diff options
Diffstat (limited to 'py/lexer.c')
| -rw-r--r-- | py/lexer.c | 36 |
1 files changed, 17 insertions, 19 deletions
diff --git a/py/lexer.c b/py/lexer.c index ac406bd46..39e9662f6 100644 --- a/py/lexer.c +++ b/py/lexer.c @@ -473,25 +473,23 @@ STATIC void parse_string_literal(mp_lexer_t *lex, bool is_raw, bool is_fstring) } } if (c != MP_LEXER_EOF) { - if (MICROPY_PY_BUILTINS_STR_UNICODE_DYNAMIC) { - if (c < 0x110000 && lex->tok_kind == MP_TOKEN_STRING) { - vstr_add_char(&lex->vstr, c); - } else if (c < 0x100 && lex->tok_kind == MP_TOKEN_BYTES) { - vstr_add_byte(&lex->vstr, c); - } else { - // unicode character out of range - // this raises a generic SyntaxError; could provide more info - lex->tok_kind = MP_TOKEN_INVALID; - } - } else { - // without unicode everything is just added as an 8-bit byte - if (c < 0x100) { - vstr_add_byte(&lex->vstr, c); - } else { - // 8-bit character out of range - // this raises a generic SyntaxError; could provide more info - lex->tok_kind = MP_TOKEN_INVALID; - } + #if MICROPY_PY_BUILTINS_STR_UNICODE + if (c < 0x110000 && lex->tok_kind == MP_TOKEN_STRING) { + // Valid unicode character in a str object. + vstr_add_char(&lex->vstr, c); + } else if (c < 0x100 && lex->tok_kind == MP_TOKEN_BYTES) { + // Valid byte in a bytes object. + vstr_add_byte(&lex->vstr, c); + } + #else + if (c < 0x100) { + // Without unicode everything is just added as an 8-bit byte. + vstr_add_byte(&lex->vstr, c); + } + #endif + else { + // Character out of range; this raises a generic SyntaxError. + lex->tok_kind = MP_TOKEN_INVALID; } } } else { |