From f2701d56385b5856f56f69bc9b185d974853e430 Mon Sep 17 00:00:00 2001
From: "Kyle J. McKay" <mackyle@gmail.com>
Date: Wed, 27 Dec 2017 06:47:29 -0800
Subject: [PATCH] Markdown.pl: apply -i and -r options to a and img tags

When a and img tags are generated using the normal Markdown syntax
any prefixes specified with the -i and -r options are inserted as
appropriate.

Extend this processing to explicit a and img tags as well.

This makes sense because they should be handled the same way the
Markdown syntax generated tags are for consistency.

It's still possible to "escape" from the prefixes by using an
explicit scheme+host+port or the commonly supported (but not a
standard) //+host+port mechanism.

And it only matters if prefixes have been set with the -i and/or
-r options (the default is no prefixes) anyway.

Signed-off-by: Kyle J. McKay <mackyle@gmail.com>
---
 Markdown.pl | 41 +++++++++++++++++++++++++++++++++++++++++
 1 file changed, 41 insertions(+)

diff --git a/Markdown.pl b/Markdown.pl
index 381d7a1..edfc74a 100755
--- a/Markdown.pl
+++ b/Markdown.pl
@@ -1979,6 +1979,8 @@ sub _DoTag {
 	if (($tag =~ m{^<($g_possible_tag_name)(?:[\s>]|/>$)} || $tag =~ m{^</($g_possible_tag_name)\s*>}) &&
 	    $ok_tag_name{lc($1)}) {
 
+	    return _ProcessURLTag("href", $tag) if $tag =~ /^<a\s/i;
+	    return _ProcessURLTag("src", $tag) if $tag =~ /^<img\s/i;
 	    return $tag;
 	}
 	$tag =~ s/</&lt;/g;
@@ -1986,6 +1988,45 @@ sub _DoTag {
 }
 
 
+sub _ProcessURLTag {
+    my $att = shift;
+    my $tag = shift;
+
+    $att = lc($att) . "=";
+    if ($tag =~ /^(<[^\s>]+\s+)/g) {
+	    my $out = $1;
+	    while ($tag =~ /\G([^\s\042\047>]+=)([\042\047])((?:(?!\2)(?!>).)*)(\2\s*)/gc) {
+		    my ($p, $q, $v, $s) = ($1, $2, $3, $4);
+		    if (lc($p) eq $att && $v ne "") {
+			    $v = _HTMLEncode(_PrefixURL($v));
+		    }
+		    $out .= $p . $q . $v . $s;
+	    }
+	    $out .= substr($tag, pos($tag));
+	    return $out;
+    }
+
+    return $tag;
+}
+
+
+sub _HTMLEncode {
+    my $text = shift;
+
+    # Ampersand-encoding based entirely on Nat Irons's Amputator MT plugin:
+    #   http://bumppo.net/projects/amputator/
+    $text =~ s/&(?!#?[xX]?(?:[0-9a-fA-F]+|\w+);)/&amp;/g;
+
+    # Remaining entities now
+    $text =~ s/\042/&quot;/g;
+    $text =~ s/\047/&apos;/g;
+    $text =~ s/</&lt;/g;
+    $text =~ s/>/&gt;/g;
+
+    return $text;
+}
+
+
 sub _EncodeAmps {
     my $text = shift;