Fix closes issue #12088 - fixes the tarfile.extractall issue when the

symlinks/hardlink was broken. It handles now in a graceful manner (No exception
is raised, behavior similar GNU tar).

2 files changed, 63 insertions, 1 deletions

diff --git a/Lib/tarfile.py b/Lib/tarfile.py
index 105a75880d..6b9303e898 100644
--- a/Lib/tarfile.py
+++ b/Lib/tarfile.py
@@ -2239,12 +2239,14 @@ class TarFile(object):
         if hasattr(os, "symlink") and hasattr(os, "link"):
             # For systems that support symbolic and hard links.
             if tarinfo.issym():
-                if os.path.exists(targetpath):
+                if os.path.lexists(targetpath):
                     os.unlink(targetpath)
                 os.symlink(tarinfo.linkname, targetpath)
             else:
                 # See extract().
                 if os.path.exists(tarinfo._link_target):
+                    if os.path.lexists(targetpath):
+                        os.unlink(targetpath)
                     os.link(tarinfo._link_target, targetpath)
                 else:
                     self._extract_member(self._find_link_target(tarinfo), targetpath)
diff --git a/Lib/test/test_tarfile.py b/Lib/test/test_tarfile.py
index f78f9ce03f..6962f8e2d7 100644
--- a/Lib/test/test_tarfile.py
+++ b/Lib/test/test_tarfile.py
@@ -872,6 +872,66 @@ class WriteTest(WriteTestBase):
             os.unlink(temparchive)
             shutil.rmtree(tempdir)
 
+    @unittest.skipUnless(hasattr(os, 'symlink'), "needs os.symlink")
+    def test_extractall_broken_symlinks(self):
+        # Test if extractall works properly when tarfile contains broken
+        # symlinks
+        tempdir = os.path.join(TEMPDIR, "testsymlinks")
+        temparchive = os.path.join(TEMPDIR, "testsymlinks.tar")
+        os.mkdir(tempdir)
+        try:
+            source_file = os.path.join(tempdir,'source')
+            target_file = os.path.join(tempdir,'symlink')
+            with open(source_file,'w') as f:
+                f.write('something\n')
+            os.symlink(source_file, target_file)
+            tar = tarfile.open(temparchive,'w')
+            tar.add(target_file, arcname=os.path.basename(target_file))
+            tar.close()
+            # remove the real file
+            os.unlink(source_file)
+            # Let's extract it to the location which contains the symlink
+            tar = tarfile.open(temparchive,'r')
+            # this should not raise OSError: [Errno 17] File exists
+            try:
+                tar.extractall(path=tempdir)
+            except OSError:
+                self.fail("extractall failed with broken symlinked files")
+            finally:
+                tar.close()
+        finally:
+            os.unlink(temparchive)
+            shutil.rmtree(tempdir)
+
+    @unittest.skipUnless(hasattr(os, 'link'), "needs os.link")
+    def test_extractall_hardlinks(self):
+        # Test if extractall works properly when tarfile contains symlinks
+        tempdir = os.path.join(TEMPDIR, "testsymlinks")
+        temparchive = os.path.join(TEMPDIR, "testsymlinks.tar")
+        os.mkdir(tempdir)
+        try:
+            source_file = os.path.join(tempdir,'source')
+            target_file = os.path.join(tempdir,'symlink')
+            with open(source_file,'w') as f:
+                f.write('something\n')
+            os.link(source_file, target_file)
+            tar = tarfile.open(temparchive,'w')
+            tar.add(source_file, arcname=os.path.basename(source_file))
+            tar.add(target_file, arcname=os.path.basename(target_file))
+            tar.close()
+            # Let's extract it to the location which contains the symlink
+            tar = tarfile.open(temparchive,'r')
+            # this should not raise OSError: [Errno 17] File exists
+            try:
+                tar.extractall(path=tempdir)
+            except OSError:
+                self.fail("extractall failed with linked files")
+            finally:
+                tar.close()
+        finally:
+            os.unlink(temparchive)
+            shutil.rmtree(tempdir)
+
 class StreamWriteTest(WriteTestBase):
 
     mode = "w|"