jenkins-bot merged this change.
[IMPR] Move main categories to top in cc
+ re-enable Personendaten on dewiki
+ fix nnwiki interwiki comments (there is a comment, but no code, weird)
+ minor improvements to standardizePageFooter
Bug: T76298
Change-Id: Ie9457953701f98e8c952f289b5a5d91934f2a99b
---
M pywikibot/cosmetic_changes.py
M pywikibot/textlib.py
M tests/cosmetic_changes_tests.py
3 files changed, 81 insertions(+), 36 deletions(-)
diff --git a/pywikibot/cosmetic_changes.py b/pywikibot/cosmetic_changes.py
index 7752809..6194ae2 100755
--- a/pywikibot/cosmetic_changes.py
+++ b/pywikibot/cosmetic_changes.py
@@ -328,26 +328,22 @@
"""
Standardize page footer.
- Makes sure that interwiki links and categories are put to the correct
- position and into the right order. This combines the old instances
- standardizeInterwiki and standardizeCategories.
- The page footer has the following section in that sequence:
+ Makes sure that interwiki links and categories are put
+ into the correct position and into the right order. This
+ combines the old instances of standardizeInterwiki
+ and standardizeCategories.
+
+ The page footer consists of the following parts
+ in that sequence:
1. categories
- 2. ## TODO: template beyond categories ##
- 3. additional information depending on local site policy
- 4. interwiki links
-
+ 2. additional information depending on the local site policy
+ 3. interwiki
"""
- categories = None
- interwikiLinks = None
+ categories = []
+ interwiki_links = []
- # Pywikibot is no longer allowed to touch categories on the
- # German Wikipedia. See
- # https://de.wikipedia.org/wiki/Hilfe_Diskussion:Personendaten/Archiv/1#Position_der_Personendaten_am_.22Artikelende.22
- # ignoring nn-wiki of cause of the comment line above iw section
- if not self.template and '{{Personendaten' not in text and \
- '{{SORTIERUNG' not in text and '{{DEFAULTSORT' not in text and \
- self.site.code not in ('et', 'it', 'bg', 'ru'):
+ # get categories
+ if not self.template:
categories = textlib.getCategoryLinks(text, site=self.site)
if not self.talkpage:
@@ -360,26 +356,34 @@
loc = None
if loc is not None and loc in self.title:
subpage = True
- interwikiLinks = textlib.getLanguageLinks(
+
+ # get interwiki
+ interwiki_links = textlib.getLanguageLinks(
text, insite=self.site, template_subpage=subpage)
- # Removing the interwiki
+ # remove interwiki
text = textlib.removeLanguageLinks(text, site=self.site)
- # Adding categories
+ # add categories, main to top
if categories:
- # TODO: Sorting categories in alphabetic order.
- # e.g. using categories.sort()
-
- # TODO: Taking main cats to top
+ # TODO: Sort categories in alphabetic order, e.g. using
+ # categories.sort()? (T100265)
+ # TODO: Get main categories from Wikidata?
+ main = pywikibot.Category(self.site, 'Category:' + self.title,
+ sortKey=' ')
+ if main in categories:
+ categories.pop(categories.index(main))
+ categories.insert(0, main)
text = textlib.replaceCategoryLinks(text, categories,
site=self.site)
- # Adding the interwiki
- if interwikiLinks:
- text = textlib.replaceLanguageLinks(text, interwikiLinks,
+
+ # add interwiki
+ if interwiki_links:
+ text = textlib.replaceLanguageLinks(text, interwiki_links,
site=self.site,
template=self.template,
template_subpage=subpage)
+
return text
def translateAndCapitalizeNamespaces(self, text):
diff --git a/pywikibot/textlib.py b/pywikibot/textlib.py
index 9180a35..a688f59 100644
--- a/pywikibot/textlib.py
+++ b/pywikibot/textlib.py
@@ -1066,7 +1066,29 @@
newtext = s2.replace(marker, '').strip() + separator + s
else:
newtext = s2.replace(marker, '')
- return newtext
+
+ # special parts above interwiki
+ above_interwiki = []
+
+ if site.sitename == 'wikipedia:nn':
+ comment = re.compile(
+ r'<!--interwiki \(no(\/nb)?, *sv, *da first; then other languages '
+ r'alphabetically by name\)-->')
+ above_interwiki.append(comment)
+
+ if above_interwiki:
+ interwiki = _get_regexes(['interwiki'], site)[0]
+ first_interwiki = interwiki.search(newtext)
+ for reg in above_interwiki:
+ special = reg.search(newtext)
+ if special and not isDisabled(newtext, special.start()):
+ newtext = (newtext[:special.start()].strip()
+ + newtext[special.end():])
+ newtext = (newtext[:first_interwiki.start()].strip()
+ + special.group() + '\n'
+ + newtext[first_interwiki.start():])
+
+ return newtext.strip()
def interwikiFormat(links, insite=None):
@@ -1299,14 +1321,6 @@
marker = findmarker(oldtext)
if site is None:
site = pywikibot.Site()
- if site.sitename == 'wikipedia:de' and '{{Personendaten' in oldtext:
- pywikibot.error(
- 'The Pywikibot is no longer allowed to touch categories on the '
- 'German\nWikipedia on pages that contain the Personendaten '
- 'template because of the\nnon-standard placement of that template.'
- '\nSee https://de.wikipedia.org/wiki/Hilfe:Personendaten'
- '#Kopiervorlage')
- return oldtext
if re.search(r'\{\{ *(' + r'|'.join(site.getmagicwords('defaultsort'))
+ r')', oldtext, flags=re.I):
separator = config.line_separator
@@ -1350,6 +1364,27 @@
langs_removed_text, interwiki, site, addOnly=True)
else:
newtext = cats_removed_text.replace(marker, '')
+
+ # special parts under categories
+ under_categories = []
+
+ if site.sitename == 'wikipedia:de':
+ personendaten = re.compile(r'\{\{ *Personendaten.*?\}\}',
+ re.I | re.DOTALL)
+ under_categories.append(personendaten)
+
+ if under_categories:
+ category = _get_regexes(['category'], site)[0]
+ for last_category in category.finditer(newtext):
+ pass
+ for reg in under_categories:
+ special = reg.search(newtext)
+ if special and not isDisabled(newtext, special.start()):
+ newtext = (newtext[:special.start()].strip()
+ + newtext[special.end():])
+ newtext = (newtext[:last_category.end()].strip() + '\n' * 2
+ + special.group() + newtext[last_category.end():])
+
return newtext.strip()
diff --git a/tests/cosmetic_changes_tests.py b/tests/cosmetic_changes_tests.py
index 59779a6..36b41db 100644
--- a/tests/cosmetic_changes_tests.py
+++ b/tests/cosmetic_changes_tests.py
@@ -49,6 +49,12 @@
self.assertEqual('Foo\n{{any template}}\n\n[[Category:Foo]]',
self.cct.standardizePageFooter(
'Foo\n[[category:foo]]\n{{any template}}'))
+ self.assertEqual('Foo\n\n[[Category:Test| ]]\n[[Category:Baz]]',
+ self.cct.standardizePageFooter(
+ 'Foo\n\n[[category:baz]]\n[[category:test]]'))
+ self.assertEqual('Foo\n\n[[Category:Foo]]\n\n{{Personendaten}}',
+ self.cct.standardizePageFooter(
+ 'Foo\n[[category:foo]]\n{{Personendaten}}'))
def test_resolveHtmlEntities(self):
"""Test resolveHtmlEntities method."""
To view, visit change 434997. To unsubscribe, visit settings.