# -*- coding: iso-8859-15 -*-

import sys

import os

import shutil

import tempfile

import StringIO

from hashlib import md5

import errno

import unittest

import tarfile

from test import test_support

# Check for our compression modules.

try:

    import gzip

    gzip.GzipFile

except (ImportError, AttributeError):

    gzip = None

try:

    import bz2

except ImportError:

    bz2 = None

def md5sum(data):

    return md5(data).hexdigest()

def path(path):

    return test_support.findfile(path)

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")

md5_regtype = "65f477c818ad9e15f7feab0c6d37742f"

md5_sparse = "a54fbc4ca4f4399a90e1b27164012fc6"

class ReadTest(unittest.TestCase):

    tarname = tarname

    mode = "r:"

    def setUp(self):

        self.tar = tarfile.open(self.tarname, mode=self.mode, encoding="iso8859-1")

    def tearDown(self):

        self.tar.close()

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_name_argument(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_no_name_attribute(self):

        data = open(self.tarname, "rb").read()

        fobj = StringIO.StringIO(data)

        self.assertRaises(AttributeError, getattr, fobj, "name")

        tar = tarfile.open(fileobj=fobj, mode=self.mode)

        self.assertEqual(tar.name, None)

    def test_empty_name_attribute(self):

        data = open(self.tarname, "rb").read()

        fobj = StringIO.StringIO(data)

        fobj.name = ""

        tar = tarfile.open(fileobj=fobj, mode=self.mode)

        self.assertEqual(tar.name, None)

    def test_fileobj_with_offset(self):

        # Skip the first member and store values from the second member

        # of the testtar.

        tar = tarfile.open(self.tarname, mode=self.mode)

        tar.next()

        t = tar.next()

        name = t.name

        offset = t.offset

        data = tar.extractfile(t).read()

        tar.close()

        # Open the testtar and seek to the offset of the second member.

        if self.mode.endswith(":gz"):

            _open = gzip.GzipFile

        elif self.mode.endswith(":bz2"):

            _open = bz2.BZ2File

        else:

            _open = open

        fobj = _open(self.tarname, "rb")

        fobj.seek(offset)

        # Test if the tarfile starts with the second member.

        tar = tar.open(self.tarname, mode="r:", fileobj=fobj)

        t = tar.next()

        self.assertEqual(t.name, name)

        # Read to the end of fileobj and test if seeking back to the

        # beginning works.

        tar.getmembers()

        self.assertEqual(tar.extractfile(t).read(), data,

                "seek back did not work")

        tar.close()

    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_xstar_type(self):

        # The xstar format stores extra atime and ctime fields inside the

        # space reserved for the prefix field. The prefix field must be

        # ignored in this case, otherwise it will mess up the name.

        try:

            self.tar.getmember("misc/regtype-xstar")

        except KeyError:

            self.fail("failed to find misc/regtype-xstar (mangled prefix?)")

    def test_check_members(self):

        for tarinfo in self.tar:

            self.assert_(int(tarinfo.mtime) == 07606136617,

                    "wrong mtime for %s" % tarinfo.name)

            if not tarinfo.name.startswith("ustar/"):

                continue

            self.assert_(tarinfo.uname == "tarfile",

                    "wrong uname for %s" % tarinfo.name)

    def test_find_members(self):

        self.assert_(self.tar.getmembers()[-1].name == "misc/eof",

                "could not find all members")

    def test_extract_hardlink(self):

        # Test hardlink extraction (e.g. bug #857297).

        tar = tarfile.open(tarname, errorlevel=1, encoding="iso8859-1")

        tar.extract("ustar/regtype", TEMPDIR)

        try:

            tar.extract("ustar/lnktype", TEMPDIR)

        except EnvironmentError, 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:

            tar.extract("ustar/symtype", TEMPDIR)

        except EnvironmentError, 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)

    def test_extractall(self):

        # Test if extractall() correctly restores directory permissions

        # and times (see issue1735).

        if sys.platform == "win32":

            # Win32 has no support for utime() on directories or

            # fine grained permissions.

            return

        tar = tarfile.open(tarname, encoding="iso8859-1")

        directories = [t for t in tar if t.isdir()]

        tar.extractall(TEMPDIR, directories)

        for tarinfo in directories:

            path = os.path.join(TEMPDIR, tarinfo.name)

            self.assertEqual(tarinfo.mode & 0777, os.stat(path).st_mode & 0777)

            self.assertEqual(tarinfo.mtime, os.path.getmtime(path))

        tar.close()

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_compare_members(self):

        tar1 = tarfile.open(tarname, encoding="iso8859-1")

        tar2 = self.tar

        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, tar2.extractfile, t2)

                continue

            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")

        tar1.close()

class DetectReadTest(unittest.TestCase):

    def _testfunc_file(self, name, mode):

        try:

            tarfile.open(name, mode)

        except tarfile.ReadError:

            self.fail()

    def _testfunc_fileobj(self, name, mode):

        try:

            tarfile.open(name, mode, fileobj=open(name, "rb"))

        except tarfile.ReadError:

            self.fail()

    def _test_modes(self, testfunc):

        testfunc(tarname, "r")

        testfunc(tarname, "r:")

        testfunc(tarname, "r:*")

        testfunc(tarname, "r|")

        testfunc(tarname, "r|*")

        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|")

            testfunc(gzipname, "r")

            testfunc(gzipname, "r:*")

            testfunc(gzipname, "r:gz")

            testfunc(gzipname, "r|*")

            testfunc(gzipname, "r|gz")

        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|")

            testfunc(bz2name, "r")

            testfunc(bz2name, "r:*")

            testfunc(bz2name, "r:bz2")

            testfunc(bz2name, "r|*")

            testfunc(bz2name, "r|bz2")

    def test_detect_file(self):

        self._test_modes(self._testfunc_file)

    def test_detect_fileobj(self):

        self._test_modes(self._testfunc_fileobj)

class MemberReadTest(ReadTest):

    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)

        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.iteritems():

            self.assert_(getattr(tarinfo, k) == v,

                    "wrong value in %s field of %s" % (k, tarinfo.name))

    def test_find_regtype(self):

        tarinfo = self.tar.getmember("ustar/regtype")

        self._test_member(tarinfo, size=7011, chksum=md5_regtype)

    def test_find_conttype(self):

        tarinfo = self.tar.getmember("ustar/conttype")

        self._test_member(tarinfo, size=7011, chksum=md5_regtype)

    def test_find_dirtype(self):

        tarinfo = self.tar.getmember("ustar/dirtype")

        self._test_member(tarinfo, size=0)

    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")

    def test_find_symtype(self):

        tarinfo = self.tar.getmember("ustar/symtype")

        self._test_member(tarinfo, size=0, linkname="regtype")

    def test_find_blktype(self):

        tarinfo = self.tar.getmember("ustar/blktype")

        self._test_member(tarinfo, size=0, devmajor=3, devminor=0)

    def test_find_chrtype(self):

        tarinfo = self.tar.getmember("ustar/chrtype")

        self._test_member(tarinfo, size=0, devmajor=1, devminor=3)

    def test_find_fifotype(self):

        tarinfo = self.tar.getmember("ustar/fifotype")

        self._test_member(tarinfo, size=0)

    def test_find_sparse(self):

        tarinfo = self.tar.getmember("ustar/sparse")

        self._test_member(tarinfo, size=86016, chksum=md5_sparse)

    def test_find_umlauts(self):

        tarinfo = self.tar.getmember("ustar/umlauts-ÄÖÜäöüß")

        self._test_member(tarinfo, size=7011, chksum=md5_regtype)

    def test_find_ustar_longname(self):

        name = "ustar/" + "12345/" * 39 + "1234567/longname"

        self.assert_(name in self.tar.getnames())

    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_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)

class LongnameTest(ReadTest):

    def test_read_longname(self):

        # Test reading of longname (bug #1471427).

        longname = self.subdir + "/" + "123/" * 125 + "longname"

        try:

            tarinfo = self.tar.getmember(longname)

        except KeyError:

            self.fail("longname not found")

        self.assert_(tarinfo.type != tarfile.DIRTYPE, "read longname as dirtype")

    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")

    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(3 * 512))

        self.assertRaises(tarfile.ReadError, tarfile.open, name="foo.tar", fileobj=fobj)

    def test_header_offset(self):

        # Test if the start offset of the TarInfo object includes

        # the preceding extended header.

        longname = self.subdir + "/" + "123/" * 125 + "longname"

        offset = self.tar.getmember(longname).offset

        fobj = open(tarname)

        fobj.seek(offset)

        tarinfo = tarfile.TarInfo.frombuf(fobj.read(512))

        self.assertEqual(tarinfo.type, self.longnametype)

class GNUReadTest(LongnameTest):

    subdir = "gnu"

    longnametype = tarfile.GNUTYPE_LONGNAME

    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 PaxReadTest(LongnameTest):

    subdir = "pax"

    longnametype = tarfile.XHDTYPE

    def test_pax_global_headers(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"), u"ÄÖÜäöüß")

        tarinfo = tar.getmember("pax/regtype2")

        self.assertEqual(tarinfo.uname, "")

        self.assertEqual(tarinfo.gname, "bar")

        self.assertEqual(tarinfo.pax_headers.get("VENDOR.umlauts"), u"ÄÖÜäöüß")

        tarinfo = tar.getmember("pax/regtype3")

        self.assertEqual(tarinfo.uname, "tarfile")

        self.assertEqual(tarinfo.gname, "tarfile")

        self.assertEqual(tarinfo.pax_headers.get("VENDOR.umlauts"), u"ÄÖÜäöüß")

    def test_pax_number_fields(self):

        # All following number fields are read from the pax header.

        tar = tarfile.open(tarname, encoding="iso8859-1")

        tarinfo = tar.getmember("pax/regtype4")

        self.assertEqual(tarinfo.size, 7011)

        self.assertEqual(tarinfo.uid, 123)

        self.assertEqual(tarinfo.gid, 123)

        self.assertEqual(tarinfo.mtime, 1041808783.0)

        self.assertEqual(type(tarinfo.mtime), float)

        self.assertEqual(float(tarinfo.pax_headers["atime"]), 1041808783.0)

        self.assertEqual(float(tarinfo.pax_headers["ctime"]), 1041808783.0)