[gentoo-commits] proj/portage:master commit in: pym/portage/, pym/portage/dep/

["Zac Medico" <zmedico@gentoo.org>]

commit:     12ff9e4d8006664c3d154651aeb8403c2c7aaa8a
Author:     Zac Medico <zmedico <AT> gentoo <DOT> org>
AuthorDate: Sat Sep 22 21:52:35 2012 +0000
Commit:     Zac Medico <zmedico <AT> gentoo <DOT> org>
CommitDate: Sat Sep 22 21:52:35 2012 +0000
URL:        http://git.overlays.gentoo.org/gitweb/?p=proj/portage.git;a=commit;h=12ff9e4d

Use re.UNICODE for category/package name regexes.

This only affects r'\w' with Python 2.x, since Python 3 already
defaults to re.UNICODE behavior when compiling unicode str objects
(unless re.ASCII is specified). If a repository wants to ban unicode
categore/package names then we can add a layout.conf setting for that,
as discussed in bug #435934.

---
 pym/portage/dep/__init__.py |   10 +++++-----
 pym/portage/manifest.py     |   16 +++++++++++++++-
 pym/portage/versions.py     |    4 ++--
 3 files changed, 22 insertions(+), 8 deletions(-)

diff --git a/pym/portage/dep/__init__.py b/pym/portage/dep/__init__.py
index b4b240d..6e03004 100644
--- a/pym/portage/dep/__init__.py
+++ b/pym/portage/dep/__init__.py
@@ -72,7 +72,7 @@ def _get_slot_re(eapi_attrs):
 	else:
 		slot_re = _slot
 
-	slot_re = re.compile('^' + slot_re + '$', re.VERBOSE)
+	slot_re = re.compile('^' + slot_re + '$', re.VERBOSE | re.UNICODE)
 
 	_slot_re_cache[cache_key] = slot_re
 	return slot_re
@@ -90,7 +90,7 @@ def _get_slot_dep_re(eapi_attrs):
 	else:
 		slot_re = _slot
 
-	slot_re = re.compile('^' + slot_re + '$', re.VERBOSE)
+	slot_re = re.compile('^' + slot_re + '$', re.VERBOSE | re.UNICODE)
 
 	_slot_dep_re_cache[cache_key] = slot_re
 	return slot_re
@@ -123,7 +123,7 @@ def _get_atom_re(eapi_attrs):
 		'(?P<star>=' + cpv_re + r'\*)|' +
 		'(?P<simple>' + cp_re + '))' + 
 		'(' + _slot_separator + _slot_loose + ')?' +
-		_repo + ')(' + _use + ')?$', re.VERBOSE)
+		_repo + ')(' + _use + ')?$', re.VERBOSE | re.UNICODE)
 
 	_atom_re_cache[cache_key] = atom_re
 	return atom_re
@@ -145,7 +145,7 @@ def _get_atom_wildcard_re(eapi_attrs):
 		_extended_cat + r')/(' + pkg_re + r'))' + \
 		'|(?P<star>=((' + _extended_cat + r')/(' + pkg_re + r'))-(?P<version>\*\d+\*)))' + \
 		'(:(?P<slot>' + _slot_loose + r'))?(' +
-		_repo_separator + r'(?P<repo>' + _repo_name + r'))?$')
+		_repo_separator + r'(?P<repo>' + _repo_name + r'))?$', re.UNICODE)
 
 	_atom_wildcard_re_cache[cache_key] = atom_re
 	return atom_re
@@ -1585,7 +1585,7 @@ def extended_cp_match(extended_cp, other_cp):
 	extended_cp_re = _extended_cp_re_cache.get(extended_cp)
 	if extended_cp_re is None:
 		extended_cp_re = re.compile("^" + re.escape(extended_cp).replace(
-			r'\*', '[^/]*') + "$")
+			r'\*', '[^/]*') + "$", re.UNICODE)
 		_extended_cp_re_cache[extended_cp] = extended_cp_re
 	return extended_cp_re.match(other_cp) is not None
 

diff --git a/pym/portage/manifest.py b/pym/portage/manifest.py
index b2f1ff2..25886bb 100644
--- a/pym/portage/manifest.py
+++ b/pym/portage/manifest.py
@@ -4,6 +4,7 @@
 import errno
 import io
 import re
+import sys
 import warnings
 
 import portage
@@ -24,6 +25,11 @@ from portage.const import (MANIFEST1_HASH_FUNCTIONS, MANIFEST2_HASH_DEFAULTS,
 	MANIFEST2_HASH_FUNCTIONS, MANIFEST2_IDENTIFIERS, MANIFEST2_REQUIRED_HASH)
 from portage.localization import _
 
+if sys.hexversion >= 0x3000000:
+	_unicode = str
+else:
+	_unicode = unicode
+
 # Characters prohibited by repoman's file.name check.
 _prohibited_filename_chars_re = re.compile(r'[^a-zA-Z0-9._\-+:]')
 
@@ -108,6 +114,14 @@ class Manifest2Entry(ManifestEntry):
 	def __ne__(self, other):
 		return not self.__eq__(other)
 
+	if sys.hexversion < 0x3000000:
+
+		__unicode__ = __str__
+
+		def __str__(self):
+			return _unicode_encode(self.__unicode__(),
+				encoding=_encodings['repo.content'], errors='strict')
+
 class Manifest(object):
 	parsers = (parseManifest2,)
 	def __init__(self, pkgdir, distdir, fetchlist_dict=None,
@@ -289,7 +303,7 @@ class Manifest(object):
 					# thin manifests with no DIST entries, myentries is
 					# non-empty for all currently known use cases.
 					write_atomic(self.getFullname(), "".join("%s\n" %
-						str(myentry) for myentry in myentries))
+						_unicode(myentry) for myentry in myentries))
 				else:
 					# With thin manifest, there's no need to have
 					# a Manifest file if there are no DIST entries.

diff --git a/pym/portage/versions.py b/pym/portage/versions.py
index 242623f..a9b7e64 100644
--- a/pym/portage/versions.py
+++ b/pym/portage/versions.py
@@ -79,7 +79,7 @@ def _get_pv_re(eapi_attrs):
 	else:
 		pv_re = _pv['dots_disallowed_in_PN']
 
-	pv_re = re.compile('^' + pv_re + '$', re.VERBOSE)
+	pv_re = re.compile(_unicode_decode('^' + pv_re + '$'), re.VERBOSE | re.UNICODE)
 
 	_pv_re_cache[cache_key] = pv_re
 	return pv_re
@@ -292,7 +292,7 @@ def _pkgsplit(mypkg, eapi=None):
 
 	return  (m.group('pn'), m.group('ver'), rev) 
 
-_cat_re = re.compile('^%s$' % _cat)
+_cat_re = re.compile('^%s$' % _cat, re.UNICODE)
 _missing_cat = 'null'
 
 def catpkgsplit(mydata, silent=1, eapi=None):