Mirror
/
cpython
mirror of https://github.com/python/cpython
4
1
Fork 0
Code Issues Releases Wiki Activity

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.
This commit is contained in:
Lars Gustäbel 2009-11-22 18:30:53 +00:00
parent 814d02dcd1
commit dd866d57af
3 changed files with 143 additions and 32 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

79
Lib/tarfile.py
View File

@ -195,7 +195,7 @@ def nti(s):
try:
n = int(nts(s) or "0", 8)
except ValueError:
raise HeaderError("invalid header")
raise InvalidHeaderError("invalid header")
else:
n = 0L
for i in xrange(len(s) - 1):
@ -346,8 +346,23 @@ class StreamError(TarError):
"""Exception for unsupported operations on stream-like TarFiles."""
pass
class HeaderError(TarError):
"""Base exception for header errors."""
pass
class EmptyHeaderError(HeaderError):
"""Exception for empty headers."""
pass
class TruncatedHeaderError(HeaderError):
"""Exception for truncated headers."""
pass
class EOFHeaderError(HeaderError):
"""Exception for end of file headers."""
pass
class InvalidHeaderError(HeaderError):
"""Exception for invalid headers."""
pass
class SubsequentHeaderError(HeaderError):
"""Exception for missing and invalid extended headers."""
pass
#---------------------------
# internal stream interface
@ -1179,14 +1194,16 @@ class TarInfo(object):
def frombuf(cls, buf):
"""Construct a TarInfo object from a 512 byte string buffer.
"""
if len(buf) == 0:
raise EmptyHeaderError("empty header")
if len(buf) != BLOCKSIZE:
raise HeaderError("truncated header")
raise TruncatedHeaderError("truncated header")
if buf.count(NUL) == BLOCKSIZE:
raise HeaderError("empty header")
raise EOFHeaderError("end of file header")
chksum = nti(buf[148:156])
if chksum not in calc_chksums(buf):
raise HeaderError("bad checksum")
raise InvalidHeaderError("bad checksum")
obj = cls()
obj.buf = buf
@ -1225,8 +1242,6 @@ class TarInfo(object):
tarfile.
"""
buf = tarfile.fileobj.read(BLOCKSIZE)
if not buf:
return
obj = cls.frombuf(buf)
obj.offset = tarfile.fileobj.tell() - BLOCKSIZE
return obj._proc_member(tarfile)
@ -1279,9 +1294,10 @@ class TarInfo(object):
buf = tarfile.fileobj.read(self._block(self.size))
# Fetch the next header and process it.
try:
next = self.fromtarfile(tarfile)
if next is None:
raise HeaderError("missing subsequent header")
except HeaderError:
raise SubsequentHeaderError("missing or bad subsequent header")
# Patch the TarInfo object from the next header with
# the longname information.
@ -1386,12 +1402,12 @@ class TarInfo(object):
pos += length
# Fetch the next header.
try:
next = self.fromtarfile(tarfile)
except HeaderError:
raise SubsequentHeaderError("missing or bad subsequent header")
if self.type in (XHDTYPE, SOLARIS_XHDTYPE):
if next is None:
raise HeaderError("missing subsequent header")
# Patch the TarInfo object with the extended header info.
next._apply_pax_info(pax_headers, tarfile.encoding, tarfile.errors)
next.offset = self.offset
@ -1565,12 +1581,16 @@ class TarFile(object):
if self.mode == "a":
# Move to the end of the archive,
# before the first empty block.
self.firstmember = None
while True:
if self.next() is None:
if self.offset > 0:
self.fileobj.seek(- BLOCKSIZE, 1)
self.fileobj.seek(self.offset)
try:
tarinfo = self.tarinfo.fromtarfile(self)
self.members.append(tarinfo)
except EOFHeaderError:
self.fileobj.seek(self.offset)
break
except HeaderError, e:
raise ReadError(str(e))
if self.mode in "aw":
self._loaded = True
@ -1735,7 +1755,7 @@ class TarFile(object):
try:
t = cls.taropen(name, mode, fileobj, **kwargs)
except IOError:
except (IOError, EOFError):
raise ReadError("not a bzip2 file")
t._extfileobj = False
return t
@ -2307,24 +2327,37 @@ class TarFile(object):
# Read the next block.
self.fileobj.seek(self.offset)
tarinfo = None
while True:
try:
tarinfo = self.tarinfo.fromtarfile(self)
if tarinfo is None:
return
self.members.append(tarinfo)
except HeaderError, e:
except EOFHeaderError, e:
if self.ignore_zeros:
self._dbg(2, "0x%X: %s" % (self.offset, e))
self.offset += BLOCKSIZE
continue
else:
except InvalidHeaderError, e:
if self.ignore_zeros:
self._dbg(2, "0x%X: %s" % (self.offset, e))
self.offset += BLOCKSIZE
continue
elif self.offset == 0:
raise ReadError(str(e))
except EmptyHeaderError:
if self.offset == 0:
raise ReadError("empty file")
except TruncatedHeaderError, e:
if self.offset == 0:
raise ReadError(str(e))
return None
except SubsequentHeaderError, e:
raise ReadError(str(e))
break
if tarinfo is not None:
self.members.append(tarinfo)
else:
self._loaded = True
return tarinfo
#--------------------------------------------------------------------------

83
Lib/test/test_tarfile.py
View File

@ -136,7 +136,53 @@ class UstarReadTest(ReadTest):
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 ('\0', '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")
@ -265,7 +311,7 @@ class MiscReadTest(ReadTest):
tar.close()
class StreamReadTest(ReadTest):
class StreamReadTest(CommonReadTest):
mode="r|"
@ -1111,12 +1157,12 @@ class AppendTest(unittest.TestCase):
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 = StringIO.StringIO()
fobj = StringIO.StringIO("\0" * 1024)
self._add_testfile(fobj)
fobj.seek(0)
self._test(fileobj=fobj)
@ -1146,6 +1192,29 @@ class AppendTest(unittest.TestCase):
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("")
def test_incomplete(self):
self._test_error("\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 + "\0" * 13)
def test_invalid(self):
self._test_error("a" * 512)
class LimitsTest(unittest.TestCase):
@ -1247,10 +1316,16 @@ class Bz2PartialReadTest(unittest.TestCase):
raise AssertionError("infinite loop detected in tarfile.open()")
self.hit_eof = self.pos == self.len
return StringIO.StringIO.read(self, n)
def seek(self, *args):
self.hit_eof = False
return StringIO.StringIO.seek(self, *args)
data = bz2.compress(tarfile.TarInfo("foo").tobuf())
for x in range(len(data) + 1):
try:
tarfile.open(fileobj=MyStringIO(data[:x]), mode=mode)
except tarfile.ReadError:
pass # we have no interest in ReadErrors
def test_partial_input(self):
self._test_partial_input("r")

3
Misc/NEWS
View File

@ -476,6 +476,9 @@ Core and Builtins
Library
-------
- Issue #6123: tarfile now opens empty archives correctly and consistently
raises ReadError on empty files.
- Issue #7354: distutils.tests.test_msvc9compiler - dragfullwindows can
be 2.