tdf#81129 Support reading non-BMP characters in HTML documents.

1. Allow character entity ( &#nnnn; ) to exceed 0xffff in HTMLParser::ScanText()
2. Return a character as sal_uInt32 ( utf32 ) instead of sal_Unicode ( utf16 )
   from SvParser::GetNextChar().

Conflicts:
	sw/qa/extras/htmlexport/htmlexport.cxx

Change-Id: Ida455040970fae800f0f11471b27f53461fb78e4
Reviewed-on: https://gerrit.libreoffice.org/21152
Tested-by: Jenkins <ci@libreoffice.org>
Reviewed-by: Mark Hung <marklh9@gmail.com>

1 files changed, 13 insertions, 0 deletions

diff --git a/include/rtl/character.hxx b/include/rtl/character.hxx
index a3d09b9b0df7..49f6803821de 100644
--- a/include/rtl/character.hxx
+++ b/include/rtl/character.hxx
@@ -222,6 +222,19 @@ sal_uInt32 const surrogatesLowLast = 0xDFFF;
 }
 /// @endcond
 
+/** Check if a codepoint is accessible via utf16 per RFC3629
+
+    @param code  A non-BMP Unicode code point.
+
+    @return  True if the code is a valid codepoint.
+
+    @since LibreOffice 5.2
+*/
+inline bool isValidCodePoint( sal_uInt32 code)
+{
+    return code <= 0x10FFFF;
+}
+
 /** Check for high surrogate.
 
     @param code  A Unicode code point.