jenkins-bot has submitted this change. ( https://gerrit.wikimedia.org/r/c/pywikibot/core/+/1132163?usp=email )

Change subject: [IMPR] Improve cleanUpLinks/handleOneLink ......................................................................

[IMPR] Improve cleanUpLinks/handleOneLink

Combine the result string with f-string. The performance increases by 3 % (only)

Bug: T390068 Change-Id: Ib430f1c5aace753f84de7836d8d43b4c60869b02 --- M pywikibot/cosmetic_changes.py 1 file changed, 18 insertions(+), 23 deletions(-)

Approvals: Xqt: Looks good to me, approved jenkins-bot: Verified

diff --git a/pywikibot/cosmetic_changes.py b/pywikibot/cosmetic_changes.py index 4bf1fdc..463e346 100644 --- a/pywikibot/cosmetic_changes.py +++ b/pywikibot/cosmetic_changes.py @@ -50,7 +50,7 @@ 'your_script_name_2'] """ # -# (C) Pywikibot team, 2006-2024 +# (C) Pywikibot team, 2006-2025 # # Distributed under the terms of the MIT license. # @@ -538,11 +538,11 @@ This function will:

* Replace underscores with spaces - * Move leading and trailing spaces out of the wikilink and into the - surrounding text + * 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 + * 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 @@ -560,7 +560,7 @@ encodings=self.site.encodings()) label = match['label'] trailingChars = match['linktrail'] - newline = match['newline'] + newline = match['newline'] or '' # entire link but convert URL-encoded text oldlink = url2string(match.group(), encodings=self.site.encodings()) @@ -582,16 +582,15 @@ if not in_main_namespace: return oldlink

- # Replace underlines by spaces, also multiple underlines - titleWithSection = re.sub('_+', ' ', titleWithSection) - # Remove double spaces - titleWithSection = re.sub(' +', ' ', titleWithSection) + # Replace underlines by spaces, remove double spaces + titleWithSection = re.sub('[_ ]+', ' ', titleWithSection) # Remove unnecessary leading spaces from title, # but remember if we did this because we eventually want # to re-add it outside of the link later. titleLength = len(titleWithSection) titleWithSection = titleWithSection.lstrip() - hadLeadingSpaces = len(titleWithSection) != titleLength + hadLeadingSpaces = not newline \ + and len(titleWithSection) != titleLength hadTrailingSpaces = False # Remove unnecessary trailing spaces from title, # but remember if we did this because it may affect @@ -609,13 +608,15 @@ # Remove unnecessary initial and final spaces from label. # Please note that some editors prefer spaces around pipes. # (See [[en:Wikipedia:Semi-bots]]). We remove them anyway. - if label is not None: + if label is None: + label = titleWithSection + else: # Remove unnecessary leading spaces from label, # but remember if we did this because we want # to re-add it outside of the link later. labelLength = len(label) label = label.lstrip() - hadLeadingSpaces = len(label) != labelLength + hadLeadingSpaces = not newline and len(label) != labelLength # Remove unnecessary trailing spaces from label, # but remember if we did this because it affects # the linktrail. @@ -623,8 +624,7 @@ labelLength = len(label) label = label.rstrip() hadTrailingSpaces = len(label) != labelLength - else: - label = titleWithSection + if trailingChars: label += trailingChars

@@ -643,7 +643,6 @@ and trailR.sub('', label[len(titleWithSection):]) == ''): newLink = (f'[[{label[:len(titleWithSection)]}]]' f'{label[len(titleWithSection):]}') - else: # Try to capitalize the first letter of the title. # Not useful for languages that don't capitalize nouns. @@ -653,19 +652,15 @@ if self.site.sitename == 'wikipedia:de': titleWithSection = first_upper(titleWithSection) newLink = f'[[{titleWithSection}|{label}]]' + # re-add spaces that were pulled out of the link. # Examples: # text[[ title ]]text -> text [[title]] text # text[[ title | name ]]text -> text [[title|name]] text # text[[ title |name]]text -> text[[title|name]]text # text[[title| name]]text -> text [[title|name]]text - if hadLeadingSpaces and not newline: - newLink = ' ' + newLink - if hadTrailingSpaces: - newLink += ' ' - if newline: - newLink = newline + newLink - return newLink + return f"{newline}{' ' if hadLeadingSpaces else ''}" \ + f"{newLink}{' ' if hadTrailingSpaces else ''}"

trailR = re.compile(self.site.linktrail()) # The regular expression which finds links. Results consist of four groups: