The marshalled dict in the response given on STDOUT by p4 uses `str` for
keys and string values. When run using python3, these values are
deserialized as `bytes`, leading to a whole host of problems as the rest
of the code assumes `str` is used throughout.
An exception is made for the `data` field as it may contain arbitrary
binary data that is not text, as well as `depotFile` which may contain
text encoded with something other than ASCII or UTF-8.
Signed-off-by: Yang Zhao <yang.zhao@xxxxxxxxxxxxxx>
---
git-p4.py | 10 ++++++++++
1 file changed, 10 insertions(+)
diff --git a/git-p4.py b/git-p4.py
index 60c73b6a37..ead9d816e1 100755
--- a/git-p4.py
+++ b/git-p4.py
@@ -36,6 +36,7 @@
unicode = str
bytes = bytes
basestring = (str,bytes)
+ use_encoded_streams = True
else:
# 'unicode' exists, must be Python 2
str = str
@@ -643,6 +644,15 @@ def p4CmdList(cmd, stdin=None, stdin_mode='w+b', cb=None, skip_info=False,
try:
while True:
entry = marshal.load(p4.stdout)
+ if use_encoded_streams:
+ # Decode unmarshalled dict to use str keys and values, except for:
+ # - `data` which may contain arbitrary binary data
+ # - `depotFile` which may contain non-UTF8 encoded text
+ decoded_entry = {}
+ for key, value in entry.items():
+ key = key.decode()
+ decoded_entry[key] = value.decode() if not (key in ['data', 'depotFile'] or isinstance(value, str)) else value
+ entry = decoded_entry
if skip_info:
if 'code' in entry and entry['code'] == 'info':
continue
--
2.24.0.windows.2
