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
// 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 alloc::format;
use alloc::rc::Rc;
use alloc::string::String;
use alloc::vec::Vec;
use core::fmt;
use core::hash::{Hash, Hasher};
use core::ptr;
use core::str;

#[cfg(feature = "pretty-print")]
use serde::ser::SerializeStruct;

use super::flat_pairs::{self, FlatPairs};
use super::pair::{self, Pair};
use super::queueable_token::QueueableToken;
use super::tokens::{self, Tokens};
use crate::{position, RuleType};

#[derive(Clone)]
pub struct Cursor {
    pub line: usize,
    pub col: usize,
    pub end: usize,
}

impl Default for Cursor {
    fn default() -> Cursor {
        Cursor {
            line: 1,
            col: 1,
            end: 0,
        }
    }
}
/// An iterator over [`Pair`]s. It is created by [`pest::state`] and [`Pair::into_inner`].
///
/// [`Pair`]: struct.Pair.html
/// [`pest::state`]: ../fn.state.html
/// [`Pair::into_inner`]: struct.Pair.html#method.into_inner
#[derive(Clone)]
pub struct Pairs<'i, R> {
    queue: Rc<Vec<QueueableToken<R>>>,
    input: &'i str,
    start: usize,
    end: usize,
    cursor: Cursor,
}

pub fn new<R: RuleType>(
    queue: Rc<Vec<QueueableToken<R>>>,
    input: &str,
    start: usize,
    end: usize,
) -> Pairs<'_, R> {
    Pairs {
        queue,
        input,
        start,
        end,
        cursor: Cursor::default(),
    }
}

impl<'i, R: RuleType> Pairs<'i, R> {
    /// Captures a slice from the `&str` defined by the starting position of the first token `Pair`
    /// and the ending position of the last token `Pair` of the `Pairs`. This also captures
    /// the input between those two token `Pair`s.
    ///
    /// # Examples
    ///
    /// ```
    /// # use std::rc::Rc;
    /// # use pest;
    /// # #[allow(non_camel_case_types)]
    /// # #[derive(Clone, Copy, Debug, Eq, Hash, Ord, PartialEq, PartialOrd)]
    /// enum Rule {
    ///     a,
    ///     b
    /// }
    ///
    /// let input = "a b";
    /// let pairs = pest::state(input, |state| {
    ///     // generating Token pairs with Rule::a and Rule::b ...
    /// #     state.rule(Rule::a, |s| s.match_string("a")).and_then(|s| s.skip(1))
    /// #         .and_then(|s| s.rule(Rule::b, |s| s.match_string("b")))
    /// }).unwrap();
    ///
    /// assert_eq!(pairs.as_str(), "a b");
    /// ```
    #[inline]
    pub fn as_str(&self) -> &'i str {
        if self.start < self.end {
            let start = self.pos(self.start);
            let end = self.pos(self.end - 1);
            // Generated positions always come from Positions and are UTF-8 borders.
            &self.input[start..end]
        } else {
            ""
        }
    }

    /// Captures inner token `Pair`s and concatenates resulting `&str`s. This does not capture
    /// the input between token `Pair`s.
    ///
    /// # Examples
    ///
    /// ```
    /// # use std::rc::Rc;
    /// # use pest;
    /// # #[allow(non_camel_case_types)]
    /// # #[derive(Clone, Copy, Debug, Eq, Hash, Ord, PartialEq, PartialOrd)]
    /// enum Rule {
    ///     a,
    ///     b
    /// }
    ///
    /// let input = "a b";
    /// let pairs = pest::state(input, |state| {
    ///     // generating Token pairs with Rule::a and Rule::b ...
    /// #     state.rule(Rule::a, |s| s.match_string("a")).and_then(|s| s.skip(1))
    /// #         .and_then(|s| s.rule(Rule::b, |s| s.match_string("b")))
    /// }).unwrap();
    ///
    /// assert_eq!(pairs.concat(), "ab");
    /// ```
    #[inline]
    pub fn concat(&self) -> String {
        self.clone()
            .fold(String::new(), |string, pair| string + pair.as_str())
    }

    /// Flattens the `Pairs`.
    ///
    /// # Examples
    ///
    /// ```
    /// # use std::rc::Rc;
    /// # use pest;
    /// # #[allow(non_camel_case_types)]
    /// # #[derive(Clone, Copy, Debug, Eq, Hash, Ord, PartialEq, PartialOrd)]
    /// enum Rule {
    ///     a,
    ///     b
    /// }
    ///
    /// let input = "";
    /// let pairs = pest::state(input, |state| {
    ///     // generating nested Token pair with Rule::b inside Rule::a
    /// #     state.rule(Rule::a, |state| {
    /// #         state.rule(Rule::b, |s| Ok(s))
    /// #     })
    /// }).unwrap();
    /// let tokens: Vec<_> = pairs.flatten().tokens().collect();
    ///
    /// assert_eq!(tokens.len(), 4);
    /// ```
    #[inline]
    pub fn flatten(self) -> FlatPairs<'i, R> {
        unsafe { flat_pairs::new(self.queue, self.input, self.start, self.end) }
    }

    /// Returns the `Tokens` for the `Pairs`.
    ///
    /// # Examples
    ///
    /// ```
    /// # use std::rc::Rc;
    /// # use pest;
    /// # #[allow(non_camel_case_types)]
    /// # #[derive(Clone, Copy, Debug, Eq, Hash, Ord, PartialEq, PartialOrd)]
    /// enum Rule {
    ///     a
    /// }
    ///
    /// let input = "";
    /// let pairs = pest::state(input, |state| {
    ///     // generating Token pair with Rule::a ...
    /// #     state.rule(Rule::a, |s| Ok(s))
    /// }).unwrap();
    /// let tokens: Vec<_> = pairs.tokens().collect();
    ///
    /// assert_eq!(tokens.len(), 2);
    /// ```
    #[inline]
    pub fn tokens(self) -> Tokens<'i, R> {
        tokens::new(self.queue, self.input, self.start, self.end)
    }

    /// Peek at the first inner `Pair` without changing the position of this iterator.
    #[inline]
    pub fn peek(&self) -> Option<Pair<'i, R>> {
        if self.start < self.end {
            Some(unsafe { pair::new(Rc::clone(&self.queue), self.input, self.start) })
        } else {
            None
        }
    }

    /// Generates a string that stores the lexical information of `self` in
    /// a pretty-printed JSON format.
    #[cfg(feature = "pretty-print")]
    pub fn to_json(&self) -> String {
        ::serde_json::to_string_pretty(self).expect("Failed to pretty-print Pairs to json.")
    }

    fn pair(&self) -> usize {
        match self.queue[self.start] {
            QueueableToken::Start {
                end_token_index, ..
            } => end_token_index,
            _ => unreachable!(),
        }
    }

    fn pair_from_end(&self) -> usize {
        match self.queue[self.end - 1] {
            QueueableToken::End {
                start_token_index, ..
            } => start_token_index,
            _ => unreachable!(),
        }
    }

    fn pos(&self, index: usize) -> usize {
        match self.queue[index] {
            QueueableToken::Start { input_pos, .. } | QueueableToken::End { input_pos, .. } => {
                input_pos
            }
        }
    }

    /// Move the cursor (line, col) by a part of the input.
    fn move_cursor(&mut self, input: &str, start: usize, end: usize) -> (usize, usize) {
        // Move cursor for some skiped characters (by skip(n))
        let prev_end = self.cursor.end;
        if prev_end != start {
            self.move_cursor(input, prev_end, start);
        }

        let (prev_line, prev_col) = (self.cursor.line, self.cursor.col);

        let part = &input[self.cursor.end..end];
        let (l, c) = position::line_col(part, part.len(), (0, 0));

        self.cursor.line += l;
        // Has new line
        if l > 0 {
            self.cursor.col = c;
        } else {
            self.cursor.col += c;
        }
        self.cursor.end = end;

        (prev_line, prev_col)
    }
}

impl<'i, R: RuleType> Iterator for Pairs<'i, R> {
    type Item = Pair<'i, R>;

    fn next(&mut self) -> Option<Self::Item> {
        let mut pair = self.peek()?;
        let span = pair.as_span();

        let (l, c) = self.move_cursor(self.input, span.start(), span.end());
        pair.line_col = Some((l, c));

        self.start = self.pair() + 1;
        Some(pair)
    }
}

impl<'i, R: RuleType> DoubleEndedIterator for Pairs<'i, R> {
    fn next_back(&mut self) -> Option<Self::Item> {
        if self.end <= self.start {
            return None;
        }

        self.end = self.pair_from_end();

        let pair = unsafe { pair::new(Rc::clone(&self.queue), self.input, self.end) };

        Some(pair)
    }
}

impl<'i, R: RuleType> fmt::Debug for Pairs<'i, R> {
    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
        f.debug_list().entries(self.clone()).finish()
    }
}

impl<'i, R: RuleType> fmt::Display for Pairs<'i, R> {
    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
        write!(
            f,
            "[{}]",
            self.clone()
                .map(|pair| format!("{}", pair))
                .collect::<Vec<_>>()
                .join(", ")
        )
    }
}

impl<'i, R: PartialEq> PartialEq for Pairs<'i, R> {
    fn eq(&self, other: &Pairs<'i, R>) -> bool {
        Rc::ptr_eq(&self.queue, &other.queue)
            && ptr::eq(self.input, other.input)
            && self.start == other.start
            && self.end == other.end
    }
}

impl<'i, R: Eq> Eq for Pairs<'i, R> {}

impl<'i, R: Hash> Hash for Pairs<'i, R> {
    fn hash<H: Hasher>(&self, state: &mut H) {
        (&*self.queue as *const Vec<QueueableToken<R>>).hash(state);
        (self.input as *const str).hash(state);
        self.start.hash(state);
        self.end.hash(state);
    }
}

#[cfg(feature = "pretty-print")]
impl<'i, R: RuleType> ::serde::Serialize for Pairs<'i, R> {
    fn serialize<S>(&self, serializer: S) -> Result<S::Ok, S::Error>
    where
        S: ::serde::Serializer,
    {
        let start = self.pos(self.start);
        let end = self.pos(self.end - 1);
        let pairs = self.clone().collect::<Vec<_>>();

        let mut ser = serializer.serialize_struct("Pairs", 2)?;
        ser.serialize_field("pos", &(start, end))?;
        ser.serialize_field("pairs", &pairs)?;
        ser.end()
    }
}

#[cfg(test)]
mod tests {
    use super::super::super::macros::tests::*;
    use super::super::super::Parser;
    use alloc::borrow::ToOwned;
    use alloc::format;
    use alloc::vec;
    use alloc::vec::Vec;

    #[test]
    #[cfg(feature = "pretty-print")]
    fn test_pretty_print() {
        let pairs = AbcParser::parse(Rule::a, "abcde").unwrap();

        let expected = r#"{
  "pos": [
    0,
    5
  ],
  "pairs": [
    {
      "pos": [
        0,
        3
      ],
      "rule": "a",
      "inner": {
        "pos": [
          1,
          2
        ],
        "pairs": [
          {
            "pos": [
              1,
              2
            ],
            "rule": "b",
            "inner": "b"
          }
        ]
      }
    },
    {
      "pos": [
        4,
        5
      ],
      "rule": "c",
      "inner": "e"
    }
  ]
}"#;

        assert_eq!(expected, pairs.to_json());
    }

    #[test]
    fn as_str() {
        let pairs = AbcParser::parse(Rule::a, "abcde").unwrap();

        assert_eq!(pairs.as_str(), "abcde");
    }

    #[test]
    fn as_str_empty() {
        let mut pairs = AbcParser::parse(Rule::a, "abcde").unwrap();

        assert_eq!(pairs.nth(1).unwrap().into_inner().as_str(), "");
    }

    #[test]
    fn concat() {
        let pairs = AbcParser::parse(Rule::a, "abcde").unwrap();

        assert_eq!(pairs.concat(), "abce");
    }

    #[test]
    fn pairs_debug() {
        let pairs = AbcParser::parse(Rule::a, "abcde").unwrap();

        #[rustfmt::skip]
        assert_eq!(
            format!("{:?}", pairs),
            "[\
                Pair { rule: a, span: Span { str: \"abc\", start: 0, end: 3 }, inner: [\
                    Pair { rule: b, span: Span { str: \"b\", start: 1, end: 2 }, inner: [] }\
                ] }, \
                Pair { rule: c, span: Span { str: \"e\", start: 4, end: 5 }, inner: [] }\
            ]"
            .to_owned()
        );
    }

    #[test]
    fn pairs_display() {
        let pairs = AbcParser::parse(Rule::a, "abcde").unwrap();

        assert_eq!(
            format!("{}", pairs),
            "[a(0, 3, [b(1, 2)]), c(4, 5)]".to_owned()
        );
    }

    #[test]
    fn iter_for_pairs() {
        let pairs = AbcParser::parse(Rule::a, "abcde").unwrap();
        assert_eq!(
            pairs.map(|p| p.as_rule()).collect::<Vec<Rule>>(),
            vec![Rule::a, Rule::c]
        );
    }

    #[test]
    fn double_ended_iter_for_pairs() {
        let pairs = AbcParser::parse(Rule::a, "abcde").unwrap();
        assert_eq!(
            pairs.rev().map(|p| p.as_rule()).collect::<Vec<Rule>>(),
            vec![Rule::c, Rule::a]
        );
    }

    #[test]
    fn test_line_col() {
        let mut pairs = AbcParser::parse(Rule::a, "abc\nefgh").unwrap();
        let pair = pairs.next().unwrap();
        assert_eq!(pair.as_str(), "abc");
        assert_eq!(pair.line_col(), (1, 1));
        assert_eq!(
            (pairs.cursor.line, pairs.cursor.col, pairs.cursor.end),
            (1, 4, 3)
        );

        let pair = pairs.next().unwrap();
        assert_eq!(pair.as_str(), "e");
        assert_eq!(pair.line_col(), (2, 1));
        assert_eq!(
            (pairs.cursor.line, pairs.cursor.col, pairs.cursor.end),
            (2, 2, 5)
        );

        let pair = pairs.next().unwrap();
        assert_eq!(pair.as_str(), "fgh");
        assert_eq!(pair.line_col(), (2, 2));
        assert_eq!(
            (pairs.cursor.line, pairs.cursor.col, pairs.cursor.end),
            (2, 5, 8)
        );
    }

    #[test]
    fn test_rev_iter_line_col() {
        let mut pairs = AbcParser::parse(Rule::a, "abc\nefgh").unwrap().rev();
        let pair = pairs.next().unwrap();
        assert_eq!(pair.as_str(), "fgh");
        assert_eq!(pair.line_col(), (2, 2));

        let pair = pairs.next().unwrap();
        assert_eq!(pair.as_str(), "e");
        assert_eq!(pair.line_col(), (2, 1));

        let pair = pairs.next().unwrap();
        assert_eq!(pair.as_str(), "abc");
        assert_eq!(pair.line_col(), (1, 1));
    }
}