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

/// This Enum lists the token types that are used by the Forth interpreter
#[derive(Debug)]
pub enum ForthToken<'a> {
    Number(i64),
    Command(&'a str),
    StringToken(&'a str),
    Colon,
    SemiColon,
    DropLineComment(&'a str),
    ParenthesizedRemark(&'a str),
}

pub struct ForthTokenizer<'a> {
    to_tokenize: &'a str,
}

// The `Iterator` trait only requires a method to be defined for the `next` element.
impl<'a> Iterator for ForthTokenizer<'a> {
    type Item = ForthToken<'a>;

    // The return type is `Option<T>`:
    //     * When the `Iterator` is finished, `None` is returned.
    //     * Otherwise, the next value is wrapped in `Some` and returned.
    fn next(&mut self) -> Option<ForthToken<'a>> {
        // We ignore whitespace
        self.to_tokenize = self.to_tokenize.trim_start();

        if let Some(c) = self.to_tokenize.chars().next() {
            return match c {
                '\\' => {
                    let (first, rest) = split_at_newline(self.to_tokenize);
                    self.to_tokenize = rest;
                    Some(ForthToken::DropLineComment(first))
                }
                ':' => {
                    self.to_tokenize = &self.to_tokenize[1..];
                    Some(ForthToken::Colon)
                }
                ';' => {
                    self.to_tokenize = &self.to_tokenize[1..];
                    Some(ForthToken::SemiColon)
                }
                '(' => {
                    let (first, rest) = split_at_token(self.to_tokenize, ')');
                    self.to_tokenize = rest;
                    Some(ForthToken::ParenthesizedRemark(first))
                }
                /* +++ CHECK THIS +++ We haven't implemented strings yet...
                                '"' => {
                                    let (first, rest) = split_at_token(&self.to_tokenize[1..], '"');
                                    self.to_tokenize = rest;
                                    Some(ForthToken::StringToken(first))
                                }
                */
                _ => {
                    let (start, rest) = split_at_ascii_whitespace(self.to_tokenize);
                    self.to_tokenize = rest;
                    Some(ForthToken::Command(start))
                }
            };
        } else {
            return None;
        }
    }
}

impl<'a> ForthTokenizer<'a> {
    pub fn new(to_tokenize: &'a str) -> ForthTokenizer<'a> {
        ForthTokenizer {
            to_tokenize: to_tokenize,
        }
    }
}

fn split_at_newline<'a>(to_split: &'a str) -> (&'a str, &'a str) {
    let mut line_iterator = to_split.splitn(2, &['\n', '\r'][..]);
    if let Some(first) = line_iterator.next() {
        if let Some(rest) = line_iterator.next() {
            return match rest.chars().next().unwrap() {
                '\n' => (first, &rest[1..]),
                _ => (first, rest),
            };
        } else {
            return (first, "");
        }
    } else {
        return ("", "");
    }
}

fn split_at_ascii_whitespace<'a>(to_split: &'a str) -> (&'a str, &'a str) {
    let mut line_iterator = to_split.splitn(2, |c: char| c.is_ascii_whitespace());
    if let Some(first) = line_iterator.next() {
        if let Some(rest) = line_iterator.next() {
            return match rest.chars().next().unwrap() {
                '\n' => (first, &rest[1..]),
                _ => (first, rest),
            };
        } else {
            return (first, "");
        }
    } else {
        return ("", "");
    }
}

fn split_at_token<'a>(to_split: &'a str, token: char) -> (&'a str, &'a str) {
    let mut line_iterator = to_split.splitn(2, token);
    if let Some(first) = line_iterator.next() {
        if let Some(rest) = line_iterator.next() {
            return match rest.chars().next().unwrap() {
                '\n' => (first, &rest[1..]),
                _ => (first, rest),
            };
        } else {
            return (first, "");
        }
    } else {
        return ("", "");
    }
}

#[cfg(test)]
mod tests {
    use super::*;

    #[test]
    fn test_split_at_newline_1() {
        assert_eq!(split_at_newline(""), ("", ""));
    }

    #[test]
    fn test_split_at_newline_2() {
        assert_eq!(split_at_newline("abc"), ("abc", ""));
    }

    #[test]
    fn test_split_at_newline_3() {
        assert_eq!(split_at_newline("abc\r\ndef"), ("abc", "def"));
    }

    #[test]
    fn test_split_at_newline_4() {
        assert_eq!(split_at_newline("abc\ndef"), ("abc", "def"));
        assert_eq!(split_at_newline(""), ("", ""));
    }
    #[test]
    fn test_split_at_newline_5() {
        assert_eq!(
            split_at_newline("abc\r\ndef\r\nghi\r\njkl"),
            ("abc", "def\r\nghi\r\njkl")
        );
    }
    #[test]
    fn test_split_at_newline_6() {
        assert_eq!(
            split_at_newline("abc\ndef\nghi\njkl"),
            ("abc", "def\nghi\njkl")
        );
        assert_eq!(split_at_newline(""), ("", ""));
    }
}