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.

6 files changed, 27 insertions, 22 deletions

diff --git a/pym/_emerge/Binpkg.py b/pym/_emerge/Binpkg.py
index 84eda21ba..b83341941 100644
--- a/pym/_emerge/Binpkg.py
+++ b/pym/_emerge/Binpkg.py
@@ -14,8 +14,9 @@ from portage.util import writemsg
 import portage
 from portage import os
 from portage import _encodings
+from portage import _unicode_decode
 from portage import _unicode_encode
-import codecs
+import io
 import logging
 from portage.output import colorize
 
@@ -239,20 +240,22 @@ class Binpkg(CompositeTask):
 			else:
 				continue
 
-			f = codecs.open(_unicode_encode(os.path.join(infloc, k),
+			f = io.open(_unicode_encode(os.path.join(infloc, k),
 				encoding=_encodings['fs'], errors='strict'),
-				mode='w', encoding=_encodings['content'], errors='replace')
+				mode='w', encoding=_encodings['content'],
+				errors='backslashreplace')
 			try:
-				f.write(v + "\n")
+				f.write(_unicode_decode(v + "\n"))
 			finally:
 				f.close()
 
 		# Store the md5sum in the vdb.
-		f = codecs.open(_unicode_encode(os.path.join(infloc, 'BINPKGMD5'),
+		f = io.open(_unicode_encode(os.path.join(infloc, 'BINPKGMD5'),
 			encoding=_encodings['fs'], errors='strict'),
 			mode='w', encoding=_encodings['content'], errors='strict')
 		try:
-			f.write(str(portage.checksum.perform_md5(pkg_path)) + "\n")
+			f.write(_unicode_decode(
+				str(portage.checksum.perform_md5(pkg_path)) + "\n"))
 		finally:
 			f.close()
 
diff --git a/pym/_emerge/EbuildFetcher.py b/pym/_emerge/EbuildFetcher.py
index 215024165..51d2f5a10 100644
--- a/pym/_emerge/EbuildFetcher.py
+++ b/pym/_emerge/EbuildFetcher.py
@@ -1,10 +1,11 @@
-# Copyright 1999-2010 Gentoo Foundation
+# Copyright 1999-2011 Gentoo Foundation
 # Distributed under the terms of the GNU General Public License v2
 
 import traceback
 
 from _emerge.SpawnProcess import SpawnProcess
 import copy
+import io
 import signal
 import sys
 import portage
@@ -12,7 +13,6 @@ from portage import os
 from portage import _encodings
 from portage import _unicode_encode
 from portage import _unicode_decode
-import codecs
 from portage.elog.messages import eerror
 from portage.package.ebuild.fetch import fetch
 from portage.util._pty import _create_pty_or_pipe
@@ -160,12 +160,13 @@ class EbuildFetcher(SpawnProcess):
 		# fetch code will be skipped, so we need to generate equivalent
 		# output here.
 		if self.logfile is not None:
-			f = codecs.open(_unicode_encode(self.logfile,
+			f = io.open(_unicode_encode(self.logfile,
 				encoding=_encodings['fs'], errors='strict'),
-				mode='a', encoding=_encodings['content'], errors='replace')
+				mode='a', encoding=_encodings['content'],
+				errors='backslashreplace')
 			for filename in uri_map:
-				f.write((' * %s size ;-) ...' % \
-					filename).ljust(73) + '[ ok ]\n')
+				f.write(_unicode_decode((' * %s size ;-) ...' % \
+					filename).ljust(73) + '[ ok ]\n'))
 			f.close()
 
 		return True
diff --git a/pym/_emerge/EbuildMetadataPhase.py b/pym/_emerge/EbuildMetadataPhase.py
index 284622d69..e53298bae 100644
--- a/pym/_emerge/EbuildMetadataPhase.py
+++ b/pym/_emerge/EbuildMetadataPhase.py
@@ -11,7 +11,7 @@ from portage import _encodings
 from portage import _unicode_decode
 from portage import _unicode_encode
 import fcntl
-import codecs
+import io
 
 class EbuildMetadataPhase(SubProcess):
 
@@ -37,7 +37,7 @@ class EbuildMetadataPhase(SubProcess):
 		if eapi is None and \
 			'parse-eapi-ebuild-head' in settings.features:
 			eapi = portage._parse_eapi_ebuild_head(
-				codecs.open(_unicode_encode(ebuild_path,
+				io.open(_unicode_encode(ebuild_path,
 				encoding=_encodings['fs'], errors='strict'),
 				mode='r', encoding=_encodings['repo.content'],
 				errors='replace'))
diff --git a/pym/_emerge/depgraph.py b/pym/_emerge/depgraph.py
index d5971d1ba..d0b8fb722 100644
--- a/pym/_emerge/depgraph.py
+++ b/pym/_emerge/depgraph.py
@@ -3,10 +3,9 @@
 
 from __future__ import print_function
 
-import codecs
 import difflib
 import errno
-import gc
+import io
 import logging
 import re
 import stat
@@ -5937,7 +5936,7 @@ class depgraph(object):
 		def write_changes(root, changes, file_to_write_to):
 			file_contents = None
 			try:
-				file_contents = codecs.open(
+				file_contents = io.open(
 					_unicode_encode(file_to_write_to,
 					encoding=_encodings['fs'], errors='strict'),
 					mode='r', encoding=_encodings['content'],
diff --git a/pym/_emerge/emergelog.py b/pym/_emerge/emergelog.py
index 9cac3b222..a195c6f84 100644
--- a/pym/_emerge/emergelog.py
+++ b/pym/_emerge/emergelog.py
@@ -3,12 +3,13 @@
 
 from __future__ import print_function
 
-import codecs
+import io
 import sys
 import time
 import portage
 from portage import os
 from portage import _encodings
+from portage import _unicode_decode
 from portage import _unicode_encode
 from portage.data import secpass
 from portage.output import xtermTitle
@@ -36,7 +37,7 @@ def emergelog(xterm_titles, mystr, short_msg=None):
 	try:
 		file_path = os.path.join(_emerge_log_dir, 'emerge.log')
 		existing_log = os.path.isfile(file_path)
-		mylogfile = codecs.open(_unicode_encode(file_path,
+		mylogfile = io.open(_unicode_encode(file_path,
 			encoding=_encodings['fs'], errors='strict'),
 			mode='a', encoding=_encodings['content'],
 			errors='backslashreplace')
@@ -50,7 +51,8 @@ def emergelog(xterm_titles, mystr, short_msg=None):
 			# seek because we may have gotten held up by the lock.
 			# if so, we may not be positioned at the end of the file.
 			mylogfile.seek(0, 2)
-			mylogfile.write(str(time.time())[:10]+": "+mystr+"\n")
+			mylogfile.write(_unicode_decode(
+				str(time.time())[:10]+": "+mystr+"\n"))
 			mylogfile.flush()
 		finally:
 			if mylock:
diff --git a/pym/_emerge/resolver/output_helpers.py b/pym/_emerge/resolver/output_helpers.py
index 874660f69..b7e73766c 100644
--- a/pym/_emerge/resolver/output_helpers.py
+++ b/pym/_emerge/resolver/output_helpers.py
@@ -7,7 +7,7 @@ in output.py
 __all__ = (
 	)
 
-import codecs
+import io
 import re
 import sys
 
@@ -502,7 +502,7 @@ def _calc_changelog(ebuildpath,current,next):
 		next = next[:-3]
 	changelogpath = os.path.join(os.path.split(ebuildpath)[0],'ChangeLog')
 	try:
-		changelog = codecs.open(_unicode_encode(changelogpath,
+		changelog = io.open(_unicode_encode(changelogpath,
 			encoding=_encodings['fs'], errors='strict'),
 			mode='r', encoding=_encodings['repo.content'], errors='replace'
 		).read()