rustc_parse/parser/mod.rs
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705
pub mod attr;
mod attr_wrapper;
mod diagnostics;
mod expr;
mod generics;
mod item;
mod nonterminal;
mod pat;
mod path;
mod stmt;
mod ty;
use std::assert_matches::debug_assert_matches;
use std::ops::Range;
use std::{fmt, mem, slice};
use attr_wrapper::{AttrWrapper, UsePreAttrPos};
pub use diagnostics::AttemptLocalParseRecovery;
pub(crate) use expr::ForbiddenLetReason;
pub(crate) use item::FnParseMode;
pub use pat::{CommaRecoveryMode, RecoverColon, RecoverComma};
use path::PathStyle;
use rustc_ast::ptr::P;
use rustc_ast::token::{
self, Delimiter, IdentIsRaw, InvisibleOrigin, MetaVarKind, Nonterminal, Token, TokenKind,
};
use rustc_ast::tokenstream::{
AttrsTarget, DelimSpacing, DelimSpan, Spacing, TokenStream, TokenTree, TokenTreeCursor,
};
use rustc_ast::util::case::Case;
use rustc_ast::{
self as ast, AnonConst, AttrArgs, AttrArgsEq, AttrId, ByRef, Const, CoroutineKind,
DUMMY_NODE_ID, DelimArgs, Expr, ExprKind, Extern, HasAttrs, HasTokens, Mutability, Recovered,
Safety, StrLit, Visibility, VisibilityKind,
};
use rustc_ast_pretty::pprust;
use rustc_data_structures::fx::FxHashMap;
use rustc_data_structures::sync::Lrc;
use rustc_errors::{Applicability, Diag, FatalError, MultiSpan, PResult};
use rustc_index::interval::IntervalSet;
use rustc_session::parse::ParseSess;
use rustc_span::symbol::{Ident, Symbol, kw, sym};
use rustc_span::{DUMMY_SP, Span};
use thin_vec::ThinVec;
use tracing::debug;
use crate::errors::{
self, IncorrectVisibilityRestriction, MismatchedClosingDelimiter, NonStringAbiLiteral,
};
use crate::lexer::UnmatchedDelim;
#[cfg(test)]
mod tests;
// Ideally, these tests would be in `rustc_ast`. But they depend on having a
// parser, so they are here.
#[cfg(test)]
mod tokenstream {
mod tests;
}
#[cfg(test)]
mod mut_visit {
mod tests;
}
bitflags::bitflags! {
#[derive(Clone, Copy, Debug)]
struct Restrictions: u8 {
const STMT_EXPR = 1 << 0;
const NO_STRUCT_LITERAL = 1 << 1;
const CONST_EXPR = 1 << 2;
const ALLOW_LET = 1 << 3;
const IN_IF_GUARD = 1 << 4;
const IS_PAT = 1 << 5;
}
}
#[derive(Clone, Copy, PartialEq, Debug)]
enum SemiColonMode {
Break,
Ignore,
Comma,
}
#[derive(Clone, Copy, PartialEq, Debug)]
enum BlockMode {
Break,
Ignore,
}
/// Whether or not we should force collection of tokens for an AST node,
/// regardless of whether or not it has attributes
#[derive(Clone, Copy, Debug, PartialEq)]
pub enum ForceCollect {
Yes,
No,
}
#[macro_export]
macro_rules! maybe_whole {
($p:expr, $constructor:ident, |$x:ident| $e:expr) => {
if let token::Interpolated(nt) = &$p.token.kind
&& let token::$constructor(x) = &**nt
{
#[allow(unused_mut)]
let mut $x = x.clone();
$p.bump();
return Ok($e);
}
};
}
/// If the next tokens are ill-formed `$ty::` recover them as `<$ty>::`.
#[macro_export]
macro_rules! maybe_recover_from_interpolated_ty_qpath {
($self: expr, $allow_qpath_recovery: expr) => {
if $allow_qpath_recovery
&& $self.may_recover()
&& $self.look_ahead(1, |t| t == &token::PathSep)
&& let token::Interpolated(nt) = &$self.token.kind
&& let token::NtTy(ty) = &**nt
{
let ty = ty.clone();
$self.bump();
return $self.maybe_recover_from_bad_qpath_stage_2($self.prev_token.span, ty);
}
};
}
#[derive(Clone, Copy, Debug)]
pub enum Recovery {
Allowed,
Forbidden,
}
#[derive(Clone)]
pub struct Parser<'a> {
pub psess: &'a ParseSess,
/// The current token.
pub token: Token,
/// The spacing for the current token.
token_spacing: Spacing,
/// The previous token.
pub prev_token: Token,
pub capture_cfg: bool,
restrictions: Restrictions,
expected_tokens: Vec<TokenType>,
token_cursor: TokenCursor,
// The number of calls to `bump`, i.e. the position in the token stream.
num_bump_calls: u32,
// During parsing we may sometimes need to "unglue" a glued token into two
// or three component tokens (e.g. `>>` into `>` and `>`, or `>>=` into `>`
// and `>` and `=`), so the parser can consume them one at a time. This
// process bypasses the normal capturing mechanism (e.g. `num_bump_calls`
// will not be incremented), since the "unglued" tokens due not exist in
// the original `TokenStream`.
//
// If we end up consuming all the component tokens, this is not an issue,
// because we'll end up capturing the single "glued" token.
//
// However, sometimes we may want to capture not all of the original
// token. For example, capturing the `Vec<u8>` in `Option<Vec<u8>>`
// requires us to unglue the trailing `>>` token. The `break_last_token`
// field is used to track these tokens. They get appended to the captured
// stream when we evaluate a `LazyAttrTokenStream`.
//
// This value is always 0, 1, or 2. It can only reach 2 when splitting
// `>>=` or `<<=`.
break_last_token: u32,
/// This field is used to keep track of how many left angle brackets we have seen. This is
/// required in order to detect extra leading left angle brackets (`<` characters) and error
/// appropriately.
///
/// See the comments in the `parse_path_segment` function for more details.
unmatched_angle_bracket_count: u16,
angle_bracket_nesting: u16,
last_unexpected_token_span: Option<Span>,
/// If present, this `Parser` is not parsing Rust code but rather a macro call.
subparser_name: Option<&'static str>,
capture_state: CaptureState,
/// This allows us to recover when the user forget to add braces around
/// multiple statements in the closure body.
current_closure: Option<ClosureSpans>,
/// Whether the parser is allowed to do recovery.
/// This is disabled when parsing macro arguments, see #103534
recovery: Recovery,
}
// This type is used a lot, e.g. it's cloned when matching many declarative macro rules with nonterminals. Make sure
// it doesn't unintentionally get bigger.
#[cfg(target_pointer_width = "64")]
rustc_data_structures::static_assert_size!(Parser<'_>, 288);
/// Stores span information about a closure.
#[derive(Clone, Debug)]
struct ClosureSpans {
whole_closure: Span,
closing_pipe: Span,
body: Span,
}
/// A token range within a `Parser`'s full token stream.
#[derive(Clone, Debug)]
struct ParserRange(Range<u32>);
/// A token range within an individual AST node's (lazy) token stream, i.e.
/// relative to that node's first token. Distinct from `ParserRange` so the two
/// kinds of range can't be mixed up.
#[derive(Clone, Debug)]
struct NodeRange(Range<u32>);
/// Indicates a range of tokens that should be replaced by an `AttrsTarget`
/// (replacement) or be replaced by nothing (deletion). This is used in two
/// places during token collection.
///
/// 1. Replacement. During the parsing of an AST node that may have a
/// `#[derive]` attribute, when we parse a nested AST node that has `#[cfg]`
/// or `#[cfg_attr]`, we replace the entire inner AST node with
/// `FlatToken::AttrsTarget`. This lets us perform eager cfg-expansion on an
/// `AttrTokenStream`.
///
/// 2. Deletion. We delete inner attributes from all collected token streams,
/// and instead track them through the `attrs` field on the AST node. This
/// lets us manipulate them similarly to outer attributes. When we create a
/// `TokenStream`, the inner attributes are inserted into the proper place
/// in the token stream.
///
/// Each replacement starts off in `ParserReplacement` form but is converted to
/// `NodeReplacement` form when it is attached to a single AST node, via
/// `LazyAttrTokenStreamImpl`.
type ParserReplacement = (ParserRange, Option<AttrsTarget>);
/// See the comment on `ParserReplacement`.
type NodeReplacement = (NodeRange, Option<AttrsTarget>);
impl NodeRange {
// Converts a range within a parser's tokens to a range within a
// node's tokens beginning at `start_pos`.
//
// For example, imagine a parser with 50 tokens in its token stream, a
// function that spans `ParserRange(20..40)` and an inner attribute within
// that function that spans `ParserRange(30..35)`. We would find the inner
// attribute's range within the function's tokens by subtracting 20, which
// is the position of the function's start token. This gives
// `NodeRange(10..15)`.
fn new(ParserRange(parser_range): ParserRange, start_pos: u32) -> NodeRange {
assert!(!parser_range.is_empty());
assert!(parser_range.start >= start_pos);
NodeRange((parser_range.start - start_pos)..(parser_range.end - start_pos))
}
}
/// Controls how we capture tokens. Capturing can be expensive,
/// so we try to avoid performing capturing in cases where
/// we will never need an `AttrTokenStream`.
#[derive(Copy, Clone, Debug)]
enum Capturing {
/// We aren't performing any capturing - this is the default mode.
No,
/// We are capturing tokens
Yes,
}
// This state is used by `Parser::collect_tokens`.
#[derive(Clone, Debug)]
struct CaptureState {
capturing: Capturing,
parser_replacements: Vec<ParserReplacement>,
inner_attr_parser_ranges: FxHashMap<AttrId, ParserRange>,
// `IntervalSet` is good for perf because attrs are mostly added to this
// set in contiguous ranges.
seen_attrs: IntervalSet<AttrId>,
}
/// Iterator over a `TokenStream` that produces `Token`s. It's a bit odd that
/// we (a) lex tokens into a nice tree structure (`TokenStream`), and then (b)
/// use this type to emit them as a linear sequence. But a linear sequence is
/// what the parser expects, for the most part.
#[derive(Clone, Debug)]
struct TokenCursor {
// Cursor for the current (innermost) token stream. The delimiters for this
// token stream are found in `self.stack.last()`; when that is `None` then
// we are in the outermost token stream which never has delimiters.
tree_cursor: TokenTreeCursor,
// Token streams surrounding the current one. The delimiters for stack[n]'s
// tokens are in `stack[n-1]`. `stack[0]` (when present) has no delimiters
// because it's the outermost token stream which never has delimiters.
stack: Vec<(TokenTreeCursor, DelimSpan, DelimSpacing, Delimiter)>,
}
impl TokenCursor {
fn next(&mut self) -> (Token, Spacing) {
self.inlined_next()
}
/// This always-inlined version should only be used on hot code paths.
#[inline(always)]
fn inlined_next(&mut self) -> (Token, Spacing) {
loop {
// FIXME: we currently don't return `Delimiter::Invisible` open/close delims. To fix
// #67062 we will need to, whereupon the `delim != Delimiter::Invisible` conditions
// below can be removed.
if let Some(tree) = self.tree_cursor.next_ref() {
match tree {
&TokenTree::Token(ref token, spacing) => {
debug_assert!(!matches!(
token.kind,
token::OpenDelim(_) | token::CloseDelim(_)
));
return (token.clone(), spacing);
}
&TokenTree::Delimited(sp, spacing, delim, ref tts) => {
let trees = tts.clone().into_trees();
self.stack.push((
mem::replace(&mut self.tree_cursor, trees),
sp,
spacing,
delim,
));
if !delim.skip() {
return (Token::new(token::OpenDelim(delim), sp.open), spacing.open);
}
// No open delimiter to return; continue on to the next iteration.
}
};
} else if let Some((tree_cursor, span, spacing, delim)) = self.stack.pop() {
// We have exhausted this token stream. Move back to its parent token stream.
self.tree_cursor = tree_cursor;
if !delim.skip() {
return (Token::new(token::CloseDelim(delim), span.close), spacing.close);
}
// No close delimiter to return; continue on to the next iteration.
} else {
// We have exhausted the outermost token stream. The use of
// `Spacing::Alone` is arbitrary and immaterial, because the
// `Eof` token's spacing is never used.
return (Token::new(token::Eof, DUMMY_SP), Spacing::Alone);
}
}
}
}
#[derive(Debug, Clone, PartialEq)]
enum TokenType {
Token(TokenKind),
Keyword(Symbol),
Operator,
Lifetime,
Ident,
Path,
Type,
Const,
}
impl TokenType {
fn to_string(&self) -> String {
match self {
TokenType::Token(t) => format!("`{}`", pprust::token_kind_to_string(t)),
TokenType::Keyword(kw) => format!("`{kw}`"),
TokenType::Operator => "an operator".to_string(),
TokenType::Lifetime => "lifetime".to_string(),
TokenType::Ident => "identifier".to_string(),
TokenType::Path => "path".to_string(),
TokenType::Type => "type".to_string(),
TokenType::Const => "a const expression".to_string(),
}
}
}
/// A sequence separator.
#[derive(Debug)]
struct SeqSep {
/// The separator token.
sep: Option<TokenKind>,
/// `true` if a trailing separator is allowed.
trailing_sep_allowed: bool,
}
impl SeqSep {
fn trailing_allowed(t: TokenKind) -> SeqSep {
SeqSep { sep: Some(t), trailing_sep_allowed: true }
}
fn none() -> SeqSep {
SeqSep { sep: None, trailing_sep_allowed: false }
}
}
#[derive(Debug)]
pub enum FollowedByType {
Yes,
No,
}
#[derive(Copy, Clone, Debug)]
enum Trailing {
No,
Yes,
}
impl From<bool> for Trailing {
fn from(b: bool) -> Trailing {
if b { Trailing::Yes } else { Trailing::No }
}
}
#[derive(Clone, Copy, Debug, PartialEq, Eq)]
pub(super) enum TokenDescription {
ReservedIdentifier,
Keyword,
ReservedKeyword,
DocComment,
// Expanded metavariables are wrapped in invisible delimiters which aren't
// pretty-printed. In error messages we must handle these specially
// otherwise we get confusing things in messages like "expected `(`, found
// ``". It's better to say e.g. "expected `(`, found type metavariable".
MetaVar(MetaVarKind),
}
impl TokenDescription {
pub(super) fn from_token(token: &Token) -> Option<Self> {
match token.kind {
_ if token.is_special_ident() => Some(TokenDescription::ReservedIdentifier),
_ if token.is_used_keyword() => Some(TokenDescription::Keyword),
_ if token.is_unused_keyword() => Some(TokenDescription::ReservedKeyword),
token::DocComment(..) => Some(TokenDescription::DocComment),
token::OpenDelim(Delimiter::Invisible(InvisibleOrigin::MetaVar(kind))) => {
Some(TokenDescription::MetaVar(kind))
}
_ => None,
}
}
}
pub fn token_descr(token: &Token) -> String {
let s = pprust::token_to_string(token).to_string();
match (TokenDescription::from_token(token), &token.kind) {
(Some(TokenDescription::ReservedIdentifier), _) => format!("reserved identifier `{s}`"),
(Some(TokenDescription::Keyword), _) => format!("keyword `{s}`"),
(Some(TokenDescription::ReservedKeyword), _) => format!("reserved keyword `{s}`"),
(Some(TokenDescription::DocComment), _) => format!("doc comment `{s}`"),
// Deliberately doesn't print `s`, which is empty.
(Some(TokenDescription::MetaVar(kind)), _) => format!("`{kind}` metavariable"),
(None, TokenKind::NtIdent(..)) => format!("identifier `{s}`"),
(None, TokenKind::NtLifetime(..)) => format!("lifetime `{s}`"),
(None, TokenKind::Interpolated(node)) => format!("{} `{s}`", node.descr()),
(None, _) => format!("`{s}`"),
}
}
impl<'a> Parser<'a> {
pub fn new(
psess: &'a ParseSess,
stream: TokenStream,
subparser_name: Option<&'static str>,
) -> Self {
let mut parser = Parser {
psess,
token: Token::dummy(),
token_spacing: Spacing::Alone,
prev_token: Token::dummy(),
capture_cfg: false,
restrictions: Restrictions::empty(),
expected_tokens: Vec::new(),
token_cursor: TokenCursor { tree_cursor: stream.into_trees(), stack: Vec::new() },
num_bump_calls: 0,
break_last_token: 0,
unmatched_angle_bracket_count: 0,
angle_bracket_nesting: 0,
last_unexpected_token_span: None,
subparser_name,
capture_state: CaptureState {
capturing: Capturing::No,
parser_replacements: Vec::new(),
inner_attr_parser_ranges: Default::default(),
seen_attrs: IntervalSet::new(u32::MAX as usize),
},
current_closure: None,
recovery: Recovery::Allowed,
};
// Make parser point to the first token.
parser.bump();
// Change this from 1 back to 0 after the bump. This eases debugging of
// `Parser::collect_tokens` because 0-indexed token positions are nicer
// than 1-indexed token positions.
parser.num_bump_calls = 0;
parser
}
#[inline]
pub fn recovery(mut self, recovery: Recovery) -> Self {
self.recovery = recovery;
self
}
/// Whether the parser is allowed to recover from broken code.
///
/// If this returns false, recovering broken code into valid code (especially if this recovery does lookahead)
/// is not allowed. All recovery done by the parser must be gated behind this check.
///
/// Technically, this only needs to restrict eager recovery by doing lookahead at more tokens.
/// But making the distinction is very subtle, and simply forbidding all recovery is a lot simpler to uphold.
#[inline]
fn may_recover(&self) -> bool {
matches!(self.recovery, Recovery::Allowed)
}
/// Version of [`unexpected`](Parser::unexpected) that "returns" any type in the `Ok`
/// (both those functions never return "Ok", and so can lie like that in the type).
pub fn unexpected_any<T>(&mut self) -> PResult<'a, T> {
match self.expect_one_of(&[], &[]) {
Err(e) => Err(e),
// We can get `Ok(true)` from `recover_closing_delimiter`
// which is called in `expected_one_of_not_found`.
Ok(_) => FatalError.raise(),
}
}
pub fn unexpected(&mut self) -> PResult<'a, ()> {
self.unexpected_any()
}
/// Expects and consumes the token `t`. Signals an error if the next token is not `t`.
pub fn expect(&mut self, t: &TokenKind) -> PResult<'a, Recovered> {
if self.expected_tokens.is_empty() {
if self.token == *t {
self.bump();
Ok(Recovered::No)
} else {
self.unexpected_try_recover(t)
}
} else {
self.expect_one_of(slice::from_ref(t), &[])
}
}
/// Expect next token to be edible or inedible token. If edible,
/// then consume it; if inedible, then return without consuming
/// anything. Signal a fatal error if next token is unexpected.
fn expect_one_of(
&mut self,
edible: &[TokenKind],
inedible: &[TokenKind],
) -> PResult<'a, Recovered> {
if edible.contains(&self.token.kind) {
self.bump();
Ok(Recovered::No)
} else if inedible.contains(&self.token.kind) {
// leave it in the input
Ok(Recovered::No)
} else if self.token != token::Eof
&& self.last_unexpected_token_span == Some(self.token.span)
{
FatalError.raise();
} else {
self.expected_one_of_not_found(edible, inedible)
.map(|error_guaranteed| Recovered::Yes(error_guaranteed))
}
}
// Public for rustfmt usage.
pub fn parse_ident(&mut self) -> PResult<'a, Ident> {
self.parse_ident_common(true)
}
fn parse_ident_common(&mut self, recover: bool) -> PResult<'a, Ident> {
let (ident, is_raw) = self.ident_or_err(recover)?;
if matches!(is_raw, IdentIsRaw::No) && ident.is_reserved() {
let err = self.expected_ident_found_err();
if recover {
err.emit();
} else {
return Err(err);
}
}
self.bump();
Ok(ident)
}
fn ident_or_err(&mut self, recover: bool) -> PResult<'a, (Ident, IdentIsRaw)> {
match self.token.ident() {
Some(ident) => Ok(ident),
None => self.expected_ident_found(recover),
}
}
/// Checks if the next token is `tok`, and returns `true` if so.
///
/// This method will automatically add `tok` to `expected_tokens` if `tok` is not
/// encountered.
#[inline]
fn check(&mut self, tok: &TokenKind) -> bool {
let is_present = self.token == *tok;
if !is_present {
self.expected_tokens.push(TokenType::Token(tok.clone()));
}
is_present
}
#[inline]
#[must_use]
fn check_noexpect(&self, tok: &TokenKind) -> bool {
self.token == *tok
}
/// Consumes a token 'tok' if it exists. Returns whether the given token was present.
///
/// the main purpose of this function is to reduce the cluttering of the suggestions list
/// which using the normal eat method could introduce in some cases.
#[inline]
#[must_use]
fn eat_noexpect(&mut self, tok: &TokenKind) -> bool {
let is_present = self.check_noexpect(tok);
if is_present {
self.bump()
}
is_present
}
/// Consumes a token 'tok' if it exists. Returns whether the given token was present.
#[inline]
#[must_use]
pub fn eat(&mut self, tok: &TokenKind) -> bool {
let is_present = self.check(tok);
if is_present {
self.bump()
}
is_present
}
/// If the next token is the given keyword, returns `true` without eating it.
/// An expectation is also added for diagnostics purposes.
#[inline]
#[must_use]
fn check_keyword(&mut self, kw: Symbol) -> bool {
self.expected_tokens.push(TokenType::Keyword(kw));
self.token.is_keyword(kw)
}
#[inline]
#[must_use]
fn check_keyword_case(&mut self, kw: Symbol, case: Case) -> bool {
if self.check_keyword(kw) {
return true;
}
// Do an ASCII case-insensitive match, because all keywords are ASCII.
if case == Case::Insensitive
&& let Some((ident, IdentIsRaw::No)) = self.token.ident()
&& ident.as_str().eq_ignore_ascii_case(kw.as_str())
{
true
} else {
false
}
}
/// If the next token is the given keyword, eats it and returns `true`.
/// Otherwise, returns `false`. An expectation is also added for diagnostics purposes.
// Public for rustc_builtin_macros and rustfmt usage.
#[inline]
#[must_use]
pub fn eat_keyword(&mut self, kw: Symbol) -> bool {
if self.check_keyword(kw) {
self.bump();
true
} else {
false
}
}
/// Eats a keyword, optionally ignoring the case.
/// If the case differs (and is ignored) an error is issued.
/// This is useful for recovery.
#[inline]
#[must_use]
fn eat_keyword_case(&mut self, kw: Symbol, case: Case) -> bool {
if self.eat_keyword(kw) {
return true;
}
if case == Case::Insensitive
&& let Some((ident, IdentIsRaw::No)) = self.token.ident()
&& ident.as_str().to_lowercase() == kw.as_str().to_lowercase()
{
self.dcx().emit_err(errors::KwBadCase { span: ident.span, kw: kw.as_str() });
self.bump();
return true;
}
false
}
/// If the next token is the given keyword, eats it and returns `true`.
/// Otherwise, returns `false`. No expectation is added.
// Public for rustc_builtin_macros usage.
#[inline]
#[must_use]
pub fn eat_keyword_noexpect(&mut self, kw: Symbol) -> bool {
if self.token.is_keyword(kw) {
self.bump();
true
} else {
false
}
}
/// If the given word is not a keyword, signals an error.
/// If the next token is not the given word, signals an error.
/// Otherwise, eats it.
pub fn expect_keyword(&mut self, kw: Symbol) -> PResult<'a, ()> {
if !self.eat_keyword(kw) { self.unexpected() } else { Ok(()) }
}
/// Is the given keyword `kw` followed by a non-reserved identifier?
fn is_kw_followed_by_ident(&self, kw: Symbol) -> bool {
self.token.is_keyword(kw) && self.look_ahead(1, |t| t.is_ident() && !t.is_reserved_ident())
}
#[inline]
fn check_or_expected(&mut self, ok: bool, typ: TokenType) -> bool {
if ok {
true
} else {
self.expected_tokens.push(typ);
false
}
}
fn check_ident(&mut self) -> bool {
self.check_or_expected(self.token.is_ident(), TokenType::Ident)
}
fn check_path(&mut self) -> bool {
self.check_or_expected(self.token.is_path_start(), TokenType::Path)
}
fn check_type(&mut self) -> bool {
self.check_or_expected(self.token.can_begin_type(), TokenType::Type)
}
fn check_const_arg(&mut self) -> bool {
self.check_or_expected(self.token.can_begin_const_arg(), TokenType::Const)
}
fn check_const_closure(&self) -> bool {
self.is_keyword_ahead(0, &[kw::Const])
&& self.look_ahead(1, |t| match &t.kind {
// async closures do not work with const closures, so we do not parse that here.
token::Ident(kw::Move | kw::Static, _) | token::OrOr | token::BinOp(token::Or) => {
true
}
_ => false,
})
}
fn check_inline_const(&self, dist: usize) -> bool {
self.is_keyword_ahead(dist, &[kw::Const])
&& self.look_ahead(dist + 1, |t| match &t.kind {
token::Interpolated(nt) => matches!(&**nt, token::NtBlock(..)),
token::OpenDelim(Delimiter::Brace) => true,
_ => false,
})
}
/// Checks to see if the next token is either `+` or `+=`.
/// Otherwise returns `false`.
#[inline]
fn check_plus(&mut self) -> bool {
self.check_or_expected(
self.token.is_like_plus(),
TokenType::Token(token::BinOp(token::Plus)),
)
}
/// Eats the expected token if it's present possibly breaking
/// compound tokens like multi-character operators in process.
/// Returns `true` if the token was eaten.
fn break_and_eat(&mut self, expected: TokenKind) -> bool {
if self.token == expected {
self.bump();
return true;
}
match self.token.kind.break_two_token_op(1) {
Some((first, second)) if first == expected => {
let first_span = self.psess.source_map().start_point(self.token.span);
let second_span = self.token.span.with_lo(first_span.hi());
self.token = Token::new(first, first_span);
// Keep track of this token - if we end token capturing now,
// we'll want to append this token to the captured stream.
//
// If we consume any additional tokens, then this token
// is not needed (we'll capture the entire 'glued' token),
// and `bump` will set this field to 0.
self.break_last_token += 1;
// Use the spacing of the glued token as the spacing of the
// unglued second token.
self.bump_with((Token::new(second, second_span), self.token_spacing));
true
}
_ => {
self.expected_tokens.push(TokenType::Token(expected));
false
}
}
}
/// Eats `+` possibly breaking tokens like `+=` in process.
fn eat_plus(&mut self) -> bool {
self.break_and_eat(token::BinOp(token::Plus))
}
/// Eats `&` possibly breaking tokens like `&&` in process.
/// Signals an error if `&` is not eaten.
fn expect_and(&mut self) -> PResult<'a, ()> {
if self.break_and_eat(token::BinOp(token::And)) { Ok(()) } else { self.unexpected() }
}
/// Eats `|` possibly breaking tokens like `||` in process.
/// Signals an error if `|` was not eaten.
fn expect_or(&mut self) -> PResult<'a, ()> {
if self.break_and_eat(token::BinOp(token::Or)) { Ok(()) } else { self.unexpected() }
}
/// Eats `<` possibly breaking tokens like `<<` in process.
fn eat_lt(&mut self) -> bool {
let ate = self.break_and_eat(token::Lt);
if ate {
// See doc comment for `unmatched_angle_bracket_count`.
self.unmatched_angle_bracket_count += 1;
debug!("eat_lt: (increment) count={:?}", self.unmatched_angle_bracket_count);
}
ate
}
/// Eats `<` possibly breaking tokens like `<<` in process.
/// Signals an error if `<` was not eaten.
fn expect_lt(&mut self) -> PResult<'a, ()> {
if self.eat_lt() { Ok(()) } else { self.unexpected() }
}
/// Eats `>` possibly breaking tokens like `>>` in process.
/// Signals an error if `>` was not eaten.
fn expect_gt(&mut self) -> PResult<'a, ()> {
if self.break_and_eat(token::Gt) {
// See doc comment for `unmatched_angle_bracket_count`.
if self.unmatched_angle_bracket_count > 0 {
self.unmatched_angle_bracket_count -= 1;
debug!("expect_gt: (decrement) count={:?}", self.unmatched_angle_bracket_count);
}
Ok(())
} else {
self.unexpected()
}
}
/// Checks if the next token is contained within `kets`, and returns `true` if so.
fn expect_any_with_type(
&mut self,
kets_expected: &[&TokenKind],
kets_not_expected: &[&TokenKind],
) -> bool {
kets_expected.iter().any(|k| self.check(k))
|| kets_not_expected.iter().any(|k| self.check_noexpect(k))
}
/// Parses a sequence until the specified delimiters. The function
/// `f` must consume tokens until reaching the next separator or
/// closing bracket.
fn parse_seq_to_before_tokens<T>(
&mut self,
kets_expected: &[&TokenKind],
kets_not_expected: &[&TokenKind],
sep: SeqSep,
mut f: impl FnMut(&mut Parser<'a>) -> PResult<'a, T>,
) -> PResult<'a, (ThinVec<T>, Trailing, Recovered)> {
let mut first = true;
let mut recovered = Recovered::No;
let mut trailing = Trailing::No;
let mut v = ThinVec::new();
while !self.expect_any_with_type(kets_expected, kets_not_expected) {
if let token::CloseDelim(..) | token::Eof = self.token.kind {
break;
}
if let Some(t) = &sep.sep {
if first {
// no separator for the first element
first = false;
} else {
// check for separator
match self.expect(t) {
Ok(Recovered::No) => {
self.current_closure.take();
}
Ok(Recovered::Yes(guar)) => {
self.current_closure.take();
recovered = Recovered::Yes(guar);
break;
}
Err(mut expect_err) => {
let sp = self.prev_token.span.shrink_to_hi();
let token_str = pprust::token_kind_to_string(t);
match self.current_closure.take() {
Some(closure_spans) if self.token == TokenKind::Semi => {
// Finding a semicolon instead of a comma
// after a closure body indicates that the
// closure body may be a block but the user
// forgot to put braces around its
// statements.
self.recover_missing_braces_around_closure_body(
closure_spans,
expect_err,
)?;
continue;
}
_ => {
// Attempt to keep parsing if it was a similar separator.
if let Some(tokens) = t.similar_tokens() {
if tokens.contains(&self.token.kind) {
self.bump();
}
}
}
}
// If this was a missing `@` in a binding pattern
// bail with a suggestion
// https://github.com/rust-lang/rust/issues/72373
if self.prev_token.is_ident() && self.token == token::DotDot {
let msg = format!(
"if you meant to bind the contents of the rest of the array \
pattern into `{}`, use `@`",
pprust::token_to_string(&self.prev_token)
);
expect_err
.with_span_suggestion_verbose(
self.prev_token.span.shrink_to_hi().until(self.token.span),
msg,
" @ ",
Applicability::MaybeIncorrect,
)
.emit();
break;
}
// Attempt to keep parsing if it was an omitted separator.
self.last_unexpected_token_span = None;
match f(self) {
Ok(t) => {
// Parsed successfully, therefore most probably the code only
// misses a separator.
expect_err
.with_span_suggestion_short(
sp,
format!("missing `{token_str}`"),
token_str,
Applicability::MaybeIncorrect,
)
.emit();
v.push(t);
continue;
}
Err(e) => {
// Parsing failed, therefore it must be something more serious
// than just a missing separator.
for xx in &e.children {
// propagate the help message from sub error 'e' to main error 'expect_err;
expect_err.children.push(xx.clone());
}
e.cancel();
if self.token == token::Colon {
// we will try to recover in `maybe_recover_struct_lit_bad_delims`
return Err(expect_err);
} else if let [token::CloseDelim(Delimiter::Parenthesis)] =
kets_expected
{
return Err(expect_err);
} else {
expect_err.emit();
break;
}
}
}
}
}
}
}
if sep.trailing_sep_allowed
&& self.expect_any_with_type(kets_expected, kets_not_expected)
{
trailing = Trailing::Yes;
break;
}
let t = f(self)?;
v.push(t);
}
Ok((v, trailing, recovered))
}
fn recover_missing_braces_around_closure_body(
&mut self,
closure_spans: ClosureSpans,
mut expect_err: Diag<'_>,
) -> PResult<'a, ()> {
let initial_semicolon = self.token.span;
while self.eat(&TokenKind::Semi) {
let _ = self.parse_stmt_without_recovery(false, ForceCollect::No).unwrap_or_else(|e| {
e.cancel();
None
});
}
expect_err
.primary_message("closure bodies that contain statements must be surrounded by braces");
let preceding_pipe_span = closure_spans.closing_pipe;
let following_token_span = self.token.span;
let mut first_note = MultiSpan::from(vec![initial_semicolon]);
first_note.push_span_label(
initial_semicolon,
"this `;` turns the preceding closure into a statement",
);
first_note.push_span_label(
closure_spans.body,
"this expression is a statement because of the trailing semicolon",
);
expect_err.span_note(first_note, "statement found outside of a block");
let mut second_note = MultiSpan::from(vec![closure_spans.whole_closure]);
second_note.push_span_label(closure_spans.whole_closure, "this is the parsed closure...");
second_note.push_span_label(
following_token_span,
"...but likely you meant the closure to end here",
);
expect_err.span_note(second_note, "the closure body may be incorrectly delimited");
expect_err.span(vec![preceding_pipe_span, following_token_span]);
let opening_suggestion_str = " {".to_string();
let closing_suggestion_str = "}".to_string();
expect_err.multipart_suggestion(
"try adding braces",
vec![
(preceding_pipe_span.shrink_to_hi(), opening_suggestion_str),
(following_token_span.shrink_to_lo(), closing_suggestion_str),
],
Applicability::MaybeIncorrect,
);
expect_err.emit();
Ok(())
}
/// Parses a sequence, not including the delimiters. The function
/// `f` must consume tokens until reaching the next separator or
/// closing bracket.
fn parse_seq_to_before_end<T>(
&mut self,
ket: &TokenKind,
sep: SeqSep,
f: impl FnMut(&mut Parser<'a>) -> PResult<'a, T>,
) -> PResult<'a, (ThinVec<T>, Trailing, Recovered)> {
self.parse_seq_to_before_tokens(&[ket], &[], sep, f)
}
/// Parses a sequence, including only the closing delimiter. The function
/// `f` must consume tokens until reaching the next separator or
/// closing bracket.
fn parse_seq_to_end<T>(
&mut self,
ket: &TokenKind,
sep: SeqSep,
f: impl FnMut(&mut Parser<'a>) -> PResult<'a, T>,
) -> PResult<'a, (ThinVec<T>, Trailing)> {
let (val, trailing, recovered) = self.parse_seq_to_before_end(ket, sep, f)?;
if matches!(recovered, Recovered::No) && !self.eat(ket) {
self.dcx().span_delayed_bug(
self.token.span,
"recovered but `parse_seq_to_before_end` did not give us the ket token",
);
}
Ok((val, trailing))
}
/// Parses a sequence, including both delimiters. The function
/// `f` must consume tokens until reaching the next separator or
/// closing bracket.
fn parse_unspanned_seq<T>(
&mut self,
bra: &TokenKind,
ket: &TokenKind,
sep: SeqSep,
f: impl FnMut(&mut Parser<'a>) -> PResult<'a, T>,
) -> PResult<'a, (ThinVec<T>, Trailing)> {
self.expect(bra)?;
self.parse_seq_to_end(ket, sep, f)
}
/// Parses a comma-separated sequence, including both delimiters.
/// The function `f` must consume tokens until reaching the next separator or
/// closing bracket.
fn parse_delim_comma_seq<T>(
&mut self,
delim: Delimiter,
f: impl FnMut(&mut Parser<'a>) -> PResult<'a, T>,
) -> PResult<'a, (ThinVec<T>, Trailing)> {
self.parse_unspanned_seq(
&token::OpenDelim(delim),
&token::CloseDelim(delim),
SeqSep::trailing_allowed(token::Comma),
f,
)
}
/// Parses a comma-separated sequence delimited by parentheses (e.g. `(x, y)`).
/// The function `f` must consume tokens until reaching the next separator or
/// closing bracket.
fn parse_paren_comma_seq<T>(
&mut self,
f: impl FnMut(&mut Parser<'a>) -> PResult<'a, T>,
) -> PResult<'a, (ThinVec<T>, Trailing)> {
self.parse_delim_comma_seq(Delimiter::Parenthesis, f)
}
/// Advance the parser by one token using provided token as the next one.
fn bump_with(&mut self, next: (Token, Spacing)) {
self.inlined_bump_with(next)
}
/// This always-inlined version should only be used on hot code paths.
#[inline(always)]
fn inlined_bump_with(&mut self, (next_token, next_spacing): (Token, Spacing)) {
// Update the current and previous tokens.
self.prev_token = mem::replace(&mut self.token, next_token);
self.token_spacing = next_spacing;
// Diagnostics.
self.expected_tokens.clear();
}
/// Advance the parser by one token.
pub fn bump(&mut self) {
// Note: destructuring here would give nicer code, but it was found in #96210 to be slower
// than `.0`/`.1` access.
let mut next = self.token_cursor.inlined_next();
self.num_bump_calls += 1;
// We got a token from the underlying cursor and no longer need to
// worry about an unglued token. See `break_and_eat` for more details.
self.break_last_token = 0;
if next.0.span.is_dummy() {
// Tweak the location for better diagnostics, but keep syntactic context intact.
let fallback_span = self.token.span;
next.0.span = fallback_span.with_ctxt(next.0.span.ctxt());
}
debug_assert!(!matches!(
next.0.kind,
token::OpenDelim(delim) | token::CloseDelim(delim) if delim.skip()
));
self.inlined_bump_with(next)
}
/// Look-ahead `dist` tokens of `self.token` and get access to that token there.
/// When `dist == 0` then the current token is looked at. `Eof` will be
/// returned if the look-ahead is any distance past the end of the tokens.
pub fn look_ahead<R>(&self, dist: usize, looker: impl FnOnce(&Token) -> R) -> R {
if dist == 0 {
return looker(&self.token);
}
// Typically around 98% of the `dist > 0` cases have `dist == 1`, so we
// have a fast special case for that.
if dist == 1 {
// The index is zero because the tree cursor's index always points
// to the next token to be gotten.
match self.token_cursor.tree_cursor.look_ahead(0) {
Some(tree) => {
// Indexing stayed within the current token tree.
match tree {
TokenTree::Token(token, _) => return looker(token),
&TokenTree::Delimited(dspan, _, delim, _) => {
if !delim.skip() {
return looker(&Token::new(token::OpenDelim(delim), dspan.open));
}
}
};
}
None => {
// The tree cursor lookahead went (one) past the end of the
// current token tree. Try to return a close delimiter.
if let Some(&(_, span, _, delim)) = self.token_cursor.stack.last()
&& !delim.skip()
{
// We are not in the outermost token stream, so we have
// delimiters. Also, those delimiters are not skipped.
return looker(&Token::new(token::CloseDelim(delim), span.close));
}
}
}
}
// Just clone the token cursor and use `next`, skipping delimiters as
// necessary. Slow but simple.
let mut cursor = self.token_cursor.clone();
let mut i = 0;
let mut token = Token::dummy();
while i < dist {
token = cursor.next().0;
if matches!(
token.kind,
token::OpenDelim(delim) | token::CloseDelim(delim) if delim.skip()
) {
continue;
}
i += 1;
}
looker(&token)
}
/// Returns whether any of the given keywords are `dist` tokens ahead of the current one.
pub(crate) fn is_keyword_ahead(&self, dist: usize, kws: &[Symbol]) -> bool {
self.look_ahead(dist, |t| kws.iter().any(|&kw| t.is_keyword(kw)))
}
/// Parses asyncness: `async` or nothing.
fn parse_coroutine_kind(&mut self, case: Case) -> Option<CoroutineKind> {
let span = self.token.uninterpolated_span();
if self.eat_keyword_case(kw::Async, case) {
// FIXME(gen_blocks): Do we want to unconditionally parse `gen` and then
// error if edition <= 2024, like we do with async and edition <= 2018?
if self.token.uninterpolated_span().at_least_rust_2024()
&& self.eat_keyword_case(kw::Gen, case)
{
let gen_span = self.prev_token.uninterpolated_span();
Some(CoroutineKind::AsyncGen {
span: span.to(gen_span),
closure_id: DUMMY_NODE_ID,
return_impl_trait_id: DUMMY_NODE_ID,
})
} else {
Some(CoroutineKind::Async {
span,
closure_id: DUMMY_NODE_ID,
return_impl_trait_id: DUMMY_NODE_ID,
})
}
} else if self.token.uninterpolated_span().at_least_rust_2024()
&& self.eat_keyword_case(kw::Gen, case)
{
Some(CoroutineKind::Gen {
span,
closure_id: DUMMY_NODE_ID,
return_impl_trait_id: DUMMY_NODE_ID,
})
} else {
None
}
}
/// Parses fn unsafety: `unsafe`, `safe` or nothing.
fn parse_safety(&mut self, case: Case) -> Safety {
if self.eat_keyword_case(kw::Unsafe, case) {
Safety::Unsafe(self.prev_token.uninterpolated_span())
} else if self.eat_keyword_case(kw::Safe, case) {
Safety::Safe(self.prev_token.uninterpolated_span())
} else {
Safety::Default
}
}
/// Parses constness: `const` or nothing.
fn parse_constness(&mut self, case: Case) -> Const {
self.parse_constness_(case, false)
}
/// Parses constness for closures (case sensitive, feature-gated)
fn parse_closure_constness(&mut self) -> Const {
let constness = self.parse_constness_(Case::Sensitive, true);
if let Const::Yes(span) = constness {
self.psess.gated_spans.gate(sym::const_closures, span);
}
constness
}
fn parse_constness_(&mut self, case: Case, is_closure: bool) -> Const {
// Avoid const blocks and const closures to be parsed as const items
if (self.check_const_closure() == is_closure)
&& !self
.look_ahead(1, |t| *t == token::OpenDelim(Delimiter::Brace) || t.is_whole_block())
&& self.eat_keyword_case(kw::Const, case)
{
Const::Yes(self.prev_token.uninterpolated_span())
} else {
Const::No
}
}
/// Parses inline const expressions.
fn parse_const_block(&mut self, span: Span, pat: bool) -> PResult<'a, P<Expr>> {
if pat {
self.psess.gated_spans.gate(sym::inline_const_pat, span);
}
self.expect_keyword(kw::Const)?;
let (attrs, blk) = self.parse_inner_attrs_and_block()?;
let anon_const = AnonConst {
id: DUMMY_NODE_ID,
value: self.mk_expr(blk.span, ExprKind::Block(blk, None)),
};
let blk_span = anon_const.value.span;
Ok(self.mk_expr_with_attrs(span.to(blk_span), ExprKind::ConstBlock(anon_const), attrs))
}
/// Parses mutability (`mut` or nothing).
fn parse_mutability(&mut self) -> Mutability {
if self.eat_keyword(kw::Mut) { Mutability::Mut } else { Mutability::Not }
}
/// Parses reference binding mode (`ref`, `ref mut`, or nothing).
fn parse_byref(&mut self) -> ByRef {
if self.eat_keyword(kw::Ref) { ByRef::Yes(self.parse_mutability()) } else { ByRef::No }
}
/// Possibly parses mutability (`const` or `mut`).
fn parse_const_or_mut(&mut self) -> Option<Mutability> {
if self.eat_keyword(kw::Mut) {
Some(Mutability::Mut)
} else if self.eat_keyword(kw::Const) {
Some(Mutability::Not)
} else {
None
}
}
fn parse_field_name(&mut self) -> PResult<'a, Ident> {
if let token::Literal(token::Lit { kind: token::Integer, symbol, suffix }) = self.token.kind
{
if let Some(suffix) = suffix {
self.expect_no_tuple_index_suffix(self.token.span, suffix);
}
self.bump();
Ok(Ident::new(symbol, self.prev_token.span))
} else {
self.parse_ident_common(true)
}
}
fn parse_delim_args(&mut self) -> PResult<'a, P<DelimArgs>> {
if let Some(args) = self.parse_delim_args_inner() {
Ok(P(args))
} else {
self.unexpected_any()
}
}
fn parse_attr_args(&mut self) -> PResult<'a, AttrArgs> {
Ok(if let Some(args) = self.parse_delim_args_inner() {
AttrArgs::Delimited(args)
} else if self.eat(&token::Eq) {
let eq_span = self.prev_token.span;
AttrArgs::Eq(eq_span, AttrArgsEq::Ast(self.parse_expr_force_collect()?))
} else {
AttrArgs::Empty
})
}
fn parse_delim_args_inner(&mut self) -> Option<DelimArgs> {
let delimited = self.check(&token::OpenDelim(Delimiter::Parenthesis))
|| self.check(&token::OpenDelim(Delimiter::Bracket))
|| self.check(&token::OpenDelim(Delimiter::Brace));
delimited.then(|| {
let TokenTree::Delimited(dspan, _, delim, tokens) = self.parse_token_tree() else {
unreachable!()
};
DelimArgs { dspan, delim, tokens }
})
}
/// Parses a single token tree from the input.
pub fn parse_token_tree(&mut self) -> TokenTree {
match self.token.kind {
token::OpenDelim(..) => {
// Grab the tokens within the delimiters.
let stream = self.token_cursor.tree_cursor.stream.clone();
let (_, span, spacing, delim) = *self.token_cursor.stack.last().unwrap();
// Advance the token cursor through the entire delimited
// sequence. After getting the `OpenDelim` we are *within* the
// delimited sequence, i.e. at depth `d`. After getting the
// matching `CloseDelim` we are *after* the delimited sequence,
// i.e. at depth `d - 1`.
let target_depth = self.token_cursor.stack.len() - 1;
loop {
// Advance one token at a time, so `TokenCursor::next()`
// can capture these tokens if necessary.
self.bump();
if self.token_cursor.stack.len() == target_depth {
debug_assert_matches!(self.token.kind, token::CloseDelim(_));
break;
}
}
// Consume close delimiter
self.bump();
TokenTree::Delimited(span, spacing, delim, stream)
}
token::CloseDelim(_) | token::Eof => unreachable!(),
_ => {
let prev_spacing = self.token_spacing;
self.bump();
TokenTree::Token(self.prev_token.clone(), prev_spacing)
}
}
}
pub fn parse_tokens(&mut self) -> TokenStream {
let mut result = Vec::new();
loop {
match self.token.kind {
token::Eof | token::CloseDelim(..) => break,
_ => result.push(self.parse_token_tree()),
}
}
TokenStream::new(result)
}
/// Evaluates the closure with restrictions in place.
///
/// Afters the closure is evaluated, restrictions are reset.
fn with_res<T>(&mut self, res: Restrictions, f: impl FnOnce(&mut Self) -> T) -> T {
let old = self.restrictions;
self.restrictions = res;
let res = f(self);
self.restrictions = old;
res
}
/// Parses `pub` and `pub(in path)` plus shortcuts `pub(crate)` for `pub(in crate)`, `pub(self)`
/// for `pub(in self)` and `pub(super)` for `pub(in super)`.
/// If the following element can't be a tuple (i.e., it's a function definition), then
/// it's not a tuple struct field), and the contents within the parentheses aren't valid,
/// so emit a proper diagnostic.
// Public for rustfmt usage.
pub fn parse_visibility(&mut self, fbt: FollowedByType) -> PResult<'a, Visibility> {
maybe_whole!(self, NtVis, |vis| vis.into_inner());
if !self.eat_keyword(kw::Pub) {
// We need a span for our `Spanned<VisibilityKind>`, but there's inherently no
// keyword to grab a span from for inherited visibility; an empty span at the
// beginning of the current token would seem to be the "Schelling span".
return Ok(Visibility {
span: self.token.span.shrink_to_lo(),
kind: VisibilityKind::Inherited,
tokens: None,
});
}
let lo = self.prev_token.span;
if self.check(&token::OpenDelim(Delimiter::Parenthesis)) {
// We don't `self.bump()` the `(` yet because this might be a struct definition where
// `()` or a tuple might be allowed. For example, `struct Struct(pub (), pub (usize));`.
// Because of this, we only `bump` the `(` if we're assured it is appropriate to do so
// by the following tokens.
if self.is_keyword_ahead(1, &[kw::In]) {
// Parse `pub(in path)`.
self.bump(); // `(`
self.bump(); // `in`
let path = self.parse_path(PathStyle::Mod)?; // `path`
self.expect(&token::CloseDelim(Delimiter::Parenthesis))?; // `)`
let vis = VisibilityKind::Restricted {
path: P(path),
id: ast::DUMMY_NODE_ID,
shorthand: false,
};
return Ok(Visibility {
span: lo.to(self.prev_token.span),
kind: vis,
tokens: None,
});
} else if self.look_ahead(2, |t| t == &token::CloseDelim(Delimiter::Parenthesis))
&& self.is_keyword_ahead(1, &[kw::Crate, kw::Super, kw::SelfLower])
{
// Parse `pub(crate)`, `pub(self)`, or `pub(super)`.
self.bump(); // `(`
let path = self.parse_path(PathStyle::Mod)?; // `crate`/`super`/`self`
self.expect(&token::CloseDelim(Delimiter::Parenthesis))?; // `)`
let vis = VisibilityKind::Restricted {
path: P(path),
id: ast::DUMMY_NODE_ID,
shorthand: true,
};
return Ok(Visibility {
span: lo.to(self.prev_token.span),
kind: vis,
tokens: None,
});
} else if let FollowedByType::No = fbt {
// Provide this diagnostic if a type cannot follow;
// in particular, if this is not a tuple struct.
self.recover_incorrect_vis_restriction()?;
// Emit diagnostic, but continue with public visibility.
}
}
Ok(Visibility { span: lo, kind: VisibilityKind::Public, tokens: None })
}
/// Recovery for e.g. `pub(something) fn ...` or `struct X { pub(something) y: Z }`
fn recover_incorrect_vis_restriction(&mut self) -> PResult<'a, ()> {
self.bump(); // `(`
let path = self.parse_path(PathStyle::Mod)?;
self.expect(&token::CloseDelim(Delimiter::Parenthesis))?; // `)`
let path_str = pprust::path_to_string(&path);
self.dcx()
.emit_err(IncorrectVisibilityRestriction { span: path.span, inner_str: path_str });
Ok(())
}
/// Parses `extern string_literal?`.
fn parse_extern(&mut self, case: Case) -> Extern {
if self.eat_keyword_case(kw::Extern, case) {
let mut extern_span = self.prev_token.span;
let abi = self.parse_abi();
if let Some(abi) = abi {
extern_span = extern_span.to(abi.span);
}
Extern::from_abi(abi, extern_span)
} else {
Extern::None
}
}
/// Parses a string literal as an ABI spec.
fn parse_abi(&mut self) -> Option<StrLit> {
match self.parse_str_lit() {
Ok(str_lit) => Some(str_lit),
Err(Some(lit)) => match lit.kind {
ast::LitKind::Err(_) => None,
_ => {
self.dcx().emit_err(NonStringAbiLiteral { span: lit.span });
None
}
},
Err(None) => None,
}
}
fn collect_tokens_no_attrs<R: HasAttrs + HasTokens>(
&mut self,
f: impl FnOnce(&mut Self) -> PResult<'a, R>,
) -> PResult<'a, R> {
// The only reason to call `collect_tokens_no_attrs` is if you want tokens, so use
// `ForceCollect::Yes`
self.collect_tokens(None, AttrWrapper::empty(), ForceCollect::Yes, |this, _attrs| {
Ok((f(this)?, Trailing::No, UsePreAttrPos::No))
})
}
/// Checks for `::` or, potentially, `:::` and then look ahead after it.
fn check_path_sep_and_look_ahead(&mut self, looker: impl Fn(&Token) -> bool) -> bool {
if self.check(&token::PathSep) {
if self.may_recover() && self.look_ahead(1, |t| t.kind == token::Colon) {
debug_assert!(!self.look_ahead(1, &looker), "Looker must not match on colon");
self.look_ahead(2, looker)
} else {
self.look_ahead(1, looker)
}
} else {
false
}
}
/// `::{` or `::*`
fn is_import_coupler(&mut self) -> bool {
self.check_path_sep_and_look_ahead(|t| {
matches!(t.kind, token::OpenDelim(Delimiter::Brace) | token::BinOp(token::Star))
})
}
// Debug view of the parser's token stream, up to `{lookahead}` tokens.
// Only used when debugging.
#[allow(unused)]
pub(crate) fn debug_lookahead(&self, lookahead: usize) -> impl fmt::Debug + '_ {
struct DebugParser<'dbg> {
parser: &'dbg Parser<'dbg>,
lookahead: usize,
}
impl fmt::Debug for DebugParser<'_> {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
let Self { parser, lookahead } = self;
let mut dbg_fmt = f.debug_struct("Parser"); // or at least, one view of
// we don't need N spans, but we want at least one, so print all of prev_token
dbg_fmt.field("prev_token", &parser.prev_token);
let mut tokens = vec![];
for i in 0..*lookahead {
let tok = parser.look_ahead(i, |tok| tok.kind.clone());
let is_eof = tok == TokenKind::Eof;
tokens.push(tok);
if is_eof {
// Don't look ahead past EOF.
break;
}
}
dbg_fmt.field_with("tokens", |field| field.debug_list().entries(tokens).finish());
dbg_fmt.field("approx_token_stream_pos", &parser.num_bump_calls);
// some fields are interesting for certain values, as they relate to macro parsing
if let Some(subparser) = parser.subparser_name {
dbg_fmt.field("subparser_name", &subparser);
}
if let Recovery::Forbidden = parser.recovery {
dbg_fmt.field("recovery", &parser.recovery);
}
// imply there's "more to know" than this view
dbg_fmt.finish_non_exhaustive()
}
}
DebugParser { parser: self, lookahead }
}
pub fn clear_expected_tokens(&mut self) {
self.expected_tokens.clear();
}
pub fn approx_token_stream_pos(&self) -> u32 {
self.num_bump_calls
}
}
pub(crate) fn make_unclosed_delims_error(
unmatched: UnmatchedDelim,
psess: &ParseSess,
) -> Option<Diag<'_>> {
// `None` here means an `Eof` was found. We already emit those errors elsewhere, we add them to
// `unmatched_delims` only for error recovery in the `Parser`.
let found_delim = unmatched.found_delim?;
let mut spans = vec![unmatched.found_span];
if let Some(sp) = unmatched.unclosed_span {
spans.push(sp);
};
let err = psess.dcx().create_err(MismatchedClosingDelimiter {
spans,
delimiter: pprust::token_kind_to_string(&token::CloseDelim(found_delim)).to_string(),
unmatched: unmatched.found_span,
opening_candidate: unmatched.candidate_span,
unclosed: unmatched.unclosed_span,
});
Some(err)
}
/// A helper struct used when building an `AttrTokenStream` from
/// a `LazyAttrTokenStream`. Both delimiter and non-delimited tokens
/// are stored as `FlatToken::Token`. A vector of `FlatToken`s
/// is then 'parsed' to build up an `AttrTokenStream` with nested
/// `AttrTokenTree::Delimited` tokens.
#[derive(Debug, Clone)]
enum FlatToken {
/// A token - this holds both delimiter (e.g. '{' and '}')
/// and non-delimiter tokens
Token((Token, Spacing)),
/// Holds the `AttrsTarget` for an AST node. The `AttrsTarget` is inserted
/// directly into the constructed `AttrTokenStream` as an
/// `AttrTokenTree::AttrsTarget`.
AttrsTarget(AttrsTarget),
/// A special 'empty' token that is ignored during the conversion
/// to an `AttrTokenStream`. This is used to simplify the
/// handling of replace ranges.
Empty,
}
// Metavar captures of various kinds.
#[derive(Clone, Debug)]
pub enum ParseNtResult {
Tt(TokenTree),
Ident(Ident, IdentIsRaw),
Lifetime(Ident, IdentIsRaw),
/// This case will eventually be removed, along with `Token::Interpolate`.
Nt(Lrc<Nonterminal>),
}