Use C++11 char16_t for sal_Unicode

...in LIBO_INTERNAL_ONLY, __cplusplus, non-MSVC case.

It turns out that sal_Unicode happens to not be mangled into any symbols that
make up the stable URE interface, so (for LIBO_INTERNAL_ONLY, at least) we are
free to replace the typedef to sal_uInt16 with a typedef to any integral type
layout-compatible with that.  (sal_Unicode does appear in some symbols in sal's
PRIVATE_textenc.1 section, but that is private between the sal and sal_textenc
libraries, so changing those symbols does not require a change of SONAME.)
C++11 chart16_t is the obvious choice (and will ultimately allow using u"..."
to write literals of type array-of-sal_Unicode).  Reportedly, char16_t is
supported since GCC 4.4 and Clang 2.9 but will only be available in MSVC 2015.

For plain C, we continue to use sal_uInt16.  We could theoretically use C11
char16_t from <uchar.h>, but at least the Mac OS X 10.11 SDK still does not
offer that C11 header.

For MSVC, we continue to use wchar_t (which is actually unsigned short, due to
/Zc:wchar_t-) for now.  Potential options there include dropping /Zc:wchar_t-
and using true wchar_t, or using C++11 char16_t once support for MSVC 2013 is
dropped.

Some code needed to be adapted that was written in a way assuming that
sal_Unicode is unsigned short (which indicates that changing sal_Unicode for
non-LIBO_INTERNAL_ONLY would be an ABI change).  OUStringBuffer::append can now
differentiate between being called with sal_Unicode (to append a single
character) and erroneously being called with sal_uInt16 (intending to append a
number's textual representation, for which the sal_Int32 overload must be used
instead).  Bugs found are 379fe0409e7973b36210cffa3dd1dfd4032f0ecc "Assume that
this code wants to append a number, not a character" and
dc148335a6a438848325f24c49198fba81043279 "Assume this wants to append the
numerical representation."

The GDB support for pretty-printing of sal_Unicode-related data in
solenv/gdb/libreoffice/sal.py can presumably be simplified now.

Change-Id: I445b3a80e65b7cb004d9e08b38bdc9ee93bc9401
Reviewed-on: https://gerrit.libreoffice.org/20036
Reviewed-by: Stephan Bergmann <sbergman@redhat.com>
Tested-by: Stephan Bergmann <sbergman@redhat.com>

4 files changed, 78 insertions, 0 deletions

diff --git a/cppu/qa/test_unotype.cxx b/cppu/qa/test_unotype.cxx
index 27323371e28b..338c6f77103f 100644
--- a/cppu/qa/test_unotype.cxx
+++ b/cppu/qa/test_unotype.cxx
@@ -233,7 +233,11 @@ void Test::testUnoType() {
 }
 
 void Test::testGetTypeFavourUnsigned() {
+#if defined SAL_W32 && !defined __MINGW32__ // cf. sal/types.h sal_Unicode
     CPPUNIT_ASSERT(typeid(sal_Unicode) == typeid(sal_uInt16));
+#else
+    CPPUNIT_ASSERT(typeid(sal_Unicode) != typeid(sal_uInt16));
+#endif
     CPPUNIT_ASSERT_EQUAL(
         cppu::getTypeFavourUnsigned(static_cast<cppu::UnoVoidType *>(nullptr)),
         cppu::UnoType<cppu::UnoVoidType>::get());
@@ -277,9 +281,15 @@ void Test::testGetTypeFavourUnsigned() {
     CPPUNIT_ASSERT_EQUAL(
         cppu::getTypeFavourUnsigned(static_cast<cppu::UnoCharType *>(nullptr)),
         cppu::UnoType<cppu::UnoCharType>::get());
+#if defined SAL_W32 && !defined __MINGW32__ // cf. sal/types.h sal_Unicode
     CPPUNIT_ASSERT_EQUAL(
         cppu::getTypeFavourUnsigned(static_cast<sal_Unicode *>(nullptr)),
         cppu::UnoType<cppu::UnoUnsignedShortType>::get());
+#else
+    CPPUNIT_ASSERT_EQUAL(
+        cppu::getTypeFavourUnsigned(static_cast<sal_Unicode *>(nullptr)),
+        cppu::UnoType<cppu::UnoCharType>::get());
+#endif
     CPPUNIT_ASSERT_EQUAL(
         cppu::getTypeFavourUnsigned(static_cast<OUString *>(nullptr)),
         cppu::UnoType<OUString>::get());
@@ -316,6 +326,7 @@ void Test::testGetTypeFavourUnsigned() {
         cppu::UnoType<
             cppu::UnoSequenceType<
                 cppu::UnoSequenceType<cppu::UnoUnsignedShortType>>>::get());
+#if defined SAL_W32 && !defined __MINGW32__ // cf. sal/types.h sal_Unicode
     CPPUNIT_ASSERT_EQUAL(
         cppu::getTypeFavourUnsigned(
             static_cast<css::uno::Sequence<sal_Unicode> *>(nullptr)),
@@ -329,6 +340,20 @@ void Test::testGetTypeFavourUnsigned() {
         cppu::UnoType<
             cppu::UnoSequenceType<
                 cppu::UnoSequenceType<cppu::UnoUnsignedShortType>>>::get());
+#else
+    CPPUNIT_ASSERT_EQUAL(
+        cppu::getTypeFavourUnsigned(
+            static_cast<css::uno::Sequence<sal_Unicode> *>(nullptr)),
+        cppu::UnoType<cppu::UnoSequenceType<cppu::UnoCharType>>::get());
+    CPPUNIT_ASSERT_EQUAL(
+        cppu::getTypeFavourUnsigned(
+            static_cast<
+                css::uno::Sequence<
+                    css::uno::Sequence<sal_Unicode>> *>(nullptr)),
+        cppu::UnoType<
+            cppu::UnoSequenceType<
+                cppu::UnoSequenceType<cppu::UnoCharType>>>::get());
+#endif
     CPPUNIT_ASSERT_EQUAL(
         cppu::getTypeFavourUnsigned(
             static_cast<css::uno::TypeClass *>(nullptr)),
@@ -399,7 +424,11 @@ void Test::testGetTypeFavourUnsigned() {
 }
 
 void Test::testGetTypeFavourChar() {
+#if defined SAL_W32 && !defined __MINGW32__ // cf. sal/types.h sal_Unicode
     CPPUNIT_ASSERT(typeid(sal_Unicode) == typeid(sal_uInt16));
+#else
+    CPPUNIT_ASSERT(typeid(sal_Unicode) != typeid(sal_uInt16));
+#endif
     CPPUNIT_ASSERT_EQUAL(
         cppu::getTypeFavourChar(static_cast<cppu::UnoVoidType *>(nullptr)),
         cppu::UnoType<cppu::UnoVoidType>::get());
@@ -419,9 +448,15 @@ void Test::testGetTypeFavourChar() {
         cppu::getTypeFavourChar(
             static_cast<cppu::UnoUnsignedShortType *>(nullptr)),
         cppu::UnoType<cppu::UnoUnsignedShortType>::get());
+#if defined SAL_W32 && !defined __MINGW32__ // cf. sal/types.h sal_Unicode
     CPPUNIT_ASSERT_EQUAL(
         cppu::getTypeFavourChar(static_cast<sal_uInt16 *>(nullptr)),
         cppu::UnoType<cppu::UnoCharType>::get());
+#else
+    CPPUNIT_ASSERT_EQUAL(
+        cppu::getTypeFavourChar(static_cast<sal_uInt16 *>(nullptr)),
+        cppu::UnoType<cppu::UnoUnsignedShortType>::get());
+#endif
     CPPUNIT_ASSERT_EQUAL(
         cppu::getTypeFavourChar(static_cast<sal_Int32 *>(nullptr)),
         cppu::UnoType<sal_Int32>::get());
@@ -461,10 +496,18 @@ void Test::testGetTypeFavourChar() {
                 cppu::UnoSequenceType<cppu::UnoUnsignedShortType> *>(nullptr)),
         cppu::UnoType<
             cppu::UnoSequenceType<cppu::UnoUnsignedShortType>>::get());
+#if defined SAL_W32 && !defined __MINGW32__ // cf. sal/types.h sal_Unicode
     CPPUNIT_ASSERT_EQUAL(
         cppu::getTypeFavourChar(
             static_cast<css::uno::Sequence<sal_uInt16> *>(nullptr)),
         cppu::UnoType<cppu::UnoSequenceType<cppu::UnoCharType>>::get());
+#else
+    CPPUNIT_ASSERT_EQUAL(
+        cppu::getTypeFavourChar(
+            static_cast<css::uno::Sequence<sal_uInt16> *>(nullptr)),
+        cppu::UnoType<
+            cppu::UnoSequenceType<cppu::UnoUnsignedShortType>>::get());
+#endif
     CPPUNIT_ASSERT_EQUAL(
         cppu::getTypeFavourChar(
             static_cast<
@@ -474,6 +517,7 @@ void Test::testGetTypeFavourChar() {
         cppu::UnoType<
             cppu::UnoSequenceType<
                 cppu::UnoSequenceType<cppu::UnoUnsignedShortType>>>::get());
+#if defined SAL_W32 && !defined __MINGW32__ // cf. sal/types.h sal_Unicode
     CPPUNIT_ASSERT_EQUAL(
         cppu::getTypeFavourChar(
             static_cast<
@@ -481,6 +525,15 @@ void Test::testGetTypeFavourChar() {
         cppu::UnoType<
             cppu::UnoSequenceType<
                 cppu::UnoSequenceType<cppu::UnoCharType>>>::get());
+#else
+    CPPUNIT_ASSERT_EQUAL(
+        cppu::getTypeFavourChar(
+            static_cast<
+                css::uno::Sequence<css::uno::Sequence<sal_uInt16>> *>(nullptr)),
+        cppu::UnoType<
+            cppu::UnoSequenceType<
+                cppu::UnoSequenceType<cppu::UnoUnsignedShortType>>>::get());
+#endif
     CPPUNIT_ASSERT_EQUAL(
         cppu::getTypeFavourChar(
             static_cast<css::uno::Sequence<sal_Unicode> *>(nullptr)),
diff --git a/include/cppu/unotype.hxx b/include/cppu/unotype.hxx
index 2ab7681e61f5..a59445043735 100644
--- a/include/cppu/unotype.hxx
+++ b/include/cppu/unotype.hxx
@@ -149,6 +149,14 @@ cppu_detail_getUnoType(
         ::typelib_TypeClass_UNSIGNED_SHORT);
 }
 
+#if LIBO_INTERNAL_ONLY && (!defined SAL_W32 || defined __MINGW32__)
+    // cf. sal/types.h sal_Unicode
+inline css::uno::Type const &
+cppu_detail_getUnoType(SAL_UNUSED_PARAMETER sal_uInt16 const *) {
+    return cppu::detail::getTypeFromTypeClass(typelib_TypeClass_UNSIGNED_SHORT);
+}
+#endif
+
 inline css::uno::Type const &
 cppu_detail_getUnoType(SAL_UNUSED_PARAMETER ::sal_Int32 const *) {
     return ::cppu::detail::getTypeFromTypeClass(::typelib_TypeClass_LONG);
@@ -186,6 +194,14 @@ cppu_detail_getUnoType(SAL_UNUSED_PARAMETER ::cppu::UnoCharType const *) {
     return ::cppu::detail::getTypeFromTypeClass(::typelib_TypeClass_CHAR);
 }
 
+#if LIBO_INTERNAL_ONLY && (!defined SAL_W32 || defined __MINGW32__)
+    // cf. sal/types.h sal_Unicode
+inline css::uno::Type const &
+cppu_detail_getUnoType(SAL_UNUSED_PARAMETER sal_Unicode const *) {
+    return cppu::detail::getTypeFromTypeClass(typelib_TypeClass_CHAR);
+}
+#endif
+
 inline css::uno::Type const &
 cppu_detail_getUnoType(SAL_UNUSED_PARAMETER ::rtl::OUString const *) {
     return ::cppu::detail::getTypeFromTypeClass(::typelib_TypeClass_STRING);
diff --git a/include/rtl/ustrbuf.hxx b/include/rtl/ustrbuf.hxx
index ef2564da978b..f8dda00538a0 100644
--- a/include/rtl/ustrbuf.hxx
+++ b/include/rtl/ustrbuf.hxx
@@ -638,6 +638,11 @@ public:
         return append( &c, 1 );
     }
 
+#if LIBO_INTERNAL_ONLY && (!defined SAL_W32 || defined __MINGW32__)
+        // cf. sal/types.h sal_Unicode
+    void append(sal_uInt16) = delete;
+#endif
+
     /**
         Appends the string representation of the <code>sal_Int32</code>
         argument to this string buffer.
diff --git a/include/sal/types.h b/include/sal/types.h
index 3f999fc15e4e..9cd77f846767 100644
--- a/include/sal/types.h
+++ b/include/sal/types.h
@@ -149,8 +149,12 @@ typedef unsigned char sal_uChar;
     typedef wchar_t             sal_Unicode;
 #else
     #define SAL_UNICODE_NOTEQUAL_WCHAR_T
+#if LIBO_INTERNAL_ONLY && defined __cplusplus
+    typedef char16_t sal_Unicode;
+#else
     typedef sal_uInt16          sal_Unicode;
 #endif
+#endif
 
 typedef void *                   sal_Handle;