Correctly detect bzip2 compressed streams with blocksizes other than 900k.
diff --git a/Lib/tarfile.py b/Lib/tarfile.py
index 6828eab..ed5bcf2 100644
--- a/Lib/tarfile.py
+++ b/Lib/tarfile.py
@@ -627,7 +627,7 @@
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"
diff --git a/Lib/test/test_tarfile.py b/Lib/test/test_tarfile.py
index 6962f8e..49d2d07 100644
--- a/Lib/test/test_tarfile.py
+++ b/Lib/test/test_tarfile.py
@@ -440,6 +440,23 @@
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):