jenkins-bot has submitted this change. (
https://gerrit.wikimedia.org/r/c/pywikibot/core/+/1346042?usp=email )
Change subject: textlib: Support legacy encoded section titles
......................................................................
textlib: Support legacy encoded section titles
Match legacy anchors against encoded heading wikitext after checking plain
titles. Encoding headings preserves literal dot sequences alongside escaped
punctuation and UTF-8 characters. Reuse section parsing to retain equals
signs that belong to the heading.
Bug: T133276
Change-Id: I983df6f7b5606bb39587431554b87503808bb3e9
---
M pywikibot/textlib.py
M tests/textlib_tests.py
2 files changed, 39 insertions(+), 5 deletions(-)
Approvals:
Xqt: Looks good to me, approved
jenkins-bot: Verified
diff --git a/pywikibot/textlib.py b/pywikibot/textlib.py
index 1a34f97..7da87fc 100644
--- a/pywikibot/textlib.py
+++ b/pywikibot/textlib.py
@@ -15,6 +15,7 @@
from dataclasses import dataclass
from html.parser import HTMLParser
from typing import NamedTuple
+from urllib.parse import quote
import pywikibot
from pywikibot.backports import pairwise
@@ -2190,15 +2191,33 @@
section with or without a preceding colon which is required for a
text link e.g. for categories and files.
+ Legacy dot-escaped titles are matched literally against encoded
+ heading wikitext, treating spaces and underscores alike.
+
+ .. version-changed:: 11.9
+ Legacy dot-escaped section titles are supported.
+
:param pagetext: The wikitext of a page
:param section: A section of a page including wikitext markups
"""
# match preceding colon for text links
- section = re.sub(r'\\\[\\\[(\\?:)?', r'\[\[\:?', re.escape(section))
+ section_regex = re.sub(
+ r'\\\[\\\[(\\?:)?', r'\[\[\:?', re.escape(section))
# match underscores and white spaces
- section = re.sub(r'\\?[ _]', '[ _]', section)
- m = re.search(f"=+[ ']*{section}[ ']*=+", pagetext)
- return bool(m)
+ section_regex = re.sub(r'\\?[ _]', '[ _]', section_regex)
+ if re.search(f"=+[ ']*{section_regex}[ ']*=+", pagetext):
+ return True
+
+ # Encode headings instead of decoding ambiguous literal dot sequences.
+ section = section.replace(' ', '_')
+ for match in get_regexes('header')[0].finditer(pagetext):
+ heading = Section(match[1], '').heading.replace(' ', '_')
+ # Legacy anchors escape '~', which quote() always leaves safe.
+ encoded = quote(heading, safe=':').replace('~', '%7E')
+ if encoded.replace('%', '.') == section:
+ return True
+
+ return False
def reformat_ISBNs(text: str, match_func) -> str:
diff --git a/tests/textlib_tests.py b/tests/textlib_tests.py
index ce008e1..127fa0e 100755
--- a/tests/textlib_tests.py
+++ b/tests/textlib_tests.py
@@ -71,11 +71,26 @@
self.assertNotContains('Minor_Edits',
'section hashes are case-sensitive')
- @unittest.expectedFailure # T133276
def test_encoded_chars_in_section(self) -> None:
"""Test encoded chars in section."""
self.assertContains('Talk_.28discussion.29_pages',
'As used in the TOC')
+ self.assertContains('.5B.5BWiki_markup.5D.5D')
+ self.assertTrue(textlib.does_text_contain_section(
+ '== آزمون ==', '.D8.A2.D8.B2.D9.85.D9.88.D9.86'))
+ self.assertTrue(textlib.does_text_contain_section(
+ '== Literal .28 title ==', 'Literal_.28_title'))
+ self.assertTrue(textlib.does_text_contain_section(
+ '== Version .28 (notes) ==', 'Version_.28_.28notes.29'))
+ self.assertTrue(textlib.does_text_contain_section(
+ '== Invalid .FF title ==', 'Invalid_.FF_title'))
+ self.assertFalse(textlib.does_text_contain_section(
+ '== .27Version (notes) ==', 'Version_.28notes.29'))
+ self.assertFalse(textlib.does_text_contain_section(
+ '== .5B.5B:Help (notes) ==', '.5B.5BHelp_.28notes.29'))
+ self.assertTrue(textlib.does_text_contain_section(
+ '===Version (notes)====', 'Version_.28notes.29.3D'))
+ self.assertNotContains('Talk_%28discussion%29_pages')
def test_underline_characters_in_section(self) -> None:
"""Test with underline chars in section."""
--
To view, visit
https://gerrit.wikimedia.org/r/c/pywikibot/core/+/1346042?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: I983df6f7b5606bb39587431554b87503808bb3e9
Gerrit-Change-Number: 1346042
Gerrit-PatchSet: 3
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]
