1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
|
#ifndef unicode_hh_INCLUDED
#define unicode_hh_INCLUDED
#include <cwctype>
#include <cwchar>
#include "array_view.hh"
#include "ranges.hh"
#include "units.hh"
namespace Kakoune
{
using Codepoint = char32_t;
inline bool is_eol(Codepoint c) noexcept
{
return c == '\n';
}
inline bool is_horizontal_blank(Codepoint c) noexcept
{
return c == ' ' or c == '\t';
}
inline bool is_blank(Codepoint c) noexcept
{
return c == ' ' or c == '\t' or c == '\n';
}
enum WordType { Word, WORD };
template<WordType word_type = Word>
inline bool is_word(Codepoint c, ConstArrayView<Codepoint> extra_word_chars = {'_'}) noexcept
{
return iswalnum((wchar_t)c) or contains(extra_word_chars, c);
}
template<>
inline bool is_word<WORD>(Codepoint c, ConstArrayView<Codepoint>) noexcept
{
return not is_blank(c);
}
inline bool is_punctuation(Codepoint c, ConstArrayView<Codepoint> extra_word_chars = {'_'}) noexcept
{
return not (is_word(c, extra_word_chars) or is_blank(c));
}
inline bool is_basic_alpha(Codepoint c) noexcept
{
return (c >= 'a' and c <= 'z') or (c >= 'A' and c <= 'Z');
}
inline bool is_basic_digit(Codepoint c) noexcept
{
return c >= '0' and c <= '9';
}
inline bool is_identifier(Codepoint c) noexcept
{
return is_basic_alpha(c) or is_basic_digit(c) or
c == '_' or c == '-';
}
inline ColumnCount codepoint_width(Codepoint c) noexcept
{
if (c == '\n')
return 1;
const auto width = wcwidth((wchar_t)c);
return width >= 0 ? width : 1;
}
enum class CharCategories
{
Blank,
EndOfLine,
Word,
Punctuation,
};
template<WordType word_type = Word>
inline CharCategories categorize(Codepoint c, ConstArrayView<Codepoint> extra_word_chars) noexcept
{
if (is_eol(c))
return CharCategories::EndOfLine;
if (is_horizontal_blank(c))
return CharCategories::Blank;
if (word_type == WORD or is_word(c, extra_word_chars))
return CharCategories::Word;
return CharCategories::Punctuation;
}
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 bool is_lower(Codepoint cp) noexcept { return iswlower((wchar_t)cp); }
inline bool is_upper(Codepoint cp) noexcept { return iswupper((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; }
inline bool is_lower(char c) noexcept { return c >= 'a' and c <= 'z'; }
inline bool is_upper(char c) noexcept { return c >= 'A' and c <= 'Z'; }
}
#endif // unicode_hh_INCLUDED
|
