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
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
// pest. The Elegant Parser
// Copyright (c) 2018 Dragoș Tiselice
//
// Licensed under the Apache License, Version 2.0
// <LICENSE-APACHE or http://www.apache.org/licenses/LICENSE-2.0> or the MIT
// license <LICENSE-MIT or http://opensource.org/licenses/MIT>, at your
// option. All files in the project carrying such notice may not be copied,
// modified, or distributed except according to those terms.

use std::cmp::Ordering;
use std::fmt;
use std::hash::{Hash, Hasher};
use std::ops::Range;
use std::ptr;
use std::str;

use span;

/// A cursor position in a `&str` which provides useful methods to manually parse that string.
#[derive(Clone)]
pub struct Position<'i> {
    input: &'i str,
    /// # Safety:
    ///
    /// `input[pos..]` must be a valid codepoint boundary (should not panic when indexing thus).
    pos: usize,
}

impl<'i> Position<'i> {
    /// Create a new `Position` without checking invariants. (Checked with `debug_assertions`.)
    ///
    /// # Safety:
    ///
    /// `input[pos..]` must be a valid codepoint boundary (should not panic when indexing thus).
    pub(crate) unsafe fn new_unchecked(input: &str, pos: usize) -> Position {
        debug_assert!(input.get(pos..).is_some());
        Position { input, pos }
    }

    /// Attempts to create a new `Position` at the given position. If the specified position is
    /// an invalid index, or the specified position is not a valid UTF8 boundary, then None is
    /// returned.
    ///
    /// # Examples
    /// ```
    /// # use pest::Position;
    /// let cheart = '💖';
    /// let heart = "💖";
    /// assert_eq!(Position::new(heart, 1), None);
    /// assert_ne!(Position::new(heart, cheart.len_utf8()), None);
    /// ```
    #[allow(clippy::new_ret_no_self)]
    pub fn new(input: &str, pos: usize) -> Option<Position> {
        input.get(pos..).map(|_| Position { input, pos })
    }

    /// Creates a `Position` at the start of a `&str`.
    ///
    /// # Examples
    ///
    /// ```
    /// # use pest::Position;
    /// let start = Position::from_start("");
    /// assert_eq!(start.pos(), 0);
    /// ```
    #[inline]
    pub fn from_start(input: &'i str) -> Position<'i> {
        // Position 0 is always safe because it's always a valid UTF-8 border.
        Position { input, pos: 0 }
    }

    /// Returns the byte position of this `Position` as a `usize`.
    ///
    /// # Examples
    ///
    /// ```
    /// # use pest::Position;
    /// let input = "ab";
    /// let mut start = Position::from_start(input);
    ///
    /// assert_eq!(start.pos(), 0);
    /// ```
    #[inline]
    pub fn pos(&self) -> usize {
        self.pos
    }

    /// Creates a `Span` from two `Position`s.
    ///
    /// # Panics
    ///
    /// Panics if the positions come from different inputs.
    ///
    /// # Examples
    ///
    /// ```
    /// # use pest::Position;
    /// let input = "ab";
    /// let start = Position::from_start(input);
    /// let span = start.span(&start.clone());
    ///
    /// assert_eq!(span.start(), 0);
    /// assert_eq!(span.end(), 0);
    /// ```
    #[inline]
    pub fn span(&self, other: &Position<'i>) -> span::Span<'i> {
        if ptr::eq(self.input, other.input)
        /* && self.input.get(self.pos..other.pos).is_some() */
        {
            // This is safe because the pos field of a Position should always be a valid str index.
            unsafe { span::Span::new_unchecked(self.input, self.pos, other.pos) }
        } else {
            // TODO: maybe a panic if self.pos < other.pos
            panic!("span created from positions from different inputs")
        }
    }

    /// Returns the line and column number of this `Position`.
    ///
    /// # Examples
    ///
    /// ```
    /// # use pest;
    /// # #[allow(non_camel_case_types)]
    /// # #[derive(Clone, Copy, Debug, Eq, Hash, Ord, PartialEq, PartialOrd)]
    /// enum Rule {}
    ///
    /// let input = "\na";
    /// let mut state: Box<pest::ParserState<Rule>> = pest::ParserState::new(input);
    /// let mut result = state.match_string("\na");
    /// assert!(result.is_ok());
    /// assert_eq!(result.unwrap().position().line_col(), (2, 2));
    /// ```
    #[inline]
    pub fn line_col(&self) -> (usize, usize) {
        if self.pos > self.input.len() {
            panic!("position out of bounds");
        }

        let mut pos = self.pos;
        // Position's pos is always a UTF-8 border.
        let slice = &self.input[..pos];
        let mut chars = slice.chars().peekable();

        let mut line_col = (1, 1);

        while pos != 0 {
            match chars.next() {
                Some('\r') => {
                    if let Some(&'\n') = chars.peek() {
                        chars.next();

                        if pos == 1 {
                            pos -= 1;
                        } else {
                            pos -= 2;
                        }

                        line_col = (line_col.0 + 1, 1);
                    } else {
                        pos -= 1;
                        line_col = (line_col.0, line_col.1 + 1);
                    }
                }
                Some('\n') => {
                    pos -= 1;
                    line_col = (line_col.0 + 1, 1);
                }
                Some(c) => {
                    pos -= c.len_utf8();
                    line_col = (line_col.0, line_col.1 + 1);
                }
                None => unreachable!(),
            }
        }

        line_col
    }

    /// Returns the entire line of the input that contains this `Position`.
    ///
    /// # Examples
    ///
    /// ```
    /// # use pest;
    /// # #[allow(non_camel_case_types)]
    /// # #[derive(Clone, Copy, Debug, Eq, Hash, Ord, PartialEq, PartialOrd)]
    /// enum Rule {}
    ///
    /// let input = "\na";
    /// let mut state: Box<pest::ParserState<Rule>> = pest::ParserState::new(input);
    /// let mut result = state.match_string("\na");
    /// assert!(result.is_ok());
    /// assert_eq!(result.unwrap().position().line_of(), "a");
    /// ```
    #[inline]
    pub fn line_of(&self) -> &'i str {
        if self.pos > self.input.len() {
            panic!("position out of bounds");
        };
        // Safe since start and end can only be valid UTF-8 borders.
        &self.input[self.find_line_start()..self.find_line_end()]
    }

    pub(crate) fn find_line_start(&self) -> usize {
        if self.input.is_empty() {
            return 0;
        };
        // Position's pos is always a UTF-8 border.
        let start = self
            .input
            .char_indices()
            .rev()
            .skip_while(|&(i, _)| i >= self.pos)
            .find(|&(_, c)| c == '\n');
        match start {
            Some((i, _)) => i + 1,
            None => 0,
        }
    }

    pub(crate) fn find_line_end(&self) -> usize {
        if self.input.is_empty() {
            0
        } else if self.pos == self.input.len() - 1 {
            self.input.len()
        } else {
            // Position's pos is always a UTF-8 border.
            let end = self
                .input
                .char_indices()
                .skip_while(|&(i, _)| i < self.pos)
                .find(|&(_, c)| c == '\n');
            match end {
                Some((i, _)) => i + 1,
                None => self.input.len(),
            }
        }
    }

    /// Returns `true` when the `Position` points to the start of the input `&str`.
    #[inline]
    pub(crate) fn at_start(&self) -> bool {
        self.pos == 0
    }

    /// Returns `true` when the `Position` points to the end of the input `&str`.
    #[inline]
    pub(crate) fn at_end(&self) -> bool {
        self.pos == self.input.len()
    }

    /// Skips `n` `char`s from the `Position` and returns `true` if the skip was possible or `false`
    /// otherwise. If the return value is `false`, `pos` will not be updated.
    #[inline]
    pub(crate) fn skip(&mut self, n: usize) -> bool {
        let skipped = {
            let mut len = 0;
            // Position's pos is always a UTF-8 border.
            let mut chars = (&self.input[self.pos..]).chars();
            for _ in 0..n {
                if let Some(c) = chars.next() {
                    len += c.len_utf8();
                } else {
                    return false;
                }
            }
            len
        };

        self.pos += skipped;
        true
    }

    /// Goes back `n` `char`s from the `Position` and returns `true` if the skip was possible or `false`
    /// otherwise. If the return value is `false`, `pos` will not be updated.
    #[inline]
    pub(crate) fn skip_back(&mut self, n: usize) -> bool {
        let skipped = {
            let mut len = 0;
            // Position's pos is always a UTF-8 border.
            let mut chars = (&self.input[..self.pos]).chars().rev();
            for _ in 0..n {
                if let Some(c) = chars.next() {
                    len += c.len_utf8();
                } else {
                    return false;
                }
            }
            len
        };

        self.pos -= skipped;
        true
    }

    /// Skips until one of the given `strings` is found. If none of the `strings` can be found,
    /// this function will return `false` but its `pos` will *still* be updated.
    #[inline]
    pub(crate) fn skip_until(&mut self, strings: &[&str]) -> bool {
        for from in self.pos..self.input.len() {
            let bytes = if let Some(string) = self.input.get(from..) {
                string.as_bytes()
            } else {
                continue;
            };

            for slice in strings.iter() {
                let to = slice.len();
                if Some(slice.as_bytes()) == bytes.get(0..to) {
                    self.pos = from;
                    return true;
                }
            }
        }

        self.pos = self.input.len();
        false
    }

    /// Matches the char at the `Position` against a filter function and returns `true` if a match
    /// was made. If no match was made, returns `false` and `pos` will not be updated.
    #[inline]
    pub(crate) fn match_char_by<F>(&mut self, f: F) -> bool
    where
        F: FnOnce(char) -> bool,
    {
        if let Some(c) = (&self.input[self.pos..]).chars().next() {
            if f(c) {
                self.pos += c.len_utf8();
                true
            } else {
                false
            }
        } else {
            false
        }
    }

    /// Matches `string` from the `Position` and returns `true` if a match was made or `false`
    /// otherwise. If no match was made, `pos` will not be updated.
    #[inline]
    pub(crate) fn match_string(&mut self, string: &str) -> bool {
        let to = self.pos + string.len();

        if Some(string.as_bytes()) == self.input.as_bytes().get(self.pos..to) {
            self.pos = to;
            true
        } else {
            false
        }
    }

    /// Case-insensitively matches `string` from the `Position` and returns `true` if a match was
    /// made or `false` otherwise. If no match was made, `pos` will not be updated.
    #[inline]
    pub(crate) fn match_insensitive(&mut self, string: &str) -> bool {
        let matched = {
            let slice = &self.input[self.pos..];
            if let Some(slice) = slice.get(0..string.len()) {
                slice.eq_ignore_ascii_case(string)
            } else {
                false
            }
        };

        if matched {
            self.pos += string.len();
            true
        } else {
            false
        }
    }

    /// Matches `char` `range` from the `Position` and returns `true` if a match was made or `false`
    /// otherwise. If no match was made, `pos` will not be updated.
    #[inline]
    pub(crate) fn match_range(&mut self, range: Range<char>) -> bool {
        if let Some(c) = (&self.input[self.pos..]).chars().next() {
            if range.start <= c && c <= range.end {
                self.pos += c.len_utf8();
                return true;
            }
        }

        false
    }
}

impl<'i> fmt::Debug for Position<'i> {
    fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
        f.debug_struct("Position").field("pos", &self.pos).finish()
    }
}

impl<'i> PartialEq for Position<'i> {
    fn eq(&self, other: &Position<'i>) -> bool {
        ptr::eq(self.input, other.input) && self.pos == other.pos
    }
}

impl<'i> Eq for Position<'i> {}

impl<'i> PartialOrd for Position<'i> {
    fn partial_cmp(&self, other: &Position<'i>) -> Option<Ordering> {
        if ptr::eq(self.input, other.input) {
            self.pos.partial_cmp(&other.pos)
        } else {
            None
        }
    }
}

impl<'i> Ord for Position<'i> {
    fn cmp(&self, other: &Position<'i>) -> Ordering {
        self.partial_cmp(other)
            .expect("cannot compare positions from different strs")
    }
}

impl<'i> Hash for Position<'i> {
    fn hash<H: Hasher>(&self, state: &mut H) {
        (self.input as *const str).hash(state);
        self.pos.hash(state);
    }
}

#[cfg(test)]
mod tests {
    use std::collections::HashSet;

    use super::*;

    #[test]
    fn empty() {
        let input = "";
        assert_eq!(Position::new(input, 0).unwrap().match_string(""), true);
        assert_eq!(!Position::new(input, 0).unwrap().match_string("a"), true);
    }

    #[test]
    fn parts() {
        let input = "asdasdf";

        assert_eq!(Position::new(input, 0).unwrap().match_string("asd"), true);
        assert_eq!(Position::new(input, 3).unwrap().match_string("asdf"), true);
    }

    #[test]
    fn line_col() {
        let input = "a\rb\nc\r\nd嗨";

        assert_eq!(Position::new(input, 0).unwrap().line_col(), (1, 1));
        assert_eq!(Position::new(input, 1).unwrap().line_col(), (1, 2));
        assert_eq!(Position::new(input, 2).unwrap().line_col(), (1, 3));
        assert_eq!(Position::new(input, 3).unwrap().line_col(), (1, 4));
        assert_eq!(Position::new(input, 4).unwrap().line_col(), (2, 1));
        assert_eq!(Position::new(input, 5).unwrap().line_col(), (2, 2));
        assert_eq!(Position::new(input, 6).unwrap().line_col(), (2, 3));
        assert_eq!(Position::new(input, 7).unwrap().line_col(), (3, 1));
        assert_eq!(Position::new(input, 8).unwrap().line_col(), (3, 2));
        assert_eq!(Position::new(input, 11).unwrap().line_col(), (3, 3));
    }

    #[test]
    fn line_of() {
        let input = "a\rb\nc\r\nd嗨";

        assert_eq!(Position::new(input, 0).unwrap().line_of(), "a\rb\n");
        assert_eq!(Position::new(input, 1).unwrap().line_of(), "a\rb\n");
        assert_eq!(Position::new(input, 2).unwrap().line_of(), "a\rb\n");
        assert_eq!(Position::new(input, 3).unwrap().line_of(), "a\rb\n");
        assert_eq!(Position::new(input, 4).unwrap().line_of(), "c\r\n");
        assert_eq!(Position::new(input, 5).unwrap().line_of(), "c\r\n");
        assert_eq!(Position::new(input, 6).unwrap().line_of(), "c\r\n");
        assert_eq!(Position::new(input, 7).unwrap().line_of(), "d嗨");
        assert_eq!(Position::new(input, 8).unwrap().line_of(), "d嗨");
        assert_eq!(Position::new(input, 11).unwrap().line_of(), "d嗨");
    }

    #[test]
    fn line_of_empty() {
        let input = "";

        assert_eq!(Position::new(input, 0).unwrap().line_of(), "");
    }

    #[test]
    fn line_of_new_line() {
        let input = "\n";

        assert_eq!(Position::new(input, 0).unwrap().line_of(), "\n");
    }

    #[test]
    fn line_of_between_new_line() {
        let input = "\n\n";

        assert_eq!(Position::new(input, 1).unwrap().line_of(), "\n");
    }

    fn measure_skip(input: &str, pos: usize, n: usize) -> Option<usize> {
        let mut p = Position::new(input, pos).unwrap();
        if p.skip(n) {
            Some(p.pos - pos)
        } else {
            None
        }
    }

    #[test]
    fn skip_empty() {
        let input = "";

        assert_eq!(measure_skip(input, 0, 0), Some(0));
        assert_eq!(measure_skip(input, 0, 1), None);
    }

    #[test]
    fn skip() {
        let input = "d嗨";

        assert_eq!(measure_skip(input, 0, 0), Some(0));
        assert_eq!(measure_skip(input, 0, 1), Some(1));
        assert_eq!(measure_skip(input, 1, 1), Some(3));
    }

    #[test]
    fn skip_until() {
        let input = "ab ac";
        let pos = Position::from_start(input);

        let mut test_pos = pos.clone();
        test_pos.skip_until(&["a", "b"]);
        assert_eq!(test_pos.pos(), 0);

        test_pos = pos.clone();
        test_pos.skip_until(&["b"]);
        assert_eq!(test_pos.pos(), 1);

        test_pos = pos.clone();
        test_pos.skip_until(&["ab"]);
        assert_eq!(test_pos.pos(), 0);

        test_pos = pos.clone();
        test_pos.skip_until(&["ac", "z"]);
        assert_eq!(test_pos.pos(), 3);

        test_pos = pos.clone();
        assert!(!test_pos.skip_until(&["z"]));
        assert_eq!(test_pos.pos(), 5);
    }

    #[test]
    fn match_range() {
        let input = "b";

        assert_eq!(Position::new(input, 0).unwrap().match_range('a'..'c'), true);
        assert_eq!(Position::new(input, 0).unwrap().match_range('b'..'b'), true);
        assert_eq!(
            !Position::new(input, 0).unwrap().match_range('a'..'a'),
            true
        );
        assert_eq!(
            !Position::new(input, 0).unwrap().match_range('c'..'c'),
            true
        );
        assert_eq!(
            Position::new(input, 0).unwrap().match_range('a'..'嗨'),
            true
        );
    }

    #[test]
    fn match_insensitive() {
        let input = "AsdASdF";

        assert_eq!(
            Position::new(input, 0).unwrap().match_insensitive("asd"),
            true
        );
        assert_eq!(
            Position::new(input, 3).unwrap().match_insensitive("asdf"),
            true
        );
    }

    #[test]
    fn cmp() {
        let input = "a";
        let start = Position::from_start(input);
        let mut end = start.clone();

        assert!(end.skip(1));
        let result = start.cmp(&end);

        assert_eq!(result, Ordering::Less);
    }

    #[test]
    #[should_panic]
    fn cmp_panic() {
        let input1 = "a";
        let input2 = "b";
        let pos1 = Position::from_start(input1);
        let pos2 = Position::from_start(input2);

        pos1.cmp(&pos2);
    }

    #[test]
    fn hash() {
        let input = "a";
        let start = Position::from_start(input);
        let mut positions = HashSet::new();

        positions.insert(start);
    }
}