def update_page(title, text, langlinks, weak_update=True):
"""
:param str title: title of the page
:param str text: wikitext of the page
:param langlinks: a sorted list of ``(tag, title)`` tuples as obtained
from :py:meth:`self.get_langlinks`
:param weak_update:
When ``True``, the langlinks present on the page are mixed with those
suggested by ``family_titles``. This is necessary only when there are
multiple "intersecting" families, in which case the intersection should
be preserved and solved manually. This is reported in _merge_families.
:returns: updated wikicode
"""
# temporarily skip main pages until the behavior switches
# (__NOTOC__ etc.) can be parsed by mwparserfromhell
# NOTE: handling whitespace right will be hard: https://wiki.archlinux.org/index.php?title=Main_page&diff=383144&oldid=382787
if re.search("__NOTOC__|__NOEDITSECTION__", text):
logger.warning("Skipping page '{}' (contains behavior switch(es))".format(title))
return text
# format langlinks, in the prefix form
# (e.g. "cs:Some title" for title="Some title" and tag="cs")
langlinks = ["[[{}:{}]]".format(tag, title) for tag, title in langlinks]
logger.info("Parsing page [[{}]] ...".format(title))
wikicode = mwparserfromhell.parse(text)
if weak_update is True:
parent, magics, cats, langlinks = header.get_header_parts(wikicode, langlinks=langlinks, remove_from_parent=True)
else:
# drop the extracted langlinks
parent, magics, cats, _ = header.get_header_parts(wikicode, remove_from_parent=True)
header.build_header(wikicode, parent, magics, cats, langlinks)
return wikicode
def fix_page(title, text_old):
langname = lang.detect_language(title)[1]
wikicode = mwparserfromhell.parse(text_old)
parent, magics, cats, langlinks = get_header_parts(wikicode, remove_from_parent=True)
for cat in cats:
# get_header_parts returns list of wikicode objects, each with one node
cat = cat.nodes[0]
pure, ln = lang.detect_language(str(cat.title))
if ln != langname:
cat.title = lang.format_title(pure, langname)
build_header(wikicode, parent, magics, cats, langlinks)
return wikicode
def fix_page(title, text_old):
langname = lang.detect_language(title)[1]
wikicode = mwparserfromhell.parse(text_old)
parent, magics, cats, langlinks = get_header_parts(wikicode, remove_from_parent=True)
for cat in cats:
# get_header_parts returns list of wikicode objects, each with one node
cat = cat.nodes[0]
pure, ln = lang.detect_language(str(cat.title))
if ln != langname:
cat.title = lang.format_title(pure, langname)
build_header(wikicode, parent, magics, cats, langlinks)
return wikicode
def update_page(title, text, langlinks, weak_update=True):
"""
:param str title: title of the page
:param str text: wikitext of the page
:param langlinks: a sorted list of ``(tag, title)`` tuples as obtained
from :py:meth:`self.get_langlinks`
:param weak_update:
When ``True``, the langlinks present on the page are mixed with those
suggested by ``family_titles``. This is necessary only when there are
multiple "intersecting" families, in which case the intersection should
be preserved and solved manually. This is reported in _merge_families.
:returns: updated wikicode
"""
# temporarily skip main pages until the behavior switches
# (__NOTOC__ etc.) can be parsed by mwparserfromhell
# NOTE: handling whitespace right will be hard: https://wiki.archlinux.org/index.php?title=Main_page&diff=383144&oldid=382787
if re.search("__NOTOC__|__NOEDITSECTION__", text):
logger.warning(
"Skipping page '{}' (contains behavior switch(es))".format(
title))
return text
# format langlinks, in the prefix form
# (e.g. "cs:Some title" for title="Some title" and tag="cs")
langlinks = [
"[[{}:{}]]".format(tag, title) for tag, title in langlinks
]
logger.info("Parsing page [[{}]] ...".format(title))
wikicode = mwparserfromhell.parse(text)
if weak_update is True:
parent, magics, cats, langlinks = header.get_header_parts(
wikicode, langlinks=langlinks, remove_from_parent=True)
else:
# drop the extracted langlinks
parent, magics, cats, _ = header.get_header_parts(
wikicode, remove_from_parent=True)
header.build_header(wikicode, parent, magics, cats, langlinks)
return wikicode
def decategorize(title, text_old):
wikicode = mwparserfromhell.parse(text_old)
parent, magics, cats, langlinks = get_header_parts(
wikicode, remove_from_parent=True)
build_header(wikicode, parent, magics, [], langlinks)
return wikicode