Cscott has uploaded a new change for review. https://gerrit.wikimedia.org/r/60877
Change subject: Normalize superfluous %xx escaping in URLs; three more parser tests pass now. ...................................................................... Normalize superfluous %xx escaping in URLs; three more parser tests pass now. This also makes the new ~ and = tests pass which were added in https://gerrit.wikimedia.org/r/60874 Change-Id: Iddb5033c606dc40f851b4f6101037bfdb2d52ea7 --- M js/lib/mediawiki.Util.js M js/tests/parserTests-blacklist.js 2 files changed, 4 insertions(+), 3 deletions(-) git pull ssh://gerrit.wikimedia.org:29418/mediawiki/extensions/Parsoid refs/changes/77/60877/1 diff --git a/js/lib/mediawiki.Util.js b/js/lib/mediawiki.Util.js index 31e486a..a4807a1 100644 --- a/js/lib/mediawiki.Util.js +++ b/js/lib/mediawiki.Util.js @@ -1019,6 +1019,8 @@ .replace(/<span[^>]+about="[^"]*"[^>]*>/g, '') .replace(/<span><\/span>/g, '') .replace(/(href=")(?:\.?\.\/)+/g, '$1') + // replace unnecessary URL escaping + .replace(/ href="[^"]*"/g, unescape) // strip thumbnail size prefixes .replace(/(src="[^"]*?)\/thumb(\/[0-9a-f]\/[0-9a-f]{2}\/[^\/]+)\/[0-9]+px-[^"\/]+(?=")/g, '$1$2') .replace(/(<(table|tbody|tr|th|td|\/th|\/td)[^<>]*>)\s+/g, '$1'); @@ -1057,6 +1059,8 @@ .replace(/<a +href/g, '<a href') .replace(/href="\/wiki\//g, 'href="') .replace(/" +>/g, '">') + // replace unnecessary URL escaping + .replace(/ href="[^"]*"/g, unescape) // strip empty spans .replace(/<span><\/span>/g, '') .replace(/(<(table|tbody|tr|th|td|\/th|\/td)[^<>]*>)\s+/g, '$1'); diff --git a/js/tests/parserTests-blacklist.js b/js/tests/parserTests-blacklist.js index 335ad97..251e664 100644 --- a/js/tests/parserTests-blacklist.js +++ b/js/tests/parserTests-blacklist.js @@ -223,7 +223,6 @@ add("wt2html", "Subpage noslash link"); add("wt2html", "Disabled subpages"); add("wt2html", "BUG 561: {{/Subpage}}"); -add("wt2html", "Link to category"); add("wt2html", "Simple category"); add("wt2html", "PAGESINCATEGORY invalid title fatal (r33546 fix)"); add("wt2html", "Category with different sort key"); @@ -679,7 +678,6 @@ add("html2html", "Bug 4781, 5267: %28, %29 in bracketed URL"); add("html2html", "External link containing double-single-quotes with no space separating the url from text in italics"); add("html2html", "Brackets in urls"); -add("html2html", "IPv6 urls (bug 21261)"); add("html2html", "Unclosed and unmatched quotes (parsoid)"); add("html2html", "Table security: embedded pipes (http://lists.wikimedia.org/mailman/htdig/wikitech-l/2006-April/022293.html)"); add("html2html", "Indented table markup mixed with indented pre content (proposed in bug 6200)"); @@ -921,7 +919,6 @@ add("html2html", "HTML ordered list item with parameters oddity"); add("html2html", "Fuzz testing: Parser14"); add("html2html", "Fuzz testing: Parser14-table"); -add("html2html", "Fuzz testing: Parser21"); add("html2html", "Fuzz testing: Parser24"); add("html2html", "Fuzz testing: URL adjacent extension (no space, dirty; pre)"); add("html2html", "Fuzz testing: encoded newline in generated HTML replacements (bug 6577)"); -- To view, visit https://gerrit.wikimedia.org/r/60877 To unsubscribe, visit https://gerrit.wikimedia.org/r/settings Gerrit-MessageType: newchange Gerrit-Change-Id: Iddb5033c606dc40f851b4f6101037bfdb2d52ea7 Gerrit-PatchSet: 1 Gerrit-Project: mediawiki/extensions/Parsoid Gerrit-Branch: master Gerrit-Owner: Cscott <[email protected]> _______________________________________________ MediaWiki-commits mailing list [email protected] https://lists.wikimedia.org/mailman/listinfo/mediawiki-commits
