Migrate from codecs.open() to io.open().

The io.open() function is the same as the built-in open() function in
python3, and its implementation is optimized in python-2.7 and later.
In addition to the possible performance improvement, this also allows
us to avoid any future compatibility issues with codecs.open() that
may arise if it is delegated to the built-in open() function as
discussed in PEP 400.

The main caveat involved with io.open() is that TextIOWrapper.write()
raises TypeError if given raw bytes, unlike the streams returned from
codecs.open(). This is mainly an issue for python2 since literal
strings are raw bytes. We handle this by wrapping TextIOWrapper.write()
arguments with our _unicode_decode() function. Also, the
atomic_ofstream class overrides the write() method in python2 so that
it performs automatic coercion to unicode when necessary.

3 files changed, 31 insertions, 12 deletions

diff --git a/pym/portage/util/ExtractKernelVersion.py b/pym/portage/util/ExtractKernelVersion.py
index 1cdb8bf13..5cb9747e6 100644
--- a/pym/portage/util/ExtractKernelVersion.py
+++ b/pym/portage/util/ExtractKernelVersion.py
@@ -1,9 +1,9 @@
-# Copyright 2010 Gentoo Foundation
+# Copyright 2010-2011 Gentoo Foundation
 # Distributed under the terms of the GNU General Public License v2
 
 __all__ = ['ExtractKernelVersion']
 
-import codecs
+import io
 
 from portage import os, _encodings, _unicode_encode
 from portage.util import getconfig, grabfile
@@ -22,7 +22,7 @@ def ExtractKernelVersion(base_dir):
 	lines = []
 	pathname = os.path.join(base_dir, 'Makefile')
 	try:
-		f = codecs.open(_unicode_encode(pathname,
+		f = io.open(_unicode_encode(pathname,
 			encoding=_encodings['fs'], errors='strict'), mode='r',
 			encoding=_encodings['content'], errors='replace')
 	except OSError as details:
diff --git a/pym/portage/util/__init__.py b/pym/portage/util/__init__.py
index 5468e28c9..b641d3ed2 100644
--- a/pym/portage/util/__init__.py
+++ b/pym/portage/util/__init__.py
@@ -11,9 +11,9 @@ __all__ = ['apply_permissions', 'apply_recursive_permissions',
 	'stack_dicts', 'stack_lists', 'unique_array', 'unique_everseen', 'varexpand',
 	'write_atomic', 'writedict', 'writemsg', 'writemsg_level', 'writemsg_stdout']
 
-import codecs
 from copy import deepcopy
 import errno
+import io
 try:
 	from itertools import filterfalse
 except ImportError:
@@ -475,7 +475,7 @@ def grablines(myfilename, recursive=0, remember_source_file=False):
 					os.path.join(myfilename, f), recursive, remember_source_file))
 	else:
 		try:
-			myfile = codecs.open(_unicode_encode(myfilename,
+			myfile = io.open(_unicode_encode(myfilename,
 				encoding=_encodings['fs'], errors='strict'),
 				mode='r', encoding=_encodings['content'], errors='replace')
 			if remember_source_file:
@@ -1091,7 +1091,7 @@ class atomic_ofstream(ObjectProxy):
 		if 'b' in mode:
 			open_func = open
 		else:
-			open_func = codecs.open
+			open_func = io.open
 			kargs.setdefault('encoding', _encodings['content'])
 			kargs.setdefault('errors', 'backslashreplace')
 
@@ -1122,10 +1122,29 @@ class atomic_ofstream(ObjectProxy):
 	def _get_target(self):
 		return object.__getattribute__(self, '_file')
 
-	def __getattribute__(self, attr):
-		if attr in ('close', 'abort', '__del__'):
-			return object.__getattribute__(self, attr)
-		return getattr(object.__getattribute__(self, '_file'), attr)
+	if sys.hexversion >= 0x3000000:
+
+		def __getattribute__(self, attr):
+			if attr in ('close', 'abort', '__del__'):
+				return object.__getattribute__(self, attr)
+			return getattr(object.__getattribute__(self, '_file'), attr)
+
+	else:
+
+		# For TextIOWrapper, automatically coerce write calls to
+		# unicode, in order to avoid TypeError when writing raw
+		# bytes with python2.
+
+		def __getattribute__(self, attr):
+			if attr in ('close', 'abort', 'write', '__del__'):
+				return object.__getattribute__(self, attr)
+			return getattr(object.__getattribute__(self, '_file'), attr)
+
+		def write(self, s):
+			f = object.__getattribute__(self, '_file')
+			if isinstance(f, io.TextIOWrapper):
+				s = _unicode_decode(s)
+			return f.write(s)
 
 	def close(self):
 		"""Closes the temporary file, copies permissions (if possible),
diff --git a/pym/portage/util/env_update.py b/pym/portage/util/env_update.py
index 3e295f00b..eb8a0d951 100644
--- a/pym/portage/util/env_update.py
+++ b/pym/portage/util/env_update.py
@@ -3,8 +3,8 @@
 
 __all__ = ['env_update']
 
-import codecs
 import errno
+import io
 import stat
 import sys
 import time
@@ -125,7 +125,7 @@ def env_update(makelinks=1, target_root=None, prev_mtimes=None, contents=None,
 
 	ldsoconf_path = os.path.join(target_root, "etc", "ld.so.conf")
 	try:
-		myld = codecs.open(_unicode_encode(ldsoconf_path,
+		myld = io.open(_unicode_encode(ldsoconf_path,
 			encoding=_encodings['fs'], errors='strict'),
 			mode='r', encoding=_encodings['content'], errors='replace')
 		myldlines=myld.readlines()