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
//! Tools to work with format string literals for the `format_args!` family of macros.
use syntax::{
AstNode, AstToken, TextRange, TextSize,
ast::{self, IsString},
};
// FIXME: This can probably be re-implemented via the HIR?
pub fn is_format_string(string: &ast::String) -> bool {
// Check if `string` is a format string argument of a macro invocation.
// `string` is a string literal, mapped down into the innermost macro expansion.
// Since `format_args!` etc. remove the format string when expanding, but place all arguments
// in the expanded output, we know that the string token is (part of) the format string if it
// appears in `format_args!` (otherwise it would have been mapped down further).
//
// This setup lets us correctly highlight the components of `concat!("{}", "bla")` format
// strings. It still fails for `concat!("{", "}")`, but that is rare.
(|| {
let lit = string.syntax().parent().and_then(ast::Literal::cast)?;
let fa = lit.syntax().parent().and_then(ast::FormatArgsExpr::cast)?;
(fa.template()? == ast::Expr::Literal(lit)).then_some(|| ())
})()
.is_some()
}
#[derive(Debug)]
pub enum FormatSpecifier {
Open,
Close,
Integer,
Identifier,
Colon,
Fill,
Align,
Sign,
NumberSign,
Zero,
DollarSign,
Dot,
Asterisk,
QuestionMark,
Escape,
}
// FIXME: Remove this, we can use rustc_format_parse instead
pub fn lex_format_specifiers(
string: &ast::String,
mut callback: &mut dyn FnMut(TextRange, FormatSpecifier),
) {
let mut char_ranges = Vec::new();
string.escaped_char_ranges(&mut |range, res| char_ranges.push((range, res)));
let mut chars = char_ranges
.iter()
.filter_map(|(range, res)| Some((*range, *res.as_ref().ok()?)))
.peekable();
while let Some((range, first_char)) = chars.next() {
if let '{' = first_char {
// Format specifier, see syntax at https://doc.rust-lang.org/std/fmt/index.html#syntax
if let Some((_, '{')) = chars.peek() {
// Escaped format specifier, `{{`
read_escaped_format_specifier(&mut chars, &mut callback);
continue;
}
callback(range, FormatSpecifier::Open);
// check for integer/identifier
let (_, int_char) = chars.peek().copied().unwrap_or_default();
match int_char {
// integer
'0'..='9' => read_integer(&mut chars, &mut callback),
// identifier
c if c == '_' || c.is_alphabetic() => read_identifier(&mut chars, &mut callback),
_ => {}
}
if let Some((_, ':')) = chars.peek() {
skip_char_and_emit(&mut chars, FormatSpecifier::Colon, &mut callback);
// check for fill/align
let mut cloned = chars.clone().take(2);
let (_, first) = cloned.next().unwrap_or_default();
let (_, second) = cloned.next().unwrap_or_default();
match second {
'<' | '^' | '>' => {
// alignment specifier, first char specifies fill
skip_char_and_emit(&mut chars, FormatSpecifier::Fill, &mut callback);
skip_char_and_emit(&mut chars, FormatSpecifier::Align, &mut callback);
}
_ => {
if let '<' | '^' | '>' = first {
skip_char_and_emit(&mut chars, FormatSpecifier::Align, &mut callback);
}
}
}
// check for sign
match chars.peek().copied().unwrap_or_default().1 {
'+' | '-' => {
skip_char_and_emit(&mut chars, FormatSpecifier::Sign, &mut callback);
}
_ => {}
}
// check for `#`
if let Some((_, '#')) = chars.peek() {
skip_char_and_emit(&mut chars, FormatSpecifier::NumberSign, &mut callback);
}
// check for `0`
let mut cloned = chars.clone().take(2);
let first = cloned.next().map(|next| next.1);
let second = cloned.next().map(|next| next.1);
if first == Some('0') && second != Some('$') {
skip_char_and_emit(&mut chars, FormatSpecifier::Zero, &mut callback);
}
// width
match chars.peek().copied().unwrap_or_default().1 {
'0'..='9' => {
read_integer(&mut chars, &mut callback);
if let Some((_, '$')) = chars.peek() {
skip_char_and_emit(
&mut chars,
FormatSpecifier::DollarSign,
&mut callback,
);
}
}
c if c == '_' || c.is_alphabetic() => {
read_identifier(&mut chars, &mut callback);
if chars.peek().map(|&(_, c)| c) == Some('?') {
skip_char_and_emit(
&mut chars,
FormatSpecifier::QuestionMark,
&mut callback,
);
}
// can be either width (indicated by dollar sign, or type in which case
// the next sign has to be `}`)
let next = chars.peek().map(|&(_, c)| c);
match next {
Some('$') => skip_char_and_emit(
&mut chars,
FormatSpecifier::DollarSign,
&mut callback,
),
Some('}') => {
skip_char_and_emit(
&mut chars,
FormatSpecifier::Close,
&mut callback,
);
continue;
}
_ => continue,
};
}
_ => {}
}
// precision
if let Some((_, '.')) = chars.peek() {
skip_char_and_emit(&mut chars, FormatSpecifier::Dot, &mut callback);
match chars.peek().copied().unwrap_or_default().1 {
'*' => {
skip_char_and_emit(
&mut chars,
FormatSpecifier::Asterisk,
&mut callback,
);
}
'0'..='9' => {
read_integer(&mut chars, &mut callback);
if let Some((_, '$')) = chars.peek() {
skip_char_and_emit(
&mut chars,
FormatSpecifier::DollarSign,
&mut callback,
);
}
}
c if c == '_' || c.is_alphabetic() => {
read_identifier(&mut chars, &mut callback);
if chars.peek().map(|&(_, c)| c) != Some('$') {
continue;
}
skip_char_and_emit(
&mut chars,
FormatSpecifier::DollarSign,
&mut callback,
);
}
_ => {
continue;
}
}
}
// type
match chars.peek().copied().unwrap_or_default().1 {
'?' => {
skip_char_and_emit(
&mut chars,
FormatSpecifier::QuestionMark,
&mut callback,
);
}
c if c == '_' || c.is_alphabetic() => {
read_identifier(&mut chars, &mut callback);
if chars.peek().map(|&(_, c)| c) == Some('?') {
skip_char_and_emit(
&mut chars,
FormatSpecifier::QuestionMark,
&mut callback,
);
}
}
_ => {}
}
}
if let Some((_, '}')) = chars.peek() {
skip_char_and_emit(&mut chars, FormatSpecifier::Close, &mut callback);
}
continue;
} else if let '}' = first_char
&& let Some((_, '}')) = chars.peek()
{
// Escaped format specifier, `}}`
read_escaped_format_specifier(&mut chars, &mut callback);
}
}
fn skip_char_and_emit<I, F>(
chars: &mut std::iter::Peekable<I>,
emit: FormatSpecifier,
callback: &mut F,
) where
I: Iterator<Item = (TextRange, char)>,
F: FnMut(TextRange, FormatSpecifier),
{
let (range, _) = chars.next().unwrap();
callback(range, emit);
}
fn read_integer<I, F>(chars: &mut std::iter::Peekable<I>, callback: &mut F)
where
I: Iterator<Item = (TextRange, char)>,
F: FnMut(TextRange, FormatSpecifier),
{
let (mut range, c) = chars.next().unwrap();
assert!(c.is_ascii_digit());
while let Some(&(r, next_char)) = chars.peek() {
if next_char.is_ascii_digit() {
chars.next();
range = range.cover(r);
} else {
break;
}
}
callback(range, FormatSpecifier::Integer);
}
fn read_identifier<I, F>(chars: &mut std::iter::Peekable<I>, callback: &mut F)
where
I: Iterator<Item = (TextRange, char)>,
F: FnMut(TextRange, FormatSpecifier),
{
let (mut range, c) = chars.next().unwrap();
assert!(c.is_alphabetic() || c == '_');
while let Some(&(r, next_char)) = chars.peek() {
if next_char == '_' || next_char.is_ascii_digit() || next_char.is_alphabetic() {
chars.next();
range = range.cover(r);
} else {
break;
}
}
callback(range, FormatSpecifier::Identifier);
}
fn read_escaped_format_specifier<I, F>(chars: &mut std::iter::Peekable<I>, callback: &mut F)
where
I: Iterator<Item = (TextRange, char)>,
F: FnMut(TextRange, FormatSpecifier),
{
let (range, _) = chars.peek().unwrap();
let offset = TextSize::from(1);
callback(TextRange::new(range.start() - offset, range.end()), FormatSpecifier::Escape);
chars.next();
}
}