New rtl::isUnicodeScalarValue, rtl::isSurrogate

There are apparently various places that want to check for a Unicode scalar
value rather than for a Unicode code point.  Changed those uses of
rtl::isUnicodeCodePoint where that was obvious.  (For changing
svtools/source/svrtf/svparser.cxx see 8e0fb74dc01927b60d8b868548ef8fe1d7a80ce3
"Revert 'svtools: HTML import: don't put lone surrogates in OUString'".)  Other
uses of rtl::isUnicodeCodePoint might also want to use rtl::isUnicodeScalarValue
instead.

As a side effect, this change also introduces rtl::isSurrogate, which is useful
in a few places as well.

Change-Id: I9245f4f98b83877145a4d392f0ddb7c5d824a535

1 files changed, 27 insertions, 0 deletions

diff --git a/include/rtl/character.hxx b/include/rtl/character.hxx
index b83121a4a6d4..ee26f4ae1f9a 100644
--- a/include/rtl/character.hxx
+++ b/include/rtl/character.hxx
@@ -335,6 +335,20 @@ sal_uInt32 const surrogatesLowLast = 0xDFFF;
 }
 /// @endcond
 
+/** Check for surrogate.
+
+    @param code  A Unicode code point.
+
+    @return  True if code is a surrogate code point (0xD800--0xDFFF).
+
+    @since LibreOffice 6.0
+*/
+inline bool isSurrogate(sal_uInt32 code) {
+    assert(isUnicodeCodePoint(code));
+    return code >= detail::surrogatesHighFirst
+        && code <= detail::surrogatesLowLast;
+}
+
 /** Check for high surrogate.
 
     @param code  A Unicode code point.
@@ -433,6 +447,19 @@ inline std::size_t splitSurrogates(sal_uInt32 code, sal_Unicode * output) {
     }
 }
 
+/** Check for Unicode scalar value.
+
+    @param code  An integer.
+
+    @return  True if code is a Unicode scalar value.
+
+    @since LibreOffice 6.0
+*/
+inline bool isUnicodeScalarValue(sal_uInt32 code)
+{
+    return isUnicodeCodePoint(code) && !isSurrogate(code);
+}
+
 }
 
 #endif