aboutsummaryrefslogtreecommitdiff
path: root/crates/ra_syntax/src/string_lexing.rs
blob: d613bb0429a9ce11cfa3da3db99c19c92440e3ae (plain)
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
use self::CharComponentKind::*;
use rowan::{TextRange, TextUnit};

pub fn parse_string_literal(src: &str) -> StringComponentIterator {
    StringComponentIterator {
        parser: Parser::new(src),
        has_closing_quote: false,
    }
}

#[derive(Debug, Eq, PartialEq, Clone)]
pub struct StringComponent {
    pub range: TextRange,
    pub kind: StringComponentKind,
}

impl StringComponent {
    fn new(range: TextRange, kind: StringComponentKind) -> StringComponent {
        StringComponent { range, kind }
    }
}

#[derive(Debug, Eq, PartialEq, Clone)]
pub enum StringComponentKind {
    IgnoreNewline,
    Char(CharComponentKind),
}

pub struct StringComponentIterator<'a> {
    parser: Parser<'a>,
    pub has_closing_quote: bool,
}

impl<'a> Iterator for StringComponentIterator<'a> {
    type Item = StringComponent;
    fn next(&mut self) -> Option<StringComponent> {
        if self.parser.pos == 0 {
            assert!(
                self.parser.advance() == '"',
                "string literal should start with double quotes"
            );
        }

        if let Some(component) = self.parser.parse_string_component() {
            return Some(component);
        }

        // We get here when there are no char components left to parse
        if self.parser.peek() == Some('"') {
            self.parser.advance();
            self.has_closing_quote = true;
        }

        assert!(
            self.parser.peek() == None,
            "string literal should leave no unparsed input: src = {}, pos = {}, length = {}",
            self.parser.src,
            self.parser.pos,
            self.parser.src.len()
        );

        None
    }
}

pub fn parse_char_literal(src: &str) -> CharComponentIterator {
    CharComponentIterator {
        parser: Parser::new(src),
        has_closing_quote: false,
    }
}

#[derive(Debug, Eq, PartialEq, Clone)]
pub struct CharComponent {
    pub range: TextRange,
    pub kind: CharComponentKind,
}

impl CharComponent {
    fn new(range: TextRange, kind: CharComponentKind) -> CharComponent {
        CharComponent { range, kind }
    }
}

#[derive(Debug, Eq, PartialEq, Clone)]
pub enum CharComponentKind {
    CodePoint,
    AsciiEscape,
    AsciiCodeEscape,
    UnicodeEscape,
}

pub struct CharComponentIterator<'a> {
    parser: Parser<'a>,
    pub has_closing_quote: bool,
}

impl<'a> Iterator for CharComponentIterator<'a> {
    type Item = CharComponent;
    fn next(&mut self) -> Option<CharComponent> {
        if self.parser.pos == 0 {
            assert!(
                self.parser.advance() == '\'',
                "char literal should start with a quote"
            );
        }

        if let Some(component) = self.parser.parse_char_component() {
            return Some(component);
        }

        // We get here when there are no char components left to parse
        if self.parser.peek() == Some('\'') {
            self.parser.advance();
            self.has_closing_quote = true;
        }

        assert!(
            self.parser.peek() == None,
            "char literal should leave no unparsed input: src = {}, pos = {}, length = {}",
            self.parser.src,
            self.parser.pos,
            self.parser.src.len()
        );

        None
    }
}

pub struct Parser<'a> {
    src: &'a str,
    pos: usize,
}

impl<'a> Parser<'a> {
    pub fn new(src: &'a str) -> Parser<'a> {
        Parser { src, pos: 0 }
    }

    // Utility methods

    pub fn peek(&self) -> Option<char> {
        if self.pos == self.src.len() {
            return None;
        }

        self.src[self.pos..].chars().next()
    }

    pub fn advance(&mut self) -> char {
        let next = self
            .peek()
            .expect("cannot advance if end of input is reached");
        self.pos += next.len_utf8();
        next
    }

    pub fn skip_whitespace(&mut self) {
        while self.peek().map(|c| c.is_whitespace()) == Some(true) {
            self.advance();
        }
    }

    pub fn get_pos(&self) -> TextUnit {
        (self.pos as u32).into()
    }

    // Char parsing methods

    fn parse_unicode_escape(&mut self, start: TextUnit) -> CharComponent {
        match self.peek() {
            Some('{') => {
                self.advance();

                // Parse anything until we reach `}`
                while let Some(next) = self.peek() {
                    self.advance();
                    if next == '}' {
                        break;
                    }
                }

                let end = self.get_pos();
                CharComponent::new(TextRange::from_to(start, end), UnicodeEscape)
            }
            Some(_) | None => {
                let end = self.get_pos();
                CharComponent::new(TextRange::from_to(start, end), UnicodeEscape)
            }
        }
    }

    fn parse_ascii_code_escape(&mut self, start: TextUnit) -> CharComponent {
        let code_start = self.get_pos();
        while let Some(next) = self.peek() {
            if next == '\'' || (self.get_pos() - code_start == 2.into()) {
                break;
            }

            self.advance();
        }

        let end = self.get_pos();
        CharComponent::new(TextRange::from_to(start, end), AsciiCodeEscape)
    }

    fn parse_escape(&mut self, start: TextUnit) -> CharComponent {
        if self.peek().is_none() {
            return CharComponent::new(TextRange::from_to(start, start), AsciiEscape);
        }

        let next = self.advance();
        let end = self.get_pos();
        let range = TextRange::from_to(start, end);
        match next {
            'x' => self.parse_ascii_code_escape(start),
            'u' => self.parse_unicode_escape(start),
            _ => CharComponent::new(range, AsciiEscape),
        }
    }

    pub fn parse_char_component(&mut self) -> Option<CharComponent> {
        let next = self.peek()?;

        // Ignore character close
        if next == '\'' {
            return None;
        }

        let start = self.get_pos();
        self.advance();

        if next == '\\' {
            Some(self.parse_escape(start))
        } else {
            let end = self.get_pos();
            Some(CharComponent::new(
                TextRange::from_to(start, end),
                CodePoint,
            ))
        }
    }

    pub fn parse_ignore_newline(&mut self, start: TextUnit) -> Option<StringComponent> {
        // In string literals, when a `\` occurs immediately before the newline, the `\`,
        // the newline, and all whitespace at the beginning of the next line are ignored
        match self.peek() {
            Some('\n') | Some('\r') => {
                self.skip_whitespace();
                Some(StringComponent::new(
                    TextRange::from_to(start, self.get_pos()),
                    StringComponentKind::IgnoreNewline,
                ))
            }
            _ => None,
        }
    }

    pub fn parse_string_component(&mut self) -> Option<StringComponent> {
        let next = self.peek()?;

        // Ignore string close
        if next == '"' {
            return None;
        }

        let start = self.get_pos();
        self.advance();

        if next == '\\' {
            // Strings can use `\` to ignore newlines, so we first try to parse one of those
            // before falling back to parsing char escapes
            self.parse_ignore_newline(start).or_else(|| {
                let char_component = self.parse_escape(start);
                Some(StringComponent::new(
                    char_component.range,
                    StringComponentKind::Char(char_component.kind),
                ))
            })
        } else {
            let end = self.get_pos();
            Some(StringComponent::new(
                TextRange::from_to(start, end),
                StringComponentKind::Char(CodePoint),
            ))
        }
    }
}

#[cfg(test)]
mod tests {
    use super::*;

    fn parse(src: &str) -> (bool, Vec<CharComponent>) {
        let component_iterator = &mut super::parse_char_literal(src);
        let components: Vec<_> = component_iterator.collect();
        (component_iterator.has_closing_quote, components)
    }

    fn unclosed_char_component(src: &str) -> CharComponent {
        let (has_closing_quote, components) = parse(src);
        assert!(!has_closing_quote, "char should not have closing quote");
        assert!(components.len() == 1);
        components[0].clone()
    }

    fn closed_char_component(src: &str) -> CharComponent {
        let (has_closing_quote, components) = parse(src);
        assert!(has_closing_quote, "char should have closing quote");
        assert!(
            components.len() == 1,
            "Literal: {}\nComponents: {:#?}",
            src,
            components
        );
        components[0].clone()
    }

    fn closed_char_components(src: &str) -> Vec<CharComponent> {
        let (has_closing_quote, components) = parse(src);
        assert!(has_closing_quote, "char should have closing quote");
        components
    }

    fn range_closed(src: &str) -> TextRange {
        TextRange::from_to(1.into(), (src.len() as u32 - 1).into())
    }

    fn range_unclosed(src: &str) -> TextRange {
        TextRange::from_to(1.into(), (src.len() as u32).into())
    }

    #[test]
    fn test_unicode_escapes() {
        let unicode_escapes = &[r"{DEAD}", "{BEEF}", "{FF}", "{}", ""];
        for escape in unicode_escapes {
            let escape_sequence = format!(r"'\u{}'", escape);
            let component = closed_char_component(&escape_sequence);
            let expected_range = range_closed(&escape_sequence);
            assert_eq!(component.kind, CharComponentKind::UnicodeEscape);
            assert_eq!(component.range, expected_range);
        }
    }

    #[test]
    fn test_unicode_escapes_unclosed() {
        let unicode_escapes = &["{DEAD", "{BEEF", "{FF"];
        for escape in unicode_escapes {
            let escape_sequence = format!(r"'\u{}'", escape);
            let component = unclosed_char_component(&escape_sequence);
            let expected_range = range_unclosed(&escape_sequence);
            assert_eq!(component.kind, CharComponentKind::UnicodeEscape);
            assert_eq!(component.range, expected_range);
        }
    }

    #[test]
    fn test_empty_char() {
        let (has_closing_quote, components) = parse("''");
        assert!(has_closing_quote, "char should have closing quote");
        assert!(components.len() == 0);
    }

    #[test]
    fn test_unclosed_char() {
        let component = unclosed_char_component("'a");
        assert!(component.kind == CodePoint);
        assert!(component.range == TextRange::from_to(1.into(), 2.into()));
    }

    #[test]
    fn test_digit_escapes() {
        let literals = &[r"", r"5", r"55"];

        for literal in literals {
            let lit_text = format!(r"'\x{}'", literal);
            let component = closed_char_component(&lit_text);
            assert!(component.kind == CharComponentKind::AsciiCodeEscape);
            assert!(component.range == range_closed(&lit_text));
        }

        // More than 2 digits starts a new codepoint
        let components = closed_char_components(r"'\x555'");
        assert!(components.len() == 2);
        assert!(components[1].kind == CharComponentKind::CodePoint);
    }

    #[test]
    fn test_ascii_escapes() {
        let literals = &[
            r"\'", "\\\"", // equivalent to \"
            r"\n", r"\r", r"\t", r"\\", r"\0",
        ];

        for literal in literals {
            let lit_text = format!("'{}'", literal);
            let component = closed_char_component(&lit_text);
            assert!(component.kind == CharComponentKind::AsciiEscape);
            assert!(component.range == range_closed(&lit_text));
        }
    }

    #[test]
    fn test_no_escapes() {
        let literals = &['"', 'n', 'r', 't', '0', 'x', 'u'];

        for &literal in literals {
            let lit_text = format!("'{}'", literal);
            let component = closed_char_component(&lit_text);
            assert!(component.kind == CharComponentKind::CodePoint);
            assert!(component.range == range_closed(&lit_text));
        }
    }
}