From 99f3bed1de69e4d3993d85674f96a9eef69073b3 Mon Sep 17 00:00:00 2001
From: John Mark Bell <jmb@netsurf-browser.org>
Date: Sat, 6 Sep 2008 23:51:50 +0000
Subject: Fixes for handling of CR followed immediately by multibyte sequences.
 Pedantic whitespace changes. More paranoia surrounding entity handling.

svn path=/trunk/hubbub/; revision=5266
---
 test/data/tokeniser2/INDEX           |  1 +
 test/data/tokeniser2/regression.test | 20 ++++++++++++++++++++
 2 files changed, 21 insertions(+)
 create mode 100644 test/data/tokeniser2/regression.test

(limited to 'test/data/tokeniser2')

diff --git a/test/data/tokeniser2/INDEX b/test/data/tokeniser2/INDEX
index 8c0bc41..49dc102 100644
--- a/test/data/tokeniser2/INDEX
+++ b/test/data/tokeniser2/INDEX
@@ -10,3 +10,4 @@ contentModelFlags.test	html5lib content model tests
 entities.test		html5lib entity tests
 escapeFlag.test		html5lib escape flag tests
 cdata.test		CDATA section tests
+regression.test		Regression tests
diff --git a/test/data/tokeniser2/regression.test b/test/data/tokeniser2/regression.test
new file mode 100644
index 0000000..ae3e66a
--- /dev/null
+++ b/test/data/tokeniser2/regression.test
@@ -0,0 +1,20 @@
+{"tests": [
+
+{"description":"CR in double-quoted attribute value",
+"input":"<foo bar=\"\r\u2022xyz\"",
+"output":[["StartTag", "foo", {"bar":"\n\u2022xyz"}]]},
+
+{"description":"CR in single-quoted attribute value",
+"input":"<foo bar='\r\u2022xyz'",
+"output":[["StartTag", "foo", {"bar":"\n\u2022xyz"}]]},
+
+{"description":"CR in comment",
+"input":"<!--\r\u2022xyz-->",
+"output":[["Comment", "\n\u2022xyz"]]},
+
+{"description":"CR in CDATA section",
+"processCDATA":true,
+"input":"<![CDATA[\r\u2022xyz]]>",
+"output":[["Character", "\n\u2022xyz"]]},
+
+]}
-- 
cgit v1.2.3