Lerking/micropython
1
0
Fork 0
mirror of https://github.com/micropython/micropython.git synced 2026-01-05 03:30:14 +01:00
Code Issues Actions 52 Packages Projects Releases Wiki Activity

py/objstr: Add check for valid UTF-8 when making a str from bytes.

Browse Source 
This patch adds a function utf8_check() to check for a valid UTF-8 encoded
string, and calls it when constructing a str from raw bytes.  The feature
is selectable at compile time via MICROPY_PY_BUILTINS_STR_UNICODE_CHECK and
is enabled if unicode is enabled.  It costs about 110 bytes on Thumb-2, 150
bytes on Xtensa and 170 bytes on x86-64.
This commit is contained in:
tll
2017-06-24 08:38:32 +08:00
committed by Damien George
parent 069fc48bf6
commit 68c28174d0
5 changed files with 58 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
py/objstr.c
View File

@@ -161,6 +161,11 @@ mp_obj_t mp_obj_str_make_new(const mp_obj_type_t *type, size_t n_args, size_t n_
if (str_hash == 0) {
str_hash = qstr_compute_hash(str_data, str_len);
}
#if MICROPY_PY_BUILTINS_STR_UNICODE_CHECK
if (!utf8_check(str_data, str_len)) {
mp_raise_msg(&mp_type_UnicodeError, NULL);
}
#endif
mp_obj_str_t *o = MP_OBJ_TO_PTR(mp_obj_new_str_of_type(type, NULL, str_len));
o->data = str_data;
o->hash = str_hash;
@@ -168,6 +173,11 @@ mp_obj_t mp_obj_str_make_new(const mp_obj_type_t *type, size_t n_args, size_t n_
} else {
mp_buffer_info_t bufinfo;
mp_get_buffer_raise(args[0], &bufinfo, MP_BUFFER_READ);
#if MICROPY_PY_BUILTINS_STR_UNICODE_CHECK
if (!utf8_check(bufinfo.buf, bufinfo.len)) {
mp_raise_msg(&mp_type_UnicodeError, NULL);
}
#endif
return mp_obj_new_str(bufinfo.buf, bufinfo.len, false);
}
}