From: Serhiy Storchaka Date: Wed, 5 Feb 2014 18:54:43 +0000 (+0200) Subject: Issue #19920: TarFile.list() no longer fails when outputs a listing X-Git-Tag: v3.4.0rc1~80 X-Git-Url: https://granicus.if.org/sourcecode?a=commitdiff_plain;h=255493c81321f56afd32fb2e18d5eb3a13bed42f;p=python Issue #19920: TarFile.list() no longer fails when outputs a listing containing non-encodable characters. Added tests for TarFile.list(). Based on patch by Vajrasky Kok. --- 255493c81321f56afd32fb2e18d5eb3a13bed42f diff --cc Lib/test/test_tarfile.py index b53f3ac399,ad6f320894..ab88be41b7 --- a/Lib/test/test_tarfile.py +++ b/Lib/test/test_tarfile.py @@@ -219,6 -217,84 +219,84 @@@ class LzmaUstarReadTest(LzmaTest, Ustar pass + class ListTest(ReadTest, unittest.TestCase): + + # Override setUp to use default encoding (UTF-8) + def setUp(self): + self.tar = tarfile.open(self.tarname, mode=self.mode) + + def test_list(self): + tio = io.TextIOWrapper(io.BytesIO(), 'ascii', newline='\n') + with support.swap_attr(sys, 'stdout', tio): + self.tar.list(verbose=False) + out = tio.detach().getvalue() + self.assertIn(b'ustar/conttype', out) + self.assertIn(b'ustar/regtype', out) + self.assertIn(b'ustar/lnktype', out) + self.assertIn(b'ustar' + (b'/12345' * 40) + b'67/longname', out) + self.assertIn(b'./ustar/linktest2/symtype', out) + self.assertIn(b'./ustar/linktest2/lnktype', out) + # Make sure it puts trailing slash for directory + self.assertIn(b'ustar/dirtype/', out) + self.assertIn(b'ustar/dirtype-with-size/', out) + # Make sure it is able to print unencodable characters + self.assertIn(br'ustar/umlauts-' + br'\udcc4\udcd6\udcdc\udce4\udcf6\udcfc\udcdf', out) + self.assertIn(br'misc/regtype-hpux-signed-chksum-' + br'\udcc4\udcd6\udcdc\udce4\udcf6\udcfc\udcdf', out) + self.assertIn(br'misc/regtype-old-v7-signed-chksum-' + br'\udcc4\udcd6\udcdc\udce4\udcf6\udcfc\udcdf', out) + self.assertIn(br'pax/bad-pax-\udce4\udcf6\udcfc', out) + self.assertIn(br'pax/hdrcharset-\udce4\udcf6\udcfc', out) + # Make sure it prints files separated by one newline without any + # 'ls -l'-like accessories if verbose flag is not being used + # ... + # ustar/conttype + # ustar/regtype + # ... + self.assertRegex(out, br'ustar/conttype ?\r?\n' + br'ustar/regtype ?\r?\n') + # Make sure it does not print the source of link without verbose flag + self.assertNotIn(b'link to', out) + self.assertNotIn(b'->', out) + + def test_list_verbose(self): + tio = io.TextIOWrapper(io.BytesIO(), 'ascii', newline='\n') + with support.swap_attr(sys, 'stdout', tio): + self.tar.list(verbose=True) + out = tio.detach().getvalue() + # Make sure it prints files separated by one newline with 'ls -l'-like + # accessories if verbose flag is being used + # ... + # ?rw-r--r-- tarfile/tarfile 7011 2003-01-06 07:19:43 ustar/conttype + # ?rw-r--r-- tarfile/tarfile 7011 2003-01-06 07:19:43 ustar/regtype + # ... - self.assertRegex(out, (br'-rw-r--r-- tarfile/tarfile\s+7011 ' ++ self.assertRegex(out, (br'\?rw-r--r-- tarfile/tarfile\s+7011 ' + br'\d{4}-\d\d-\d\d\s+\d\d:\d\d:\d\d ' + br'ustar/\w+type ?\r?\n') * 2) + # Make sure it prints the source of link with verbose flag + self.assertIn(b'ustar/symtype -> regtype', out) + self.assertIn(b'./ustar/linktest2/symtype -> ../linktest1/regtype', out) + self.assertIn(b'./ustar/linktest2/lnktype link to ' + b'./ustar/linktest1/regtype', out) + self.assertIn(b'gnu' + (b'/123' * 125) + b'/longlink link to gnu' + + (b'/123' * 125) + b'/longname', out) + self.assertIn(b'pax' + (b'/123' * 125) + b'/longlink link to pax' + + (b'/123' * 125) + b'/longname', out) + + + class GzipListTest(GzipTest, ListTest): + pass + + + class Bz2ListTest(Bz2Test, ListTest): + pass + + + class LzmaListTest(LzmaTest, ListTest): + pass + + class CommonReadTest(ReadTest): def test_empty_tarfile(self): @@@ -1764,168 -1845,6 +1842,171 @@@ class MiscTest(unittest.TestCase) tarfile.itn(0x10000000000, 6, tarfile.GNU_FORMAT) +class CommandLineTest(unittest.TestCase): + - def tarfilecmd(self, *args): - rc, out, err = script_helper.assert_python_ok('-m', 'tarfile', *args) ++ def tarfilecmd(self, *args, **kwargs): ++ rc, out, err = script_helper.assert_python_ok('-m', 'tarfile', *args, ++ **kwargs) + return out.replace(os.linesep.encode(), b'\n') + + def tarfilecmd_failure(self, *args): + return script_helper.assert_python_failure('-m', 'tarfile', *args) + + def make_simple_tarfile(self, tar_name): + files = [support.findfile('tokenize_tests.txt'), + support.findfile('tokenize_tests-no-coding-cookie-' + 'and-utf8-bom-sig-only.txt')] + self.addCleanup(support.unlink, tar_name) + with tarfile.open(tar_name, 'w') as tf: + for tardata in files: + tf.add(tardata, arcname=os.path.basename(tardata)) + + def test_test_command(self): + for tar_name in testtarnames: + for opt in '-t', '--test': + out = self.tarfilecmd(opt, tar_name) + self.assertEqual(out, b'') + + def test_test_command_verbose(self): + for tar_name in testtarnames: + for opt in '-v', '--verbose': + out = self.tarfilecmd(opt, '-t', tar_name) + self.assertIn(b'is a tar archive.\n', out) + + def test_test_command_invalid_file(self): + zipname = support.findfile('zipdir.zip') + rc, out, err = self.tarfilecmd_failure('-t', zipname) + self.assertIn(b' is not a tar archive.', err) + self.assertEqual(out, b'') + self.assertEqual(rc, 1) + + for tar_name in testtarnames: + with self.subTest(tar_name=tar_name): + with open(tar_name, 'rb') as f: + data = f.read() + try: + with open(tmpname, 'wb') as f: + f.write(data[:511]) + rc, out, err = self.tarfilecmd_failure('-t', tmpname) + self.assertEqual(out, b'') + self.assertEqual(rc, 1) + finally: + support.unlink(tmpname) + + def test_list_command(self): - self.make_simple_tarfile(tmpname) - with support.captured_stdout() as t: - with tarfile.open(tmpname, 'r') as tf: - tf.list(verbose=False) - expected = t.getvalue().encode(sys.getfilesystemencoding()) - for opt in '-l', '--list': - out = self.tarfilecmd(opt, tmpname) - self.assertEqual(out, expected) ++ for tar_name in testtarnames: ++ with support.captured_stdout() as t: ++ with tarfile.open(tar_name, 'r') as tf: ++ tf.list(verbose=False) ++ expected = t.getvalue().encode('ascii', 'backslashreplace') ++ for opt in '-l', '--list': ++ out = self.tarfilecmd(opt, tar_name, ++ PYTHONIOENCODING='ascii') ++ self.assertEqual(out, expected) + + def test_list_command_verbose(self): - self.make_simple_tarfile(tmpname) - with support.captured_stdout() as t: - with tarfile.open(tmpname, 'r') as tf: - tf.list(verbose=True) - expected = t.getvalue().encode(sys.getfilesystemencoding()) - for opt in '-v', '--verbose': - out = self.tarfilecmd(opt, '-l', tmpname) - self.assertEqual(out, expected) ++ for tar_name in testtarnames: ++ with support.captured_stdout() as t: ++ with tarfile.open(tar_name, 'r') as tf: ++ tf.list(verbose=True) ++ expected = t.getvalue().encode('ascii', 'backslashreplace') ++ for opt in '-v', '--verbose': ++ out = self.tarfilecmd(opt, '-l', tar_name, ++ PYTHONIOENCODING='ascii') ++ self.assertEqual(out, expected) + + def test_list_command_invalid_file(self): + zipname = support.findfile('zipdir.zip') + rc, out, err = self.tarfilecmd_failure('-l', zipname) + self.assertIn(b' is not a tar archive.', err) + self.assertEqual(out, b'') + self.assertEqual(rc, 1) + + def test_create_command(self): + files = [support.findfile('tokenize_tests.txt'), + support.findfile('tokenize_tests-no-coding-cookie-' + 'and-utf8-bom-sig-only.txt')] + for opt in '-c', '--create': + try: + out = self.tarfilecmd(opt, tmpname, *files) + self.assertEqual(out, b'') + with tarfile.open(tmpname) as tar: + tar.getmembers() + finally: + support.unlink(tmpname) + + def test_create_command_verbose(self): + files = [support.findfile('tokenize_tests.txt'), + support.findfile('tokenize_tests-no-coding-cookie-' + 'and-utf8-bom-sig-only.txt')] + for opt in '-v', '--verbose': + try: + out = self.tarfilecmd(opt, '-c', tmpname, *files) + self.assertIn(b' file created.', out) + with tarfile.open(tmpname) as tar: + tar.getmembers() + finally: + support.unlink(tmpname) + + def test_create_command_dotless_filename(self): + files = [support.findfile('tokenize_tests.txt')] + try: + out = self.tarfilecmd('-c', dotlessname, *files) + self.assertEqual(out, b'') + with tarfile.open(dotlessname) as tar: + tar.getmembers() + finally: + support.unlink(dotlessname) + + def test_create_command_dot_started_filename(self): + tar_name = os.path.join(TEMPDIR, ".testtar") + files = [support.findfile('tokenize_tests.txt')] + try: + out = self.tarfilecmd('-c', tar_name, *files) + self.assertEqual(out, b'') + with tarfile.open(tar_name) as tar: + tar.getmembers() + finally: + support.unlink(tar_name) + + def test_extract_command(self): + self.make_simple_tarfile(tmpname) + for opt in '-e', '--extract': + try: + with support.temp_cwd(tarextdir): + out = self.tarfilecmd(opt, tmpname) + self.assertEqual(out, b'') + finally: + support.rmtree(tarextdir) + + def test_extract_command_verbose(self): + self.make_simple_tarfile(tmpname) + for opt in '-v', '--verbose': + try: + with support.temp_cwd(tarextdir): + out = self.tarfilecmd(opt, '-e', tmpname) + self.assertIn(b' file is extracted.', out) + finally: + support.rmtree(tarextdir) + + def test_extract_command_different_directory(self): + self.make_simple_tarfile(tmpname) + try: + with support.temp_cwd(tarextdir): + out = self.tarfilecmd('-e', tmpname, 'spamdir') + self.assertEqual(out, b'') + finally: + support.rmtree(tarextdir) + + def test_extract_command_invalid_file(self): + zipname = support.findfile('zipdir.zip') + with support.temp_cwd(tarextdir): + rc, out, err = self.tarfilecmd_failure('-e', zipname) + self.assertIn(b' is not a tar archive.', err) + self.assertEqual(out, b'') + self.assertEqual(rc, 1) + + class ContextManagerTest(unittest.TestCase): def test_basic(self): diff --cc Misc/NEWS index 90da3a73f4,59bc95d269..99214b74ea --- a/Misc/NEWS +++ b/Misc/NEWS @@@ -98,110 -80,6 +101,112 @@@ Librar codecs.StreamReader returned incomplete data when were called after readline() or read(size). Based on patch by Amaury Forgeot d'Arc. +- Issue #20105: the codec exception chaining now correctly sets the + traceback of the original exception as its __traceback__ attribute. + +- Issue #17481: inspect.getfullargspec() now uses inspect.signature() API. + +- Issue #15304: concurrent.futures.wait() can block forever even if + Futures have completed. Patch by Glenn Langford. + +IDLE +---- + +- Update the python.gif icon for the Idle classbrowser and pathbowser + from the old green snake to the new new blue and yellow snakes. + +- Issue #17721: Remove non-functional configuration dialog help button until we + make it actually gives some help when clicked. Patch by Guilherme Simões. + +Tests +----- + ++- Issue #19920: Added tests for TarFile.list(). Based on patch by Vajrasky Kok. ++ +- Issue #19990: Added tests for the imghdr module. Based on patch by + Claudiu Popa. + +- Issue #20474: Fix test_socket "unexpected success" failures on OS X 10.7+. + +Tools/Demos +----------- + +- #Issue 20456: Argument Clinic now observes the C preprocessor conditional + compilation statements of the C files it parses. When a Clinic block is + inside a conditional code, it adjusts its output to match, including + automatically generating an empty methoddef macro. + +- #Issue 20456: Cloned functions in Argument Clinic now use the correct + name, not the name of the function they were cloned from, for text + strings inside generated code. + +- #Issue 20456: Fixed Argument Clinic's test suite and "--converters" feature. + +- #Issue 20456: Argument Clinic now allows specifying different names + for a parameter in Python and C, using "as" on the parameter line. + +- Issue #20326: Argument Clinic now uses a simple, unique signature to + annotate text signatures in docstrings, resulting in fewer false + positives. "self" parameters are also explicitly marked, allowing + inspect.Signature() to authoritatively detect (and skip) said parameters. + +- Issue #20326: Argument Clinic now generates separate checksums for the + input and output sections of the block, allowing external tools to verify + that the input has not changed (and thus the output is not out-of-date). + +Build +----- + +- Issue #20465: Update SQLite shipped with OS X installer to 3.8.3. + + +What's New in Python 3.4.0 Beta 3? +================================== + +Release date: 2014-01-26 + +Core and Builtins +----------------- + +- Issue #20189: Four additional builtin types (PyTypeObject, + PyMethodDescr_Type, _PyMethodWrapper_Type, and PyWrapperDescr_Type) + have been modified to provide introspection information for builtins. + +- Issue #17825: Cursor "^" is correctly positioned for SyntaxError and + IndentationError. + +- Issue #2382: SyntaxError cursor "^" is now written at correct position in most + cases when multibyte characters are in line (before "^"). This still not + works correctly with wide East Asian characters. + +- Issue #18960: The first line of Python script could be executed twice when + the source encoding was specified on the second line. Now the source encoding + declaration on the second line isn't effective if the first line contains + anything except a comment. 'python -x' works now again with files with the + source encoding declarations, and can be used to make Python batch files + on Windows. + +Library +------- + +- asyncio: Various improvements and small changes not all covered by + issues listed below. E.g. wait_for() now cancels the inner task if + the timeout occcurs; tweaked the set of exported symbols; renamed + Empty/Full to QueueEmpty/QueueFull; "with (yield from lock)" now + uses a separate context manager; readexactly() raises if not enough + data was read; PTY support tweaks. + +- Issue #20311: asyncio: Add a granularity attribute to BaseEventLoop: maximum + between the resolution of the BaseEventLoop.time() method and the resolution + of the selector. The granuarility is used in the scheduler to round time and + deadline. + +- Issue #20311: selectors: Add a resolution attribute to BaseSelector. + +- Issue #20189: unittest.mock now no longer assumes that any object for + which it could get an inspect.Signature is a callable written in Python. + Fix courtesy of Michael Foord. + - Issue #20317: ExitStack.__exit__ could create a self-referential loop if an exception raised by a cleanup operation already had its context set correctly (for example, by the @contextmanager decorator). The infinite