Index: source/data/mappings/euc-kr-html.ucm |
diff --git a/source/data/mappings/euc-kr-html.ucm b/source/data/mappings/euc-kr-html.ucm |
index 247e934bae75328bc633c48c3b32d728209eccf1..34272a45898dd8e58658891f19182bd0d39686ca 100644 |
--- a/source/data/mappings/euc-kr-html.ucm |
+++ b/source/data/mappings/euc-kr-html.ucm |
@@ -14,8 +14,12 @@ |
<subchar> \x3F |
<icu:charsetFamily> "ASCII" |
-<icu:state> 0-80, 81-fe:1, ff |
+# 81-fe in states 2 and 3 can be tigher and a1-fe, but |
+# to be compliant to HTML5 spec, it should be 81-fe. |
+<icu:state> 0-7f, 81-c5:1, c6:2, c7-fe:3 |
<icu:state> 41-5a, 61-7a, 81-fe |
+<icu:state> 41-52, 81-fe |
+<icu:state> 81-fe |
CHARMAP |
<U0000> \x00 |0 |