cpython/Lib/test/string_tests.py
Thomas Wouters 4d70c3d9dd Partially merge trunk into p3yk. The removal of Mac/Tools is confusing svn
merge in bad ways, so I'll have to merge that extra-carefully (probably manually.)

Merged revisions 46495-46605 via svnmerge from
svn+ssh://pythondev@svn.python.org/python/trunk

........
  r46495 | tim.peters | 2006-05-28 03:52:38 +0200 (Sun, 28 May 2006) | 2 lines

  Added missing svn:eol-style property to text files.
........
  r46497 | tim.peters | 2006-05-28 12:41:29 +0200 (Sun, 28 May 2006) | 3 lines

  PyErr_Display(), PyErr_WriteUnraisable():  Coverity found a cut-and-paste
  bug in both:  `className` was referenced before being checked for NULL.
........
  r46499 | fredrik.lundh | 2006-05-28 14:06:46 +0200 (Sun, 28 May 2006) | 5 lines

  needforspeed: added Py_MEMCPY macro (currently tuned for Visual C only),
  and use it for string copy operations.  this gives a 20% speedup on some
  string benchmarks.
........
  r46501 | michael.hudson | 2006-05-28 17:51:40 +0200 (Sun, 28 May 2006) | 26 lines

  Quality control, meet exceptions.c.

  Fix a number of problems with the need for speed code:

  One is doing this sort of thing:

      Py_DECREF(self->field);
      self->field = newval;
      Py_INCREF(self->field);

  without being very sure that self->field doesn't start with a
  value that has a __del__, because that almost certainly can lead
  to segfaults.

  As self->args is constrained to be an exact tuple we may as well
  exploit this fact consistently.  This leads to quite a lot of
  simplification (and, hey, probably better performance).

  Add some error checking in places lacking it.

  Fix some rather strange indentation in the Unicode code.

  Delete some trailing whitespace.

  More to come, I haven't fixed all the reference leaks yet...
........
  r46502 | george.yoshida | 2006-05-28 18:39:09 +0200 (Sun, 28 May 2006) | 3 lines

  Patch #1080727: add "encoding" parameter to doctest.DocFileSuite
  Contributed by Bjorn Tillenius.
........
  r46503 | martin.v.loewis | 2006-05-28 18:57:38 +0200 (Sun, 28 May 2006) | 4 lines

  Rest of patch #1490384: Commit icon source, remove
  claim that Erik von Blokland is the author of the
  installer picture.
........
  r46504 | michael.hudson | 2006-05-28 19:40:29 +0200 (Sun, 28 May 2006) | 16 lines

  Quality control, meet exceptions.c, round two.

  Make some functions that should have been static static.

  Fix a bunch of refleaks by fixing the definition of
  MiddlingExtendsException.

  Remove all the __new__ implementations apart from
  BaseException_new.  Rewrite most code that needs it to cope with
  NULL fields (such code could get excercised anyway, the
  __new__-removal just makes it more likely).  This involved
  editing the code for WindowsError, which I can't test.

  This fixes all the refleaks in at least the start of a regrtest
  -R :: run.
........
  r46505 | marc-andre.lemburg | 2006-05-28 19:46:58 +0200 (Sun, 28 May 2006) | 10 lines

  Initial version of systimes - a module to provide platform dependent
  performance measurements.

  The module is currently just a proof-of-concept implementation, but
  will integrated into pybench once it is stable enough.

  License: pybench license.
  Author: Marc-Andre Lemburg.
........
  r46507 | armin.rigo | 2006-05-28 21:13:17 +0200 (Sun, 28 May 2006) | 15 lines

  ("Forward-port" of r46506)

  Remove various dependencies on dictionary order in the standard library
  tests, and one (clearly an oversight, potentially critical) in the
  standard library itself - base64.py.

  Remaining open issues:
   * test_extcall is an output test, messy to make robust
   * tarfile.py has a potential bug here, but I'm not familiar
     enough with this code.  Filed in as SF bug #1496501.
   * urllib2.HTTPPasswordMgr() returns a random result if there is more
     than one matching root path.  I'm asking python-dev for
     clarification...
........
  r46508 | georg.brandl | 2006-05-28 22:11:45 +0200 (Sun, 28 May 2006) | 4 lines

  The empty string is a valid import path.
   (fixes #1496539)
........
  r46509 | georg.brandl | 2006-05-28 22:23:12 +0200 (Sun, 28 May 2006) | 3 lines

  Patch #1496206: urllib2 PasswordMgr ./. default ports
........
  r46510 | georg.brandl | 2006-05-28 22:57:09 +0200 (Sun, 28 May 2006) | 3 lines

  Fix refleaks in UnicodeError get and set methods.
........
  r46511 | michael.hudson | 2006-05-28 23:19:03 +0200 (Sun, 28 May 2006) | 3 lines

  use the UnicodeError traversal and clearing functions in UnicodeError
  subclasses.
........
  r46512 | thomas.wouters | 2006-05-28 23:32:12 +0200 (Sun, 28 May 2006) | 4 lines


  Make last patch valid C89 so Windows compilers can deal with it.
........
  r46513 | georg.brandl | 2006-05-28 23:42:54 +0200 (Sun, 28 May 2006) | 3 lines

  Fix ref-antileak in _struct.c which eventually lead to deallocating None.
........
  r46514 | georg.brandl | 2006-05-28 23:57:35 +0200 (Sun, 28 May 2006) | 4 lines

  Correct None refcount issue in Mac modules. (Are they
  still used?)
........
  r46515 | armin.rigo | 2006-05-29 00:07:08 +0200 (Mon, 29 May 2006) | 3 lines

  A clearer error message when passing -R to regrtest.py with
  release builds of Python.
........
  r46516 | georg.brandl | 2006-05-29 00:14:04 +0200 (Mon, 29 May 2006) | 3 lines

  Fix C function calling conventions in _sre module.
........
  r46517 | georg.brandl | 2006-05-29 00:34:51 +0200 (Mon, 29 May 2006) | 3 lines

  Convert audioop over to METH_VARARGS.
........
  r46518 | georg.brandl | 2006-05-29 00:38:57 +0200 (Mon, 29 May 2006) | 3 lines

  METH_NOARGS functions do get called with two args.
........
  r46519 | georg.brandl | 2006-05-29 11:46:51 +0200 (Mon, 29 May 2006) | 4 lines

  Fix refleak in socketmodule. Replace bogus Py_BuildValue calls.
  Fix refleak in exceptions.
........
  r46520 | nick.coghlan | 2006-05-29 14:43:05 +0200 (Mon, 29 May 2006) | 7 lines

  Apply modified version of Collin Winter's patch #1478788

  Renames functional extension module to _functools and adds a Python
  functools module so that utility functions like update_wrapper can be
  added easily.
........
  r46522 | georg.brandl | 2006-05-29 15:53:16 +0200 (Mon, 29 May 2006) | 3 lines

  Convert fmmodule to METH_VARARGS.
........
  r46523 | georg.brandl | 2006-05-29 16:13:21 +0200 (Mon, 29 May 2006) | 3 lines

  Fix #1494605.
........
  r46524 | georg.brandl | 2006-05-29 16:28:05 +0200 (Mon, 29 May 2006) | 3 lines

  Handle PyMem_Malloc failure in pystrtod.c. Closes #1494671.
........
  r46525 | georg.brandl | 2006-05-29 16:33:55 +0200 (Mon, 29 May 2006) | 3 lines

  Fix compiler warning.
........
  r46526 | georg.brandl | 2006-05-29 16:39:00 +0200 (Mon, 29 May 2006) | 3 lines

  Fix #1494787 (pyclbr counts whitespace as superclass name)
........
  r46527 | bob.ippolito | 2006-05-29 17:47:29 +0200 (Mon, 29 May 2006) | 1 line

  simplify the struct code a bit (no functional changes)
........
  r46528 | armin.rigo | 2006-05-29 19:59:47 +0200 (Mon, 29 May 2006) | 2 lines

  Silence a warning.
........
  r46529 | georg.brandl | 2006-05-29 21:39:45 +0200 (Mon, 29 May 2006) | 3 lines

  Correct some value converting strangenesses.
........
  r46530 | nick.coghlan | 2006-05-29 22:27:44 +0200 (Mon, 29 May 2006) | 1 line

  When adding a module like functools, it helps to let SVN know about the file.
........
  r46531 | georg.brandl | 2006-05-29 22:52:54 +0200 (Mon, 29 May 2006) | 4 lines

  Patches #1497027 and #972322: try HTTP digest auth first,
  and watch out for handler name collisions.
........
  r46532 | georg.brandl | 2006-05-29 22:57:01 +0200 (Mon, 29 May 2006) | 3 lines

  Add News entry for last commit.
........
  r46533 | georg.brandl | 2006-05-29 23:04:52 +0200 (Mon, 29 May 2006) | 4 lines

  Make use of METH_O and METH_NOARGS where possible.
  Use Py_UnpackTuple instead of PyArg_ParseTuple where possible.
........
  r46534 | georg.brandl | 2006-05-29 23:58:42 +0200 (Mon, 29 May 2006) | 3 lines

  Convert more modules to METH_VARARGS.
........
  r46535 | georg.brandl | 2006-05-30 00:00:30 +0200 (Tue, 30 May 2006) | 3 lines

  Whoops.
........
  r46536 | fredrik.lundh | 2006-05-30 00:42:07 +0200 (Tue, 30 May 2006) | 4 lines

  fixed "abc".count("", 100) == -96 error (hopefully, nobody's relying on
  the current behaviour ;-)
........
  r46537 | bob.ippolito | 2006-05-30 00:55:48 +0200 (Tue, 30 May 2006) | 1 line

  struct: modulo math plus warning on all endian-explicit formats for compatibility with older struct usage (ugly)
........
  r46539 | bob.ippolito | 2006-05-30 02:26:01 +0200 (Tue, 30 May 2006) | 1 line

  Add a length check to aifc to ensure it doesn't write a bogus file
........
  r46540 | tim.peters | 2006-05-30 04:25:25 +0200 (Tue, 30 May 2006) | 10 lines

  deprecated_err():  Stop bizarre warning messages when the tests
  are run in the order:

      test_genexps (or any other doctest-based test)
      test_struct
      test_doctest

  The `warnings` module needs an advertised way to save/restore
  its internal filter list.
........
  r46541 | tim.peters | 2006-05-30 04:26:46 +0200 (Tue, 30 May 2006) | 2 lines

  Whitespace normalization.
........
  r46542 | tim.peters | 2006-05-30 04:30:30 +0200 (Tue, 30 May 2006) | 2 lines

  Set a binary svn:mime-type property on this UTF-8 encoded file.
........
  r46543 | neal.norwitz | 2006-05-30 05:18:50 +0200 (Tue, 30 May 2006) | 1 line

  Simplify further by using AddStringConstant
........
  r46544 | tim.peters | 2006-05-30 06:16:25 +0200 (Tue, 30 May 2006) | 6 lines

  Convert relevant dict internals to Py_ssize_t.

  I don't have a box with nearly enough RAM, or an OS,
  that could get close to tickling this, though (requires
  a dict w/ at least 2**31 entries).
........
  r46545 | neal.norwitz | 2006-05-30 06:19:21 +0200 (Tue, 30 May 2006) | 1 line

  Remove stray | in comment
........
  r46546 | neal.norwitz | 2006-05-30 06:25:05 +0200 (Tue, 30 May 2006) | 1 line

  Use Py_SAFE_DOWNCAST for safety.  Fix format strings.  Remove 2 more stray | in comment
........
  r46547 | neal.norwitz | 2006-05-30 06:43:23 +0200 (Tue, 30 May 2006) | 1 line

  No DOWNCAST is required since sizeof(Py_ssize_t) >= sizeof(int) and Py_ReprEntr returns an int
........
  r46548 | tim.peters | 2006-05-30 07:04:59 +0200 (Tue, 30 May 2006) | 3 lines

  dict_print():  Explicitly narrow the return value
  from a (possibly) wider variable.
........
  r46549 | tim.peters | 2006-05-30 07:23:59 +0200 (Tue, 30 May 2006) | 5 lines

  dict_print():  So that Neal & I don't spend the rest of
  our lives taking turns rewriting code that works ;-),
  get rid of casting illusions by declaring a new variable
  with the obvious type.
........
  r46550 | georg.brandl | 2006-05-30 09:04:55 +0200 (Tue, 30 May 2006) | 3 lines

  Restore exception pickle support. #1497319.
........
  r46551 | georg.brandl | 2006-05-30 09:13:29 +0200 (Tue, 30 May 2006) | 3 lines

  Add a test case for exception pickling. args is never NULL.
........
  r46552 | neal.norwitz | 2006-05-30 09:21:10 +0200 (Tue, 30 May 2006) | 1 line

  Don't fail if the (sub)pkgname already exist.
........
  r46553 | georg.brandl | 2006-05-30 09:34:45 +0200 (Tue, 30 May 2006) | 3 lines

  Disallow keyword args for exceptions.
........
  r46554 | neal.norwitz | 2006-05-30 09:36:54 +0200 (Tue, 30 May 2006) | 5 lines

  I'm impatient.  I think this will fix a few more problems with the buildbots.
  I'm not sure this is the best approach, but I can't think of anything better.
  If this creates problems, feel free to revert, but I think it's safe and
  should make things a little better.
........
  r46555 | georg.brandl | 2006-05-30 10:17:00 +0200 (Tue, 30 May 2006) | 4 lines

  Do the check for no keyword arguments in __init__ so that
  subclasses of Exception can be supplied keyword args
........
  r46556 | georg.brandl | 2006-05-30 10:47:19 +0200 (Tue, 30 May 2006) | 3 lines

  Convert test_exceptions to unittest.
........
  r46557 | andrew.kuchling | 2006-05-30 14:52:01 +0200 (Tue, 30 May 2006) | 1 line

  Add SoC name, and reorganize this section a bit
........
  r46559 | tim.peters | 2006-05-30 17:53:34 +0200 (Tue, 30 May 2006) | 11 lines

  PyLong_FromString():  Continued fraction analysis (explained in
  a new comment) suggests there are almost certainly large input
  integers in all non-binary input bases for which one Python digit
  too few is initally allocated to hold the final result.  Instead
  of assert-failing when that happens, allocate more space.  Alas,
  I estimate it would take a few days to find a specific such case,
  so this isn't backed up by a new test (not to mention that such
  a case may take hours to run, since conversion time is quadratic
  in the number of digits, and preliminary attempts suggested that
  the smallest such inputs contain at least a million digits).
........
  r46560 | fredrik.lundh | 2006-05-30 19:11:48 +0200 (Tue, 30 May 2006) | 3 lines

  changed find/rfind to return -1 for matches outside the source string
........
  r46561 | bob.ippolito | 2006-05-30 19:37:54 +0200 (Tue, 30 May 2006) | 1 line

  Change wrapping terminology to overflow masking
........
  r46562 | fredrik.lundh | 2006-05-30 19:39:58 +0200 (Tue, 30 May 2006) | 3 lines

  changed count to return 0 for slices outside the source string
........
  r46568 | tim.peters | 2006-05-31 01:28:02 +0200 (Wed, 31 May 2006) | 2 lines

  Whitespace normalization.
........
  r46569 | brett.cannon | 2006-05-31 04:19:54 +0200 (Wed, 31 May 2006) | 5 lines

  Clarify wording on default values for strptime(); defaults are used when better
  values cannot be inferred.

  Closes bug #1496315.
........
  r46572 | neal.norwitz | 2006-05-31 09:43:27 +0200 (Wed, 31 May 2006) | 1 line

  Calculate smallest properly (it was off by one) and use proper ssize_t types for Win64
........
  r46573 | neal.norwitz | 2006-05-31 10:01:08 +0200 (Wed, 31 May 2006) | 1 line

  Revert last checkin, it is better to do make distclean
........
  r46574 | neal.norwitz | 2006-05-31 11:02:44 +0200 (Wed, 31 May 2006) | 3 lines

  On 64-bit platforms running test_struct after test_tarfile would fail
  since the deprecation warning wouldn't be raised.
........
  r46575 | thomas.heller | 2006-05-31 13:37:58 +0200 (Wed, 31 May 2006) | 3 lines

  PyTuple_Pack is not available in Python 2.3, but ctypes must stay
  compatible with that.
........
  r46576 | andrew.kuchling | 2006-05-31 15:18:56 +0200 (Wed, 31 May 2006) | 1 line

  'functional' module was renamed to 'functools'
........
  r46577 | kristjan.jonsson | 2006-05-31 15:35:41 +0200 (Wed, 31 May 2006) | 1 line

  Fixup the PCBuild8 project directory.  exceptions.c have moved to Objects, and the functionalmodule.c has been replaced with _functoolsmodule.c.  Other minor changes to .vcproj files and .sln to fix compilation
........
  r46578 | andrew.kuchling | 2006-05-31 16:08:48 +0200 (Wed, 31 May 2006) | 15 lines

  [Bug #1473048]
  SimpleXMLRPCServer and DocXMLRPCServer don't look at
  the path of the HTTP request at all; you can POST or
  GET from / or /RPC2 or /blahblahblah with the same results.
  Security scanners that look for /cgi-bin/phf will therefore report
  lots of vulnerabilities.

  Fix: add a .rpc_paths attribute to the SimpleXMLRPCServer class,
  and report a 404 error if the path isn't on the allowed list.

  Possibly-controversial aspect of this change: the default makes only
  '/' and '/RPC2' legal.  Maybe this will break people's applications
  (though I doubt it).  We could just set the default to an empty tuple,
  which would exactly match the current behaviour.
........
  r46579 | andrew.kuchling | 2006-05-31 16:12:47 +0200 (Wed, 31 May 2006) | 1 line

  Mention SimpleXMLRPCServer change
........
  r46580 | tim.peters | 2006-05-31 16:28:07 +0200 (Wed, 31 May 2006) | 2 lines

  Trimmed trailing whitespace.
........
  r46581 | tim.peters | 2006-05-31 17:33:22 +0200 (Wed, 31 May 2006) | 4 lines

  _range_error():  Speed and simplify (there's no real need for
  loops here).  Assert that size_t is actually big enough, and
  that f->size is at least one.  Wrap a long line.
........
  r46582 | tim.peters | 2006-05-31 17:34:37 +0200 (Wed, 31 May 2006) | 2 lines

  Repaired error in new comment.
........
  r46584 | neal.norwitz | 2006-06-01 07:32:49 +0200 (Thu, 01 Jun 2006) | 4 lines

  Remove ; at end of macro.  There was a compiler recently that warned
  about extra semi-colons.  It may have been the HP C compiler.
  This file will trigger a bunch of those warnings now.
........
  r46585 | georg.brandl | 2006-06-01 08:39:19 +0200 (Thu, 01 Jun 2006) | 3 lines

  Correctly unpickle 2.4 exceptions via __setstate__ (patch #1498571)
........
  r46586 | georg.brandl | 2006-06-01 10:27:32 +0200 (Thu, 01 Jun 2006) | 3 lines

  Correctly allocate complex types with tp_alloc. (bug #1498638)
........
  r46587 | georg.brandl | 2006-06-01 14:30:46 +0200 (Thu, 01 Jun 2006) | 2 lines

  Correctly dispatch Faults in loads (patch #1498627)
........
  r46588 | georg.brandl | 2006-06-01 15:00:49 +0200 (Thu, 01 Jun 2006) | 3 lines

  Some code style tweaks, and remove apply.
........
  r46589 | armin.rigo | 2006-06-01 15:19:12 +0200 (Thu, 01 Jun 2006) | 5 lines

  [ 1497053 ] Let dicts propagate the exceptions in user __eq__().

  [ 1456209 ] dictresize() vulnerability ( <- backport candidate ).
........
  r46590 | tim.peters | 2006-06-01 15:41:46 +0200 (Thu, 01 Jun 2006) | 2 lines

  Whitespace normalization.
........
  r46591 | tim.peters | 2006-06-01 15:49:23 +0200 (Thu, 01 Jun 2006) | 2 lines

  Record bugs 1275608 and 1456209 as being fixed.
........
  r46592 | tim.peters | 2006-06-01 15:56:26 +0200 (Thu, 01 Jun 2006) | 5 lines

  Re-enable a new empty-string test added during the NFS sprint,
  but disabled then because str and unicode strings gave different
  results.  The implementations were repaired later during the
  sprint, but the new test remained disabled.
........
  r46594 | tim.peters | 2006-06-01 17:50:44 +0200 (Thu, 01 Jun 2006) | 7 lines

  Armin committed his patch while I was reviewing it (I'm sure
  he didn't know this), so merged in some changes I made during
  review.  Nothing material apart from changing a new `mask` local
  from int to Py_ssize_t.  Mostly this is repairing comments that
  were made incorrect, and adding new comments.  Also a few
  minor code rewrites for clarity or helpful succinctness.
........
  r46599 | neal.norwitz | 2006-06-02 06:45:53 +0200 (Fri, 02 Jun 2006) | 1 line

  Convert docstrings to comments so regrtest -v prints method names
........
  r46600 | neal.norwitz | 2006-06-02 06:50:49 +0200 (Fri, 02 Jun 2006) | 2 lines

  Fix memory leak found by valgrind.
........
  r46601 | neal.norwitz | 2006-06-02 06:54:52 +0200 (Fri, 02 Jun 2006) | 1 line

  More memory leaks from valgrind
........
  r46602 | neal.norwitz | 2006-06-02 08:23:00 +0200 (Fri, 02 Jun 2006) | 11 lines

  Patch #1357836:

  Prevent an invalid memory read from test_coding in case the done flag is set.
  In that case, the loop isn't entered.  I wonder if rather than setting
  the done flag in the cases before the loop, if they should just exit early.

  This code looks like it should be refactored.

  Backport candidate (also the early break above if decoding_fgets fails)
........
  r46603 | martin.blais | 2006-06-02 15:03:43 +0200 (Fri, 02 Jun 2006) | 1 line

  Fixed struct test to not use unittest.
........
  r46605 | tim.peters | 2006-06-03 01:22:51 +0200 (Sat, 03 Jun 2006) | 10 lines

  pprint functions used to sort a dict (by key) if and only if
  the output required more than one line.  "Small" dicts got
  displayed in seemingly random order (the hash-induced order
  produced by dict.__repr__).  None of this was documented.
  Now pprint functions always sort dicts by key, and the docs
  promise it.

  This was proposed and agreed to during the PyCon 2006 core
  sprint -- I just didn't have time for it before now.
........
2006-06-08 14:42:34 +00:00

1136 lines
52 KiB
Python

"""
Common tests shared by test_str, test_unicode, test_userstring and test_string.
"""
import unittest, string, sys
from test import test_support
from UserList import UserList
class Sequence:
def __init__(self, seq='wxyz'): self.seq = seq
def __len__(self): return len(self.seq)
def __getitem__(self, i): return self.seq[i]
class BadSeq1(Sequence):
def __init__(self): self.seq = [7, 'hello', 123L]
class BadSeq2(Sequence):
def __init__(self): self.seq = ['a', 'b', 'c']
def __len__(self): return 8
class CommonTest(unittest.TestCase):
# This testcase contains test that can be used in all
# stringlike classes. Currently this is str, unicode
# UserString and the string module.
# The type to be tested
# Change in subclasses to change the behaviour of fixtesttype()
type2test = None
# All tests pass their arguments to the testing methods
# as str objects. fixtesttype() can be used to propagate
# these arguments to the appropriate type
def fixtype(self, obj):
if isinstance(obj, str):
return self.__class__.type2test(obj)
elif isinstance(obj, list):
return [self.fixtype(x) for x in obj]
elif isinstance(obj, tuple):
return tuple([self.fixtype(x) for x in obj])
elif isinstance(obj, dict):
return dict([
(self.fixtype(key), self.fixtype(value))
for (key, value) in obj.iteritems()
])
else:
return obj
# check that object.method(*args) returns result
def checkequal(self, result, object, methodname, *args):
result = self.fixtype(result)
object = self.fixtype(object)
args = self.fixtype(args)
realresult = getattr(object, methodname)(*args)
self.assertEqual(
result,
realresult
)
# if the original is returned make sure that
# this doesn't happen with subclasses
if object == realresult:
class subtype(self.__class__.type2test):
pass
object = subtype(object)
realresult = getattr(object, methodname)(*args)
self.assert_(object is not realresult)
# check that object.method(*args) raises exc
def checkraises(self, exc, object, methodname, *args):
object = self.fixtype(object)
args = self.fixtype(args)
self.assertRaises(
exc,
getattr(object, methodname),
*args
)
# call object.method(*args) without any checks
def checkcall(self, object, methodname, *args):
object = self.fixtype(object)
args = self.fixtype(args)
getattr(object, methodname)(*args)
def test_hash(self):
# SF bug 1054139: += optimization was not invalidating cached hash value
a = self.type2test('DNSSEC')
b = self.type2test('')
for c in a:
b += c
hash(b)
self.assertEqual(hash(a), hash(b))
def test_capitalize(self):
self.checkequal(' hello ', ' hello ', 'capitalize')
self.checkequal('Hello ', 'Hello ','capitalize')
self.checkequal('Hello ', 'hello ','capitalize')
self.checkequal('Aaaa', 'aaaa', 'capitalize')
self.checkequal('Aaaa', 'AaAa', 'capitalize')
self.checkraises(TypeError, 'hello', 'capitalize', 42)
def test_count(self):
self.checkequal(3, 'aaa', 'count', 'a')
self.checkequal(0, 'aaa', 'count', 'b')
self.checkequal(3, 'aaa', 'count', 'a')
self.checkequal(0, 'aaa', 'count', 'b')
self.checkequal(3, 'aaa', 'count', 'a')
self.checkequal(0, 'aaa', 'count', 'b')
self.checkequal(0, 'aaa', 'count', 'b')
self.checkequal(2, 'aaa', 'count', 'a', 1)
self.checkequal(0, 'aaa', 'count', 'a', 10)
self.checkequal(1, 'aaa', 'count', 'a', -1)
self.checkequal(3, 'aaa', 'count', 'a', -10)
self.checkequal(1, 'aaa', 'count', 'a', 0, 1)
self.checkequal(3, 'aaa', 'count', 'a', 0, 10)
self.checkequal(2, 'aaa', 'count', 'a', 0, -1)
self.checkequal(0, 'aaa', 'count', 'a', 0, -10)
self.checkequal(3, 'aaa', 'count', '', 1)
self.checkequal(1, 'aaa', 'count', '', 3)
self.checkequal(0, 'aaa', 'count', '', 10)
self.checkequal(2, 'aaa', 'count', '', -1)
self.checkequal(4, 'aaa', 'count', '', -10)
self.checkraises(TypeError, 'hello', 'count')
self.checkraises(TypeError, 'hello', 'count', 42)
# For a variety of combinations,
# verify that str.count() matches an equivalent function
# replacing all occurrences and then differencing the string lengths
charset = ['', 'a', 'b']
digits = 7
base = len(charset)
teststrings = set()
for i in xrange(base ** digits):
entry = []
for j in xrange(digits):
i, m = divmod(i, base)
entry.append(charset[m])
teststrings.add(''.join(entry))
teststrings = list(teststrings)
for i in teststrings:
i = self.fixtype(i)
n = len(i)
for j in teststrings:
r1 = i.count(j)
if j:
r2, rem = divmod(n - len(i.replace(j, '')), len(j))
else:
r2, rem = len(i)+1, 0
if rem or r1 != r2:
self.assertEqual(rem, 0)
self.assertEqual(r1, r2)
def test_find(self):
self.checkequal(0, 'abcdefghiabc', 'find', 'abc')
self.checkequal(9, 'abcdefghiabc', 'find', 'abc', 1)
self.checkequal(-1, 'abcdefghiabc', 'find', 'def', 4)
self.checkequal(0, 'abc', 'find', '', 0)
self.checkequal(3, 'abc', 'find', '', 3)
self.checkequal(-1, 'abc', 'find', '', 4)
self.checkraises(TypeError, 'hello', 'find')
self.checkraises(TypeError, 'hello', 'find', 42)
# For a variety of combinations,
# verify that str.find() matches __contains__
# and that the found substring is really at that location
charset = ['', 'a', 'b', 'c']
digits = 5
base = len(charset)
teststrings = set()
for i in xrange(base ** digits):
entry = []
for j in xrange(digits):
i, m = divmod(i, base)
entry.append(charset[m])
teststrings.add(''.join(entry))
teststrings = list(teststrings)
for i in teststrings:
i = self.fixtype(i)
for j in teststrings:
loc = i.find(j)
r1 = (loc != -1)
r2 = j in i
if r1 != r2:
self.assertEqual(r1, r2)
if loc != -1:
self.assertEqual(i[loc:loc+len(j)], j)
def test_rfind(self):
self.checkequal(9, 'abcdefghiabc', 'rfind', 'abc')
self.checkequal(12, 'abcdefghiabc', 'rfind', '')
self.checkequal(0, 'abcdefghiabc', 'rfind', 'abcd')
self.checkequal(-1, 'abcdefghiabc', 'rfind', 'abcz')
self.checkequal(3, 'abc', 'rfind', '', 0)
self.checkequal(3, 'abc', 'rfind', '', 3)
self.checkequal(-1, 'abc', 'rfind', '', 4)
self.checkraises(TypeError, 'hello', 'rfind')
self.checkraises(TypeError, 'hello', 'rfind', 42)
def test_index(self):
self.checkequal(0, 'abcdefghiabc', 'index', '')
self.checkequal(3, 'abcdefghiabc', 'index', 'def')
self.checkequal(0, 'abcdefghiabc', 'index', 'abc')
self.checkequal(9, 'abcdefghiabc', 'index', 'abc', 1)
self.checkraises(ValueError, 'abcdefghiabc', 'index', 'hib')
self.checkraises(ValueError, 'abcdefghiab', 'index', 'abc', 1)
self.checkraises(ValueError, 'abcdefghi', 'index', 'ghi', 8)
self.checkraises(ValueError, 'abcdefghi', 'index', 'ghi', -1)
self.checkraises(TypeError, 'hello', 'index')
self.checkraises(TypeError, 'hello', 'index', 42)
def test_rindex(self):
self.checkequal(12, 'abcdefghiabc', 'rindex', '')
self.checkequal(3, 'abcdefghiabc', 'rindex', 'def')
self.checkequal(9, 'abcdefghiabc', 'rindex', 'abc')
self.checkequal(0, 'abcdefghiabc', 'rindex', 'abc', 0, -1)
self.checkraises(ValueError, 'abcdefghiabc', 'rindex', 'hib')
self.checkraises(ValueError, 'defghiabc', 'rindex', 'def', 1)
self.checkraises(ValueError, 'defghiabc', 'rindex', 'abc', 0, -1)
self.checkraises(ValueError, 'abcdefghi', 'rindex', 'ghi', 0, 8)
self.checkraises(ValueError, 'abcdefghi', 'rindex', 'ghi', 0, -1)
self.checkraises(TypeError, 'hello', 'rindex')
self.checkraises(TypeError, 'hello', 'rindex', 42)
def test_lower(self):
self.checkequal('hello', 'HeLLo', 'lower')
self.checkequal('hello', 'hello', 'lower')
self.checkraises(TypeError, 'hello', 'lower', 42)
def test_upper(self):
self.checkequal('HELLO', 'HeLLo', 'upper')
self.checkequal('HELLO', 'HELLO', 'upper')
self.checkraises(TypeError, 'hello', 'upper', 42)
def test_expandtabs(self):
self.checkequal('abc\rab def\ng hi', 'abc\rab\tdef\ng\thi', 'expandtabs')
self.checkequal('abc\rab def\ng hi', 'abc\rab\tdef\ng\thi', 'expandtabs', 8)
self.checkequal('abc\rab def\ng hi', 'abc\rab\tdef\ng\thi', 'expandtabs', 4)
self.checkequal('abc\r\nab def\ng hi', 'abc\r\nab\tdef\ng\thi', 'expandtabs', 4)
self.checkequal('abc\rab def\ng hi', 'abc\rab\tdef\ng\thi', 'expandtabs')
self.checkequal('abc\rab def\ng hi', 'abc\rab\tdef\ng\thi', 'expandtabs', 8)
self.checkequal('abc\r\nab\r\ndef\ng\r\nhi', 'abc\r\nab\r\ndef\ng\r\nhi', 'expandtabs', 4)
self.checkraises(TypeError, 'hello', 'expandtabs', 42, 42)
def test_split(self):
self.checkequal(['this', 'is', 'the', 'split', 'function'],
'this is the split function', 'split')
# by whitespace
self.checkequal(['a', 'b', 'c', 'd'], 'a b c d ', 'split')
self.checkequal(['a', 'b c d'], 'a b c d', 'split', None, 1)
self.checkequal(['a', 'b', 'c d'], 'a b c d', 'split', None, 2)
self.checkequal(['a', 'b', 'c', 'd'], 'a b c d', 'split', None, 3)
self.checkequal(['a', 'b', 'c', 'd'], 'a b c d', 'split', None, 4)
self.checkequal(['a', 'b', 'c', 'd'], 'a b c d', 'split', None,
sys.maxint-1)
self.checkequal(['a b c d'], 'a b c d', 'split', None, 0)
self.checkequal(['a b c d'], ' a b c d', 'split', None, 0)
self.checkequal(['a', 'b', 'c d'], 'a b c d', 'split', None, 2)
self.checkequal([], ' ', 'split')
self.checkequal(['a'], ' a ', 'split')
self.checkequal(['a', 'b'], ' a b ', 'split')
self.checkequal(['a', 'b '], ' a b ', 'split', None, 1)
self.checkequal(['a', 'b c '], ' a b c ', 'split', None, 1)
self.checkequal(['a', 'b', 'c '], ' a b c ', 'split', None, 2)
self.checkequal(['a', 'b'], '\n\ta \t\r b \v ', 'split')
aaa = ' a '*20
self.checkequal(['a']*20, aaa, 'split')
self.checkequal(['a'] + [aaa[4:]], aaa, 'split', None, 1)
self.checkequal(['a']*19 + ['a '], aaa, 'split', None, 19)
# by a char
self.checkequal(['a', 'b', 'c', 'd'], 'a|b|c|d', 'split', '|')
self.checkequal(['a|b|c|d'], 'a|b|c|d', 'split', '|', 0)
self.checkequal(['a', 'b|c|d'], 'a|b|c|d', 'split', '|', 1)
self.checkequal(['a', 'b', 'c|d'], 'a|b|c|d', 'split', '|', 2)
self.checkequal(['a', 'b', 'c', 'd'], 'a|b|c|d', 'split', '|', 3)
self.checkequal(['a', 'b', 'c', 'd'], 'a|b|c|d', 'split', '|', 4)
self.checkequal(['a', 'b', 'c', 'd'], 'a|b|c|d', 'split', '|',
sys.maxint-2)
self.checkequal(['a|b|c|d'], 'a|b|c|d', 'split', '|', 0)
self.checkequal(['a', '', 'b||c||d'], 'a||b||c||d', 'split', '|', 2)
self.checkequal(['endcase ', ''], 'endcase |', 'split', '|')
self.checkequal(['', ' startcase'], '| startcase', 'split', '|')
self.checkequal(['', 'bothcase', ''], '|bothcase|', 'split', '|')
self.checkequal(['a', '', 'b\x00c\x00d'], 'a\x00\x00b\x00c\x00d', 'split', '\x00', 2)
self.checkequal(['a']*20, ('a|'*20)[:-1], 'split', '|')
self.checkequal(['a']*15 +['a|a|a|a|a'],
('a|'*20)[:-1], 'split', '|', 15)
# by string
self.checkequal(['a', 'b', 'c', 'd'], 'a//b//c//d', 'split', '//')
self.checkequal(['a', 'b//c//d'], 'a//b//c//d', 'split', '//', 1)
self.checkequal(['a', 'b', 'c//d'], 'a//b//c//d', 'split', '//', 2)
self.checkequal(['a', 'b', 'c', 'd'], 'a//b//c//d', 'split', '//', 3)
self.checkequal(['a', 'b', 'c', 'd'], 'a//b//c//d', 'split', '//', 4)
self.checkequal(['a', 'b', 'c', 'd'], 'a//b//c//d', 'split', '//',
sys.maxint-10)
self.checkequal(['a//b//c//d'], 'a//b//c//d', 'split', '//', 0)
self.checkequal(['a', '', 'b////c////d'], 'a////b////c////d', 'split', '//', 2)
self.checkequal(['endcase ', ''], 'endcase test', 'split', 'test')
self.checkequal(['', ' begincase'], 'test begincase', 'split', 'test')
self.checkequal(['', ' bothcase ', ''], 'test bothcase test',
'split', 'test')
self.checkequal(['a', 'bc'], 'abbbc', 'split', 'bb')
self.checkequal(['', ''], 'aaa', 'split', 'aaa')
self.checkequal(['aaa'], 'aaa', 'split', 'aaa', 0)
self.checkequal(['ab', 'ab'], 'abbaab', 'split', 'ba')
self.checkequal(['aaaa'], 'aaaa', 'split', 'aab')
self.checkequal([''], '', 'split', 'aaa')
self.checkequal(['aa'], 'aa', 'split', 'aaa')
self.checkequal(['A', 'bobb'], 'Abbobbbobb', 'split', 'bbobb')
self.checkequal(['A', 'B', ''], 'AbbobbBbbobb', 'split', 'bbobb')
self.checkequal(['a']*20, ('aBLAH'*20)[:-4], 'split', 'BLAH')
self.checkequal(['a']*20, ('aBLAH'*20)[:-4], 'split', 'BLAH', 19)
self.checkequal(['a']*18 + ['aBLAHa'], ('aBLAH'*20)[:-4],
'split', 'BLAH', 18)
# mixed use of str and unicode
self.checkequal([u'a', u'b', u'c d'], 'a b c d', 'split', u' ', 2)
# argument type
self.checkraises(TypeError, 'hello', 'split', 42, 42, 42)
# null case
self.checkraises(ValueError, 'hello', 'split', '')
self.checkraises(ValueError, 'hello', 'split', '', 0)
def test_rsplit(self):
self.checkequal(['this', 'is', 'the', 'rsplit', 'function'],
'this is the rsplit function', 'rsplit')
# by whitespace
self.checkequal(['a', 'b', 'c', 'd'], 'a b c d ', 'rsplit')
self.checkequal(['a b c', 'd'], 'a b c d', 'rsplit', None, 1)
self.checkequal(['a b', 'c', 'd'], 'a b c d', 'rsplit', None, 2)
self.checkequal(['a', 'b', 'c', 'd'], 'a b c d', 'rsplit', None, 3)
self.checkequal(['a', 'b', 'c', 'd'], 'a b c d', 'rsplit', None, 4)
self.checkequal(['a', 'b', 'c', 'd'], 'a b c d', 'rsplit', None,
sys.maxint-20)
self.checkequal(['a b c d'], 'a b c d', 'rsplit', None, 0)
self.checkequal(['a b c d'], 'a b c d ', 'rsplit', None, 0)
self.checkequal(['a b', 'c', 'd'], 'a b c d', 'rsplit', None, 2)
self.checkequal([], ' ', 'rsplit')
self.checkequal(['a'], ' a ', 'rsplit')
self.checkequal(['a', 'b'], ' a b ', 'rsplit')
self.checkequal([' a', 'b'], ' a b ', 'rsplit', None, 1)
self.checkequal([' a b','c'], ' a b c ', 'rsplit',
None, 1)
self.checkequal([' a', 'b', 'c'], ' a b c ', 'rsplit',
None, 2)
self.checkequal(['a', 'b'], '\n\ta \t\r b \v ', 'rsplit', None, 88)
aaa = ' a '*20
self.checkequal(['a']*20, aaa, 'rsplit')
self.checkequal([aaa[:-4]] + ['a'], aaa, 'rsplit', None, 1)
self.checkequal([' a a'] + ['a']*18, aaa, 'rsplit', None, 18)
# by a char
self.checkequal(['a', 'b', 'c', 'd'], 'a|b|c|d', 'rsplit', '|')
self.checkequal(['a|b|c', 'd'], 'a|b|c|d', 'rsplit', '|', 1)
self.checkequal(['a|b', 'c', 'd'], 'a|b|c|d', 'rsplit', '|', 2)
self.checkequal(['a', 'b', 'c', 'd'], 'a|b|c|d', 'rsplit', '|', 3)
self.checkequal(['a', 'b', 'c', 'd'], 'a|b|c|d', 'rsplit', '|', 4)
self.checkequal(['a', 'b', 'c', 'd'], 'a|b|c|d', 'rsplit', '|',
sys.maxint-100)
self.checkequal(['a|b|c|d'], 'a|b|c|d', 'rsplit', '|', 0)
self.checkequal(['a||b||c', '', 'd'], 'a||b||c||d', 'rsplit', '|', 2)
self.checkequal(['', ' begincase'], '| begincase', 'rsplit', '|')
self.checkequal(['endcase ', ''], 'endcase |', 'rsplit', '|')
self.checkequal(['', 'bothcase', ''], '|bothcase|', 'rsplit', '|')
self.checkequal(['a\x00\x00b', 'c', 'd'], 'a\x00\x00b\x00c\x00d', 'rsplit', '\x00', 2)
self.checkequal(['a']*20, ('a|'*20)[:-1], 'rsplit', '|')
self.checkequal(['a|a|a|a|a']+['a']*15,
('a|'*20)[:-1], 'rsplit', '|', 15)
# by string
self.checkequal(['a', 'b', 'c', 'd'], 'a//b//c//d', 'rsplit', '//')
self.checkequal(['a//b//c', 'd'], 'a//b//c//d', 'rsplit', '//', 1)
self.checkequal(['a//b', 'c', 'd'], 'a//b//c//d', 'rsplit', '//', 2)
self.checkequal(['a', 'b', 'c', 'd'], 'a//b//c//d', 'rsplit', '//', 3)
self.checkequal(['a', 'b', 'c', 'd'], 'a//b//c//d', 'rsplit', '//', 4)
self.checkequal(['a', 'b', 'c', 'd'], 'a//b//c//d', 'rsplit', '//',
sys.maxint-5)
self.checkequal(['a//b//c//d'], 'a//b//c//d', 'rsplit', '//', 0)
self.checkequal(['a////b////c', '', 'd'], 'a////b////c////d', 'rsplit', '//', 2)
self.checkequal(['', ' begincase'], 'test begincase', 'rsplit', 'test')
self.checkequal(['endcase ', ''], 'endcase test', 'rsplit', 'test')
self.checkequal(['', ' bothcase ', ''], 'test bothcase test',
'rsplit', 'test')
self.checkequal(['ab', 'c'], 'abbbc', 'rsplit', 'bb')
self.checkequal(['', ''], 'aaa', 'rsplit', 'aaa')
self.checkequal(['aaa'], 'aaa', 'rsplit', 'aaa', 0)
self.checkequal(['ab', 'ab'], 'abbaab', 'rsplit', 'ba')
self.checkequal(['aaaa'], 'aaaa', 'rsplit', 'aab')
self.checkequal([''], '', 'rsplit', 'aaa')
self.checkequal(['aa'], 'aa', 'rsplit', 'aaa')
self.checkequal(['bbob', 'A'], 'bbobbbobbA', 'rsplit', 'bbobb')
self.checkequal(['', 'B', 'A'], 'bbobbBbbobbA', 'rsplit', 'bbobb')
self.checkequal(['a']*20, ('aBLAH'*20)[:-4], 'rsplit', 'BLAH')
self.checkequal(['a']*20, ('aBLAH'*20)[:-4], 'rsplit', 'BLAH', 19)
self.checkequal(['aBLAHa'] + ['a']*18, ('aBLAH'*20)[:-4],
'rsplit', 'BLAH', 18)
# mixed use of str and unicode
self.checkequal([u'a b', u'c', u'd'], 'a b c d', 'rsplit', u' ', 2)
# argument type
self.checkraises(TypeError, 'hello', 'rsplit', 42, 42, 42)
# null case
self.checkraises(ValueError, 'hello', 'rsplit', '')
self.checkraises(ValueError, 'hello', 'rsplit', '', 0)
def test_strip(self):
self.checkequal('hello', ' hello ', 'strip')
self.checkequal('hello ', ' hello ', 'lstrip')
self.checkequal(' hello', ' hello ', 'rstrip')
self.checkequal('hello', 'hello', 'strip')
# strip/lstrip/rstrip with None arg
self.checkequal('hello', ' hello ', 'strip', None)
self.checkequal('hello ', ' hello ', 'lstrip', None)
self.checkequal(' hello', ' hello ', 'rstrip', None)
self.checkequal('hello', 'hello', 'strip', None)
# strip/lstrip/rstrip with str arg
self.checkequal('hello', 'xyzzyhelloxyzzy', 'strip', 'xyz')
self.checkequal('helloxyzzy', 'xyzzyhelloxyzzy', 'lstrip', 'xyz')
self.checkequal('xyzzyhello', 'xyzzyhelloxyzzy', 'rstrip', 'xyz')
self.checkequal('hello', 'hello', 'strip', 'xyz')
# strip/lstrip/rstrip with unicode arg
if test_support.have_unicode:
self.checkequal(unicode('hello', 'ascii'), 'xyzzyhelloxyzzy',
'strip', unicode('xyz', 'ascii'))
self.checkequal(unicode('helloxyzzy', 'ascii'), 'xyzzyhelloxyzzy',
'lstrip', unicode('xyz', 'ascii'))
self.checkequal(unicode('xyzzyhello', 'ascii'), 'xyzzyhelloxyzzy',
'rstrip', unicode('xyz', 'ascii'))
self.checkequal(unicode('hello', 'ascii'), 'hello',
'strip', unicode('xyz', 'ascii'))
self.checkraises(TypeError, 'hello', 'strip', 42, 42)
self.checkraises(TypeError, 'hello', 'lstrip', 42, 42)
self.checkraises(TypeError, 'hello', 'rstrip', 42, 42)
def test_ljust(self):
self.checkequal('abc ', 'abc', 'ljust', 10)
self.checkequal('abc ', 'abc', 'ljust', 6)
self.checkequal('abc', 'abc', 'ljust', 3)
self.checkequal('abc', 'abc', 'ljust', 2)
self.checkequal('abc*******', 'abc', 'ljust', 10, '*')
self.checkraises(TypeError, 'abc', 'ljust')
def test_rjust(self):
self.checkequal(' abc', 'abc', 'rjust', 10)
self.checkequal(' abc', 'abc', 'rjust', 6)
self.checkequal('abc', 'abc', 'rjust', 3)
self.checkequal('abc', 'abc', 'rjust', 2)
self.checkequal('*******abc', 'abc', 'rjust', 10, '*')
self.checkraises(TypeError, 'abc', 'rjust')
def test_center(self):
self.checkequal(' abc ', 'abc', 'center', 10)
self.checkequal(' abc ', 'abc', 'center', 6)
self.checkequal('abc', 'abc', 'center', 3)
self.checkequal('abc', 'abc', 'center', 2)
self.checkequal('***abc****', 'abc', 'center', 10, '*')
self.checkraises(TypeError, 'abc', 'center')
def test_swapcase(self):
self.checkequal('hEllO CoMPuTErS', 'HeLLo cOmpUteRs', 'swapcase')
self.checkraises(TypeError, 'hello', 'swapcase', 42)
def test_replace(self):
EQ = self.checkequal
# Operations on the empty string
EQ("", "", "replace", "", "")
EQ("A", "", "replace", "", "A")
EQ("", "", "replace", "A", "")
EQ("", "", "replace", "A", "A")
EQ("", "", "replace", "", "", 100)
EQ("", "", "replace", "", "", sys.maxint)
# interleave (from=="", 'to' gets inserted everywhere)
EQ("A", "A", "replace", "", "")
EQ("*A*", "A", "replace", "", "*")
EQ("*1A*1", "A", "replace", "", "*1")
EQ("*-#A*-#", "A", "replace", "", "*-#")
EQ("*-A*-A*-", "AA", "replace", "", "*-")
EQ("*-A*-A*-", "AA", "replace", "", "*-", -1)
EQ("*-A*-A*-", "AA", "replace", "", "*-", sys.maxint)
EQ("*-A*-A*-", "AA", "replace", "", "*-", 4)
EQ("*-A*-A*-", "AA", "replace", "", "*-", 3)
EQ("*-A*-A", "AA", "replace", "", "*-", 2)
EQ("*-AA", "AA", "replace", "", "*-", 1)
EQ("AA", "AA", "replace", "", "*-", 0)
# single character deletion (from=="A", to=="")
EQ("", "A", "replace", "A", "")
EQ("", "AAA", "replace", "A", "")
EQ("", "AAA", "replace", "A", "", -1)
EQ("", "AAA", "replace", "A", "", sys.maxint)
EQ("", "AAA", "replace", "A", "", 4)
EQ("", "AAA", "replace", "A", "", 3)
EQ("A", "AAA", "replace", "A", "", 2)
EQ("AA", "AAA", "replace", "A", "", 1)
EQ("AAA", "AAA", "replace", "A", "", 0)
EQ("", "AAAAAAAAAA", "replace", "A", "")
EQ("BCD", "ABACADA", "replace", "A", "")
EQ("BCD", "ABACADA", "replace", "A", "", -1)
EQ("BCD", "ABACADA", "replace", "A", "", sys.maxint)
EQ("BCD", "ABACADA", "replace", "A", "", 5)
EQ("BCD", "ABACADA", "replace", "A", "", 4)
EQ("BCDA", "ABACADA", "replace", "A", "", 3)
EQ("BCADA", "ABACADA", "replace", "A", "", 2)
EQ("BACADA", "ABACADA", "replace", "A", "", 1)
EQ("ABACADA", "ABACADA", "replace", "A", "", 0)
EQ("BCD", "ABCAD", "replace", "A", "")
EQ("BCD", "ABCADAA", "replace", "A", "")
EQ("BCD", "BCD", "replace", "A", "")
EQ("*************", "*************", "replace", "A", "")
EQ("^A^", "^"+"A"*1000+"^", "replace", "A", "", 999)
# substring deletion (from=="the", to=="")
EQ("", "the", "replace", "the", "")
EQ("ater", "theater", "replace", "the", "")
EQ("", "thethe", "replace", "the", "")
EQ("", "thethethethe", "replace", "the", "")
EQ("aaaa", "theatheatheathea", "replace", "the", "")
EQ("that", "that", "replace", "the", "")
EQ("thaet", "thaet", "replace", "the", "")
EQ("here and re", "here and there", "replace", "the", "")
EQ("here and re and re", "here and there and there",
"replace", "the", "", sys.maxint)
EQ("here and re and re", "here and there and there",
"replace", "the", "", -1)
EQ("here and re and re", "here and there and there",
"replace", "the", "", 3)
EQ("here and re and re", "here and there and there",
"replace", "the", "", 2)
EQ("here and re and there", "here and there and there",
"replace", "the", "", 1)
EQ("here and there and there", "here and there and there",
"replace", "the", "", 0)
EQ("here and re and re", "here and there and there", "replace", "the", "")
EQ("abc", "abc", "replace", "the", "")
EQ("abcdefg", "abcdefg", "replace", "the", "")
# substring deletion (from=="bob", to=="")
EQ("bob", "bbobob", "replace", "bob", "")
EQ("bobXbob", "bbobobXbbobob", "replace", "bob", "")
EQ("aaaaaaa", "aaaaaaabob", "replace", "bob", "")
EQ("aaaaaaa", "aaaaaaa", "replace", "bob", "")
# single character replace in place (len(from)==len(to)==1)
EQ("Who goes there?", "Who goes there?", "replace", "o", "o")
EQ("WhO gOes there?", "Who goes there?", "replace", "o", "O")
EQ("WhO gOes there?", "Who goes there?", "replace", "o", "O", sys.maxint)
EQ("WhO gOes there?", "Who goes there?", "replace", "o", "O", -1)
EQ("WhO gOes there?", "Who goes there?", "replace", "o", "O", 3)
EQ("WhO gOes there?", "Who goes there?", "replace", "o", "O", 2)
EQ("WhO goes there?", "Who goes there?", "replace", "o", "O", 1)
EQ("Who goes there?", "Who goes there?", "replace", "o", "O", 0)
EQ("Who goes there?", "Who goes there?", "replace", "a", "q")
EQ("who goes there?", "Who goes there?", "replace", "W", "w")
EQ("wwho goes there?ww", "WWho goes there?WW", "replace", "W", "w")
EQ("Who goes there!", "Who goes there?", "replace", "?", "!")
EQ("Who goes there!!", "Who goes there??", "replace", "?", "!")
EQ("Who goes there?", "Who goes there?", "replace", ".", "!")
# substring replace in place (len(from)==len(to) > 1)
EQ("Th** ** a t**sue", "This is a tissue", "replace", "is", "**")
EQ("Th** ** a t**sue", "This is a tissue", "replace", "is", "**", sys.maxint)
EQ("Th** ** a t**sue", "This is a tissue", "replace", "is", "**", -1)
EQ("Th** ** a t**sue", "This is a tissue", "replace", "is", "**", 4)
EQ("Th** ** a t**sue", "This is a tissue", "replace", "is", "**", 3)
EQ("Th** ** a tissue", "This is a tissue", "replace", "is", "**", 2)
EQ("Th** is a tissue", "This is a tissue", "replace", "is", "**", 1)
EQ("This is a tissue", "This is a tissue", "replace", "is", "**", 0)
EQ("cobob", "bobob", "replace", "bob", "cob")
EQ("cobobXcobocob", "bobobXbobobob", "replace", "bob", "cob")
EQ("bobob", "bobob", "replace", "bot", "bot")
# replace single character (len(from)==1, len(to)>1)
EQ("ReyKKjaviKK", "Reykjavik", "replace", "k", "KK")
EQ("ReyKKjaviKK", "Reykjavik", "replace", "k", "KK", -1)
EQ("ReyKKjaviKK", "Reykjavik", "replace", "k", "KK", sys.maxint)
EQ("ReyKKjaviKK", "Reykjavik", "replace", "k", "KK", 2)
EQ("ReyKKjavik", "Reykjavik", "replace", "k", "KK", 1)
EQ("Reykjavik", "Reykjavik", "replace", "k", "KK", 0)
EQ("A----B----C----", "A.B.C.", "replace", ".", "----")
EQ("Reykjavik", "Reykjavik", "replace", "q", "KK")
# replace substring (len(from)>1, len(to)!=len(from))
EQ("ham, ham, eggs and ham", "spam, spam, eggs and spam",
"replace", "spam", "ham")
EQ("ham, ham, eggs and ham", "spam, spam, eggs and spam",
"replace", "spam", "ham", sys.maxint)
EQ("ham, ham, eggs and ham", "spam, spam, eggs and spam",
"replace", "spam", "ham", -1)
EQ("ham, ham, eggs and ham", "spam, spam, eggs and spam",
"replace", "spam", "ham", 4)
EQ("ham, ham, eggs and ham", "spam, spam, eggs and spam",
"replace", "spam", "ham", 3)
EQ("ham, ham, eggs and spam", "spam, spam, eggs and spam",
"replace", "spam", "ham", 2)
EQ("ham, spam, eggs and spam", "spam, spam, eggs and spam",
"replace", "spam", "ham", 1)
EQ("spam, spam, eggs and spam", "spam, spam, eggs and spam",
"replace", "spam", "ham", 0)
EQ("bobob", "bobobob", "replace", "bobob", "bob")
EQ("bobobXbobob", "bobobobXbobobob", "replace", "bobob", "bob")
EQ("BOBOBOB", "BOBOBOB", "replace", "bob", "bobby")
#
self.checkequal('one@two!three!', 'one!two!three!', 'replace', '!', '@', 1)
self.checkequal('onetwothree', 'one!two!three!', 'replace', '!', '')
self.checkequal('one@two@three!', 'one!two!three!', 'replace', '!', '@', 2)
self.checkequal('one@two@three@', 'one!two!three!', 'replace', '!', '@', 3)
self.checkequal('one@two@three@', 'one!two!three!', 'replace', '!', '@', 4)
self.checkequal('one!two!three!', 'one!two!three!', 'replace', '!', '@', 0)
self.checkequal('one@two@three@', 'one!two!three!', 'replace', '!', '@')
self.checkequal('one!two!three!', 'one!two!three!', 'replace', 'x', '@')
self.checkequal('one!two!three!', 'one!two!three!', 'replace', 'x', '@', 2)
self.checkequal('-a-b-c-', 'abc', 'replace', '', '-')
self.checkequal('-a-b-c', 'abc', 'replace', '', '-', 3)
self.checkequal('abc', 'abc', 'replace', '', '-', 0)
self.checkequal('', '', 'replace', '', '')
self.checkequal('abc', 'abc', 'replace', 'ab', '--', 0)
self.checkequal('abc', 'abc', 'replace', 'xy', '--')
# Next three for SF bug 422088: [OSF1 alpha] string.replace(); died with
# MemoryError due to empty result (platform malloc issue when requesting
# 0 bytes).
self.checkequal('', '123', 'replace', '123', '')
self.checkequal('', '123123', 'replace', '123', '')
self.checkequal('x', '123x123', 'replace', '123', '')
self.checkraises(TypeError, 'hello', 'replace')
self.checkraises(TypeError, 'hello', 'replace', 42)
self.checkraises(TypeError, 'hello', 'replace', 42, 'h')
self.checkraises(TypeError, 'hello', 'replace', 'h', 42)
def test_replace_overflow(self):
# Check for overflow checking on 32 bit machines
if sys.maxint != 2147483647:
return
A2_16 = "A" * (2**16)
self.checkraises(OverflowError, A2_16, "replace", "", A2_16)
self.checkraises(OverflowError, A2_16, "replace", "A", A2_16)
self.checkraises(OverflowError, A2_16, "replace", "AA", A2_16+A2_16)
def test_zfill(self):
self.checkequal('123', '123', 'zfill', 2)
self.checkequal('123', '123', 'zfill', 3)
self.checkequal('0123', '123', 'zfill', 4)
self.checkequal('+123', '+123', 'zfill', 3)
self.checkequal('+123', '+123', 'zfill', 4)
self.checkequal('+0123', '+123', 'zfill', 5)
self.checkequal('-123', '-123', 'zfill', 3)
self.checkequal('-123', '-123', 'zfill', 4)
self.checkequal('-0123', '-123', 'zfill', 5)
self.checkequal('000', '', 'zfill', 3)
self.checkequal('34', '34', 'zfill', 1)
self.checkequal('0034', '34', 'zfill', 4)
self.checkraises(TypeError, '123', 'zfill')
class MixinStrUnicodeUserStringTest:
# additional tests that only work for
# stringlike objects, i.e. str, unicode, UserString
# (but not the string module)
def test_islower(self):
self.checkequal(False, '', 'islower')
self.checkequal(True, 'a', 'islower')
self.checkequal(False, 'A', 'islower')
self.checkequal(False, '\n', 'islower')
self.checkequal(True, 'abc', 'islower')
self.checkequal(False, 'aBc', 'islower')
self.checkequal(True, 'abc\n', 'islower')
self.checkraises(TypeError, 'abc', 'islower', 42)
def test_isupper(self):
self.checkequal(False, '', 'isupper')
self.checkequal(False, 'a', 'isupper')
self.checkequal(True, 'A', 'isupper')
self.checkequal(False, '\n', 'isupper')
self.checkequal(True, 'ABC', 'isupper')
self.checkequal(False, 'AbC', 'isupper')
self.checkequal(True, 'ABC\n', 'isupper')
self.checkraises(TypeError, 'abc', 'isupper', 42)
def test_istitle(self):
self.checkequal(False, '', 'istitle')
self.checkequal(False, 'a', 'istitle')
self.checkequal(True, 'A', 'istitle')
self.checkequal(False, '\n', 'istitle')
self.checkequal(True, 'A Titlecased Line', 'istitle')
self.checkequal(True, 'A\nTitlecased Line', 'istitle')
self.checkequal(True, 'A Titlecased, Line', 'istitle')
self.checkequal(False, 'Not a capitalized String', 'istitle')
self.checkequal(False, 'Not\ta Titlecase String', 'istitle')
self.checkequal(False, 'Not--a Titlecase String', 'istitle')
self.checkequal(False, 'NOT', 'istitle')
self.checkraises(TypeError, 'abc', 'istitle', 42)
def test_isspace(self):
self.checkequal(False, '', 'isspace')
self.checkequal(False, 'a', 'isspace')
self.checkequal(True, ' ', 'isspace')
self.checkequal(True, '\t', 'isspace')
self.checkequal(True, '\r', 'isspace')
self.checkequal(True, '\n', 'isspace')
self.checkequal(True, ' \t\r\n', 'isspace')
self.checkequal(False, ' \t\r\na', 'isspace')
self.checkraises(TypeError, 'abc', 'isspace', 42)
def test_isalpha(self):
self.checkequal(False, '', 'isalpha')
self.checkequal(True, 'a', 'isalpha')
self.checkequal(True, 'A', 'isalpha')
self.checkequal(False, '\n', 'isalpha')
self.checkequal(True, 'abc', 'isalpha')
self.checkequal(False, 'aBc123', 'isalpha')
self.checkequal(False, 'abc\n', 'isalpha')
self.checkraises(TypeError, 'abc', 'isalpha', 42)
def test_isalnum(self):
self.checkequal(False, '', 'isalnum')
self.checkequal(True, 'a', 'isalnum')
self.checkequal(True, 'A', 'isalnum')
self.checkequal(False, '\n', 'isalnum')
self.checkequal(True, '123abc456', 'isalnum')
self.checkequal(True, 'a1b3c', 'isalnum')
self.checkequal(False, 'aBc000 ', 'isalnum')
self.checkequal(False, 'abc\n', 'isalnum')
self.checkraises(TypeError, 'abc', 'isalnum', 42)
def test_isdigit(self):
self.checkequal(False, '', 'isdigit')
self.checkequal(False, 'a', 'isdigit')
self.checkequal(True, '0', 'isdigit')
self.checkequal(True, '0123456789', 'isdigit')
self.checkequal(False, '0123456789a', 'isdigit')
self.checkraises(TypeError, 'abc', 'isdigit', 42)
def test_title(self):
self.checkequal(' Hello ', ' hello ', 'title')
self.checkequal('Hello ', 'hello ', 'title')
self.checkequal('Hello ', 'Hello ', 'title')
self.checkequal('Format This As Title String', "fOrMaT thIs aS titLe String", 'title')
self.checkequal('Format,This-As*Title;String', "fOrMaT,thIs-aS*titLe;String", 'title', )
self.checkequal('Getint', "getInt", 'title')
self.checkraises(TypeError, 'hello', 'title', 42)
def test_splitlines(self):
self.checkequal(['abc', 'def', '', 'ghi'], "abc\ndef\n\rghi", 'splitlines')
self.checkequal(['abc', 'def', '', 'ghi'], "abc\ndef\n\r\nghi", 'splitlines')
self.checkequal(['abc', 'def', 'ghi'], "abc\ndef\r\nghi", 'splitlines')
self.checkequal(['abc', 'def', 'ghi'], "abc\ndef\r\nghi\n", 'splitlines')
self.checkequal(['abc', 'def', 'ghi', ''], "abc\ndef\r\nghi\n\r", 'splitlines')
self.checkequal(['', 'abc', 'def', 'ghi', ''], "\nabc\ndef\r\nghi\n\r", 'splitlines')
self.checkequal(['\n', 'abc\n', 'def\r\n', 'ghi\n', '\r'], "\nabc\ndef\r\nghi\n\r", 'splitlines', 1)
self.checkraises(TypeError, 'abc', 'splitlines', 42, 42)
def test_startswith(self):
self.checkequal(True, 'hello', 'startswith', 'he')
self.checkequal(True, 'hello', 'startswith', 'hello')
self.checkequal(False, 'hello', 'startswith', 'hello world')
self.checkequal(True, 'hello', 'startswith', '')
self.checkequal(False, 'hello', 'startswith', 'ello')
self.checkequal(True, 'hello', 'startswith', 'ello', 1)
self.checkequal(True, 'hello', 'startswith', 'o', 4)
self.checkequal(False, 'hello', 'startswith', 'o', 5)
self.checkequal(True, 'hello', 'startswith', '', 5)
self.checkequal(False, 'hello', 'startswith', 'lo', 6)
self.checkequal(True, 'helloworld', 'startswith', 'lowo', 3)
self.checkequal(True, 'helloworld', 'startswith', 'lowo', 3, 7)
self.checkequal(False, 'helloworld', 'startswith', 'lowo', 3, 6)
# test negative indices
self.checkequal(True, 'hello', 'startswith', 'he', 0, -1)
self.checkequal(True, 'hello', 'startswith', 'he', -53, -1)
self.checkequal(False, 'hello', 'startswith', 'hello', 0, -1)
self.checkequal(False, 'hello', 'startswith', 'hello world', -1, -10)
self.checkequal(False, 'hello', 'startswith', 'ello', -5)
self.checkequal(True, 'hello', 'startswith', 'ello', -4)
self.checkequal(False, 'hello', 'startswith', 'o', -2)
self.checkequal(True, 'hello', 'startswith', 'o', -1)
self.checkequal(True, 'hello', 'startswith', '', -3, -3)
self.checkequal(False, 'hello', 'startswith', 'lo', -9)
self.checkraises(TypeError, 'hello', 'startswith')
self.checkraises(TypeError, 'hello', 'startswith', 42)
def test_endswith(self):
self.checkequal(True, 'hello', 'endswith', 'lo')
self.checkequal(False, 'hello', 'endswith', 'he')
self.checkequal(True, 'hello', 'endswith', '')
self.checkequal(False, 'hello', 'endswith', 'hello world')
self.checkequal(False, 'helloworld', 'endswith', 'worl')
self.checkequal(True, 'helloworld', 'endswith', 'worl', 3, 9)
self.checkequal(True, 'helloworld', 'endswith', 'world', 3, 12)
self.checkequal(True, 'helloworld', 'endswith', 'lowo', 1, 7)
self.checkequal(True, 'helloworld', 'endswith', 'lowo', 2, 7)
self.checkequal(True, 'helloworld', 'endswith', 'lowo', 3, 7)
self.checkequal(False, 'helloworld', 'endswith', 'lowo', 4, 7)
self.checkequal(False, 'helloworld', 'endswith', 'lowo', 3, 8)
self.checkequal(False, 'ab', 'endswith', 'ab', 0, 1)
self.checkequal(False, 'ab', 'endswith', 'ab', 0, 0)
# test negative indices
self.checkequal(True, 'hello', 'endswith', 'lo', -2)
self.checkequal(False, 'hello', 'endswith', 'he', -2)
self.checkequal(True, 'hello', 'endswith', '', -3, -3)
self.checkequal(False, 'hello', 'endswith', 'hello world', -10, -2)
self.checkequal(False, 'helloworld', 'endswith', 'worl', -6)
self.checkequal(True, 'helloworld', 'endswith', 'worl', -5, -1)
self.checkequal(True, 'helloworld', 'endswith', 'worl', -5, 9)
self.checkequal(True, 'helloworld', 'endswith', 'world', -7, 12)
self.checkequal(True, 'helloworld', 'endswith', 'lowo', -99, -3)
self.checkequal(True, 'helloworld', 'endswith', 'lowo', -8, -3)
self.checkequal(True, 'helloworld', 'endswith', 'lowo', -7, -3)
self.checkequal(False, 'helloworld', 'endswith', 'lowo', 3, -4)
self.checkequal(False, 'helloworld', 'endswith', 'lowo', -8, -2)
self.checkraises(TypeError, 'hello', 'endswith')
self.checkraises(TypeError, 'hello', 'endswith', 42)
def test___contains__(self):
self.checkequal(True, '', '__contains__', '') # vereq('' in '', True)
self.checkequal(True, 'abc', '__contains__', '') # vereq('' in 'abc', True)
self.checkequal(False, 'abc', '__contains__', '\0') # vereq('\0' in 'abc', False)
self.checkequal(True, '\0abc', '__contains__', '\0') # vereq('\0' in '\0abc', True)
self.checkequal(True, 'abc\0', '__contains__', '\0') # vereq('\0' in 'abc\0', True)
self.checkequal(True, '\0abc', '__contains__', 'a') # vereq('a' in '\0abc', True)
self.checkequal(True, 'asdf', '__contains__', 'asdf') # vereq('asdf' in 'asdf', True)
self.checkequal(False, 'asd', '__contains__', 'asdf') # vereq('asdf' in 'asd', False)
self.checkequal(False, '', '__contains__', 'asdf') # vereq('asdf' in '', False)
def test_subscript(self):
self.checkequal(u'a', 'abc', '__getitem__', 0)
self.checkequal(u'c', 'abc', '__getitem__', -1)
self.checkequal(u'a', 'abc', '__getitem__', 0L)
self.checkequal(u'abc', 'abc', '__getitem__', slice(0, 3))
self.checkequal(u'abc', 'abc', '__getitem__', slice(0, 1000))
self.checkequal(u'a', 'abc', '__getitem__', slice(0, 1))
self.checkequal(u'', 'abc', '__getitem__', slice(0, 0))
# FIXME What about negative indizes? This is handled differently by [] and __getitem__(slice)
self.checkraises(TypeError, 'abc', '__getitem__', 'def')
def test_slice(self):
self.checkequal('abc', 'abc', '__getslice__', 0, 1000)
self.checkequal('abc', 'abc', '__getslice__', 0, 3)
self.checkequal('ab', 'abc', '__getslice__', 0, 2)
self.checkequal('bc', 'abc', '__getslice__', 1, 3)
self.checkequal('b', 'abc', '__getslice__', 1, 2)
self.checkequal('', 'abc', '__getslice__', 2, 2)
self.checkequal('', 'abc', '__getslice__', 1000, 1000)
self.checkequal('', 'abc', '__getslice__', 2000, 1000)
self.checkequal('', 'abc', '__getslice__', 2, 1)
# FIXME What about negative indizes? This is handled differently by [] and __getslice__
self.checkraises(TypeError, 'abc', '__getslice__', 'def')
def test_mul(self):
self.checkequal('', 'abc', '__mul__', -1)
self.checkequal('', 'abc', '__mul__', 0)
self.checkequal('abc', 'abc', '__mul__', 1)
self.checkequal('abcabcabc', 'abc', '__mul__', 3)
self.checkraises(TypeError, 'abc', '__mul__')
self.checkraises(TypeError, 'abc', '__mul__', '')
# XXX: on a 64-bit system, this doesn't raise an overflow error,
# but either raises a MemoryError, or succeeds (if you have 54TiB)
#self.checkraises(OverflowError, 10000*'abc', '__mul__', 2000000000)
def test_join(self):
# join now works with any sequence type
# moved here, because the argument order is
# different in string.join (see the test in
# test.test_string.StringTest.test_join)
self.checkequal('a b c d', ' ', 'join', ['a', 'b', 'c', 'd'])
self.checkequal('abcd', '', 'join', ('a', 'b', 'c', 'd'))
self.checkequal('w x y z', ' ', 'join', Sequence())
self.checkequal('abc', 'a', 'join', ('abc',))
self.checkequal('z', 'a', 'join', UserList(['z']))
if test_support.have_unicode:
self.checkequal(unicode('a.b.c'), unicode('.'), 'join', ['a', 'b', 'c'])
self.checkequal(unicode('a.b.c'), '.', 'join', [unicode('a'), 'b', 'c'])
self.checkequal(unicode('a.b.c'), '.', 'join', ['a', unicode('b'), 'c'])
self.checkequal(unicode('a.b.c'), '.', 'join', ['a', 'b', unicode('c')])
self.checkraises(TypeError, '.', 'join', ['a', unicode('b'), 3])
for i in [5, 25, 125]:
self.checkequal(((('a' * i) + '-') * i)[:-1], '-', 'join',
['a' * i] * i)
self.checkequal(((('a' * i) + '-') * i)[:-1], '-', 'join',
('a' * i,) * i)
self.checkraises(TypeError, ' ', 'join', BadSeq1())
self.checkequal('a b c', ' ', 'join', BadSeq2())
self.checkraises(TypeError, ' ', 'join')
self.checkraises(TypeError, ' ', 'join', 7)
self.checkraises(TypeError, ' ', 'join', Sequence([7, 'hello', 123L]))
try:
def f():
yield 4 + ""
self.fixtype(' ').join(f())
except TypeError, e:
if '+' not in str(e):
self.fail('join() ate exception message')
else:
self.fail('exception not raised')
def test_formatting(self):
self.checkequal('+hello+', '+%s+', '__mod__', 'hello')
self.checkequal('+10+', '+%d+', '__mod__', 10)
self.checkequal('a', "%c", '__mod__', "a")
self.checkequal('a', "%c", '__mod__', "a")
self.checkequal('"', "%c", '__mod__', 34)
self.checkequal('$', "%c", '__mod__', 36)
self.checkequal('10', "%d", '__mod__', 10)
self.checkequal('\x7f', "%c", '__mod__', 0x7f)
for ordinal in (-100, 0x200000):
# unicode raises ValueError, str raises OverflowError
self.checkraises((ValueError, OverflowError), '%c', '__mod__', ordinal)
self.checkequal(' 42', '%3ld', '__mod__', 42)
self.checkequal('0042.00', '%07.2f', '__mod__', 42)
self.checkequal('0042.00', '%07.2F', '__mod__', 42)
self.checkraises(TypeError, 'abc', '__mod__')
self.checkraises(TypeError, '%(foo)s', '__mod__', 42)
self.checkraises(TypeError, '%s%s', '__mod__', (42,))
self.checkraises(TypeError, '%c', '__mod__', (None,))
self.checkraises(ValueError, '%(foo', '__mod__', {})
self.checkraises(TypeError, '%(foo)s %(bar)s', '__mod__', ('foo', 42))
# argument names with properly nested brackets are supported
self.checkequal('bar', '%((foo))s', '__mod__', {'(foo)': 'bar'})
# 100 is a magic number in PyUnicode_Format, this forces a resize
self.checkequal(103*'a'+'x', '%sx', '__mod__', 103*'a')
self.checkraises(TypeError, '%*s', '__mod__', ('foo', 'bar'))
self.checkraises(TypeError, '%10.*f', '__mod__', ('foo', 42.))
self.checkraises(ValueError, '%10', '__mod__', (42,))
def test_floatformatting(self):
# float formatting
for prec in xrange(100):
format = '%%.%if' % prec
value = 0.01
for x in xrange(60):
value = value * 3.141592655 / 3.0 * 10.0
# The formatfloat() code in stringobject.c and
# unicodeobject.c uses a 120 byte buffer and switches from
# 'f' formatting to 'g' at precision 50, so we expect
# OverflowErrors for the ranges x < 50 and prec >= 67.
if x < 50 and prec >= 67:
self.checkraises(OverflowError, format, "__mod__", value)
else:
self.checkcall(format, "__mod__", value)
def test_inplace_rewrites(self):
# Check that strings don't copy and modify cached single-character strings
self.checkequal('a', 'A', 'lower')
self.checkequal(True, 'A', 'isupper')
self.checkequal('A', 'a', 'upper')
self.checkequal(True, 'a', 'islower')
self.checkequal('a', 'A', 'replace', 'A', 'a')
self.checkequal(True, 'A', 'isupper')
self.checkequal('A', 'a', 'capitalize')
self.checkequal(True, 'a', 'islower')
self.checkequal('A', 'a', 'swapcase')
self.checkequal(True, 'a', 'islower')
self.checkequal('A', 'a', 'title')
self.checkequal(True, 'a', 'islower')
def test_partition(self):
self.checkequal(('this is the par', 'ti', 'tion method'),
'this is the partition method', 'partition', 'ti')
# from raymond's original specification
S = 'http://www.python.org'
self.checkequal(('http', '://', 'www.python.org'), S, 'partition', '://')
self.checkequal(('http://www.python.org', '', ''), S, 'partition', '?')
self.checkequal(('', 'http://', 'www.python.org'), S, 'partition', 'http://')
self.checkequal(('http://www.python.', 'org', ''), S, 'partition', 'org')
self.checkraises(ValueError, S, 'partition', '')
self.checkraises(TypeError, S, 'partition', None)
def test_rpartition(self):
self.checkequal(('this is the rparti', 'ti', 'on method'),
'this is the rpartition method', 'rpartition', 'ti')
# from raymond's original specification
S = 'http://www.python.org'
self.checkequal(('http', '://', 'www.python.org'), S, 'rpartition', '://')
self.checkequal(('http://www.python.org', '', ''), S, 'rpartition', '?')
self.checkequal(('', 'http://', 'www.python.org'), S, 'rpartition', 'http://')
self.checkequal(('http://www.python.', 'org', ''), S, 'rpartition', 'org')
self.checkraises(ValueError, S, 'rpartition', '')
self.checkraises(TypeError, S, 'rpartition', None)
class MixinStrStringUserStringTest:
# Additional tests for 8bit strings, i.e. str, UserString and
# the string module
def test_maketrans(self):
self.assertEqual(
''.join(map(chr, xrange(256))).replace('abc', 'xyz'),
string.maketrans('abc', 'xyz')
)
self.assertRaises(ValueError, string.maketrans, 'abc', 'xyzw')
def test_translate(self):
table = string.maketrans('abc', 'xyz')
self.checkequal('xyzxyz', 'xyzabcdef', 'translate', table, 'def')
table = string.maketrans('a', 'A')
self.checkequal('Abc', 'abc', 'translate', table)
self.checkequal('xyz', 'xyz', 'translate', table)
self.checkequal('yz', 'xyz', 'translate', table, 'x')
self.checkraises(ValueError, 'xyz', 'translate', 'too short', 'strip')
self.checkraises(ValueError, 'xyz', 'translate', 'too short')
class MixinStrUserStringTest:
# Additional tests that only work with
# 8bit compatible object, i.e. str and UserString
if test_support.have_unicode:
def test_encoding_decoding(self):
codecs = [('rot13', 'uryyb jbeyq'),
('base64', 'aGVsbG8gd29ybGQ=\n'),
('hex', '68656c6c6f20776f726c64'),
('uu', 'begin 666 <data>\n+:&5L;&\\@=V]R;&0 \n \nend\n')]
for encoding, data in codecs:
self.checkequal(data, 'hello world', 'encode', encoding)
self.checkequal('hello world', data, 'decode', encoding)
# zlib is optional, so we make the test optional too...
try:
import zlib
except ImportError:
pass
else:
data = 'x\x9c\xcbH\xcd\xc9\xc9W(\xcf/\xcaI\x01\x00\x1a\x0b\x04]'
self.checkequal(data, 'hello world', 'encode', 'zlib')
self.checkequal('hello world', data, 'decode', 'zlib')
self.checkraises(TypeError, 'xyz', 'decode', 42)
self.checkraises(TypeError, 'xyz', 'encode', 42)
class MixinStrUnicodeTest:
# Additional tests that only work with str and unicode.
def test_bug1001011(self):
# Make sure join returns a NEW object for single item sequences
# involving a subclass.
# Make sure that it is of the appropriate type.
# Check the optimisation still occurs for standard objects.
t = self.type2test
class subclass(t):
pass
s1 = subclass("abcd")
s2 = t().join([s1])
self.assert_(s1 is not s2)
self.assert_(type(s2) is t)
s1 = t("abcd")
s2 = t().join([s1])
self.assert_(s1 is s2)
# Should also test mixed-type join.
if t is unicode:
s1 = subclass("abcd")
s2 = "".join([s1])
self.assert_(s1 is not s2)
self.assert_(type(s2) is t)
s1 = t("abcd")
s2 = "".join([s1])
self.assert_(s1 is s2)
elif t is str:
s1 = subclass("abcd")
s2 = u"".join([s1])
self.assert_(s1 is not s2)
self.assert_(type(s2) is unicode) # promotes!
s1 = t("abcd")
s2 = u"".join([s1])
self.assert_(s1 is not s2)
self.assert_(type(s2) is unicode) # promotes!
else:
self.fail("unexpected type for MixinStrUnicodeTest %r" % t)