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
use crate::pt::Comment;
#[derive(Clone, Debug, PartialEq, Eq)]
pub enum DocComment {
Line {
comment: DocCommentTag,
},
Block {
comments: Vec<DocCommentTag>,
},
}
impl DocComment {
pub fn comments(&self) -> Vec<&DocCommentTag> {
match self {
DocComment::Line { comment } => vec![comment],
DocComment::Block { comments } => comments.iter().collect(),
}
}
pub fn into_comments(self) -> Vec<DocCommentTag> {
match self {
DocComment::Line { comment } => vec![comment],
DocComment::Block { comments } => comments,
}
}
}
#[derive(Clone, Debug, Default, PartialEq, Eq)]
pub struct DocCommentTag {
pub tag: String,
pub tag_offset: usize,
pub value: String,
pub value_offset: usize,
}
enum CommentType {
Line,
Block,
}
pub fn parse_doccomments(comments: &[Comment], start: usize, end: usize) -> Vec<DocComment> {
let mut tags = Vec::with_capacity(comments.len());
for (ty, comment_lines) in filter_comments(comments, start, end) {
let mut single_tags = Vec::with_capacity(comment_lines.len());
for (start_offset, line) in comment_lines {
let mut chars = line.char_indices().peekable();
if let Some((_, '@')) = chars.peek() {
let (tag_start, _) = chars.next().unwrap();
let mut tag_end = tag_start;
while let Some((offset, c)) = chars.peek() {
if c.is_whitespace() {
break;
}
tag_end = *offset;
chars.next();
}
let leading = line[tag_end + 1..]
.chars()
.take_while(|ch| ch.is_whitespace())
.count();
single_tags.push(DocCommentTag {
tag_offset: start_offset + tag_start + 1,
tag: line[tag_start + 1..tag_end + 1].to_owned(),
value_offset: start_offset + tag_end + leading + 1,
value: line[tag_end + 1..].trim().to_owned(),
});
} else if !single_tags.is_empty() || !tags.is_empty() {
let line = line.trim();
if !line.is_empty() {
let single_doc_comment = if let Some(single_tag) = single_tags.last_mut() {
Some(single_tag)
} else if let Some(tag) = tags.last_mut() {
match tag {
DocComment::Line { comment } => Some(comment),
DocComment::Block { comments } => comments.last_mut(),
}
} else {
None
};
if let Some(comment) = single_doc_comment {
comment.value.push('\n');
comment.value.push_str(line);
}
}
} else {
let leading = line.chars().take_while(|ch| ch.is_whitespace()).count();
single_tags.push(DocCommentTag {
tag_offset: start_offset + start_offset + leading,
tag: String::from("notice"),
value_offset: start_offset + start_offset + leading,
value: line.trim().to_owned(),
});
}
}
match ty {
CommentType::Line if !single_tags.is_empty() => tags.push(DocComment::Line {
comment: single_tags.swap_remove(0),
}),
CommentType::Block => tags.push(DocComment::Block {
comments: single_tags,
}),
_ => {}
}
}
tags
}
fn filter_comments(
comments: &[Comment],
start: usize,
end: usize,
) -> impl Iterator<Item = (CommentType, Vec<(usize, &str)>)> {
comments.iter().filter_map(move |comment| {
match comment {
Comment::Block(..) | Comment::Line(..) => None,
Comment::DocLine(loc, _) | Comment::DocBlock(loc, _)
if loc.start() >= end || loc.end() < start =>
{
None
}
Comment::DocLine(loc, comment) => {
let leading = comment
.find(|c: char| c != '/' && !c.is_whitespace())
.unwrap_or(3);
let comment = (loc.start() + leading, comment[leading..].trim_end());
Some((CommentType::Line, vec![comment]))
}
Comment::DocBlock(loc, comment) => {
let mut start = loc.start() + 3;
let mut grouped_comments = Vec::new();
let len = comment.len();
for s in comment[3..len - 2].lines() {
if let Some((i, _)) = s
.char_indices()
.find(|(_, ch)| !ch.is_whitespace() && *ch != '*')
{
grouped_comments.push((start + i, s[i..].trim_end()));
}
start += s.len() + 1;
}
Some((CommentType::Block, grouped_comments))
}
}
})
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn parse() {
let src = r#"
pragma solidity ^0.8.19;
/// @name Test
/// no tag
///@notice Cool contract
/// @ dev This is not a dev tag
/**
* @dev line one
* line 2
*/
contract Test {
/*** my function
i like whitespace
*/
function test() {}
}
"#;
let (_, comments) = crate::parse(src, 0).unwrap();
assert_eq!(comments.len(), 6);
let actual = parse_doccomments(&comments, 0, usize::MAX);
let expected = vec![
DocComment::Line {
comment: DocCommentTag {
tag: "name".into(),
tag_offset: 31,
value: "Test\nno tag".into(),
value_offset: 36,
},
},
DocComment::Line {
comment: DocCommentTag {
tag: "notice".into(),
tag_offset: 57,
value: "Cool contract".into(),
value_offset: 67,
},
},
DocComment::Line {
comment: DocCommentTag {
tag: "".into(),
tag_offset: 92,
value: "dev This is not a dev tag".into(),
value_offset: 94,
},
},
DocComment::Block {
comments: vec![DocCommentTag {
tag: "dev".into(),
tag_offset: 133,
value: "line one\nline 2\nmy function\ni like whitespace".into(),
value_offset: 137,
}],
},
DocComment::Block { comments: vec![] },
];
assert_eq!(actual, expected);
}
}