mortar_compiler 0.5.3

Mortar language compiler core library
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
//! # token.rs
//!
//! # token.rs 文件
//!
//! ## Module Overview
//!
//! ## 模块概述
//!
//! Defines the `Token` enum and lexical analysis logic for the Mortar language.
//!
//! 定义 Mortar 语言的 `Token` 枚举和词法分析逻辑。
//!
//! Uses the `logos` crate to generate a high-performance lexer.
//!
//! 使用 `logos` crate 生成高性能的词法分析器。
//!
//! ## Source File Overview
//!
//! ## 源文件概述
//!
//! Contains the `Token` enum definition, token display formatting, and the `tokenize` function used by the parser and LSP.
//!
//! 包含 `Token` 枚举定义、token 显示格式化以及解析器和 LSP 使用的 `tokenize` 函数。

use logos::Logos;
use owo_colors::OwoColorize;
use std::fmt;

#[derive(Logos, Debug, PartialEq, Clone)]
// Ignore whitespace
#[logos(skip r"[ \t\r\n]+")]
pub enum Token<'a> {
    #[allow(dead_code)]
    Error,

    // region Comments
    #[regex(r"//[^\n]*", |lex| lex.slice())]
    SingleLineComment(&'a str),

    #[regex(r"/\*([^*]|\*[^/])*\*/", |lex| lex.slice())]
    MultiLineComment(&'a str),
    // endregion

    // region Keywords
    #[token("node")]
    #[token("nd")]
    Node,
    #[token("text")]
    Text,
    #[token("line")]
    Line,
    #[token("events")]
    Events,
    #[token("choice")]
    Choice,
    #[token("fn")]
    #[token("function")]
    Fn,
    #[token("return")]
    Return,
    #[token("break")]
    Break,
    #[token("when")]
    When,

    // Variable and constant keywords
    #[token("let")]
    Let,
    #[token("const")]
    Const,
    #[token("pub")]
    #[token("public")]
    Pub,
    #[token("enum")]
    Enum,

    // Branch interpolation keyword
    #[token("branch")]
    Branch,

    // Control flow keywords
    #[token("if")]
    If,
    #[token("else")]
    Else,

    // Performance system keywords
    #[token("event")]
    Event,
    #[token("run")]
    Run,
    #[token("with")]
    With,
    #[token("now")]
    Now,
    #[token("timeline")]
    #[token("tl")]
    Timeline,
    #[token("wait")]
    Wait,
    #[token("index")]
    Index,
    #[token("action")]
    Action,
    #[token("duration")]
    Duration,

    // Type keywords
    #[token("String")]
    StringType,
    #[token("Number")]
    NumberType,
    #[token("Boolean")]
    #[token("Bool")]
    BooleanType,

    // Boolean literals
    #[token("true")]
    True,
    #[token("false")]
    False,
    // endregion

    // region Operators & Punctuation
    #[token("->")]
    Arrow,
    #[token(":")]
    Colon,
    #[token(",")]
    Comma,
    #[token(";")]
    Semicolon,
    #[token(".")]
    Dot,
    #[token("{")]
    LeftBrace,
    #[token("}")]
    RightBrace,
    #[token("[")]
    LeftBracket,
    #[token("]")]
    RightBracket,
    #[token("(")]
    LeftParen,
    #[token(")")]
    RightParen,
    #[token("=")]
    Equals,
    #[token("<")]
    Less,
    #[token(">")]
    Greater,
    #[token("<=")]
    LessEqual,
    #[token(">=")]
    GreaterEqual,
    #[token("==")]
    EqualEqual,
    #[token("!=")]
    NotEqual,
    #[token("&&")]
    And,
    #[token("||")]
    Or,
    #[token("!")]
    Not,
    // endregion

    // region Literals
    // Triple-quoted multiline string: """..."""
    #[token("\"\"\"", lex_triple_quoted_string)]
    TripleQuotedString(&'a str),

    #[regex(r#""([^"\\]|\\.)*""#, |lex| {
        let s = lex.slice();
        &s[1..s.len()-1]
    })]
    #[regex(r#"'([^'\\]|\\.)*'"#, |lex| {
        let s = lex.slice();
        &s[1..s.len()-1]
    })]
    String(&'a str),

    // Interpolated string: $"text {expression} more text"
    // Using callback to properly handle nested quotes
    #[token("$\"", lex_interpolated_string)]
    InterpolatedString(&'a str),

    #[regex(r"[0-9]+(\.[0-9]+)?")]
    Number(&'a str),

    #[regex(r"[A-Za-z_][A-Za-z0-9_]*")]
    Identifier(&'a str),
    // endregion
}

/// Lexical analysis result containing token information and position
#[derive(Debug, Clone)]
pub struct TokenInfo<'a> {
    pub token: Token<'a>,
    pub start: usize,
    pub end: usize,
    pub text: &'a str,
}

/// Public lexical analysis interface for LSP and other external components
pub fn tokenize(input: &str) -> Vec<TokenInfo<'_>> {
    use logos::Logos;

    let mut lexer = Token::lexer(input);
    let mut tokens = Vec::new();

    while let Some(token_result) = lexer.next() {
        match token_result {
            Ok(token) => {
                let span = lexer.span();
                tokens.push(TokenInfo {
                    token,
                    start: span.start,
                    end: span.end,
                    text: &input[span.start..span.end],
                });
            }
            Err(_) => {
                let span = lexer.span();
                tokens.push(TokenInfo {
                    token: Token::Error,
                    start: span.start,
                    end: span.end,
                    text: &input[span.start..span.end],
                });
            }
        }
    }

    tokens
}

impl fmt::Display for Token<'_> {
    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
        use Token::*;
        match self {
            Error => write!(f, "Error"),

            SingleLineComment(s) => write!(f, "{}", s),
            MultiLineComment(s) => write!(f, "{}", s),

            Node => write!(f, "node"),
            Text => write!(f, "text"),
            Line => write!(f, "line"),
            Events => write!(f, "events"),
            Choice => write!(f, "choice"),
            Fn => write!(f, "fn"),
            Return => write!(f, "return"),
            Break => write!(f, "break"),
            When => write!(f, "when"),
            Let => write!(f, "let"),
            Const => write!(f, "const"),
            Pub => write!(f, "pub"),
            Enum => write!(f, "enum"),
            Branch => write!(f, "branch"),
            If => write!(f, "if"),
            Else => write!(f, "else"),
            Event => write!(f, "event"),
            Run => write!(f, "run"),
            With => write!(f, "with"),
            Now => write!(f, "now"),
            Timeline => write!(f, "timeline"),
            Wait => write!(f, "wait"),
            Index => write!(f, "index"),
            Action => write!(f, "action"),
            Duration => write!(f, "duration"),

            StringType => write!(f, "String"),
            NumberType => write!(f, "Number"),
            BooleanType => write!(f, "Boolean"),
            True => write!(f, "true"),
            False => write!(f, "false"),

            Arrow => write!(f, "->"),
            Colon => write!(f, ":"),
            Comma => write!(f, ","),
            Semicolon => write!(f, ";"),
            Dot => write!(f, "."),
            LeftBrace => write!(f, "{{"),
            RightBrace => write!(f, "}}"),
            LeftBracket => write!(f, "["),
            RightBracket => write!(f, "]"),
            LeftParen => write!(f, "("),
            RightParen => write!(f, ")"),
            Equals => write!(f, "="),
            Less => write!(f, "<"),
            Greater => write!(f, ">"),
            LessEqual => write!(f, "<="),
            GreaterEqual => write!(f, ">="),
            EqualEqual => write!(f, "=="),
            NotEqual => write!(f, "!="),
            And => write!(f, "&&"),
            Or => write!(f, "||"),
            Not => write!(f, "!"),

            TripleQuotedString(s) => write!(f, "\"\"\"{}\"\"\"", s),
            String(s) => write!(f, "\"{}\"", s),
            InterpolatedString(s) => write!(f, "$\"{}\"", s),
            Number(s) => write!(f, "{}", s),
            Identifier(s) => write!(f, "{}", s),
        }
    }
}

fn lex_interpolated_string<'a>(lex: &mut logos::Lexer<'a, Token<'a>>) -> Option<&'a str> {
    let start = lex.span().end;
    let source = lex.source();
    let bytes = source.as_bytes();

    let mut pos = start;
    let mut depth = 0;
    let mut in_string_literal = false;
    let mut escape_next = false;

    while pos < bytes.len() {
        let ch = bytes[pos] as char;
        pos += 1;

        if escape_next {
            escape_next = false;
            continue;
        }

        if ch == '\\' {
            escape_next = true;
            continue;
        }

        if ch == '"' && depth == 0 && !in_string_literal {
            // Found the closing quote
            lex.bump(pos - start);
            let content_start = start;
            let content_end = pos - 1;
            return Some(&source[content_start..content_end]);
        }

        if ch == '"' {
            in_string_literal = !in_string_literal;
            continue;
        }

        if !in_string_literal {
            if ch == '{' {
                depth += 1;
            } else if ch == '}' && depth > 0 {
                depth -= 1;
            }
        }
    }

    None
}

/// Lexes a triple-quoted string: """..."""
/// Returns the content between the opening and closing triple quotes.
fn lex_triple_quoted_string<'a>(lex: &mut logos::Lexer<'a, Token<'a>>) -> Option<&'a str> {
    let start = lex.span().end; // Position after opening """
    let source = lex.source();
    let bytes = source.as_bytes();

    let mut pos = start;

    // Look for closing """
    while pos + 2 < bytes.len() {
        if bytes[pos] == b'"' && bytes[pos + 1] == b'"' && bytes[pos + 2] == b'"' {
            // Found closing """
            lex.bump(pos - start + 3); // Include the closing """
            return Some(&source[start..pos]);
        }
        pos += 1;
    }

    // Check edge case: """ at the very end
    if pos + 2 == bytes.len()
        && bytes[pos] == b'"'
        && bytes[pos + 1] == b'"'
        && bytes.get(pos + 2) == Some(&b'"')
    {
        lex.bump(pos - start + 3);
        return Some(&source[start..pos]);
    }

    // No closing """ found
    None
}

pub(crate) fn lex_with_output(input: &str) -> Vec<Token<'_>> {
    let lex = Token::lexer(input);
    let mut tokens = Vec::new();

    println!();
    println!("{}", "(Mortar) Lexer output:".green());

    for result in lex {
        match result {
            Ok(token) => {
                print!("{:?} ", token);
                tokens.push(token);
            }
            Err(_) => {
                println!("{}", "Lexer error encountered!".red());
                break;
            }
        }
    }

    println!("\n");
    tokens
}

#[allow(dead_code)]
pub(crate) fn lex_silent(input: &str) -> Vec<Token<'_>> {
    let lex = Token::lexer(input);
    let mut tokens = Vec::new();

    for result in lex {
        match result {
            Ok(token) => {
                tokens.push(token);
            }
            Err(_) => {
                break;
            }
        }
    }

    tokens
}