[Python-checkins] cpython (3.2): Fix GzipFile's handling of filenames given as bytes objects.

nadeem.vawda python-checkins at python.org
Wed Jun 20 01:51:45 CEST 2012


http://hg.python.org/cpython/rev/e044fa016c85
changeset:   77520:e044fa016c85
branch:      3.2
parent:      77507:e1cd1f430ff1
user:        Nadeem Vawda <nadeem.vawda at gmail.com>
date:        Wed Jun 20 01:35:22 2012 +0200
summary:
  Fix GzipFile's handling of filenames given as bytes objects.

files:
  Lib/gzip.py           |   8 ++++----
  Lib/test/test_gzip.py |  14 ++++++++++++++
  Misc/NEWS             |   2 ++
  3 files changed, 20 insertions(+), 4 deletions(-)


diff --git a/Lib/gzip.py b/Lib/gzip.py
--- a/Lib/gzip.py
+++ b/Lib/gzip.py
@@ -159,9 +159,8 @@
         if fileobj is None:
             fileobj = self.myfileobj = builtins.open(filename, mode or 'rb')
         if filename is None:
-            if hasattr(fileobj, 'name') and isinstance(fileobj.name, str):
-                filename = fileobj.name
-            else:
+            filename = getattr(fileobj, 'name', '')
+            if not isinstance(filename, (str, bytes)):
                 filename = ''
         if mode is None:
             if hasattr(fileobj, 'mode'): mode = fileobj.mode
@@ -236,7 +235,8 @@
             # RFC 1952 requires the FNAME field to be Latin-1. Do not
             # include filenames that cannot be represented that way.
             fname = os.path.basename(self.name)
-            fname = fname.encode('latin-1')
+            if not isinstance(fname, bytes):
+                fname = fname.encode('latin-1')
             if fname.endswith(b'.gz'):
                 fname = fname[:-3]
         except UnicodeEncodeError:
diff --git a/Lib/test/test_gzip.py b/Lib/test/test_gzip.py
--- a/Lib/test/test_gzip.py
+++ b/Lib/test/test_gzip.py
@@ -331,6 +331,20 @@
             with gzip.GzipFile(fileobj=f, mode="w") as g:
                 pass
 
+    def test_bytes_filename(self):
+        str_filename = self.filename
+        try:
+            bytes_filename = str_filename.encode("ascii")
+        except UnicodeEncodeError:
+            self.skipTest("Temporary file name needs to be ASCII")
+        with gzip.GzipFile(bytes_filename, "wb") as f:
+            f.write(data1 * 50)
+        with gzip.GzipFile(bytes_filename, "rb") as f:
+            self.assertEqual(f.read(), data1 * 50)
+        # Sanity check that we are actually operating on the right file.
+        with gzip.GzipFile(str_filename, "rb") as f:
+            self.assertEqual(f.read(), data1 * 50)
+
     # Testing compress/decompress shortcut functions
 
     def test_compress(self):
diff --git a/Misc/NEWS b/Misc/NEWS
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -70,6 +70,8 @@
 Library
 -------
 
+- Fix GzipFile's handling of filenames given as bytes objects.
+
 - Issue #15101: Make pool finalizer avoid joining current thread.
 
 - Issue #15036: Mailbox no longer throws an error if a flush is done

-- 
Repository URL: http://hg.python.org/cpython


More information about the Python-checkins mailing list