cpython/Lib/test/test_unicode_file.py
Christian Heimes e25f35ecd8 Merged revisions 61644,61646-61647,61649-61652,61656-61658,61663,61665,61667 via svnmerge from
svn+ssh://pythondev@svn.python.org/python/trunk

........
  r61644 | trent.nelson | 2008-03-19 22:51:16 +0100 (Mi, 19 Mär 2008) | 1 line

  Force a clean of the tcltk/tcltk64 directories now that we've completely changed the tcl/tk build environment.
........
  r61646 | gregory.p.smith | 2008-03-19 23:23:51 +0100 (Mi, 19 Mär 2008) | 2 lines

  Improve the error message when the CRCs don't match.
........
  r61647 | trent.nelson | 2008-03-19 23:41:10 +0100 (Mi, 19 Mär 2008) | 1 line

  Comment out tcltk/tcltk64 removal.
........
  r61649 | raymond.hettinger | 2008-03-19 23:47:48 +0100 (Mi, 19 Mär 2008) | 1 line

  Remove unnecessary traceback save/restore pair.
........
  r61650 | trent.nelson | 2008-03-19 23:51:42 +0100 (Mi, 19 Mär 2008) | 1 line

  Bump the SIGALM delay from 3 seconds to 20 seconds, mainly in an effort to see if it fixes the alarm failures in this test experienced by some of the buildbots.
........
  r61651 | brett.cannon | 2008-03-20 00:01:17 +0100 (Do, 20 Mär 2008) | 5 lines

  Make sure that the warnings filter is not reset or changed beyond the current
  running test file.

  Closes issue2407. Thanks Jerry Seutter.
........
  r61652 | gregory.p.smith | 2008-03-20 00:03:25 +0100 (Do, 20 Mär 2008) | 10 lines

  Prevent ioctl op codes from being sign extended from int to unsigned long
  when used on platforms that actually define ioctl as taking an unsigned long.
  (the BSDs and OS X / Darwin)

  Adds a unittest for fcntl.ioctl that tests what happens with both positive and
  negative numbers.

  This was done because of issue1471 but I'm not able to reproduce -that- problem
  in the first place on Linux 32bit or 64bit or OS X 10.4 & 10.5 32bit or 64 bit.
........
  r61656 | sean.reifschneider | 2008-03-20 01:46:50 +0100 (Do, 20 Mär 2008) | 2 lines

  Issue #2143: Fix embedded readline() hang on SSL socket EOF.
........
  r61657 | sean.reifschneider | 2008-03-20 01:50:07 +0100 (Do, 20 Mär 2008) | 2 lines

  Forgot to add NEWS item about smtplib SSL readline hang fix.
........
  r61658 | trent.nelson | 2008-03-20 01:58:44 +0100 (Do, 20 Mär 2008) | 1 line

  Revert r61650; the intent of this commit was to try and address alarm failures on some of the build slaves.  As Neal points out, it's called after test_main(), so it's not going to factor into the test when run via regrtest.py (and removes the original functionality that Jeffrey wanted that would kill the test if it took longer than 3 seconds to run when executing it directly during development).
........
  r61663 | sean.reifschneider | 2008-03-20 04:20:48 +0100 (Do, 20 Mär 2008) | 2 lines

  Issue 2188: Documentation hint about disabling proxy detection.
........
  r61665 | gregory.p.smith | 2008-03-20 06:41:53 +0100 (Do, 20 Mär 2008) | 7 lines

  Attempt to fix the Solaris Sparc 10 buildbot.  It was failing with an invalid
  argument error on ioctl.  This was caused by the added test_fcntl ioctl test
  that hard coded 0 as the fd to use.  Without a terminal, this fails on solaris.
  (it passed from the command line on sol 10, both 32 and 64 bit)

  Also, test_ioctl exists so I moved the test into there where it belongs.
........
  r61667 | georg.brandl | 2008-03-20 08:25:55 +0100 (Do, 20 Mär 2008) | 2 lines

  #2383: remove obsolete XXX comment in stat.py.
........
2008-03-20 10:49:03 +00:00

168 lines
6.9 KiB
Python

# Test some Unicode file name semantics
# We dont test many operations on files other than
# that their names can be used with Unicode characters.
import os, glob, time, shutil
import unicodedata
import unittest
from test.test_support import run_unittest, TestSkipped, TESTFN_UNICODE
from test.test_support import TESTFN_ENCODING, TESTFN_UNICODE_UNENCODEABLE
try:
TESTFN_UNICODE.encode(TESTFN_ENCODING)
except (UnicodeError, TypeError):
# Either the file system encoding is None, or the file name
# cannot be encoded in the file system encoding.
raise TestSkipped("No Unicode filesystem semantics on this platform")
def remove_if_exists(filename):
if os.path.exists(filename):
os.unlink(filename)
class TestUnicodeFiles(unittest.TestCase):
# The 'do_' functions are the actual tests. They generally assume the
# file already exists etc.
# Do all the tests we can given only a single filename. The file should
# exist.
def _do_single(self, filename):
self.failUnless(os.path.exists(filename))
self.failUnless(os.path.isfile(filename))
self.failUnless(os.access(filename, os.R_OK))
self.failUnless(os.path.exists(os.path.abspath(filename)))
self.failUnless(os.path.isfile(os.path.abspath(filename)))
self.failUnless(os.access(os.path.abspath(filename), os.R_OK))
os.chmod(filename, 0o777)
os.utime(filename, None)
os.utime(filename, (time.time(), time.time()))
# Copy/rename etc tests using the same filename
self._do_copyish(filename, filename)
# Filename should appear in glob output
self.failUnless(
os.path.abspath(filename)==os.path.abspath(glob.glob(filename)[0]))
# basename should appear in listdir.
path, base = os.path.split(os.path.abspath(filename))
file_list = os.listdir(path)
# Normalize the unicode strings, as round-tripping the name via the OS
# may return a different (but equivalent) value.
base = unicodedata.normalize("NFD", base)
file_list = [unicodedata.normalize("NFD", f) for f in file_list]
self.failUnless(base in file_list)
# Do as many "equivalancy' tests as we can - ie, check that although we
# have different types for the filename, they refer to the same file.
def _do_equivalent(self, filename1, filename2):
# Note we only check "filename1 against filename2" - we don't bother
# checking "filename2 against 1", as we assume we are called again with
# the args reversed.
self.failUnless(type(filename1)!=type(filename2),
"No point checking equivalent filenames of the same type")
# stat and lstat should return the same results.
self.failUnlessEqual(os.stat(filename1),
os.stat(filename2))
self.failUnlessEqual(os.lstat(filename1),
os.lstat(filename2))
# Copy/rename etc tests using equivalent filename
self._do_copyish(filename1, filename2)
# Tests that copy, move, etc one file to another.
def _do_copyish(self, filename1, filename2):
# Should be able to rename the file using either name.
self.failUnless(os.path.isfile(filename1)) # must exist.
os.rename(filename1, filename2 + ".new")
self.failUnless(os.path.isfile(filename1+".new"))
os.rename(filename1 + ".new", filename2)
self.failUnless(os.path.isfile(filename2))
shutil.copy(filename1, filename2 + ".new")
os.unlink(filename1 + ".new") # remove using equiv name.
# And a couple of moves, one using each name.
shutil.move(filename1, filename2 + ".new")
self.failUnless(not os.path.exists(filename2))
shutil.move(filename1 + ".new", filename2)
self.failUnless(os.path.exists(filename1))
# Note - due to the implementation of shutil.move,
# it tries a rename first. This only fails on Windows when on
# different file systems - and this test can't ensure that.
# So we test the shutil.copy2 function, which is the thing most
# likely to fail.
shutil.copy2(filename1, filename2 + ".new")
os.unlink(filename1 + ".new")
def _do_directory(self, make_name, chdir_name, encoded):
cwd = os.getcwd()
if os.path.isdir(make_name):
os.rmdir(make_name)
os.mkdir(make_name)
try:
os.chdir(chdir_name)
try:
if not encoded:
cwd_result = os.getcwdu()
name_result = make_name
else:
cwd_result = os.getcwd().decode(TESTFN_ENCODING)
name_result = make_name.decode(TESTFN_ENCODING)
cwd_result = unicodedata.normalize("NFD", cwd_result)
name_result = unicodedata.normalize("NFD", name_result)
self.failUnlessEqual(os.path.basename(cwd_result),name_result)
finally:
os.chdir(cwd)
finally:
os.rmdir(make_name)
# The '_test' functions 'entry points with params' - ie, what the
# top-level 'test' functions would be if they could take params
def _test_single(self, filename):
remove_if_exists(filename)
f = open(filename, "w")
f.close()
try:
self._do_single(filename)
finally:
os.unlink(filename)
self.failUnless(not os.path.exists(filename))
# and again with os.open.
f = os.open(filename, os.O_CREAT)
os.close(f)
try:
self._do_single(filename)
finally:
os.unlink(filename)
def _test_equivalent(self, filename1, filename2):
remove_if_exists(filename1)
self.failUnless(not os.path.exists(filename2))
f = file(filename1, "w")
f.close()
try:
self._do_equivalent(filename1, filename2)
finally:
os.unlink(filename1)
# The 'test' functions are unittest entry points, and simply call our
# _test functions with each of the filename combinations we wish to test
def test_single_files(self):
self._test_single(TESTFN_UNICODE)
if TESTFN_UNICODE_UNENCODEABLE is not None:
self._test_single(TESTFN_UNICODE_UNENCODEABLE)
def test_directories(self):
# For all 'equivalent' combinations:
# Make dir with encoded, chdir with unicode, checkdir with encoded
# (or unicode/encoded/unicode, etc
ext = ".dir"
self._do_directory(TESTFN_UNICODE+ext, TESTFN_UNICODE+ext, False)
# Our directory name that can't use a non-unicode name.
if TESTFN_UNICODE_UNENCODEABLE is not None:
self._do_directory(TESTFN_UNICODE_UNENCODEABLE+ext,
TESTFN_UNICODE_UNENCODEABLE+ext,
False)
def test_main():
run_unittest(__name__)
if __name__ == "__main__":
test_main()