summaryrefslogtreecommitdiffstats
path: root/Lib/test/test_tarfile.py
diff options
context:
space:
mode:
Diffstat (limited to 'Lib/test/test_tarfile.py')
-rw-r--r--Lib/test/test_tarfile.py1342
1 files changed, 761 insertions, 581 deletions
diff --git a/Lib/test/test_tarfile.py b/Lib/test/test_tarfile.py
index e9bf497..ac7dca3 100644
--- a/Lib/test/test_tarfile.py
+++ b/Lib/test/test_tarfile.py
@@ -1,8 +1,12 @@
+# encoding: iso8859-1
+
import sys
import os
import shutil
import tempfile
import StringIO
+import md5
+import errno
import unittest
import tarfile
@@ -20,452 +24,547 @@ try:
except ImportError:
bz2 = None
+def md5sum(data):
+ return md5.new(data).hexdigest()
+
def path(path):
return test_support.findfile(path)
-testtar = path("testtar.tar")
-tempdir = os.path.join(tempfile.gettempdir(), "testtar" + os.extsep + "dir")
-tempname = test_support.TESTFN
-membercount = 12
-
-def tarname(comp=""):
- if not comp:
- return testtar
- return os.path.join(tempdir, "%s%s%s" % (testtar, os.extsep, comp))
+TEMPDIR = os.path.join(tempfile.gettempdir(), "test_tarfile_tmp")
+tarname = path("testtar.tar")
+gzipname = os.path.join(TEMPDIR, "testtar.tar.gz")
+bz2name = os.path.join(TEMPDIR, "testtar.tar.bz2")
+tmpname = os.path.join(TEMPDIR, "tmp.tar")
-def dirname():
- if not os.path.exists(tempdir):
- os.mkdir(tempdir)
- return tempdir
+md5_regtype = "65f477c818ad9e15f7feab0c6d37742f"
+md5_sparse = "a54fbc4ca4f4399a90e1b27164012fc6"
-def tmpname():
- return tempname
+class ReadTest(unittest.TestCase):
-class BaseTest(unittest.TestCase):
- comp = ''
- mode = 'r'
- sep = ':'
+ tarname = tarname
+ mode = "r:"
def setUp(self):
- mode = self.mode + self.sep + self.comp
- self.tar = tarfile.open(tarname(self.comp), mode)
+ self.tar = tarfile.open(self.tarname, mode=self.mode, encoding="iso8859-1")
def tearDown(self):
self.tar.close()
-class ReadTest(BaseTest):
- def test(self):
- """Test member extraction.
- """
- members = 0
+class UstarReadTest(ReadTest):
+
+ def test_fileobj_regular_file(self):
+ tarinfo = self.tar.getmember("ustar/regtype")
+ fobj = self.tar.extractfile(tarinfo)
+ data = fobj.read()
+ self.assert_((len(data), md5sum(data)) == (tarinfo.size, md5_regtype),
+ "regular file extraction failed")
+
+ def test_fileobj_readlines(self):
+ self.tar.extract("ustar/regtype", TEMPDIR)
+ tarinfo = self.tar.getmember("ustar/regtype")
+ fobj1 = open(os.path.join(TEMPDIR, "ustar/regtype"), "rU")
+ fobj2 = self.tar.extractfile(tarinfo)
+
+ lines1 = fobj1.readlines()
+ lines2 = fobj2.readlines()
+ self.assert_(lines1 == lines2,
+ "fileobj.readlines() failed")
+ self.assert_(len(lines2) == 114,
+ "fileobj.readlines() failed")
+ self.assert_(lines2[83] == \
+ "I will gladly admit that Python is not the fastest running scripting language.\n",
+ "fileobj.readlines() failed")
+
+ def test_fileobj_iter(self):
+ self.tar.extract("ustar/regtype", TEMPDIR)
+ tarinfo = self.tar.getmember("ustar/regtype")
+ fobj1 = open(os.path.join(TEMPDIR, "ustar/regtype"), "rU")
+ fobj2 = self.tar.extractfile(tarinfo)
+ lines1 = fobj1.readlines()
+ lines2 = [line for line in fobj2]
+ self.assert_(lines1 == lines2,
+ "fileobj.__iter__() failed")
+
+ def test_fileobj_seek(self):
+ self.tar.extract("ustar/regtype", TEMPDIR)
+ fobj = open(os.path.join(TEMPDIR, "ustar/regtype"), "rb")
+ data = fobj.read()
+ fobj.close()
+
+ tarinfo = self.tar.getmember("ustar/regtype")
+ fobj = self.tar.extractfile(tarinfo)
+
+ text = fobj.read()
+ fobj.seek(0)
+ self.assert_(0 == fobj.tell(),
+ "seek() to file's start failed")
+ fobj.seek(2048, 0)
+ self.assert_(2048 == fobj.tell(),
+ "seek() to absolute position failed")
+ fobj.seek(-1024, 1)
+ self.assert_(1024 == fobj.tell(),
+ "seek() to negative relative position failed")
+ fobj.seek(1024, 1)
+ self.assert_(2048 == fobj.tell(),
+ "seek() to positive relative position failed")
+ s = fobj.read(10)
+ self.assert_(s == data[2048:2058],
+ "read() after seek failed")
+ fobj.seek(0, 2)
+ self.assert_(tarinfo.size == fobj.tell(),
+ "seek() to file's end failed")
+ self.assert_(fobj.read() == "",
+ "read() at file's end did not return empty string")
+ fobj.seek(-tarinfo.size, 2)
+ self.assert_(0 == fobj.tell(),
+ "relative seek() to file's start failed")
+ fobj.seek(512)
+ s1 = fobj.readlines()
+ fobj.seek(512)
+ s2 = fobj.readlines()
+ self.assert_(s1 == s2,
+ "readlines() after seek failed")
+ fobj.seek(0)
+ self.assert_(len(fobj.readline()) == fobj.tell(),
+ "tell() after readline() failed")
+ fobj.seek(512)
+ self.assert_(len(fobj.readline()) + 512 == fobj.tell(),
+ "tell() after seek() and readline() failed")
+ fobj.seek(0)
+ line = fobj.readline()
+ self.assert_(fobj.read() == data[len(line):],
+ "read() after readline() failed")
+ fobj.close()
+
+
+class MiscReadTest(ReadTest):
+
+ def test_no_filename(self):
+ fobj = open(self.tarname, "rb")
+ tar = tarfile.open(fileobj=fobj, mode=self.mode)
+ self.assertEqual(tar.name, os.path.abspath(fobj.name))
+
+ def test_fail_comp(self):
+ # For Gzip and Bz2 Tests: fail with a ReadError on an uncompressed file.
+ if self.mode == "r:":
+ return
+ self.assertRaises(tarfile.ReadError, tarfile.open, tarname, self.mode)
+ fobj = open(tarname, "rb")
+ self.assertRaises(tarfile.ReadError, tarfile.open, fileobj=fobj, mode=self.mode)
+
+ def test_v7_dirtype(self):
+ # Test old style dirtype member (bug #1336623):
+ # Old V7 tars create directory members using an AREGTYPE
+ # header with a "/" appended to the filename field.
+ tarinfo = self.tar.getmember("misc/dirtype-old-v7")
+ self.assert_(tarinfo.type == tarfile.DIRTYPE,
+ "v7 dirtype failed")
+
+ def test_check_members(self):
for tarinfo in self.tar:
- members += 1
- if not tarinfo.isreg():
+ self.assert_(int(tarinfo.mtime) == 07606136617,
+ "wrong mtime for %s" % tarinfo.name)
+ if not tarinfo.name.startswith("ustar/"):
continue
- f = self.tar.extractfile(tarinfo)
- self.assert_(len(f.read()) == tarinfo.size,
- "size read does not match expected size")
- f.close()
-
- self.assert_(members == membercount,
- "could not find all members")
-
- def test_sparse(self):
- """Test sparse member extraction.
- """
- if self.sep != "|":
- f1 = self.tar.extractfile("S-SPARSE")
- f2 = self.tar.extractfile("S-SPARSE-WITH-NULLS")
- self.assert_(f1.read() == f2.read(),
- "_FileObject failed on sparse file member")
-
- def test_readlines(self):
- """Test readlines() method of _FileObject.
- """
- if self.sep != "|":
- filename = "0-REGTYPE-TEXT"
- self.tar.extract(filename, dirname())
- f = open(os.path.join(dirname(), filename), "rU")
- lines1 = f.readlines()
- f.close()
- lines2 = self.tar.extractfile(filename).readlines()
- self.assert_(lines1 == lines2,
- "_FileObject.readline() does not work correctly")
-
- def test_iter(self):
- # Test iteration over ExFileObject.
- if self.sep != "|":
- filename = "0-REGTYPE-TEXT"
- self.tar.extract(filename, dirname())
- f = open(os.path.join(dirname(), filename), "rU")
- lines1 = f.readlines()
- f.close()
- lines2 = [line for line in self.tar.extractfile(filename)]
- self.assert_(lines1 == lines2,
- "ExFileObject iteration does not work correctly")
-
- def test_seek(self):
- """Test seek() method of _FileObject, incl. random reading.
- """
- if self.sep != "|":
- filename = "0-REGTYPE-TEXT"
- self.tar.extract(filename, dirname())
- f = open(os.path.join(dirname(), filename), "rb")
- data = f.read()
- f.close()
-
- tarinfo = self.tar.getmember(filename)
- fobj = self.tar.extractfile(tarinfo)
-
- text = fobj.read()
- fobj.seek(0)
- self.assert_(0 == fobj.tell(),
- "seek() to file's start failed")
- fobj.seek(2048, 0)
- self.assert_(2048 == fobj.tell(),
- "seek() to absolute position failed")
- fobj.seek(-1024, 1)
- self.assert_(1024 == fobj.tell(),
- "seek() to negative relative position failed")
- fobj.seek(1024, 1)
- self.assert_(2048 == fobj.tell(),
- "seek() to positive relative position failed")
- s = fobj.read(10)
- self.assert_(s == data[2048:2058],
- "read() after seek failed")
- fobj.seek(0, 2)
- self.assert_(tarinfo.size == fobj.tell(),
- "seek() to file's end failed")
- self.assert_(fobj.read() == "",
- "read() at file's end did not return empty string")
- fobj.seek(-tarinfo.size, 2)
- self.assert_(0 == fobj.tell(),
- "relative seek() to file's start failed")
- fobj.seek(512)
- s1 = fobj.readlines()
- fobj.seek(512)
- s2 = fobj.readlines()
- self.assert_(s1 == s2,
- "readlines() after seek failed")
- fobj.seek(0)
- self.assert_(len(fobj.readline()) == fobj.tell(),
- "tell() after readline() failed")
- fobj.seek(512)
- self.assert_(len(fobj.readline()) + 512 == fobj.tell(),
- "tell() after seek() and readline() failed")
- fobj.seek(0)
- line = fobj.readline()
- self.assert_(fobj.read() == data[len(line):],
- "read() after readline() failed")
- fobj.close()
+ self.assert_(tarinfo.uname == "tarfile",
+ "wrong uname for %s" % tarinfo.name)
- def test_old_dirtype(self):
- """Test old style dirtype member (bug #1336623).
- """
- # Old tars create directory members using a REGTYPE
- # header with a "/" appended to the filename field.
+ def test_find_members(self):
+ self.assert_(self.tar.getmembers()[-1].name == "misc/eof",
+ "could not find all members")
- # Create an old tar style directory entry.
- filename = tmpname()
- tarinfo = tarfile.TarInfo("directory/")
- tarinfo.type = tarfile.REGTYPE
+ def test_extract_hardlink(self):
+ # Test hardlink extraction (e.g. bug #857297).
+ tar = tarfile.open(tarname, errorlevel=1, encoding="iso8859-1")
- fobj = open(filename, "w")
- fobj.write(tarinfo.tobuf())
- fobj.close()
+ tar.extract("ustar/regtype", TEMPDIR)
+ try:
+ tar.extract("ustar/lnktype", TEMPDIR)
+ except EnvironmentError as e:
+ if e.errno == errno.ENOENT:
+ self.fail("hardlink not extracted properly")
+
+ data = open(os.path.join(TEMPDIR, "ustar/lnktype"), "rb").read()
+ self.assertEqual(md5sum(data), md5_regtype)
try:
- # Test if it is still a directory entry when
- # read back.
- tar = tarfile.open(filename)
- tarinfo = tar.getmembers()[0]
- tar.close()
-
- self.assert_(tarinfo.type == tarfile.DIRTYPE)
- self.assert_(tarinfo.name.endswith("/"))
- finally:
- try:
- os.unlink(filename)
- except:
- pass
-
-class ReadStreamTest(ReadTest):
- sep = "|"
-
- def test(self):
- """Test member extraction, and for StreamError when
- seeking backwards.
- """
- ReadTest.test(self)
- tarinfo = self.tar.getmembers()[0]
- f = self.tar.extractfile(tarinfo)
+ tar.extract("ustar/symtype", TEMPDIR)
+ except EnvironmentError as e:
+ if e.errno == errno.ENOENT:
+ self.fail("symlink not extracted properly")
+
+ data = open(os.path.join(TEMPDIR, "ustar/symtype"), "rb").read()
+ self.assertEqual(md5sum(data), md5_regtype)
+
+
+class StreamReadTest(ReadTest):
+
+ mode="r|"
+
+ def test_fileobj_regular_file(self):
+ tarinfo = self.tar.next() # get "regtype" (can't use getmember)
+ fobj = self.tar.extractfile(tarinfo)
+ data = fobj.read()
+ self.assert_((len(data), md5sum(data)) == (tarinfo.size, md5_regtype),
+ "regular file extraction failed")
+
+ def test_provoke_stream_error(self):
+ tarinfos = self.tar.getmembers()
+ f = self.tar.extractfile(tarinfos[0]) # read the first member
self.assertRaises(tarfile.StreamError, f.read)
- def test_stream(self):
- """Compare the normal tar and the stream tar.
- """
- stream = self.tar
- tar = tarfile.open(tarname(), 'r')
+ def test_compare_members(self):
+ tar1 = tarfile.open(tarname, encoding="iso8859-1")
+ tar2 = self.tar
- while 1:
- t1 = tar.next()
- t2 = stream.next()
+ while True:
+ t1 = tar1.next()
+ t2 = tar2.next()
if t1 is None:
break
self.assert_(t2 is not None, "stream.next() failed.")
if t2.islnk() or t2.issym():
- self.assertRaises(tarfile.StreamError, stream.extractfile, t2)
+ self.assertRaises(tarfile.StreamError, tar2.extractfile, t2)
continue
- v1 = tar.extractfile(t1)
- v2 = stream.extractfile(t2)
+
+ v1 = tar1.extractfile(t1)
+ v2 = tar2.extractfile(t2)
if v1 is None:
continue
self.assert_(v2 is not None, "stream.extractfile() failed")
self.assert_(v1.read() == v2.read(), "stream extraction failed")
- tar.close()
- stream.close()
+ tar1.close()
-class ReadDetectTest(ReadTest):
- def setUp(self):
- self.tar = tarfile.open(tarname(self.comp), self.mode)
+class DetectReadTest(unittest.TestCase):
-class ReadDetectFileobjTest(ReadTest):
+ def _testfunc_file(self, name, mode):
+ try:
+ tarfile.open(name, mode)
+ except tarfile.ReadError:
+ self.fail()
- def setUp(self):
- name = tarname(self.comp)
- self.tar = tarfile.open(name, mode=self.mode,
- fileobj=open(name, "rb"))
+ def _testfunc_fileobj(self, name, mode):
+ try:
+ tarfile.open(name, mode, fileobj=open(name, "rb"))
+ except tarfile.ReadError:
+ self.fail()
-class ReadAsteriskTest(ReadTest):
+ def _test_modes(self, testfunc):
+ testfunc(tarname, "r")
+ testfunc(tarname, "r:")
+ testfunc(tarname, "r:*")
+ testfunc(tarname, "r|")
+ testfunc(tarname, "r|*")
- def setUp(self):
- mode = self.mode + self.sep + "*"
- self.tar = tarfile.open(tarname(self.comp), mode)
+ if gzip:
+ self.assertRaises(tarfile.ReadError, tarfile.open, tarname, mode="r:gz")
+ self.assertRaises(tarfile.ReadError, tarfile.open, tarname, mode="r|gz")
+ self.assertRaises(tarfile.ReadError, tarfile.open, gzipname, mode="r:")
+ self.assertRaises(tarfile.ReadError, tarfile.open, gzipname, mode="r|")
-class ReadStreamAsteriskTest(ReadStreamTest):
+ testfunc(gzipname, "r")
+ testfunc(gzipname, "r:*")
+ testfunc(gzipname, "r:gz")
+ testfunc(gzipname, "r|*")
+ testfunc(gzipname, "r|gz")
- def setUp(self):
- mode = self.mode + self.sep + "*"
- self.tar = tarfile.open(tarname(self.comp), mode)
+ if bz2:
+ self.assertRaises(tarfile.ReadError, tarfile.open, tarname, mode="r:bz2")
+ self.assertRaises(tarfile.ReadError, tarfile.open, tarname, mode="r|bz2")
+ self.assertRaises(tarfile.ReadError, tarfile.open, bz2name, mode="r:")
+ self.assertRaises(tarfile.ReadError, tarfile.open, bz2name, mode="r|")
-class WriteTest(BaseTest):
- mode = 'w'
+ testfunc(bz2name, "r")
+ testfunc(bz2name, "r:*")
+ testfunc(bz2name, "r:bz2")
+ testfunc(bz2name, "r|*")
+ testfunc(bz2name, "r|bz2")
- def setUp(self):
- mode = self.mode + self.sep + self.comp
- self.src = tarfile.open(tarname(self.comp), 'r')
- self.dstname = tmpname()
- self.dst = tarfile.open(self.dstname, mode)
+ def test_detect_file(self):
+ self._test_modes(self._testfunc_file)
- def tearDown(self):
- self.src.close()
- self.dst.close()
+ def test_detect_fileobj(self):
+ self._test_modes(self._testfunc_fileobj)
- def test_posix(self):
- self.dst.posix = 1
- self._test()
- def test_nonposix(self):
- self.dst.posix = 0
- self._test()
+class MemberReadTest(ReadTest):
- def test_small(self):
- self.dst.add(os.path.join(os.path.dirname(__file__),"cfgparser.1"))
- self.dst.close()
- self.assertNotEqual(os.stat(self.dstname).st_size, 0)
+ def _test_member(self, tarinfo, chksum=None, **kwargs):
+ if chksum is not None:
+ self.assert_(md5sum(self.tar.extractfile(tarinfo).read()) == chksum,
+ "wrong md5sum for %s" % tarinfo.name)
- def _test(self):
- for tarinfo in self.src:
- if not tarinfo.isreg():
- continue
- f = self.src.extractfile(tarinfo)
- if self.dst.posix and len(tarinfo.name) > tarfile.LENGTH_NAME and "/" not in tarinfo.name:
- self.assertRaises(ValueError, self.dst.addfile,
- tarinfo, f)
- else:
- self.dst.addfile(tarinfo, f)
+ kwargs["mtime"] = 07606136617
+ kwargs["uid"] = 1000
+ kwargs["gid"] = 100
+ if "old-v7" not in tarinfo.name:
+ # V7 tar can't handle alphabetic owners.
+ kwargs["uname"] = "tarfile"
+ kwargs["gname"] = "tarfile"
+ for k, v in kwargs.items():
+ self.assert_(getattr(tarinfo, k) == v,
+ "wrong value in %s field of %s" % (k, tarinfo.name))
- def test_add_self(self):
- dstname = os.path.abspath(self.dstname)
+ def test_find_regtype(self):
+ tarinfo = self.tar.getmember("ustar/regtype")
+ self._test_member(tarinfo, size=7011, chksum=md5_regtype)
- self.assertEqual(self.dst.name, dstname, "archive name must be absolute")
+ def test_find_conttype(self):
+ tarinfo = self.tar.getmember("ustar/conttype")
+ self._test_member(tarinfo, size=7011, chksum=md5_regtype)
- self.dst.add(dstname)
- self.assertEqual(self.dst.getnames(), [], "added the archive to itself")
+ def test_find_dirtype(self):
+ tarinfo = self.tar.getmember("ustar/dirtype")
+ self._test_member(tarinfo, size=0)
- cwd = os.getcwd()
- os.chdir(dirname())
- self.dst.add(dstname)
- os.chdir(cwd)
- self.assertEqual(self.dst.getnames(), [], "added the archive to itself")
+ def test_find_dirtype_with_size(self):
+ tarinfo = self.tar.getmember("ustar/dirtype-with-size")
+ self._test_member(tarinfo, size=255)
+ def test_find_lnktype(self):
+ tarinfo = self.tar.getmember("ustar/lnktype")
+ self._test_member(tarinfo, size=0, linkname="ustar/regtype")
-class AppendTest(unittest.TestCase):
- # Test append mode (cp. patch #1652681).
+ def test_find_symtype(self):
+ tarinfo = self.tar.getmember("ustar/symtype")
+ self._test_member(tarinfo, size=0, linkname="regtype")
- def setUp(self):
- self.tarname = tmpname()
- if os.path.exists(self.tarname):
- os.remove(self.tarname)
+ def test_find_blktype(self):
+ tarinfo = self.tar.getmember("ustar/blktype")
+ self._test_member(tarinfo, size=0, devmajor=3, devminor=0)
- def _add_testfile(self, fileobj=None):
- tar = tarfile.open(self.tarname, "a", fileobj=fileobj)
- tar.addfile(tarfile.TarInfo("bar"))
- tar.close()
+ def test_find_chrtype(self):
+ tarinfo = self.tar.getmember("ustar/chrtype")
+ self._test_member(tarinfo, size=0, devmajor=1, devminor=3)
- def _create_testtar(self):
- src = tarfile.open(tarname())
- t = src.getmember("0-REGTYPE")
- t.name = "foo"
- f = src.extractfile(t)
- tar = tarfile.open(self.tarname, "w")
- tar.addfile(t, f)
- tar.close()
+ def test_find_fifotype(self):
+ tarinfo = self.tar.getmember("ustar/fifotype")
+ self._test_member(tarinfo, size=0)
- def _test(self, names=["bar"], fileobj=None):
- tar = tarfile.open(self.tarname, fileobj=fileobj)
- self.assert_(tar.getnames() == names)
+ def test_find_sparse(self):
+ tarinfo = self.tar.getmember("ustar/sparse")
+ self._test_member(tarinfo, size=86016, chksum=md5_sparse)
- def test_non_existing(self):
- self._add_testfile()
- self._test()
+ def test_find_umlauts(self):
+ tarinfo = self.tar.getmember("ustar/umlauts-ÄÖÜäöüß")
+ self._test_member(tarinfo, size=7011, chksum=md5_regtype)
- def test_empty(self):
- open(self.tarname, "wb").close()
- self._add_testfile()
- self._test()
+ def test_find_ustar_longname(self):
+ name = "ustar/" + "12345/" * 39 + "1234567/longname"
+ self.assert_(name in self.tar.getnames())
- def test_empty_fileobj(self):
- fobj = StringIO.StringIO()
- self._add_testfile(fobj)
- fobj.seek(0)
- self._test(fileobj=fobj)
+ def test_find_regtype_oldv7(self):
+ tarinfo = self.tar.getmember("misc/regtype-old-v7")
+ self._test_member(tarinfo, size=7011, chksum=md5_regtype)
- def test_fileobj(self):
- self._create_testtar()
- data = open(self.tarname, "rb").read()
- fobj = StringIO.StringIO(data)
- self._add_testfile(fobj)
- fobj.seek(0)
- self._test(names=["foo", "bar"], fileobj=fobj)
+ def test_find_pax_umlauts(self):
+ self.tar = tarfile.open(self.tarname, mode=self.mode, encoding="iso8859-1")
+ tarinfo = self.tar.getmember("pax/umlauts-ÄÖÜäöüß")
+ self._test_member(tarinfo, size=7011, chksum=md5_regtype)
- def test_existing(self):
- self._create_testtar()
- self._add_testfile()
- self._test(names=["foo", "bar"])
+class LongnameTest(ReadTest):
-class Write100Test(BaseTest):
- # The name field in a tar header stores strings of at most 100 chars.
- # If a string is shorter than 100 chars it has to be padded with '\0',
- # which implies that a string of exactly 100 chars is stored without
- # a trailing '\0'.
+ def test_read_longname(self):
+ # Test reading of longname (bug #1471427).
+ name = self.subdir + "/" + "123/" * 125 + "longname"
+ try:
+ tarinfo = self.tar.getmember(name)
+ except KeyError:
+ self.fail("longname not found")
+ self.assert_(tarinfo.type != tarfile.DIRTYPE, "read longname as dirtype")
- def setUp(self):
- self.name = "01234567890123456789012345678901234567890123456789"
- self.name += "01234567890123456789012345678901234567890123456789"
+ def test_read_longlink(self):
+ longname = self.subdir + "/" + "123/" * 125 + "longname"
+ longlink = self.subdir + "/" + "123/" * 125 + "longlink"
+ try:
+ tarinfo = self.tar.getmember(longlink)
+ except KeyError:
+ self.fail("longlink not found")
+ self.assert_(tarinfo.linkname == longname, "linkname wrong")
- self.tar = tarfile.open(tmpname(), "w")
- t = tarfile.TarInfo(self.name)
- self.tar.addfile(t)
- self.tar.close()
+ def test_truncated_longname(self):
+ longname = self.subdir + "/" + "123/" * 125 + "longname"
+ tarinfo = self.tar.getmember(longname)
+ offset = tarinfo.offset
+ self.tar.fileobj.seek(offset)
+ fobj = StringIO.StringIO(self.tar.fileobj.read(1536))
+ self.assertRaises(tarfile.ReadError, tarfile.open, name="foo.tar", fileobj=fobj)
- self.tar = tarfile.open(tmpname())
- def tearDown(self):
- self.tar.close()
+class GNUReadTest(LongnameTest):
- def test(self):
- self.assertEqual(self.tar.getnames()[0], self.name,
- "failed to store 100 char filename")
+ subdir = "gnu"
+ def test_sparse_file(self):
+ tarinfo1 = self.tar.getmember("ustar/sparse")
+ fobj1 = self.tar.extractfile(tarinfo1)
+ tarinfo2 = self.tar.getmember("gnu/sparse")
+ fobj2 = self.tar.extractfile(tarinfo2)
+ self.assert_(fobj1.read() == fobj2.read(),
+ "sparse file extraction failed")
-class WriteSize0Test(BaseTest):
- mode = 'w'
- def setUp(self):
- self.tmpdir = dirname()
- self.dstname = tmpname()
- self.dst = tarfile.open(self.dstname, "w")
+class PaxReadTest(ReadTest):
- def tearDown(self):
- self.dst.close()
+ subdir = "pax"
+
+ def test_pax_globheaders(self):
+ tar = tarfile.open(tarname, encoding="iso8859-1")
+ tarinfo = tar.getmember("pax/regtype1")
+ self.assertEqual(tarinfo.uname, "foo")
+ self.assertEqual(tarinfo.gname, "bar")
+ self.assertEqual(tarinfo.pax_headers.get("VENDOR.umlauts"), "ÄÖÜäöüß")
+
+ tarinfo = tar.getmember("pax/regtype2")
+ self.assertEqual(tarinfo.uname, "")
+ self.assertEqual(tarinfo.gname, "bar")
+ self.assertEqual(tarinfo.pax_headers.get("VENDOR.umlauts"), "ÄÖÜäöüß")
+
+ tarinfo = tar.getmember("pax/regtype3")
+ self.assertEqual(tarinfo.uname, "tarfile")
+ self.assertEqual(tarinfo.gname, "tarfile")
+ self.assertEqual(tarinfo.pax_headers.get("VENDOR.umlauts"), "ÄÖÜäöüß")
+
+
+class WriteTest(unittest.TestCase):
+
+ mode = "w:"
+
+ def test_100_char_name(self):
+ # The name field in a tar header stores strings of at most 100 chars.
+ # If a string is shorter than 100 chars it has to be padded with '\0',
+ # which implies that a string of exactly 100 chars is stored without
+ # a trailing '\0'.
+ name = "0123456789" * 10
+ tar = tarfile.open(tmpname, self.mode)
+ t = tarfile.TarInfo(name)
+ tar.addfile(t)
+ tar.close()
+
+ tar = tarfile.open(tmpname)
+ self.assert_(tar.getnames()[0] == name,
+ "failed to store 100 char filename")
+ tar.close()
+
+ def test_tar_size(self):
+ # Test for bug #1013882.
+ tar = tarfile.open(tmpname, self.mode)
+ path = os.path.join(TEMPDIR, "file")
+ fobj = open(path, "wb")
+ fobj.write("aaa")
+ fobj.close()
+ tar.add(path)
+ tar.close()
+ self.assert_(os.path.getsize(tmpname) > 0,
+ "tarfile is empty")
+
+ # The test_*_size tests test for bug #1167128.
+ def test_file_size(self):
+ tar = tarfile.open(tmpname, self.mode)
- def test_file(self):
- path = os.path.join(self.tmpdir, "file")
- f = open(path, "w")
- f.close()
- tarinfo = self.dst.gettarinfo(path)
+ path = os.path.join(TEMPDIR, "file")
+ fobj = open(path, "wb")
+ fobj.close()
+ tarinfo = tar.gettarinfo(path)
self.assertEqual(tarinfo.size, 0)
- f = open(path, "w")
- f.write("aaa")
- f.close()
- tarinfo = self.dst.gettarinfo(path)
+
+ fobj = open(path, "wb")
+ fobj.write("aaa")
+ fobj.close()
+ tarinfo = tar.gettarinfo(path)
self.assertEqual(tarinfo.size, 3)
- def test_directory(self):
- path = os.path.join(self.tmpdir, "directory")
- if os.path.exists(path):
- # This shouldn't be necessary, but is <wink> if a previous
- # run was killed in mid-stream.
- shutil.rmtree(path)
- os.mkdir(path)
- tarinfo = self.dst.gettarinfo(path)
- self.assertEqual(tarinfo.size, 0)
+ tar.close()
- def test_symlink(self):
+ def test_directory_size(self):
+ path = os.path.join(TEMPDIR, "directory")
+ os.mkdir(path)
+ try:
+ tar = tarfile.open(tmpname, self.mode)
+ tarinfo = tar.gettarinfo(path)
+ self.assertEqual(tarinfo.size, 0)
+ finally:
+ os.rmdir(path)
+
+ def test_link_size(self):
+ if hasattr(os, "link"):
+ link = os.path.join(TEMPDIR, "link")
+ target = os.path.join(TEMPDIR, "link_target")
+ open(target, "wb").close()
+ os.link(target, link)
+ try:
+ tar = tarfile.open(tmpname, self.mode)
+ tarinfo = tar.gettarinfo(link)
+ self.assertEqual(tarinfo.size, 0)
+ finally:
+ os.remove(target)
+ os.remove(link)
+
+ def test_symlink_size(self):
if hasattr(os, "symlink"):
- path = os.path.join(self.tmpdir, "symlink")
+ path = os.path.join(TEMPDIR, "symlink")
os.symlink("link_target", path)
- tarinfo = self.dst.gettarinfo(path)
- self.assertEqual(tarinfo.size, 0)
+ try:
+ tar = tarfile.open(tmpname, self.mode)
+ tarinfo = tar.gettarinfo(path)
+ self.assertEqual(tarinfo.size, 0)
+ finally:
+ os.remove(path)
+ def test_add_self(self):
+ # Test for #1257255.
+ dstname = os.path.abspath(tmpname)
-class WriteStreamTest(WriteTest):
- sep = '|'
+ tar = tarfile.open(tmpname, self.mode)
+ self.assert_(tar.name == dstname, "archive name must be absolute")
- def test_padding(self):
- self.dst.close()
+ tar.add(dstname)
+ self.assert_(tar.getnames() == [], "added the archive to itself")
- if self.comp == "gz":
- f = gzip.GzipFile(self.dstname)
- s = f.read()
- f.close()
- elif self.comp == "bz2":
- f = bz2.BZ2Decompressor()
- s = open(self.dstname).read()
- s = f.decompress(s)
- self.assertEqual(len(f.unused_data), 0, "trailing data")
- else:
- f = open(self.dstname)
- s = f.read()
- f.close()
+ cwd = os.getcwd()
+ os.chdir(TEMPDIR)
+ tar.add(dstname)
+ os.chdir(cwd)
+ self.assert_(tar.getnames() == [], "added the archive to itself")
- self.assertEqual(s.count("\0"), tarfile.RECORDSIZE,
- "incorrect zero padding")
+class StreamWriteTest(unittest.TestCase):
-class WriteGNULongTest(unittest.TestCase):
- """This testcase checks for correct creation of GNU Longname
- and Longlink extensions.
+ mode = "w|"
- It creates a tarfile and adds empty members with either
- long names, long linknames or both and compares the size
- of the tarfile with the expected size.
+ def test_stream_padding(self):
+ # Test for bug #1543303.
+ tar = tarfile.open(tmpname, self.mode)
+ tar.close()
- It checks for SF bug #812325 in TarFile._create_gnulong().
+ if self.mode.endswith("gz"):
+ fobj = gzip.GzipFile(tmpname)
+ data = fobj.read()
+ fobj.close()
+ elif self.mode.endswith("bz2"):
+ dec = bz2.BZ2Decompressor()
+ data = open(tmpname, "rb").read()
+ data = dec.decompress(data)
+ self.assert_(len(dec.unused_data) == 0,
+ "found trailing data")
+ else:
+ fobj = open(tmpname, "rb")
+ data = fobj.read()
+ fobj.close()
+
+ self.assert_(data.count("\0") == tarfile.RECORDSIZE,
+ "incorrect zero padding")
- While I was writing this testcase, I noticed a second bug
- in the same method:
- Long{names,links} weren't null-terminated which lead to
- bad tarfiles when their length was a multiple of 512. This
- is tested as well.
- """
+
+class GNUWriteTest(unittest.TestCase):
+ # This testcase checks for correct creation of GNU Longname
+ # and Longlink extended headers (cp. bug #812325).
def _length(self, s):
blocks, remainder = divmod(len(s) + 1, 512)
@@ -474,19 +573,17 @@ class WriteGNULongTest(unittest.TestCase):
return blocks * 512
def _calc_size(self, name, link=None):
- # initial tar header
+ # Initial tar header
count = 512
if len(name) > tarfile.LENGTH_NAME:
- # gnu longname extended header + longname
+ # GNU longname extended header + longname
count += 512
count += self._length(name)
-
if link is not None and len(link) > tarfile.LENGTH_LINK:
- # gnu longlink extended header + longlink
+ # GNU longlink extended header + longlink
count += 512
count += self._length(link)
-
return count
def _test(self, name, link=None):
@@ -495,17 +592,17 @@ class WriteGNULongTest(unittest.TestCase):
tarinfo.linkname = link
tarinfo.type = tarfile.LNKTYPE
- tar = tarfile.open(tmpname(), "w")
- tar.posix = False
+ tar = tarfile.open(tmpname, "w")
+ tar.format = tarfile.GNU_FORMAT
tar.addfile(tarinfo)
v1 = self._calc_size(name, link)
v2 = tar.offset
- self.assertEqual(v1, v2, "GNU longname/longlink creation failed")
+ self.assert_(v1 == v2, "GNU longname/longlink creation failed")
tar.close()
- tar = tarfile.open(tmpname())
+ tar = tarfile.open(tmpname)
member = tar.next()
self.failIf(member is None, "unable to read longname member")
self.assert_(tarinfo.name == member.name and \
@@ -542,268 +639,351 @@ class WriteGNULongTest(unittest.TestCase):
self._test(("longnam/" * 127) + "longname_",
("longlnk/" * 127) + "longlink_")
-class ReadGNULongTest(unittest.TestCase):
+
+class HardlinkTest(unittest.TestCase):
+ # Test the creation of LNKTYPE (hardlink) members in an archive.
def setUp(self):
- self.tar = tarfile.open(tarname())
+ self.foo = os.path.join(TEMPDIR, "foo")
+ self.bar = os.path.join(TEMPDIR, "bar")
+
+ fobj = open(self.foo, "wb")
+ fobj.write("foo")
+ fobj.close()
+
+ os.link(self.foo, self.bar)
+
+ self.tar = tarfile.open(tmpname, "w")
+ self.tar.add(self.foo)
def tearDown(self):
- self.tar.close()
+ os.remove(self.foo)
+ os.remove(self.bar)
- def test_1471427(self):
- """Test reading of longname (bug #1471427).
- """
- name = "test/" * 20 + "0-REGTYPE"
- try:
- tarinfo = self.tar.getmember(name)
- except KeyError:
- tarinfo = None
- self.assert_(tarinfo is not None, "longname not found")
- self.assert_(tarinfo.type != tarfile.DIRTYPE, "read longname as dirtype")
+ def test_add_twice(self):
+ # The same name will be added as a REGTYPE every
+ # time regardless of st_nlink.
+ tarinfo = self.tar.gettarinfo(self.foo)
+ self.assert_(tarinfo.type == tarfile.REGTYPE,
+ "add file as regular failed")
- def test_read_name(self):
- name = ("0-LONGNAME-" * 10)[:101]
- try:
- tarinfo = self.tar.getmember(name)
- except KeyError:
- tarinfo = None
- self.assert_(tarinfo is not None, "longname not found")
+ def test_add_hardlink(self):
+ tarinfo = self.tar.gettarinfo(self.bar)
+ self.assert_(tarinfo.type == tarfile.LNKTYPE,
+ "add file as hardlink failed")
- def test_read_link(self):
- link = ("1-LONGLINK-" * 10)[:101]
- name = ("0-LONGNAME-" * 10)[:101]
- try:
- tarinfo = self.tar.getmember(link)
- except KeyError:
- tarinfo = None
- self.assert_(tarinfo is not None, "longlink not found")
- self.assert_(tarinfo.linkname == name, "linkname wrong")
+ def test_dereference_hardlink(self):
+ self.tar.dereference = True
+ tarinfo = self.tar.gettarinfo(self.bar)
+ self.assert_(tarinfo.type == tarfile.REGTYPE,
+ "dereferencing hardlink failed")
- def test_truncated_longname(self):
- f = open(tarname())
- fobj = StringIO.StringIO(f.read(1024))
- f.close()
- tar = tarfile.open(name="foo.tar", fileobj=fobj)
- self.assert_(len(tar.getmembers()) == 0, "")
+
+class PaxWriteTest(GNUWriteTest):
+
+ def _test(self, name, link=None):
+ # See GNUWriteTest.
+ tarinfo = tarfile.TarInfo(name)
+ if link:
+ tarinfo.linkname = link
+ tarinfo.type = tarfile.LNKTYPE
+
+ tar = tarfile.open(tmpname, "w", format=tarfile.PAX_FORMAT)
+ tar.addfile(tarinfo)
tar.close()
+ tar = tarfile.open(tmpname)
+ if link:
+ l = tar.getmembers()[0].linkname
+ self.assert_(link == l, "PAX longlink creation failed")
+ else:
+ n = tar.getmembers()[0].name
+ self.assert_(name == n, "PAX longname creation failed")
-class ExtractHardlinkTest(BaseTest):
+ def test_iso8859_15_filename(self):
+ self._test_unicode_filename("iso8859-15")
- def test_hardlink(self):
- """Test hardlink extraction (bug #857297)
- """
- # Prevent errors from being caught
- self.tar.errorlevel = 1
+ def test_utf8_filename(self):
+ self._test_unicode_filename("utf8")
- self.tar.extract("0-REGTYPE", dirname())
- try:
- # Extract 1-LNKTYPE which is a hardlink to 0-REGTYPE
- self.tar.extract("1-LNKTYPE", dirname())
- except EnvironmentError as e:
- import errno
- if e.errno == errno.ENOENT:
- self.fail("hardlink not extracted properly")
+ def test_utf16_filename(self):
+ self._test_unicode_filename("utf16")
-class CreateHardlinkTest(BaseTest):
- """Test the creation of LNKTYPE (hardlink) members in an archive.
- In this respect tarfile.py mimics the behaviour of GNU tar: If
- a file has a st_nlink > 1, it will be added a REGTYPE member
- only the first time.
- """
+ def _test_unicode_filename(self, encoding):
+ tar = tarfile.open(tmpname, "w", format=tarfile.PAX_FORMAT)
+ name = u"\u20ac".encode(encoding) # Euro sign
+ tar.encoding = encoding
+ tar.addfile(tarfile.TarInfo(name))
+ tar.close()
- def setUp(self):
- self.tar = tarfile.open(tmpname(), "w")
+ tar = tarfile.open(tmpname, encoding=encoding)
+ self.assertEqual(tar.getmembers()[0].name, name)
+ tar.close()
- self.foo = os.path.join(dirname(), "foo")
- self.bar = os.path.join(dirname(), "bar")
+ def test_unicode_filename_error(self):
+ # The euro sign filename cannot be translated to iso8859-1 encoding.
+ tar = tarfile.open(tmpname, "w", format=tarfile.PAX_FORMAT, encoding="utf8")
+ name = u"\u20ac".encode("utf8") # Euro sign
+ tar.addfile(tarfile.TarInfo(name))
+ tar.close()
- if os.path.exists(self.foo):
- os.remove(self.foo)
- if os.path.exists(self.bar):
- os.remove(self.bar)
+ self.assertRaises(UnicodeError, tarfile.open, tmpname, encoding="iso8859-1")
- f = open(self.foo, "w")
- f.write("foo")
- f.close()
- self.tar.add(self.foo)
+ def test_pax_headers(self):
+ self._test_pax_headers({"foo": "bar", "uid": 0, "mtime": 1.23})
- def test_add_twice(self):
- # If st_nlink == 1 then the same file will be added as
- # REGTYPE every time.
- tarinfo = self.tar.gettarinfo(self.foo)
- self.assertEqual(tarinfo.type, tarfile.REGTYPE,
- "add file as regular failed")
+ self._test_pax_headers({"euro": u"\u20ac".encode("utf8")})
- def test_add_hardlink(self):
- # If st_nlink > 1 then the same file will be added as
- # LNKTYPE.
- os.link(self.foo, self.bar)
- tarinfo = self.tar.gettarinfo(self.foo)
- self.assertEqual(tarinfo.type, tarfile.LNKTYPE,
- "add file as hardlink failed")
+ self._test_pax_headers({"euro": u"\u20ac"},
+ {"euro": u"\u20ac".encode("utf8")})
- tarinfo = self.tar.gettarinfo(self.bar)
- self.assertEqual(tarinfo.type, tarfile.LNKTYPE,
- "add file as hardlink failed")
+ self._test_pax_headers({u"\u20ac": "euro"},
+ {u"\u20ac".encode("utf8"): "euro"})
- def test_dereference_hardlink(self):
- self.tar.dereference = True
- os.link(self.foo, self.bar)
- tarinfo = self.tar.gettarinfo(self.bar)
- self.assertEqual(tarinfo.type, tarfile.REGTYPE,
- "dereferencing hardlink failed")
+ def _test_pax_headers(self, pax_headers, cmp_headers=None):
+ if cmp_headers is None:
+ cmp_headers = pax_headers
+ tar = tarfile.open(tmpname, "w", format=tarfile.PAX_FORMAT, \
+ pax_headers=pax_headers, encoding="utf8")
+ tar.addfile(tarfile.TarInfo("test"))
+ tar.close()
-# Gzip TestCases
-class ReadTestGzip(ReadTest):
- comp = "gz"
-class ReadStreamTestGzip(ReadStreamTest):
- comp = "gz"
-class WriteTestGzip(WriteTest):
- comp = "gz"
-class WriteStreamTestGzip(WriteStreamTest):
- comp = "gz"
-class ReadDetectTestGzip(ReadDetectTest):
- comp = "gz"
-class ReadDetectFileobjTestGzip(ReadDetectFileobjTest):
- comp = "gz"
-class ReadAsteriskTestGzip(ReadAsteriskTest):
- comp = "gz"
-class ReadStreamAsteriskTestGzip(ReadStreamAsteriskTest):
- comp = "gz"
-
-# Filemode test cases
-
-class FileModeTest(unittest.TestCase):
- def test_modes(self):
- self.assertEqual(tarfile.filemode(0755), '-rwxr-xr-x')
- self.assertEqual(tarfile.filemode(07111), '---s--s--t')
-
-class HeaderErrorTest(unittest.TestCase):
+ tar = tarfile.open(tmpname, encoding="utf8")
+ self.assertEqual(tar.pax_headers, cmp_headers)
def test_truncated_header(self):
- self.assertRaises(tarfile.HeaderError, tarfile.TarInfo.frombuf, "")
- self.assertRaises(tarfile.HeaderError, tarfile.TarInfo.frombuf, "filename\0")
- self.assertRaises(tarfile.HeaderError, tarfile.TarInfo.frombuf, "\0" * 511)
- self.assertRaises(tarfile.HeaderError, tarfile.TarInfo.frombuf, "\0" * 513)
-
- def test_empty_header(self):
- self.assertRaises(tarfile.HeaderError, tarfile.TarInfo.frombuf, "\0" * 512)
-
- def test_invalid_header(self):
- buf = tarfile.TarInfo("filename").tobuf()
- buf = buf[:148] + "foo\0\0\0\0\0" + buf[156:] # invalid number field.
- self.assertRaises(tarfile.HeaderError, tarfile.TarInfo.frombuf, buf)
-
- def test_bad_checksum(self):
- buf = tarfile.TarInfo("filename").tobuf()
- b = buf[:148] + " " + buf[156:] # clear the checksum field.
- self.assertRaises(tarfile.HeaderError, tarfile.TarInfo.frombuf, b)
- b = "a" + buf[1:] # manipulate the buffer, so checksum won't match.
- self.assertRaises(tarfile.HeaderError, tarfile.TarInfo.frombuf, b)
-
-class OpenFileobjTest(BaseTest):
- # Test for SF bug #1496501.
-
- def test_opener(self):
- fobj = StringIO.StringIO("foo\n")
- try:
- tarfile.open("", "r", fileobj=fobj)
- except tarfile.ReadError:
- self.assertEqual(fobj.tell(), 0, "fileobj's position has moved")
-
-if bz2:
- # Bzip2 TestCases
- class ReadTestBzip2(ReadTestGzip):
- comp = "bz2"
- class ReadStreamTestBzip2(ReadStreamTestGzip):
- comp = "bz2"
- class WriteTestBzip2(WriteTest):
- comp = "bz2"
- class WriteStreamTestBzip2(WriteStreamTestGzip):
- comp = "bz2"
- class ReadDetectTestBzip2(ReadDetectTest):
- comp = "bz2"
- class ReadDetectFileobjTestBzip2(ReadDetectFileobjTest):
- comp = "bz2"
- class ReadAsteriskTestBzip2(ReadAsteriskTest):
- comp = "bz2"
- class ReadStreamAsteriskTestBzip2(ReadStreamAsteriskTest):
- comp = "bz2"
-
-# If importing gzip failed, discard the Gzip TestCases.
-if not gzip:
- del ReadTestGzip
- del ReadStreamTestGzip
- del WriteTestGzip
- del WriteStreamTestGzip
+ tar = tarfile.open(tmpname, "w", format=tarfile.PAX_FORMAT)
+ tarinfo = tarfile.TarInfo("123/" * 126 + "longname")
+ tar.addfile(tarinfo)
+ tar.close()
-def test_main():
- # Create archive.
- f = open(tarname(), "rb")
- fguts = f.read()
- f.close()
- if gzip:
- # create testtar.tar.gz
- tar = gzip.open(tarname("gz"), "wb")
- tar.write(fguts)
+ # Simulate a premature EOF.
+ open(tmpname, "rb+").truncate(1536)
+ tar = tarfile.open(tmpname)
+ self.assertEqual(tar.getmembers(), [])
+
+
+class AppendTest(unittest.TestCase):
+ # Test append mode (cp. patch #1652681).
+
+ def setUp(self):
+ self.tarname = tmpname
+ if os.path.exists(self.tarname):
+ os.remove(self.tarname)
+
+ def _add_testfile(self, fileobj=None):
+ tar = tarfile.open(self.tarname, "a", fileobj=fileobj)
+ tar.addfile(tarfile.TarInfo("bar"))
tar.close()
- if bz2:
- # create testtar.tar.bz2
- tar = bz2.BZ2File(tarname("bz2"), "wb")
- tar.write(fguts)
+
+ def _create_testtar(self, mode="w:"):
+ src = tarfile.open(tarname, encoding="iso8859-1")
+ t = src.getmember("ustar/regtype")
+ t.name = "foo"
+ f = src.extractfile(t)
+ tar = tarfile.open(self.tarname, mode)
+ tar.addfile(t, f)
tar.close()
+ def _test(self, names=["bar"], fileobj=None):
+ tar = tarfile.open(self.tarname, fileobj=fileobj)
+ self.assertEqual(tar.getnames(), names)
+
+ def test_non_existing(self):
+ self._add_testfile()
+ self._test()
+
+ def test_empty(self):
+ open(self.tarname, "w").close()
+ self._add_testfile()
+ self._test()
+
+ def test_empty_fileobj(self):
+ fobj = StringIO.StringIO()
+ self._add_testfile(fobj)
+ fobj.seek(0)
+ self._test(fileobj=fobj)
+
+ def test_fileobj(self):
+ self._create_testtar()
+ data = open(self.tarname).read()
+ fobj = StringIO.StringIO(data)
+ self._add_testfile(fobj)
+ fobj.seek(0)
+ self._test(names=["foo", "bar"], fileobj=fobj)
+
+ def test_existing(self):
+ self._create_testtar()
+ self._add_testfile()
+ self._test(names=["foo", "bar"])
+
+ def test_append_gz(self):
+ if gzip is None:
+ return
+ self._create_testtar("w:gz")
+ self.assertRaises(tarfile.ReadError, tarfile.open, tmpname, "a")
+
+ def test_append_bz2(self):
+ if bz2 is None:
+ return
+ self._create_testtar("w:bz2")
+ self.assertRaises(tarfile.ReadError, tarfile.open, tmpname, "a")
+
+
+class LimitsTest(unittest.TestCase):
+
+ def test_ustar_limits(self):
+ # 100 char name
+ tarinfo = tarfile.TarInfo("0123456789" * 10)
+ tarinfo.create_ustar_header()
+
+ # 101 char name that cannot be stored
+ tarinfo = tarfile.TarInfo("0123456789" * 10 + "0")
+ self.assertRaises(ValueError, tarinfo.create_ustar_header)
+
+ # 256 char name with a slash at pos 156
+ tarinfo = tarfile.TarInfo("123/" * 62 + "longname")
+ tarinfo.create_ustar_header()
+
+ # 256 char name that cannot be stored
+ tarinfo = tarfile.TarInfo("1234567/" * 31 + "longname")
+ self.assertRaises(ValueError, tarinfo.create_ustar_header)
+
+ # 512 char name
+ tarinfo = tarfile.TarInfo("123/" * 126 + "longname")
+ self.assertRaises(ValueError, tarinfo.create_ustar_header)
+
+ # 512 char linkname
+ tarinfo = tarfile.TarInfo("longlink")
+ tarinfo.linkname = "123/" * 126 + "longname"
+ self.assertRaises(ValueError, tarinfo.create_ustar_header)
+
+ # uid > 8 digits
+ tarinfo = tarfile.TarInfo("name")
+ tarinfo.uid = 010000000
+ self.assertRaises(ValueError, tarinfo.create_ustar_header)
+
+ def test_gnu_limits(self):
+ tarinfo = tarfile.TarInfo("123/" * 126 + "longname")
+ tarinfo.create_gnu_header()
+
+ tarinfo = tarfile.TarInfo("longlink")
+ tarinfo.linkname = "123/" * 126 + "longname"
+ tarinfo.create_gnu_header()
+
+ # uid >= 256 ** 7
+ tarinfo = tarfile.TarInfo("name")
+ tarinfo.uid = 04000000000000000000
+ self.assertRaises(ValueError, tarinfo.create_gnu_header)
+
+ def test_pax_limits(self):
+ # A 256 char name that can be stored without an extended header.
+ tarinfo = tarfile.TarInfo("123/" * 62 + "longname")
+ self.assert_(len(tarinfo.create_pax_header("utf8")) == 512,
+ "create_pax_header attached superfluous extended header")
+
+ tarinfo = tarfile.TarInfo("123/" * 126 + "longname")
+ tarinfo.create_pax_header("utf8")
+
+ tarinfo = tarfile.TarInfo("longlink")
+ tarinfo.linkname = "123/" * 126 + "longname"
+ tarinfo.create_pax_header("utf8")
+
+ tarinfo = tarfile.TarInfo("name")
+ tarinfo.uid = 04000000000000000000
+ tarinfo.create_pax_header("utf8")
+
+
+class GzipMiscReadTest(MiscReadTest):
+ tarname = gzipname
+ mode = "r:gz"
+class GzipUstarReadTest(UstarReadTest):
+ tarname = gzipname
+ mode = "r:gz"
+class GzipStreamReadTest(StreamReadTest):
+ tarname = gzipname
+ mode = "r|gz"
+class GzipWriteTest(WriteTest):
+ mode = "w:gz"
+class GzipStreamWriteTest(StreamWriteTest):
+ mode = "w|gz"
+
+
+class Bz2MiscReadTest(MiscReadTest):
+ tarname = bz2name
+ mode = "r:bz2"
+class Bz2UstarReadTest(UstarReadTest):
+ tarname = bz2name
+ mode = "r:bz2"
+class Bz2StreamReadTest(StreamReadTest):
+ tarname = bz2name
+ mode = "r|bz2"
+class Bz2WriteTest(WriteTest):
+ mode = "w:bz2"
+class Bz2StreamWriteTest(StreamWriteTest):
+ mode = "w|bz2"
+
+def test_main():
+ if not os.path.exists(TEMPDIR):
+ os.mkdir(TEMPDIR)
+
tests = [
- FileModeTest,
- HeaderErrorTest,
- OpenFileobjTest,
- ReadTest,
- ReadStreamTest,
- ReadDetectTest,
- ReadDetectFileobjTest,
- ReadAsteriskTest,
- ReadStreamAsteriskTest,
+ UstarReadTest,
+ MiscReadTest,
+ StreamReadTest,
+ DetectReadTest,
+ MemberReadTest,
+ GNUReadTest,
+ PaxReadTest,
WriteTest,
+ StreamWriteTest,
+ GNUWriteTest,
+ PaxWriteTest,
AppendTest,
- Write100Test,
- WriteSize0Test,
- WriteStreamTest,
- WriteGNULongTest,
- ReadGNULongTest,
+ LimitsTest,
]
if hasattr(os, "link"):
- tests.append(ExtractHardlinkTest)
- tests.append(CreateHardlinkTest)
+ tests.append(HardlinkTest)
+
+ fobj = open(tarname, "rb")
+ data = fobj.read()
+ fobj.close()
if gzip:
- tests.extend([
- ReadTestGzip, ReadStreamTestGzip,
- WriteTestGzip, WriteStreamTestGzip,
- ReadDetectTestGzip, ReadDetectFileobjTestGzip,
- ReadAsteriskTestGzip, ReadStreamAsteriskTestGzip
- ])
+ # Create testtar.tar.gz and add gzip-specific tests.
+ tar = gzip.open(gzipname, "wb")
+ tar.write(data)
+ tar.close()
+
+ tests += [
+ GzipMiscReadTest,
+ GzipUstarReadTest,
+ GzipStreamReadTest,
+ GzipWriteTest,
+ GzipStreamWriteTest,
+ ]
if bz2:
- tests.extend([
- ReadTestBzip2, ReadStreamTestBzip2,
- WriteTestBzip2, WriteStreamTestBzip2,
- ReadDetectTestBzip2, ReadDetectFileobjTestBzip2,
- ReadAsteriskTestBzip2, ReadStreamAsteriskTestBzip2
- ])
+ # Create testtar.tar.bz2 and add bz2-specific tests.
+ tar = bz2.BZ2File(bz2name, "wb")
+ tar.write(data)
+ tar.close()
+
+ tests += [
+ Bz2MiscReadTest,
+ Bz2UstarReadTest,
+ Bz2StreamReadTest,
+ Bz2WriteTest,
+ Bz2StreamWriteTest,
+ ]
+
try:
test_support.run_unittest(*tests)
finally:
- if gzip:
- os.remove(tarname("gz"))
- if bz2:
- os.remove(tarname("bz2"))
- if os.path.exists(dirname()):
- shutil.rmtree(dirname())
- if os.path.exists(tmpname()):
- os.remove(tmpname())
+ if os.path.exists(TEMPDIR):
+ shutil.rmtree(TEMPDIR)
if __name__ == "__main__":
test_main()