Merge branch 'unicode'

1 files changed, 17 insertions, 1 deletions

diff --git a/py/misc.h b/py/misc.h
index 3f62e3198f..bf63ce1354 100644
--- a/py/misc.h
+++ b/py/misc.h
@@ -100,7 +100,9 @@ bool unichar_isupper(unichar c);
 bool unichar_islower(unichar c);
 unichar unichar_tolower(unichar c);
 unichar unichar_toupper(unichar c);
-#define unichar_charlen(s, bytelen) (bytelen)
+uint unichar_charlen(const char *str, uint len); // TODO this should return machine_uint_t
+#define UTF8_IS_NONASCII(ch) ((ch) & 0x80)
+#define UTF8_IS_CONT(ch) (((ch) & 0xC0) == 0x80)
 
 /** variable string *********************************************/
 
@@ -164,4 +166,18 @@ int DEBUG_printf(const char *fmt, ...);
 
 extern uint mp_verbose_flag;
 
+// This is useful for unicode handling. Some CPU archs has
+// special instructions for efficient implentation of this
+// function (e.g. CLZ on ARM).
+// NOTE: this function is unused at the moment
+#ifndef count_lead_ones
+static inline uint count_lead_ones(byte val) {
+    uint c = 0;
+    for (byte mask = 0x80; val & mask; mask >>= 1) {
+        c++;
+    }
+    return c;
+}
+#endif
+
 #endif // _INCLUDED_MINILIB_H