jenkins-bot has submitted this change. (
https://gerrit.wikimedia.org/r/c/pywikibot/core/+/942603 )
Change subject: [IMPR] Convert URL-encoded characters also for links outside
main namespace
......................................................................
[IMPR] Convert URL-encoded characters also for links outside main namespace
As found by T342470 the CosmeticChangesToolkit.cleanUpLinks() does not
convert URL-encoded characters outside main namespace or for interwiki
links. This patch solved this issue.
Bug: T342470
Change-Id: Ie9f8fc503df842ad45fe44eefc57449c0473cd29
---
M pywikibot/cosmetic_changes.py
1 file changed, 28 insertions(+), 12 deletions(-)
Approvals:
Meno25: Looks good to me, approved
jenkins-bot: Verified
diff --git a/pywikibot/cosmetic_changes.py b/pywikibot/cosmetic_changes.py
index ffd43a5..bf3e112 100644
--- a/pywikibot/cosmetic_changes.py
+++ b/pywikibot/cosmetic_changes.py
@@ -501,32 +501,38 @@
"""Tidy up wikilinks found in a string.
This function will:
- * Replace underscores with spaces
+ * Replace underscores with spaces
* Move leading and trailing spaces out of the wikilink and into the
surrounding text
-
* Convert URL-encoded characters into Unicode-encoded characters
-
* Move trailing characters out of the link and make the link without
using a pipe, if possible
-
* Capitalize the article title of the link, if appropriate
+ .. versionchanged:: 8.4
+ Convert URL-encoded characters if a link is an interwiki link
+ or different from main namespace.
+
:param text: string to perform the clean-up on
:return: text with tidied wikilinks
"""
# helper function which works on one link and either returns it
# unmodified, or returns a replacement.
def handleOneLink(match: Match[str]) -> str:
- titleWithSection = match['titleWithSection']
+ # Convert URL-encoded characters to str
+ titleWithSection = url2string(match['titleWithSection'],
+ encodings=self.site.encodings())
label = match['label']
trailingChars = match['linktrail']
newline = match['newline']
+ # entire link but convert URL-encoded text
+ oldlink = url2string(match.group(),
+ encodings=self.site.encodings())
is_interwiki = self.site.isInterwikiLink(titleWithSection)
if is_interwiki:
- return match.group()
+ return oldlink
# The link looks like this:
# [[page_title|link_text]]trailing_chars
@@ -538,7 +544,7 @@
except InvalidTitleError:
in_main_namespace = False
if not in_main_namespace:
- return match.group()
+ return oldlink
# Replace underlines by spaces, also multiple underlines
titleWithSection = re.sub('_+', ' ', titleWithSection)
@@ -560,13 +566,9 @@
titleWithSection = titleWithSection.rstrip()
hadTrailingSpaces = len(titleWithSection) != titleLength
- # Convert URL-encoded characters to str
- titleWithSection = url2string(titleWithSection,
- encodings=self.site.encodings())
-
if not titleWithSection:
# just skip empty links.
- return match.group()
+ return match.groups()
# Remove unnecessary initial and final spaces from label.
# Please note that some editors prefer spaces around pipes.
--
To view, visit https://gerrit.wikimedia.org/r/c/pywikibot/core/+/942603
To unsubscribe, or for help writing mail filters, visit
https://gerrit.wikimedia.org/r/settings
Gerrit-Project: pywikibot/core
Gerrit-Branch: master
Gerrit-Change-Id: Ie9f8fc503df842ad45fe44eefc57449c0473cd29
Gerrit-Change-Number: 942603
Gerrit-PatchSet: 1
Gerrit-Owner: Xqt <[email protected]>
Gerrit-Reviewer: Meno25 <[email protected]>
Gerrit-Reviewer: jenkins-bot
Gerrit-MessageType: merged
_______________________________________________
Pywikibot-commits mailing list -- [email protected]
To unsubscribe send an email to [email protected]
