lexxor 0.9.2

A fast, extensible, greedy, single-pass text tokenizer for Rust
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
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
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
/// The `exact` module provides the `ExactMatcher`, which matches strings exactly as specified.
/// It allows users to define a list of strings to match against, ensuring that only exact matches
/// are recognized, regardless of their position in the input stream.
use crate::matcher::{Matcher, MatcherResult};
use crate::token::Token;
use std::collections::HashMap;

/// An exact match to be made
#[derive(Clone, Debug)]
pub struct Target {
    /// If this match can still be made or not
    pub matching: bool,
    /// What this match is
    pub target: Box<Vec<char>>,
}

/// The Exact matcher does exactly what you'd expect. You give it a list of strings to match against
/// and it looks EXACTLY for those strings, not being picky about where those strings are.
///
/// # Example
///
/// ```rust
/// use lexxor::{Lexxor, Lexxer};
/// use lexxor::token::{TOKEN_TYPE_EXACT, TOKEN_TYPE_SYMBOL};
/// use lexxor::input::InputString;
/// use lexxor::matcher::exact::ExactMatcher;
/// use lexxor::matcher::symbol::SymbolMatcher;
///
/// let lexxor_input = InputString::new(String::from("^%$gxv llj)9^%d$rrr"));
///
/// let mut lexxor: Box<dyn Lexxer> = Box::new(Lexxor::<512>::new(
///     Box::new(lexxor_input),
///     vec![
///         Box::new(SymbolMatcher { index: 0, precedence: 0, running: true }),
///         // Note the precedence of 1 will cause the ExactMatcher to be be returned
///         // when the SymbolMatcher would have matched the same, or a longer thing.
///         Box::new(ExactMatcher::build_exact_matcher(vec!["^", "$gxv ", "gxv ", "llj)9", "d$rrr"], TOKEN_TYPE_EXACT, 1)),
///     ]
/// ));
///
/// // Because of the precedence settings the ExactMatcher matched "^"
/// // even though the SymbolMtcher would have matched "^%$"
/// assert!(matches!(lexxor.next_token(), Ok(Some(t)) if t.value == "^" && t.token_type == TOKEN_TYPE_EXACT && t.line == 1 && t.column == 1));
/// assert!(matches!(lexxor.next_token(), Ok(Some(t)) if t.value == "%$" && t.token_type == TOKEN_TYPE_SYMBOL && t.line == 1 && t.column == 2));
/// // NOTE that "$gxv " is NOT found because the symbol matcher matched "%$"
/// // the ExactMatcher gave up at '%' and never saw '$gxv '
/// // matchers can not find matches that start inside the valid matches of other matchers.
/// assert!(matches!(lexxor.next_token(), Ok(Some(t)) if t.value == "gxv " && t.token_type == TOKEN_TYPE_EXACT && t.line == 1 && t.column == 4));
/// assert!(matches!(lexxor.next_token(), Ok(Some(t)) if t.value == "llj)9" && t.token_type == TOKEN_TYPE_EXACT && t.line == 1 && t.column == 8));
/// assert!(matches!(lexxor.next_token(), Ok(Some(t)) if t.value == "^" && t.token_type == TOKEN_TYPE_EXACT && t.line == 1 && t.column == 13));
/// assert!(matches!(lexxor.next_token(), Ok(Some(t)) if t.value == "%" && t.token_type == TOKEN_TYPE_SYMBOL && t.line == 1 && t.column == 14));
/// assert!(matches!(lexxor.next_token(), Ok(Some(t)) if t.value == "d$rrr" && t.token_type == TOKEN_TYPE_EXACT && t.line == 1 && t.column == 15));
/// assert!(matches!(lexxor.next_token(), Ok(None)));
/// ```
#[derive(Clone, Debug)]
pub struct ExactMatcher {
    /// Current size of the ongoing match.
    pub index: usize,
    /// This matchers precedence.
    pub precedence: u8,
    /// If the matcher is currently running.
    pub running: bool,
    /// What is the currently found match index, if a longer one is found it will replace this one.
    pub found: Option<usize>,
    /// The array of possible matches to check.
    pub targets: Box<Vec<Target>>,
    /// What token type to return if a match is made.
    pub token_type: u16,
}

impl Matcher for ExactMatcher {
    fn reset(&mut self, _ctx: &mut Box<HashMap<String, i32>>) {
        for t in self.targets.iter_mut() {
            t.matching = true
        }
        self.found = None;
        self.index = 0;
        self.running = true;
    }

    fn find_match(
        &mut self,
        oc: Option<char>,
        _value: &[char],
        _ctx: &mut Box<HashMap<String, i32>>,
    ) -> MatcherResult {
        match oc {
            None => {
                self.running = false;
                for (i, target) in self.targets.iter_mut().enumerate() {
                    if target.matching && target.target.get(self.index).is_none() {
                        self.found = Some(i);
                    }
                }
                self.generate_exact_token()
            }
            Some(c) => {
                self.running = false;
                for (i, target) in self.targets.iter_mut().enumerate() {
                    if target.matching {
                        match target.target.get(self.index) {
                            Some(&m) if m == c => {
                                self.running = true;
                            }
                            Some(_) | None => {
                                target.matching = false;
                                if target.target.get(self.index).is_none() && self.index > 0 {
                                    self.found = Some(i);
                                }
                            }
                        }
                    }
                }
                self.index += 1;
                if !self.running {
                    self.generate_exact_token()
                } else {
                    MatcherResult::Running()
                }
            }
        }
    }
    fn is_running(&self) -> bool {
        self.running
    }
    fn precedence(&self) -> u8 {
        self.precedence
    }
}

impl ExactMatcher {
    /// Build an exact matcher
    ///
    /// # Arguments
    ///
    /// * `matches` - a [vec] of [&str](std::str)s that will be matched
    /// * `token_type` - the token type to produce
    /// * `precedence` - the precedence for this matcher
    ///
    pub fn build_exact_matcher(
        matches: Vec<&str>,
        token_type: u16,
        precedence: u8,
    ) -> ExactMatcher {
        // Pre-allocate with the exact capacity needed
        let mut targets = Vec::with_capacity(matches.len());

        for m in matches {
            // Only allocate the vector once with the exact capacity needed
            let mut chars = Vec::with_capacity(m.len());
            // Extend is more efficient than pushing chars one by one
            chars.extend(m.chars());

            targets.push(Target {
                matching: true,
                target: Box::new(chars),
            });
        }

        ExactMatcher {
            index: 0,
            precedence,
            found: None,
            running: true,
            token_type,
            targets: Box::new(targets),
        }
    }

    #[inline(always)]
    fn generate_exact_token(&mut self) -> MatcherResult {
        match self.found {
            None => MatcherResult::Failed(),
            Some(_) => {
                let i = self.found.unwrap();
                let target = &self.targets.get(i).unwrap().target;
                let token_value: String = target.clone().into_iter().collect();
                let len = target.len();
                MatcherResult::Matched(Token {
                    value: token_value,
                    token_type: self.token_type,
                    len,
                    line: 0,
                    column: len,
                    precedence: self.precedence,
                })
            }
        }
    }
}

#[cfg(test)]
mod tests {
    use crate::input::InputString;
    use crate::matcher::exact::ExactMatcher;
    use crate::matcher::symbol::SymbolMatcher;
    use crate::matcher::whitespace::WhitespaceMatcher;
    use crate::matcher::{Matcher, MatcherResult};
    use crate::token::TOKEN_TYPE_EXACT;
    use crate::{LexxError, Lexxer, Lexxor};

    #[test]
    fn matcher_exact_matches_word() {
        let mut lexxor: Box<dyn Lexxer> = Box::new(Lexxor::<512>::new(
            Box::new(InputString::new(String::from("The"))),
            vec![Box::new(ExactMatcher::build_exact_matcher(
                vec!["The"],
                TOKEN_TYPE_EXACT,
                0,
            ))],
        ));

        match lexxor.next_token() {
            Err(e) => match e {
                LexxError::TokenNotFound(_) => {
                    unreachable!("Should not have failed parsing file");
                }
                LexxError::Error(_) => {
                    unreachable!("Should not have failed parsing file");
                }
            },
            Ok(Some(t)) => {
                assert_eq!(t.value, "The");
                assert_eq!(t.token_type, TOKEN_TYPE_EXACT)
            }
            Ok(None) => {
                unreachable!("Should not hit None");
            }
        }
    }

    #[test]
    fn matcher_exact_matches_multiple_words() {
        use crate::token::TOKEN_TYPE_WHITESPACE;
        let mut lexxor = Lexxor::<512>::new(
            Box::new(InputString::new(String::from("The quick brown fox qquick"))),
            vec![
                Box::new(ExactMatcher::build_exact_matcher(
                    vec!["brown", "The", "fox", "quick", "qquick"],
                    TOKEN_TYPE_EXACT,
                    0,
                )),
                Box::new(WhitespaceMatcher {
                    index: 0,
                    column: 0,
                    line: 0,
                    precedence: 0,
                    running: true,
                }),
            ],
        );

        assert!(matches!(lexxor.next_token(), Ok(Some(t)) if t.value == "The"));
        assert!(
            matches!(lexxor.next_token(), Ok(Some(t)) if t.token_type == TOKEN_TYPE_WHITESPACE)
        );
        assert!(matches!(lexxor.next_token(), Ok(Some(t)) if t.value == "quick"));
        assert!(
            matches!(lexxor.next_token(), Ok(Some(t)) if t.token_type == TOKEN_TYPE_WHITESPACE)
        );
        assert!(matches!(lexxor.next_token(), Ok(Some(t)) if t.value == "brown"));
        assert!(
            matches!(lexxor.next_token(), Ok(Some(t)) if t.token_type == TOKEN_TYPE_WHITESPACE)
        );
        assert!(matches!(lexxor.next_token(), Ok(Some(t)) if t.value == "fox"));
        assert!(
            matches!(lexxor.next_token(), Ok(Some(t)) if t.token_type == TOKEN_TYPE_WHITESPACE)
        );

        match lexxor.next_token() {
            Err(e) => match e {
                LexxError::TokenNotFound(_) => {
                    unreachable!("Should not have failed parsing file");
                }
                LexxError::Error(_) => {
                    unreachable!("Should not have failed parsing file");
                }
            },
            Ok(Some(t)) => {
                assert_eq!(t.value, "qquick");
                assert_eq!(t.line, 1);
                assert_eq!(t.column, 21);
            }
            Ok(None) => {
                unreachable!("Should not hit None");
            }
        }
    }

    #[test]
    fn matcher_exact_matches_multiple_words_and_lines() {
        use crate::token::TOKEN_TYPE_WHITESPACE;
        let mut lexxor = Lexxor::<512>::new(
            Box::new(InputString::new(String::from(
                "The quick\rbrown\rfox jumped\rover the lazy dog",
            ))),
            vec![
                Box::new(ExactMatcher::build_exact_matcher(
                    vec![
                        "brown", "The", "fox", "quick", "dog", "over", "jumped", "lazy", "the",
                    ],
                    TOKEN_TYPE_EXACT,
                    0,
                )),
                Box::new(WhitespaceMatcher {
                    index: 0,
                    column: 0,
                    line: 0,
                    precedence: 0,
                    running: true,
                }),
            ],
        );

        assert!(matches!(lexxor.next_token(), Ok(Some(t)) if t.value == "The"));
        assert!(
            matches!(lexxor.next_token(), Ok(Some(t)) if t.token_type == TOKEN_TYPE_WHITESPACE)
        );
        assert!(matches!(lexxor.next_token(), Ok(Some(t)) if t.value == "quick"));
        assert!(
            matches!(lexxor.next_token(), Ok(Some(t)) if t.token_type == TOKEN_TYPE_WHITESPACE)
        );
        assert!(matches!(lexxor.next_token(), Ok(Some(t)) if t.value == "brown"));
        assert!(
            matches!(lexxor.next_token(), Ok(Some(t)) if t.token_type == TOKEN_TYPE_WHITESPACE)
        );
        assert!(matches!(lexxor.next_token(), Ok(Some(t)) if t.value == "fox"));
        assert!(
            matches!(lexxor.next_token(), Ok(Some(t)) if t.token_type == TOKEN_TYPE_WHITESPACE)
        );
        assert!(matches!(lexxor.next_token(), Ok(Some(t)) if t.value == "jumped"));
        assert!(
            matches!(lexxor.next_token(), Ok(Some(t)) if t.token_type == TOKEN_TYPE_WHITESPACE)
        );
        assert!(matches!(lexxor.next_token(), Ok(Some(t)) if t.value == "over"));
        assert!(
            matches!(lexxor.next_token(), Ok(Some(t)) if t.token_type == TOKEN_TYPE_WHITESPACE)
        );
        assert!(matches!(lexxor.next_token(), Ok(Some(t)) if t.value == "the"));
        assert!(
            matches!(lexxor.next_token(), Ok(Some(t)) if t.token_type == TOKEN_TYPE_WHITESPACE)
        );
        assert!(matches!(lexxor.next_token(), Ok(Some(t)) if t.value == "lazy"));
        assert!(
            matches!(lexxor.next_token(), Ok(Some(t)) if t.token_type == TOKEN_TYPE_WHITESPACE)
        );
        match lexxor.next_token() {
            Err(e) => match e {
                LexxError::TokenNotFound(_) => {
                    unreachable!("Should not have failed parsing file");
                }
                LexxError::Error(_) => {
                    unreachable!("Should not have failed parsing file");
                }
            },
            Ok(Some(t)) => {
                assert_eq!(t.value, "dog");
                assert_eq!(t.line, 1);
                assert_eq!(t.column, 39);
            }
            Ok(None) => {
                unreachable!("Should not hit None");
            }
        }
    }

    #[test]
    fn matcher_exact_matches_partial_word() {
        let mut lexxor = Lexxor::<512>::new(
            Box::new(InputString::new(String::from("Then"))),
            vec![Box::new(ExactMatcher::build_exact_matcher(
                vec!["The"],
                TOKEN_TYPE_EXACT,
                0,
            ))],
        );

        match lexxor.next_token() {
            Err(e) => match e {
                LexxError::TokenNotFound(_) => {
                    unreachable!("Should not have failed parsing file");
                }
                LexxError::Error(_) => {
                    unreachable!("Should not have failed parsing file");
                }
            },
            Ok(Some(t)) => {
                assert_eq!(t.value, "The");
                assert_eq!(t.token_type, TOKEN_TYPE_EXACT)
            }
            Ok(None) => {
                unreachable!("Should not hit None");
            }
        }
    }

    #[test]
    fn example_test() {
        use crate::Lexxor;
        use crate::token::{TOKEN_TYPE_EXACT, TOKEN_TYPE_SYMBOL};

        let lexxor_input = InputString::new(String::from("^%$gxv llj)9^%d$rrr"));

        let mut lexxor = Lexxor::<512>::new(
            Box::new(lexxor_input),
            vec![
                Box::new(SymbolMatcher {
                    index: 0,
                    precedence: 0,
                    running: true,
                }),
                // Note the precedence of 1 will cause the ExactMatcher to be be returned when
                // when the SymbolMatcher would have matched the same thing.
                Box::new(ExactMatcher::build_exact_matcher(
                    vec!["^", "$gxv ", "gxv ", "llj)9", "d$rrr"],
                    TOKEN_TYPE_EXACT,
                    1,
                )),
            ],
        );

        assert!(
            matches!(lexxor.next_token(), Ok(Some(t)) if t.value == "^" && t.token_type == TOKEN_TYPE_EXACT && t.line == 1 && t.column == 1)
        );
        assert!(
            matches!(lexxor.next_token(), Ok(Some(t)) if t.value == "%$" && t.token_type == TOKEN_TYPE_SYMBOL && t.line == 1 && t.column == 2)
        );
        // NOTE that "$gxv " is NOT found because the symbol matcher ate "%$"
        assert!(
            matches!(lexxor.next_token(), Ok(Some(t)) if t.value == "gxv " && t.token_type == TOKEN_TYPE_EXACT && t.line == 1 && t.column == 4)
        );
        assert!(
            matches!(lexxor.next_token(), Ok(Some(t)) if t.value == "llj)9" && t.token_type == TOKEN_TYPE_EXACT && t.line == 1 && t.column == 8)
        );
        assert!(
            matches!(lexxor.next_token(), Ok(Some(t)) if t.value == "^" && t.token_type == TOKEN_TYPE_EXACT && t.line == 1 && t.column == 13)
        );
        assert!(
            matches!(lexxor.next_token(), Ok(Some(t)) if t.value == "%" && t.token_type == TOKEN_TYPE_SYMBOL && t.line == 1 && t.column == 14)
        );
        assert!(
            matches!(lexxor.next_token(), Ok(Some(t)) if t.value == "d$rrr" && t.token_type == TOKEN_TYPE_EXACT && t.line == 1 && t.column == 15)
        );
    }

    #[test]
    fn test_overlapping_matches_with_precedence() {
        // Test that when multiple matches are possible, the one with higher precedence wins
        let mut lexxor = Lexxor::<512>::new(
            Box::new(InputString::new(String::from("abcdef"))),
            vec![
                Box::new(ExactMatcher::build_exact_matcher(
                    vec!["abc"],
                    TOKEN_TYPE_EXACT,
                    1, // Higher precedence
                )),
                Box::new(ExactMatcher::build_exact_matcher(
                    vec!["abcdef"],
                    TOKEN_TYPE_EXACT + 1, // Different token type to distinguish
                    0,                    // Lower precedence
                )),
            ],
        );

        // The matcher with higher precedence should win, even though the other would match more
        assert!(
            matches!(lexxor.next_token(), Ok(Some(t)) if t.value == "abc" && t.token_type == TOKEN_TYPE_EXACT)
        );

        // The remaining text should not match anything
        assert!(matches!(
            lexxor.next_token(),
            Err(LexxError::TokenNotFound(_))
        ));
    }

    #[test]
    fn test_case_sensitivity() {
        // Test that matching is case-sensitive
        let mut lexxor = Lexxor::<512>::new(
            Box::new(InputString::new(String::from("The THE the"))),
            vec![Box::new(ExactMatcher::build_exact_matcher(
                vec!["The", "the"],
                TOKEN_TYPE_EXACT,
                0,
            ))],
        );

        // Should match "The" exactly
        assert!(
            matches!(lexxor.next_token(), Ok(Some(t)) if t.value == "The" && t.token_type == TOKEN_TYPE_EXACT)
        );

        // "THE" is not in the target list, so it should not be matched
        assert!(matches!(
            lexxor.next_token(),
            Err(LexxError::TokenNotFound(_))
        ));
    }

    #[test]
    fn test_unicode_character_handling() {
        // Test that Unicode characters are handled correctly
        let mut lexxor = Lexxor::<512>::new(
            Box::new(InputString::new(String::from("こんにちは世界"))),
            vec![Box::new(ExactMatcher::build_exact_matcher(
                vec!["こんにちは", "世界"],
                TOKEN_TYPE_EXACT,
                0,
            ))],
        );

        // Should match "こんにちは" exactly
        assert!(
            matches!(lexxor.next_token(), Ok(Some(t)) if t.value == "こんにちは" && t.token_type == TOKEN_TYPE_EXACT)
        );

        // Should match "世界" exactly
        assert!(
            matches!(lexxor.next_token(), Ok(Some(t)) if t.value == "世界" && t.token_type == TOKEN_TYPE_EXACT)
        );

        // No more tokens
        assert!(matches!(lexxor.next_token(), Ok(None)));
    }

    #[test]
    fn test_reset_functionality() {
        use std::collections::HashMap;

        // Test that the reset function properly resets the matcher state
        let mut matcher =
            ExactMatcher::build_exact_matcher(vec!["abc", "def"], TOKEN_TYPE_EXACT, 0);

        // Simulate partial matching
        let mut ctx = Box::new(HashMap::new());
        assert!(matches!(
            matcher.find_match(Some('a'), &[], &mut ctx),
            MatcherResult::Running()
        ));
        assert!(matches!(
            matcher.find_match(Some('b'), &[], &mut ctx),
            MatcherResult::Running()
        ));

        // Now reset
        matcher.reset(&mut ctx);

        // Verify that the matcher state has been reset
        assert_eq!(matcher.index, 0);
        assert_eq!(matcher.found, None);
        assert!(matcher.running);

        // All targets should be matching again
        for target in matcher.targets.iter() {
            assert!(target.matching);
        }
    }

    #[test]
    fn test_empty_targets_list() {
        // Test behavior with an empty targets list
        let mut lexxor = Lexxor::<512>::new(
            Box::new(InputString::new(String::from("abc"))),
            vec![Box::new(ExactMatcher::build_exact_matcher(
                vec![],
                TOKEN_TYPE_EXACT,
                0,
            ))],
        );

        // Should fail to match anything with an empty targets list
        assert!(matches!(
            lexxor.next_token(),
            Err(LexxError::TokenNotFound(_))
        ));
    }
}