From 1e7310e6cd84a42bcf76d84b053257dc0df104da Mon Sep 17 00:00:00 2001 From: Alex Kerfoot Date: Tue, 8 Mar 2016 16:05:02 -0800 Subject: Fix CreateString with already-encoded string or bytearray in Python 2.7. There was no way to pass an already-encoded string to `builder.CreateString` in Python 2.7: - Passing a `bytearray` raised a TypeError because `bytearray` was not recognized as an instance of `compat.binary_type`. - Passing a utf-8 encoded `str` would cause the string to be double-encoded, because `compat.string_types = (basestring,)` and `basestring` is the base class of `str` and `unicode`, so the logic would never reach the `elif isinstance(s, compat.binary_type)` case. - Converting a utf-8 encoded bytearray to `bytes` like `builder.CreateString(bytes(encoded_string))` does not work because in Python 2.7, bytes is just an alias for `str` so it behaves as above. This change allows either `bytes` or `bytearray` as an already-encoded string to be passed to `CreateString` in versions of Python that support `bytearray`, and falls back to `str` in older versions. In Python 2, it restricts unencoded string types to `unicode`, so `str` can be used as an encoded, binary representaiton. --- python/flatbuffers/builder.py | 2 +- python/flatbuffers/compat.py | 9 ++++++--- 2 files changed, 7 insertions(+), 4 deletions(-) (limited to 'python') diff --git a/python/flatbuffers/builder.py b/python/flatbuffers/builder.py index 18cfab9c..552d0e2b 100644 --- a/python/flatbuffers/builder.py +++ b/python/flatbuffers/builder.py @@ -401,7 +401,7 @@ class Builder(object): if isinstance(s, compat.string_types): x = s.encode(encoding, errors) - elif isinstance(s, compat.binary_type): + elif isinstance(s, compat.binary_types): x = s else: raise TypeError("non-string passed to CreateString") diff --git a/python/flatbuffers/compat.py b/python/flatbuffers/compat.py index 345e38cb..c592901c 100644 --- a/python/flatbuffers/compat.py +++ b/python/flatbuffers/compat.py @@ -11,13 +11,16 @@ PY34 = sys.version_info[0:2] >= (3, 4) if PY3: string_types = (str,) - binary_type = bytes + binary_types = (bytes,bytearray) range_func = range memoryview_type = memoryview struct_bool_decl = "?" else: - string_types = (basestring,) - binary_type = str + string_types = (unicode,) + if PY26 or PY27: + binary_types = (str,bytearray) + else: + binary_types = (str,) range_func = xrange if PY26 or (PY27 and not PY275): memoryview_type = buffer -- cgit v1.2.3