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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984
//! Build script for rusty_lr
//!
//! This crate is private and not intended to be used directly.
//! Please use the [`rusty_lr`](https://crates.io/crates/rusty_lr) crate instead.
//!
//! ```no_run
//! fn main() {
//! println!("cargo::rerun-if-changed=src/parser/parser.rs");
//!
//! let output_dir = std::env::var("OUT_DIR").unwrap();
//! let output = format!("{}/parser.rs", output_dir);
//! Builder::new()
//! .file("src/parser/parser.rs")
//! .build(&output);
//! }
//!
pub mod output;
mod split;
mod utils;
use codespan_reporting::diagnostic::Diagnostic;
use codespan_reporting::diagnostic::Label;
use codespan_reporting::files::SimpleFiles;
use codespan_reporting::term;
use codespan_reporting::term::termcolor::ColorChoice;
use codespan_reporting::term::termcolor::StandardStream;
use proc_macro2::Ident;
use proc_macro2::Span;
use proc_macro2::TokenStream;
use quote::quote;
use rusty_lr_core::ShiftedRule;
use rusty_lr_parser::error::ArgError;
use rusty_lr_parser::error::EmitError;
use rusty_lr_parser::error::ParseArgError;
use rusty_lr_parser::error::ParseError;
use std::collections::BTreeMap;
use std::collections::BTreeSet;
use std::fs::read;
use std::fs::write;
/// Main entry for the build script
pub struct Builder {
/// input_file to read
input_file: Option<String>,
/// when `vebose` is on, print debug information about
/// any shift/reduce, reduce/reduce conflicts.
/// This is for GLR parser, to show where the conflicts occured.
verbose_conflicts: bool,
/// when `vebose` is on, print debug information about
/// conflicts resolving process by `%left` or `%right` for any shift/reduce, reduce/reduce conflicts.
verbose_conflicts_resolving: bool,
/// print verbose information to stderr
verbose_on_stderr: bool,
}
impl Builder {
pub fn new() -> Self {
Self {
input_file: None,
verbose_conflicts: false,
verbose_conflicts_resolving: false,
verbose_on_stderr: false,
}
}
/// set input file
pub fn file(&mut self, filename: &str) -> &mut Self {
self.input_file = Some(filename.to_string());
self
}
/// turns on all verbose options
pub fn verbose(&mut self) -> &mut Self {
self.verbose_conflicts();
self.verbose_conflicts_resolving();
self
}
/// when `vebose` is on, print debug information about
/// any shift/reduce, reduce/reduce conflicts.
pub fn verbose_conflicts(&mut self) -> &mut Self {
self.verbose_conflicts = true;
self
}
/// when `vebose` is on, print debug information about
/// conflicts resolving process by `%left` or `%right` for any shift/reduce, reduce/reduce conflicts.
pub fn verbose_conflicts_resolving(&mut self) -> &mut Self {
self.verbose_conflicts_resolving = true;
self
}
/// print debug information to stderr.
pub fn verbose_on_stderr(&mut self) -> &mut Self {
self.verbose_on_stderr = true;
self
}
fn verbose_stream(&self) -> StandardStream {
if self.verbose_on_stderr {
StandardStream::stderr(ColorChoice::Auto)
} else {
StandardStream::stdout(ColorChoice::Auto)
}
}
/// build and emit code to output file
pub fn build(&self, output_file: &str) {
let output = match self.build_impl() {
Ok(output) => {
let stream1 = output.user_stream;
let stream2 = output.generated_stream;
quote! {
#stream1
#stream2
}
}
Err(_) => {
panic!("build failed");
}
};
write(output_file, output.to_string()).expect("Failed to write to file");
}
/// extend `labels` with messages about the source of the rule
/// if `ruleid` is auto-generated rule, "{} was generated here" will be added
/// if `ruleid` is user-written rule, "{} was defined here" will be added
fn extend_rule_source_label(
labels: &mut Vec<codespan_reporting::diagnostic::Label<usize>>,
fileid: usize,
ruleid: usize,
grammar: &rusty_lr_parser::grammar::Grammar,
prefix_str: &str,
) {
let (nonterm, local_rule) = grammar.get_rule_by_id(ruleid).expect("Rule not found");
if let Some(origin_span) = &nonterm.regex_span {
let origin_range = origin_span.0.byte_range().start..origin_span.1.byte_range().end;
labels.push(Label::primary(fileid, origin_range).with_message(format!(
"{}{} was generated here",
prefix_str, nonterm.pretty_name,
)));
} else {
let (rule_begin, rule_end) = nonterm.rules[local_rule].span_pair();
let rule_range = rule_begin.byte_range().start..rule_end.byte_range().end;
labels.push(
Label::primary(fileid, nonterm.name.span().byte_range()).with_message(format!(
"{}{} was defined here",
prefix_str, nonterm.pretty_name
)),
);
labels.push(
Label::secondary(fileid, rule_range).with_message("in this line".to_string()),
);
}
}
/// for internal use
pub fn build_impl(&self) -> Result<output::Output, String> {
if self.input_file.is_none() {
eprintln!("Input file not set");
return Err("Input file not set".to_string());
}
let input_file = self.input_file.as_ref().unwrap();
// read file
let input_bytes = match read(input_file) {
Ok(bytes) => bytes,
Err(e) => {
let message = format!("Error reading file: {}", e);
eprintln!("{}", message);
return Err(message);
}
};
let str = match String::from_utf8(input_bytes) {
Ok(str) => str,
Err(e) => {
let message = format!("Error reading utf-8: {}", e);
eprintln!("{}", message);
return Err(message);
}
};
let mut files = SimpleFiles::new();
let file_id = files.add(input_file, str.clone());
// lex with proc-macro2
let token_stream: TokenStream = match str.parse() {
Ok(token_stream) => token_stream,
Err(e) => {
let range = e.span().byte_range();
let diag = Diagnostic::error()
.with_message("Lexing error")
.with_labels(vec![
Label::primary(file_id, range).with_message(e.to_string())
]);
let writer = StandardStream::stderr(ColorChoice::Auto);
let config = codespan_reporting::term::Config::default();
term::emit(&mut writer.lock(), &config, &files, &diag)
.expect("Failed to write to stderr");
return Err("Lexing error".to_string());
}
};
// split stream by '%%'
let (output_stream, macro_stream) = match split::split_stream(token_stream) {
Ok((output_stream, macro_stream)) => (output_stream, macro_stream),
Err(_) => {
let diag = Diagnostic::error()
.with_message("Cannot find `%%`")
.with_notes(vec![
"Please put `%%` to separate the code part and the context-free grammar part"
.to_string(),
]);
let writer = StandardStream::stderr(ColorChoice::Auto);
let config = codespan_reporting::term::Config::default();
term::emit(&mut writer.lock(), &config, &files, &diag)
.expect("Failed to write to stderr");
return Err(diag.message);
}
};
let grammar_args = match rusty_lr_parser::grammar::Grammar::parse_args(macro_stream) {
Ok(grammar_args) => grammar_args,
Err(e) => {
let diag =
match e {
ParseArgError::MacroLineParse { span, message } => {
let range = span.byte_range();
Diagnostic::error()
.with_message("Parse Failed")
.with_labels(vec![
Label::primary(file_id, range).with_message("Error here")
])
.with_notes(vec![message])
}
ParseArgError::MacroLineParseEnd { message } => Diagnostic::error()
.with_message("Parse Failed")
.with_notes(vec![message]),
_ => {
let message = e.short_message();
let span = e.span().byte_range();
Diagnostic::error().with_message(message).with_labels(vec![
Label::primary(file_id, span).with_message("occured here"),
])
}
};
let writer = StandardStream::stderr(ColorChoice::Auto);
let config = codespan_reporting::term::Config::default();
term::emit(&mut writer.lock(), &config, &files, &diag)
.expect("Failed to write to stderr");
return Err(diag.message);
}
};
match rusty_lr_parser::grammar::Grammar::arg_check_error(&grammar_args) {
Ok(_) => {}
Err(e) => {
let diag = match e {
ArgError::MultipleModulePrefixDefinition(
(span1, tokenstream1),
(span2, tokenstream2),
) => {
let range1 = utils::span_stream_range(span1, tokenstream1);
let range2 = utils::span_stream_range(span2, tokenstream2);
Diagnostic::error()
.with_message("Multiple %moduleprefix definition")
.with_labels(vec![
Label::primary(file_id, range1).with_message("First definition"),
Label::primary(file_id, range2).with_message("Other definition"),
])
.with_notes(vec![
"Only one %moduleprefix definition is allowed".to_string()
])
}
ArgError::MultipleUserDataDefinition(
(span1, tokenstream1),
(span2, tokenstream2),
) => {
let range1 = utils::span_stream_range(span1, tokenstream1);
let range2 = utils::span_stream_range(span2, tokenstream2);
Diagnostic::error()
.with_message("Multiple %userdata definition")
.with_labels(vec![
Label::primary(file_id, range1).with_message("First definition"),
Label::primary(file_id, range2).with_message("Other definition"),
])
.with_notes(
vec!["Only one %userdata definition is allowed".to_string()],
)
}
ArgError::MultipleErrorDefinition(
(span1, tokenstream1),
(span2, tokenstream2),
) => {
let range1 = utils::span_stream_range(span1, tokenstream1);
let range2 = utils::span_stream_range(span2, tokenstream2);
Diagnostic::error()
.with_message("Multiple %error definition")
.with_labels(vec![
Label::primary(file_id, range1).with_message("First definition"),
Label::primary(file_id, range2).with_message("Other definition"),
])
.with_notes(vec!["Only one %error definition is allowed".to_string()])
}
ArgError::MultipleTokenTypeDefinition(
(span1, tokenstream1),
(span2, tokenstream2),
) => {
let range1 = utils::span_stream_range(span1, tokenstream1);
let range2 = utils::span_stream_range(span2, tokenstream2);
Diagnostic::error()
.with_message("Multiple %tokentype definition")
.with_labels(vec![
Label::primary(file_id, range1).with_message("First definition"),
Label::primary(file_id, range2).with_message("Other definition"),
])
.with_notes(vec![
"Only one %tokentype definition is allowed".to_string()
])
}
ArgError::MultipleEofDefinition(
(span1, tokenstream1),
(span2, tokenstream2),
) => {
let range1 = utils::span_stream_range(span1, tokenstream1);
let range2 = utils::span_stream_range(span2, tokenstream2);
Diagnostic::error()
.with_message("Multiple %eof definition")
.with_labels(vec![
Label::primary(file_id, range1).with_message("First definition"),
Label::primary(file_id, range2).with_message("Other definition"),
])
.with_notes(vec!["Only one %eof definition is allowed".to_string()])
}
ArgError::MultipleStartDefinition(ident1, ident2) => {
let range1 = ident1.span().byte_range();
let range2 = ident2.span().byte_range();
Diagnostic::error()
.with_message("Multiple %start definition")
.with_labels(vec![
Label::primary(file_id, range1).with_message("First definition"),
Label::primary(file_id, range2).with_message("Other definition"),
])
.with_notes(vec!["Only one %start definition is allowed".to_string()])
}
ArgError::StartNotDefined => Diagnostic::error()
.with_message("%start not defined")
.with_labels(vec![])
.with_notes(vec![
"%start must be defined".to_string(),
">>> %start <non-terminal>".to_string(),
]),
ArgError::EofNotDefined => Diagnostic::error()
.with_message("%eof not defined")
.with_labels(vec![])
.with_notes(vec![
"%eof must be defined".to_string(),
">>> %eof <terminal>".to_string(),
]),
ArgError::TokenTypeNotDefined => Diagnostic::error()
.with_message("%tokentype not defined")
.with_labels(vec![])
.with_notes(vec![
"%tokentype must be defined".to_string(),
">>> %tokentype <TokenType>".to_string(),
]),
_ => {
let message = e.short_message();
let span = e.span().byte_range();
Diagnostic::error()
.with_message(message)
.with_labels(vec![
Label::primary(file_id, span).with_message("occured here")
])
}
};
let writer = StandardStream::stderr(ColorChoice::Auto);
let config = codespan_reporting::term::Config::default();
term::emit(&mut writer.lock(), &config, &files, &diag)
.expect("Failed to write to stderr");
return Err(diag.message);
}
}
// parse lines
let grammar = match rusty_lr_parser::grammar::Grammar::from_grammar_args(grammar_args) {
Ok(grammar) => grammar,
Err(e) => {
let diag = match e {
ParseError::MultipleRuleDefinition(ident1, ident2) => {
let range1 = ident1.span().byte_range();
let range2 = ident2.span().byte_range();
Diagnostic::error()
.with_message("Multiple rule definition")
.with_labels(vec![
Label::primary(file_id, range1).with_message("First definition"),
Label::primary(file_id, range2).with_message("Other definition"),
])
.with_notes(vec!["Rule name must be unique".to_string()])
}
ParseError::MultipleReduceDefinition { terminal, old, new } => {
let old_range = old.0.byte_range().start..old.1.byte_range().end;
let old_string = match old.2 {
rusty_lr_core::ReduceType::Left => "%left",
rusty_lr_core::ReduceType::Right => "%right",
};
let new_range = new.0.byte_range().start..new.1.byte_range().end;
let new_string = match new.2 {
rusty_lr_core::ReduceType::Left => "%left",
rusty_lr_core::ReduceType::Right => "%right",
};
Diagnostic::error()
.with_message("Multiple reduce definition")
.with_labels(vec![
Label::primary(file_id, terminal.span().byte_range()).with_message(
"This terminal symbol is defined as both of %left and %right",
),
Label::secondary(file_id, old_range)
.with_message(format!("was set as {} here", old_string)),
Label::secondary(file_id, new_range)
.with_message(format!("was set as {} here", new_string)),
])
.with_notes(vec![
"Reduce type must be unique, either %left or %right".to_string()
])
}
ParseError::TermNonTermConflict {
name,
terminal,
non_terminal,
} => {
let range = name.span().byte_range();
Diagnostic::error()
.with_message("Ambiguous token name")
.with_labels(vec![
Label::primary(file_id, range).with_message(
"This name is used for both terminal and non-terminal",
),
Label::secondary(file_id, terminal.span().byte_range())
.with_message("Terminal definition here"),
Label::secondary(file_id, non_terminal.span().byte_range())
.with_message("Non-terminal definition here"),
])
.with_notes(vec![
"Terminal and non-terminal name must be unique".to_string()
])
}
ParseError::InvalidTerminalRange(
(first, first_index, first_stream),
(last, last_index, last_stream),
) => {
let range1 = first.span().byte_range();
let range2 = last.span().byte_range();
let range = range1.start..range2.end;
let range1 = utils::tokenstream_range(first_stream);
let range2 = utils::tokenstream_range(last_stream);
Diagnostic::error()
.with_message("Invalid terminal range")
.with_labels(vec![
Label::primary(file_id, range).with_message("Invalid range here"),
Label::secondary(file_id, range1).with_message(format!("First terminal symbol (index {})", first_index)),
Label::secondary(file_id, range2).with_message(format!("Last terminal symbol (index {})", last_index)),
]).with_notes(vec![
"First terminal symbol has to be less than or equal to the last terminal symbol".to_string()
])
}
ParseError::StartNonTerminalNotDefined(ident) => {
let range = ident.span().byte_range();
Diagnostic::error()
.with_message("Start non-terminal not defined")
.with_labels(vec![Label::primary(file_id, range)
.with_message("This name is given to %start")])
.with_notes(vec!["Non-terminal name must be defined".to_string()])
}
ParseError::TerminalNotDefined(ident) => {
let range = ident.span().byte_range();
Diagnostic::error()
.with_message("Terminal symbol not defined")
.with_labels(vec![Label::primary(file_id, range)
.with_message("This terminal symbol is not defined")])
.with_notes(vec!["Terminal symbol must be defined".to_string()])
}
ParseError::MultipleTokenDefinition(ident1, ident2) => {
let range1 = ident1.span().byte_range();
let range2 = ident2.span().byte_range();
Diagnostic::error()
.with_message("Multiple %token definition")
.with_labels(vec![
Label::primary(file_id, range1).with_message("First definition"),
Label::primary(file_id, range2).with_message("Other definition"),
])
.with_notes(vec!["Token name must be unique".to_string()])
}
ParseError::EofDefined(ident) => {
let range = ident.span().byte_range();
Diagnostic::error()
.with_message("'eof' is reserved name")
.with_labels(vec![Label::primary(file_id, range)
.with_message("This name is reserved")])
}
ParseError::AugmentedDefined(ident) => {
let range = ident.span().byte_range();
Diagnostic::error()
.with_message("'Augmented' is reserved name")
.with_labels(vec![Label::primary(file_id, range)
.with_message("This name is reserved")])
}
_ => {
let message = e.short_message();
let span = e.span().byte_range();
Diagnostic::error()
.with_message(message)
.with_labels(vec![
Label::primary(file_id, span).with_message("occured here")
])
}
};
let writer = StandardStream::stderr(ColorChoice::Auto);
let config = codespan_reporting::term::Config::default();
term::emit(&mut writer.lock(), &config, &files, &diag)
.expect("Failed to write to stderr");
return Err(diag.message);
}
};
// expand macro
let expanded_stream = match grammar.emit_compiletime() {
Ok(expanded_stream) => expanded_stream,
Err(e) => {
let diag = match e.as_ref() {
EmitError::RuleTypeDefinedButActionNotDefined {
name,
rule_local_id,
} => {
// `name` must not be generated rule,
// since it is programmically generated, it must have a proper reduce action
let rule_id = *grammar.nonterminals_index.get(name).unwrap();
let rule_line = &grammar.nonterminals[rule_id].rules[*rule_local_id];
let rule_line_range = if rule_line.tokens.is_empty() {
rule_line.separator_span.byte_range()
} else {
let first = rule_line.separator_span.byte_range().start;
let last = rule_line.tokens.last().unwrap().end_span.byte_range().end;
first..last
};
Diagnostic::error()
.with_message("Reduce action not defined")
.with_labels(vec![
Label::secondary(file_id, name.span().byte_range())
.with_message("This rule has a type definition"),
Label::primary(file_id, rule_line_range)
.with_message("This rule line has no reduce action"),
])
.with_notes(vec!["".to_string()])
}
EmitError::ShiftReduceConflict {
term,
reduce_rule: (reduceid, reduce_production_rule),
shift_rules,
} => {
let mut message = format!(
"Shift/Reduce conflict:\nReduce rule:\n\t>>> {}\nShift rules:",
reduce_production_rule
);
for (_, shifted_rule) in shift_rules.iter() {
message.push_str(format!("\n\t>>> {}", shifted_rule).as_str());
}
let mut labels = Vec::new();
Self::extend_rule_source_label(
&mut labels,
file_id,
*reduceid,
&grammar,
"(Reduce) ",
);
for (shiftid, _) in shift_rules.iter() {
Self::extend_rule_source_label(
&mut labels,
file_id,
*shiftid,
&grammar,
"(Shift) ",
);
}
Diagnostic::error()
.with_message(message)
.with_labels(labels)
.with_notes(vec![
format!("conflict terminal: {}", term),
format!(
"Try to rearrange the rules or resolve conflict by set reduce type"
),
format!(">>> %left {}", term),
format!(">>> %right {}", term),
])
}
EmitError::ReduceReduceConflict {
lookahead,
rule1: (ruleid1, production_rule1),
rule2: (ruleid2, production_rule2),
} => {
let mut labels = Vec::new();
Self::extend_rule_source_label(
&mut labels,
file_id,
*ruleid1,
&grammar,
"(Rule1) ",
);
Self::extend_rule_source_label(
&mut labels,
file_id,
*ruleid2,
&grammar,
"(Rule2) ",
);
Diagnostic::error()
.with_message(format!(
"Reduce/Reduce conflict:\n>>> {}\n>>> {}",
production_rule1, production_rule2
))
.with_labels(labels)
.with_notes(vec![format!("with lookahead {}", lookahead)])
}
_ => {
let message = e.short_message();
let span = e.span().byte_range();
Diagnostic::error()
.with_message(message)
.with_labels(vec![
Label::primary(file_id, span).with_message("occured here")
])
}
};
let writer = StandardStream::stderr(ColorChoice::Auto);
let config = codespan_reporting::term::Config::default();
term::emit(&mut writer.lock(), &config, &files, &diag)
.expect("Failed to write to stderr");
return Err(diag.message);
}
};
// this comments will be printed to the output file
// build again here whether it was built before
// since many informations are removed in the rusty_lr_parser output
let mut debug_comments = String::new();
{
// to map production rule to its pretty name abbreviation
let term_mapper = |term_idx: usize| grammar.terminals[term_idx].name.to_string();
let nonterm_mapper = |nonterm: usize| grammar.nonterminals[nonterm].pretty_name.clone();
let mut builder = grammar.create_grammar();
debug_comments.push_str(format!("{:=^80}\n", "Grammar").as_str());
for (rule, _) in builder.rules.iter() {
debug_comments.push_str(
format!("{}\n", rule.clone().map(term_mapper, nonterm_mapper)).as_str(),
);
}
let augmented_rule_id = *grammar
.nonterminals_index
.get(&Ident::new(
rusty_lr_parser::utils::AUGMENTED_NAME,
Span::call_site(),
))
.unwrap();
let parser = if grammar.lalr {
match builder.build_lalr(augmented_rule_id) {
Ok(parser) => parser,
Err(_) => unreachable!("Grammar building failed"),
}
} else {
match builder.build(augmented_rule_id) {
Ok(parser) => parser,
Err(_) => unreachable!("Grammar building failed"),
}
};
// print note about shift/reduce conflict resolved with `%left` or `%right`
if self.verbose_conflicts_resolving {
for state in parser.states.iter() {
let mut reduce_rules = BTreeMap::new();
let mut shift_rules = BTreeMap::new();
for (shifted_rule_ref, lookaheads) in state.ruleset.rules.iter() {
// is end of rule, add to reduce
if shifted_rule_ref.shifted
== builder.rules[shifted_rule_ref.rule].0.rule.len()
{
for token in lookaheads.iter() {
reduce_rules.insert(token, shifted_rule_ref.rule);
}
}
// if it is not end, and next token is terminal, add to shift
if let Some(rusty_lr_core::Token::Term(token)) = builder.rules
[shifted_rule_ref.rule]
.0
.rule
.get(shifted_rule_ref.shifted)
{
shift_rules
.entry(token)
.or_insert_with(BTreeSet::new)
.insert(*shifted_rule_ref);
}
}
// check shift/reduce conflict
for (term, shift_rules) in shift_rules.into_iter() {
if let Some(reduce_rule) = reduce_rules.get(term) {
// shift/reduce conflict here
// since there were not error reaching here, 'term' must be set reduce_type
let mut message = format!(
"Shift/Reduce conflict with token {} was resolved:\nReduce rule:\n\t>>> {}\nShift rules:",
grammar.terminals[*term].name,
builder.rules[*reduce_rule].0.clone().map(term_mapper, nonterm_mapper)
);
for shifted_rule in shift_rules.iter() {
let shifted_rule = ShiftedRule {
rule: builder.rules[shifted_rule.rule]
.0
.clone()
.map(term_mapper, nonterm_mapper),
shifted: shifted_rule.shifted,
};
message.push_str(format!("\n\t>>> {}", shifted_rule).as_str());
}
let mut labels = Vec::new();
Self::extend_rule_source_label(
&mut labels,
file_id,
*reduce_rule,
&grammar,
"(Reduce) ",
);
let mut shift_source_inserted = BTreeSet::new();
for shift_rule in shift_rules.iter() {
let name = &builder.rules[shift_rule.rule].0.name;
if !shift_source_inserted.contains(name) {
shift_source_inserted.insert(name);
Self::extend_rule_source_label(
&mut labels,
file_id,
shift_rule.rule,
&grammar,
"(Shift) ",
);
}
}
let term_info = &grammar.terminals[*term];
if let Some(reduce_type_origin) = &term_info.reduce_type {
let reduce_type = reduce_type_origin.reduce_type;
let type_string = match reduce_type {
rusty_lr_core::ReduceType::Left => "%left",
rusty_lr_core::ReduceType::Right => "%right",
};
for (first, last) in reduce_type_origin.sources.iter() {
let range = first.byte_range().start..last.byte_range().end;
labels.push(Label::primary(file_id, range).with_message(
format!("Reduce type was set as {} here", type_string),
));
}
let diag =
Diagnostic::note().with_message(message).with_labels(labels);
let writer = self.verbose_stream();
let config = codespan_reporting::term::Config::default();
term::emit(&mut writer.lock(), &config, &files, &diag)
.expect("Failed to write to stderr");
}
}
}
}
}
// print note about reduce/reduce conflict and shift/reduce conflict not resolved
if self.verbose_conflicts {
// to prevent duplicated messages, collect them into BTreeMap first
let mut reduce_rules_set = BTreeMap::new();
for state in parser.states.iter() {
for (term, reduce_rules) in state.reduce_map.iter() {
if reduce_rules.len() > 1 {
reduce_rules_set
.entry(reduce_rules)
.or_insert_with(BTreeSet::new)
.insert(term);
}
}
}
for (reduce_rules, terms) in reduce_rules_set.into_iter() {
let mut message = "Reduce/Reduce conflict:".to_string();
let mut labels = Vec::new();
let mut note = "with lookaheads: ".to_string();
let len = terms.len();
for (idx, term) in terms.into_iter().enumerate() {
if idx < len - 1 {
note.push_str(format!("{}, ", term).as_str());
} else {
note.push_str(format!("{}", term).as_str());
}
}
let mut reduce_source_inserted = BTreeSet::new();
for reduce_rule in reduce_rules.iter() {
message.push_str(
format!(
"\n\t>>> {}",
builder.rules[*reduce_rule]
.0
.clone()
.map(term_mapper, nonterm_mapper)
)
.as_str(),
);
let name = &builder.rules[*reduce_rule].0.name;
if !reduce_source_inserted.contains(name) {
reduce_source_inserted.insert(name);
Self::extend_rule_source_label(
&mut labels,
file_id,
*reduce_rule,
&grammar,
"",
);
}
}
let diag = Diagnostic::note()
.with_message(message)
.with_labels(labels)
.with_notes(vec![note]);
let writer = self.verbose_stream();
let config = codespan_reporting::term::Config::default();
term::emit(&mut writer.lock(), &config, &files, &diag)
.expect("Failed to write to stderr");
}
let mut shift_map = BTreeMap::new();
for state in parser.states.iter() {
for (term, reduce_rules) in state.reduce_map.iter() {
if let Some(next_state) = state.shift_goto_map_term.get(term) {
shift_map
.entry(
parser.states[*next_state]
.ruleset
.rules
.keys()
.copied()
.collect::<BTreeSet<_>>(),
)
.or_insert_with(BTreeSet::new)
.append(&mut reduce_rules.clone());
}
}
}
for (shift_ruleset, reduce_rules) in shift_map.into_iter() {
let mut message = "Shift/Reduce conflict:".to_string();
let mut labels = Vec::new();
let mut reduce_source_inserted = BTreeSet::new();
message.push_str("\nReduce rules:");
for reduce_rule in reduce_rules.iter() {
message.push_str(
format!(
"\n\t>>> {}",
builder.rules[*reduce_rule]
.0
.clone()
.map(term_mapper, nonterm_mapper)
)
.as_str(),
);
let name = &builder.rules[*reduce_rule].0.name;
if !reduce_source_inserted.contains(name) {
reduce_source_inserted.insert(name);
Self::extend_rule_source_label(
&mut labels,
file_id,
*reduce_rule,
&grammar,
"(Reduce) ",
);
}
}
let mut shift_source_inserted = BTreeSet::new();
message.push_str("\nShift rules:");
for shifted_rule in shift_ruleset.into_iter() {
let shifted_rule_ = ShiftedRule {
rule: builder.rules[shifted_rule.rule]
.0
.clone()
.map(term_mapper, nonterm_mapper),
shifted: shifted_rule.shifted,
};
message.push_str(format!("\n\t>>> {}", shifted_rule_).as_str());
let name = &builder.rules[shifted_rule.rule].0.name;
if !shift_source_inserted.contains(name) {
shift_source_inserted.insert(name);
Self::extend_rule_source_label(
&mut labels,
file_id,
shifted_rule.rule,
&grammar,
"(Shift) ",
);
}
}
let diag = Diagnostic::note().with_message(message).with_labels(labels);
let writer = self.verbose_stream();
let config = codespan_reporting::term::Config::default();
term::emit(&mut writer.lock(), &config, &files, &diag)
.expect("Failed to write to stderr");
}
}
}
Ok(output::Output {
user_stream: output_stream,
generated_stream: expanded_stream,
debug_comments,
})
}
}