py: Small comments, name changes, use of machine_int_t.

py/builtin.c

@@ -173,7 +173,7 @@ MP_DEFINE_CONST_FUN_OBJ_1(mp_builtin_callable_obj, mp_builtin_callable);
 
 STATIC mp_obj_t mp_builtin_chr(mp_obj_t o_in) {
     #if MICROPY_PY_BUILTINS_STR_UNICODE
-    int c = mp_obj_get_int(o_in);
+    machine_int_t c = mp_obj_get_int(o_in);
     char str[4];
     int len = 0;
     if (c < 0x80) {
@@ -198,7 +198,7 @@ STATIC mp_obj_t mp_builtin_chr(mp_obj_t o_in) {
     }
     return mp_obj_new_str(str, len, true);
     #else
-    int ord = mp_obj_get_int(o_in);
+    machine_int_t ord = mp_obj_get_int(o_in);
     if (0 <= ord && ord <= 0x10ffff) {
         char str[1] = {ord};
         return mp_obj_new_str(str, 1, true);

py/misc.h

@@ -100,7 +100,7 @@ bool unichar_isupper(unichar c);
 bool unichar_islower(unichar c);
 unichar unichar_tolower(unichar c);
 unichar unichar_toupper(unichar c);
-uint unichar_charlen(const char *str, uint len);
+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)
 
@@ -169,6 +169,7 @@ 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;

py/objstr.c

@@ -251,7 +251,7 @@ STATIC const byte *find_subbytes(const byte *haystack, machine_uint_t hlen, cons
     return NULL;
 }
 
-mp_obj_t str_binary_op(int op, mp_obj_t lhs_in, mp_obj_t rhs_in) {
+mp_obj_t mp_obj_str_binary_op(int op, mp_obj_t lhs_in, mp_obj_t rhs_in) {
     GET_STR_DATA_LEN(lhs_in, lhs_data, lhs_len);
     mp_obj_type_t *lhs_type = mp_obj_get_type(lhs_in);
     mp_obj_type_t *rhs_type = mp_obj_get_type(rhs_in);
@@ -566,7 +566,6 @@ STATIC mp_obj_t str_rsplit(uint n_args, const mp_obj_t *args) {
     return res;
 }
 
-
 STATIC mp_obj_t str_finder(uint n_args, const mp_obj_t *args, machine_int_t direction, bool is_index) {
     const mp_obj_type_t *self_type = mp_obj_get_type(args[0]);
     assert(2 <= n_args && n_args <= 4);
@@ -1610,7 +1609,7 @@ STATIC mp_obj_t str_encode(uint n_args, const mp_obj_t *args) {
 }
 #endif
 
-machine_int_t str_get_buffer(mp_obj_t self_in, mp_buffer_info_t *bufinfo, int flags) {
+machine_int_t mp_obj_str_get_buffer(mp_obj_t self_in, mp_buffer_info_t *bufinfo, int flags) {
     if (flags == MP_BUFFER_READ) {
         GET_STR_DATA_LEN(self_in, str_data, str_len);
         bufinfo->buf = (void*)str_data;
@@ -1701,10 +1700,10 @@ const mp_obj_type_t mp_type_str = {
     .name = MP_QSTR_str,
     .print = str_print,
     .make_new = str_make_new,
-    .binary_op = str_binary_op,
+    .binary_op = mp_obj_str_binary_op,
     .subscr = str_subscr,
     .getiter = mp_obj_new_str_iterator,
-    .buffer_p = { .get_buffer = str_get_buffer },
+    .buffer_p = { .get_buffer = mp_obj_str_get_buffer },
     .locals_dict = (mp_obj_t)&str_locals_dict,
 };
 #endif
@@ -1715,10 +1714,10 @@ const mp_obj_type_t mp_type_bytes = {
     .name = MP_QSTR_bytes,
     .print = str_print,
     .make_new = bytes_make_new,
-    .binary_op = str_binary_op,
+    .binary_op = mp_obj_str_binary_op,
     .subscr = str_subscr,
     .getiter = mp_obj_new_bytes_iterator,
-    .buffer_p = { .get_buffer = str_get_buffer },
+    .buffer_p = { .get_buffer = mp_obj_str_get_buffer },
     .locals_dict = (mp_obj_t)&str_locals_dict,
 };
 

py/objstr.h

@@ -54,8 +54,8 @@ typedef struct _mp_obj_str_t {
 mp_obj_t mp_obj_str_format(uint n_args, const mp_obj_t *args);
 mp_obj_t mp_obj_new_str_of_type(const mp_obj_type_t *type, const byte* data, uint len);
 
-mp_obj_t str_binary_op(int op, mp_obj_t lhs_in, mp_obj_t rhs_in);
-machine_int_t str_get_buffer(mp_obj_t self_in, mp_buffer_info_t *bufinfo, int flags);
+mp_obj_t mp_obj_str_binary_op(int op, mp_obj_t lhs_in, mp_obj_t rhs_in);
+machine_int_t mp_obj_str_get_buffer(mp_obj_t self_in, mp_buffer_info_t *bufinfo, int flags);
 
 const byte *str_index_to_ptr(const mp_obj_type_t *type, const byte *self_data, uint self_len,
                              mp_obj_t index, bool is_slice);

py/objstrunicode.c

@@ -106,7 +106,7 @@ STATIC mp_obj_t uni_unary_op(int op, mp_obj_t self_in) {
         case MP_UNARY_OP_BOOL:
             return MP_BOOL(str_len != 0);
         case MP_UNARY_OP_LEN:
-            return MP_OBJ_NEW_SMALL_INT(unichar_charlen((const char *)str_data, str_len));
+            return MP_OBJ_NEW_SMALL_INT((machine_int_t)unichar_charlen((const char *)str_data, str_len));
         default:
             return MP_OBJ_NULL; // op not supported
     }
@@ -311,10 +311,10 @@ const mp_obj_type_t mp_type_str = {
     .print = uni_print,
     .make_new = str_make_new,
     .unary_op = uni_unary_op,
-    .binary_op = str_binary_op,
+    .binary_op = mp_obj_str_binary_op,
     .subscr = str_subscr,
     .getiter = mp_obj_new_str_iterator,
-    .buffer_p = { .get_buffer = str_get_buffer },
+    .buffer_p = { .get_buffer = mp_obj_str_get_buffer },
     .locals_dict = (mp_obj_t)&str_locals_dict,
 };
 

py/unicode.c

@@ -107,6 +107,7 @@ machine_uint_t utf8_ptr_to_index(const char *s, const char *ptr) {
     return i;
 }
 
+// TODO: Rename to str_charlen; return machine_uint_t
 uint unichar_charlen(const char *str, uint len)
 {
 #if MICROPY_PY_BUILTINS_STR_UNICODE