Merged revisions 76443 via svnmerge from
svn+ssh://pythondev@svn.python.org/python/trunk
........
r76443 | lars.gustaebel | 2009-11-22 19:30:53 +0100 (Sun, 22 Nov 2009) | 24 lines
Issue #6123: Fix opening empty archives and files.
(Note that an empty archive is not the same as an empty file. An
empty archive contains no members and is correctly terminated with an
EOF block full of zeros. An empty file contains no data at all.)
The problem was that although tarfile was able to create empty
archives, it failed to open them raising a ReadError. On the other
hand, tarfile opened empty files without error in most read modes and
presented them as empty archives. (However, some modes still raised
errors: "r|gz" raised ReadError, but "r:gz" worked, "r:bz2" even
raised EOFError.)
In order to get a more fine-grained control over the various internal
error conditions I now split up the HeaderError exception into a
number of meaningful sub-exceptions. This makes it easier in the
TarFile.next() method to react to the different conditions in the
correct way.
The visible change in its behaviour now is that tarfile will open
empty archives correctly and raise ReadError consistently for empty
files.
........
diff --git a/Lib/test/test_tarfile.py b/Lib/test/test_tarfile.py
index 551d098..5719f08 100644
--- a/Lib/test/test_tarfile.py
+++ b/Lib/test/test_tarfile.py
@@ -135,7 +135,53 @@
fobj.close()
-class MiscReadTest(ReadTest):
+class CommonReadTest(ReadTest):
+
+ def test_empty_tarfile(self):
+ # Test for issue6123: Allow opening empty archives.
+ # This test checks if tarfile.open() is able to open an empty tar
+ # archive successfully. Note that an empty tar archive is not the
+ # same as an empty file!
+ tarfile.open(tmpname, self.mode.replace("r", "w")).close()
+ try:
+ tar = tarfile.open(tmpname, self.mode)
+ tar.getnames()
+ except tarfile.ReadError:
+ self.fail("tarfile.open() failed on empty archive")
+ self.assertListEqual(tar.getmembers(), [])
+
+ def test_null_tarfile(self):
+ # Test for issue6123: Allow opening empty archives.
+ # This test guarantees that tarfile.open() does not treat an empty
+ # file as an empty tar archive.
+ open(tmpname, "wb").close()
+ self.assertRaises(tarfile.ReadError, tarfile.open, tmpname, self.mode)
+ self.assertRaises(tarfile.ReadError, tarfile.open, tmpname)
+
+ def test_ignore_zeros(self):
+ # Test TarFile's ignore_zeros option.
+ if self.mode.endswith(":gz"):
+ _open = gzip.GzipFile
+ elif self.mode.endswith(":bz2"):
+ _open = bz2.BZ2File
+ else:
+ _open = open
+
+ for char in (b'\0', b'a'):
+ # Test if EOFHeaderError ('\0') and InvalidHeaderError ('a')
+ # are ignored correctly.
+ fobj = _open(tmpname, "wb")
+ fobj.write(char * 1024)
+ fobj.write(tarfile.TarInfo("foo").tobuf())
+ fobj.close()
+
+ tar = tarfile.open(tmpname, mode="r", ignore_zeros=True)
+ self.assertListEqual(tar.getnames(), ["foo"],
+ "ignore_zeros=True should have skipped the %r-blocks" % char)
+ tar.close()
+
+
+class MiscReadTest(CommonReadTest):
def test_no_name_argument(self):
fobj = open(self.tarname, "rb")
@@ -264,7 +310,7 @@
tar.close()
-class StreamReadTest(ReadTest):
+class StreamReadTest(CommonReadTest):
mode="r|"
@@ -1079,12 +1125,12 @@
self._test()
def test_empty(self):
- open(self.tarname, "w").close()
+ tarfile.open(self.tarname, "w:").close()
self._add_testfile()
self._test()
def test_empty_fileobj(self):
- fobj = io.BytesIO()
+ fobj = io.BytesIO(b"\0" * 1024)
self._add_testfile(fobj)
fobj.seek(0)
self._test(fileobj=fobj)
@@ -1114,6 +1160,29 @@
self._create_testtar("w:bz2")
self.assertRaises(tarfile.ReadError, tarfile.open, tmpname, "a")
+ # Append mode is supposed to fail if the tarfile to append to
+ # does not end with a zero block.
+ def _test_error(self, data):
+ open(self.tarname, "wb").write(data)
+ self.assertRaises(tarfile.ReadError, self._add_testfile)
+
+ def test_null(self):
+ self._test_error(b"")
+
+ def test_incomplete(self):
+ self._test_error(b"\0" * 13)
+
+ def test_premature_eof(self):
+ data = tarfile.TarInfo("foo").tobuf()
+ self._test_error(data)
+
+ def test_trailing_garbage(self):
+ data = tarfile.TarInfo("foo").tobuf()
+ self._test_error(data + b"\0" * 13)
+
+ def test_invalid(self):
+ self._test_error(b"a" * 512)
+
class LimitsTest(unittest.TestCase):
@@ -1228,10 +1297,16 @@
raise AssertionError("infinite loop detected in tarfile.open()")
self.hit_eof = self.tell() == len(self.getvalue())
return super(MyBytesIO, self).read(n)
+ def seek(self, *args):
+ self.hit_eof = False
+ return super(MyBytesIO, self).seek(*args)
data = bz2.compress(tarfile.TarInfo("foo").tobuf())
for x in range(len(data) + 1):
- tarfile.open(fileobj=MyBytesIO(data[:x]), mode=mode)
+ try:
+ tarfile.open(fileobj=MyBytesIO(data[:x]), mode=mode)
+ except tarfile.ReadError:
+ pass # we have no interest in ReadErrors
def test_partial_input(self):
self._test_partial_input("r")