Patch #1338314, Bug #1336623: fix tarfile so it can extract

REGTYPE directories from tarfiles written by old programs.

Will backport.

3 files changed, 39 insertions, 5 deletions

diff --git a/Lib/tarfile.py b/Lib/tarfile.py
index c86248c..0b3d477 100644
--- a/Lib/tarfile.py
+++ b/Lib/tarfile.py
@@ -739,6 +739,11 @@ class TarInfo(object):
             tarinfo.devmajor = tarinfo.devmajor = 0
         tarinfo.prefix = buf[345:500]
 
+        # Some old tar programs represent a directory as a regular
+        # file with a trailing slash.
+        if tarinfo.isreg() and tarinfo.name.endswith("/"):
+            tarinfo.type = DIRTYPE
+
         # The prefix field is used for filenames > 100 in
         # the POSIX standard.
         # name = prefix + '/' + name
@@ -746,7 +751,7 @@ class TarInfo(object):
             tarinfo.name = normpath(os.path.join(nts(tarinfo.prefix), tarinfo.name))
 
         # Directory names should have a '/' at the end.
-        if tarinfo.isdir() and tarinfo.name[-1:] != "/":
+        if tarinfo.isdir():
             tarinfo.name += "/"
         return tarinfo
 
@@ -1716,10 +1721,6 @@ class TarFile(object):
             # Skip the following data blocks.
             self.offset += self._block(tarinfo.size)
 
-        if tarinfo.isreg() and tarinfo.name[:-1] == "/":
-            # some old tar programs don't know DIRTYPE
-            tarinfo.type = DIRTYPE
-
         self.members.append(tarinfo)
         return tarinfo
 
diff --git a/Lib/test/test_tarfile.py b/Lib/test/test_tarfile.py
index b202ea5..98349c4 100644
--- a/Lib/test/test_tarfile.py
+++ b/Lib/test/test_tarfile.py
@@ -144,6 +144,36 @@ class ReadTest(BaseTest):
                          "readlines() after seek failed")
             fobj.close()
 
+    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.
+
+        # Create an old tar style directory entry.
+        filename = tmpname()
+        tarinfo = tarfile.TarInfo("directory/")
+        tarinfo.type = tarfile.REGTYPE
+
+        fobj = file(filename, "w")
+        fobj.write(tarinfo.tobuf())
+        fobj.close()
+
+        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 = "|"
 
diff --git a/Misc/NEWS b/Misc/NEWS
index 8ee1e35..e88311f 100644
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -177,6 +177,9 @@ Core and builtins
 Extension Modules
 -----------------
 
+- Patch #1338314, Bug #1336623: fix tarfile so it can extract
+  REGTYPE directories from tarfiles written by old programs.
+
 - Get bsddb module to build with BSD DB version 3.2
 
 - Patch #1309009, Fix segfault in pyexpat when the XML document is in latin_1,