kakoune/src/unicode.hh

88 lines
1.8 KiB
C++
Raw Normal View History

#ifndef unicode_hh_INCLUDED
#define unicode_hh_INCLUDED
#include <cwctype>
#include <cwchar>
#include <locale>
2016-11-29 00:53:50 +01:00
#include "units.hh"
namespace Kakoune
{
2015-04-29 14:51:15 +02:00
using Codepoint = char32_t;
inline bool is_eol(Codepoint c) noexcept
{
return c == '\n';
}
inline bool is_horizontal_blank(Codepoint c) noexcept
2013-11-17 23:54:26 +01:00
{
return c == ' ' or c == '\t';
}
inline bool is_blank(Codepoint c) noexcept
{
return c == ' ' or c == '\t' or c == '\n';
}
2013-12-14 15:49:10 +01:00
enum WordType { Word, WORD };
template<WordType word_type = Word>
inline bool is_word(Codepoint c) noexcept
2013-12-14 15:49:10 +01:00
{
return c == '_' or iswalnum((wchar_t)c);
2013-12-14 15:49:10 +01:00
}
template<>
inline bool is_word<WORD>(Codepoint c) noexcept
2013-12-14 15:49:10 +01:00
{
return not is_blank(c);
2013-12-14 15:49:10 +01:00
}
inline bool is_punctuation(Codepoint c) noexcept
2013-12-14 15:49:10 +01:00
{
return not (is_word(c) or is_blank(c));
2013-12-14 15:49:10 +01:00
}
inline bool is_basic_alpha(Codepoint c) noexcept
2015-11-15 14:24:39 +01:00
{
return (c >= 'a' and c <= 'z') or (c >= 'A' and c <= 'Z');
}
inline ColumnCount codepoint_width(Codepoint c) noexcept
{
2016-10-04 20:37:43 +02:00
return c == '\n' ? 1 : wcwidth((wchar_t)c);
}
2013-12-14 15:49:10 +01:00
enum class CharCategories
{
Blank,
EndOfLine,
Word,
Punctuation,
};
template<WordType word_type = Word>
inline CharCategories categorize(Codepoint c) noexcept
2013-12-14 15:49:10 +01:00
{
if (is_eol(c))
return CharCategories::EndOfLine;
if (is_horizontal_blank(c))
2013-12-14 15:49:10 +01:00
return CharCategories::Blank;
if (word_type == WORD or is_word(c))
return CharCategories::Word;
return CharCategories::Punctuation;
2013-12-14 15:49:10 +01:00
}
inline Codepoint to_lower(Codepoint cp) noexcept { return towlower((wchar_t)cp); }
inline Codepoint to_upper(Codepoint cp) noexcept { return towupper((wchar_t)cp); }
inline char to_lower(char c) noexcept { return c >= 'A' and c <= 'Z' ? c - 'A' + 'a' : c; }
inline char to_upper(char c) noexcept { return c >= 'a' and c <= 'z' ? c - 'a' + 'A' : c; }
}
#endif // unicode_hh_INCLUDED