systemd/xml_helper.py
Zbigniew Jędrzejewski-Szmek 1a13e31d27 build-sys,man: use XML entities to substite strings
This makes it easier to add substitutions to man pages,
avoiding the separate transformation step.

mkdir -p's are removed from the rule, because xsltproc will
will create directories on it's own.

All in all, two or three forks per man page are avoided,
which should make things marginally faster.

Unfortunately python parsers must too be tweaked to handle
entities. This isn't particularly easy: with lxml a custom
Resolver can be used, but the stdlib etree doesn't support
external entities *at all*. So when running without lxml,
the entities are just removed. Right now it doesn't matter,
since the entities are not indexed anyway. But I intend to
add indexing of filenames in the near future, and then the
index generated without lxml might be missing a few lines.
Oh well.
2013-03-29 20:30:21 -04:00

41 lines
1.5 KiB
Python

# -*- Mode: python; coding: utf-8; indent-tabs-mode: nil -*- */
#
# This file is part of systemd.
#
# Copyright 2012-2013 Zbigniew Jędrzejewski-Szmek
#
# systemd is free software; you can redistribute it and/or modify it
# under the terms of the GNU Lesser General Public License as published by
# the Free Software Foundation; either version 2.1 of the License, or
# (at your option) any later version.
#
# systemd is distributed in the hope that it will be useful, but
# WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
# Lesser General Public License for more details.
#
# You should have received a copy of the GNU Lesser General Public License
# along with systemd; If not, see <http://www.gnu.org/licenses/>.
try:
from lxml import etree as tree
class CustomResolver(tree.Resolver):
def resolve(self, url, id, context):
if 'custom-entities.ent' in url:
return self.resolve_filename('man/custom-entities.ent', context)
_parser = tree.XMLParser()
_parser.resolvers.add(CustomResolver())
xml_parse = lambda page: tree.parse(page, _parser)
xml_print = lambda xml: tree.tostring(xml, pretty_print=True)
except ImportError:
import xml.etree.ElementTree as tree
import re as _re
import io as _io
def xml_parse(page):
s = _re.sub(b'&[a-zA-Z0-9_]+;', b'', open(page, 'rb').read())
return tree.parse(_io.BytesIO(s))
xml_print = tree.tostring