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
pub use CommentStyle::*;

use crate::ast;
use crate::sess::ParseSess;

use rustc_span::source_map::SourceMap;
use rustc_span::{BytePos, CharPos, FileName, Pos};

use std::usize;

use log::debug;

#[cfg(test)]
mod tests;

#[derive(Clone, Copy, PartialEq, Debug)]
pub enum CommentStyle {
    /// No code on either side of each line of the comment
    Isolated,
    /// Code exists to the left of the comment
    Trailing,
    /// Code before /* foo */ and after the comment
    Mixed,
    /// Just a manual blank line "\n\n", for layout
    BlankLine,
}

#[derive(Clone)]
pub struct Comment {
    pub style: CommentStyle,
    pub lines: Vec<String>,
    pub pos: BytePos,
}

pub fn is_line_doc_comment(s: &str) -> bool {
    let res = (s.starts_with("///") && *s.as_bytes().get(3).unwrap_or(&b' ') != b'/')
        || s.starts_with("//!");
    debug!("is {:?} a doc comment? {}", s, res);
    res
}

pub fn is_block_doc_comment(s: &str) -> bool {
    // Prevent `/**/` from being parsed as a doc comment
    let res = ((s.starts_with("/**") && *s.as_bytes().get(3).unwrap_or(&b' ') != b'*')
        || s.starts_with("/*!"))
        && s.len() >= 5;
    debug!("is {:?} a doc comment? {}", s, res);
    res
}

// FIXME(#64197): Try to privatize this again.
pub fn is_doc_comment(s: &str) -> bool {
    (s.starts_with("///") && is_line_doc_comment(s))
        || s.starts_with("//!")
        || (s.starts_with("/**") && is_block_doc_comment(s))
        || s.starts_with("/*!")
}

pub fn doc_comment_style(comment: &str) -> ast::AttrStyle {
    assert!(is_doc_comment(comment));
    if comment.starts_with("//!") || comment.starts_with("/*!") {
        ast::AttrStyle::Inner
    } else {
        ast::AttrStyle::Outer
    }
}

pub fn strip_doc_comment_decoration(comment: &str) -> String {
    /// remove whitespace-only lines from the start/end of lines
    fn vertical_trim(lines: Vec<String>) -> Vec<String> {
        let mut i = 0;
        let mut j = lines.len();
        // first line of all-stars should be omitted
        if !lines.is_empty() && lines[0].chars().all(|c| c == '*') {
            i += 1;
        }

        while i < j && lines[i].trim().is_empty() {
            i += 1;
        }
        // like the first, a last line of all stars should be omitted
        if j > i && lines[j - 1].chars().skip(1).all(|c| c == '*') {
            j -= 1;
        }

        while j > i && lines[j - 1].trim().is_empty() {
            j -= 1;
        }

        lines[i..j].to_vec()
    }

    /// remove a "[ \t]*\*" block from each line, if possible
    fn horizontal_trim(lines: Vec<String>) -> Vec<String> {
        let mut i = usize::MAX;
        let mut can_trim = true;
        let mut first = true;

        for line in &lines {
            for (j, c) in line.chars().enumerate() {
                if j > i || !"* \t".contains(c) {
                    can_trim = false;
                    break;
                }
                if c == '*' {
                    if first {
                        i = j;
                        first = false;
                    } else if i != j {
                        can_trim = false;
                    }
                    break;
                }
            }
            if i >= line.len() {
                can_trim = false;
            }
            if !can_trim {
                break;
            }
        }

        if can_trim {
            lines.iter().map(|line| (&line[i + 1..line.len()]).to_string()).collect()
        } else {
            lines
        }
    }

    // one-line comments lose their prefix
    const ONELINERS: &[&str] = &["///!", "///", "//!", "//"];

    for prefix in ONELINERS {
        if comment.starts_with(*prefix) {
            return (&comment[prefix.len()..]).to_string();
        }
    }

    if comment.starts_with("/*") {
        let lines =
            comment[3..comment.len() - 2].lines().map(|s| s.to_string()).collect::<Vec<String>>();

        let lines = vertical_trim(lines);
        let lines = horizontal_trim(lines);

        return lines.join("\n");
    }

    panic!("not a doc-comment: {}", comment);
}

/// Returns `None` if the first `col` chars of `s` contain a non-whitespace char.
/// Otherwise returns `Some(k)` where `k` is first char offset after that leading
/// whitespace. Note that `k` may be outside bounds of `s`.
fn all_whitespace(s: &str, col: CharPos) -> Option<usize> {
    let mut idx = 0;
    for (i, ch) in s.char_indices().take(col.to_usize()) {
        if !ch.is_whitespace() {
            return None;
        }
        idx = i + ch.len_utf8();
    }
    Some(idx)
}

fn trim_whitespace_prefix(s: &str, col: CharPos) -> &str {
    let len = s.len();
    match all_whitespace(&s, col) {
        Some(col) => {
            if col < len {
                &s[col..]
            } else {
                ""
            }
        }
        None => s,
    }
}

fn split_block_comment_into_lines(text: &str, col: CharPos) -> Vec<String> {
    let mut res: Vec<String> = vec![];
    let mut lines = text.lines();
    // just push the first line
    res.extend(lines.next().map(|it| it.to_string()));
    // for other lines, strip common whitespace prefix
    for line in lines {
        res.push(trim_whitespace_prefix(line, col).to_string())
    }
    res
}

// it appears this function is called only from pprust... that's
// probably not a good thing.
crate fn gather_comments(sess: &ParseSess, path: FileName, src: String) -> Vec<Comment> {
    let cm = SourceMap::new(sess.source_map().path_mapping().clone());
    let source_file = cm.new_source_file(path, src);
    let text = (*source_file.src.as_ref().unwrap()).clone();

    let text: &str = text.as_str();
    let start_bpos = source_file.start_pos;
    let mut pos = 0;
    let mut comments: Vec<Comment> = Vec::new();
    let mut code_to_the_left = false;

    if let Some(shebang_len) = rustc_lexer::strip_shebang(text) {
        comments.push(Comment {
            style: Isolated,
            lines: vec![text[..shebang_len].to_string()],
            pos: start_bpos,
        });
        pos += shebang_len;
    }

    for token in rustc_lexer::tokenize(&text[pos..]) {
        let token_text = &text[pos..pos + token.len];
        match token.kind {
            rustc_lexer::TokenKind::Whitespace => {
                if let Some(mut idx) = token_text.find('\n') {
                    code_to_the_left = false;
                    while let Some(next_newline) = &token_text[idx + 1..].find('\n') {
                        idx = idx + 1 + next_newline;
                        comments.push(Comment {
                            style: BlankLine,
                            lines: vec![],
                            pos: start_bpos + BytePos((pos + idx) as u32),
                        });
                    }
                }
            }
            rustc_lexer::TokenKind::BlockComment { terminated: _ } => {
                if !is_block_doc_comment(token_text) {
                    let code_to_the_right = match text[pos + token.len..].chars().next() {
                        Some('\r') | Some('\n') => false,
                        _ => true,
                    };
                    let style = match (code_to_the_left, code_to_the_right) {
                        (true, true) | (false, true) => Mixed,
                        (false, false) => Isolated,
                        (true, false) => Trailing,
                    };

                    // Count the number of chars since the start of the line by rescanning.
                    let pos_in_file = start_bpos + BytePos(pos as u32);
                    let line_begin_in_file = source_file.line_begin_pos(pos_in_file);
                    let line_begin_pos = (line_begin_in_file - start_bpos).to_usize();
                    let col = CharPos(text[line_begin_pos..pos].chars().count());

                    let lines = split_block_comment_into_lines(token_text, col);
                    comments.push(Comment { style, lines, pos: pos_in_file })
                }
            }
            rustc_lexer::TokenKind::LineComment => {
                if !is_doc_comment(token_text) {
                    comments.push(Comment {
                        style: if code_to_the_left { Trailing } else { Isolated },
                        lines: vec![token_text.to_string()],
                        pos: start_bpos + BytePos(pos as u32),
                    })
                }
            }
            _ => {
                code_to_the_left = true;
            }
        }
        pos += token.len;
    }

    comments
}