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

use logos::*;
use crate::RantString;

#[derive(Logos, Debug, PartialEq)]
pub enum RantToken {
  #[error]
  #[regex(r"[\w\-_]+")]
  Fragment,
  
  #[token("{")]
  LeftBrace,
  
  #[token("|")]
  Pipe,
  
  #[token("}")]
  RightBrace,
  
  #[token("[")]
  LeftBracket,
  
  #[token("]")]
  RightBracket,

  #[token("(")]
  LeftParen,

  #[token(")")]
  RightParen,

  #[token("<>")]
  EmptyValue,

  #[token("<")]
  LeftAngle,

  #[token(">")]
  RightAngle,
  
  #[token(":")]
  Colon,
  
  #[token("*")]
  Star,
  
  #[token("+")]
  Plus,

  #[token("=")]
  Equals,

  #[token("!")]
  Bang,
  
  #[token("?")]
  Question,
  
  #[token(";")]
  Semi,
  
  #[token("@")]
  At,
  
  #[token("/")]
  Slash,

  #[token("^")]
  Caret,
  
  #[token("$")]
  Dollar,
  
  #[token("'")]
  Hint,
  
  #[token("_")]
  Sink,
  
  #[token("true")]
  True,
  
  #[token("false")]
  False,
  
  #[regex(r"\s+", filter_bs, priority = 2)]
  Whitespace,
  
  #[regex(r"[\r\n]+\s*|\s*[\r\n]+", logos::skip, priority = 3)]
  Blackspace,
  
  #[regex(r"\-?[0-9]+", parse_integer, priority = 2)]
  Integer(i64),
  
  #[regex(r"\-?[0-9]+\.[0-9]+", parse_float, priority = 3)]
  Float(f64),
  
  #[regex(r"\s*##([^#]|#[^#])*(##\s*)?", logos::skip, priority = 6)]
  #[regex(r"\s*#([^#][^\r\n]*)?\n?", logos::skip, priority = 5)]
  Comment,
  
  #[regex(r"\\\S", parse_escape, priority = 10)]
  #[regex(r"\\x[0-9a-fA-F][0-9a-fA-F]", parse_code_point_escape, priority = 7)]
  Escape(char),
  
  #[regex(r#""(""|[^"])*""#, parse_string_literal)]
  StringLiteral(RantString),
  
  #[regex(r#""(""|[^"])*"#)]
  UnterminatedStringLiteral,
}

fn parse_string_literal<'a>(lex: &mut Lexer<'a, RantToken>) -> Option<RantString> {
  let literal: String = lex.slice().to_owned();
  let literal_content = &literal[1..literal.len() - 1];
  let mut string_content = RantString::new();
  let mut prev_quote = false;
  for c in literal_content.chars() {
    match c {
      '"' => {
        if prev_quote {
          prev_quote = false;
          string_content.push('"');
        } else {
          prev_quote = true;
        }
      },
      c => {
        string_content.push(c)
      }
    }
  }
  Some(string_content)
}

/// Filter function for whitespace lexer rule to exclude whitespace at start of source

fn filter_bs<'a>(lex: &mut Lexer<'a, RantToken>) -> Filter<()> {
  if lex.span().start > 0 {
    return Filter::Emit(())
  }
  Filter::Skip
}

fn parse_escape<'a>(lex: &mut Lexer<'a, RantToken>) -> Option<char> {
  let slice = lex.slice();
  Some(match slice.chars().nth(1)? {
    'r' => '\r',
    'n' => '\n',
    't' => '\t',
    '0' => '\0',
    's' => ' ',
    other => other
  })
}

fn parse_code_point_escape<'a>(lex: &mut Lexer<'a, RantToken>) -> Option<char> {
  let codepoint = u8::from_str_radix(&lex.slice()[2..], 16).ok()?;
  Some(codepoint as char)
}

fn parse_float<'a>(lex: &mut Lexer<'a, RantToken>) -> Option<f64> {
  let slice = lex.slice();
  let n = slice.parse().ok()?;
  Some(n)
}

fn parse_integer<'a>(lex: &mut Lexer<'a, RantToken>) -> Option<i64> {
  let slice = lex.slice();
  let n = slice.parse().ok()?;
  Some(n)
}