improved sanitiser test suite

diff --git a/t/htmlize.t b/t/htmlize.t
index 670500a6796970f0cb54bb51fee054d3ccd9a1d5..9e2e3ec594eded64c1b9388c705db515583b89e1 100755 (executable)
--- a/t/htmlize.t
+++ b/t/htmlize.t
@@ -1,7 +1,7 @@
 #!/usr/bin/perl
 use warnings;
 use strict;
 #!/usr/bin/perl
 use warnings;
 use strict;

-use Test::More tests => 5;
+use Test::More tests => 16;

 use Encode;
 
 BEGIN { use_ok("IkiWiki"); }
 use Encode;
 
 BEGIN { use_ok("IkiWiki"); }


@@ -19,7 +19,32 @@ is(IkiWiki::htmlize("foo", "mdwn", readfile("t/test1.mdwn")),
        "utf8; bug #373203");
 ok(IkiWiki::htmlize("foo", "mdwn", readfile("t/test2.mdwn")),
        "this file crashes markdown if it's fed in as decoded utf-8");
        "utf8; bug #373203");
 ok(IkiWiki::htmlize("foo", "mdwn", readfile("t/test2.mdwn")),
        "this file crashes markdown if it's fed in as decoded utf-8");

-my $ret=IkiWiki::htmlize("foo", "mdwn", readfile("t/javascript.mdwn"));
-ok($ret !~ /GOTCHA/,
-       "javascript.mdwn contains a number of attempts at getting
-       javascript that contains GOTCHA past the html sanitiser.");
+
+# embedded javascript sanitisation tests
+sub gotcha {
+       my $html=IkiWiki::htmlize("foo", "mdwn", shift);
+       return $html =~ /GOTCHA/;
+}
+ok(!gotcha(q{<a href="javascript:alert('GOTCHA')">click me</a>}),
+       "javascript url");
+ok(!gotcha(q{<a href="javascript&#x3A;alert('GOTCHA')">click me</a>}),
+       "partially encoded javascript url");
+ok(!gotcha(q{<a href="jscript:alert('GOTCHA')">click me</a>}),
+       "jscript url");
+ok(!gotcha(q{<a href="vbscript:alert('GOTCHA')">click me</a>}),
+       "vbscrpt url");
+ok(!gotcha(q{<a href="java     script:alert('GOTCHA')">click me</a>}),
+       "java-tab-script url");
+ok(!gotcha(q{<span style="&#x61;&#x6e;&#x79;&#x3a;&#x20;&#x65;&#x78;&#x70;&#x72;&#x65;&#x73;&#x73;&#x69;&#x6f;(GOTCHA)&#x6e;&#x28;&#x77;&#x69;&#x6e;&#x64;&#x6f;&#x77;&#x2e;&#x6c;&#x6f;&#x63;&#x61;&#x74;&#x69;&#x6f;&#x6e;&#x3d;&#x27;&#x68;&#x74;&#x74;&#x70;&#x3a;&#x2f;&#x2f;&#x65;&#x78;&#x61;&#x6d;&#x70;&#x6c;&#x65;&#x2e;&#x6f;&#x72;&#x67;&#x2f;&#x27;&#x29;">foo</span>}),
+       "entity-encoded CSS script test");
+ok(!gotcha(q{<span style="&#97;&#110;&#121;&#58;&#32;&#101;&#120;&#112;&#114;&#101;&#115;&#115;&#105;&#111;&#110;(GOTCHA)&#40;&#119;&#105;&#110;&#100;&#111;&#119;&#46;&#108;&#111;&#99;&#97;&#116;&#105;&#111;&#110;&#61;&#39;&#104;&#116;&#116;&#112;&#58;&#47;&#47;&#101;&#120;&#97;&#109;&#112;&#108;&#101;&#46;&#111;&#114;&#103;&#47;&#39;&#41;">foo</span>}),
+       "another entity-encoded CSS script test");
+ok(!gotcha(q{<script>GOTCHA</script>}),
+       "script tag");
+ok(!gotcha(q{<span style="background: url(javascript:window.location=GOTCHA)">a</span>}),
+       "CSS script test");
+ok(gotcha(q{<p>javascript:alert('GOTCHA')</p>}),
+       "not javascript AFAIK (but perhaps some web browser would like to
+       be perverse and assume it is?)");
+ok(gotcha(q{<img src="javascript.png?GOTCHA">}), "not javascript");
+ok(gotcha(q{<a href="javascript.png?GOTCHA">foo</a>}), "not javascript");

diff --git a/t/javascript.mdwn b/t/javascript.mdwn
deleted file mode 100644 (file)
index f768d29..0000000
--- a/t/javascript.mdwn
+++ /dev/null
@@ -1,9 +0,0 @@
-<a href="javascript&#x3A;alert('GOTCHA')">click me</a>
-<a href="javascript:alert('GOTCHA')">click me</a>
-<a href="jscript:alert('GOTCHA')">click me</a>
-<a href="vbscript:alert('GOTCHA')">click me</a>
-<a href="java\tscript:alert('GOTCHA')">click me</a>
-<span style="&#x61;&#x6e;&#x79;&#x3a;&#x20;&#x65;&#x78;&#x70;&#x72;&#x65;&#x73;&#x73;&#x69;&#x6f;(GOTCHA)&#x6e;&#x28;&#x77;&#x69;&#x6e;&#x64;&#x6f;&#x77;&#x2e;&#x6c;&#x6f;&#x63;&#x61;&#x74;&#x69;&#x6f;&#x6e;&#x3d;&#x27;&#x68;&#x74;&#x74;&#x70;&#x3a;&#x2f;&#x2f;&#x65;&#x78;&#x61;&#x6d;&#x70;&#x6c;&#x65;&#x2e;&#x6f;&#x72;&#x67;&#x2f;&#x27;&#x29;">entity-encoded CSS script test</span>
-<span style="&#97;&#110;&#121;&#58;&#32;&#101;&#120;&#112;&#114;&#101;&#115;&#115;&#105;&#111;&#110;(GOTCHA)&#40;&#119;&#105;&#110;&#100;&#111;&#119;&#46;&#108;&#111;&#99;&#97;&#116;&#105;&#111;&#110;&#61;&#39;&#104;&#116;&#116;&#112;&#58;&#47;&#47;&#101;&#120;&#97;&#109;&#112;&#108;&#101;&#46;&#111;&#114;&#103;&#47;&#39;&#41;">entity-encoded CSS script test</span>
-<script>GOTCHA</script>
-<span style="background: url(javascript:window.location=GOTCHA)">CSS script test</span>