Repository navigation
Expand file tree
/
Copy pathtoken.rs
More file actions
878 lines (818 loc) · 29.2 KB
/
Copy pathtoken.rs
File metadata and controls
878 lines (818 loc) · 29.2 KB
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
//! Token kinds for Python source code created by the lexer and consumed by the `ruff_python_parser`.
//!
//! This module defines the tokens that the lexer recognizes. The tokens are
//! loosely based on the token definitions found in the [CPython source].
//!
//! [CPython source]: https://github.com/python/cpython/blob/dfc2e065a2e71011017077e549cd2f9bf4944c54/Grammar/Tokens
use std::fmt;
use bitflags::bitflags;
use crate::str::{Quote, TripleQuotes};
use crate::str_prefix::{
AnyStringPrefix, ByteStringPrefix, FStringPrefix, StringLiteralPrefix, TStringPrefix,
};
use crate::{AnyStringFlags, BoolOp, Operator, StringFlags, UnaryOp};
use ruff_text_size::{Ranged, TextRange};
mod parentheses;
mod tokens;
pub use parentheses::{parentheses_iterator, parenthesized_range};
pub use tokens::{TokenAt, TokenIterWithContext, Tokens};
#[derive(Clone, Copy, PartialEq, Eq)]
#[cfg_attr(feature = "get-size", derive(get_size2::GetSize))]
pub struct Token {
/// The kind of the token.
kind: TokenKind,
/// The range of the token.
range: TextRange,
/// The set of flags describing this token.
flags: TokenFlags,
}
impl Token {
pub fn new(kind: TokenKind, range: TextRange, flags: TokenFlags) -> Token {
Self { kind, range, flags }
}
/// Returns the token kind.
#[inline]
pub const fn kind(&self) -> TokenKind {
self.kind
}
/// Returns the token as a tuple of (kind, range).
#[inline]
pub const fn as_tuple(&self) -> (TokenKind, TextRange) {
(self.kind, self.range)
}
/// Returns `true` if the current token is a triple-quoted string of any kind.
///
/// # Panics
///
/// If it isn't a string or any f/t-string tokens.
pub fn is_triple_quoted_string(self) -> bool {
self.unwrap_string_flags().is_triple_quoted()
}
/// Returns the [`Quote`] style for the current string token of any kind.
///
/// # Panics
///
/// If it isn't a string or any f/t-string tokens.
pub fn string_quote_style(self) -> Quote {
self.unwrap_string_flags().quote_style()
}
/// Returns the [`AnyStringFlags`] style for the current string token of any kind.
///
/// # Panics
///
/// If it isn't a string or any f/t-string tokens.
pub fn unwrap_string_flags(self) -> AnyStringFlags {
self.string_flags()
.unwrap_or_else(|| panic!("token to be a string"))
}
/// Returns true if the current token is a string and it is raw.
pub fn string_flags(self) -> Option<AnyStringFlags> {
if self.is_any_string() {
Some(self.flags.as_any_string_flags())
} else {
None
}
}
/// Returns `true` if this is any kind of string token - including
/// tokens in t-strings (which do not have type `str`).
const fn is_any_string(self) -> bool {
matches!(
self.kind,
TokenKind::String
| TokenKind::FStringStart
| TokenKind::FStringMiddle
| TokenKind::FStringEnd
| TokenKind::TStringStart
| TokenKind::TStringMiddle
| TokenKind::TStringEnd
)
}
}
impl Ranged for Token {
fn range(&self) -> TextRange {
self.range
}
}
impl fmt::Debug for Token {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
write!(f, "{:?} {:?}", self.kind, self.range)?;
if !self.flags.is_empty() {
f.write_str(" (flags = ")?;
let mut first = true;
for (name, _) in self.flags.iter_names() {
if first {
first = false;
} else {
f.write_str(" | ")?;
}
f.write_str(name)?;
}
f.write_str(")")?;
}
Ok(())
}
}
/// A kind of a token.
#[derive(Copy, Clone, PartialEq, Eq, Hash, Debug, PartialOrd, Ord)]
#[cfg_attr(feature = "get-size", derive(get_size2::GetSize))]
pub enum TokenKind {
/// Token kind for an identifier.
///
/// The lexer emits separate token kinds for keywords and soft keywords. The parser
/// converts soft keyword tokens to this kind when they are used as identifiers.
Identifier,
/// Token kind for an integer.
Int,
/// Token kind for a floating point number.
Float,
/// Token kind for a complex number.
Complex,
/// Token kind for a string.
String,
/// Token kind for the start of an f-string. This includes the `f`/`F`/`fr` prefix
/// and the opening quote(s).
FStringStart,
/// Token kind that includes the portion of text inside the f-string that's not
/// part of the expression part and isn't an opening or closing brace.
FStringMiddle,
/// Token kind for the end of an f-string. This includes the closing quote.
FStringEnd,
/// Token kind for the start of a t-string. This includes the `t`/`T`/`tr` prefix
/// and the opening quote(s).
TStringStart,
/// Token kind that includes the portion of text inside the t-string that's not
/// part of the interpolation part and isn't an opening or closing brace.
TStringMiddle,
/// Token kind for the end of a t-string. This includes the closing quote.
TStringEnd,
/// Token kind for a IPython escape command.
IpyEscapeCommand,
/// Token kind for a comment. These are filtered out of the token stream prior to parsing.
Comment,
/// Token kind for a newline.
Newline,
/// Token kind for a newline that is not a logical line break. These are filtered out of
/// the token stream prior to parsing.
NonLogicalNewline,
/// Token kind for an indent.
Indent,
/// Token kind for a dedent.
Dedent,
EndOfFile,
/// Token kind for a question mark `?`.
Question,
/// Token kind for an exclamation mark `!`.
Exclamation,
/// Token kind for a left parenthesis `(`.
Lpar,
/// Token kind for a right parenthesis `)`.
Rpar,
/// Token kind for a left square bracket `[`.
Lsqb,
/// Token kind for a right square bracket `]`.
Rsqb,
/// Token kind for a colon `:`.
Colon,
/// Token kind for a comma `,`.
Comma,
/// Token kind for a semicolon `;`.
Semi,
/// Token kind for plus `+`.
Plus,
/// Token kind for minus `-`.
Minus,
/// Token kind for star `*`.
Star,
/// Token kind for slash `/`.
Slash,
/// Token kind for vertical bar `|`.
Vbar,
/// Token kind for ampersand `&`.
Amper,
/// Token kind for less than `<`.
Less,
/// Token kind for greater than `>`.
Greater,
/// Token kind for equal `=`.
Equal,
/// Token kind for dot `.`.
Dot,
/// Token kind for percent `%`.
Percent,
/// Token kind for left bracket `{`.
Lbrace,
/// Token kind for right bracket `}`.
Rbrace,
/// Token kind for double equal `==`.
EqEqual,
/// Token kind for not equal `!=`.
NotEqual,
/// Token kind for less than or equal `<=`.
LessEqual,
/// Token kind for greater than or equal `>=`.
GreaterEqual,
/// Token kind for tilde `~`.
Tilde,
/// Token kind for caret `^`.
CircumFlex,
/// Token kind for left shift `<<`.
LeftShift,
/// Token kind for right shift `>>`.
RightShift,
/// Token kind for double star `**`.
DoubleStar,
/// Token kind for double star equal `**=`.
DoubleStarEqual,
/// Token kind for plus equal `+=`.
PlusEqual,
/// Token kind for minus equal `-=`.
MinusEqual,
/// Token kind for star equal `*=`.
StarEqual,
/// Token kind for slash equal `/=`.
SlashEqual,
/// Token kind for percent equal `%=`.
PercentEqual,
/// Token kind for ampersand equal `&=`.
AmperEqual,
/// Token kind for vertical bar equal `|=`.
VbarEqual,
/// Token kind for caret equal `^=`.
CircumflexEqual,
/// Token kind for left shift equal `<<=`.
LeftShiftEqual,
/// Token kind for right shift equal `>>=`.
RightShiftEqual,
/// Token kind for double slash `//`.
DoubleSlash,
/// Token kind for double slash equal `//=`.
DoubleSlashEqual,
/// Token kind for colon equal `:=`.
ColonEqual,
/// Token kind for at `@`.
At,
/// Token kind for at equal `@=`.
AtEqual,
/// Token kind for arrow `->`.
Rarrow,
/// Token kind for ellipsis `...`.
Ellipsis,
// The keywords should be sorted in alphabetical order. If the boundary tokens for the
// "Keywords" and "Soft keywords" group change, update the related methods on `TokenKind`.
// Keywords
And,
As,
Assert,
Async,
Await,
Break,
Class,
Continue,
Def,
Del,
Elif,
Else,
Except,
False,
Finally,
For,
From,
Global,
If,
Import,
In,
Is,
Lambda,
None,
Nonlocal,
Not,
Or,
Pass,
Raise,
Return,
True,
Try,
While,
With,
Yield,
// Soft keywords
Case,
Lazy,
Match,
Type,
Unknown,
}
impl TokenKind {
/// Returns `true` if this is an end of file token.
#[inline]
pub const fn is_eof(self) -> bool {
matches!(self, TokenKind::EndOfFile)
}
/// Returns `true` if this is a dot token (`.`).
#[inline]
pub const fn is_dot(self) -> bool {
matches!(self, TokenKind::Dot)
}
/// Returns `true` if this is a left brace token (`{`).
#[inline]
pub const fn is_lbrace(self) -> bool {
matches!(self, TokenKind::Lbrace)
}
/// Returns `true` if this is either a newline or non-logical newline token.
#[inline]
pub const fn is_any_newline(self) -> bool {
matches!(self, TokenKind::Newline | TokenKind::NonLogicalNewline)
}
/// Returns `true` if the token is a keyword (including soft keywords).
///
/// See also [`is_soft_keyword`], [`is_non_soft_keyword`].
///
/// [`is_soft_keyword`]: TokenKind::is_soft_keyword
/// [`is_non_soft_keyword`]: TokenKind::is_non_soft_keyword
#[inline]
pub fn is_keyword(self) -> bool {
TokenKind::And <= self && self <= TokenKind::Type
}
/// Returns `true` if the token is strictly a soft keyword.
///
/// See also [`is_keyword`], [`is_non_soft_keyword`].
///
/// [`is_keyword`]: TokenKind::is_keyword
/// [`is_non_soft_keyword`]: TokenKind::is_non_soft_keyword
#[inline]
pub fn is_soft_keyword(self) -> bool {
TokenKind::Case <= self && self <= TokenKind::Type
}
/// Returns `true` if the token is strictly a non-soft keyword.
///
/// See also [`is_keyword`], [`is_soft_keyword`].
///
/// [`is_keyword`]: TokenKind::is_keyword
/// [`is_soft_keyword`]: TokenKind::is_soft_keyword
#[inline]
pub fn is_non_soft_keyword(self) -> bool {
TokenKind::And <= self && self <= TokenKind::Yield
}
#[inline]
pub const fn is_operator(self) -> bool {
matches!(
self,
TokenKind::Lpar
| TokenKind::Rpar
| TokenKind::Lsqb
| TokenKind::Rsqb
| TokenKind::Comma
| TokenKind::Semi
| TokenKind::Plus
| TokenKind::Minus
| TokenKind::Star
| TokenKind::Slash
| TokenKind::Vbar
| TokenKind::Amper
| TokenKind::Less
| TokenKind::Greater
| TokenKind::Equal
| TokenKind::Dot
| TokenKind::Percent
| TokenKind::Lbrace
| TokenKind::Rbrace
| TokenKind::EqEqual
| TokenKind::NotEqual
| TokenKind::LessEqual
| TokenKind::GreaterEqual
| TokenKind::Tilde
| TokenKind::CircumFlex
| TokenKind::LeftShift
| TokenKind::RightShift
| TokenKind::DoubleStar
| TokenKind::PlusEqual
| TokenKind::MinusEqual
| TokenKind::StarEqual
| TokenKind::SlashEqual
| TokenKind::PercentEqual
| TokenKind::AmperEqual
| TokenKind::VbarEqual
| TokenKind::CircumflexEqual
| TokenKind::LeftShiftEqual
| TokenKind::RightShiftEqual
| TokenKind::DoubleStarEqual
| TokenKind::DoubleSlash
| TokenKind::DoubleSlashEqual
| TokenKind::At
| TokenKind::AtEqual
| TokenKind::Rarrow
| TokenKind::Ellipsis
| TokenKind::ColonEqual
| TokenKind::Colon
| TokenKind::And
| TokenKind::Or
| TokenKind::Not
| TokenKind::In
| TokenKind::Is
)
}
/// Returns `true` if this is a singleton token i.e., `True`, `False`, or `None`.
#[inline]
pub const fn is_singleton(self) -> bool {
matches!(self, TokenKind::False | TokenKind::True | TokenKind::None)
}
/// Returns `true` if this is a trivia token i.e., a comment or a non-logical newline.
#[inline]
pub const fn is_trivia(&self) -> bool {
matches!(self, TokenKind::Comment | TokenKind::NonLogicalNewline)
}
/// Returns `true` if this is a comment token.
#[inline]
pub const fn is_comment(&self) -> bool {
matches!(self, TokenKind::Comment)
}
#[inline]
pub const fn is_arithmetic(self) -> bool {
matches!(
self,
TokenKind::DoubleStar
| TokenKind::Star
| TokenKind::Plus
| TokenKind::Minus
| TokenKind::Slash
| TokenKind::DoubleSlash
| TokenKind::At
)
}
#[inline]
pub const fn is_bitwise_or_shift(self) -> bool {
matches!(
self,
TokenKind::LeftShift
| TokenKind::LeftShiftEqual
| TokenKind::RightShift
| TokenKind::RightShiftEqual
| TokenKind::Amper
| TokenKind::AmperEqual
| TokenKind::Vbar
| TokenKind::VbarEqual
| TokenKind::CircumFlex
| TokenKind::CircumflexEqual
| TokenKind::Tilde
)
}
/// Returns `true` if the current token is a unary arithmetic operator.
#[inline]
pub const fn is_unary_arithmetic_operator(self) -> bool {
matches!(self, TokenKind::Plus | TokenKind::Minus)
}
#[inline]
pub const fn is_interpolated_string_end(self) -> bool {
matches!(self, TokenKind::FStringEnd | TokenKind::TStringEnd)
}
/// Returns the [`UnaryOp`] that corresponds to this token kind, if it is a unary arithmetic
/// operator, otherwise return [None].
///
/// Use [`as_unary_operator`] to match against any unary operator.
///
/// [`as_unary_operator`]: TokenKind::as_unary_operator
#[inline]
pub const fn as_unary_arithmetic_operator(self) -> Option<UnaryOp> {
Some(match self {
TokenKind::Plus => UnaryOp::UAdd,
TokenKind::Minus => UnaryOp::USub,
_ => return None,
})
}
/// Returns the [`UnaryOp`] that corresponds to this token kind, if it is a unary operator,
/// otherwise return [None].
///
/// Use [`as_unary_arithmetic_operator`] to match against only an arithmetic unary operator.
///
/// [`as_unary_arithmetic_operator`]: TokenKind::as_unary_arithmetic_operator
#[inline]
pub const fn as_unary_operator(self) -> Option<UnaryOp> {
Some(match self {
TokenKind::Plus => UnaryOp::UAdd,
TokenKind::Minus => UnaryOp::USub,
TokenKind::Tilde => UnaryOp::Invert,
TokenKind::Not => UnaryOp::Not,
_ => return None,
})
}
/// Returns the [`BoolOp`] that corresponds to this token kind, if it is a boolean operator,
/// otherwise return [None].
#[inline]
pub const fn as_bool_operator(self) -> Option<BoolOp> {
Some(match self {
TokenKind::And => BoolOp::And,
TokenKind::Or => BoolOp::Or,
_ => return None,
})
}
/// Returns the binary [`Operator`] that corresponds to the current token, if it's a binary
/// operator, otherwise return [None].
///
/// Use [`as_augmented_assign_operator`] to match against an augmented assignment token.
///
/// [`as_augmented_assign_operator`]: TokenKind::as_augmented_assign_operator
pub const fn as_binary_operator(self) -> Option<Operator> {
Some(match self {
TokenKind::Plus => Operator::Add,
TokenKind::Minus => Operator::Sub,
TokenKind::Star => Operator::Mult,
TokenKind::At => Operator::MatMult,
TokenKind::DoubleStar => Operator::Pow,
TokenKind::Slash => Operator::Div,
TokenKind::DoubleSlash => Operator::FloorDiv,
TokenKind::Percent => Operator::Mod,
TokenKind::Amper => Operator::BitAnd,
TokenKind::Vbar => Operator::BitOr,
TokenKind::CircumFlex => Operator::BitXor,
TokenKind::LeftShift => Operator::LShift,
TokenKind::RightShift => Operator::RShift,
_ => return None,
})
}
/// Returns the [`Operator`] that corresponds to this token kind, if it is
/// an augmented assignment operator, or [`None`] otherwise.
#[inline]
pub const fn as_augmented_assign_operator(self) -> Option<Operator> {
Some(match self {
TokenKind::PlusEqual => Operator::Add,
TokenKind::MinusEqual => Operator::Sub,
TokenKind::StarEqual => Operator::Mult,
TokenKind::AtEqual => Operator::MatMult,
TokenKind::DoubleStarEqual => Operator::Pow,
TokenKind::SlashEqual => Operator::Div,
TokenKind::DoubleSlashEqual => Operator::FloorDiv,
TokenKind::PercentEqual => Operator::Mod,
TokenKind::AmperEqual => Operator::BitAnd,
TokenKind::VbarEqual => Operator::BitOr,
TokenKind::CircumflexEqual => Operator::BitXor,
TokenKind::LeftShiftEqual => Operator::LShift,
TokenKind::RightShiftEqual => Operator::RShift,
_ => return None,
})
}
}
impl From<BoolOp> for TokenKind {
#[inline]
fn from(op: BoolOp) -> Self {
match op {
BoolOp::And => TokenKind::And,
BoolOp::Or => TokenKind::Or,
}
}
}
impl From<UnaryOp> for TokenKind {
#[inline]
fn from(op: UnaryOp) -> Self {
match op {
UnaryOp::Invert => TokenKind::Tilde,
UnaryOp::Not => TokenKind::Not,
UnaryOp::UAdd => TokenKind::Plus,
UnaryOp::USub => TokenKind::Minus,
}
}
}
impl From<Operator> for TokenKind {
#[inline]
fn from(op: Operator) -> Self {
match op {
Operator::Add => TokenKind::Plus,
Operator::Sub => TokenKind::Minus,
Operator::Mult => TokenKind::Star,
Operator::MatMult => TokenKind::At,
Operator::Div => TokenKind::Slash,
Operator::Mod => TokenKind::Percent,
Operator::Pow => TokenKind::DoubleStar,
Operator::LShift => TokenKind::LeftShift,
Operator::RShift => TokenKind::RightShift,
Operator::BitOr => TokenKind::Vbar,
Operator::BitXor => TokenKind::CircumFlex,
Operator::BitAnd => TokenKind::Amper,
Operator::FloorDiv => TokenKind::DoubleSlash,
}
}
}
impl fmt::Display for TokenKind {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
let value = match self {
TokenKind::Unknown => "Unknown",
TokenKind::Newline => "newline",
TokenKind::NonLogicalNewline => "NonLogicalNewline",
TokenKind::Indent => "indent",
TokenKind::Dedent => "dedent",
TokenKind::EndOfFile => "end of file",
TokenKind::Identifier => "identifier",
TokenKind::Int => "int",
TokenKind::Float => "float",
TokenKind::Complex => "complex",
TokenKind::String => "string",
TokenKind::FStringStart => "FStringStart",
TokenKind::FStringMiddle => "FStringMiddle",
TokenKind::FStringEnd => "FStringEnd",
TokenKind::TStringStart => "TStringStart",
TokenKind::TStringMiddle => "TStringMiddle",
TokenKind::TStringEnd => "TStringEnd",
TokenKind::IpyEscapeCommand => "IPython escape command",
TokenKind::Comment => "comment",
TokenKind::Question => "`?`",
TokenKind::Exclamation => "`!`",
TokenKind::Lpar => "`(`",
TokenKind::Rpar => "`)`",
TokenKind::Lsqb => "`[`",
TokenKind::Rsqb => "`]`",
TokenKind::Lbrace => "`{`",
TokenKind::Rbrace => "`}`",
TokenKind::Equal => "`=`",
TokenKind::ColonEqual => "`:=`",
TokenKind::Dot => "`.`",
TokenKind::Colon => "`:`",
TokenKind::Semi => "`;`",
TokenKind::Comma => "`,`",
TokenKind::Rarrow => "`->`",
TokenKind::Plus => "`+`",
TokenKind::Minus => "`-`",
TokenKind::Star => "`*`",
TokenKind::DoubleStar => "`**`",
TokenKind::Slash => "`/`",
TokenKind::DoubleSlash => "`//`",
TokenKind::Percent => "`%`",
TokenKind::Vbar => "`|`",
TokenKind::Amper => "`&`",
TokenKind::CircumFlex => "`^`",
TokenKind::LeftShift => "`<<`",
TokenKind::RightShift => "`>>`",
TokenKind::Tilde => "`~`",
TokenKind::At => "`@`",
TokenKind::Less => "`<`",
TokenKind::Greater => "`>`",
TokenKind::EqEqual => "`==`",
TokenKind::NotEqual => "`!=`",
TokenKind::LessEqual => "`<=`",
TokenKind::GreaterEqual => "`>=`",
TokenKind::PlusEqual => "`+=`",
TokenKind::MinusEqual => "`-=`",
TokenKind::StarEqual => "`*=`",
TokenKind::DoubleStarEqual => "`**=`",
TokenKind::SlashEqual => "`/=`",
TokenKind::DoubleSlashEqual => "`//=`",
TokenKind::PercentEqual => "`%=`",
TokenKind::VbarEqual => "`|=`",
TokenKind::AmperEqual => "`&=`",
TokenKind::CircumflexEqual => "`^=`",
TokenKind::LeftShiftEqual => "`<<=`",
TokenKind::RightShiftEqual => "`>>=`",
TokenKind::AtEqual => "`@=`",
TokenKind::Ellipsis => "`...`",
TokenKind::False => "`False`",
TokenKind::None => "`None`",
TokenKind::True => "`True`",
TokenKind::And => "`and`",
TokenKind::As => "`as`",
TokenKind::Assert => "`assert`",
TokenKind::Async => "`async`",
TokenKind::Await => "`await`",
TokenKind::Break => "`break`",
TokenKind::Class => "`class`",
TokenKind::Continue => "`continue`",
TokenKind::Def => "`def`",
TokenKind::Del => "`del`",
TokenKind::Elif => "`elif`",
TokenKind::Else => "`else`",
TokenKind::Except => "`except`",
TokenKind::Finally => "`finally`",
TokenKind::For => "`for`",
TokenKind::From => "`from`",
TokenKind::Global => "`global`",
TokenKind::If => "`if`",
TokenKind::Import => "`import`",
TokenKind::In => "`in`",
TokenKind::Is => "`is`",
TokenKind::Lambda => "`lambda`",
TokenKind::Nonlocal => "`nonlocal`",
TokenKind::Not => "`not`",
TokenKind::Or => "`or`",
TokenKind::Pass => "`pass`",
TokenKind::Raise => "`raise`",
TokenKind::Return => "`return`",
TokenKind::Try => "`try`",
TokenKind::While => "`while`",
TokenKind::Lazy => "`lazy`",
TokenKind::Match => "`match`",
TokenKind::Type => "`type`",
TokenKind::Case => "`case`",
TokenKind::With => "`with`",
TokenKind::Yield => "`yield`",
};
f.write_str(value)
}
}
bitflags! {
#[derive(Clone, Copy, Debug, PartialEq, Eq)]
pub struct TokenFlags: u16 {
/// The token is a string with double quotes (`"`).
const DOUBLE_QUOTES = 1 << 0;
/// The token is a triple-quoted string i.e., it starts and ends with three consecutive
/// quote characters (`"""` or `'''`).
const TRIPLE_QUOTED_STRING = 1 << 1;
/// The token is a unicode string i.e., prefixed with `u` or `U`
const UNICODE_STRING = 1 << 2;
/// The token is a byte string i.e., prefixed with `b` or `B`
const BYTE_STRING = 1 << 3;
/// The token is an f-string i.e., prefixed with `f` or `F`
const F_STRING = 1 << 4;
/// The token is a t-string i.e., prefixed with `t` or `T`
const T_STRING = 1 << 5;
/// The token is a raw string and the prefix character is in lowercase.
const RAW_STRING_LOWERCASE = 1 << 6;
/// The token is a raw string and the prefix character is in uppercase.
const RAW_STRING_UPPERCASE = 1 << 7;
/// String without matching closing quote(s)
const UNCLOSED_STRING = 1 << 8;
/// The token is an identifier containing at least one non-ASCII codepoint.
const NON_ASCII_IDENTIFIER = 1 << 9;
/// The token is a raw string i.e., prefixed with `r` or `R`
const RAW_STRING = Self::RAW_STRING_LOWERCASE.bits() | Self::RAW_STRING_UPPERCASE.bits();
}
}
#[cfg(feature = "get-size")]
impl get_size2::GetSize for TokenFlags {}
impl StringFlags for TokenFlags {
fn quote_style(self) -> Quote {
if self.intersects(TokenFlags::DOUBLE_QUOTES) {
Quote::Double
} else {
Quote::Single
}
}
fn triple_quotes(self) -> TripleQuotes {
if self.intersects(TokenFlags::TRIPLE_QUOTED_STRING) {
TripleQuotes::Yes
} else {
TripleQuotes::No
}
}
fn prefix(self) -> AnyStringPrefix {
if self.intersects(TokenFlags::F_STRING) {
if self.intersects(TokenFlags::RAW_STRING_LOWERCASE) {
AnyStringPrefix::Format(FStringPrefix::Raw { uppercase_r: false })
} else if self.intersects(TokenFlags::RAW_STRING_UPPERCASE) {
AnyStringPrefix::Format(FStringPrefix::Raw { uppercase_r: true })
} else {
AnyStringPrefix::Format(FStringPrefix::Regular)
}
} else if self.intersects(TokenFlags::T_STRING) {
if self.intersects(TokenFlags::RAW_STRING_LOWERCASE) {
AnyStringPrefix::Template(TStringPrefix::Raw { uppercase_r: false })
} else if self.intersects(TokenFlags::RAW_STRING_UPPERCASE) {
AnyStringPrefix::Template(TStringPrefix::Raw { uppercase_r: true })
} else {
AnyStringPrefix::Template(TStringPrefix::Regular)
}
} else if self.intersects(TokenFlags::BYTE_STRING) {
if self.intersects(TokenFlags::RAW_STRING_LOWERCASE) {
AnyStringPrefix::Bytes(ByteStringPrefix::Raw { uppercase_r: false })
} else if self.intersects(TokenFlags::RAW_STRING_UPPERCASE) {
AnyStringPrefix::Bytes(ByteStringPrefix::Raw { uppercase_r: true })
} else {
AnyStringPrefix::Bytes(ByteStringPrefix::Regular)
}
} else if self.intersects(TokenFlags::RAW_STRING_LOWERCASE) {
AnyStringPrefix::Regular(StringLiteralPrefix::Raw { uppercase: false })
} else if self.intersects(TokenFlags::RAW_STRING_UPPERCASE) {
AnyStringPrefix::Regular(StringLiteralPrefix::Raw { uppercase: true })
} else if self.intersects(TokenFlags::UNICODE_STRING) {
AnyStringPrefix::Regular(StringLiteralPrefix::Unicode)
} else {
AnyStringPrefix::Regular(StringLiteralPrefix::Empty)
}
}
fn is_unclosed(self) -> bool {
self.intersects(TokenFlags::UNCLOSED_STRING)
}
}
impl TokenFlags {
/// Returns `true` if the token is an f-string.
pub const fn is_f_string(self) -> bool {
self.intersects(TokenFlags::F_STRING)
}
/// Returns `true` if the token is a t-string.
pub const fn is_t_string(self) -> bool {
self.intersects(TokenFlags::T_STRING)
}
/// Returns `true` if the token is a t-string.
pub const fn is_interpolated_string(self) -> bool {
self.intersects(TokenFlags::T_STRING.union(TokenFlags::F_STRING))
}
/// Returns `true` if the token is a triple-quoted t-string.
pub fn is_triple_quoted_interpolated_string(self) -> bool {
self.intersects(TokenFlags::TRIPLE_QUOTED_STRING) && self.is_interpolated_string()
}
/// Returns `true` if the token is a raw string.
pub const fn is_raw_string(self) -> bool {
self.intersects(TokenFlags::RAW_STRING)
}
/// Returns `true` if the token is an identifier containing at least one non-ASCII codepoint.
#[inline]
pub const fn is_non_ascii_identifier(self) -> bool {
self.intersects(TokenFlags::NON_ASCII_IDENTIFIER)
}
}