From: Eric Wong <e@80x24.org>
To: meta@public-inbox.org
Subject: [PATCH] linkify: don't get confused by URLs in Perl code, at least
Date: Thu, 18 Apr 2019 22:47:01 +0000 [thread overview]
Message-ID: <20190418224701.8135-1-e@80x24.org> (raw)
The URLs at the top of WwwStream.pm weren't getting linkified
correctly.
---
lib/PublicInbox/Linkify.pm | 15 +++++++++++----
t/linkify.t | 19 +++++++++++++++++++
2 files changed, 30 insertions(+), 4 deletions(-)
diff --git a/lib/PublicInbox/Linkify.pm b/lib/PublicInbox/Linkify.pm
index aa472cd..71193bc 100644
--- a/lib/PublicInbox/Linkify.pm
+++ b/lib/PublicInbox/Linkify.pm
@@ -15,7 +15,7 @@ package PublicInbox::Linkify;
use Digest::SHA qw/sha1_hex/;
my $SALT = rand;
-my $LINK_RE = qr{(\()?\b((?:ftps?|https?|nntps?|gopher)://
+my $LINK_RE = qr{([\('!])?\b((?:ftps?|https?|nntps?|gopher)://
[\@:\w\.-]+(?:/
(?:[a-z0-9\-\._~!\$\&\';\(\)\*\+,;=:@/%]*)
(?:\?[a-z0-9\-\._~!\$\&\';\(\)\*\+,;=:@/%]+)?
@@ -25,6 +25,14 @@ package PublicInbox::Linkify;
sub new { bless {}, $_[0] }
+# try to distinguish paired punctuation chars from the URL itself
+# Maybe other languages/formats can be supported here, too...
+my %pairs = (
+ "(" => qr/(\)[\.,;\+]?)\z/, # Markdown (,), Ruby (+) (, for arrays)
+ "'" => qr/('[\.,;\+]?)\z/, # Perl / Ruby
+ "!" => qr/(![\.,;\+]?)\z/, # Perl / Ruby
+);
+
sub linkify_1 {
$_[1] =~ s^$LINK_RE^
my $beg = $1 || '';
@@ -35,9 +43,8 @@ sub linkify_1 {
# '.', ',' or ';' to denote the end of a statement;
# assume the intent was to end the statement/sentence
# in English
- # Markdown compatibility:
- if ($beg eq '(') {
- if ($url =~ s/(\)[\.,;]?)\z//) {
+ if (defined(my $re = $pairs{$beg})) {
+ if ($url =~ s/$re//) {
$end = $1;
}
} elsif ($url =~ s/([\.,;])\z//) {
diff --git a/t/linkify.t b/t/linkify.t
index f0b3a6d..bef4ffd 100644
--- a/t/linkify.t
+++ b/t/linkify.t
@@ -98,4 +98,23 @@ use PublicInbox::Linkify;
'Markdown-compatible end of sentence');
}
+# Perl and Ruby code compatibility
+{
+ my $l = PublicInbox::Linkify->new;
+ my $u = 'http://example.com/';
+ foreach my $q ("'%s'", '"%s"', 'q!%s!', 'q(%s)') {
+ # Perl
+ my $s = sprintf("my \$var = $q;", $u);
+ $s = $l->linkify_1($s);
+ $s = $l->linkify_2($s);
+ like($s, qr/>\Q$u\E</, "no quote($q) in URL");
+
+ # applies to Ruby, too
+ $s = sprintf("$q,", $u);
+ $s = $l->linkify_1($s);
+ $s = $l->linkify_2($s);
+ like($s, qr/>\Q$u\E</, "no quote($q) in URL array");
+ }
+}
+
done_testing();
--
EW
reply other threads:[~2019-04-18 22:47 UTC|newest]
Thread overview: [no followups] expand[flat|nested] mbox.gz Atom feed
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
List information: http://public-inbox.org/README
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20190418224701.8135-1-e@80x24.org \
--to=e@80x24.org \
--cc=meta@public-inbox.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
Code repositories for project(s) associated with this public inbox
https://80x24.org/public-inbox.git
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).