mirror of
https://github.com/freedombox/FreedomBox.git
synced 2026-01-21 07:55:00 +00:00
f0000c4ba3
The previous logic of the wiki links fix didn't work for translated pages. Closes: #1908. Signed-off-by: Fioddor Superconcentrado <fioddor@gmail.com> [jvalleroy: Remove extra spaces] [jvalleroy: Fix output path] Signed-off-by: James Valleroy <jvalleroy@mailbox.org> Reviewed-by: James Valleroy <jvalleroy@mailbox.org>
98 lines
3.1 KiB
Python
Executable File
98 lines
3.1 KiB
Python
Executable File
#!/usr/bin/python3
|
|
# SPDX-License-Identifier: AGPL-3.0-or-later
|
|
|
|
import argparse
|
|
import xml.etree.ElementTree as etree
|
|
|
|
|
|
def parse_arguments():
|
|
"""Return parsed command line arguments as dictionary."""
|
|
parser = argparse.ArgumentParser()
|
|
subparsers = parser.add_subparsers(dest='subcommand', help='Sub command')
|
|
|
|
subparser = subparsers.add_parser(
|
|
'remove-footer', help='Remove footer from the XML document')
|
|
subparser.add_argument('filename', help='Name of the XML file')
|
|
|
|
subparser = subparsers.add_parser('fix-wiki-urls',
|
|
help='Fix wrongly formatted wiki urls')
|
|
subparser.add_argument('filename', help='Name of the Docbook file')
|
|
|
|
subparsers.required = True
|
|
return parser.parse_args()
|
|
|
|
|
|
def subcommand_fix_wiki_urls(arguments):
|
|
""" Rebase the wiki urls.
|
|
|
|
The base for relative links in Debian wiki is the wiki's URL but our
|
|
extraction process rebases the relative links to the page containing
|
|
the link. This function fixes that.
|
|
"""
|
|
WIKI_URL = 'https://wiki.debian.org'
|
|
_, lang, file_name = arguments.filename.split('/')
|
|
page_name = file_name.split('.')[0]
|
|
|
|
with open(arguments.filename, 'r') as xml_file:
|
|
lines = xml_file.readlines()
|
|
|
|
if 'en' == lang:
|
|
pattern = f'{WIKI_URL}/FreedomBox/Manual/{page_name}'
|
|
else:
|
|
pattern = f'{WIKI_URL}/{lang}/FreedomBox/Manual/{page_name}'
|
|
lines = list(map(lambda s: s.replace(pattern, f'{WIKI_URL}'), lines))
|
|
|
|
with open(arguments.filename, 'w') as xml_file:
|
|
xml_file.writelines(lines)
|
|
|
|
|
|
def subcommand_remove_footer(arguments):
|
|
"""Remove the footer template from the given wiki page."""
|
|
filename = arguments.filename
|
|
tree = etree.parse(filename)
|
|
root = tree.getroot()
|
|
|
|
# The footer will always be in the last <section>
|
|
def find_last_section(elem):
|
|
if len(elem):
|
|
last_element = elem[-1]
|
|
if last_element.tag == 'section':
|
|
return find_last_section(last_element)
|
|
return elem
|
|
|
|
last_section = find_last_section(root)
|
|
|
|
if len(last_section):
|
|
# Remove all elements till <informaltable> is reached
|
|
while last_section[-1].tag != 'informaltable':
|
|
last_section.remove(last_section[-1])
|
|
# remove <informaltable> itself
|
|
last_section.remove(last_section[-1])
|
|
|
|
# Remove the line "Back to Features introduction or manual pages."
|
|
if last_section[-1].text.startswith('Back to'):
|
|
last_section.remove(last_section[-1])
|
|
|
|
processed_xml = etree.tostring(root, encoding='utf-8').decode()
|
|
|
|
with open(filename, 'r') as xml_file:
|
|
# <xml> and <DOCTYPE> elements which etree skips
|
|
header = xml_file.readlines()[:2]
|
|
|
|
with open(filename, 'w') as xml_file:
|
|
xml_file.writelines(header)
|
|
xml_file.write(processed_xml)
|
|
|
|
|
|
def main():
|
|
"""Parse arguments and perform all duties."""
|
|
arguments = parse_arguments()
|
|
|
|
subcommand = arguments.subcommand.replace('-', '_')
|
|
subcommand_method = globals()['subcommand_' + subcommand]
|
|
subcommand_method(arguments)
|
|
|
|
|
|
if __name__ == '__main__':
|
|
main()
|