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
use std::iter::once;
use std::ops::Range;
use rustc_errors::{pluralize, Applicability, Handler};
use rustc_lexer::unescape::{EscapeError, Mode};
use rustc_span::{BytePos, Span};
pub(crate) fn emit_unescape_error(
handler: &Handler,
lit: &str,
span_with_quotes: Span,
span: Span,
mode: Mode,
range: Range<usize>,
error: EscapeError,
) {
debug!(
"emit_unescape_error: {:?}, {:?}, {:?}, {:?}, {:?}",
lit, span_with_quotes, mode, range, error
);
let last_char = || {
let c = lit[range.clone()].chars().rev().next().unwrap();
let span = span.with_lo(span.hi() - BytePos(c.len_utf8() as u32));
(c, span)
};
match error {
EscapeError::LoneSurrogateUnicodeEscape => {
handler
.struct_span_err(span, "invalid unicode character escape")
.span_label(span, "invalid escape")
.help("unicode escape must not be a surrogate")
.emit();
}
EscapeError::OutOfRangeUnicodeEscape => {
handler
.struct_span_err(span, "invalid unicode character escape")
.span_label(span, "invalid escape")
.help("unicode escape must be at most 10FFFF")
.emit();
}
EscapeError::MoreThanOneChar => {
use unicode_normalization::{char::is_combining_mark, UnicodeNormalization};
let mut has_help = false;
let mut handler = handler.struct_span_err(
span_with_quotes,
"character literal may only contain one codepoint",
);
if lit.chars().skip(1).all(|c| is_combining_mark(c)) {
let escaped_marks =
lit.chars().skip(1).map(|c| c.escape_default().to_string()).collect::<Vec<_>>();
handler.span_note(
span,
&format!(
"this `{}` is followed by the combining mark{} `{}`",
lit.chars().next().unwrap(),
pluralize!(escaped_marks.len()),
escaped_marks.join(""),
),
);
let normalized = lit.nfc().to_string();
if normalized.chars().count() == 1 {
has_help = true;
handler.span_suggestion(
span,
&format!(
"consider using the normalized form `{}` of this character",
normalized.chars().next().unwrap().escape_default()
),
normalized,
Applicability::MachineApplicable,
);
}
} else {
let printable: Vec<char> = lit
.chars()
.filter(|&x| {
unicode_width::UnicodeWidthChar::width(x).unwrap_or(0) != 0
&& !x.is_whitespace()
})
.collect();
if let [ch] = printable.as_slice() {
has_help = true;
handler.span_note(
span,
&format!(
"there are non-printing characters, the full sequence is `{}`",
lit.escape_default(),
),
);
handler.span_suggestion(
span,
"consider removing the non-printing characters",
ch,
Applicability::MaybeIncorrect,
);
}
}
if !has_help {
let (prefix, msg) = if mode.is_bytes() {
("b", "if you meant to write a byte string literal, use double quotes")
} else {
("", "if you meant to write a `str` literal, use double quotes")
};
handler.span_suggestion(
span_with_quotes,
msg,
format!("{}\"{}\"", prefix, lit),
Applicability::MachineApplicable,
);
}
handler.emit();
}
EscapeError::EscapeOnlyChar => {
let (c, char_span) = last_char();
let msg = if mode.is_bytes() {
"byte constant must be escaped"
} else {
"character constant must be escaped"
};
handler
.struct_span_err(span, &format!("{}: `{}`", msg, escaped_char(c)))
.span_suggestion(
char_span,
"escape the character",
c.escape_default(),
Applicability::MachineApplicable,
)
.emit();
}
EscapeError::BareCarriageReturn => {
let msg = if mode.in_double_quotes() {
"bare CR not allowed in string, use `\\r` instead"
} else {
"character constant must be escaped: `\\r`"
};
handler
.struct_span_err(span, msg)
.span_suggestion(
span,
"escape the character",
"\\r",
Applicability::MachineApplicable,
)
.emit();
}
EscapeError::BareCarriageReturnInRawString => {
assert!(mode.in_double_quotes());
let msg = "bare CR not allowed in raw string";
handler.span_err(span, msg);
}
EscapeError::InvalidEscape => {
let (c, span) = last_char();
let label =
if mode.is_bytes() { "unknown byte escape" } else { "unknown character escape" };
let ec = escaped_char(c);
let mut diag = handler.struct_span_err(span, &format!("{}: `{}`", label, ec));
diag.span_label(span, label);
if c == '{' || c == '}' && !mode.is_bytes() {
diag.help(
"if used in a formatting string, curly braces are escaped with `{{` and `}}`",
);
} else if c == '\r' {
diag.help(
"this is an isolated carriage return; consider checking your editor and \
version control settings",
);
} else {
if !mode.is_bytes() {
diag.span_suggestion(
span_with_quotes,
"if you meant to write a literal backslash (perhaps escaping in a regular expression), consider a raw string literal",
format!("r\"{}\"", lit),
Applicability::MaybeIncorrect,
);
}
diag.help(
"for more information, visit \
<https://static.rust-lang.org/doc/master/reference.html#literals>",
);
}
diag.emit();
}
EscapeError::TooShortHexEscape => {
handler.span_err(span, "numeric character escape is too short");
}
EscapeError::InvalidCharInHexEscape | EscapeError::InvalidCharInUnicodeEscape => {
let (c, span) = last_char();
let msg = if error == EscapeError::InvalidCharInHexEscape {
"invalid character in numeric character escape"
} else {
"invalid character in unicode escape"
};
let c = escaped_char(c);
handler
.struct_span_err(span, &format!("{}: `{}`", msg, c))
.span_label(span, msg)
.emit();
}
EscapeError::NonAsciiCharInByte => {
assert!(mode.is_bytes());
let (c, span) = last_char();
let mut err = handler.struct_span_err(span, "non-ASCII character in byte constant");
let postfix = if unicode_width::UnicodeWidthChar::width(c).unwrap_or(1) == 0 {
format!(" but is {:?}", c)
} else {
String::new()
};
err.span_label(span, &format!("byte constant must be ASCII{}", postfix));
if (c as u32) <= 0xFF {
err.span_suggestion(
span,
&format!(
"if you meant to use the unicode code point for {:?}, use a \\xHH escape",
c
),
format!("\\x{:X}", c as u32),
Applicability::MaybeIncorrect,
);
} else if matches!(mode, Mode::Byte) {
err.span_label(span, "this multibyte character does not fit into a single byte");
} else if matches!(mode, Mode::ByteStr) {
let mut utf8 = String::new();
utf8.push(c);
err.span_suggestion(
span,
&format!(
"if you meant to use the UTF-8 encoding of {:?}, use \\xHH escapes",
c
),
utf8.as_bytes()
.iter()
.map(|b: &u8| format!("\\x{:X}", *b))
.fold("".to_string(), |a, c| a + &c),
Applicability::MaybeIncorrect,
);
}
err.emit();
}
EscapeError::NonAsciiCharInByteString => {
assert!(mode.is_bytes());
let (c, span) = last_char();
let postfix = if unicode_width::UnicodeWidthChar::width(c).unwrap_or(1) == 0 {
format!(" but is {:?}", c)
} else {
String::new()
};
handler
.struct_span_err(span, "raw byte string must be ASCII")
.span_label(span, &format!("must be ASCII{}", postfix))
.emit();
}
EscapeError::OutOfRangeHexEscape => {
handler
.struct_span_err(span, "out of range hex escape")
.span_label(span, "must be a character in the range [\\x00-\\x7f]")
.emit();
}
EscapeError::LeadingUnderscoreUnicodeEscape => {
let (c, span) = last_char();
let msg = "invalid start of unicode escape";
handler
.struct_span_err(span, &format!("{}: `{}`", msg, c))
.span_label(span, msg)
.emit();
}
EscapeError::OverlongUnicodeEscape => {
handler
.struct_span_err(span, "overlong unicode escape")
.span_label(span, "must have at most 6 hex digits")
.emit();
}
EscapeError::UnclosedUnicodeEscape => {
handler
.struct_span_err(span, "unterminated unicode escape")
.span_label(span, "missing a closing `}`")
.span_suggestion_verbose(
span.shrink_to_hi(),
"terminate the unicode escape",
"}",
Applicability::MaybeIncorrect,
)
.emit();
}
EscapeError::NoBraceInUnicodeEscape => {
let msg = "incorrect unicode escape sequence";
let mut diag = handler.struct_span_err(span, msg);
let mut suggestion = "\\u{".to_owned();
let mut suggestion_len = 0;
let (c, char_span) = last_char();
let chars = once(c).chain(lit[range.end..].chars());
for c in chars.take(6).take_while(|c| c.is_digit(16)) {
suggestion.push(c);
suggestion_len += c.len_utf8();
}
if suggestion_len > 0 {
suggestion.push('}');
let hi = char_span.lo() + BytePos(suggestion_len as u32);
diag.span_suggestion(
span.with_hi(hi),
"format of unicode escape sequences uses braces",
suggestion,
Applicability::MaybeIncorrect,
);
} else {
diag.span_label(span, msg);
diag.help("format of unicode escape sequences is `\\u{...}`");
}
diag.emit();
}
EscapeError::UnicodeEscapeInByte => {
let msg = "unicode escape in byte string";
handler
.struct_span_err(span, msg)
.span_label(span, msg)
.help("unicode escape sequences cannot be used as a byte or in a byte string")
.emit();
}
EscapeError::EmptyUnicodeEscape => {
handler
.struct_span_err(span, "empty unicode escape")
.span_label(span, "this escape must have at least 1 hex digit")
.emit();
}
EscapeError::ZeroChars => {
let msg = "empty character literal";
handler.struct_span_err(span, msg).span_label(span, msg).emit();
}
EscapeError::LoneSlash => {
let msg = "invalid trailing slash in literal";
handler.struct_span_err(span, msg).span_label(span, msg).emit();
}
EscapeError::UnskippedWhitespaceWarning => {
let (c, char_span) = last_char();
let msg =
format!("non-ASCII whitespace symbol '{}' is not skipped", c.escape_unicode());
handler.struct_span_warn(span, &msg).span_label(char_span, &msg).emit();
}
EscapeError::MultipleSkippedLinesWarning => {
let msg = "multiple lines skipped by escaped newline";
let bottom_msg = "skipping everything up to and including this point";
handler.struct_span_warn(span, msg).span_label(span, bottom_msg).emit();
}
}
}
pub(crate) fn escaped_char(c: char) -> String {
match c {
'\u{20}'..='\u{7e}' => {
c.to_string()
}
_ => c.escape_default().to_string(),
}
}