unicode_types 0.2.0

A mapping of all the unicode characters into convenience types (one enum per block of characters with one variant per character).
Documentation 
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
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186


/// An enum to represent all characters in the Ugaritic block.
#[derive(Debug, Clone, Copy, Hash, PartialEq, Eq)]
pub enum Ugaritic {
    /// \u{10380}: '𐎀'
    LetterAlpa,
    /// \u{10381}: '𐎁'
    LetterBeta,
    /// \u{10382}: '𐎂'
    LetterGamla,
    /// \u{10383}: '𐎃'
    LetterKha,
    /// \u{10384}: '𐎄'
    LetterDelta,
    /// \u{10385}: '𐎅'
    LetterHo,
    /// \u{10386}: '𐎆'
    LetterWo,
    /// \u{10387}: '𐎇'
    LetterZeta,
    /// \u{10388}: '𐎈'
    LetterHota,
    /// \u{10389}: '𐎉'
    LetterTet,
    /// \u{1038a}: '𐎊'
    LetterYod,
    /// \u{1038b}: '𐎋'
    LetterKaf,
    /// \u{1038c}: '𐎌'
    LetterShin,
    /// \u{1038d}: '𐎍'
    LetterLamda,
    /// \u{1038e}: '𐎎'
    LetterMem,
    /// \u{1038f}: '𐎏'
    LetterDhal,
    /// \u{10390}: '𐎐'
    LetterNun,
    /// \u{10391}: '𐎑'
    LetterZu,
    /// \u{10392}: '𐎒'
    LetterSamka,
    /// \u{10393}: '𐎓'
    LetterAin,
    /// \u{10394}: '𐎔'
    LetterPu,
    /// \u{10395}: '𐎕'
    LetterSade,
    /// \u{10396}: '𐎖'
    LetterQopa,
    /// \u{10397}: '𐎗'
    LetterRasha,
    /// \u{10398}: '𐎘'
    LetterThanna,
    /// \u{10399}: '𐎙'
    LetterGhain,
    /// \u{1039a}: '𐎚'
    LetterTo,
    /// \u{1039b}: '𐎛'
    LetterI,
    /// \u{1039c}: '𐎜'
    LetterU,
    /// \u{1039d}: '𐎝'
    LetterSsu,
}

impl Into<char> for Ugaritic {
    fn into(self) -> char {
        match self {
            Ugaritic::LetterAlpa => '𐎀',
            Ugaritic::LetterBeta => '𐎁',
            Ugaritic::LetterGamla => '𐎂',
            Ugaritic::LetterKha => '𐎃',
            Ugaritic::LetterDelta => '𐎄',
            Ugaritic::LetterHo => '𐎅',
            Ugaritic::LetterWo => '𐎆',
            Ugaritic::LetterZeta => '𐎇',
            Ugaritic::LetterHota => '𐎈',
            Ugaritic::LetterTet => '𐎉',
            Ugaritic::LetterYod => '𐎊',
            Ugaritic::LetterKaf => '𐎋',
            Ugaritic::LetterShin => '𐎌',
            Ugaritic::LetterLamda => '𐎍',
            Ugaritic::LetterMem => '𐎎',
            Ugaritic::LetterDhal => '𐎏',
            Ugaritic::LetterNun => '𐎐',
            Ugaritic::LetterZu => '𐎑',
            Ugaritic::LetterSamka => '𐎒',
            Ugaritic::LetterAin => '𐎓',
            Ugaritic::LetterPu => '𐎔',
            Ugaritic::LetterSade => '𐎕',
            Ugaritic::LetterQopa => '𐎖',
            Ugaritic::LetterRasha => '𐎗',
            Ugaritic::LetterThanna => '𐎘',
            Ugaritic::LetterGhain => '𐎙',
            Ugaritic::LetterTo => '𐎚',
            Ugaritic::LetterI => '𐎛',
            Ugaritic::LetterU => '𐎜',
            Ugaritic::LetterSsu => '𐎝',
        }
    }
}

impl std::convert::TryFrom<char> for Ugaritic {
    type Error = ();
    fn try_from(c: char) -> Result<Self, Self::Error> {
        match c {
            '𐎀' => Ok(Ugaritic::LetterAlpa),
            '𐎁' => Ok(Ugaritic::LetterBeta),
            '𐎂' => Ok(Ugaritic::LetterGamla),
            '𐎃' => Ok(Ugaritic::LetterKha),
            '𐎄' => Ok(Ugaritic::LetterDelta),
            '𐎅' => Ok(Ugaritic::LetterHo),
            '𐎆' => Ok(Ugaritic::LetterWo),
            '𐎇' => Ok(Ugaritic::LetterZeta),
            '𐎈' => Ok(Ugaritic::LetterHota),
            '𐎉' => Ok(Ugaritic::LetterTet),
            '𐎊' => Ok(Ugaritic::LetterYod),
            '𐎋' => Ok(Ugaritic::LetterKaf),
            '𐎌' => Ok(Ugaritic::LetterShin),
            '𐎍' => Ok(Ugaritic::LetterLamda),
            '𐎎' => Ok(Ugaritic::LetterMem),
            '𐎏' => Ok(Ugaritic::LetterDhal),
            '𐎐' => Ok(Ugaritic::LetterNun),
            '𐎑' => Ok(Ugaritic::LetterZu),
            '𐎒' => Ok(Ugaritic::LetterSamka),
            '𐎓' => Ok(Ugaritic::LetterAin),
            '𐎔' => Ok(Ugaritic::LetterPu),
            '𐎕' => Ok(Ugaritic::LetterSade),
            '𐎖' => Ok(Ugaritic::LetterQopa),
            '𐎗' => Ok(Ugaritic::LetterRasha),
            '𐎘' => Ok(Ugaritic::LetterThanna),
            '𐎙' => Ok(Ugaritic::LetterGhain),
            '𐎚' => Ok(Ugaritic::LetterTo),
            '𐎛' => Ok(Ugaritic::LetterI),
            '𐎜' => Ok(Ugaritic::LetterU),
            '𐎝' => Ok(Ugaritic::LetterSsu),
            _ => Err(()),
        }
    }
}

impl Into<u32> for Ugaritic {
    fn into(self) -> u32 {
        let c: char = self.into();
        let hex = c
            .escape_unicode()
            .to_string()
            .replace("\\u{", "")
            .replace("}", "");
        u32::from_str_radix(&hex, 16).unwrap()
    }
}

impl std::convert::TryFrom<u32> for Ugaritic {
    type Error = ();
    fn try_from(u: u32) -> Result<Self, Self::Error> {
        if let Ok(c) = char::try_from(u) {
            Self::try_from(c)
        } else {
            Err(())
        }
    }
}

impl Iterator for Ugaritic {
    type Item = Self;
    fn next(&mut self) -> Option<Self> {
        let index: u32 = (*self).into();
        use std::convert::TryFrom;
        Self::try_from(index + 1).ok()
    }
}

impl Ugaritic {
    /// The character with the lowest index in this unicode block
    pub fn new() -> Self {
        Ugaritic::LetterAlpa
    }

    /// The character's name, in sentence case
    pub fn name(&self) -> String {
        let s = std::format!("Ugaritic{:#?}", self);
        string_morph::to_sentence_case(&s)
    }
}