def test_first_edit(self):
expect = (
u'The Addams Family (pinball)',
u'Talk:Nowy Sącz',
u'Template:Template',
)
gen = PagesFromTitlesGenerator(self.titles, self.site)
gen = pagegenerators.EdittimeFilterPageGenerator(
gen, first_edit_end=datetime.datetime(2006, 1, 1))
self.assertPagelistTitles(gen, titles=expect, site=self.site)
gen = PagesFromTitlesGenerator(self.titles, self.site)
gen = pagegenerators.EdittimeFilterPageGenerator(
gen, first_edit_start=datetime.datetime(2006, 1, 1))
opposite_pages = list(gen)
self.assertTrue(
all(isinstance(p, pywikibot.Page) for p in opposite_pages))
self.assertTrue(all(p.title not in expect for p in opposite_pages))
def test_last_edit(self):
two_days_ago = datetime.datetime.now() - datetime.timedelta(days=2)
nine_days_ago = datetime.datetime.now() - datetime.timedelta(days=9)
gen = PagesFromTitlesGenerator(['Wikipedia:Sandbox'], self.site)
gen = pagegenerators.EdittimeFilterPageGenerator(
gen, last_edit_start=two_days_ago)
self.assertEqual(len(list(gen)), 1)
gen = PagesFromTitlesGenerator(['Wikipedia:Sandbox'], self.site)
gen = pagegenerators.EdittimeFilterPageGenerator(
gen, last_edit_end=two_days_ago)
self.assertEqual(len(list(gen)), 0)
gen = PagesFromTitlesGenerator(['Template:Sidebox'], self.site)
gen = pagegenerators.EdittimeFilterPageGenerator(
gen, last_edit_end=nine_days_ago)
self.assertEqual(len(list(gen)), 1)
gen = PagesFromTitlesGenerator(['Template:Sidebox'], self.site)
gen = pagegenerators.EdittimeFilterPageGenerator(
gen, last_edit_start=nine_days_ago)
self.assertEqual(len(list(gen)), 0)
def process_parameter(self, parameter):
'''
Process the given template parameter supplied to the request template
and return a set of articles referred to by the parameter.
@param parameter: the parameter
@type parameter: unicode
'''
# Regular expression to match parameters on the form "category1= ..."
# and so on, localised to the language we're talking
catparam_regex = re.compile(r"\s*{catparam}\d*=".format(
catparam=config.th_category[self.lang]), re.I)
# Suffix to use when using categories to fetch pages of interest
catname_suffix = config.wikiproject_suffix[self.lang]
# Titles as a set to automatically ignore duplicates
listed_titles = set()
# All articles we've found (stored as pywikibot.Page objects)
found_articles = set()
# Support "category=" parameter by removing the
# keyword and adding the category namespace name
# to the title.
if catparam_regex.match(parameter):
parameter = self.site.category_namespace() \
+ ":" + cataparam_regex.sub("", parameter)
listed_titles.add(parameter)
# Support category suffixes by adding that as well
if catname_suffix:
listed_titles.add('{param}{suffix}'.format(
param=parameter,
suffix=catname_suffix))
else:
# Just this one title
listed_titles.add(parameter)
try:
# Turn title set into a list and process articles/categories
seed_pages = PagesFromTitlesGenerator(list(listed_titles),
site=self.site)
for seedpage in seed_pages:
if not seedpage.exists():
logging.warning("listed {page} does not exist".format(page=seedpage.title()))
continue
if not seedpage.isCategory():
if seedpage.namespace() != 0:
logging.warning("listed page {page} not in ns 0".format(page=seedpage.title()))
elif seedpage.isRedirectPage():
try:
found_articles.add(seedpage.getRedirectTarget())
except pywikibot.exceptions.NoPage:
logging.warning("listed {page} redirects to a non-existent page".format(page=seedpage.title()))
else:
# Everything looks OK, add the page
found_articles.add(seedpage);
else:
# We use the site's categorymembers() method
# to get articles and talk pages, ordered by
# when they were added to the category.
# For large categories we should thereby get
# the oldest and hopefully most developed
# articles in our seed set of articles.
if seedpage.isCategoryRedirect():
try:
seedpage = seedpage.getCategoryRedirectTarget()
except pywikibot.exceptions.NoPage:
logging.warning("listed {title} redirects to a non-existent category".format(title=seedpage.title()))
continue # skip this category
cat_articles = set();
for catmember in self.site.categorymembers(seedpage,
namespaces=[0,1],
sortby="timestamp",
reverse=True):
if catmember.namespace() == 0:
cat_articles.add(catmember)
else:
cat_articles.add(catmember.toggleTalkPage())
if len(cat_articles) >= 256:
break
# Add the category's articles to our result
found_articles = found_articles.union(cat_articles)
except pywikibot.Error:
logging.warning("Failed to instantiate and iterate over list generator, or something else went wrong")
# okay, done
return found_articles
