Correctly detect bzip2 compressed streams with blocksizes other than 900k.

1 files changed, 17 insertions, 0 deletions

diff --git a/Lib/test/test_tarfile.py b/Lib/test/test_tarfile.py
index 6962f8e2d7..49d2d07d90 100644
--- a/Lib/test/test_tarfile.py
+++ b/Lib/test/test_tarfile.py
@@ -440,6 +440,23 @@ class DetectReadTest(unittest.TestCase):
     def test_detect_fileobj(self):
         self._test_modes(self._testfunc_fileobj)
 
+    def test_detect_stream_bz2(self):
+        # Originally, tarfile's stream detection looked for the string
+        # "BZh91" at the start of the file. This is incorrect because
+        # the '9' represents the blocksize (900kB). If the file was
+        # compressed using another blocksize autodetection fails.
+        if not bz2:
+            return
+
+        with open(tarname, "rb") as fobj:
+            data = fobj.read()
+
+        # Compress with blocksize 100kB, the file starts with "BZh11".
+        with bz2.BZ2File(tmpname, "wb", compresslevel=1) as fobj:
+            fobj.write(data)
+
+        self._testfunc_file(tmpname, "r|*")
+
 
 class MemberReadTest(ReadTest):