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

Lib/tarfile.py

@@ -627,7 +627,7 @@ class _StreamProxy(object):
     def getcomptype(self):
         if self.buf.startswith("\037\213\010"):
             return "gz"
-        if self.buf.startswith("BZh91"):
+        if self.buf[0:3] == "BZh" and self.buf[4:10] == "1AY&SY":
             return "bz2"
         return "tar"
 

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):
 

Misc/NEWS

@@ -79,6 +79,9 @@ Core and Builtins
 Library
 -------
 
+- tarfile.py: Correctly detect bzip2 compressed streams with blocksizes
+  other than 900k.
+
 - Issue #13439: Fix many errors in turtle docstrings.
 
 - Issue #12856: Ensure child processes do not inherit the parent's random