unicode: String API is const byte*.
We still have that char vs byte dichotomy, but majority of string operations
now use byte.
diff --git a/py/lexer.c b/py/lexer.c
index 2699392..a65df54 100644
--- a/py/lexer.c
+++ b/py/lexer.c
@@ -83,8 +83,8 @@
void mp_token_show(const mp_token_t *tok) {
printf("(%d:%d) kind:%d str:%p len:%d", tok->src_line, tok->src_column, tok->kind, tok->str, tok->len);
if (tok->str != NULL && tok->len > 0) {
- const char *i = tok->str;
- const char *j = i + tok->len;
+ const byte *i = (const byte *)tok->str;
+ const byte *j = (const byte *)i + tok->len;
printf(" ");
while (i < j) {
unichar c = utf8_get_char(i);
diff --git a/py/misc.h b/py/misc.h
index fd54147..97e16c2 100644
--- a/py/misc.h
+++ b/py/misc.h
@@ -88,8 +88,8 @@
typedef int unichar; // TODO
-unichar utf8_get_char(const char *s);
-char *utf8_next_char(const char *s);
+unichar utf8_get_char(const byte *s);
+const byte *utf8_next_char(const byte *s);
bool unichar_isspace(unichar c);
bool unichar_isalpha(unichar c);
diff --git a/py/unicode.c b/py/unicode.c
index 131ddc8..c8faa57 100644
--- a/py/unicode.c
+++ b/py/unicode.c
@@ -65,12 +65,12 @@
AT_LO, AT_LO, AT_LO, AT_PR, AT_PR, AT_PR, AT_PR, 0
};
-unichar utf8_get_char(const char *s) {
+unichar utf8_get_char(const byte *s) {
return *s;
}
-char *utf8_next_char(const char *s) {
- return (char*)(s + 1);
+const byte *utf8_next_char(const byte *s) {
+ return s + 1;
}
bool unichar_isspace(unichar c) {