-
Notifications
You must be signed in to change notification settings - Fork 1.6k
/
lex.rs
365 lines (332 loc) · 12.3 KB
/
lex.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
use crate::ParseError;
use nu_protocol::Span;
#[derive(Debug, PartialEq, Eq)]
pub enum TokenContents {
Item,
Comment,
Pipe,
Semicolon,
Eol,
}
#[derive(Debug, PartialEq, Eq)]
pub struct Token {
pub contents: TokenContents,
pub span: Span,
}
impl Token {
pub fn new(contents: TokenContents, span: Span) -> Token {
Token { contents, span }
}
}
#[derive(Clone, Copy, Debug)]
pub enum BlockKind {
Paren,
CurlyBracket,
SquareBracket,
}
impl BlockKind {
fn closing(self) -> u8 {
match self {
BlockKind::Paren => b')',
BlockKind::SquareBracket => b']',
BlockKind::CurlyBracket => b'}',
}
}
}
// A baseline token is terminated if it's not nested inside of a paired
// delimiter and the next character is one of: `|`, `;`, `#` or any
// whitespace.
fn is_item_terminator(
block_level: &[BlockKind],
c: u8,
additional_whitespace: &[u8],
special_tokens: &[u8],
) -> bool {
block_level.is_empty()
&& (c == b' '
|| c == b'\t'
|| c == b'\n'
|| c == b'\r'
|| c == b'|'
|| c == b';'
|| c == b'#'
|| additional_whitespace.contains(&c)
|| special_tokens.contains(&c))
}
// A special token is one that is a byte that stands alone as its own token. For example
// when parsing a signature you may want to have `:` be able to separate tokens and also
// to be handled as its own token to notify you you're about to parse a type in the example
// `foo:bar`
fn is_special_item(block_level: &[BlockKind], c: u8, special_tokens: &[u8]) -> bool {
block_level.is_empty() && special_tokens.contains(&c)
}
pub fn lex_item(
input: &[u8],
curr_offset: &mut usize,
span_offset: usize,
additional_whitespace: &[u8],
special_tokens: &[u8],
) -> (Span, Option<ParseError>) {
// This variable tracks the starting character of a string literal, so that
// we remain inside the string literal lexer mode until we encounter the
// closing quote.
let mut quote_start: Option<u8> = None;
let mut in_comment = false;
let token_start = *curr_offset;
// This Vec tracks paired delimiters
let mut block_level: Vec<BlockKind> = vec![];
// The process of slurping up a baseline token repeats:
//
// - String literal, which begins with `'` or `"`, and continues until
// the same character is encountered again.
// - Delimiter pair, which begins with `[`, `(`, or `{`, and continues until
// the matching closing delimiter is found, skipping comments and string
// literals.
// - When not nested inside of a delimiter pair, when a terminating
// character (whitespace, `|`, `;` or `#`) is encountered, the baseline
// token is done.
// - Otherwise, accumulate the character into the current baseline token.
while let Some(c) = input.get(*curr_offset) {
let c = *c;
if let Some(start) = quote_start {
// Check if we're in an escape sequence
if c == b'\\' && start == b'"' {
// Go ahead and consume the escape character if possible
if input.get(*curr_offset + 1).is_some() {
// Successfully escaped the character
*curr_offset += 2;
continue;
} else {
let span = Span::new(span_offset + token_start, span_offset + *curr_offset);
return (
span,
Some(ParseError::UnexpectedEof(
(start as char).to_string(),
Span {
start: span.end,
end: span.end,
},
)),
);
}
}
// If we encountered the closing quote character for the current
// string, we're done with the current string.
if c == start {
// Also need to check to make sure we aren't escaped
quote_start = None;
}
} else if c == b'#' {
if is_item_terminator(&block_level, c, additional_whitespace, special_tokens) {
break;
}
in_comment = true;
} else if c == b'\n' || c == b'\r' {
in_comment = false;
if is_item_terminator(&block_level, c, additional_whitespace, special_tokens) {
break;
}
} else if in_comment {
if is_item_terminator(&block_level, c, additional_whitespace, special_tokens) {
break;
}
} else if is_special_item(&block_level, c, special_tokens) && token_start == *curr_offset {
*curr_offset += 1;
break;
} else if c == b'\'' || c == b'"' {
// We encountered the opening quote of a string literal.
quote_start = Some(c);
} else if c == b'[' {
// We encountered an opening `[` delimiter.
block_level.push(BlockKind::SquareBracket);
} else if c == b']' {
// We encountered a closing `]` delimiter. Pop off the opening `[`
// delimiter.
if let Some(BlockKind::SquareBracket) = block_level.last() {
let _ = block_level.pop();
}
} else if c == b'{' {
// We encountered an opening `{` delimiter.
block_level.push(BlockKind::CurlyBracket);
} else if c == b'}' {
// We encountered a closing `}` delimiter. Pop off the opening `{`.
if let Some(BlockKind::CurlyBracket) = block_level.last() {
let _ = block_level.pop();
}
} else if c == b'(' {
// We encountered an opening `(` delimiter.
block_level.push(BlockKind::Paren);
} else if c == b')' {
// We encountered a closing `)` delimiter. Pop off the opening `(`.
if let Some(BlockKind::Paren) = block_level.last() {
let _ = block_level.pop();
}
} else if is_item_terminator(&block_level, c, additional_whitespace, special_tokens) {
break;
}
*curr_offset += 1;
}
let span = Span::new(span_offset + token_start, span_offset + *curr_offset);
// If there is still unclosed opening delimiters, remember they were missing
if let Some(block) = block_level.last() {
let delim = block.closing();
let cause = ParseError::UnexpectedEof(
(delim as char).to_string(),
Span {
start: span.end,
end: span.end,
},
);
return (span, Some(cause));
}
if let Some(delim) = quote_start {
// The non-lite parse trims quotes on both sides, so we add the expected quote so that
// anyone wanting to consume this partial parse (e.g., completions) will be able to get
// correct information from the non-lite parse.
return (
span,
Some(ParseError::UnexpectedEof(
(delim as char).to_string(),
Span {
start: span.end,
end: span.end,
},
)),
);
}
// If we didn't accumulate any characters, it's an unexpected error.
if *curr_offset - token_start == 0 {
return (
span,
Some(ParseError::UnexpectedEof("command".to_string(), span)),
);
}
(span, None)
}
pub fn lex(
input: &[u8],
span_offset: usize,
additional_whitespace: &[u8],
special_tokens: &[u8],
skip_comment: bool,
) -> (Vec<Token>, Option<ParseError>) {
let mut error = None;
let mut curr_offset = 0;
let mut output = vec![];
let mut is_complete = true;
while let Some(c) = input.get(curr_offset) {
let c = *c;
if c == b'|' {
// If the next character is `|`, it's either `|` or `||`.
let idx = curr_offset;
let prev_idx = idx;
curr_offset += 1;
// If the next character is `|`, we're looking at a `||`.
if let Some(c) = input.get(curr_offset) {
if *c == b'|' {
let idx = curr_offset;
curr_offset += 1;
output.push(Token::new(
TokenContents::Item,
Span::new(span_offset + prev_idx, span_offset + idx + 1),
));
continue;
}
}
// Otherwise, it's just a regular `|` token.
// Before we push, check to see if the previous character was a newline.
// If so, then this is a continuation of the previous line
if let Some(prev) = output.last_mut() {
match prev.contents {
TokenContents::Eol => {
*prev = Token::new(
TokenContents::Pipe,
Span::new(span_offset + idx, span_offset + idx + 1),
)
}
_ => {
output.push(Token::new(
TokenContents::Pipe,
Span::new(span_offset + idx, span_offset + idx + 1),
));
}
}
} else {
output.push(Token::new(
TokenContents::Pipe,
Span::new(span_offset + idx, span_offset + idx + 1),
));
}
is_complete = false;
} else if c == b';' {
// If the next character is a `;`, we're looking at a semicolon token.
if !is_complete && error.is_none() {
error = Some(ParseError::ExtraTokens(Span::new(
curr_offset,
curr_offset + 1,
)));
}
let idx = curr_offset;
curr_offset += 1;
output.push(Token::new(
TokenContents::Semicolon,
Span::new(span_offset + idx, span_offset + idx + 1),
));
} else if c == b'\r' {
// Ignore a stand-alone carriage return
curr_offset += 1;
} else if c == b'\n' {
// If the next character is a newline, we're looking at an EOL (end of line) token.
let idx = curr_offset;
curr_offset += 1;
if !additional_whitespace.contains(&c) {
output.push(Token::new(
TokenContents::Eol,
Span::new(span_offset + idx, span_offset + idx + 1),
));
}
} else if c == b'#' {
// If the next character is `#`, we're at the beginning of a line
// comment. The comment continues until the next newline.
let mut start = curr_offset;
while let Some(input) = input.get(curr_offset) {
if *input == b'\n' {
if !skip_comment {
output.push(Token::new(
TokenContents::Comment,
Span::new(span_offset + start, span_offset + curr_offset),
));
}
start = curr_offset;
break;
} else {
curr_offset += 1;
}
}
if start != curr_offset && !skip_comment {
output.push(Token::new(
TokenContents::Comment,
Span::new(span_offset + start, span_offset + curr_offset),
));
}
} else if c == b' ' || c == b'\t' || additional_whitespace.contains(&c) {
// If the next character is non-newline whitespace, skip it.
curr_offset += 1;
} else {
// Otherwise, try to consume an unclassified token.
let (span, err) = lex_item(
input,
&mut curr_offset,
span_offset,
additional_whitespace,
special_tokens,
);
if error.is_none() {
error = err;
}
is_complete = true;
output.push(Token::new(TokenContents::Item, span));
}
}
(output, error)
}