On Sun, Jul 26, 2009 at 03:06:58PM +0200, John Wright wrote:
> I really wish it were possible to ensure the apt_pkg parser gave the
> same results as the native parser, though. :(
Looks like we can actually do this, with a small patch to python-apt [1]
and the attached patch.
[1]: http://bugs.debian.org/538723
--
John Wright <j...@debian.org>
commit a26b007a91c9723d33690e7e0b897c70c2006ee5
Author: John Wright <j...@johnwright.org>
Date: Sun Jul 26 17:20:20 2009 +0200
Don't ignore leading newlines on field data with apt_pkg
This depends on the patch to python-apt in #538723 being accepted.
diff --git a/debian_bundle/deb822.py b/debian_bundle/deb822.py
index fb1ed7c..a5662af 100644
--- a/debian_bundle/deb822.py
+++ b/debian_bundle/deb822.py
@@ -37,6 +37,31 @@ import sys
import StringIO
import UserDict
+class TagSectionWrapper(object, UserDict.DictMixin):
+ """Wrap a TagSection object, using the FindRaw method instead of Find
+
+ This allows us to pick which whitespace to strip off the beginning and end
+ of the data, so we don't lose leading newlines.
+ """
+
+ def __init__(self, parser):
+ self.parser = parser
+
+ def keys(self):
+ return self.parser.keys()
+
+ def __getitem__(self, key):
+ s = self.parser.FindRaw(key)
+
+ if s is None:
+ raise KeyError(key)
+
+ data = s.partition(':')[2]
+
+ # Get rid of spaces and tabs after the :, but not newlines, and strip
+ # off any newline at the end of the data.
+ return data.lstrip(' \t').rstrip('\n')
+
class OrderedSet(object):
"""A set-like object that preserves order when iterating over it
@@ -242,16 +267,12 @@ class Deb822(Deb822Dict):
if _have_apt_pkg and use_apt_pkg and isinstance(sequence, file):
parser = apt_pkg.ParseTagFile(sequence)
+ section = TagSectionWrapper(parser.Section)
while parser.Step() == 1:
if shared_storage:
- parsed = parser.Section
+ parsed = section
else:
- # Since parser.Section doesn't have an items method, we
- # need to imitate that method here and make a Deb822Dict
- # from the result in order to preserve order.
- items = [(key, parser.Section[key])
- for key in parser.Section.keys()]
- parsed = Deb822Dict(items)
+ parsed = Deb822Dict(section)
yield cls(fields=fields, _parsed=parsed)
else:
