closes bpo-34056: Always return bytes from _HackedGetData.get_data(). (GH-8130)

* Always return bytes from _HackedGetData.get_data().

Ensure the imp.load_source shim always returns bytes by reopening the file in
binary mode if needed. Hash-based pycs have to receive the source code in bytes.

It's tempting to change imp.get_suffixes() to always return 'rb' as a mode, but
that breaks some stdlib tests and likely 3rdparty code, too.

1 files changed, 6 insertions, 7 deletions

diff --git a/Lib/imp.py b/Lib/imp.py
index 866464b..31f8c76 100644
--- a/Lib/imp.py
+++ b/Lib/imp.py
@@ -142,17 +142,16 @@ class _HackedGetData:
     def get_data(self, path):
         """Gross hack to contort loader to deal w/ load_*()'s bad API."""
         if self.file and path == self.path:
+            # The contract of get_data() requires us to return bytes. Reopen the
+            # file in binary mode if needed.
             if not self.file.closed:
                 file = self.file
-            else:
-                self.file = file = open(self.path, 'r')
+                if 'b' not in file.mode:
+                    file.close()
+            if self.file.closed:
+                self.file = file = open(self.path, 'rb')
 
             with file:
-                # Technically should be returning bytes, but
-                # SourceLoader.get_code() just passed what is returned to
-                # compile() which can handle str. And converting to bytes would
-                # require figuring out the encoding to decode to and
-                # tokenize.detect_encoding() only accepts bytes.
                 return file.read()
         else:
             return super().get_data(path)