cpython/Lib/test/multibytecodec_support.py

379 lines
14 KiB
Python
Raw Normal View History

#
# multibytecodec_support.py
# Common Unittest Routines for CJK codecs
#
import codecs
import os
import re
import sys
import unittest
from http.client import HTTPException
from test import support
from io import BytesIO
class TestBase:
encoding = '' # codec name
codec = None # codec tuple (with 4 elements)
tstring = None # must set. 2 strings to test StreamReader
codectests = None # must set. codec test tuple
roundtriptest = 1 # set if roundtrip is possible with unicode
has_iso10646 = 0 # set if this encoding contains whole iso10646 map
xmlcharnametest = None # string to test xmlcharrefreplace
unmappedunicode = '\udeee' # a unicode codepoint that is not mapped.
def setUp(self):
if self.codec is None:
self.codec = codecs.lookup(self.encoding)
self.encode = self.codec.encode
self.decode = self.codec.decode
self.reader = self.codec.streamreader
self.writer = self.codec.streamwriter
self.incrementalencoder = self.codec.incrementalencoder
self.incrementaldecoder = self.codec.incrementaldecoder
def test_chunkcoding(self):
tstring_lines = []
for b in self.tstring:
lines = b.split(b"\n")
last = lines.pop()
assert last == b""
lines = [line + b"\n" for line in lines]
tstring_lines.append(lines)
for native, utf8 in zip(*tstring_lines):
u = self.decode(native)[0]
self.assertEqual(u, utf8.decode('utf-8'))
if self.roundtriptest:
self.assertEqual(native, self.encode(u)[0])
def test_errorhandle(self):
for source, scheme, expected in self.codectests:
if isinstance(source, bytes):
func = self.decode
else:
func = self.encode
if expected:
result = func(source, scheme)[0]
if func is self.decode:
self.assertTrue(type(result) is str, type(result))
self.assertEqual(result, expected,
'%a.decode(%r, %r)=%a != %a'
% (source, self.encoding, scheme, result,
expected))
else:
self.assertTrue(type(result) is bytes, type(result))
self.assertEqual(result, expected,
'%a.encode(%r, %r)=%a != %a'
% (source, self.encoding, scheme, result,
expected))
else:
self.assertRaises(UnicodeError, func, source, scheme)
def test_xmlcharrefreplace(self):
if self.has_iso10646:
self.skipTest('encoding contains full ISO 10646 map')
s = "\u0b13\u0b23\u0b60 nd eggs"
self.assertEqual(
self.encode(s, "xmlcharrefreplace")[0],
b"ଓଣୠ nd eggs"
)
def test_customreplace_encode(self):
if self.has_iso10646:
self.skipTest('encoding contains full ISO 10646 map')
from html.entities import codepoint2name
def xmlcharnamereplace(exc):
if not isinstance(exc, UnicodeEncodeError):
raise TypeError("don't know how to handle %r" % exc)
l = []
for c in exc.object[exc.start:exc.end]:
if ord(c) in codepoint2name:
l.append("&%s;" % codepoint2name[ord(c)])
else:
l.append("&#%d;" % ord(c))
return ("".join(l), exc.end)
codecs.register_error("test.xmlcharnamereplace", xmlcharnamereplace)
if self.xmlcharnametest:
sin, sout = self.xmlcharnametest
else:
sin = "\xab\u211c\xbb = \u2329\u1234\u232a"
sout = b"«ℜ» = ⟨ሴ⟩"
self.assertEqual(self.encode(sin,
"test.xmlcharnamereplace")[0], sout)
def test_callback_returns_bytes(self):
def myreplace(exc):
return (b"1234", exc.end)
codecs.register_error("test.cjktest", myreplace)
enc = self.encode("abc" + self.unmappedunicode + "def", "test.cjktest")[0]
self.assertEqual(enc, b"abc1234def")
def test_callback_wrong_objects(self):
def myreplace(exc):
return (ret, exc.end)
codecs.register_error("test.cjktest", myreplace)
2012-12-02 13:37:04 -04:00
for ret in ([1, 2, 3], [], None, object()):
self.assertRaises(TypeError, self.encode, self.unmappedunicode,
'test.cjktest')
def test_callback_long_index(self):
def myreplace(exc):
return ('x', int(exc.end))
codecs.register_error("test.cjktest", myreplace)
self.assertEqual(self.encode('abcd' + self.unmappedunicode + 'efgh',
'test.cjktest'), (b'abcdxefgh', 9))
def myreplace(exc):
return ('x', sys.maxsize + 1)
codecs.register_error("test.cjktest", myreplace)
self.assertRaises(IndexError, self.encode, self.unmappedunicode,
'test.cjktest')
def test_callback_None_index(self):
def myreplace(exc):
return ('x', None)
codecs.register_error("test.cjktest", myreplace)
self.assertRaises(TypeError, self.encode, self.unmappedunicode,
'test.cjktest')
def test_callback_backward_index(self):
def myreplace(exc):
if myreplace.limit > 0:
myreplace.limit -= 1
return ('REPLACED', 0)
else:
return ('TERMINAL', exc.end)
myreplace.limit = 3
codecs.register_error("test.cjktest", myreplace)
self.assertEqual(self.encode('abcd' + self.unmappedunicode + 'efgh',
'test.cjktest'),
(b'abcdREPLACEDabcdREPLACEDabcdREPLACEDabcdTERMINALefgh', 9))
def test_callback_forward_index(self):
def myreplace(exc):
return ('REPLACED', exc.end + 2)
codecs.register_error("test.cjktest", myreplace)
self.assertEqual(self.encode('abcd' + self.unmappedunicode + 'efgh',
'test.cjktest'), (b'abcdREPLACEDgh', 9))
def test_callback_index_outofbound(self):
def myreplace(exc):
return ('TERM', 100)
codecs.register_error("test.cjktest", myreplace)
self.assertRaises(IndexError, self.encode, self.unmappedunicode,
'test.cjktest')
def test_incrementalencoder(self):
UTF8Reader = codecs.getreader('utf-8')
Merged revisions 55007-55179 via svnmerge from svn+ssh://pythondev@svn.python.org/python/branches/p3yk ........ r55077 | guido.van.rossum | 2007-05-02 11:54:37 -0700 (Wed, 02 May 2007) | 2 lines Use the new print syntax, at least. ........ r55142 | fred.drake | 2007-05-04 21:27:30 -0700 (Fri, 04 May 2007) | 1 line remove old cruftiness ........ r55143 | fred.drake | 2007-05-04 21:52:16 -0700 (Fri, 04 May 2007) | 1 line make this work with the new Python ........ r55162 | neal.norwitz | 2007-05-06 22:29:18 -0700 (Sun, 06 May 2007) | 1 line Get asdl code gen working with Python 2.3. Should continue to work with 3.0 ........ r55164 | neal.norwitz | 2007-05-07 00:00:38 -0700 (Mon, 07 May 2007) | 1 line Verify checkins to p3yk (sic) branch go to 3000 list. ........ r55166 | neal.norwitz | 2007-05-07 00:12:35 -0700 (Mon, 07 May 2007) | 1 line Fix this test so it runs again by importing warnings_test properly. ........ r55167 | neal.norwitz | 2007-05-07 01:03:22 -0700 (Mon, 07 May 2007) | 8 lines So long xrange. range() now supports values that are outside -sys.maxint to sys.maxint. floats raise a TypeError. This has been sitting for a long time. It probably has some problems and needs cleanup. Objects/rangeobject.c now uses 4-space indents since it is almost completely new. ........ r55171 | guido.van.rossum | 2007-05-07 10:21:26 -0700 (Mon, 07 May 2007) | 4 lines Fix two tests that were previously depending on significant spaces at the end of a line (and before that on Python 2.x print behavior that has no exact equivalent in 3.0). ........
2007-05-07 19:24:25 -03:00
for sizehint in [None] + list(range(1, 33)) + \
[64, 128, 256, 512, 1024]:
istream = UTF8Reader(BytesIO(self.tstring[1]))
ostream = BytesIO()
encoder = self.incrementalencoder()
while 1:
if sizehint is not None:
data = istream.read(sizehint)
else:
data = istream.read()
if not data:
break
e = encoder.encode(data)
ostream.write(e)
self.assertEqual(ostream.getvalue(), self.tstring[0])
def test_incrementaldecoder(self):
UTF8Writer = codecs.getwriter('utf-8')
Merged revisions 55007-55179 via svnmerge from svn+ssh://pythondev@svn.python.org/python/branches/p3yk ........ r55077 | guido.van.rossum | 2007-05-02 11:54:37 -0700 (Wed, 02 May 2007) | 2 lines Use the new print syntax, at least. ........ r55142 | fred.drake | 2007-05-04 21:27:30 -0700 (Fri, 04 May 2007) | 1 line remove old cruftiness ........ r55143 | fred.drake | 2007-05-04 21:52:16 -0700 (Fri, 04 May 2007) | 1 line make this work with the new Python ........ r55162 | neal.norwitz | 2007-05-06 22:29:18 -0700 (Sun, 06 May 2007) | 1 line Get asdl code gen working with Python 2.3. Should continue to work with 3.0 ........ r55164 | neal.norwitz | 2007-05-07 00:00:38 -0700 (Mon, 07 May 2007) | 1 line Verify checkins to p3yk (sic) branch go to 3000 list. ........ r55166 | neal.norwitz | 2007-05-07 00:12:35 -0700 (Mon, 07 May 2007) | 1 line Fix this test so it runs again by importing warnings_test properly. ........ r55167 | neal.norwitz | 2007-05-07 01:03:22 -0700 (Mon, 07 May 2007) | 8 lines So long xrange. range() now supports values that are outside -sys.maxint to sys.maxint. floats raise a TypeError. This has been sitting for a long time. It probably has some problems and needs cleanup. Objects/rangeobject.c now uses 4-space indents since it is almost completely new. ........ r55171 | guido.van.rossum | 2007-05-07 10:21:26 -0700 (Mon, 07 May 2007) | 4 lines Fix two tests that were previously depending on significant spaces at the end of a line (and before that on Python 2.x print behavior that has no exact equivalent in 3.0). ........
2007-05-07 19:24:25 -03:00
for sizehint in [None, -1] + list(range(1, 33)) + \
[64, 128, 256, 512, 1024]:
istream = BytesIO(self.tstring[0])
ostream = UTF8Writer(BytesIO())
decoder = self.incrementaldecoder()
while 1:
data = istream.read(sizehint)
if not data:
break
else:
u = decoder.decode(data)
ostream.write(u)
self.assertEqual(ostream.getvalue(), self.tstring[1])
def test_incrementalencoder_error_callback(self):
inv = self.unmappedunicode
e = self.incrementalencoder()
self.assertRaises(UnicodeEncodeError, e.encode, inv, True)
e.errors = 'ignore'
self.assertEqual(e.encode(inv, True), b'')
e.reset()
def tempreplace(exc):
return ('called', exc.end)
codecs.register_error('test.incremental_error_callback', tempreplace)
e.errors = 'test.incremental_error_callback'
self.assertEqual(e.encode(inv, True), b'called')
# again
e.errors = 'ignore'
self.assertEqual(e.encode(inv, True), b'')
def test_streamreader(self):
UTF8Writer = codecs.getwriter('utf-8')
for name in ["read", "readline", "readlines"]:
Merged revisions 55007-55179 via svnmerge from svn+ssh://pythondev@svn.python.org/python/branches/p3yk ........ r55077 | guido.van.rossum | 2007-05-02 11:54:37 -0700 (Wed, 02 May 2007) | 2 lines Use the new print syntax, at least. ........ r55142 | fred.drake | 2007-05-04 21:27:30 -0700 (Fri, 04 May 2007) | 1 line remove old cruftiness ........ r55143 | fred.drake | 2007-05-04 21:52:16 -0700 (Fri, 04 May 2007) | 1 line make this work with the new Python ........ r55162 | neal.norwitz | 2007-05-06 22:29:18 -0700 (Sun, 06 May 2007) | 1 line Get asdl code gen working with Python 2.3. Should continue to work with 3.0 ........ r55164 | neal.norwitz | 2007-05-07 00:00:38 -0700 (Mon, 07 May 2007) | 1 line Verify checkins to p3yk (sic) branch go to 3000 list. ........ r55166 | neal.norwitz | 2007-05-07 00:12:35 -0700 (Mon, 07 May 2007) | 1 line Fix this test so it runs again by importing warnings_test properly. ........ r55167 | neal.norwitz | 2007-05-07 01:03:22 -0700 (Mon, 07 May 2007) | 8 lines So long xrange. range() now supports values that are outside -sys.maxint to sys.maxint. floats raise a TypeError. This has been sitting for a long time. It probably has some problems and needs cleanup. Objects/rangeobject.c now uses 4-space indents since it is almost completely new. ........ r55171 | guido.van.rossum | 2007-05-07 10:21:26 -0700 (Mon, 07 May 2007) | 4 lines Fix two tests that were previously depending on significant spaces at the end of a line (and before that on Python 2.x print behavior that has no exact equivalent in 3.0). ........
2007-05-07 19:24:25 -03:00
for sizehint in [None, -1] + list(range(1, 33)) + \
[64, 128, 256, 512, 1024]:
istream = self.reader(BytesIO(self.tstring[0]))
ostream = UTF8Writer(BytesIO())
func = getattr(istream, name)
while 1:
data = func(sizehint)
if not data:
break
if name == "readlines":
ostream.writelines(data)
else:
ostream.write(data)
self.assertEqual(ostream.getvalue(), self.tstring[1])
def test_streamwriter(self):
readfuncs = ('read', 'readline', 'readlines')
UTF8Reader = codecs.getreader('utf-8')
for name in readfuncs:
Merged revisions 55007-55179 via svnmerge from svn+ssh://pythondev@svn.python.org/python/branches/p3yk ........ r55077 | guido.van.rossum | 2007-05-02 11:54:37 -0700 (Wed, 02 May 2007) | 2 lines Use the new print syntax, at least. ........ r55142 | fred.drake | 2007-05-04 21:27:30 -0700 (Fri, 04 May 2007) | 1 line remove old cruftiness ........ r55143 | fred.drake | 2007-05-04 21:52:16 -0700 (Fri, 04 May 2007) | 1 line make this work with the new Python ........ r55162 | neal.norwitz | 2007-05-06 22:29:18 -0700 (Sun, 06 May 2007) | 1 line Get asdl code gen working with Python 2.3. Should continue to work with 3.0 ........ r55164 | neal.norwitz | 2007-05-07 00:00:38 -0700 (Mon, 07 May 2007) | 1 line Verify checkins to p3yk (sic) branch go to 3000 list. ........ r55166 | neal.norwitz | 2007-05-07 00:12:35 -0700 (Mon, 07 May 2007) | 1 line Fix this test so it runs again by importing warnings_test properly. ........ r55167 | neal.norwitz | 2007-05-07 01:03:22 -0700 (Mon, 07 May 2007) | 8 lines So long xrange. range() now supports values that are outside -sys.maxint to sys.maxint. floats raise a TypeError. This has been sitting for a long time. It probably has some problems and needs cleanup. Objects/rangeobject.c now uses 4-space indents since it is almost completely new. ........ r55171 | guido.van.rossum | 2007-05-07 10:21:26 -0700 (Mon, 07 May 2007) | 4 lines Fix two tests that were previously depending on significant spaces at the end of a line (and before that on Python 2.x print behavior that has no exact equivalent in 3.0). ........
2007-05-07 19:24:25 -03:00
for sizehint in [None] + list(range(1, 33)) + \
[64, 128, 256, 512, 1024]:
istream = UTF8Reader(BytesIO(self.tstring[1]))
ostream = self.writer(BytesIO())
func = getattr(istream, name)
while 1:
if sizehint is not None:
data = func(sizehint)
else:
data = func()
if not data:
break
if name == "readlines":
ostream.writelines(data)
else:
ostream.write(data)
self.assertEqual(ostream.getvalue(), self.tstring[0])
class TestBase_Mapping(unittest.TestCase):
pass_enctest = []
pass_dectest = []
supmaps = []
codectests = []
def __init__(self, *args, **kw):
unittest.TestCase.__init__(self, *args, **kw)
try:
2010-10-14 19:11:44 -03:00
self.open_mapping_file().close() # test it to report the error early
2012-12-25 10:47:37 -04:00
except (OSError, HTTPException):
self.skipTest("Could not retrieve "+self.mapfileurl)
def open_mapping_file(self):
return support.open_urlresource(self.mapfileurl)
def test_mapping_file(self):
Merged revisions 56753-56781 via svnmerge from svn+ssh://pythondev@svn.python.org/python/branches/p3yk ................ r56760 | neal.norwitz | 2007-08-05 18:55:39 -0700 (Sun, 05 Aug 2007) | 178 lines Merged revisions 56477-56759 via svnmerge from svn+ssh://pythondev@svn.python.org/python/trunk ........ r56485 | facundo.batista | 2007-07-21 17:13:00 -0700 (Sat, 21 Jul 2007) | 5 lines Selectively enable tests for asyncore.readwrite based on the presence of poll support in the select module (since this is the only case in which readwrite can be called). [GSoC - Alan McIntyre] ........ r56488 | nick.coghlan | 2007-07-22 03:18:07 -0700 (Sun, 22 Jul 2007) | 1 line Add explicit relative import tests for runpy.run_module ........ r56509 | nick.coghlan | 2007-07-23 06:41:45 -0700 (Mon, 23 Jul 2007) | 5 lines Correctly cleanup sys.modules after executing runpy relative import tests Restore Python 2.4 ImportError when attempting to execute a package (as imports cannot be guaranteed to work properly if you try it) ........ r56519 | nick.coghlan | 2007-07-24 06:07:38 -0700 (Tue, 24 Jul 2007) | 1 line Tweak runpy test to do a better job of confirming that sys has been manipulated correctly ........ r56520 | nick.coghlan | 2007-07-24 06:58:28 -0700 (Tue, 24 Jul 2007) | 1 line Fix an incompatibility between the -i and -m command line switches as reported on python-dev by PJE - runpy.run_module now leaves any changes it makes to the sys module intact after the function terminates ........ r56523 | nick.coghlan | 2007-07-24 07:39:23 -0700 (Tue, 24 Jul 2007) | 1 line Try to get rid of spurious failure in test_resource on the Debian buildbots by changing the file size limit before attempting to close the file ........ r56533 | facundo.batista | 2007-07-24 14:20:42 -0700 (Tue, 24 Jul 2007) | 7 lines New tests for basic behavior of smtplib.SMTP and smtpd.DebuggingServer. Change to use global host & port number variables. Modified the 'server' to take a string to send back in order to vary test server responses. Added a test for the reaction of smtplib.SMTP to a non-200 HELO response. [GSoC - Alan McIntyre] ........ r56538 | nick.coghlan | 2007-07-25 05:57:48 -0700 (Wed, 25 Jul 2007) | 1 line More buildbot cleanup - let the OS assign the port for test_urllib2_localnet ........ r56539 | nick.coghlan | 2007-07-25 06:18:58 -0700 (Wed, 25 Jul 2007) | 1 line Add a temporary diagnostic message before a strange failure on the alpha Debian buildbot ........ r56543 | martin.v.loewis | 2007-07-25 09:24:23 -0700 (Wed, 25 Jul 2007) | 2 lines Change location of the package index to pypi.python.org/pypi ........ r56551 | georg.brandl | 2007-07-26 02:36:25 -0700 (Thu, 26 Jul 2007) | 2 lines tabs, newlines and crs are valid XML characters. ........ r56553 | nick.coghlan | 2007-07-26 07:03:00 -0700 (Thu, 26 Jul 2007) | 1 line Add explicit test for a misbehaving math.floor ........ r56561 | mark.hammond | 2007-07-26 21:52:32 -0700 (Thu, 26 Jul 2007) | 3 lines In consultation with Kristjan Jonsson, only define WINVER and _WINNT_WIN32 if (a) we are building Python itself and (b) no one previously defined them ........ r56562 | mark.hammond | 2007-07-26 22:08:54 -0700 (Thu, 26 Jul 2007) | 2 lines Correctly detect AMD64 architecture on VC2003 ........ r56566 | nick.coghlan | 2007-07-27 03:36:30 -0700 (Fri, 27 Jul 2007) | 1 line Make test_math error messages more meaningful for small discrepancies in results ........ r56588 | martin.v.loewis | 2007-07-27 11:28:22 -0700 (Fri, 27 Jul 2007) | 2 lines Bug #978833: Close https sockets by releasing the _ssl object. ........ r56601 | martin.v.loewis | 2007-07-28 00:03:05 -0700 (Sat, 28 Jul 2007) | 3 lines Bug #1704793: Return UTF-16 pair if unicodedata.lookup cannot represent the result in a single character. ........ r56604 | facundo.batista | 2007-07-28 07:21:22 -0700 (Sat, 28 Jul 2007) | 9 lines Moved all of the capture_server socket setup code into the try block so that the event gets set if a failure occurs during server setup (otherwise the test will block forever). Changed to let the OS assign the server port number, and client side of test waits for port number assignment before proceeding. The test data in DispatcherWithSendTests is also sent in multiple send() calls instead of one to make sure this works properly. [GSoC - Alan McIntyre] ........ r56611 | georg.brandl | 2007-07-29 01:26:10 -0700 (Sun, 29 Jul 2007) | 2 lines Clarify PEP 343 description. ........ r56614 | georg.brandl | 2007-07-29 02:11:15 -0700 (Sun, 29 Jul 2007) | 2 lines try-except-finally is new in 2.5. ........ r56617 | facundo.batista | 2007-07-29 07:23:08 -0700 (Sun, 29 Jul 2007) | 9 lines Added tests for asynchat classes simple_producer & fifo, and the find_prefix_at_end function. Check behavior of a string given as a producer. Added tests for behavior of asynchat.async_chat when given int, long, and None terminator arguments. Added usepoll attribute to TestAsynchat to allow running the asynchat tests with poll support chosen whether it's available or not (improves coverage of asyncore code). [GSoC - Alan McIntyre] ........ r56620 | georg.brandl | 2007-07-29 10:38:35 -0700 (Sun, 29 Jul 2007) | 2 lines Bug #1763149: use proper slice syntax in docstring. (backport) ........ r56624 | mark.hammond | 2007-07-29 17:45:29 -0700 (Sun, 29 Jul 2007) | 4 lines Correct use of Py_BUILD_CORE - now make sure it is defined before it is referenced, and also fix definition of _WIN32_WINNT. Resolves patch 1761803. ........ r56632 | facundo.batista | 2007-07-30 20:03:34 -0700 (Mon, 30 Jul 2007) | 8 lines When running asynchat tests on OS X (darwin), the test client now overrides asyncore.dispatcher.handle_expt to do nothing, since select.poll gives a POLLHUP error at the completion of these tests. Added timeout & count arguments to several asyncore.loop calls to avoid the possibility of a test hanging up a build. [GSoC - Alan McIntyre] ........ r56633 | nick.coghlan | 2007-07-31 06:38:01 -0700 (Tue, 31 Jul 2007) | 1 line Eliminate RLock race condition reported in SF bug #1764059 ........ r56636 | martin.v.loewis | 2007-07-31 12:57:56 -0700 (Tue, 31 Jul 2007) | 2 lines Define _BSD_SOURCE, to get access to POSIX extensions on OpenBSD 4.1+. ........ r56653 | facundo.batista | 2007-08-01 16:18:36 -0700 (Wed, 01 Aug 2007) | 9 lines Allow the OS to select a free port for each test server. For DebuggingServerTests, construct SMTP objects with a localhost argument to avoid abysmally long FQDN lookups (not relevant to items under test) on some machines that would cause the test to fail. Moved server setup code in the server function inside the try block to avoid the possibility of setup failure hanging the test. Minor edits to conform to PEP 8. [GSoC - Alan McIntyre] ........ r56681 | matthias.klose | 2007-08-02 14:33:13 -0700 (Thu, 02 Aug 2007) | 2 lines - Allow Emacs 22 for building the documentation in info format. ........ r56689 | neal.norwitz | 2007-08-02 23:46:29 -0700 (Thu, 02 Aug 2007) | 1 line Py_ssize_t is defined regardless of HAVE_LONG_LONG. Will backport ........ r56727 | hyeshik.chang | 2007-08-03 21:10:18 -0700 (Fri, 03 Aug 2007) | 3 lines Fix gb18030 codec's bug that doesn't map two-byte characters on GB18030 extension in encoding. (bug reported by Bjorn Stabell) ........ r56751 | neal.norwitz | 2007-08-04 20:23:31 -0700 (Sat, 04 Aug 2007) | 7 lines Handle errors when generating a warning. The value is always written to the returned pointer if getting it was successful, even if a warning causes an error. (This probably doesn't matter as the caller will probably discard the value.) Will backport. ........ ................
2007-08-06 20:33:07 -03:00
if self.mapfileurl.endswith('.xml'):
self._test_mapping_file_ucm()
else:
self._test_mapping_file_plain()
def _test_mapping_file_plain(self):
unichrs = lambda s: ''.join(map(chr, map(eval, s.split('+'))))
urt_wa = {}
2010-10-14 19:11:44 -03:00
with self.open_mapping_file() as f:
for line in f:
if not line:
break
data = line.split('#')[0].strip().split()
if len(data) != 2:
continue
csetval = eval(data[0])
if csetval <= 0x7F:
csetch = bytes([csetval & 0xff])
elif csetval >= 0x1000000:
csetch = bytes([(csetval >> 24), ((csetval >> 16) & 0xff),
((csetval >> 8) & 0xff), (csetval & 0xff)])
elif csetval >= 0x10000:
csetch = bytes([(csetval >> 16), ((csetval >> 8) & 0xff),
(csetval & 0xff)])
elif csetval >= 0x100:
csetch = bytes([(csetval >> 8), (csetval & 0xff)])
else:
continue
2010-10-14 19:11:44 -03:00
unich = unichrs(data[1])
if ord(unich) == 0xfffd or unich in urt_wa:
continue
urt_wa[unich] = csetch
2010-10-14 19:11:44 -03:00
self._testpoint(csetch, unich)
Merged revisions 56753-56781 via svnmerge from svn+ssh://pythondev@svn.python.org/python/branches/p3yk ................ r56760 | neal.norwitz | 2007-08-05 18:55:39 -0700 (Sun, 05 Aug 2007) | 178 lines Merged revisions 56477-56759 via svnmerge from svn+ssh://pythondev@svn.python.org/python/trunk ........ r56485 | facundo.batista | 2007-07-21 17:13:00 -0700 (Sat, 21 Jul 2007) | 5 lines Selectively enable tests for asyncore.readwrite based on the presence of poll support in the select module (since this is the only case in which readwrite can be called). [GSoC - Alan McIntyre] ........ r56488 | nick.coghlan | 2007-07-22 03:18:07 -0700 (Sun, 22 Jul 2007) | 1 line Add explicit relative import tests for runpy.run_module ........ r56509 | nick.coghlan | 2007-07-23 06:41:45 -0700 (Mon, 23 Jul 2007) | 5 lines Correctly cleanup sys.modules after executing runpy relative import tests Restore Python 2.4 ImportError when attempting to execute a package (as imports cannot be guaranteed to work properly if you try it) ........ r56519 | nick.coghlan | 2007-07-24 06:07:38 -0700 (Tue, 24 Jul 2007) | 1 line Tweak runpy test to do a better job of confirming that sys has been manipulated correctly ........ r56520 | nick.coghlan | 2007-07-24 06:58:28 -0700 (Tue, 24 Jul 2007) | 1 line Fix an incompatibility between the -i and -m command line switches as reported on python-dev by PJE - runpy.run_module now leaves any changes it makes to the sys module intact after the function terminates ........ r56523 | nick.coghlan | 2007-07-24 07:39:23 -0700 (Tue, 24 Jul 2007) | 1 line Try to get rid of spurious failure in test_resource on the Debian buildbots by changing the file size limit before attempting to close the file ........ r56533 | facundo.batista | 2007-07-24 14:20:42 -0700 (Tue, 24 Jul 2007) | 7 lines New tests for basic behavior of smtplib.SMTP and smtpd.DebuggingServer. Change to use global host & port number variables. Modified the 'server' to take a string to send back in order to vary test server responses. Added a test for the reaction of smtplib.SMTP to a non-200 HELO response. [GSoC - Alan McIntyre] ........ r56538 | nick.coghlan | 2007-07-25 05:57:48 -0700 (Wed, 25 Jul 2007) | 1 line More buildbot cleanup - let the OS assign the port for test_urllib2_localnet ........ r56539 | nick.coghlan | 2007-07-25 06:18:58 -0700 (Wed, 25 Jul 2007) | 1 line Add a temporary diagnostic message before a strange failure on the alpha Debian buildbot ........ r56543 | martin.v.loewis | 2007-07-25 09:24:23 -0700 (Wed, 25 Jul 2007) | 2 lines Change location of the package index to pypi.python.org/pypi ........ r56551 | georg.brandl | 2007-07-26 02:36:25 -0700 (Thu, 26 Jul 2007) | 2 lines tabs, newlines and crs are valid XML characters. ........ r56553 | nick.coghlan | 2007-07-26 07:03:00 -0700 (Thu, 26 Jul 2007) | 1 line Add explicit test for a misbehaving math.floor ........ r56561 | mark.hammond | 2007-07-26 21:52:32 -0700 (Thu, 26 Jul 2007) | 3 lines In consultation with Kristjan Jonsson, only define WINVER and _WINNT_WIN32 if (a) we are building Python itself and (b) no one previously defined them ........ r56562 | mark.hammond | 2007-07-26 22:08:54 -0700 (Thu, 26 Jul 2007) | 2 lines Correctly detect AMD64 architecture on VC2003 ........ r56566 | nick.coghlan | 2007-07-27 03:36:30 -0700 (Fri, 27 Jul 2007) | 1 line Make test_math error messages more meaningful for small discrepancies in results ........ r56588 | martin.v.loewis | 2007-07-27 11:28:22 -0700 (Fri, 27 Jul 2007) | 2 lines Bug #978833: Close https sockets by releasing the _ssl object. ........ r56601 | martin.v.loewis | 2007-07-28 00:03:05 -0700 (Sat, 28 Jul 2007) | 3 lines Bug #1704793: Return UTF-16 pair if unicodedata.lookup cannot represent the result in a single character. ........ r56604 | facundo.batista | 2007-07-28 07:21:22 -0700 (Sat, 28 Jul 2007) | 9 lines Moved all of the capture_server socket setup code into the try block so that the event gets set if a failure occurs during server setup (otherwise the test will block forever). Changed to let the OS assign the server port number, and client side of test waits for port number assignment before proceeding. The test data in DispatcherWithSendTests is also sent in multiple send() calls instead of one to make sure this works properly. [GSoC - Alan McIntyre] ........ r56611 | georg.brandl | 2007-07-29 01:26:10 -0700 (Sun, 29 Jul 2007) | 2 lines Clarify PEP 343 description. ........ r56614 | georg.brandl | 2007-07-29 02:11:15 -0700 (Sun, 29 Jul 2007) | 2 lines try-except-finally is new in 2.5. ........ r56617 | facundo.batista | 2007-07-29 07:23:08 -0700 (Sun, 29 Jul 2007) | 9 lines Added tests for asynchat classes simple_producer & fifo, and the find_prefix_at_end function. Check behavior of a string given as a producer. Added tests for behavior of asynchat.async_chat when given int, long, and None terminator arguments. Added usepoll attribute to TestAsynchat to allow running the asynchat tests with poll support chosen whether it's available or not (improves coverage of asyncore code). [GSoC - Alan McIntyre] ........ r56620 | georg.brandl | 2007-07-29 10:38:35 -0700 (Sun, 29 Jul 2007) | 2 lines Bug #1763149: use proper slice syntax in docstring. (backport) ........ r56624 | mark.hammond | 2007-07-29 17:45:29 -0700 (Sun, 29 Jul 2007) | 4 lines Correct use of Py_BUILD_CORE - now make sure it is defined before it is referenced, and also fix definition of _WIN32_WINNT. Resolves patch 1761803. ........ r56632 | facundo.batista | 2007-07-30 20:03:34 -0700 (Mon, 30 Jul 2007) | 8 lines When running asynchat tests on OS X (darwin), the test client now overrides asyncore.dispatcher.handle_expt to do nothing, since select.poll gives a POLLHUP error at the completion of these tests. Added timeout & count arguments to several asyncore.loop calls to avoid the possibility of a test hanging up a build. [GSoC - Alan McIntyre] ........ r56633 | nick.coghlan | 2007-07-31 06:38:01 -0700 (Tue, 31 Jul 2007) | 1 line Eliminate RLock race condition reported in SF bug #1764059 ........ r56636 | martin.v.loewis | 2007-07-31 12:57:56 -0700 (Tue, 31 Jul 2007) | 2 lines Define _BSD_SOURCE, to get access to POSIX extensions on OpenBSD 4.1+. ........ r56653 | facundo.batista | 2007-08-01 16:18:36 -0700 (Wed, 01 Aug 2007) | 9 lines Allow the OS to select a free port for each test server. For DebuggingServerTests, construct SMTP objects with a localhost argument to avoid abysmally long FQDN lookups (not relevant to items under test) on some machines that would cause the test to fail. Moved server setup code in the server function inside the try block to avoid the possibility of setup failure hanging the test. Minor edits to conform to PEP 8. [GSoC - Alan McIntyre] ........ r56681 | matthias.klose | 2007-08-02 14:33:13 -0700 (Thu, 02 Aug 2007) | 2 lines - Allow Emacs 22 for building the documentation in info format. ........ r56689 | neal.norwitz | 2007-08-02 23:46:29 -0700 (Thu, 02 Aug 2007) | 1 line Py_ssize_t is defined regardless of HAVE_LONG_LONG. Will backport ........ r56727 | hyeshik.chang | 2007-08-03 21:10:18 -0700 (Fri, 03 Aug 2007) | 3 lines Fix gb18030 codec's bug that doesn't map two-byte characters on GB18030 extension in encoding. (bug reported by Bjorn Stabell) ........ r56751 | neal.norwitz | 2007-08-04 20:23:31 -0700 (Sat, 04 Aug 2007) | 7 lines Handle errors when generating a warning. The value is always written to the returned pointer if getting it was successful, even if a warning causes an error. (This probably doesn't matter as the caller will probably discard the value.) Will backport. ........ ................
2007-08-06 20:33:07 -03:00
def _test_mapping_file_ucm(self):
2010-10-14 19:11:44 -03:00
with self.open_mapping_file() as f:
ucmdata = f.read()
Merged revisions 56753-56781 via svnmerge from svn+ssh://pythondev@svn.python.org/python/branches/p3yk ................ r56760 | neal.norwitz | 2007-08-05 18:55:39 -0700 (Sun, 05 Aug 2007) | 178 lines Merged revisions 56477-56759 via svnmerge from svn+ssh://pythondev@svn.python.org/python/trunk ........ r56485 | facundo.batista | 2007-07-21 17:13:00 -0700 (Sat, 21 Jul 2007) | 5 lines Selectively enable tests for asyncore.readwrite based on the presence of poll support in the select module (since this is the only case in which readwrite can be called). [GSoC - Alan McIntyre] ........ r56488 | nick.coghlan | 2007-07-22 03:18:07 -0700 (Sun, 22 Jul 2007) | 1 line Add explicit relative import tests for runpy.run_module ........ r56509 | nick.coghlan | 2007-07-23 06:41:45 -0700 (Mon, 23 Jul 2007) | 5 lines Correctly cleanup sys.modules after executing runpy relative import tests Restore Python 2.4 ImportError when attempting to execute a package (as imports cannot be guaranteed to work properly if you try it) ........ r56519 | nick.coghlan | 2007-07-24 06:07:38 -0700 (Tue, 24 Jul 2007) | 1 line Tweak runpy test to do a better job of confirming that sys has been manipulated correctly ........ r56520 | nick.coghlan | 2007-07-24 06:58:28 -0700 (Tue, 24 Jul 2007) | 1 line Fix an incompatibility between the -i and -m command line switches as reported on python-dev by PJE - runpy.run_module now leaves any changes it makes to the sys module intact after the function terminates ........ r56523 | nick.coghlan | 2007-07-24 07:39:23 -0700 (Tue, 24 Jul 2007) | 1 line Try to get rid of spurious failure in test_resource on the Debian buildbots by changing the file size limit before attempting to close the file ........ r56533 | facundo.batista | 2007-07-24 14:20:42 -0700 (Tue, 24 Jul 2007) | 7 lines New tests for basic behavior of smtplib.SMTP and smtpd.DebuggingServer. Change to use global host & port number variables. Modified the 'server' to take a string to send back in order to vary test server responses. Added a test for the reaction of smtplib.SMTP to a non-200 HELO response. [GSoC - Alan McIntyre] ........ r56538 | nick.coghlan | 2007-07-25 05:57:48 -0700 (Wed, 25 Jul 2007) | 1 line More buildbot cleanup - let the OS assign the port for test_urllib2_localnet ........ r56539 | nick.coghlan | 2007-07-25 06:18:58 -0700 (Wed, 25 Jul 2007) | 1 line Add a temporary diagnostic message before a strange failure on the alpha Debian buildbot ........ r56543 | martin.v.loewis | 2007-07-25 09:24:23 -0700 (Wed, 25 Jul 2007) | 2 lines Change location of the package index to pypi.python.org/pypi ........ r56551 | georg.brandl | 2007-07-26 02:36:25 -0700 (Thu, 26 Jul 2007) | 2 lines tabs, newlines and crs are valid XML characters. ........ r56553 | nick.coghlan | 2007-07-26 07:03:00 -0700 (Thu, 26 Jul 2007) | 1 line Add explicit test for a misbehaving math.floor ........ r56561 | mark.hammond | 2007-07-26 21:52:32 -0700 (Thu, 26 Jul 2007) | 3 lines In consultation with Kristjan Jonsson, only define WINVER and _WINNT_WIN32 if (a) we are building Python itself and (b) no one previously defined them ........ r56562 | mark.hammond | 2007-07-26 22:08:54 -0700 (Thu, 26 Jul 2007) | 2 lines Correctly detect AMD64 architecture on VC2003 ........ r56566 | nick.coghlan | 2007-07-27 03:36:30 -0700 (Fri, 27 Jul 2007) | 1 line Make test_math error messages more meaningful for small discrepancies in results ........ r56588 | martin.v.loewis | 2007-07-27 11:28:22 -0700 (Fri, 27 Jul 2007) | 2 lines Bug #978833: Close https sockets by releasing the _ssl object. ........ r56601 | martin.v.loewis | 2007-07-28 00:03:05 -0700 (Sat, 28 Jul 2007) | 3 lines Bug #1704793: Return UTF-16 pair if unicodedata.lookup cannot represent the result in a single character. ........ r56604 | facundo.batista | 2007-07-28 07:21:22 -0700 (Sat, 28 Jul 2007) | 9 lines Moved all of the capture_server socket setup code into the try block so that the event gets set if a failure occurs during server setup (otherwise the test will block forever). Changed to let the OS assign the server port number, and client side of test waits for port number assignment before proceeding. The test data in DispatcherWithSendTests is also sent in multiple send() calls instead of one to make sure this works properly. [GSoC - Alan McIntyre] ........ r56611 | georg.brandl | 2007-07-29 01:26:10 -0700 (Sun, 29 Jul 2007) | 2 lines Clarify PEP 343 description. ........ r56614 | georg.brandl | 2007-07-29 02:11:15 -0700 (Sun, 29 Jul 2007) | 2 lines try-except-finally is new in 2.5. ........ r56617 | facundo.batista | 2007-07-29 07:23:08 -0700 (Sun, 29 Jul 2007) | 9 lines Added tests for asynchat classes simple_producer & fifo, and the find_prefix_at_end function. Check behavior of a string given as a producer. Added tests for behavior of asynchat.async_chat when given int, long, and None terminator arguments. Added usepoll attribute to TestAsynchat to allow running the asynchat tests with poll support chosen whether it's available or not (improves coverage of asyncore code). [GSoC - Alan McIntyre] ........ r56620 | georg.brandl | 2007-07-29 10:38:35 -0700 (Sun, 29 Jul 2007) | 2 lines Bug #1763149: use proper slice syntax in docstring. (backport) ........ r56624 | mark.hammond | 2007-07-29 17:45:29 -0700 (Sun, 29 Jul 2007) | 4 lines Correct use of Py_BUILD_CORE - now make sure it is defined before it is referenced, and also fix definition of _WIN32_WINNT. Resolves patch 1761803. ........ r56632 | facundo.batista | 2007-07-30 20:03:34 -0700 (Mon, 30 Jul 2007) | 8 lines When running asynchat tests on OS X (darwin), the test client now overrides asyncore.dispatcher.handle_expt to do nothing, since select.poll gives a POLLHUP error at the completion of these tests. Added timeout & count arguments to several asyncore.loop calls to avoid the possibility of a test hanging up a build. [GSoC - Alan McIntyre] ........ r56633 | nick.coghlan | 2007-07-31 06:38:01 -0700 (Tue, 31 Jul 2007) | 1 line Eliminate RLock race condition reported in SF bug #1764059 ........ r56636 | martin.v.loewis | 2007-07-31 12:57:56 -0700 (Tue, 31 Jul 2007) | 2 lines Define _BSD_SOURCE, to get access to POSIX extensions on OpenBSD 4.1+. ........ r56653 | facundo.batista | 2007-08-01 16:18:36 -0700 (Wed, 01 Aug 2007) | 9 lines Allow the OS to select a free port for each test server. For DebuggingServerTests, construct SMTP objects with a localhost argument to avoid abysmally long FQDN lookups (not relevant to items under test) on some machines that would cause the test to fail. Moved server setup code in the server function inside the try block to avoid the possibility of setup failure hanging the test. Minor edits to conform to PEP 8. [GSoC - Alan McIntyre] ........ r56681 | matthias.klose | 2007-08-02 14:33:13 -0700 (Thu, 02 Aug 2007) | 2 lines - Allow Emacs 22 for building the documentation in info format. ........ r56689 | neal.norwitz | 2007-08-02 23:46:29 -0700 (Thu, 02 Aug 2007) | 1 line Py_ssize_t is defined regardless of HAVE_LONG_LONG. Will backport ........ r56727 | hyeshik.chang | 2007-08-03 21:10:18 -0700 (Fri, 03 Aug 2007) | 3 lines Fix gb18030 codec's bug that doesn't map two-byte characters on GB18030 extension in encoding. (bug reported by Bjorn Stabell) ........ r56751 | neal.norwitz | 2007-08-04 20:23:31 -0700 (Sat, 04 Aug 2007) | 7 lines Handle errors when generating a warning. The value is always written to the returned pointer if getting it was successful, even if a warning causes an error. (This probably doesn't matter as the caller will probably discard the value.) Will backport. ........ ................
2007-08-06 20:33:07 -03:00
uc = re.findall('<a u="([A-F0-9]{4})" b="([0-9A-F ]+)"/>', ucmdata)
for uni, coded in uc:
unich = chr(int(uni, 16))
codech = bytes(int(c, 16) for c in coded.split())
self._testpoint(codech, unich)
def test_mapping_supplemental(self):
for mapping in self.supmaps:
self._testpoint(*mapping)
def _testpoint(self, csetch, unich):
if (csetch, unich) not in self.pass_enctest:
self.assertEqual(unich.encode(self.encoding), csetch)
if (csetch, unich) not in self.pass_dectest:
self.assertEqual(str(csetch, self.encoding), unich)
def test_errorhandle(self):
for source, scheme, expected in self.codectests:
if isinstance(source, bytes):
func = source.decode
else:
func = source.encode
if expected:
if isinstance(source, bytes):
result = func(self.encoding, scheme)
self.assertTrue(type(result) is str, type(result))
self.assertEqual(result, expected,
'%a.decode(%r, %r)=%a != %a'
% (source, self.encoding, scheme, result,
expected))
else:
result = func(self.encoding, scheme)
self.assertTrue(type(result) is bytes, type(result))
self.assertEqual(result, expected,
'%a.encode(%r, %r)=%a != %a'
% (source, self.encoding, scheme, result,
expected))
else:
self.assertRaises(UnicodeError, func, self.encoding, scheme)
def load_teststring(name):
dir = os.path.join(os.path.dirname(__file__), 'cjkencodings')
with open(os.path.join(dir, name + '.txt'), 'rb') as f:
encoded = f.read()
with open(os.path.join(dir, name + '-utf8.txt'), 'rb') as f:
utf8 = f.read()
return encoded, utf8