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
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
#![allow(dead_code)]
#![allow(unused_mut)]
#![allow(unreachable_code)]

extern crate regex;

#[macro_use]
extern crate lazy_static;

use regex::Regex;
use std::collections::HashMap;

/**
 * Stack value.
 */
enum SV {
    Undefined,
    _0(Token),
    _1(i32)
}

/**
 * Lex rules.
 */
static LEX_RULES: [&'static str; 6] = [
    r##########"^\s+"##########,
    r##########"^\d+"##########,
    r##########"^\+"##########,
    r##########"^\*"##########,
    r##########"^\("##########,
    r##########"^\)"##########
];

/**
 * EOF value.
 */
static EOF: &'static str = "$";

/**
 * A macro for map literals.
 *
 * hashmap!{ 1 => "one", 2 => "two" };
 */
macro_rules! hashmap(
    { $($key:expr => $value:expr),+ } => {
        {
            let mut m = ::std::collections::HashMap::new();
            $(
                m.insert($key, $value);
            )+
            m
        }
     };
);

/**
 * Unwraps a SV for the result. The result type is known from the grammar.
 */
macro_rules! get_result {
    ($r:expr, $ty:ident) => (match $r { SV::$ty(v) => v, _ => unreachable!() });
}

/**
 * Pops a SV with needed enum value.
 */
macro_rules! pop {
    ($s:expr, $ty:ident) => (get_result!($s.pop().unwrap(), $ty));
}

/**
 * Productions data.
 *
 * 0 - encoded non-terminal, 1 - length of RHS to pop from the stack
 */
static PRODUCTIONS : [[i32; 2]; 5] = [
    [-1, 1],
    [0, 3],
    [0, 3],
    [0, 1],
    [0, 3]
];

/**
 * Table entry.
 */
enum TE {
    Accept,

    // Shift, and transit to the state.
    Shift(usize),

    // Reduce by a production number.
    Reduce(usize),

    // Simple state transition.
    Transit(usize),
}

lazy_static! {
    /**
     * Lexical rules grouped by lexer state (by start condition).
     */
    static ref LEX_RULES_BY_START_CONDITIONS: HashMap<&'static str, Vec<i32>> = hashmap! { "INITIAL" => vec! [ 0, 1, 2, 3, 4, 5 ] };

    /**
     * Maps a string name of a token type to its encoded number (the first
     * token number starts after all numbers for non-terminal).
     */
    static ref TOKENS_MAP: HashMap<&'static str, i32> = hashmap! { "+" => 1, "*" => 2, "NUMBER" => 3, "(" => 4, ")" => 5, "$" => 6 };

    /**
     * Parsing table.
     *
     * Vector index is the state number, value is a map
     * from an encoded symbol to table entry (TE).
     */
    static ref TABLE: Vec<HashMap<i32, TE>>= vec![
    hashmap! { 0 => TE::Transit(1), 3 => TE::Shift(2), 4 => TE::Shift(3) },
    hashmap! { 1 => TE::Shift(4), 2 => TE::Shift(5), 6 => TE::Accept },
    hashmap! { 1 => TE::Reduce(3), 2 => TE::Reduce(3), 5 => TE::Reduce(3), 6 => TE::Reduce(3) },
    hashmap! { 0 => TE::Transit(8), 3 => TE::Shift(2), 4 => TE::Shift(3) },
    hashmap! { 0 => TE::Transit(6), 3 => TE::Shift(2), 4 => TE::Shift(3) },
    hashmap! { 0 => TE::Transit(7), 3 => TE::Shift(2), 4 => TE::Shift(3) },
    hashmap! { 1 => TE::Reduce(1), 2 => TE::Shift(5), 5 => TE::Reduce(1), 6 => TE::Reduce(1) },
    hashmap! { 1 => TE::Reduce(2), 2 => TE::Reduce(2), 5 => TE::Reduce(2), 6 => TE::Reduce(2) },
    hashmap! { 1 => TE::Shift(4), 2 => TE::Shift(5), 5 => TE::Shift(9) },
    hashmap! { 1 => TE::Reduce(4), 2 => TE::Reduce(4), 5 => TE::Reduce(4), 6 => TE::Reduce(4) }
];
}

// ------------------------------------
// Module include prologue.
//
// Should include at least result type:
//
// type TResult = <...>;
//
// Can also include parsing hooks:
//
//   fn on_parse_begin(parser: &mut Parser, string: &'static str) {
//     ...
//   }
//
//   fn on_parse_begin(parser: &mut Parser, string: &'static str) {
//     ...
//   }
//

// Important: define the type of the parsing result:

type TResult = i32;

// ---  end of Module include ---------

/**
 * Generic tokenizer used by the parser in the Syntax tool.
 *
 * https://www.npmjs.com/package/syntax-cli
 */

// ------------------------------------------------------------------
// Token.

#[derive(Debug, Clone, Copy)]
struct Token {
    kind: i32,
    value: &'static str,

    start_offset: i32,
    end_offset: i32,
    start_line: i32,
    end_line: i32,
    start_column: i32,
    end_column: i32,
}

// NOTE: LEX_RULES_BY_START_CONDITIONS, and TOKENS_MAP
// are defined in the lazy_static! block in lr.templates.rs

// ------------------------------------------------------------------
// Tokenizer.

lazy_static! {
    /** 
     * Pre-parse the regex instead of parsing it every time when calling `get_next_token`.
     */
    static ref REGEX_RULES: Vec<Regex> = LEX_RULES.iter().map(|rule| Regex::new(rule).unwrap()).collect();
}

struct Tokenizer {
    /**
     * Tokenizing string.
     */
    string: &'static str,

    /**
     * Cursor for current symbol.
     */
    cursor: i32,

    /**
     * States.
     */
    states: Vec<&'static str>,

    /**
     * Line-based location tracking.
     */
    current_line: i32,
    current_column: i32,
    current_line_begin_offset: i32,

    /**
     * Location data of a matched token.
     */
    token_start_offset: i32,
    token_end_offset: i32,
    token_start_line: i32,
    token_end_line: i32,
    token_start_column: i32,
    token_end_column: i32,

    /**
     * Matched text, and its length.
     */
    yytext: &'static str,
    yyleng: usize,

    handlers: [fn(&mut Tokenizer) -> &'static str; 6],
}

impl Tokenizer {

    /**
     * Creates a new Tokenizer instance.
     *
     * The same instance can be then reused in parser
     * by calling `init_string`.
     */
    pub fn new() -> Tokenizer {
        let mut tokenizer = Tokenizer {
            string: "",
            cursor: 0,

            states: Vec::new(),

            current_line: 1,
            current_column: 0,
            current_line_begin_offset: 0,

            token_start_offset: 0,
            token_end_offset: 0,
            token_start_line: 0,
            token_end_line: 0,
            token_start_column: 0,
            token_end_column: 0,

            yytext: "",
            yyleng: 0,

            handlers: [
    Tokenizer::_lex_rule0,
    Tokenizer::_lex_rule1,
    Tokenizer::_lex_rule2,
    Tokenizer::_lex_rule3,
    Tokenizer::_lex_rule4,
    Tokenizer::_lex_rule5
],
        };

        tokenizer
    }

    /**
     * Initializes a parsing string.
     */
    pub fn init_string(&mut self, string: &'static str) -> &mut Tokenizer {
        self.string = string;

        // Initialize states.
        self.states.clear();
        self.states.push("INITIAL");

        self.cursor = 0;
        self.current_line = 1;
        self.current_column = 0;
        self.current_line_begin_offset = 0;

        self.token_start_offset = 0;
        self.token_end_offset = 0;
        self.token_start_line = 0;
        self.token_end_line = 0;
        self.token_start_column = 0;
        self.token_end_column = 0;

        self
    }

    /**
     * Returns next token.
     */
    pub fn get_next_token(&mut self) -> Token {
        if !self.has_more_tokens() {
            self.yytext = EOF;
            return self.to_token(EOF)
        }

        let str_slice = &self.string[self.cursor as usize..];

        let lex_rules_for_state = LEX_RULES_BY_START_CONDITIONS
            .get(self.get_current_state())
            .unwrap();

        for i in lex_rules_for_state {
            let i = *i as usize;
            
            if let Some(matched) = self._match(str_slice, &REGEX_RULES[i]) {

                // Manual handling of EOF token (the end of string). Return it
                // as `EOF` symbol.
                if matched.len() == 0 {
                    self.cursor = self.cursor + 1;
                }
                
                self.yytext = matched;
                self.yyleng = matched.len();

                let token_type = self.handlers[i](self);

                // "" - no token (skip)
                if token_type.len() == 0 {
                    return self.get_next_token();
                }

                return self.to_token(token_type)
            }
        }

        if self.is_eof() {
            self.cursor = self.cursor + 1;
            self.yytext = EOF;
            return self.to_token(EOF);
        }

        self.panic_unexpected_token(
            &str_slice[0..1],
            self.current_line,
            self.current_column
        );

        unreachable!()
    }

    /**
     * Throws default "Unexpected token" exception, showing the actual
     * line from the source, pointing with the ^ marker to the bad token.
     * In addition, shows `line:column` location.
     */
    fn panic_unexpected_token(&self, string: &'static str, line: i32, column: i32) {
        let line_source = self.string
            .split('\n')
            .collect::<Vec<&str>>()
            [(line - 1) as usize];

        let pad = ::std::iter::repeat(" ")
            .take(column as usize)
            .collect::<String>();

        let line_data = format!("\n\n{}\n{}^\n", line_source, pad);

        panic!(
            "{} Unexpected token: \"{}\" at {}:{}.",
            line_data,
            string,
            line,
            column
        );
    }

    fn capture_location(&mut self, matched: &'static str) {
        let nl_re = Regex::new(r"\n").unwrap();

        // Absolute offsets.
        self.token_start_offset = self.cursor;

        // Line-based locations, start.
        self.token_start_line = self.current_line;
        self.token_start_column = self.token_start_offset - self.current_line_begin_offset;

        // Extract `\n` in the matched token.
        for cap in nl_re.captures_iter(matched) {
            self.current_line = self.current_line + 1;
            self.current_line_begin_offset = self.token_start_offset +
                cap.get(0).unwrap().start() as i32 + 1;
        }

        self.token_end_offset = self.cursor + matched.len() as i32;

        // Line-based locations, end.
        self.token_end_line = self.current_line;
        self.token_end_column = self.token_end_offset - self.current_line_begin_offset;
        self.current_column = self.token_end_column;
    }

    fn _match(&mut self, str_slice: &'static str, re: &Regex) -> Option<&'static str> {
        match re.captures(str_slice) {
            Some(caps) => {
                let matched = caps.get(0).unwrap().as_str();
                self.capture_location(matched);
                self.cursor = self.cursor + (matched.len() as i32);
                Some(matched)
            },
            None => None
        }
    }

    fn to_token(&self, token: &'static str) -> Token {
        Token {
            kind: *TOKENS_MAP.get(token).unwrap(),
            value: self.yytext,
            start_offset: self.token_start_offset,
            end_offset: self.token_end_offset,
            start_line: self.token_start_line,
            end_line: self.token_end_line,
            start_column: self.token_start_column,
            end_column: self.token_end_column,
        }
    }

    /**
     * Whether there are still tokens in the stream.
     */
    pub fn has_more_tokens(&mut self) -> bool {
        self.cursor <= self.string.len() as i32
    }

    /**
     * Whether the cursor is at the EOF.
     */
    pub fn is_eof(&mut self) -> bool {
        self.cursor == self.string.len() as i32
    }

    /**
     * Returns current tokenizing state.
     */
    pub fn get_current_state(&mut self) -> &'static str {
        match self.states.last() {
            Some(last) => last,
            None => "INITIAL"
        }
    }

    /**
     * Enters a new state pushing it on the states stack.
     */
    pub fn push_state(&mut self, state: &'static str) -> &mut Tokenizer {
        self.states.push(state);
        self
    }

    /**
     * Alias for `push_state`.
     */
    pub fn begin(&mut self, state: &'static str) -> &mut Tokenizer {
        self.push_state(state);
        self
    }

    /**
     * Exits a current state popping it from the states stack.
     */
    pub fn pop_state(&mut self) -> &'static str {
        match self.states.pop() {
            Some(top) => top,
            None => "INITIAL"
        }
    }

    /**
     * Lex rule handlers.
     */
    fn _lex_rule0(&mut self) -> &'static str {
/* skip whitespace */ return "";
}

fn _lex_rule1(&mut self) -> &'static str {
return "NUMBER";
}

fn _lex_rule2(&mut self) -> &'static str {
return "+";
}

fn _lex_rule3(&mut self) -> &'static str {
return "*";
}

fn _lex_rule4(&mut self) -> &'static str {
return "(";
}

fn _lex_rule5(&mut self) -> &'static str {
return ")";
}
}


// ------------------------------------------------------------------
// Parser.

/**
 * Parser.
 */
pub struct Parser {
    /**
     * Parsing stack: semantic values.
     */
    values_stack: Vec<SV>,

    /**
     * Parsing stack: state numbers.
     */
    states_stack: Vec<usize>,

    /**
     * Tokenizer instance.
     */
    tokenizer: Tokenizer,

    /**
     * Semantic action handlers.
     */
    handlers: [fn(&mut Parser) -> SV; 5],
}

impl Parser {
    /**
     * Creates a new Parser instance.
     */
    pub fn new() -> Parser {
        Parser {
            // Stacks.
            values_stack: Vec::new(),
            states_stack: Vec::new(),

            tokenizer: Tokenizer::new(),

            handlers: [
    Parser::_handler0,
    Parser::_handler1,
    Parser::_handler2,
    Parser::_handler3,
    Parser::_handler4
],
        }
    }

    /**
     * Parses a string.
     */
    pub fn parse(&mut self, string: &'static str) -> TResult {
        

        // Initialize the tokenizer and the string.
        self.tokenizer.init_string(string);

        // Initialize the stacks.
        self.values_stack.clear();

        // Initial 0 state.
        self.states_stack.clear();
        self.states_stack.push(0);

        let mut token = self.tokenizer.get_next_token();
        let mut shifted_token = token;

        loop {
            let state = *self.states_stack.last().unwrap();
            let column = token.kind;

            if !TABLE[state].contains_key(&column) {
                self.unexpected_token(&token);
                break;
            }

            let entry = &TABLE[state][&column];

            match entry {

                // Shift a token, go to state.
                &TE::Shift(next_state) => {
                    // Push token.
                    self.values_stack.push(SV::_0(token));

                    // Push next state number: "s5" -> 5
                    self.states_stack.push(next_state as usize);

                    shifted_token = token;
                    token = self.tokenizer.get_next_token();
                },

                // Reduce by production.
                &TE::Reduce(production_number) => {
                    let production = PRODUCTIONS[production_number];

                    self.tokenizer.yytext = shifted_token.value;
                    self.tokenizer.yyleng = shifted_token.value.len();

                    let mut rhs_length = production[1];
                    while rhs_length > 0 {
                        self.states_stack.pop();
                        rhs_length = rhs_length - 1;
                    }

                    // Call the handler, push result onto the stack.
                    let result_value = self.handlers[production_number](self);

                    let previous_state = *self.states_stack.last().unwrap();
                    let symbol_to_reduce_with = production[0];

                    // Then push LHS onto the stack.
                    self.values_stack.push(result_value);

                    let next_state = match &TABLE[previous_state][&symbol_to_reduce_with] {
                        &TE::Transit(next_state) => next_state,
                        _ => unreachable!(),
                    };

                    self.states_stack.push(next_state);
                },

                // Accept the string.
                &TE::Accept => {
                    // Pop state number.
                    self.states_stack.pop();

                    // Pop the parsed value.
                    let parsed = self.values_stack.pop().unwrap();

                    if self.states_stack.len() != 1 ||
                        self.states_stack.pop().unwrap() != 0 ||
                        self.tokenizer.has_more_tokens() {
                        self.unexpected_token(&token);
                    }

                    let result = get_result!(parsed, _1);
                    
                    return result;
                },

                _ => unreachable!(),
            }
        }

        unreachable!();
    }

    fn unexpected_token(&mut self, token: &Token) {
        
  if token.value == EOF && !self.tokenizer.has_more_tokens() {
    panic!("Unexpected end of input.");
  }
  self.tokenizer.panic_unexpected_token(token.value, token.start_line, token.start_column);

    }

    fn _handler0(&mut self) -> SV {
// Semantic values prologue.
let mut _1 = self.values_stack.pop().unwrap();

let __ = _1;
__
}

fn _handler1(&mut self) -> SV {
// Semantic values prologue.
let mut _3 = pop!(self.values_stack, _1);
self.values_stack.pop();
let mut _1 = pop!(self.values_stack, _1);

// Types of used args, and the return type.

        let __ = _1 + _3;
SV::_1(__)
}

fn _handler2(&mut self) -> SV {
// Semantic values prologue.
let mut _3 = pop!(self.values_stack, _1);
self.values_stack.pop();
let mut _1 = pop!(self.values_stack, _1);

let __ = _1 * _3;
SV::_1(__)
}

fn _handler3(&mut self) -> SV {
// Semantic values prologue.
self.values_stack.pop();

let __ = self.tokenizer.yytext.parse::<i32>().unwrap();
SV::_1(__)
}

fn _handler4(&mut self) -> SV {
// Semantic values prologue.
self.values_stack.pop();
let mut _2 = self.values_stack.pop().unwrap();
self.values_stack.pop();

let __ = _2;
__
}
}