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
use crate::lints::{
    ConfusableIdentifierPair, IdentifierNonAsciiChar, IdentifierUncommonCodepoints,
    MixedScriptConfusables,
};
use crate::{EarlyContext, EarlyLintPass, LintContext};
use rustc_ast as ast;
use rustc_data_structures::fx::FxHashMap;
use rustc_span::symbol::Symbol;

declare_lint! {
    /// The `non_ascii_idents` lint detects non-ASCII identifiers.
    ///
    /// ### Example
    ///
    /// ```rust,compile_fail
    /// # #![allow(unused)]
    /// #![deny(non_ascii_idents)]
    /// fn main() {
    ///     let föö = 1;
    /// }
    /// ```
    ///
    /// {{produces}}
    ///
    /// ### Explanation
    ///
    /// This lint allows projects that wish to retain the limit of only using
    /// ASCII characters to switch this lint to "forbid" (for example to ease
    /// collaboration or for security reasons).
    /// See [RFC 2457] for more details.
    ///
    /// [RFC 2457]: https://github.com/rust-lang/rfcs/blob/master/text/2457-non-ascii-idents.md
    pub NON_ASCII_IDENTS,
    Allow,
    "detects non-ASCII identifiers",
    crate_level_only
}

declare_lint! {
    /// The `uncommon_codepoints` lint detects uncommon Unicode codepoints in
    /// identifiers.
    ///
    /// ### Example
    ///
    /// ```rust
    /// # #![allow(unused)]
    /// const µ: f64 = 0.000001;
    /// ```
    ///
    /// {{produces}}
    ///
    /// ### Explanation
    ///
    /// This lint warns about using characters which are not commonly used, and may
    /// cause visual confusion.
    ///
    /// This lint is triggered by identifiers that contain a codepoint that is
    /// not part of the set of "Allowed" codepoints as described by [Unicode®
    /// Technical Standard #39 Unicode Security Mechanisms Section 3.1 General
    /// Security Profile for Identifiers][TR39Allowed].
    ///
    /// Note that the set of uncommon codepoints may change over time. Beware
    /// that if you "forbid" this lint that existing code may fail in the
    /// future.
    ///
    /// [TR39Allowed]: https://www.unicode.org/reports/tr39/#General_Security_Profile
    pub UNCOMMON_CODEPOINTS,
    Warn,
    "detects uncommon Unicode codepoints in identifiers",
    crate_level_only
}

declare_lint! {
    /// The `confusable_idents` lint detects visually confusable pairs between
    /// identifiers.
    ///
    /// ### Example
    ///
    /// ```rust
    /// // Latin Capital Letter E With Caron
    /// pub const Ě: i32 = 1;
    /// // Latin Capital Letter E With Breve
    /// pub const Ĕ: i32 = 2;
    /// ```
    ///
    /// {{produces}}
    ///
    /// ### Explanation
    ///
    /// This lint warns when different identifiers may appear visually similar,
    /// which can cause confusion.
    ///
    /// The confusable detection algorithm is based on [Unicode® Technical
    /// Standard #39 Unicode Security Mechanisms Section 4 Confusable
    /// Detection][TR39Confusable]. For every distinct identifier X execute
    /// the function `skeleton(X)`. If there exist two distinct identifiers X
    /// and Y in the same crate where `skeleton(X) = skeleton(Y)` report it.
    /// The compiler uses the same mechanism to check if an identifier is too
    /// similar to a keyword.
    ///
    /// Note that the set of confusable characters may change over time.
    /// Beware that if you "forbid" this lint that existing code may fail in
    /// the future.
    ///
    /// [TR39Confusable]: https://www.unicode.org/reports/tr39/#Confusable_Detection
    pub CONFUSABLE_IDENTS,
    Warn,
    "detects visually confusable pairs between identifiers",
    crate_level_only
}

declare_lint! {
    /// The `mixed_script_confusables` lint detects visually confusable
    /// characters in identifiers between different [scripts].
    ///
    /// [scripts]: https://en.wikipedia.org/wiki/Script_(Unicode)
    ///
    /// ### Example
    ///
    /// ```rust
    /// // The Japanese katakana character エ can be confused with the Han character 工.
    /// const エ: &'static str = "アイウ";
    /// ```
    ///
    /// {{produces}}
    ///
    /// ### Explanation
    ///
    /// This lint warns when characters between different scripts may appear
    /// visually similar, which can cause confusion.
    ///
    /// If the crate contains other identifiers in the same script that have
    /// non-confusable characters, then this lint will *not* be issued. For
    /// example, if the example given above has another identifier with
    /// katakana characters (such as `let カタカナ = 123;`), then this indicates
    /// that you are intentionally using katakana, and it will not warn about
    /// it.
    ///
    /// Note that the set of confusable characters may change over time.
    /// Beware that if you "forbid" this lint that existing code may fail in
    /// the future.
    pub MIXED_SCRIPT_CONFUSABLES,
    Warn,
    "detects Unicode scripts whose mixed script confusables codepoints are solely used",
    crate_level_only
}

declare_lint_pass!(NonAsciiIdents => [NON_ASCII_IDENTS, UNCOMMON_CODEPOINTS, CONFUSABLE_IDENTS, MIXED_SCRIPT_CONFUSABLES]);

impl EarlyLintPass for NonAsciiIdents {
    fn check_crate(&mut self, cx: &EarlyContext<'_>, _: &ast::Crate) {
        use rustc_session::lint::Level;
        use rustc_span::Span;
        use std::collections::BTreeMap;
        use unicode_security::GeneralSecurityProfile;

        let check_non_ascii_idents = cx.builder.lint_level(NON_ASCII_IDENTS).0 != Level::Allow;
        let check_uncommon_codepoints =
            cx.builder.lint_level(UNCOMMON_CODEPOINTS).0 != Level::Allow;
        let check_confusable_idents = cx.builder.lint_level(CONFUSABLE_IDENTS).0 != Level::Allow;
        let check_mixed_script_confusables =
            cx.builder.lint_level(MIXED_SCRIPT_CONFUSABLES).0 != Level::Allow;

        if !check_non_ascii_idents
            && !check_uncommon_codepoints
            && !check_confusable_idents
            && !check_mixed_script_confusables
        {
            return;
        }

        let mut has_non_ascii_idents = false;
        let symbols = cx.sess().parse_sess.symbol_gallery.symbols.lock();

        // Sort by `Span` so that error messages make sense with respect to the
        // order of identifier locations in the code.
        let mut symbols: Vec<_> = symbols.iter().collect();
        symbols.sort_by_key(|k| k.1);

        for (symbol, &sp) in symbols.iter() {
            let symbol_str = symbol.as_str();
            if symbol_str.is_ascii() {
                continue;
            }
            has_non_ascii_idents = true;
            cx.emit_spanned_lint(NON_ASCII_IDENTS, sp, IdentifierNonAsciiChar);
            if check_uncommon_codepoints
                && !symbol_str.chars().all(GeneralSecurityProfile::identifier_allowed)
            {
                cx.emit_spanned_lint(UNCOMMON_CODEPOINTS, sp, IdentifierUncommonCodepoints);
            }
        }

        if has_non_ascii_idents && check_confusable_idents {
            let mut skeleton_map: FxHashMap<Symbol, (Symbol, Span, bool)> =
                FxHashMap::with_capacity_and_hasher(symbols.len(), Default::default());
            let mut skeleton_buf = String::new();

            for (&symbol, &sp) in symbols.iter() {
                use unicode_security::confusable_detection::skeleton;

                let symbol_str = symbol.as_str();
                let is_ascii = symbol_str.is_ascii();

                // Get the skeleton as a `Symbol`.
                skeleton_buf.clear();
                skeleton_buf.extend(skeleton(&symbol_str));
                let skeleton_sym = if *symbol_str == *skeleton_buf {
                    symbol
                } else {
                    Symbol::intern(&skeleton_buf)
                };

                skeleton_map
                    .entry(skeleton_sym)
                    .and_modify(|(existing_symbol, existing_span, existing_is_ascii)| {
                        if !*existing_is_ascii || !is_ascii {
                            cx.emit_spanned_lint(
                                CONFUSABLE_IDENTS,
                                sp,
                                ConfusableIdentifierPair {
                                    existing_sym: *existing_symbol,
                                    sym: symbol,
                                    label: *existing_span,
                                },
                            );
                        }
                        if *existing_is_ascii && !is_ascii {
                            *existing_symbol = symbol;
                            *existing_span = sp;
                            *existing_is_ascii = is_ascii;
                        }
                    })
                    .or_insert((symbol, sp, is_ascii));
            }
        }

        if has_non_ascii_idents && check_mixed_script_confusables {
            use unicode_security::is_potential_mixed_script_confusable_char;
            use unicode_security::mixed_script::AugmentedScriptSet;

            #[derive(Clone)]
            enum ScriptSetUsage {
                Suspicious(Vec<char>, Span),
                Verified,
            }

            let mut script_states: FxHashMap<AugmentedScriptSet, ScriptSetUsage> =
                FxHashMap::default();
            let latin_augmented_script_set = AugmentedScriptSet::for_char('A');
            script_states.insert(latin_augmented_script_set, ScriptSetUsage::Verified);

            let mut has_suspicous = false;
            for (symbol, &sp) in symbols.iter() {
                let symbol_str = symbol.as_str();
                for ch in symbol_str.chars() {
                    if ch.is_ascii() {
                        // all ascii characters are covered by exception.
                        continue;
                    }
                    if !GeneralSecurityProfile::identifier_allowed(ch) {
                        // this character is covered by `uncommon_codepoints` lint.
                        continue;
                    }
                    let augmented_script_set = AugmentedScriptSet::for_char(ch);
                    script_states
                        .entry(augmented_script_set)
                        .and_modify(|existing_state| {
                            if let ScriptSetUsage::Suspicious(ch_list, _) = existing_state {
                                if is_potential_mixed_script_confusable_char(ch) {
                                    ch_list.push(ch);
                                } else {
                                    *existing_state = ScriptSetUsage::Verified;
                                }
                            }
                        })
                        .or_insert_with(|| {
                            if !is_potential_mixed_script_confusable_char(ch) {
                                ScriptSetUsage::Verified
                            } else {
                                has_suspicous = true;
                                ScriptSetUsage::Suspicious(vec![ch], sp)
                            }
                        });
                }
            }

            if has_suspicous {
                let verified_augmented_script_sets = script_states
                    .iter()
                    .flat_map(|(k, v)| match v {
                        ScriptSetUsage::Verified => Some(*k),
                        _ => None,
                    })
                    .collect::<Vec<_>>();

                // we're sorting the output here.
                let mut lint_reports: BTreeMap<(Span, Vec<char>), AugmentedScriptSet> =
                    BTreeMap::new();

                'outerloop: for (augment_script_set, usage) in script_states {
                    let ScriptSetUsage::Suspicious(mut ch_list, sp) = usage else { continue };

                    if augment_script_set.is_all() {
                        continue;
                    }

                    for existing in verified_augmented_script_sets.iter() {
                        if existing.is_all() {
                            continue;
                        }
                        let mut intersect = *existing;
                        intersect.intersect_with(augment_script_set);
                        if !intersect.is_empty() && !intersect.is_all() {
                            continue 'outerloop;
                        }
                    }

                    // We sort primitive chars here and can use unstable sort
                    ch_list.sort_unstable();
                    ch_list.dedup();
                    lint_reports.insert((sp, ch_list), augment_script_set);
                }

                for ((sp, ch_list), script_set) in lint_reports {
                    let mut includes = String::new();
                    for (idx, ch) in ch_list.into_iter().enumerate() {
                        if idx != 0 {
                            includes += ", ";
                        }
                        let char_info = format!("'{}' (U+{:04X})", ch, ch as u32);
                        includes += &char_info;
                    }
                    cx.emit_spanned_lint(
                        MIXED_SCRIPT_CONFUSABLES,
                        sp,
                        MixedScriptConfusables { set: script_set.to_string(), includes },
                    );
                }
            }
        }
    }
}