From dfe55f5ee5bd6e3a12d933a6570eb94f294d1c54 Mon Sep 17 00:00:00 2001 From: Eric Wong Date: Thu, 18 Aug 2016 02:02:50 +0000 Subject: linkify: be stricter about matching RFC 3986 We're not to-the-letter about percent-encoding, but we should allow all the characters. This is mainly so we can effectively use the link to some Wikipedia pages with parentheses in them: https://en.wikipedia.org/wiki/Atom_(standard) https://en.wikipedia.org/wiki/Git_(software) --- t/linkify.t | 34 ++++++++++++++++++++++++++++++++++ 1 file changed, 34 insertions(+) (limited to 't') diff --git a/t/linkify.t b/t/linkify.t index 586691ae..49cbbd64 100644 --- a/t/linkify.t +++ b/t/linkify.t @@ -23,4 +23,38 @@ use PublicInbox::Linkify; is($s, qq($u;), 'trailing semicolon not in URL'); } +{ + my $l = PublicInbox::Linkify->new; + my $u = 'http://example.com/url-with-(parens)'; + my $s = "hello $u world"; + $s = $l->linkify_1($s); + $s = $l->linkify_2($s); + is($s, qq(hello $u world), 'URL preserved'); + + $u .= "?query=a"; + $s = "hello $u world"; + $s = $l->linkify_1($s); + $s = $l->linkify_2($s); + is($s, qq(hello $u world), 'query preserved'); + + $u .= "#fragment"; + $s = "hello $u world"; + $s = $l->linkify_1($s); + $s = $l->linkify_2($s); + is($s, qq(hello $u world), + 'query + fragment preserved'); + + $u = "http://example.com/"; + $s = "hello $u world"; + $s = $l->linkify_1($s); + $s = $l->linkify_2($s); + is($s, qq(hello $u world), "root URL preserved"); + + $u = "http://example.com/#fragment"; + $s = "hello $u world"; + $s = $l->linkify_1($s); + $s = $l->linkify_2($s); + is($s, qq(hello $u world), "root + fragment"); +} + done_testing(); -- cgit v1.2.3-24-ge0c7