Avoid possible lexer truncation warnings

Instead of static_cast calls that convert int to char, literals of type
char are now used directly with the value encoded via escape sequence.

The benefits are:
- code without static_cast is much more compact and expresses intent
better
- fixed value truncation warning on some compilers (e.g. C4309 on Visual
Studio 2017)
This commit is contained in:
Jajauma's GitHub
2022-08-12 23:02:44 +03:00
parent c7627ff6a1
commit 72af7b48d3

View File

@@ -264,21 +264,20 @@ using lex_array_table = sequence<lex_array_table_open,
using lex_utf8_1byte = in_range<0x00, 0x7F>;
using lex_utf8_2byte = sequence<
in_range<static_cast<char>(0xC2), static_cast<char>(0xDF)>,
in_range<static_cast<char>(0x80), static_cast<char>(0xBF)>
in_range<'\xC2', '\xDF'>,
in_range<'\x80', '\xBF'>
>;
using lex_utf8_3byte = sequence<either<
sequence<character<static_cast<char>(0xE0)>, in_range<static_cast<char>(0xA0), static_cast<char>(0xBF)>>,
sequence<in_range <static_cast<char>(0xE1), static_cast<char>(0xEC)>, in_range<static_cast<char>(0x80), static_cast<char>(0xBF)>>,
sequence<character<static_cast<char>(0xED)>, in_range<static_cast<char>(0x80), static_cast<char>(0x9F)>>,
sequence<in_range <static_cast<char>(0xEE), static_cast<char>(0xEF)>, in_range<static_cast<char>(0x80), static_cast<char>(0xBF)>>
>, in_range<static_cast<char>(0x80), static_cast<char>(0xBF)>>;
sequence<character<'\xE0'>, in_range<'\xA0', '\xBF'>>,
sequence<in_range<'\xE1', '\xEC'>, in_range<'\x80', '\xBF'>>,
sequence<character<'\xED'>, in_range<'\x80', '\x9F'>>,
sequence<in_range<'\xEE', '\xEF'>, in_range<'\x80', '\xBF'>>
>, in_range<'\x80', '\xBF'>>;
using lex_utf8_4byte = sequence<either<
sequence<character<static_cast<char>(0xF0)>, in_range<static_cast<char>(0x90), static_cast<char>(0xBF)>>,
sequence<in_range <static_cast<char>(0xF1), static_cast<char>(0xF3)>, in_range<static_cast<char>(0x80), static_cast<char>(0xBF)>>,
sequence<character<static_cast<char>(0xF4)>, in_range<static_cast<char>(0x80), static_cast<char>(0x8F)>>
>, in_range<static_cast<char>(0x80), static_cast<char>(0xBF)>,
in_range<static_cast<char>(0x80), static_cast<char>(0xBF)>>;
sequence<character<'\xF0'>, in_range<'\x90', '\xBF'>>,
sequence<in_range<'\xF1', '\xF3'>, in_range<'\x80', '\xBF'>>,
sequence<character<'\xF4'>, in_range<'\x80', '\x8F'>>
>, in_range<'\x80', '\xBF'>, in_range<'\x80', '\xBF'>>;
using lex_utf8_code = either<
lex_utf8_1byte,
lex_utf8_2byte,