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.

2 files changed, 25 insertions, 12 deletions

diff --git a/pym/portage/cache/flat_hash.py b/pym/portage/cache/flat_hash.py
index 6be0fe4b2..b6bc0744e 100644
--- a/pym/portage/cache/flat_hash.py
+++ b/pym/portage/cache/flat_hash.py
@@ -1,21 +1,26 @@
-# Copyright: 2005 Gentoo Foundation
+# Copyright: 2005-2011 Gentoo Foundation
+# Distributed under the terms of the GNU General Public License v2
 # Author(s): Brian Harring (ferringb@gentoo.org)
-# License: GPL2
 
-import codecs
 from portage.cache import fs_template
 from portage.cache import cache_errors
 import errno
+import io
 import stat
 import sys
 import os as _os
 from portage import os
 from portage import _encodings
+from portage import _unicode_decode
 from portage import _unicode_encode
 
 if sys.hexversion >= 0x3000000:
 	long = int
 
+# Coerce to unicode, in order to prevent TypeError when writing
+# raw bytes to TextIOWrapper with python2.
+_setitem_fmt = _unicode_decode("%s=%s\n")
+
 class database(fs_template.FsBased):
 
 	autocommits = True
@@ -35,7 +40,7 @@ class database(fs_template.FsBased):
 		# Don't use os.path.join, for better performance.
 		fp = self.location + _os.sep + cpv
 		try:
-			myf = codecs.open(_unicode_encode(fp,
+			myf = io.open(_unicode_encode(fp,
 				encoding=_encodings['fs'], errors='strict'),
 				mode='r', encoding=_encodings['repo.content'],
 				errors='replace')
@@ -68,7 +73,7 @@ class database(fs_template.FsBased):
 		s = cpv.rfind("/")
 		fp = os.path.join(self.location,cpv[:s],".update.%i.%s" % (os.getpid(), cpv[s+1:]))
 		try:
-			myf = codecs.open(_unicode_encode(fp,
+			myf = io.open(_unicode_encode(fp,
 				encoding=_encodings['fs'], errors='strict'),
 				mode='w', encoding=_encodings['repo.content'],
 				errors='backslashreplace')
@@ -76,7 +81,7 @@ class database(fs_template.FsBased):
 			if errno.ENOENT == e.errno:
 				try:
 					self._ensure_dirs(cpv)
-					myf = codecs.open(_unicode_encode(fp,
+					myf = io.open(_unicode_encode(fp,
 						encoding=_encodings['fs'], errors='strict'),
 						mode='w', encoding=_encodings['repo.content'],
 						errors='backslashreplace')
@@ -90,7 +95,7 @@ class database(fs_template.FsBased):
 				v = values.get(k)
 				if not v:
 					continue
-				myf.write("%s=%s\n" % (k, v))
+				myf.write(_setitem_fmt % (k, v))
 		finally:
 			myf.close()
 		self._ensure_access(fp)
diff --git a/pym/portage/cache/flat_list.py b/pym/portage/cache/flat_list.py
index eb7558398..728830753 100644
--- a/pym/portage/cache/flat_list.py
+++ b/pym/portage/cache/flat_list.py
@@ -1,16 +1,24 @@
+# Copyright 2005-2011 Gentoo Foundation
+# Distributed under the terms of the GNU General Public License v2
+
 from portage.cache import fs_template
 from portage.cache import cache_errors
 from portage import os
 from portage import _encodings
+from portage import _unicode_decode
 from portage import _unicode_encode
-import codecs
 import errno
+import io
 import stat
 import sys
 
 if sys.hexversion >= 0x3000000:
 	long = int
 
+# Coerce to unicode, in order to prevent TypeError when writing
+# raw bytes to TextIOWrapper with python2.
+_setitem_fmt = _unicode_decode("%s\n")
+
 # store the current key order *here*.
 class database(fs_template.FsBased):
 
@@ -36,7 +44,7 @@ class database(fs_template.FsBased):
 	def _getitem(self, cpv):
 		d = {}
 		try:
-			myf = codecs.open(_unicode_encode(os.path.join(self.location, cpv),
+			myf = io.open(_unicode_encode(os.path.join(self.location, cpv),
 				encoding=_encodings['fs'], errors='strict'),
 				mode='r', encoding=_encodings['repo.content'],
 				errors='replace')
@@ -60,7 +68,7 @@ class database(fs_template.FsBased):
 		s = cpv.rfind("/")
 		fp=os.path.join(self.location,cpv[:s],".update.%i.%s" % (os.getpid(), cpv[s+1:]))
 		try:
-			myf = codecs.open(_unicode_encode(fp,
+			myf = io.open(_unicode_encode(fp,
 				encoding=_encodings['fs'], errors='strict'),
 				mode='w', encoding=_encodings['repo.content'],
 				errors='backslashreplace')
@@ -68,7 +76,7 @@ class database(fs_template.FsBased):
 			if errno.ENOENT == e.errno:
 				try:
 					self._ensure_dirs(cpv)
-					myf = codecs.open(_unicode_encode(fp,
+					myf = io.open(_unicode_encode(fp,
 						encoding=_encodings['fs'], errors='strict'),
 						mode='w', encoding=_encodings['repo.content'],
 						errors='backslashreplace')
@@ -79,7 +87,7 @@ class database(fs_template.FsBased):
 		
 
 		for x in self.auxdbkey_order:
-			myf.write(values.get(x,"")+"\n")
+			myf.write(_setitem_fmt % (values.get(x, ""),))
 
 		myf.close()
 		self._ensure_access(fp, mtime=values["_mtime_"])