From e5a7990dbe8d5c45541a7d56b07d64d20b1fe002 Mon Sep 17 00:00:00 2001 From: Zachary Turner Date: Mon, 1 Feb 2016 18:12:59 +0000 Subject: Always write the session file in UTF-8. This patch attempts to solve the Python 2 / Python 3 incompatibilities by introducing a new `encoded_file` abstraction that we use instead of `io.open()`. The problem with the builtin implementation of `io.open` is that `read` and `write` accept and return `unicode` objects, which are not always convenient to work with in Python 2. We solve this by making `encoded_file.open()` return the same object returned by `io.open()` but with hooked `read()` and `write()` methods. These hooked methods will accept binary or text data, and conditionally convert what it gets to a `unicode` object using the correct encoding. When calling `read()` it also does any conversion necessary to convert the output back into the native `string` type of the running python version. Differential Revision: http://reviews.llvm.org/D16736 llvm-svn: 259379 --- .../Python/lldbsuite/support/encoded_file.py | 48 ++++++++++++++++++++++ 1 file changed, 48 insertions(+) create mode 100644 lldb/packages/Python/lldbsuite/support/encoded_file.py (limited to 'lldb/packages/Python/lldbsuite/support/encoded_file.py') diff --git a/lldb/packages/Python/lldbsuite/support/encoded_file.py b/lldb/packages/Python/lldbsuite/support/encoded_file.py new file mode 100644 index 00000000000..7581564f7e3 --- /dev/null +++ b/lldb/packages/Python/lldbsuite/support/encoded_file.py @@ -0,0 +1,48 @@ +""" + The LLVM Compiler Infrastructure + +This file is distributed under the University of Illinois Open Source +License. See LICENSE.TXT for details. + +Prepares language bindings for LLDB build process. Run with --help +to see a description of the supported command line arguments. +""" + +# Python modules: +import io + +# Third party modules +import six + +def _encoded_read(old_read, encoding): + def impl(size): + result = old_read(size) + # If this is Python 2 then we need to convert the resulting `unicode` back + # into a `str` before returning + if six.PY2: + result = result.encode(encoding) + return result + return impl + +def _encoded_write(old_write, encoding): + def impl(s): + # If we were asked to write a `str` (in Py2) or a `bytes` (in Py3) decode it + # as unicode before attempting to write. + if isinstance(s, six.binary_type): + s = s.decode(encoding) + return old_write(s) + return impl + +''' +Create a Text I/O file object that can be written to with either unicode strings or byte strings +under Python 2 and Python 3, and automatically encodes and decodes as necessary to return the +native string type for the current Python version +''' +def open(file, encoding, mode='r', buffering=-1, errors=None, newline=None, closefd=True): + wrapped_file = io.open(file, mode=mode, buffering=buffering, encoding=encoding, + errors=errors, newline=newline, closefd=closefd) + new_read = _encoded_read(getattr(wrapped_file, 'read'), encoding) + new_write = _encoded_write(getattr(wrapped_file, 'write'), encoding) + setattr(wrapped_file, 'read', new_read) + setattr(wrapped_file, 'write', new_write) + return wrapped_file -- cgit v1.2.3