jenkins-bot has submitted this change. (
https://gerrit.wikimedia.org/r/c/pywikibot/core/+/1334092?usp=email )
Change subject: pagegenerators: Apply title filters first
......................................................................
pagegenerators: Apply title filters first
Apply title regex filters before filters which may load page data. Pages
rejected by title are discarded without redirect, claim, quality or category
lookups.
Change-Id: I09a8210651f38199e2ecc32663c6c938735b6962
---
M pywikibot/pagegenerators/_factory.py
M tests/pagegenerators_tests.py
2 files changed, 32 insertions(+), 8 deletions(-)
Approvals:
jenkins-bot: Verified
Xqt: Looks good to me, approved
diff --git a/pywikibot/pagegenerators/_factory.py
b/pywikibot/pagegenerators/_factory.py
index f7aab25..c01c43e 100644
--- a/pywikibot/pagegenerators/_factory.py
+++ b/pywikibot/pagegenerators/_factory.py
@@ -284,6 +284,15 @@
combine = roundrobin_generators if self.limit else itertools.chain
dupfiltergen = _filter_unique_pages(combine(*self.gens))
+ # Apply title-only filters before filters which may load page data.
+ if self.titlefilter_list:
+ dupfiltergen = RegexFilterPageGenerator(
+ dupfiltergen, self.titlefilter_list)
+
+ if self.titlenotfilter_list:
+ dupfiltergen = RegexFilterPageGenerator(
+ dupfiltergen, self.titlenotfilter_list, 'none')
+
# Add on subpage filter generator
if self.subpage_max_depth is not None:
dupfiltergen = SubpageFilterGenerator(
@@ -305,14 +314,6 @@
dupfiltergen = QualityFilterPageGenerator(
dupfiltergen, self.qualityfilter_list)
- if self.titlefilter_list:
- dupfiltergen = RegexFilterPageGenerator(
- dupfiltergen, self.titlefilter_list)
-
- if self.titlenotfilter_list:
- dupfiltergen = RegexFilterPageGenerator(
- dupfiltergen, self.titlenotfilter_list, 'none')
-
if self.catfilter_list:
dupfiltergen = CategoryFilterPageGenerator(
dupfiltergen, self.catfilter_list)
diff --git a/tests/pagegenerators_tests.py b/tests/pagegenerators_tests.py
index d63a043..29b7f4f 100755
--- a/tests/pagegenerators_tests.py
+++ b/tests/pagegenerators_tests.py
@@ -808,6 +808,29 @@
dry = True
+ def test_title_filters_run_before_redirect_filter(self) -> None:
+ """Test title filters discard pages before redirect checks."""
+ site = self.get_site()
+ keep = pywikibot.Page(site, 'Keep this')
+ pages = [
+ pywikibot.Page(site, 'Drop this'),
+ pywikibot.Page(site, 'Keep excluded'),
+ keep,
+ ]
+ gf = pagegenerators.GeneratorFactory(site=site)
+ gf.gens = [pages]
+ gf.titlefilter_list = ['^Keep']
+ gf.titlenotfilter_list = ['excluded']
+ gf.redirectfilter = False
+
+ with mock.patch.object(
+ pywikibot.Page, 'isRedirectPage', return_value=False
+ ) as is_redirect:
+ result = list(gf.getCombinedGenerator())
+
+ self.assertEqual(result, [keep])
+ is_redirect.assert_called_once_with()
+
def test_one_namespace(self) -> None:
"""Test one namespace."""
gf = pagegenerators.GeneratorFactory(site=self.get_site())
--
To view, visit
https://gerrit.wikimedia.org/r/c/pywikibot/core/+/1334092?usp=email
To unsubscribe, or for help writing mail filters, visit
https://gerrit.wikimedia.org/r/settings?usp=email
Gerrit-MessageType: merged
Gerrit-Project: pywikibot/core
Gerrit-Branch: master
Gerrit-Change-Id: I09a8210651f38199e2ecc32663c6c938735b6962
Gerrit-Change-Number: 1334092
Gerrit-PatchSet: 2
Gerrit-Owner: Mahveotm <[email protected]>
Gerrit-Reviewer: Xqt <[email protected]>
Gerrit-Reviewer: jenkins-bot
_______________________________________________
Pywikibot-commits mailing list -- [email protected]
To unsubscribe send an email to [email protected]