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
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
//! Lexer for semver ranges.
//!
//! Breaks a string of input into an iterator of tokens that can be used with a parser.
//!
//! This should be used with the [`parser`] module.
//!
//! [`parser`]: ../parser/index.html
//!
//! # Examples
//!
//! Example without errors:
//!
//! ```rust
//! use semver_parser::lexer::{Lexer, Token};
//!
//! let mut l = Lexer::new("foo 123 *");
//!
//! assert_eq!(Some(Ok(Token::AlphaNumeric("foo"))), l.next());
//! assert_eq!(Some(Ok(Token::Whitespace(3, 4))), l.next());
//! assert_eq!(Some(Ok(Token::Numeric(123))), l.next());
//! assert_eq!(Some(Ok(Token::Whitespace(7, 8))), l.next());
//! assert_eq!(Some(Ok(Token::Star)), l.next());
//! assert_eq!(None, l.next());
//! ```
//!
//! Example with error:
//!
//! ```rust
//! use semver_parser::lexer::{Lexer, Token, Error};
//!
//! let mut l = Lexer::new("foo / *");
//!
//! assert_eq!(Some(Ok(Token::AlphaNumeric("foo"))), l.next());
//! assert_eq!(Some(Ok(Token::Whitespace(3, 4))), l.next());
//! assert_eq!(Some(Err(Error::UnexpectedChar('/'))), l.next());
//! ```

use self::Error::*;
use self::Token::*;
use std::str;

macro_rules! scan_while {
    ($slf:expr, $start:expr, $first:pat $(| $rest:pat)*) => {{
        let mut __end = $start;

        loop {
            if let Some((idx, c)) = $slf.one() {
                __end = idx;

                match c {
                    $first $(| $rest)* => $slf.step(),
                    _ => break,
                }

                continue;
            } else {
                __end = $slf.input.len();
            }

            break;
        }

        __end
    }}
}

/// Semver tokens.
#[derive(Debug, PartialEq, Eq, PartialOrd, Ord)]
pub enum Token<'input> {
    /// `=`
    Eq,
    /// `>`
    Gt,
    /// `<`
    Lt,
    /// `<=`
    LtEq,
    /// `>=`
    GtEq,
    /// '^`
    Caret,
    /// '~`
    Tilde,
    /// '*`
    Star,
    /// `.`
    Dot,
    /// `,`
    Comma,
    /// `-`
    Hyphen,
    /// `+`
    Plus,
    /// '||'
    Or,
    /// any number of whitespace (`\t\r\n `) and its span.
    Whitespace(usize, usize),
    /// Numeric component, like `0` or `42`.
    Numeric(u64),
    /// Alphanumeric component, like `alpha1` or `79deadbe`.
    AlphaNumeric(&'input str),
}

impl<'input> Token<'input> {
    /// Check if the current token is a whitespace token.
    pub fn is_whitespace(&self) -> bool {
        match *self {
            Whitespace(..) => true,
            _ => false,
        }
    }

    /// Check if the current token is a wildcard token.
    pub fn is_wildcard(&self) -> bool {
        match *self {
            Star | AlphaNumeric("X") | AlphaNumeric("x") => true,
            _ => false,
        }
    }
}

#[derive(Debug, PartialEq, Eq, PartialOrd, Ord)]
pub enum Error {
    /// Unexpected character.
    UnexpectedChar(char),
}

/// Lexer for semver tokens belonging to a range.
#[derive(Debug)]
pub struct Lexer<'input> {
    input: &'input str,
    chars: str::CharIndices<'input>,
    // lookahead
    c1: Option<(usize, char)>,
    c2: Option<(usize, char)>,
}

impl<'input> Lexer<'input> {
    /// Construct a new lexer for the given input.
    pub fn new(input: &str) -> Lexer {
        let mut chars = input.char_indices();
        let c1 = chars.next();
        let c2 = chars.next();

        Lexer {
            input,
            chars,
            c1,
            c2,
        }
    }

    /// Shift all lookahead storage by one.
    fn step(&mut self) {
        self.c1 = self.c2;
        self.c2 = self.chars.next();
    }

    fn step_n(&mut self, n: usize) {
        for _ in 0..n {
            self.step();
        }
    }

    /// Access the one character, or set it if it is not set.
    fn one(&mut self) -> Option<(usize, char)> {
        self.c1
    }

    /// Access two characters.
    fn two(&mut self) -> Option<(usize, char, char)> {
        self.c1
            .and_then(|(start, c1)| self.c2.map(|(_, c2)| (start, c1, c2)))
    }

    /// Consume a component.
    ///
    /// A component can either be an alphanumeric or numeric.
    /// Does not permit leading zeroes if numeric.
    fn component(&mut self, start: usize) -> Result<Token<'input>, Error> {
        let end = scan_while!(self, start, '0'..='9' | 'A'..='Z' | 'a'..='z');
        let input = &self.input[start..end];

        let mut it = input.chars();
        let (a, b) = (it.next(), it.next());

        // exactly zero
        if a == Some('0') && b.is_none() {
            return Ok(Numeric(0));
        }

        if a != Some('0') {
            if let Ok(numeric) = input.parse::<u64>() {
                return Ok(Numeric(numeric));
            }
        }

        Ok(AlphaNumeric(input))
    }

    /// Consume whitespace.
    fn whitespace(&mut self, start: usize) -> Result<Token<'input>, Error> {
        let end = scan_while!(self, start, ' ' | '\t' | '\n' | '\r');
        Ok(Whitespace(start, end))
    }
}

impl<'input> Iterator for Lexer<'input> {
    type Item = Result<Token<'input>, Error>;

    fn next(&mut self) -> Option<Self::Item> {
        #[allow(clippy::never_loop)]
        loop {
            // two subsequent char tokens.
            if let Some((_, a, b)) = self.two() {
                let two = match (a, b) {
                    ('<', '=') => Some(LtEq),
                    ('>', '=') => Some(GtEq),
                    ('|', '|') => Some(Or),
                    _ => None,
                };

                if let Some(two) = two {
                    self.step_n(2);
                    return Some(Ok(two));
                }
            }

            // single char and start of numeric tokens.
            if let Some((start, c)) = self.one() {
                let tok = match c {
                    ' ' | '\t' | '\n' | '\r' => {
                        self.step();
                        return Some(self.whitespace(start));
                    }
                    '=' => Eq,
                    '>' => Gt,
                    '<' => Lt,
                    '^' => Caret,
                    '~' => Tilde,
                    '*' => Star,
                    '.' => Dot,
                    ',' => Comma,
                    '-' => Hyphen,
                    '+' => Plus,
                    '0'..='9' | 'a'..='z' | 'A'..='Z' => {
                        self.step();
                        return Some(self.component(start));
                    }
                    c => return Some(Err(UnexpectedChar(c))),
                };

                self.step();
                return Some(Ok(tok));
            };

            return None;
        }
    }
}

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

    fn lex(input: &str) -> Vec<Token> {
        Lexer::new(input).map(Result::unwrap).collect::<Vec<_>>()
    }

    #[test]
    pub fn simple_tokens() {
        assert_eq!(
            lex("=><<=>=^~*.,-+||"),
            vec![Eq, Gt, Lt, LtEq, GtEq, Caret, Tilde, Star, Dot, Comma, Hyphen, Plus, Or,]
        );
    }

    #[test]
    pub fn whitespace() {
        assert_eq!(
            lex("  foo \t\n\rbar"),
            vec![
                Whitespace(0, 2),
                AlphaNumeric("foo"),
                Whitespace(5, 9),
                AlphaNumeric("bar"),
            ]
        );
    }

    #[test]
    pub fn components() {
        assert_eq!(lex("42"), vec![Numeric(42)]);
        assert_eq!(lex("0"), vec![Numeric(0)]);
        assert_eq!(lex("01"), vec![AlphaNumeric("01")]);
        assert_eq!(lex("01"), vec![AlphaNumeric("01")]);
        assert_eq!(lex("5885644aa"), vec![AlphaNumeric("5885644aa")]);
        assert_eq!(lex("beta2"), vec![AlphaNumeric("beta2")]);
        assert_eq!(lex("beta.2"), vec![AlphaNumeric("beta"), Dot, Numeric(2)]);
    }

    #[test]
    pub fn is_wildcard() {
        assert_eq!(Star.is_wildcard(), true);
        assert_eq!(AlphaNumeric("x").is_wildcard(), true);
        assert_eq!(AlphaNumeric("X").is_wildcard(), true);
        assert_eq!(AlphaNumeric("other").is_wildcard(), false);
    }

    #[test]
    pub fn empty() {
        assert_eq!(lex(""), vec![]);
    }

    #[test]
    pub fn numeric_all_numbers() {
        let expected: Vec<Token> = vec![0, 1, 2, 3, 4, 5, 6, 7, 8, 9]
            .into_iter()
            .map(Numeric)
            .collect::<Vec<_>>();

        let actual: Vec<_> = lex("0 1 2 3 4 5 6 7 8 9")
            .into_iter()
            .filter(|t| !t.is_whitespace())
            .collect();

        assert_eq!(actual, expected);
    }
}