Fix a path to an assert in fileio_read().
Some misc tweaks.

embeds the result of PyObject_Unicode() into the resulting
unicode string.

PyUnicode_FromFormat().

test_bz2 passes.

Change binascii.Error to derive from ValueError
and raise binascii.Error everywhere where values are bad
(why on earth did the old code use TypeError?!?).

svn+ssh://pythondev@svn.python.org/python/branches/p3yk

................
  r55413 | fred.drake | 2007-05-17 12:30:10 -0700 (Thu, 17 May 2007) | 1 line

  fix argument name in documentation; match the implementation
................
  r55430 | jack.diederich | 2007-05-18 06:39:59 -0700 (Fri, 18 May 2007) | 1 line

  Implements class decorators, PEP 3129.
................
  r55432 | guido.van.rossum | 2007-05-18 08:09:41 -0700 (Fri, 18 May 2007) | 2 lines

  obsubmit.
................
  r55434 | guido.van.rossum | 2007-05-18 09:39:10 -0700 (Fri, 18 May 2007) | 3 lines

  Fix bug in test_inspect.  (I presume this is how it should be fixed;
  Jack Diedrich, please verify.)
................
  r55460 | brett.cannon | 2007-05-20 00:31:57 -0700 (Sun, 20 May 2007) | 4 lines

  Remove the imageop module.  With imgfile already removed in Python 3.0 and
  rgbimg gone in Python 2.6 the unit tests themselves were made worthless.  Plus
  third-party libraries perform the same function much better.
................
  r55469 | neal.norwitz | 2007-05-20 11:28:20 -0700 (Sun, 20 May 2007) | 118 lines

  Merged revisions 55324-55467 via svnmerge from
  svn+ssh://pythondev@svn.python.org/python/trunk

  ........
    r55348 | georg.brandl | 2007-05-15 13:19:34 -0700 (Tue, 15 May 2007) | 4 lines

    HTML-escape the plain traceback in cgitb's HTML output, to prevent
    the traceback inadvertently or maliciously closing the comment and
    injecting HTML into the error page.
  ........
    r55372 | neal.norwitz | 2007-05-15 21:33:50 -0700 (Tue, 15 May 2007) | 6 lines

    Port rev 55353 from Guido:
    Add what looks like a necessary call to PyErr_NoMemory() when PyMem_MALLOC()
    fails.

    Will backport.
  ........
    r55377 | neal.norwitz | 2007-05-15 22:06:33 -0700 (Tue, 15 May 2007) | 1 line

    Mention removal of some directories for obsolete platforms
  ........
    r55380 | brett.cannon | 2007-05-15 22:50:03 -0700 (Tue, 15 May 2007) | 2 lines

    Change the maintainer of the BeOS port.
  ........
    r55383 | georg.brandl | 2007-05-16 06:44:18 -0700 (Wed, 16 May 2007) | 2 lines

    Bug #1719995: don't use deprecated method in sets example.
  ........
    r55386 | neal.norwitz | 2007-05-16 13:05:11 -0700 (Wed, 16 May 2007) | 5 lines

    Fix bug in marshal where bad data would cause a segfault due to
    lack of an infinite recursion check.

    Contributed by Damien Miller at Google.
  ........
    r55389 | brett.cannon | 2007-05-16 15:42:29 -0700 (Wed, 16 May 2007) | 6 lines

    Remove the gopherlib module.  It has been raising a DeprecationWarning since
    Python 2.5.

    Also remove gopher support from urllib/urllib2.  As both imported gopherlib the
    usage of the support would have raised a DeprecationWarning.
  ........
    r55394 | raymond.hettinger | 2007-05-16 18:08:04 -0700 (Wed, 16 May 2007) | 1 line

    calendar.py gets no benefit from xrange() instead of range()
  ........
    r55395 | brett.cannon | 2007-05-16 19:02:56 -0700 (Wed, 16 May 2007) | 3 lines

    Complete deprecation of BaseException.message.  Some subclasses were directly
    accessing the message attribute instead of using the descriptor.
  ........
    r55396 | neal.norwitz | 2007-05-16 23:11:36 -0700 (Wed, 16 May 2007) | 4 lines

    Reduce the max stack depth to see if this fixes the segfaults on
    Windows and some other boxes.  If this is successful, this rev should
    be backported.  I'm not sure how close to the limit we should push this.
  ........
    r55397 | neal.norwitz | 2007-05-16 23:23:50 -0700 (Wed, 16 May 2007) | 4 lines

    Set the depth to something very small to try to determine if the
    crashes on Windows are really due to the stack size or possibly
    some other problem.
  ........
    r55398 | neal.norwitz | 2007-05-17 00:04:46 -0700 (Thu, 17 May 2007) | 4 lines

    Last try for tweaking the max stack depth.  5000 was the original value,
    4000 didn't work either.  1000 does work on Windows.  If 2000 works,
    that will hopefully be a reasonable balance.
  ........
    r55412 | fred.drake | 2007-05-17 12:29:58 -0700 (Thu, 17 May 2007) | 1 line

    fix argument name in documentation; match the implementation
  ........
    r55427 | neal.norwitz | 2007-05-17 22:47:16 -0700 (Thu, 17 May 2007) | 1 line

    Verify neither dumps or loads overflow the stack and segfault.
  ........
    r55446 | collin.winter | 2007-05-18 16:11:24 -0700 (Fri, 18 May 2007) | 1 line

    Backport PEP 3110's new 'except' syntax to 2.6.
  ........
    r55448 | raymond.hettinger | 2007-05-18 18:11:16 -0700 (Fri, 18 May 2007) | 1 line

    Improvements to NamedTuple's implementation, tests, and documentation
  ........
    r55449 | raymond.hettinger | 2007-05-18 18:50:11 -0700 (Fri, 18 May 2007) | 1 line

    Fix beginner mistake -- don't mix spaces and tabs.
  ........
    r55450 | neal.norwitz | 2007-05-18 20:48:47 -0700 (Fri, 18 May 2007) | 1 line

    Clear data so random memory does not get freed.  Will backport.
  ........
    r55452 | neal.norwitz | 2007-05-18 21:34:55 -0700 (Fri, 18 May 2007) | 3 lines

    Whoops, need to pay attention to those test failures.
    Move the clear to *before* the first use, not after.
  ........
    r55453 | neal.norwitz | 2007-05-18 21:35:52 -0700 (Fri, 18 May 2007) | 1 line

    Give some clue as to what happened if the test fails.
  ........
    r55455 | georg.brandl | 2007-05-19 11:09:26 -0700 (Sat, 19 May 2007) | 2 lines

    Fix docstring for add_package in site.py.
  ........
    r55458 | brett.cannon | 2007-05-20 00:09:50 -0700 (Sun, 20 May 2007) | 2 lines

    Remove the rgbimg module.  It has been deprecated since Python 2.5.
  ........
    r55465 | nick.coghlan | 2007-05-20 04:12:49 -0700 (Sun, 20 May 2007) | 1 line

    Fix typo in example (should be backported, but my maintenance branch is woefully out of date)
  ........
................
  r55472 | brett.cannon | 2007-05-20 12:06:18 -0700 (Sun, 20 May 2007) | 2 lines

  Remove imageop from the Windows build process.
................
  r55486 | neal.norwitz | 2007-05-20 23:59:52 -0700 (Sun, 20 May 2007) | 1 line

  Remove callable() builtin
................
  r55506 | neal.norwitz | 2007-05-22 00:43:29 -0700 (Tue, 22 May 2007) | 78 lines

  Merged revisions 55468-55505 via svnmerge from
  svn+ssh://pythondev@svn.python.org/python/trunk

  ........
    r55468 | neal.norwitz | 2007-05-20 11:06:27 -0700 (Sun, 20 May 2007) | 1 line

    rotor is long gone.
  ........
    r55470 | neal.norwitz | 2007-05-20 11:43:00 -0700 (Sun, 20 May 2007) | 1 line

    Update directories/files at the top-level.
  ........
    r55471 | brett.cannon | 2007-05-20 12:05:06 -0700 (Sun, 20 May 2007) | 2 lines

    Try to remove rgbimg from Windows builds.
  ........
    r55474 | brett.cannon | 2007-05-20 16:17:38 -0700 (Sun, 20 May 2007) | 4 lines

    Remove the macfs module.  This led to the deprecation of macostools.touched();
    it completely relied on macfs and is a no-op on OS X according to code
    comments.
  ........
    r55476 | brett.cannon | 2007-05-20 16:56:18 -0700 (Sun, 20 May 2007) | 3 lines

    Move imgfile import to the global namespace to trigger an import error ASAP to
    prevent creation of a test file.
  ........
    r55477 | brett.cannon | 2007-05-20 16:57:38 -0700 (Sun, 20 May 2007) | 3 lines

    Cause posixfile to raise a DeprecationWarning.  Documented as deprecated since
    Ptyhon 1.5.
  ........
    r55479 | andrew.kuchling | 2007-05-20 17:03:15 -0700 (Sun, 20 May 2007) | 1 line

    Note removed modules
  ........
    r55481 | martin.v.loewis | 2007-05-20 21:35:47 -0700 (Sun, 20 May 2007) | 2 lines

    Add Alexandre Vassalotti.
  ........
    r55482 | george.yoshida | 2007-05-20 21:41:21 -0700 (Sun, 20 May 2007) | 4 lines

    fix against r55474 [Remove the macfs module]

    Remove "libmacfs.tex" from Makefile.deps and mac/mac.tex.
  ........
    r55487 | raymond.hettinger | 2007-05-21 01:13:35 -0700 (Mon, 21 May 2007) | 1 line

    Replace assertion with straight error-checking.
  ........
    r55489 | raymond.hettinger | 2007-05-21 09:40:10 -0700 (Mon, 21 May 2007) | 1 line

    Allow all alphanumeric and underscores in type and field names.
  ........
    r55490 | facundo.batista | 2007-05-21 10:32:32 -0700 (Mon, 21 May 2007) | 5 lines


    Added timeout support to HTTPSConnection, through the
    socket.create_connection function. Also added a small
    test for this, and updated NEWS file.
  ........
    r55495 | georg.brandl | 2007-05-21 13:34:16 -0700 (Mon, 21 May 2007) | 2 lines

    Patch #1686487: you can now pass any mapping after '**' in function calls.
  ........
    r55502 | neal.norwitz | 2007-05-21 23:03:36 -0700 (Mon, 21 May 2007) | 1 line

    Document new params to HTTPSConnection
  ........
    r55504 | neal.norwitz | 2007-05-22 00:16:10 -0700 (Tue, 22 May 2007) | 1 line

    Stop using METH_OLDARGS
  ........
    r55505 | neal.norwitz | 2007-05-22 00:16:44 -0700 (Tue, 22 May 2007) | 1 line

    Stop using METH_OLDARGS implicitly
  ........
................

selects sys.stdout.

accordingly (bytes.strip() always requires an argument).

normal code (or drop them if they only repeat previous
tests).

unicodedata and the CJK codecs are built again.

The zipfile module now does all I/O in binary mode using bytes.
(Maybe we should support wrapping a TextIOWrapper around it
when text mode reading is requested?)
Even the password is a bytes array now.
Had to fix py_compile.py to use bytes while I was at it.
The _struct needed a patch to support bytes, str8 and str
for the 's' and 'p' formats.

recv()) now return bytes, not str or str8.  The socket.py code is
redone; it now subclasses _socket.socket and instead of having its own
_fileobject for makefile(), it uses io.SocketIO.  Some stuff in io.py
was moved around to make this work.  (I really need to rethink my
policy regarding readline() and read(-1) on raw files; and readline()
on buffered files ought to use peeking().  Later.)

Remove duplicate tests.

Test str and str8 in test_both().

type name in various spots.

the result of a call to PyObject_Repr() into the string. This makes
it possible to simplify many repr implementations.

PyUnicode_FromFormat() uses two steps to create the final string: A first
pass through the format string determines the size of the final string and
a second pass creates the string. To avoid calling PyObject_Repr() twice
for each %R specifier, PyObject_Repr() is called during the size
calculation step and the results are stored in an array (whose size is
determined at the start by counting %R specifiers).

This does nothing to fix the tests though...

hostname was passed.

PyString_Concat() and PyString_ConcatAndDel() (the name PyUnicode_Concat()
was already taken).

Change PyObject_Repr() to always return a unicode object.

Update all repr implementations to return unicode objects.

Add a function PyObject_ReprStr8() that calls PyObject_Repr() and converts
the result to an 8bit string.

Use PyObject_ReprStr8() where using PyObject_Repr() can't be done
straightforward.