jenkins-bot has submitted this change and it was merged.
Change subject: fix bug
http://sourceforge.net/p/pywikipediabot/bugs/1671/ weblinkchecker:
url incorrect parsed when using a multiline template
......................................................................
fix bug
http://sourceforge.net/p/pywikipediabot/bugs/1671/
weblinkchecker: url incorrect parsed when using a multiline template
Change-Id: I33d77e9da4da609e12fe551ba6e5df18903fce17
---
M weblinkchecker.py
1 file changed, 7 insertions(+), 2 deletions(-)
Approvals:
Merlijn van Deen: Looks good to me, approved
jenkins-bot: Verified
diff --git a/weblinkchecker.py b/weblinkchecker.py
index 389a967..1e61f99 100644
--- a/weblinkchecker.py
+++ b/weblinkchecker.py
@@ -143,22 +143,27 @@
while nestedTemplateR.search(text):
text = nestedTemplateR.sub(r'{{\1 \2 \3}}', text)
- # Then blow up the templates with spaces so that the | and }} will not be regarded as
part of the link:.
+ # Then blow up the templates with spaces so that the | and }} will not
+ # be regarded as part of the link:.
templateWithParamsR = re.compile(r'{{([^}]*?[^ ])\|([^ ][^}]*?)}}',
re.DOTALL)
while templateWithParamsR.search(text):
text = templateWithParamsR.sub(r'{{ \1 | \2 }}', text)
- linkR = pywikibot.compileLinkR(withoutBracketed, onlyBracketed)
+ # Add <blank> at the end of a template
+ # URL as last param of multiline template would not be correct
+ text = text.replace('}}', ' }}')
# Remove HTML comments in URLs as well as URLs in HTML comments.
# Also remove text inside nowiki links etc.
text = pywikibot.removeDisabledParts(text)
+ linkR = pywikibot.compileLinkR(withoutBracketed, onlyBracketed)
for m in linkR.finditer(text):
if m.group('url'):
yield m.group('url')
else:
yield m.group('urlb')
+
class InternetArchiveConsulter:
def __init__(self, url):
self.url = url
--
To view, visit
https://gerrit.wikimedia.org/r/84229
To unsubscribe, visit
https://gerrit.wikimedia.org/r/settings
Gerrit-MessageType: merged
Gerrit-Change-Id: I33d77e9da4da609e12fe551ba6e5df18903fce17
Gerrit-PatchSet: 2
Gerrit-Project: pywikibot/compat
Gerrit-Branch: master
Gerrit-Owner: Mpaa <mpaa.wiki(a)gmail.com>
Gerrit-Reviewer: Ladsgroup <ladsgroup(a)gmail.com>
Gerrit-Reviewer: Legoktm <legoktm.wikipedia(a)gmail.com>
Gerrit-Reviewer: Merlijn van Deen <valhallasw(a)arctus.nl>
Gerrit-Reviewer: Xqt <info(a)gno.de>
Gerrit-Reviewer: jenkins-bot