From 3ac221a78eba2f447a7990fc5c4709853dc32fee Mon Sep 17 00:00:00 2001 From: John Keeping Date: Sun, 27 Jan 2013 14:50:56 +0000 Subject: [PATCH] git-remote-testpy: fix path hashing on Python 3 When this change was originally made (0846b0c - git-remote-testpy: hash bytes explicitly , I didn't realise that the "hex" encoding we chose is a "bytes to bytes" encoding so it just fails with an error on Python 3 in the same way as the original code. It is not possible to provide a single code path that works on Python 2 and Python 3 since Python 2.x will attempt to decode the string before encoding it, which fails for strings that are not valid in the default encoding. Python 3.1 introduced the "surrogateescape" error handler which handles this correctly and permits a bytes -> unicode -> bytes round-trip to be lossless. As the original came from reading the filesystem path, we convert them back into the original bytes encoded in sys.getfilesystemencoding(). At this point Python 3.0 is unsupported so we don't go out of our way to try to support it. Helped-by: Michael Haggerty Signed-off-by: John Keeping Signed-off-by: Junio C Hamano --- git-remote-testpy.py | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) diff --git a/git-remote-testpy.py b/git-remote-testpy.py index c7a04ecae..ca6789996 100644 --- a/git-remote-testpy.py +++ b/git-remote-testpy.py @@ -36,6 +36,22 @@ if sys.hexversion < 0x02000000: sys.stderr.write("git-remote-testgit: requires Python 2.0 or later.\n") sys.exit(1) + +def encode_filepath(path): + """Encodes a Unicode file path to a byte string. + + On Python 2 this is a no-op; on Python 3 we encode the string as + suggested by [1] which allows an exact round-trip from the command line + to the filesystem. + + [1] http://docs.python.org/3/c-api/unicode.html#file-system-encoding + + """ + if sys.hexversion < 0x03000000: + return path + return path.encode(sys.getfilesystemencoding(), 'surrogateescape') + + def get_repo(alias, url): """Returns a git repository object initialized for usage. """ @@ -45,7 +61,7 @@ def get_repo(alias, url): repo.get_head() hasher = _digest() - hasher.update(repo.path.encode('hex')) + hasher.update(encode_filepath(repo.path)) repo.hash = hasher.hexdigest() repo.get_base_path = lambda base: os.path.join( -- 2.26.2