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
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
use is_macro::Is;
use itertools::Itertools;
use serde::{Deserialize, Serialize};

use crate::span::Span;

#[derive(Debug, Clone, Copy, Serialize, Deserialize, PartialEq, Default)]
pub struct Token {
    pub span: Span,
    pub kind: TokenKind,
}

impl Token {
    /// Convert to an allocated [`FatToken`].
    pub fn to_fat(&self, source: &[char]) -> FatToken {
        let content = self.span.get_content(source).to_vec();

        FatToken {
            content,
            kind: self.kind,
        }
    }
}

/// A [`Token`] that holds its content as a fat [`Vec<char>`] rather than as a [`Span`].
#[derive(Debug, Clone, Serialize, Deserialize, PartialEq, PartialOrd)]
pub struct FatToken {
    pub content: Vec<char>,
    pub kind: TokenKind,
}

#[derive(Debug, Is, Clone, Copy, Serialize, Deserialize, PartialEq, Default, PartialOrd)]
#[serde(tag = "kind", content = "value")]
pub enum TokenKind {
    #[default]
    Word,
    Punctuation(Punctuation),
    Number(f64),
    /// A sequence of " " spaces.
    Space(usize),
    /// A sequence of "\n" newlines
    Newline(usize),
    /// A special token used for things like inline code blocks that should be ignored by all
    /// linters.
    Unlintable,
}

impl TokenKind {
    pub fn as_mut_quote(&mut self) -> Option<&mut Quote> {
        self.as_mut_punctuation()?.as_mut_quote()
    }

    pub fn as_quote(&self) -> Option<&Quote> {
        self.as_punctuation()?.as_quote()
    }

    pub fn is_apostrophe(&self) -> bool {
        matches!(self, TokenKind::Punctuation(Punctuation::Apostrophe))
    }

    /// Checks whether the token is whitespace.
    pub fn is_whitespace(&self) -> bool {
        match self {
            TokenKind::Space(_) => true,
            TokenKind::Newline(_) => true,
            _ => false,
        }
    }
}

#[derive(Debug, Is, Clone, Copy, Serialize, Deserialize, PartialEq, Eq, PartialOrd)]
#[serde(tag = "kind")]
pub enum Punctuation {
    /// `…`
    Ellipsis,
    /// `–`
    EnDash,
    /// `—`
    EmDash,
    /// `&`
    Ampersand,
    /// `.`
    Period,
    /// `!`
    Bang,
    /// `?`
    Question,
    /// `:`
    Colon,
    /// ``;``
    Semicolon,
    /// `"`
    Quote(Quote),
    /// `,`
    Comma,
    /// `-`
    Hyphen,
    /// `[`
    OpenSquare,
    /// `]`
    CloseSquare,
    /// `(`
    OpenRound,
    /// `)`
    CloseRound,
    /// `"`
    Hash,
    /// `'`
    Apostrophe,
    /// `%`
    Percent,
    /// `/`
    ForwardSlash,
    /// `\`
    Backslash,
    /// `<`
    LessThan,
    /// `>`
    GreaterThan,
    /// `=`
    Equal,
    /// `*`
    Star,
    /// `~`
    Tilde,
    /// `@`
    At,
}

#[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Deserialize, PartialOrd)]
pub struct Quote {
    /// The location of the matching quote, if it exists.
    pub twin_loc: Option<usize>,
}

pub trait TokenStringExt {
    fn first_word(&self) -> Option<Token>;
    /// Grabs the first word in the sentence.
    /// Will also return [`None`] if there is an unlintable token in the position of the first
    /// word.
    fn first_sentence_word(&self) -> Option<Token>;
    /// Grabs the first token that isn't whitespace from the token string.
    fn first_non_whitespace(&self) -> Option<Token>;
    fn iter_word_indices(&self) -> impl Iterator<Item = usize> + '_;
    fn iter_words(&self) -> impl Iterator<Item = &Token> + '_;
    fn iter_space_indices(&self) -> impl Iterator<Item = usize> + '_;
    fn iter_spaces(&self) -> impl Iterator<Item = &Token> + '_;
    fn iter_apostrophe_indices(&self) -> impl Iterator<Item = usize> + '_;
    fn iter_apostrophes(&self) -> impl Iterator<Item = &Token> + '_;
    /// Grab the span that represents the beginning of the first element and the end of the last
    /// element.
    fn span(&self) -> Option<Span>;
}

impl TokenStringExt for [Token] {
    fn first_word(&self) -> Option<Token> {
        self.iter().find(|v| v.kind.is_word()).copied()
    }

    fn first_non_whitespace(&self) -> Option<Token> {
        self.iter().find(|t| !t.kind.is_whitespace()).copied()
    }

    fn first_sentence_word(&self) -> Option<Token> {
        let (w_idx, word) = self.iter().find_position(|v| v.kind.is_word())?;

        let Some(u_idx) = self.iter().position(|v| v.kind.is_unlintable()) else {
            return Some(*word);
        };

        if w_idx < u_idx {
            Some(*word)
        } else {
            None
        }
    }

    fn iter_word_indices(&self) -> impl Iterator<Item = usize> + '_ {
        self.iter()
            .enumerate()
            .filter(|(_, t)| t.kind.is_word())
            .map(|(i, _)| i)
    }

    fn iter_words(&self) -> impl Iterator<Item = &Token> + '_ {
        self.iter_word_indices().map(|i| &self[i])
    }

    fn iter_space_indices(&self) -> impl Iterator<Item = usize> + '_ {
        self.iter()
            .enumerate()
            .filter(|(_, t)| t.kind.is_space())
            .map(|(i, _)| i)
    }

    fn iter_spaces(&self) -> impl Iterator<Item = &Token> + '_ {
        self.iter_space_indices().map(|i| &self[i])
    }

    fn iter_apostrophe_indices(&self) -> impl Iterator<Item = usize> + '_ {
        self.iter()
            .enumerate()
            .filter(|(_, t)| t.kind.is_apostrophe())
            .map(|(i, _)| i)
    }

    fn iter_apostrophes(&self) -> impl Iterator<Item = &Token> + '_ {
        self.iter_apostrophe_indices().map(|i| &self[i])
    }

    fn span(&self) -> Option<Span> {
        Some(Span::new(self.first()?.span.start, self.last()?.span.end))
    }
}