--- pyzor-old   2019-11-07 12:36:52.240794793 -0500
+++ pyzor       2019-11-14 15:40:30.881470181 -0500
@@ -171,11 +171,35 @@


 def _get_input_msg(digester):
-    msg = email.message_from_file(sys.stdin)
+    # Read and process stdin as bytes because we don't know its
+    # encoding. Python-3.x will try to guess -- and can sometimes
+    # guess wrong -- leading to decoding errors in read().
+    msg = email.message_from_bytes(get_binary_stdin().read())
     digested = digester(msg).value
     yield digested


+def _is_binary_reader(stream, default=False):
+    try:
+        return isinstance(stream.read(0), bytes)
+    except Exception:
+        return default
+
+
+def get_binary_stdin():
+    # sys.stdin might or might not be binary in some extra cases.  By
+    # default it's obviously non binary which is the core of the
+    # problem but the docs recommend changing it to binary for such
+    # cases so we need to deal with it.
+    is_binary = _is_binary_reader(sys.stdin, False)
+    if is_binary:
+        return sys.stdin
+    buf = getattr(sys.stdin, 'buffer', None)
+    if buf is not None and _is_binary_reader(buf, True):
+        return buf
+    raise RuntimeError('Did not manage to get binary stdin')
+
+
 def _get_input_mbox(digester):
     tfile = tempfile.NamedTemporaryFile()
     tfile.write(sys.stdin.read().encode("utf8"))