value in a dictionary-fashion, the SmartCookie will
|
|
|
|
serialize (ala cPickle) the value *if and only if* it isn't a
|
|
|
|
Python string. String objects are *not* serialized. Similarly,
|
|
|
|
when the load() method parses out values, it attempts to de-serialize
|
|
|
|
the value. If it fails, then it fallsback to treating the value
|
|
|
|
as a string.
|
|
|
|
|
|
|
|
>>> C = Cookie.SmartCookie()
|
|
|
|
>>> C["number"] = 7
|
|
|
|
>>> C["string"] = "seven"
|
|
|
|
>>> C["number"].value
|
|
|
|
7
|
|
|
|
>>> C["string"].value
|
|
|
|
'seven'
|
2005-08-24 19:34:21 -03:00
|
|
|
>>> C.output()
|
|
|
|
'Set-Cookie: number="I7\\012."\r\nSet-Cookie: string=seven'
|
2000-08-19 10:01:19 -03:00
|
|
|
|
|
|
|
|
|
|
|
Backwards Compatibility
|
|
|
|
-----------------------
|
|
|
|
|
|
|
|
In order to keep compatibilty with earlier versions of Cookie.py,
|
|
|
|
it is still possible to use Cookie.Cookie() to create a Cookie. In
|
|
|
|
fact, this simply returns a SmartCookie.
|
|
|
|
|
|
|
|
>>> C = Cookie.Cookie()
|
2007-02-09 16:33:44 -04:00
|
|
|
>>> print(C.__class__.__name__)
|
2001-04-06 16:39:11 -03:00
|
|
|
SmartCookie
|
2000-08-19 10:01:19 -03:00
|
|
|
|
|
|
|
|
|
|
|
Finis.
|
|
|
|
""" #"
|
|
|
|
# ^
|
|
|
|
# |----helps out font-lock
|
|
|
|
|
|
|
|
#
|
|
|
|
# Import our required modules
|
2001-01-14 19:36:06 -04:00
|
|
|
#
|
2001-08-02 04:15:29 -03:00
|
|
|
import string
|
2000-08-19 10:01:19 -03:00
|
|
|
|
|
|
|
try:
|
|
|
|
from cPickle import dumps, loads
|
|
|
|
except ImportError:
|
|
|
|
from pickle import dumps, loads
|
|
|
|
|
2002-12-29 12:44:31 -04:00
|
|
|
import re, warnings
|
2000-08-19 10:01:19 -03:00
|
|
|
|
2001-01-20 15:54:20 -04:00
|
|
|
__all__ = ["CookieError","BaseCookie","SimpleCookie","SerialCookie",
|
|
|
|
"SmartCookie","Cookie"]
|
2000-08-19 10:01:19 -03:00
|
|
|
|
2002-04-25 23:29:55 -03:00
|
|
|
_nulljoin = ''.join
|
2005-08-24 19:34:21 -03:00
|
|
|
_semispacejoin = '; '.join
|
2005-08-25 04:32:42 -03:00
|
|
|
_spacejoin = ' '.join
|
2002-04-25 23:29:55 -03:00
|
|
|
|
2000-08-19 10:01:19 -03:00
|
|
|
#
|
|
|
|
# Define an exception visible to External modules
|
|
|
|
#
|
|
|
|
class CookieError(Exception):
|
|
|
|
pass
|
|
|
|
|
|
|
|
|
|
|
|
# These quoting routines conform to the RFC2109 specification, which in
|
|
|
|
# turn references the character definitions from RFC2068. They provide
|
|
|
|
# a two-way quoting algorithm. Any non-text character is translated
|
|
|
|
# into a 4 character sequence: a forward-slash followed by the
|
|
|
|
# three-digit octal equivalent of the character. Any '\' or '"' is
|
|
|
|
# quoted with a preceeding '\' slash.
|
2001-01-14 19:36:06 -04:00
|
|
|
#
|
2000-08-19 10:01:19 -03:00
|
|
|
# These are taken from RFC2068 and RFC2109.
|
|
|
|
# _LegalChars is the list of chars which don't require "'s
|
|
|
|
# _Translator hash-table for fast quoting
|
|
|
|
#
|
2001-07-20 16:05:50 -03:00
|
|
|
_LegalChars = string.ascii_letters + string.digits + "!#$%&'*+-.^_`|~"
|
2000-08-19 10:01:19 -03:00
|
|
|
_Translator = {
|
|
|
|
'\000' : '\\000', '\001' : '\\001', '\002' : '\\002',
|
|
|
|
'\003' : '\\003', '\004' : '\\004', '\005' : '\\005',
|
|
|
|
'\006' : '\\006', '\007' : '\\007', '\010' : '\\010',
|
|
|
|
'\011' : '\\011', '\012' : '\\012', '\013' : '\\013',
|
|
|
|
'\014' : '\\014', '\015' : '\\015', '\016' : '\\016',
|
|
|
|
'\017' : '\\017', '\020' : '\\020', '\021' : '\\021',
|
|
|
|
'\022' : '\\022', '\023' : '\\023', '\024' : '\\024',
|
|
|
|
'\025' : '\\025', '\026' : '\\026', '\027' : '\\027',
|
|
|
|
'\030' : '\\030', '\031' : '\\031', '\032' : '\\032',
|
|
|
|
'\033' : '\\033', '\034' : '\\034', '\035' : '\\035',
|
|
|
|
'\036' : '\\036', '\037' : '\\037',
|
|
|
|
|
|
|
|
'"' : '\\"', '\\' : '\\\\',
|
|
|
|
|
|
|
|
'\177' : '\\177', '\200' : '\\200', '\201' : '\\201',
|
|
|
|
'\202' : '\\202', '\203' : '\\203', '\204' : '\\204',
|
|
|
|
'\205' : '\\205', '\206' : '\\206', '\207' : '\\207',
|
|
|
|
'\210' : '\\210', '\211' : '\\211', '\212' : '\\212',
|
|
|
|
'\213' : '\\213', '\214' : '\\214', '\215' : '\\215',
|
|
|
|
'\216' : '\\216', '\217' : '\\217', '\220' : '\\220',
|
|
|
|
'\221' : '\\221', '\222' : '\\222', '\223' : '\\223',
|
|
|
|
'\224' : '\\224', '\225' : '\\225', '\226' : '\\226',
|
|
|
|
'\227' : '\\227', '\230' : '\\230', '\231' : '\\231',
|
|
|
|
'\232' : '\\232', '\233' : '\\233', '\234' : '\\234',
|
|
|
|
'\235' : '\\235', '\236' : '\\236', '\237' : '\\237',
|
|
|
|
'\240' : '\\240', '\241' : '\\241', '\242' : '\\242',
|
|
|
|
'\243' : '\\243', '\244' : '\\244', '\245' : '\\245',
|
|
|
|
'\246' : '\\246', '\247' : '\\247', '\250' : '\\250',
|
|
|
|
'\251' : '\\251', '\252' : '\\252', '\253' : '\\253',
|
|
|
|
'\254' : '\\254', '\255' : '\\255', '\256' : '\\256',
|
|
|
|
'\257' : '\\257', '\260' : '\\260', '\261' : '\\261',
|
|
|
|
'\262' : '\\262', '\263' : '\\263', '\264' : '\\264',
|
|
|
|
'\265' : '\\265', '\266' : '\\266', '\267' : '\\267',
|
|
|
|
'\270' : '\\270', '\271' : '\\271', '\272' : '\\272',
|
|
|
|
'\273' : '\\273', '\274' : '\\274', '\275' : '\\275',
|
|
|
|
'\276' : '\\276', '\277' : '\\277', '\300' : '\\300',
|
|
|
|
'\301' : '\\301', '\302' : '\\302', '\303' : '\\303',
|
|
|
|
'\304' : '\\304', '\305' : '\\305', '\306' : '\\306',
|
|
|
|
'\307' : '\\307', '\310' : '\\310', '\311' : '\\311',
|
|
|
|
'\312' : '\\312', '\313' : '\\313', '\314' : '\\314',
|
|
|
|
'\315' : '\\315', '\316' : '\\316', '\317' : '\\317',
|
|
|
|
'\320' : '\\320', '\321' : '\\321', '\322' : '\\322',
|
|
|
|
'\323' : '\\323', '\324' : '\\324', '\325' : '\\325',
|
|
|
|
'\326' : '\\326', '\327' : '\\327', '\330' : '\\330',
|
|
|
|
'\331' : '\\331', '\332' : '\\332', '\333' : '\\333',
|
|
|
|
'\334' : '\\334', '\335' : '\\335', '\336' : '\\336',
|
|
|
|
'\337' : '\\337', '\340' : '\\340', '\341' : '\\341',
|
|
|
|
'\342' : '\\342', '\343' : '\\343', '\344' : '\\344',
|
|
|
|
'\345' : '\\345', '\346' : '\\346', '\347' : '\\347',
|
|
|
|
'\350' : '\\350', '\351' : '\\351', '\352' : '\\352',
|
|
|
|
'\353' : '\\353', '\354' : '\\354', '\355' : '\\355',
|
|
|
|
'\356' : '\\356', '\357' : '\\357', '\360' : '\\360',
|
|
|
|
'\361' : '\\361', '\362' : '\\362', '\363' : '\\363',
|
|
|
|
'\364' : '\\364', '\365' : '\\365', '\366' : '\\366',
|
|
|
|
'\367' : '\\367', '\370' : '\\370', '\371' : '\\371',
|
|
|
|
'\372' : '\\372', '\373' : '\\373', '\374' : '\\374',
|
|
|
|
'\375' : '\\375', '\376' : '\\376', '\377' : '\\377'
|
|
|
|
}
|
|
|
|
|
Merge current trunk into p3yk. This includes the PyNumber_Index API change,
which unfortunately means the errors from the bytes type change somewhat:
bytes([300]) still raises a ValueError, but bytes([10**100]) now raises a
TypeError (either that, or bytes(1.0) also raises a ValueError --
PyNumber_AsSsize_t() can only raise one type of exception.)
Merged revisions 51188-51433 via svnmerge from
svn+ssh://pythondev@svn.python.org/python/trunk
........
r51189 | kurt.kaiser | 2006-08-10 19:11:09 +0200 (Thu, 10 Aug 2006) | 4 lines
Retrieval of previous shell command was not always preserving indentation
since 1.2a1) Patch 1528468 Tal Einat.
........
r51190 | guido.van.rossum | 2006-08-10 19:41:07 +0200 (Thu, 10 Aug 2006) | 3 lines
Chris McDonough's patch to defend against certain DoS attacks on FieldStorage.
SF bug #1112549.
........
r51191 | guido.van.rossum | 2006-08-10 19:42:50 +0200 (Thu, 10 Aug 2006) | 2 lines
News item for SF bug 1112549.
........
r51192 | guido.van.rossum | 2006-08-10 20:09:25 +0200 (Thu, 10 Aug 2006) | 2 lines
Fix title -- it's rc1, not beta3.
........
r51194 | martin.v.loewis | 2006-08-10 21:04:00 +0200 (Thu, 10 Aug 2006) | 3 lines
Update dangling references to the 3.2 database to
mention that this is UCD 4.1 now.
........
r51195 | tim.peters | 2006-08-11 00:45:34 +0200 (Fri, 11 Aug 2006) | 6 lines
Followup to bug #1069160.
PyThreadState_SetAsyncExc(): internal correctness changes wrt
refcount safety and deadlock avoidance. Also added a basic test
case (relying on ctypes) and repaired the docs.
........
r51196 | tim.peters | 2006-08-11 00:48:45 +0200 (Fri, 11 Aug 2006) | 2 lines
Whitespace normalization.
........
r51197 | tim.peters | 2006-08-11 01:22:13 +0200 (Fri, 11 Aug 2006) | 5 lines
Whitespace normalization broke test_cgi, because a line
of quoted test data relied on preserving a single trailing
blank. Changed the string from raw to regular, and forced
in the trailing blank via an explicit \x20 escape.
........
r51198 | tim.peters | 2006-08-11 02:49:01 +0200 (Fri, 11 Aug 2006) | 10 lines
test_PyThreadState_SetAsyncExc(): This is failing on some
64-bit boxes. I have no idea what the ctypes docs mean
by "integers", and blind-guessing here that it intended to
mean the signed C "int" type, in which case perhaps I can
repair this by feeding the thread id argument to type
ctypes.c_long().
Also made the worker thread daemonic, so it doesn't hang
Python shutdown if the test continues to fail.
........
r51199 | tim.peters | 2006-08-11 05:49:10 +0200 (Fri, 11 Aug 2006) | 6 lines
force_test_exit(): This has been completely ineffective
at stopping test_signal from hanging forever on the Tru64
buildbot. That could be because there's no such thing as
signal.SIGALARM. Changed to the idiotic (but standard)
signal.SIGALRM instead, and added some more debug output.
........
r51202 | neal.norwitz | 2006-08-11 08:09:41 +0200 (Fri, 11 Aug 2006) | 6 lines
Fix the failures on cygwin (2006-08-10 fixed the actual locking issue).
The first hunk changes the colon to an ! like other Windows variants.
We need to always wait on the child so the lock gets released and
no other tests fail. This is the try/finally in the second hunk.
........
r51205 | georg.brandl | 2006-08-11 09:15:38 +0200 (Fri, 11 Aug 2006) | 3 lines
Add Chris McDonough (latest cgi.py patch)
........
r51206 | georg.brandl | 2006-08-11 09:26:10 +0200 (Fri, 11 Aug 2006) | 3 lines
logging's atexit hook now runs even if the rest of the module has
already been cleaned up.
........
r51212 | thomas.wouters | 2006-08-11 17:02:39 +0200 (Fri, 11 Aug 2006) | 4 lines
Add ignore of *.pyc and *.pyo to Lib/xml/etree/.
........
r51215 | thomas.heller | 2006-08-11 21:55:35 +0200 (Fri, 11 Aug 2006) | 7 lines
When a ctypes C callback function is called, zero out the result
storage before converting the result to C data. See the comment in
the code for details.
Provide a better context for errors when the conversion of a callback
function's result cannot be converted.
........
r51218 | neal.norwitz | 2006-08-12 03:43:40 +0200 (Sat, 12 Aug 2006) | 6 lines
Klocwork made another run and found a bunch more problems.
This is the first batch of fixes that should be easy to verify based on context.
This fixes problem numbers: 220 (ast), 323-324 (symtable),
321-322 (structseq), 215 (array), 210 (hotshot), 182 (codecs), 209 (etree).
........
r51219 | neal.norwitz | 2006-08-12 03:45:47 +0200 (Sat, 12 Aug 2006) | 9 lines
Even though _Py_Mangle() isn't truly public anyone can call it and
there was no verification that privateobj was a PyString. If it wasn't
a string, this could have allowed a NULL pointer to creep in below and crash.
I wonder if this should be PyString_CheckExact? Must identifiers be strings
or can they be subclasses?
Klocwork #275
........
r51220 | neal.norwitz | 2006-08-12 03:46:42 +0200 (Sat, 12 Aug 2006) | 5 lines
It's highly unlikely, though possible for PyEval_Get*() to return NULLs.
So be safe and do an XINCREF.
Klocwork # 221-222.
........
r51221 | neal.norwitz | 2006-08-12 03:47:59 +0200 (Sat, 12 Aug 2006) | 7 lines
This code is actually not used unless WITHOUT_COMPLEX is defined.
However, there was no error checking that PyFloat_FromDouble returned
a valid pointer. I believe this change is correct as it seemed
to follow other code in the area.
Klocwork # 292.
........
r51222 | neal.norwitz | 2006-08-12 03:49:12 +0200 (Sat, 12 Aug 2006) | 5 lines
Handle NULL nodes while parsing. I'm not entirely sure this is correct.
There might be something else that needs to be done to setup the error.
Klocwork #295.
........
r51223 | neal.norwitz | 2006-08-12 03:50:38 +0200 (Sat, 12 Aug 2006) | 6 lines
If _stat_float_times is false, we will try to INCREF ival which could be NULL.
Return early in that case. The caller checks for PyErr_Occurred so this
should be ok.
Klocwork #297
........
r51224 | neal.norwitz | 2006-08-12 03:51:12 +0200 (Sat, 12 Aug 2006) | 3 lines
Move the assert which checks for a NULL pointer first.
Klocwork #274.
........
r51225 | neal.norwitz | 2006-08-12 03:53:28 +0200 (Sat, 12 Aug 2006) | 5 lines
Try to handle a malloc failure. I'm not entirely sure this is correct.
There might be something else we need to do to handle the exception.
Klocwork # 212-213
........
r51226 | neal.norwitz | 2006-08-12 03:57:47 +0200 (Sat, 12 Aug 2006) | 6 lines
I'm not sure why this code allocates this string for the error message.
I think it would be better to always use snprintf and have the format
limit the size of the name appropriately (like %.200s).
Klocwork #340
........
r51227 | neal.norwitz | 2006-08-12 04:06:34 +0200 (Sat, 12 Aug 2006) | 3 lines
Check returned pointer is valid.
Klocwork #233
........
r51228 | neal.norwitz | 2006-08-12 04:12:30 +0200 (Sat, 12 Aug 2006) | 1 line
Whoops, how did that get in there. :-) Revert all the parts of 51227 that were not supposed to go it. Only Modules/_ctypes/cfields.c was supposed to be changed
........
r51229 | neal.norwitz | 2006-08-12 04:33:36 +0200 (Sat, 12 Aug 2006) | 4 lines
Don't deref v if it's NULL.
Klocwork #214
........
r51230 | neal.norwitz | 2006-08-12 05:16:54 +0200 (Sat, 12 Aug 2006) | 5 lines
Check return of PyMem_MALLOC (garbage) is non-NULL.
Check seq in both portions of if/else.
Klocwork #289-290.
........
r51231 | neal.norwitz | 2006-08-12 05:17:41 +0200 (Sat, 12 Aug 2006) | 4 lines
PyModule_GetDict() can fail, produce fatal errors if this happens on startup.
Klocwork #298-299.
........
r51232 | neal.norwitz | 2006-08-12 05:18:50 +0200 (Sat, 12 Aug 2006) | 5 lines
Verify verdat which is returned from malloc is not NULL.
Ensure we don't pass NULL to free.
Klocwork #306 (at least the first part, checking malloc)
........
r51233 | tim.peters | 2006-08-12 06:42:47 +0200 (Sat, 12 Aug 2006) | 35 lines
test_signal: Signal handling on the Tru64 buildbot
appears to be utterly insane. Plug some theoretical
insecurities in the test script:
- Verify that the SIGALRM handler was actually installed.
- Don't call alarm() before the handler is installed.
- Move everything that can fail inside the try/finally,
so the test cleans up after itself more often.
- Try sending all the expected signals in
force_test_exit(), not just SIGALRM. Since that was
fixed to actually send SIGALRM (instead of invisibly
dying with an AttributeError), we've seen that sending
SIGALRM alone does not stop this from hanging.
- Move the "kill the child" business into the finally
clause, so the child doesn't survive test failure
to send SIGALRM to other tests later (there are also
baffling SIGALRM-related failures in test_socket).
- Cancel the alarm in the finally clause -- if the
test dies early, we again don't want SIGALRM showing
up to confuse a later test.
Alas, this still relies on timing luck wrt the spawned
script that sends the test signals, but it's hard to see
how waiting for seconds can so often be so unlucky.
test_threadedsignals: curiously, this test never fails
on Tru64, but doesn't normally signal SIGALRM. Anyway,
fixed an obvious (but probably inconsequential) logic
error.
........
r51234 | tim.peters | 2006-08-12 07:17:41 +0200 (Sat, 12 Aug 2006) | 8 lines
Ah, fudge. One of the prints here actually "shouldn't be"
protected by "if verbose:", which caused the test to fail on
all non-Windows boxes.
Note that I deliberately didn't convert this to unittest yet,
because I expect it would be even harder to debug this on Tru64
after conversion.
........
r51235 | georg.brandl | 2006-08-12 10:32:02 +0200 (Sat, 12 Aug 2006) | 3 lines
Repair logging test spew caused by rev. 51206.
........
r51236 | neal.norwitz | 2006-08-12 19:03:09 +0200 (Sat, 12 Aug 2006) | 8 lines
Patch #1538606, Patch to fix __index__() clipping.
I modified this patch some by fixing style, some error checking, and adding
XXX comments. This patch requires review and some changes are to be expected.
I'm checking in now to get the greatest possible review and establish a
baseline for moving forward. I don't want this to hold up release if possible.
........
r51238 | neal.norwitz | 2006-08-12 20:44:06 +0200 (Sat, 12 Aug 2006) | 10 lines
Fix a couple of bugs exposed by the new __index__ code. The 64-bit buildbots
were failing due to inappropriate clipping of numbers larger than 2**31
with new-style classes. (typeobject.c) In reviewing the code for classic
classes, there were 2 problems. Any negative value return could be returned.
Always return -1 if there was an error. Also make the checks similar
with the new-style classes. I believe this is correct for 32 and 64 bit
boxes, including Windows64.
Add a test of classic classes too.
........
r51240 | neal.norwitz | 2006-08-13 02:20:49 +0200 (Sun, 13 Aug 2006) | 1 line
SF bug #1539336, distutils example code missing
........
r51245 | neal.norwitz | 2006-08-13 20:10:10 +0200 (Sun, 13 Aug 2006) | 6 lines
Move/copy assert for tstate != NULL before first use.
Verify that PyEval_Get{Globals,Locals} returned valid pointers.
Klocwork 231-232
........
r51246 | neal.norwitz | 2006-08-13 20:10:28 +0200 (Sun, 13 Aug 2006) | 5 lines
Handle a whole lot of failures from PyString_FromInternedString().
Should fix most of Klocwork 234-272.
........
r51247 | neal.norwitz | 2006-08-13 20:10:47 +0200 (Sun, 13 Aug 2006) | 8 lines
cpathname could be NULL if it was longer than MAXPATHLEN. Don't try
to write the .pyc to NULL.
Check results of PyList_GetItem() and PyModule_GetDict() are not NULL.
Klocwork 282, 283, 285
........
r51248 | neal.norwitz | 2006-08-13 20:11:08 +0200 (Sun, 13 Aug 2006) | 6 lines
Fix segfault when doing string formatting on subclasses of long if
__oct__, __hex__ don't return a string.
Klocwork 308
........
r51250 | neal.norwitz | 2006-08-13 20:11:27 +0200 (Sun, 13 Aug 2006) | 5 lines
Check return result of PyModule_GetDict().
Fix a bunch of refleaks in the init of the module. This would only be found
when running python -v.
........
r51251 | neal.norwitz | 2006-08-13 20:11:43 +0200 (Sun, 13 Aug 2006) | 5 lines
Handle malloc and fopen failures more gracefully.
Klocwork 180-181
........
r51252 | neal.norwitz | 2006-08-13 20:12:03 +0200 (Sun, 13 Aug 2006) | 7 lines
It's very unlikely, though possible that source is not a string. Verify
that PyString_AsString() returns a valid pointer. (The problem can
arise when zlib.decompress doesn't return a string.)
Klocwork 346
........
r51253 | neal.norwitz | 2006-08-13 20:12:26 +0200 (Sun, 13 Aug 2006) | 5 lines
Handle failures from lookup.
Klocwork 341-342
........
r51254 | neal.norwitz | 2006-08-13 20:12:45 +0200 (Sun, 13 Aug 2006) | 6 lines
Handle failure from PyModule_GetDict() (Klocwork 208).
Fix a bunch of refleaks in the init of the module. This would only be found
when running python -v.
........
r51255 | neal.norwitz | 2006-08-13 20:13:02 +0200 (Sun, 13 Aug 2006) | 4 lines
Really address the issue of where to place the assert for leftblock.
(Followup of Klocwork 274)
........
r51256 | neal.norwitz | 2006-08-13 20:13:36 +0200 (Sun, 13 Aug 2006) | 4 lines
Handle malloc failure.
Klocwork 281
........
r51258 | neal.norwitz | 2006-08-13 20:40:39 +0200 (Sun, 13 Aug 2006) | 4 lines
Handle alloca failures.
Klocwork 225-228
........
r51259 | neal.norwitz | 2006-08-13 20:41:15 +0200 (Sun, 13 Aug 2006) | 1 line
Get rid of compiler warning
........
r51261 | neal.norwitz | 2006-08-14 02:51:15 +0200 (Mon, 14 Aug 2006) | 1 line
Ignore pgen.exe and kill_python.exe for cygwin
........
r51262 | neal.norwitz | 2006-08-14 02:59:03 +0200 (Mon, 14 Aug 2006) | 4 lines
Can't return NULL from a void function. If there is a memory error,
about the best we can do is call PyErr_WriteUnraisable and go on.
We won't be able to do the call below either, so verify delstr is valid.
........
r51263 | neal.norwitz | 2006-08-14 03:49:54 +0200 (Mon, 14 Aug 2006) | 1 line
Update purify doc some.
........
r51264 | thomas.heller | 2006-08-14 09:13:05 +0200 (Mon, 14 Aug 2006) | 2 lines
Remove unused, buggy test function.
Fixes klockwork issue #207.
........
r51265 | thomas.heller | 2006-08-14 09:14:09 +0200 (Mon, 14 Aug 2006) | 2 lines
Check for NULL return value from new_CArgObject().
Fixes klockwork issues #183, #184, #185.
........
r51266 | thomas.heller | 2006-08-14 09:50:14 +0200 (Mon, 14 Aug 2006) | 2 lines
Check for NULL return value of GenericCData_new().
Fixes klockwork issues #188, #189.
........
r51274 | thomas.heller | 2006-08-14 12:02:24 +0200 (Mon, 14 Aug 2006) | 2 lines
Revert the change that tries to zero out a closure's result storage
area because the size if unknown in source/callproc.c.
........
r51276 | marc-andre.lemburg | 2006-08-14 12:55:19 +0200 (Mon, 14 Aug 2006) | 11 lines
Slightly revised version of patch #1538956:
Replace UnicodeDecodeErrors raised during == and !=
compares of Unicode and other objects with a new
UnicodeWarning.
All other comparisons continue to raise exceptions.
Exceptions other than UnicodeDecodeErrors are also left
untouched.
........
r51277 | thomas.heller | 2006-08-14 13:17:48 +0200 (Mon, 14 Aug 2006) | 13 lines
Apply the patch #1532975 plus ideas from the patch #1533481.
ctypes instances no longer have the internal and undocumented
'_as_parameter_' attribute which was used to adapt them to foreign
function calls; this mechanism is replaced by a function pointer in
the type's stgdict.
In the 'from_param' class methods, try the _as_parameter_ attribute if
other conversions are not possible.
This makes the documented _as_parameter_ mechanism work as intended.
Change the ctypes version number to 1.0.1.
........
r51278 | marc-andre.lemburg | 2006-08-14 13:44:34 +0200 (Mon, 14 Aug 2006) | 3 lines
Readd NEWS items that were accidentally removed by r51276.
........
r51279 | georg.brandl | 2006-08-14 14:36:06 +0200 (Mon, 14 Aug 2006) | 3 lines
Improve markup in PyUnicode_RichCompare.
........
r51280 | marc-andre.lemburg | 2006-08-14 14:57:27 +0200 (Mon, 14 Aug 2006) | 3 lines
Correct an accidentally removed previous patch.
........
r51281 | thomas.heller | 2006-08-14 18:17:41 +0200 (Mon, 14 Aug 2006) | 3 lines
Patch #1536908: Add support for AMD64 / OpenBSD.
Remove the -no-stack-protector compiler flag for OpenBSD
as it has been reported to be unneeded.
........
r51282 | thomas.heller | 2006-08-14 18:20:04 +0200 (Mon, 14 Aug 2006) | 1 line
News item for rev 51281.
........
r51283 | georg.brandl | 2006-08-14 22:25:39 +0200 (Mon, 14 Aug 2006) | 3 lines
Fix refleak introduced in rev. 51248.
........
r51284 | georg.brandl | 2006-08-14 23:34:08 +0200 (Mon, 14 Aug 2006) | 5 lines
Make tabnanny recognize IndentationErrors raised by tokenize.
Add a test to test_inspect to make sure indented source
is recognized correctly. (fixes #1224621)
........
r51285 | georg.brandl | 2006-08-14 23:42:55 +0200 (Mon, 14 Aug 2006) | 3 lines
Patch #1535500: fix segfault in BZ2File.writelines and make sure it
raises the correct exceptions.
........
r51287 | georg.brandl | 2006-08-14 23:45:32 +0200 (Mon, 14 Aug 2006) | 3 lines
Add an additional test: BZ2File write methods should raise IOError
when file is read-only.
........
r51289 | georg.brandl | 2006-08-14 23:55:28 +0200 (Mon, 14 Aug 2006) | 3 lines
Patch #1536071: trace.py should now find the full module name of a
file correctly even on Windows.
........
r51290 | georg.brandl | 2006-08-15 00:01:24 +0200 (Tue, 15 Aug 2006) | 3 lines
Cookie.py shouldn't "bogusly" use string._idmap.
........
r51291 | georg.brandl | 2006-08-15 00:10:24 +0200 (Tue, 15 Aug 2006) | 3 lines
Patch #1511317: don't crash on invalid hostname info
........
r51292 | tim.peters | 2006-08-15 02:25:04 +0200 (Tue, 15 Aug 2006) | 2 lines
Whitespace normalization.
........
r51293 | neal.norwitz | 2006-08-15 06:14:57 +0200 (Tue, 15 Aug 2006) | 3 lines
Georg fixed one of my bugs, so I'll repay him with 2 NEWS entries.
Now we're even. :-)
........
r51295 | neal.norwitz | 2006-08-15 06:58:28 +0200 (Tue, 15 Aug 2006) | 8 lines
Fix the test for SocketServer so it should pass on cygwin and not fail
sporadically on other platforms. This is really a band-aid that doesn't
fix the underlying issue in SocketServer. It's not clear if it's worth
it to fix SocketServer, however, I opened a bug to track it:
http://python.org/sf/1540386
........
r51296 | neal.norwitz | 2006-08-15 06:59:30 +0200 (Tue, 15 Aug 2006) | 3 lines
Update the docstring to use a version a little newer than 1999. This was
taken from a Debian patch. Should we update the version for each release?
........
r51298 | neal.norwitz | 2006-08-15 08:29:03 +0200 (Tue, 15 Aug 2006) | 2 lines
Subclasses of int/long are allowed to define an __index__.
........
r51300 | thomas.heller | 2006-08-15 15:07:21 +0200 (Tue, 15 Aug 2006) | 1 line
Check for NULL return value from new_CArgObject calls.
........
r51303 | kurt.kaiser | 2006-08-16 05:15:26 +0200 (Wed, 16 Aug 2006) | 2 lines
The 'with' statement is now a Code Context block opener
........
r51304 | anthony.baxter | 2006-08-16 05:42:26 +0200 (Wed, 16 Aug 2006) | 1 line
preparing for 2.5c1
........
r51305 | anthony.baxter | 2006-08-16 05:58:37 +0200 (Wed, 16 Aug 2006) | 1 line
preparing for 2.5c1 - no, really this time
........
r51306 | kurt.kaiser | 2006-08-16 07:01:42 +0200 (Wed, 16 Aug 2006) | 9 lines
Patch #1540892: site.py Quitter() class attempts to close sys.stdin
before raising SystemExit, allowing IDLE to honor quit() and exit().
M Lib/site.py
M Lib/idlelib/PyShell.py
M Lib/idlelib/CREDITS.txt
M Lib/idlelib/NEWS.txt
M Misc/NEWS
........
r51307 | ka-ping.yee | 2006-08-16 09:02:50 +0200 (Wed, 16 Aug 2006) | 6 lines
Update code and tests to support the 'bytes_le' attribute (for
little-endian byte order on Windows), and to work around clocks
with low resolution yielding duplicate UUIDs.
Anthony Baxter has approved this change.
........
r51308 | kurt.kaiser | 2006-08-16 09:04:17 +0200 (Wed, 16 Aug 2006) | 2 lines
Get quit() and exit() to work cleanly when not using subprocess.
........
r51309 | marc-andre.lemburg | 2006-08-16 10:13:26 +0200 (Wed, 16 Aug 2006) | 2 lines
Revert to having static version numbers again.
........
r51310 | martin.v.loewis | 2006-08-16 14:55:10 +0200 (Wed, 16 Aug 2006) | 2 lines
Build _hashlib on Windows. Build OpenSSL with masm assembler code.
Fixes #1535502.
........
r51311 | thomas.heller | 2006-08-16 15:03:11 +0200 (Wed, 16 Aug 2006) | 6 lines
Add commented assert statements to check that the result of
PyObject_stgdict() and PyType_stgdict() calls are non-NULL before
dereferencing the result. Hopefully this fixes what klocwork is
complaining about.
Fix a few other nits as well.
........
r51312 | anthony.baxter | 2006-08-16 15:08:25 +0200 (Wed, 16 Aug 2006) | 1 line
news entry for 51307
........
r51313 | andrew.kuchling | 2006-08-16 15:22:20 +0200 (Wed, 16 Aug 2006) | 1 line
Add UnicodeWarning
........
r51314 | andrew.kuchling | 2006-08-16 15:41:52 +0200 (Wed, 16 Aug 2006) | 1 line
Bump document version to 1.0; remove pystone paragraph
........
r51315 | andrew.kuchling | 2006-08-16 15:51:32 +0200 (Wed, 16 Aug 2006) | 1 line
Link to docs; remove an XXX comment
........
r51316 | martin.v.loewis | 2006-08-16 15:58:51 +0200 (Wed, 16 Aug 2006) | 1 line
Make cl build step compile-only (/c). Remove libs from source list.
........
r51317 | thomas.heller | 2006-08-16 16:07:44 +0200 (Wed, 16 Aug 2006) | 5 lines
The __repr__ method of a NULL py_object does no longer raise an
exception. Remove a stray '?' character from the exception text
when the value is retrieved of such an object.
Includes tests.
........
r51318 | andrew.kuchling | 2006-08-16 16:18:23 +0200 (Wed, 16 Aug 2006) | 1 line
Update bug/patch counts
........
r51319 | andrew.kuchling | 2006-08-16 16:21:14 +0200 (Wed, 16 Aug 2006) | 1 line
Wording/typo fixes
........
r51320 | thomas.heller | 2006-08-16 17:10:12 +0200 (Wed, 16 Aug 2006) | 9 lines
Remove the special casing of Py_None when converting the return value
of the Python part of a callback function to C. If it cannot be
converted, call PyErr_WriteUnraisable with the exception we got.
Before, arbitrary data has been passed to the calling C code in this
case.
(I'm not really sure the NEWS entry is understandable, but I cannot
find better words)
........
r51321 | marc-andre.lemburg | 2006-08-16 18:11:01 +0200 (Wed, 16 Aug 2006) | 2 lines
Add NEWS item mentioning the reverted distutils version number patch.
........
r51322 | fredrik.lundh | 2006-08-16 18:47:07 +0200 (Wed, 16 Aug 2006) | 5 lines
SF#1534630
ignore data that arrives before the opening start tag
........
r51324 | andrew.kuchling | 2006-08-16 19:11:18 +0200 (Wed, 16 Aug 2006) | 1 line
Grammar fix
........
r51328 | thomas.heller | 2006-08-16 20:02:11 +0200 (Wed, 16 Aug 2006) | 12 lines
Tutorial:
Clarify somewhat how parameters are passed to functions
(especially explain what integer means).
Correct the table - Python integers and longs can both be used.
Further clarification to the table comparing ctypes types, Python
types, and C types.
Reference:
Replace integer by C ``int`` where it makes sense.
........
r51329 | kurt.kaiser | 2006-08-16 23:45:59 +0200 (Wed, 16 Aug 2006) | 8 lines
File menu hotkeys: there were three 'p' assignments. Reassign the
'Save Copy As' and 'Print' hotkeys to 'y' and 't'. Change the
Shell menu hotkey from 's' to 'l'.
M Bindings.py
M PyShell.py
M NEWS.txt
........
r51330 | neil.schemenauer | 2006-08-17 01:38:05 +0200 (Thu, 17 Aug 2006) | 3 lines
Fix a bug in the ``compiler`` package that caused invalid code to be
generated for generator expressions.
........
r51342 | martin.v.loewis | 2006-08-17 21:19:32 +0200 (Thu, 17 Aug 2006) | 3 lines
Merge 51340 and 51341 from 2.5 branch:
Leave tk build directory to restore original path.
Invoke debug mk1mf.pl after running Configure.
........
r51354 | martin.v.loewis | 2006-08-18 05:47:18 +0200 (Fri, 18 Aug 2006) | 3 lines
Bug #1541863: uuid.uuid1 failed to generate unique identifiers
on systems with low clock resolution.
........
r51355 | neal.norwitz | 2006-08-18 05:57:54 +0200 (Fri, 18 Aug 2006) | 1 line
Add template for 2.6 on HEAD
........
r51356 | neal.norwitz | 2006-08-18 06:01:38 +0200 (Fri, 18 Aug 2006) | 1 line
More post-release wibble
........
r51357 | neal.norwitz | 2006-08-18 06:58:33 +0200 (Fri, 18 Aug 2006) | 1 line
Try to get Windows bots working again
........
r51358 | neal.norwitz | 2006-08-18 07:10:00 +0200 (Fri, 18 Aug 2006) | 1 line
Try to get Windows bots working again. Take 2
........
r51359 | neal.norwitz | 2006-08-18 07:39:20 +0200 (Fri, 18 Aug 2006) | 1 line
Try to get Unix bots install working again.
........
r51360 | neal.norwitz | 2006-08-18 07:41:46 +0200 (Fri, 18 Aug 2006) | 1 line
Set version to 2.6a0, seems more consistent.
........
r51362 | neal.norwitz | 2006-08-18 08:14:52 +0200 (Fri, 18 Aug 2006) | 1 line
More version wibble
........
r51364 | georg.brandl | 2006-08-18 09:27:59 +0200 (Fri, 18 Aug 2006) | 4 lines
Bug #1541682: Fix example in the "Refcount details" API docs.
Additionally, remove a faulty example showing PySequence_SetItem applied
to a newly created list object and add notes that this isn't a good idea.
........
r51366 | anthony.baxter | 2006-08-18 09:29:02 +0200 (Fri, 18 Aug 2006) | 3 lines
Updating IDLE's version number to match Python's (as per python-dev
discussion).
........
r51367 | anthony.baxter | 2006-08-18 09:30:07 +0200 (Fri, 18 Aug 2006) | 1 line
RPM specfile updates
........
r51368 | georg.brandl | 2006-08-18 09:35:47 +0200 (Fri, 18 Aug 2006) | 2 lines
Typo in tp_clear docs.
........
r51378 | andrew.kuchling | 2006-08-18 15:57:13 +0200 (Fri, 18 Aug 2006) | 1 line
Minor edits
........
r51379 | thomas.heller | 2006-08-18 16:38:46 +0200 (Fri, 18 Aug 2006) | 6 lines
Add asserts to check for 'impossible' NULL values, with comments.
In one place where I'n not 1000% sure about the non-NULL, raise
a RuntimeError for safety.
This should fix the klocwork issues that Neal sent me. If so,
it should be applied to the release25-maint branch also.
........
r51400 | neal.norwitz | 2006-08-19 06:22:33 +0200 (Sat, 19 Aug 2006) | 5 lines
Move initialization of interned strings to before allocating the
object so we don't leak op. (Fixes an earlier patch to this code)
Klockwork #350
........
r51401 | neal.norwitz | 2006-08-19 06:23:04 +0200 (Sat, 19 Aug 2006) | 4 lines
Move assert to after NULL check, otherwise we deref NULL in the assert.
Klocwork #307
........
r51402 | neal.norwitz | 2006-08-19 06:25:29 +0200 (Sat, 19 Aug 2006) | 2 lines
SF #1542693: Remove semi-colon at end of PyImport_ImportModuleEx macro
........
r51403 | neal.norwitz | 2006-08-19 06:28:55 +0200 (Sat, 19 Aug 2006) | 6 lines
Move initialization to after the asserts for non-NULL values.
Klocwork 286-287.
(I'm not backporting this, but if someone wants to, feel free.)
........
r51404 | neal.norwitz | 2006-08-19 06:52:03 +0200 (Sat, 19 Aug 2006) | 6 lines
Handle PyString_FromInternedString() failing (unlikely, but possible).
Klocwork #325
(I'm not backporting this, but if someone wants to, feel free.)
........
r51416 | georg.brandl | 2006-08-20 15:15:39 +0200 (Sun, 20 Aug 2006) | 2 lines
Patch #1542948: fix urllib2 header casing issue. With new test.
........
r51428 | jeremy.hylton | 2006-08-21 18:19:37 +0200 (Mon, 21 Aug 2006) | 3 lines
Move peephole optimizer to separate file.
........
r51429 | jeremy.hylton | 2006-08-21 18:20:29 +0200 (Mon, 21 Aug 2006) | 2 lines
Move peephole optimizer to separate file. (Forgot .h in previous checkin.)
........
r51432 | neal.norwitz | 2006-08-21 19:59:46 +0200 (Mon, 21 Aug 2006) | 5 lines
Fix bug #1543303, tarfile adds padding that breaks gunzip.
Patch # 1543897.
Will backport to 2.5
........
r51433 | neal.norwitz | 2006-08-21 20:01:30 +0200 (Mon, 21 Aug 2006) | 2 lines
Add assert to make Klocwork happy (#276)
........
2006-08-21 16:07:27 -03:00
|
|
|
_idmap = ''.join(chr(x) for x in xrange(256))
|
|
|
|
|
2007-04-17 05:48:32 -03:00
|
|
|
def _quote(str, LegalChars=_LegalChars, idmap=_idmap):
|
2000-08-19 10:01:19 -03:00
|
|
|
#
|
|
|
|
# If the string does not need to be double-quoted,
|
|
|
|
# then just return the string. Otherwise, surround
|
|
|
|
# the string in doublequotes and precede quote (with a \)
|
|
|
|
# special characters.
|
|
|
|
#
|
2007-04-17 05:48:32 -03:00
|
|
|
if "" == str.translate(idmap, LegalChars):
|
2000-08-24 11:40:35 -03:00
|
|
|
return str
|
2000-08-19 10:01:19 -03:00
|
|
|
else:
|
2002-04-25 23:29:55 -03:00
|
|
|
return '"' + _nulljoin( map(_Translator.get, str, str) ) + '"'
|
2000-08-19 10:01:19 -03:00
|
|
|
# end _quote
|
|
|
|
|
|
|
|
|
|
|
|
_OctalPatt = re.compile(r"\\[0-3][0-7][0-7]")
|
|
|
|
_QuotePatt = re.compile(r"[\\].")
|
|
|
|
|
2002-04-25 23:29:55 -03:00
|
|
|
def _unquote(str):
|
2000-08-19 10:01:19 -03:00
|
|
|
# If there aren't any doublequotes,
|
|
|
|
# then there can't be any special characters. See RFC 2109.
|
|
|
|
if len(str) < 2:
|
|
|
|
return str
|
|
|
|
if str[0] != '"' or str[-1] != '"':
|
|
|
|
return str
|
|
|
|
|
|
|
|
# We have to assume that we must decode this string.
|
|
|
|
# Down to work.
|
|
|
|
|
|
|
|
# Remove the "s
|
|
|
|
str = str[1:-1]
|
2000-08-24 11:40:35 -03:00
|
|
|
|
2000-08-19 10:01:19 -03:00
|
|
|
# Check for special sequences. Examples:
|
|
|
|
# \012 --> \n
|
|
|
|
# \" --> "
|
|
|
|
#
|
|
|
|
i = 0
|
|
|
|
n = len(str)
|
|
|
|
res = []
|
|
|
|
while 0 <= i < n:
|
|
|
|
Omatch = _OctalPatt.search(str, i)
|
|
|
|
Qmatch = _QuotePatt.search(str, i)
|
|
|
|
if not Omatch and not Qmatch: # Neither matched
|
|
|
|
res.append(str[i:])
|
|
|
|
break
|
|
|
|
# else:
|
|
|
|
j = k = -1
|
|
|
|
if Omatch: j = Omatch.start(0)
|
|
|
|
if Qmatch: k = Qmatch.start(0)
|
|
|
|
if Qmatch and ( not Omatch or k < j ): # QuotePatt matched
|
|
|
|
res.append(str[i:k])
|
|
|
|
res.append(str[k+1])
|
|
|
|
i = k+2
|
|
|
|
else: # OctalPatt matched
|
|
|
|
res.append(str[i:j])
|
2002-04-25 23:29:55 -03:00
|
|
|
res.append( chr( int(str[j+1:j+4], 8) ) )
|
2000-08-19 10:01:19 -03:00
|
|
|
i = j+4
|
2002-04-25 23:29:55 -03:00
|
|
|
return _nulljoin(res)
|
2000-08-19 10:01:19 -03:00
|
|
|
# end _unquote
|
|
|
|
|
|
|
|
# The _getdate() routine is used to set the expiration time in
|
|
|
|
# the cookie's HTTP header. By default, _getdate() returns the
|
2001-01-14 19:36:06 -04:00
|
|
|
# current time in the appropriate "expires" format for a
|
2000-08-19 10:01:19 -03:00
|
|
|
# Set-Cookie header. The one optional argument is an offset from
|
|
|
|
# now, in seconds. For example, an offset of -3600 means "one hour ago".
|
|
|
|
# The offset may be a floating point number.
|
|
|
|
#
|
|
|
|
|
|
|
|
_weekdayname = ['Mon', 'Tue', 'Wed', 'Thu', 'Fri', 'Sat', 'Sun']
|
|
|
|
|
|
|
|
_monthname = [None,
|
|
|
|
'Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun',
|
|
|
|
'Jul', 'Aug', 'Sep', 'Oct', 'Nov', 'Dec']
|
|
|
|
|
|
|
|
def _getdate(future=0, weekdayname=_weekdayname, monthname=_monthname):
|
|
|
|
from time import gmtime, time
|
|
|
|
now = time()
|
|
|
|
year, month, day, hh, mm, ss, wd, y, z = gmtime(now + future)
|
|
|
|
return "%s, %02d-%3s-%4d %02d:%02d:%02d GMT" % \
|
|
|
|
(weekdayname[wd], day, monthname[month], year, hh, mm, ss)
|
|
|
|
|
|
|
|
|
|
|
|
#
|
|
|
|
# A class to hold ONE key,value pair.
|
|
|
|
# In a cookie, each such pair may have several attributes.
|
|
|
|
# so this class is used to keep the attributes associated
|
|
|
|
# with the appropriate key,value pair.
|
|
|
|
# This class also includes a coded_value attribute, which
|
|
|
|
# is used to hold the network representation of the
|
|
|
|
# value. This is most useful when Python objects are
|
|
|
|
# pickled for network transit.
|
|
|
|
#
|
|
|
|
|
2002-06-26 12:19:01 -03:00
|
|
|
class Morsel(dict):
|
2000-08-19 10:01:19 -03:00
|
|
|
# RFC 2109 lists these attributes as reserved:
|
|
|
|
# path comment domain
|
|
|
|
# max-age secure version
|
2001-01-14 19:36:06 -04:00
|
|
|
#
|
2000-08-19 10:01:19 -03:00
|
|
|
# For historical reasons, these attributes are also reserved:
|
|
|
|
# expires
|
|
|
|
#
|
|
|
|
# This dictionary provides a mapping from the lowercase
|
|
|
|
# variant on the left to the appropriate traditional
|
|
|
|
# formatting on the right.
|
|
|
|
_reserved = { "expires" : "expires",
|
|
|
|
"path" : "Path",
|
|
|
|
"comment" : "Comment",
|
|
|
|
"domain" : "Domain",
|
|
|
|
"max-age" : "Max-Age",
|
|
|
|
"secure" : "secure",
|
|
|
|
"version" : "Version",
|
|
|
|
}
|
2000-08-24 11:40:35 -03:00
|
|
|
|
2000-08-19 10:01:19 -03:00
|
|
|
def __init__(self):
|
|
|
|
# Set defaults
|
|
|
|
self.key = self.value = self.coded_value = None
|
|
|
|
|
|
|
|
# Set default attributes
|
2002-06-26 12:19:01 -03:00
|
|
|
for K in self._reserved:
|
|
|
|
dict.__setitem__(self, K, "")
|
2000-08-19 10:01:19 -03:00
|
|
|
# end __init__
|
|
|
|
|
|
|
|
def __setitem__(self, K, V):
|
2002-04-25 23:29:55 -03:00
|
|
|
K = K.lower()
|
2002-06-26 12:19:01 -03:00
|
|
|
if not K in self._reserved:
|
2000-08-19 10:01:19 -03:00
|
|
|
raise CookieError("Invalid Attribute %s" % K)
|
2002-06-26 12:19:01 -03:00
|
|
|
dict.__setitem__(self, K, V)
|
2000-08-19 10:01:19 -03:00
|
|
|
# end __setitem__
|
|
|
|
|
|
|
|
def isReservedKey(self, K):
|
2002-06-26 12:19:01 -03:00
|
|
|
return K.lower() in self._reserved
|
2000-08-19 10:01:19 -03:00
|
|
|
# end isReservedKey
|
|
|
|
|
2007-04-17 05:48:32 -03:00
|
|
|
def set(self, key, val, coded_val, LegalChars=_LegalChars, idmap=_idmap):
|
2000-08-19 10:01:19 -03:00
|
|
|
# First we verify that the key isn't a reserved word
|
|
|
|
# Second we make sure it only contains legal characters
|
2002-06-26 12:19:01 -03:00
|
|
|
if key.lower() in self._reserved:
|
2000-08-19 10:01:19 -03:00
|
|
|
raise CookieError("Attempt to set a reserved key: %s" % key)
|
2007-04-17 05:48:32 -03:00
|
|
|
if "" != key.translate(idmap, LegalChars):
|
2000-08-19 10:01:19 -03:00
|
|
|
raise CookieError("Illegal key value: %s" % key)
|
|
|
|
|
|
|
|
# It's a good key, so save it.
|
|
|
|
self.key = key
|
|
|
|
self.value = val
|
|
|
|
self.coded_value = coded_val
|
|
|
|
# end set
|
|
|
|
|
|
|
|
def output(self, attrs=None, header = "Set-Cookie:"):
|
|
|
|
return "%s %s" % ( header, self.OutputString(attrs) )
|
|
|
|
|
2000-08-24 08:52:33 -03:00
|
|
|
__str__ = output
|
2000-08-19 10:01:19 -03:00
|
|
|
|
2000-08-24 08:52:33 -03:00
|
|
|
def __repr__(self):
|
|
|
|
return '<%s: %s=%s>' % (self.__class__.__name__,
|
|
|
|
self.key, repr(self.value) )
|
2000-08-24 11:40:35 -03:00
|
|
|
|
2000-08-19 10:01:19 -03:00
|
|
|
def js_output(self, attrs=None):
|
|
|
|
# Print javascript
|
|
|
|
return """
|
2005-06-26 18:02:49 -03:00
|
|
|
<script type="text/javascript">
|
2000-08-19 10:01:19 -03:00
|
|
|
<!-- begin hiding
|
2005-06-26 18:02:49 -03:00
|
|
|
document.cookie = \"%s\";
|
2000-08-19 10:01:19 -03:00
|
|
|
// end hiding -->
|
|
|
|
</script>
|
|
|
|
""" % ( self.OutputString(attrs), )
|
|
|
|
# end js_output()
|
|
|
|
|
|
|
|
def OutputString(self, attrs=None):
|
|
|
|
# Build up our result
|
|
|
|
#
|
|
|
|
result = []
|
|
|
|
RA = result.append
|
2000-08-24 11:40:35 -03:00
|
|
|
|
2000-08-19 10:01:19 -03:00
|
|
|
# First, the key=value pair
|
2005-08-24 19:34:21 -03:00
|
|
|
RA("%s=%s" % (self.key, self.coded_value))
|
2000-08-19 10:01:19 -03:00
|
|
|
|
|
|
|
# Now add any defined attributes
|
2000-12-12 19:20:45 -04:00
|
|
|
if attrs is None:
|
2002-06-26 12:19:01 -03:00
|
|
|
attrs = self._reserved
|
2007-02-11 02:12:03 -04:00
|
|
|
items = sorted(self.items())
|
Get rid of the superstitious "~" in dict hashing's "i = (~hash) & mask".
The comment following used to say:
/* We use ~hash instead of hash, as degenerate hash functions, such
as for ints <sigh>, can have lots of leading zeros. It's not
really a performance risk, but better safe than sorry.
12-Dec-00 tim: so ~hash produces lots of leading ones instead --
what's the gain? */
That is, there was never a good reason for doing it. And to the contrary,
as explained on Python-Dev last December, it tended to make the *sum*
(i + incr) & mask (which is the first table index examined in case of
collison) the same "too often" across distinct hashes.
Changing to the simpler "i = hash & mask" reduced the number of string-dict
collisions (== # number of times we go around the lookup for-loop) from about
6 million to 5 million during a full run of the test suite (these are
approximate because the test suite does some random stuff from run to run).
The number of collisions in non-string dicts also decreased, but not as
dramatically.
Note that this may, for a given dict, change the order (wrt previous
releases) of entries exposed by .keys(), .values() and .items(). A number
of std tests suffered bogus failures as a result. For dicts keyed by
small ints, or (less so) by characters, the order is much more likely to be
in increasing order of key now; e.g.,
>>> d = {}
>>> for i in range(10):
... d[i] = i
...
>>> d
{0: 0, 1: 1, 2: 2, 3: 3, 4: 4, 5: 5, 6: 6, 7: 7, 8: 8, 9: 9}
>>>
Unfortunately. people may latch on to that in small examples and draw a
bogus conclusion.
test_support.py
Moved test_extcall's sortdict() into test_support, made it stronger,
and imported sortdict into other std tests that needed it.
test_unicode.py
Excluced cp875 from the "roundtrip over range(128)" test, because
cp875 doesn't have a well-defined inverse for unicode("?", "cp875").
See Python-Dev for excruciating details.
Cookie.py
Chaged various output functions to sort dicts before building
strings from them.
test_extcall
Fiddled the expected-result file. This remains sensitive to native
dict ordering, because, e.g., if there are multiple errors in a
keyword-arg dict (and test_extcall sets up many cases like that), the
specific error Python complains about first depends on native dict
ordering.
2001-05-12 21:19:31 -03:00
|
|
|
for K,V in items:
|
2000-08-24 08:52:33 -03:00
|
|
|
if V == "": continue
|
2000-08-19 10:01:19 -03:00
|
|
|
if K not in attrs: continue
|
|
|
|
if K == "expires" and type(V) == type(1):
|
2005-08-24 19:34:21 -03:00
|
|
|
RA("%s=%s" % (self._reserved[K], _getdate(V)))
|
2000-08-19 10:01:19 -03:00
|
|
|
elif K == "max-age" and type(V) == type(1):
|
2005-08-24 19:34:21 -03:00
|
|
|
RA("%s=%d" % (self._reserved[K], V))
|
2000-08-19 10:01:19 -03:00
|
|
|
elif K == "secure":
|
2005-08-24 19:34:21 -03:00
|
|
|
RA(str(self._reserved[K]))
|
2000-08-19 10:01:19 -03:00
|
|
|
else:
|
2005-08-24 19:34:21 -03:00
|
|
|
RA("%s=%s" % (self._reserved[K], V))
|
2000-08-24 11:40:35 -03:00
|
|
|
|
2000-08-19 10:01:19 -03:00
|
|
|
# Return the result
|
2005-08-24 19:34:21 -03:00
|
|
|
return _semispacejoin(result)
|
2000-08-19 10:01:19 -03:00
|
|
|
# end OutputString
|
|
|
|
# end Morsel class
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
#
|
|
|
|
# Pattern for finding cookie
|
|
|
|
#
|
|
|
|
# This used to be strict parsing based on the RFC2109 and RFC2068
|
|
|
|
# specifications. I have since discovered that MSIE 3.0x doesn't
|
|
|
|
# follow the character rules outlined in those specs. As a
|
|
|
|
# result, the parsing rules here are less strict.
|
|
|
|
#
|
|
|
|
|
2001-02-20 18:11:24 -04:00
|
|
|
_LegalCharsPatt = r"[\w\d!#%&'~_`><@,:/\$\*\+\-\.\^\|\)\(\?\}\{\=]"
|
2000-08-19 10:01:19 -03:00
|
|
|
_CookiePattern = re.compile(
|
|
|
|
r"(?x)" # This is a Verbose pattern
|
|
|
|
r"(?P<key>" # Start of group 'key'
|
2001-02-20 18:11:24 -04:00
|
|
|
""+ _LegalCharsPatt +"+?" # Any word of at least one letter, nongreedy
|
2000-08-19 10:01:19 -03:00
|
|
|
r")" # End of group 'key'
|
|
|
|
r"\s*=\s*" # Equal Sign
|
|
|
|
r"(?P<val>" # Start of group 'val'
|
|
|
|
r'"(?:[^\\"]|\\.)*"' # Any doublequoted string
|
|
|
|
r"|" # or
|
|
|
|
""+ _LegalCharsPatt +"*" # Any word or empty string
|
|
|
|
r")" # End of group 'val'
|
|
|
|
r"\s*;?" # Probably ending in a semi-colon
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
|
|
# At long last, here is the cookie class.
|
|
|
|
# Using this class is almost just like using a dictionary.
|
|
|
|
# See this module's docstring for example usage.
|
|
|
|
#
|
2002-06-26 12:19:01 -03:00
|
|
|
class BaseCookie(dict):
|
2000-08-19 10:01:19 -03:00
|
|
|
# A container class for a set of Morsels
|
|
|
|
#
|
2000-08-24 11:40:35 -03:00
|
|
|
|
2000-08-19 10:01:19 -03:00
|
|
|
def value_decode(self, val):
|
|
|
|
"""real_value, coded_value = value_decode(STRING)
|
|
|
|
Called prior to setting a cookie's value from the network
|
|
|
|
representation. The VALUE is the value read from HTTP
|
|
|
|
header.
|
|
|
|
Override this function to modify the behavior of cookies.
|
|
|
|
"""
|
|
|
|
return val, val
|
|
|
|
# end value_encode
|
|
|
|
|
|
|
|
def value_encode(self, val):
|
|
|
|
"""real_value, coded_value = value_encode(VALUE)
|
|
|
|
Called prior to setting a cookie's value from the dictionary
|
|
|
|
representation. The VALUE is the value being assigned.
|
|
|
|
Override this function to modify the behavior of cookies.
|
|
|
|
"""
|
|
|
|
strval = str(val)
|
|
|
|
return strval, strval
|
|
|
|
# end value_encode
|
2000-08-24 11:40:35 -03:00
|
|
|
|
2000-08-19 10:01:19 -03:00
|
|
|
def __init__(self, input=None):
|
|
|
|
if input: self.load(input)
|
|
|
|
# end __init__
|
|
|
|
|
|
|
|
def __set(self, key, real_value, coded_value):
|
|
|
|
"""Private method for setting a cookie's value"""
|
|
|
|
M = self.get(key, Morsel())
|
|
|
|
M.set(key, real_value, coded_value)
|
2002-06-26 12:19:01 -03:00
|
|
|
dict.__setitem__(self, key, M)
|
2000-08-19 10:01:19 -03:00
|
|
|
# end __set
|
|
|
|
|
|
|
|
def __setitem__(self, key, value):
|
|
|
|
"""Dictionary style assignment."""
|
|
|
|
rval, cval = self.value_encode(value)
|
|
|
|
self.__set(key, rval, cval)
|
|
|
|
# end __setitem__
|
|
|
|
|
2005-08-24 19:34:21 -03:00
|
|
|
def output(self, attrs=None, header="Set-Cookie:", sep="\015\012"):
|
2000-08-19 10:01:19 -03:00
|
|
|
"""Return a string suitable for HTTP."""
|
|
|
|
result = []
|
2007-02-11 02:12:03 -04:00
|
|
|
items = sorted(self.items())
|
Get rid of the superstitious "~" in dict hashing's "i = (~hash) & mask".
The comment following used to say:
/* We use ~hash instead of hash, as degenerate hash functions, such
as for ints <sigh>, can have lots of leading zeros. It's not
really a performance risk, but better safe than sorry.
12-Dec-00 tim: so ~hash produces lots of leading ones instead --
what's the gain? */
That is, there was never a good reason for doing it. And to the contrary,
as explained on Python-Dev last December, it tended to make the *sum*
(i + incr) & mask (which is the first table index examined in case of
collison) the same "too often" across distinct hashes.
Changing to the simpler "i = hash & mask" reduced the number of string-dict
collisions (== # number of times we go around the lookup for-loop) from about
6 million to 5 million during a full run of the test suite (these are
approximate because the test suite does some random stuff from run to run).
The number of collisions in non-string dicts also decreased, but not as
dramatically.
Note that this may, for a given dict, change the order (wrt previous
releases) of entries exposed by .keys(), .values() and .items(). A number
of std tests suffered bogus failures as a result. For dicts keyed by
small ints, or (less so) by characters, the order is much more likely to be
in increasing order of key now; e.g.,
>>> d = {}
>>> for i in range(10):
... d[i] = i
...
>>> d
{0: 0, 1: 1, 2: 2, 3: 3, 4: 4, 5: 5, 6: 6, 7: 7, 8: 8, 9: 9}
>>>
Unfortunately. people may latch on to that in small examples and draw a
bogus conclusion.
test_support.py
Moved test_extcall's sortdict() into test_support, made it stronger,
and imported sortdict into other std tests that needed it.
test_unicode.py
Excluced cp875 from the "roundtrip over range(128)" test, because
cp875 doesn't have a well-defined inverse for unicode("?", "cp875").
See Python-Dev for excruciating details.
Cookie.py
Chaged various output functions to sort dicts before building
strings from them.
test_extcall
Fiddled the expected-result file. This remains sensitive to native
dict ordering, because, e.g., if there are multiple errors in a
keyword-arg dict (and test_extcall sets up many cases like that), the
specific error Python complains about first depends on native dict
ordering.
2001-05-12 21:19:31 -03:00
|
|
|
for K,V in items:
|
2000-08-19 10:01:19 -03:00
|
|
|
result.append( V.output(attrs, header) )
|
2002-04-25 23:29:55 -03:00
|
|
|
return sep.join(result)
|
2000-08-19 10:01:19 -03:00
|
|
|
# end output
|
|
|
|
|
2000-08-24 08:52:33 -03:00
|
|
|
__str__ = output
|
|
|
|
|
|
|
|
def __repr__(self):
|
|
|
|
L = []
|
2007-02-11 02:12:03 -04:00
|
|
|
items = sorted(self.items())
|
Get rid of the superstitious "~" in dict hashing's "i = (~hash) & mask".
The comment following used to say:
/* We use ~hash instead of hash, as degenerate hash functions, such
as for ints <sigh>, can have lots of leading zeros. It's not
really a performance risk, but better safe than sorry.
12-Dec-00 tim: so ~hash produces lots of leading ones instead --
what's the gain? */
That is, there was never a good reason for doing it. And to the contrary,
as explained on Python-Dev last December, it tended to make the *sum*
(i + incr) & mask (which is the first table index examined in case of
collison) the same "too often" across distinct hashes.
Changing to the simpler "i = hash & mask" reduced the number of string-dict
collisions (== # number of times we go around the lookup for-loop) from about
6 million to 5 million during a full run of the test suite (these are
approximate because the test suite does some random stuff from run to run).
The number of collisions in non-string dicts also decreased, but not as
dramatically.
Note that this may, for a given dict, change the order (wrt previous
releases) of entries exposed by .keys(), .values() and .items(). A number
of std tests suffered bogus failures as a result. For dicts keyed by
small ints, or (less so) by characters, the order is much more likely to be
in increasing order of key now; e.g.,
>>> d = {}
>>> for i in range(10):
... d[i] = i
...
>>> d
{0: 0, 1: 1, 2: 2, 3: 3, 4: 4, 5: 5, 6: 6, 7: 7, 8: 8, 9: 9}
>>>
Unfortunately. people may latch on to that in small examples and draw a
bogus conclusion.
test_support.py
Moved test_extcall's sortdict() into test_support, made it stronger,
and imported sortdict into other std tests that needed it.
test_unicode.py
Excluced cp875 from the "roundtrip over range(128)" test, because
cp875 doesn't have a well-defined inverse for unicode("?", "cp875").
See Python-Dev for excruciating details.
Cookie.py
Chaged various output functions to sort dicts before building
strings from them.
test_extcall
Fiddled the expected-result file. This remains sensitive to native
dict ordering, because, e.g., if there are multiple errors in a
keyword-arg dict (and test_extcall sets up many cases like that), the
specific error Python complains about first depends on native dict
ordering.
2001-05-12 21:19:31 -03:00
|
|
|
for K,V in items:
|
2000-08-24 08:52:33 -03:00
|
|
|
L.append( '%s=%s' % (K,repr(V.value) ) )
|
2005-08-25 04:32:42 -03:00
|
|
|
return '<%s: %s>' % (self.__class__.__name__, _spacejoin(L))
|
2000-08-24 11:40:35 -03:00
|
|
|
|
2000-08-19 10:01:19 -03:00
|
|
|
def js_output(self, attrs=None):
|
|
|
|
"""Return a string suitable for JavaScript."""
|
|
|
|
result = []
|
2007-02-11 02:12:03 -04:00
|
|
|
items = sorted(self.items())
|
Get rid of the superstitious "~" in dict hashing's "i = (~hash) & mask".
The comment following used to say:
/* We use ~hash instead of hash, as degenerate hash functions, such
as for ints <sigh>, can have lots of leading zeros. It's not
really a performance risk, but better safe than sorry.
12-Dec-00 tim: so ~hash produces lots of leading ones instead --
what's the gain? */
That is, there was never a good reason for doing it. And to the contrary,
as explained on Python-Dev last December, it tended to make the *sum*
(i + incr) & mask (which is the first table index examined in case of
collison) the same "too often" across distinct hashes.
Changing to the simpler "i = hash & mask" reduced the number of string-dict
collisions (== # number of times we go around the lookup for-loop) from about
6 million to 5 million during a full run of the test suite (these are
approximate because the test suite does some random stuff from run to run).
The number of collisions in non-string dicts also decreased, but not as
dramatically.
Note that this may, for a given dict, change the order (wrt previous
releases) of entries exposed by .keys(), .values() and .items(). A number
of std tests suffered bogus failures as a result. For dicts keyed by
small ints, or (less so) by characters, the order is much more likely to be
in increasing order of key now; e.g.,
>>> d = {}
>>> for i in range(10):
... d[i] = i
...
>>> d
{0: 0, 1: 1, 2: 2, 3: 3, 4: 4, 5: 5, 6: 6, 7: 7, 8: 8, 9: 9}
>>>
Unfortunately. people may latch on to that in small examples and draw a
bogus conclusion.
test_support.py
Moved test_extcall's sortdict() into test_support, made it stronger,
and imported sortdict into other std tests that needed it.
test_unicode.py
Excluced cp875 from the "roundtrip over range(128)" test, because
cp875 doesn't have a well-defined inverse for unicode("?", "cp875").
See Python-Dev for excruciating details.
Cookie.py
Chaged various output functions to sort dicts before building
strings from them.
test_extcall
Fiddled the expected-result file. This remains sensitive to native
dict ordering, because, e.g., if there are multiple errors in a
keyword-arg dict (and test_extcall sets up many cases like that), the
specific error Python complains about first depends on native dict
ordering.
2001-05-12 21:19:31 -03:00
|
|
|
for K,V in items:
|
2000-08-19 10:01:19 -03:00
|
|
|
result.append( V.js_output(attrs) )
|
2002-04-25 23:29:55 -03:00
|
|
|
return _nulljoin(result)
|
2000-08-19 10:01:19 -03:00
|
|
|
# end js_output
|
|
|
|
|
|
|
|
def load(self, rawdata):
|
|
|
|
"""Load cookies from a string (presumably HTTP_COOKIE) or
|
|
|
|
from a dictionary. Loading cookies from a dictionary 'd'
|
|
|
|
is equivalent to calling:
|
|
|
|
map(Cookie.__setitem__, d.keys(), d.values())
|
|
|
|
"""
|
|
|
|
if type(rawdata) == type(""):
|
|
|
|
self.__ParseString(rawdata)
|
|
|
|
else:
|
|
|
|
self.update(rawdata)
|
|
|
|
return
|
|
|
|
# end load()
|
2000-08-24 11:40:35 -03:00
|
|
|
|
2000-08-19 10:01:19 -03:00
|
|
|
def __ParseString(self, str, patt=_CookiePattern):
|
|
|
|
i = 0 # Our starting point
|
|
|
|
n = len(str) # Length of string
|
|
|
|
M = None # current morsel
|
|
|
|
|
|
|
|
while 0 <= i < n:
|
|
|
|
# Start looking for a cookie
|
|
|
|
match = patt.search(str, i)
|
|
|
|
if not match: break # No more cookies
|
|
|
|
|
|
|
|
K,V = match.group("key"), match.group("val")
|
|
|
|
i = match.end(0)
|
|
|
|
|
|
|
|
# Parse the key, value in case it's metainfo
|
|
|
|
if K[0] == "$":
|
|
|
|
# We ignore attributes which pertain to the cookie
|
|
|
|
# mechanism as a whole. See RFC 2109.
|
|
|
|
# (Does anyone care?)
|
|
|
|
if M:
|
|
|
|
M[ K[1:] ] = V
|
2002-06-26 12:19:01 -03:00
|
|
|
elif K.lower() in Morsel._reserved:
|
2000-08-19 10:01:19 -03:00
|
|
|
if M:
|
2000-08-24 08:52:33 -03:00
|
|
|
M[ K ] = _unquote(V)
|
2000-08-19 10:01:19 -03:00
|
|
|
else:
|
|
|
|
rval, cval = self.value_decode(V)
|
|
|
|
self.__set(K, rval, cval)
|
|
|
|
M = self[K]
|
|
|
|
# end __ParseString
|
|
|
|
# end BaseCookie class
|
|
|
|
|
|
|
|
class SimpleCookie(BaseCookie):
|
|
|
|
"""SimpleCookie
|
|
|
|
SimpleCookie supports strings as cookie values. When setting
|
|
|
|
the value using the dictionary assignment notation, SimpleCookie
|
|
|
|
calls the builtin str() to convert the value to a string. Values
|
|
|
|
received from HTTP are kept as strings.
|
|
|
|
"""
|
|
|
|
def value_decode(self, val):
|
|
|
|
return _unquote( val ), val
|
|
|
|
def value_encode(self, val):
|
|
|
|
strval = str(val)
|
|
|
|
return strval, _quote( strval )
|
|
|
|
# end SimpleCookie
|
|
|
|
|
|
|
|
class SerialCookie(BaseCookie):
|
|
|
|
"""SerialCookie
|
|
|
|
SerialCookie supports arbitrary objects as cookie values. All
|
|
|
|
values are serialized (using cPickle) before being sent to the
|
|
|
|
client. All incoming values are assumed to be valid Pickle
|
|
|
|
representations. IF AN INCOMING VALUE IS NOT IN A VALID PICKLE
|
|
|
|
FORMAT, THEN AN EXCEPTION WILL BE RAISED.
|
|
|
|
|
|
|
|
Note: Large cookie values add overhead because they must be
|
|
|
|
retransmitted on every HTTP transaction.
|
2000-08-24 11:40:35 -03:00
|
|
|
|
2000-08-19 10:01:19 -03:00
|
|
|
Note: HTTP has a 2k limit on the size of a cookie. This class
|
|
|
|
does not check for this limit, so be careful!!!
|
|
|
|
"""
|
2002-12-29 12:44:31 -04:00
|
|
|
def __init__(self, input=None):
|
|
|
|
warnings.warn("SerialCookie class is insecure; do not use it",
|
|
|
|
DeprecationWarning)
|
|
|
|
BaseCookie.__init__(self, input)
|
|
|
|
# end __init__
|
2000-08-19 10:01:19 -03:00
|
|
|
def value_decode(self, val):
|
|
|
|
# This could raise an exception!
|
|
|
|
return loads( _unquote(val) ), val
|
|
|
|
def value_encode(self, val):
|
|
|
|
return val, _quote( dumps(val) )
|
|
|
|
# end SerialCookie
|
|
|
|
|
|
|
|
class SmartCookie(BaseCookie):
|
|
|
|
"""SmartCookie
|
|
|
|
SmartCookie supports arbitrary objects as cookie values. If the
|
|
|
|
object is a string, then it is quoted. If the object is not a
|
|
|
|
string, however, then SmartCookie will use cPickle to serialize
|
|
|
|
the object into a string representation.
|
|
|
|
|
|
|
|
Note: Large cookie values add overhead because they must be
|
|
|
|
retransmitted on every HTTP transaction.
|
2000-08-24 11:40:35 -03:00
|
|
|
|
2000-08-19 10:01:19 -03:00
|
|
|
Note: HTTP has a 2k limit on the size of a cookie. This class
|
|
|
|
does not check for this limit, so be careful!!!
|
|
|
|
"""
|
2002-12-29 12:44:31 -04:00
|
|
|
def __init__(self, input=None):
|
|
|
|
warnings.warn("Cookie/SmartCookie class is insecure; do not use it",
|
|
|
|
DeprecationWarning)
|
|
|
|
BaseCookie.__init__(self, input)
|
|
|
|
# end __init__
|
2000-08-19 10:01:19 -03:00
|
|
|
def value_decode(self, val):
|
|
|
|
strval = _unquote(val)
|
|
|
|
try:
|
|
|
|
return loads(strval), val
|
|
|
|
except:
|
|
|
|
return strval, val
|
|
|
|
def value_encode(self, val):
|
|
|
|
if type(val) == type(""):
|
|
|
|
return val, _quote(val)
|
|
|
|
else:
|
|
|
|
return val, _quote( dumps(val) )
|
|
|
|
# end SmartCookie
|
|
|
|
|
|
|
|
|
|
|
|
###########################################################
|
|
|
|
# Backwards Compatibility: Don't break any existing code!
|
|
|
|
|
|
|
|
# We provide Cookie() as an alias for SmartCookie()
|
|
|
|
Cookie = SmartCookie
|
|
|
|
|
|
|
|
#
|
|
|
|
###########################################################
|
|
|
|
|
2001-04-06 16:39:11 -03:00
|
|
|
def _test():
|
|
|
|
import doctest, Cookie
|
|
|
|
return doctest.testmod(Cookie)
|
|
|
|
|
|
|
|
if __name__ == "__main__":
|
|
|
|
_test()
|
2000-08-19 10:01:19 -03:00
|
|
|
|
|
|
|
|
2000-08-24 08:52:33 -03:00
|
|
|
#Local Variables:
|
|
|
|
#tab-width: 4
|
|
|
|
#end:
|