-#define DELETE_NATIVE 0x007F /* U+007F */
-#define LATIN_SMALL_LETTER_SHARP_S_NATIVE 0x00DF /* U+00DF */
-#define LATIN_SMALL_LETTER_A_WITH_RING_ABOVE_NATIVE 0x00E5 /* U+00E5 */
-#define LATIN_CAPITAL_LETTER_A_WITH_RING_ABOVE_NATIVE 0x00C5 /* U+00C5 */
-#define LATIN_SMALL_LETTER_Y_WITH_DIAERESIS_NATIVE 0x00FF /* U+00FF */
-#define MICRO_SIGN_NATIVE 0x00B5 /* U+00B5 */
+#define LATIN_SMALL_LIGATURE_LONG_S_T_UTF8 "\xEF\xAC\x85" /* U+FB05 */
+#define LATIN_SMALL_LIGATURE_ST_UTF8 "\xEF\xAC\x86" /* U+FB06 */
+
+#define HYPHEN_UTF8 "\xE2\x80\x90" /* U+2010 */
+#define FIRST_SURROGATE_UTF8_FIRST_BYTE 0xED /* U+D800 */
+#define BOM_UTF8_FIRST_BYTE 0xEF /* U+FEFF */
+#define BOM_UTF8_TAIL "\xBB\xBF" /* U+FEFF */
+
+#define DEL_NATIVE 0x7F /* U+007F */
+#define CR_NATIVE 0x0D /* U+000D */
+#define LF_NATIVE 0x0A /* U+000A */
+#define LATIN_SMALL_LETTER_SHARP_S_NATIVE 0xDF /* U+00DF */
+#define LATIN_SMALL_LETTER_A_WITH_RING_ABOVE_NATIVE 0xE5 /* U+00E5 */
+#define LATIN_CAPITAL_LETTER_A_WITH_RING_ABOVE_NATIVE 0xC5 /* U+00C5 */
+#define LATIN_SMALL_LETTER_Y_WITH_DIAERESIS_NATIVE 0xFF /* U+00FF */
+#define MICRO_SIGN_NATIVE 0xB5 /* U+00B5 */