UtfString is going really well. It can now parse Utf8, Utf16 (le,be), and

Utf32 (le,be).  The internal storage seems to be working fine, although we do
have a problem with random access, but at least we can tell which half of a
surrogate pair we're on, so we can always rapidly determine the entire code
point from any utf16 index that we're on.
The only optomization that I'm not doing yet is reading in entire 16bit or 32bit
words at a time and converting them from their byte order to native.  There are
a few potential issues with that, so we'll see.

I added a couple of testing datafiles and a test program, I'll delete them all
just as soon as it's verified to write correctly.

1 files changed, 42 insertions, 0 deletions

diff --git a/utf16.cpp b/utf16.cpp
new file mode 100644
index 0000000..eedb521
--- /dev/null
+++ b/utf16.cpp
@@ -0,0 +1,42 @@
+#include <stdio.h>
+#include <stdint.h>
+
+void bitprint( uint16_t u )
+{
+        for( int i = 15; i >= 0; i-- )
+                printf("%c", (u&(1<<i))?'1':'0');
+        printf("\n");
+}
+
+void bitprint( uint32_t u )
+{
+        for( int i = 31; i >= 0; i-- )
+                printf("%c", (u&(1<<i))?'1':'0');
+        printf("\n");
+}
+
+void utoutf16( uint32_t in, uint16_t &outHi, uint16_t &outLo )
+{
+        outHi = (((in-0x10000)>>10)&0x3FF)| 0xD800u;
+        outLo = ((in-0x10000)&0x3FF)| 0xDC00u;
+        printf("0x%X == 0x%X, 0x%X\n", in, outHi, outLo );
+}
+
+int32_t utf16tou( uint16_t hi, uint16_t lo )
+{
+        return (((uint32_t)hi&0x3FF)<<10 | lo&0x3FF)+0x10000;
+}
+
+int main()
+{
+        bitprint( 0xD800u );
+        bitprint( 0xDC00u );
+        uint16_t hi, lo;
+        utoutf16( 0x1D11E, hi, lo ); // Cat face with wry smile
+        utoutf16( 0x10FFFD, hi, lo ); // Cat face with wry smile
+        utoutf16( 0x1F63C, hi, lo ); // Cat face with wry smile
+        bitprint( hi );
+        bitprint( lo );
+        printf("0x%X\n", utf16tou( hi, lo ) );
+        return 0;
+}