tokit 0.0.0

Blazing fast parser combinators: parse-while-lexing (zero-copy), deterministic LALR-style parsing, no backtracking. Flexible emitters for fail-fast runtime or greedy compiler diagnostics
Documentation
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
//! Keywordifier types for language syntax trees.
//!
//! This module provides generic identifier types that can be used across different
//! programming languages and string representations. Keywordifiers are fundamental
//! building blocks in most languages, representing names for variables, functions,
//! types, and other named entities.
//!
//! # Design Philosophy
//!
//! The [`Keyword`] type is generic over both the source string type (`S`) and the
//! language marker (`Lang`). This design provides maximum flexibility:
//!
//! - **String type flexibility**: Use `&str` for zero-copy parsing, `String` for
//!   owned data, or custom interned string types for memory efficiency
//! - **Language safety**: The `Lang` parameter ensures keywords from different
//!   languages don't mix accidentally
//! - **SimpleSpan tracking**: All keywords carry their source location for diagnostics
//!
//! # Common Usage Patterns
//!
//! ## Zero-Copy Parsing
//!
//! ```rust,ignore
//! use tokit::types::Keyword;
//! use tokit::utils::SimpleSimpleSpan;
//!
//! // Parse keywords without allocating
//! type YulKeyword<'a> = Keyword<&'a str, YulLang>;
//!
//! let ident = YulKeyword::new(SimpleSpan::new(0, 3), "foo");
//! assert_eq!(ident.source_ref(), &"foo");
//! ```
//!
//! ## Owned Keywordifiers
//!
//! ```rust,ignore
//! // Store keywords in AST nodes that outlive the source
//! type OwnedKeyword = Keyword<String, MyLang>;
//!
//! let ident = OwnedKeyword::new(span, source_str.to_string());
//! ```
//!
//! ## String Interning
//!
//! ```rust,ignore
//! // Use interned strings for memory efficiency
//! type InternedKeyword = Keyword<Symbol, MyLang>;
//!
//! let ident = InternedKeyword::new(span, interner.intern("identifier"));
//! ```
//!
//! # Error Recovery
//!
//! `Keyword` implements [`ErrorNode`] when the source type `S` also implements it,
//! allowing creation of placeholder keywords during error recovery:
//!
//! ```rust,ignore
//! use tokit::error::ErrorNode;
//!
//! // Create placeholder for malformed identifier
//! let bad_ident = Keyword::<String, YulLang>::error(span);
//!
//! // Create placeholder for missing identifier
//! let missing_ident = Keyword::<String, YulLang>::missing(span);
//! ```

use core::marker::PhantomData;

use crate::{
  error::ErrorNode,
  utils::{AsSpan, IntoComponents, SimpleSpan},
};

/// A language identifier with span tracking.
///
/// Keywordifiers are names used in source code to refer to variables, functions,
/// types, and other named entities. This type wraps a source string representation
/// with position information and a language marker.
///
/// # Type Parameters
///
/// - `S`: The source string type (`&str`, `String`, interned string, etc.)
/// - `Lang`: Language marker type for type safety (e.g., `YulLang`, `SolidityLang`)
///
/// # Design Notes
///
/// ## Why Generic Over String Type?
///
/// Different use cases require different string representations:
/// - **Parsing**: Use `&str` for zero-copy efficiency
/// - **AST storage**: Use `String` when the AST outlives the source
/// - **Large codebases**: Use interned strings to deduplicate common keywords
///
/// ## Why Language Marker?
///
/// The `Lang` parameter prevents mixing keywords from different languages:
/// ```rust,ignore
/// let yul_ident: Keyword<&str, YulLang> = ...;
/// let sol_ident: Keyword<&str, SolidityLang> = ...;
///
/// // Compile error: type mismatch
/// // let mixed = vec![yul_ident, sol_ident];
/// ```
///
/// # Examples
///
/// ## Creating Keywordifiers
///
/// ```rust
/// use tokit::types::Keyword;
/// use tokit::utils::SimpleSimpleSpan;
/// # struct MyLang;
///
/// // Zero-copy identifier
/// let span = SimpleSpan::new(5, 11);
/// let ident = Keyword::<&str, MyLang>::new(span, "my_var");
///
/// assert_eq!(ident.span(), span);
/// assert_eq!(ident.source_ref(), &"my_var");
/// ```
///
/// ## Extracting Components
///
/// ```rust
/// # use tokit::types::Keyword;
/// # use tokit::utils::{SimpleSpan, IntoComponents};
/// # struct MyLang;
/// # let span = SimpleSpan::new(0, 3);
/// let ident = Keyword::<&str, MyLang>::new(span, "foo");
///
/// // Destructure into span and source
/// let (span, source) = ident.into_components();
/// assert_eq!(source, "foo");
/// ```
///
/// ## Mutable Access
///
/// ```rust
/// # use tokit::types::Keyword;
/// # use tokit::utils::SimpleSimpleSpan;
/// # struct MyLang;
/// # let span = SimpleSpan::new(0, 3);
/// let mut ident = Keyword::<String, MyLang>::new(span, "original".to_string());
///
/// // Update the source string
/// *ident.source_mut() = "modified".to_string();
/// assert_eq!(ident.source_ref(), "modified");
///
/// // Update the span
/// *ident.span_mut() = SimpleSpan::new(10, 18);
/// assert_eq!(ident.span(), SimpleSpan::new(10, 18));
/// ```
#[derive(Debug, Copy, Clone, PartialEq, Eq, Hash)]
pub struct Keyword<S, Lang> {
  span: SimpleSpan,
  ident: S,
  _lang: PhantomData<Lang>,
}

impl<S, Lang> From<Keyword<S, Lang>> for super::Ident<S, Lang> {
  #[cfg_attr(not(tarpaulin), inline(always))]
  fn from(keyword: Keyword<S, Lang>) -> Self {
    Self::new(keyword.span, keyword.ident)
  }
}

impl<S, Lang> AsSpan<SimpleSpan> for Keyword<S, Lang> {
  #[cfg_attr(not(tarpaulin), inline(always))]
  fn as_span(&self) -> &SimpleSpan {
    self.span_ref()
  }
}

impl<S, Lang> IntoComponents for Keyword<S, Lang> {
  type Components = (SimpleSpan, S);

  #[cfg_attr(not(tarpaulin), inline(always))]
  fn into_components(self) -> Self::Components {
    (self.span, self.ident)
  }
}

impl<S, Lang> Keyword<S, Lang> {
  /// Creates a new identifier with the given span and source string.
  ///
  /// # Parameters
  ///
  /// - `span`: The source location of this identifier
  /// - `source`: The identifier string (can be `&str`, `String`, or custom type)
  ///
  /// # Examples
  ///
  /// ```rust
  /// use tokit::types::Keyword;
  /// use tokit::utils::SimpleSimpleSpan;
  /// # struct YulLang;
  ///
  /// let span = SimpleSpan::new(10, 15);
  /// let ident = Keyword::<&str, YulLang>::new(span, "count");
  ///
  /// assert_eq!(ident.span(), span);
  /// assert_eq!(ident.source_ref(), &"count");
  /// ```
  #[cfg_attr(not(tarpaulin), inline(always))]
  pub const fn new(span: SimpleSpan, source: S) -> Self {
    Self {
      span,
      ident: source,
      _lang: PhantomData,
    }
  }

  /// Returns the span (source location) of this identifier.
  ///
  /// # Examples
  ///
  /// ```rust
  /// # use tokit::types::Keyword;
  /// # use tokit::utils::SimpleSimpleSpan;
  /// # struct MyLang;
  /// let ident = Keyword::<&str, MyLang>::new(SimpleSpan::new(5, 10), "value");
  ///
  /// assert_eq!(ident.span(), SimpleSpan::new(5, 10));
  /// ```
  #[cfg_attr(not(tarpaulin), inline(always))]
  pub const fn span(&self) -> SimpleSpan {
    self.span
  }

  /// Returns an immutable reference to the span.
  ///
  /// Use this when you need to borrow the span without copying it.
  ///
  /// # Examples
  ///
  /// ```rust
  /// # use tokit::types::Keyword;
  /// # use tokit::utils::SimpleSimpleSpan;
  /// # struct MyLang;
  /// let ident = Keyword::<&str, MyLang>::new(SimpleSpan::new(0, 3), "foo");
  ///
  /// let span_ref = ident.span_ref();
  /// assert_eq!(*span_ref, SimpleSpan::new(0, 3));
  /// ```
  #[cfg_attr(not(tarpaulin), inline(always))]
  pub const fn span_ref(&self) -> &SimpleSpan {
    &self.span
  }

  /// Returns a mutable reference to the span.
  ///
  /// Use this to update the identifier's source location, for example during
  /// AST transformations or span adjustments.
  ///
  /// # Examples
  ///
  /// ```rust
  /// # use tokit::types::Keyword;
  /// # use tokit::utils::SimpleSimpleSpan;
  /// # struct MyLang;
  /// let mut ident = Keyword::<&str, MyLang>::new(SimpleSpan::new(0, 3), "foo");
  ///
  /// *ident.span_mut() = SimpleSpan::new(10, 13);
  /// assert_eq!(ident.span(), SimpleSpan::new(10, 13));
  /// ```
  #[cfg_attr(not(tarpaulin), inline(always))]
  pub const fn span_mut(&mut self) -> &mut SimpleSpan {
    &mut self.span
  }

  /// Returns a mutable reference to the source string.
  ///
  /// Use this to modify the identifier's text, for example during AST
  /// transformations or name mangling.
  ///
  /// # Examples
  ///
  /// ```rust
  /// # use tokit::types::Keyword;
  /// # use tokit::utils::SimpleSimpleSpan;
  /// # struct MyLang;
  /// let mut ident = Keyword::<String, MyLang>::new(SimpleSpan::new(0, 3), "foo".to_string());
  ///
  /// *ident.source_mut() = "bar".to_string();
  /// assert_eq!(ident.source_ref(), "bar");
  /// ```
  #[cfg_attr(not(tarpaulin), inline(always))]
  pub const fn source_mut(&mut self) -> &mut S {
    &mut self.ident
  }

  /// Returns an immutable reference to the source string.
  ///
  /// This is the most common way to access the identifier's text without
  /// consuming or copying it.
  ///
  /// # Examples
  ///
  /// ```rust
  /// # use tokit::types::Keyword;
  /// # use tokit::utils::SimpleSimpleSpan;
  /// # struct MyLang;
  /// let ident = Keyword::<&str, MyLang>::new(SimpleSpan::new(0, 8), "variable");
  ///
  /// assert_eq!(ident.source_ref(), &"variable");
  /// assert_eq!(ident.source_ref().len(), 8);
  /// ```
  #[cfg_attr(not(tarpaulin), inline(always))]
  pub const fn source_ref(&self) -> &S {
    &self.ident
  }

  /// Returns a copy of the source string by value.
  ///
  /// This method is only available when the source type `S` implements [`Copy`].
  /// Useful for types like `&str` or interned string handles.
  ///
  /// For owned types like `String`, use [`source_ref`](Self::source_ref) to
  /// avoid cloning, or consume the identifier with
  /// [`into_components`](crate::utils::IntoComponents::into_components).
  ///
  /// # Examples
  ///
  /// ```rust
  /// # use tokit::types::Keyword;
  /// # use tokit::utils::SimpleSimpleSpan;
  /// # struct MyLang;
  /// let ident = Keyword::<&str, MyLang>::new(SimpleSpan::new(0, 2), "id");
  ///
  /// let source: &str = ident.source(); // Copy
  /// assert_eq!(source, "id");
  /// // ident is still usable
  /// assert_eq!(ident.source_ref(), &"id");
  /// ```
  #[cfg_attr(not(tarpaulin), inline(always))]
  pub const fn source(&self) -> S
  where
    S: Copy,
  {
    self.ident
  }

  /// Consumes the identifier and returns the span and source string.
  #[cfg_attr(not(tarpaulin), inline(always))]
  pub fn into_components(self) -> (SimpleSpan, S) {
    (self.span, self.ident)
  }

  /// Maps the source string to a new type, preserving the span and language.
  #[cfg_attr(not(tarpaulin), inline(always))]
  pub fn map<U>(self, f: impl FnOnce(S) -> U) -> Keyword<U, Lang> {
    Keyword::new(self.span, f(self.ident))
  }
}

impl<S, Lang> ErrorNode for Keyword<S, Lang>
where
  S: ErrorNode,
{
  /// Creates a placeholder identifier for **malformed content**.
  ///
  /// Used during error recovery when the parser encounters invalid identifier
  /// syntax. The source string `S` will also be created as an error placeholder.
  ///
  /// # Examples
  ///
  /// ```rust,ignore
  /// use tokit::types::Keyword;
  /// use tokit::error::ErrorNode;
  ///
  /// // Parser found "123abc" where an identifier was expected
  /// let bad_ident = Keyword::<String, YulLang>::error(span);
  /// ```
  #[cfg_attr(not(tarpaulin), inline(always))]
  fn error(span: SimpleSpan) -> Self {
    Self::new(span, S::error(span))
  }

  /// Creates a placeholder identifier for **missing required content**.
  ///
  /// Used during error recovery when the parser expects an identifier but
  /// finds nothing at all. The source string `S` will also be created as
  /// a missing placeholder.
  ///
  /// # Examples
  ///
  /// ```rust,ignore
  /// use tokit::types::Keyword;
  /// use tokit::error::ErrorNode;
  ///
  /// // Parser expected identifier after "let" but found "="
  /// // Correct: let name = 5;
  /// // Found:   let = 5;
  /// let missing_ident = Keyword::<String, YulLang>::missing(span);
  /// ```
  #[cfg_attr(not(tarpaulin), inline(always))]
  fn missing(span: SimpleSpan) -> Self {
    Self::new(span, S::missing(span))
  }
}

// #[cfg(feature = "chumsky")]
// #[cfg_attr(docsrs, doc(cfg(feature = "chumsky")))]
// const _: () = {
//   use chumsky::{Parser, extra::ParserExtra, prelude::*};
//   use logos::{Logos, Source};

//   use crate::{
//     KeywordToken, Lexed, LogoStream, error::UnexpectedToken, syntax::Language, utils::SimpleSimpleSpanned,
//   };

//   impl<S, Lang> Keyword<S, Lang> {
//     /// Creates a Chumsky parser that parses identifier tokens into `Keyword`.
//     ///
//     /// This parser validates that the token is an identifier (not a keyword or other
//     /// token type) and converts it to an `Keyword` with proper span tracking.
//     ///
//     /// # Type Parameters
//     ///
//     /// - `'a`: Lifetime of the input source
//     /// - `I`: Token stream implementing [`LogoStream`]
//     /// - `T`: Token type implementing [`KeywordifierToken`]
//     /// - `Error`: Error type that can be constructed from lexer and parser errors
//     /// - `E`: Parser extra state carrying errors and metadata
//     ///
//     /// # Parameters
//     ///
//     /// - `ident_kind`: Function that returns the expected syntax kind for error
//     ///   reporting. Called when a non-identifier token is found.
//     ///
//     /// # Returns
//     ///
//     /// A Chumsky parser that produces `Keyword<S, Lang>` on success or emits an
//     /// [`UnexpectedToken`] error when a non-identifier is found.
//     ///
//     /// # Error Behavior
//     ///
//     /// The parser fails with an error in these cases:
//     /// - Token is not an identifier (e.g., keyword, operator, literal)
//     /// - Lexer error occurred while scanning the token
//     ///
//     /// # Examples
//     ///
//     /// ## Basic Usage
//     ///
//     /// ```rust,ignore
//     /// use tokit::types::Keyword;
//     /// use tokit::chumsky::Parser;
//     ///
//     /// // Parser for YUL keywords
//     /// let ident_parser = Keyword::<&str, YulLang>::parser(|| YulSyntaxKind::Keyword);
//     ///
//     /// // Parse "count" into Keyword
//     /// let result = ident_parser.parse(stream)?;
//     /// assert_eq!(result.source_ref(), &"count");
//     /// ```
//     ///
//     /// ## With Error Recovery
//     ///
//     /// ```rust,ignore
//     /// use tokit::types::Keyword;
//     /// use tokit::error::ErrorNode;
//     /// use tokit::chumsky::{Parser, prelude::*};
//     ///
//     /// // Parser with recovery for missing keywords
//     /// let ident_parser = Keyword::<String, YulLang>::parser(|| YulSyntaxKind::Keyword)
//     ///     .recover_with(via_parser(
//     ///         // Create placeholder on error
//     ///         empty().map_with(|_, exa| Keyword::missing(exa.span()))
//     ///     ));
//     ///
//     /// // Even with missing identifier, parsing continues
//     /// let result = ident_parser.parse(stream)?;
//     /// ```
//     ///
//     /// ## Custom String Type
//     ///
//     /// ```rust,ignore
//     /// // Use owned String for keywords
//     /// let parser = Keyword::<String, MyLang>::parser(|| MyKind::Keywordifier);
//     ///
//     /// // Use interned strings
//     /// let parser = Keyword::<Symbol, MyLang>::parser(|| MyKind::Keywordifier);
//     /// ```
//     ///
//     /// # See Also
//     ///
//     /// - [`KeywordToken`]: Trait for tokens that can be keywords
//     /// - [`UnexpectedToken`]: Error emitted when wrong token type is found
//     /// - [`ErrorNode`]: For creating placeholder keywords during recovery
//     #[cfg_attr(not(tarpaulin), inline(always))]
//     pub fn parser<'a, I, T, E>(
//       keyword_kind: impl Fn() -> Lang::SyntaxKind + Clone + 'a,
//     ) -> impl Parser<'a, I, Self, E> + Clone + 'a
//     where
//       I: LogoStream<'a, T>,
//       T: KeywordToken<'a>,
//       S: From<<<T::Logos as Logos<'a>>::Source as Source>::Slice<'a>> + 'a,
//       Lang: Language,
//       Lang::SyntaxKind: 'a,
//       E::Error: From<<T::Logos as Logos<'a>>::Error>
//         + From<<T::Logos as Logos<'a>>::Error>
//         + From<UnexpectedToken<'a, T, Lang::SyntaxKind>>,
//       E: ParserExtra<'a, I> + 'a,
//     {
//       any().try_map_with(move |tok: Lexed<'_, T>, exa| match tok {
//         Lexed::Token(SimpleSpanned { span, data: tok }) => match tok.is_keyword() {
//           true => Ok(Self::new(span, S::from(exa.slice()))),
//           false => Err(UnexpectedToken::expected_one_with_found(span, tok, keyword_kind()).into()),
//         },
//         Lexed::Error(e) => Err(E::Error::from(e)),
//       })
//     }
//   }
// };