From 84a2490200458f5892e156a95dc2f51b9767b128 Mon Sep 17 00:00:00 2001
From: Lu Wang <coolwanglu@gmail.com>
Date: Sat, 4 May 2013 13:52:58 +0800
Subject: [PATCH] workaround of soft hyphen

---
 src/util/css_const.h.in |  2 +-
 src/util/unicode.cc     | 14 +++++++++++++-
 2 files changed, 14 insertions(+), 2 deletions(-)

diff --git a/src/util/css_const.h.in b/src/util/css_const.h.in
index a1803c7..1e9f1aa 100644
--- a/src/util/css_const.h.in
+++ b/src/util/css_const.h.in
@@ -1,4 +1,4 @@
-/* vim: filetype=cpp : */
+/* vim: set filetype=cpp : */
 /*
  * css_const.h
  *
diff --git a/src/util/unicode.cc b/src/util/unicode.cc
index 7e047b6..e7c96ee 100644
--- a/src/util/unicode.cc
+++ b/src/util/unicode.cc
@@ -17,7 +17,12 @@ using std::cerr;
 using std::endl;
 using std::ostream;
 
-/* Test legal for HTML */
+/* 
+ * Test legal for HTML 
+ * 
+ * A legal unicode character should be accepted by browsers, and displayed correctly.
+ * This function is not complete, just to be improved.
+ */
 bool isLegalUnicode(Unicode u)
 {
     /*
@@ -47,6 +52,13 @@ bool isLegalUnicode(Unicode u)
     if((u >= 127) && (u <= 160))
         return false;
 
+    /*
+     * 173, or 0xad, is the soft hyphen
+     * which can be ignored by the browser in the middle of a line
+     */
+    if(u == 173)
+        return false;
+
     if((u >= 0xd800) && (u <= 0xdfff))
         return false;