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
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
//! Characters and their corresponding confusables were collected from
//! <https://www.unicode.org/Public/security/10.0.0/confusables.txt>

use super::StringReader;
use crate::{
    errors::TokenSubstitution,
    token::{self, Delimiter},
};
use rustc_span::{symbol::kw, BytePos, Pos, Span};

#[rustfmt::skip] // for line breaks
pub(crate) const UNICODE_ARRAY: &[(char, &str, &str)] = &[
    ('
', "Line Separator", " "),
    ('
', "Paragraph Separator", " "),
    (' ', "Ogham Space mark", " "),
    (' ', "En Quad", " "),
    (' ', "Em Quad", " "),
    (' ', "En Space", " "),
    (' ', "Em Space", " "),
    (' ', "Three-Per-Em Space", " "),
    (' ', "Four-Per-Em Space", " "),
    (' ', "Six-Per-Em Space", " "),
    (' ', "Punctuation Space", " "),
    (' ', "Thin Space", " "),
    (' ', "Hair Space", " "),
    (' ', "Medium Mathematical Space", " "),
    (' ', "No-Break Space", " "),
    (' ', "Figure Space", " "),
    (' ', "Narrow No-Break Space", " "),
    (' ', "Ideographic Space", " "),

    ('ߺ', "Nko Lajanyalan", "_"),
    ('﹍', "Dashed Low Line", "_"),
    ('﹎', "Centreline Low Line", "_"),
    ('﹏', "Wavy Low Line", "_"),
    ('_', "Fullwidth Low Line", "_"),

    ('‐', "Hyphen", "-"),
    ('‑', "Non-Breaking Hyphen", "-"),
    ('‒', "Figure Dash", "-"),
    ('–', "En Dash", "-"),
    ('—', "Em Dash", "-"),
    ('﹘', "Small Em Dash", "-"),
    ('۔', "Arabic Full Stop", "-"),
    ('⁃', "Hyphen Bullet", "-"),
    ('˗', "Modifier Letter Minus Sign", "-"),
    ('−', "Minus Sign", "-"),
    ('➖', "Heavy Minus Sign", "-"),
    ('Ⲻ', "Coptic Letter Dialect-P Ni", "-"),
    ('ー', "Katakana-Hiragana Prolonged Sound Mark", "-"),
    ('-', "Fullwidth Hyphen-Minus", "-"),
    ('―', "Horizontal Bar", "-"),
    ('─', "Box Drawings Light Horizontal", "-"),
    ('━', "Box Drawings Heavy Horizontal", "-"),
    ('㇐', "CJK Stroke H", "-"),
    ('ꟷ', "Latin Epigraphic Letter Sideways I", "-"),
    ('ᅳ', "Hangul Jungseong Eu", "-"),
    ('ㅡ', "Hangul Letter Eu", "-"),
    ('一', "CJK Unified Ideograph-4E00", "-"),
    ('⼀', "Kangxi Radical One", "-"),

    ('؍', "Arabic Date Separator", ","),
    ('٫', "Arabic Decimal Separator", ","),
    ('‚', "Single Low-9 Quotation Mark", ","),
    ('¸', "Cedilla", ","),
    ('ꓹ', "Lisu Letter Tone Na Po", ","),
    (',', "Fullwidth Comma", ","),

    (';', "Greek Question Mark", ";"),
    (';', "Fullwidth Semicolon", ";"),
    ('︔', "Presentation Form For Vertical Semicolon", ";"),

    ('ः', "Devanagari Sign Visarga", ":"),
    ('ઃ', "Gujarati Sign Visarga", ":"),
    (':', "Fullwidth Colon", ":"),
    ('։', "Armenian Full Stop", ":"),
    ('܃', "Syriac Supralinear Colon", ":"),
    ('܄', "Syriac Sublinear Colon", ":"),
    ('᛬', "Runic Multiple Punctuation", ":"),
    ('︰', "Presentation Form For Vertical Two Dot Leader", ":"),
    ('᠃', "Mongolian Full Stop", ":"),
    ('᠉', "Mongolian Manchu Full Stop", ":"),
    ('⁚', "Two Dot Punctuation", ":"),
    ('׃', "Hebrew Punctuation Sof Pasuq", ":"),
    ('˸', "Modifier Letter Raised Colon", ":"),
    ('꞉', "Modifier Letter Colon", ":"),
    ('∶', "Ratio", ":"),
    ('ː', "Modifier Letter Triangular Colon", ":"),
    ('ꓽ', "Lisu Letter Tone Mya Jeu", ":"),
    ('︓', "Presentation Form For Vertical Colon", ":"),

    ('!', "Fullwidth Exclamation Mark", "!"),
    ('ǃ', "Latin Letter Retroflex Click", "!"),
    ('ⵑ', "Tifinagh Letter Tuareg Yang", "!"),
    ('︕', "Presentation Form For Vertical Exclamation Mark", "!"),

    ('ʔ', "Latin Letter Glottal Stop", "?"),
    ('Ɂ', "Latin Capital Letter Glottal Stop", "?"),
    ('ॽ', "Devanagari Letter Glottal Stop", "?"),
    ('Ꭾ', "Cherokee Letter He", "?"),
    ('ꛫ', "Bamum Letter Ntuu", "?"),
    ('?', "Fullwidth Question Mark", "?"),
    ('︖', "Presentation Form For Vertical Question Mark", "?"),

    ('𝅭', "Musical Symbol Combining Augmentation Dot", "."),
    ('․', "One Dot Leader", "."),
    ('܁', "Syriac Supralinear Full Stop", "."),
    ('܂', "Syriac Sublinear Full Stop", "."),
    ('꘎', "Vai Full Stop", "."),
    ('𐩐', "Kharoshthi Punctuation Dot", "."),
    ('٠', "Arabic-Indic Digit Zero", "."),
    ('۰', "Extended Arabic-Indic Digit Zero", "."),
    ('ꓸ', "Lisu Letter Tone Mya Ti", "."),
    ('·', "Middle Dot", "."),
    ('・', "Katakana Middle Dot", "."),
    ('・', "Halfwidth Katakana Middle Dot", "."),
    ('᛫', "Runic Single Punctuation", "."),
    ('·', "Greek Ano Teleia", "."),
    ('⸱', "Word Separator Middle Dot", "."),
    ('𐄁', "Aegean Word Separator Dot", "."),
    ('•', "Bullet", "."),
    ('‧', "Hyphenation Point", "."),
    ('∙', "Bullet Operator", "."),
    ('⋅', "Dot Operator", "."),
    ('ꞏ', "Latin Letter Sinological Dot", "."),
    ('ᐧ', "Canadian Syllabics Final Middle Dot", "."),
    ('ᐧ', "Canadian Syllabics Final Middle Dot", "."),
    ('.', "Fullwidth Full Stop", "."),
    ('。', "Ideographic Full Stop", "."),
    ('︒', "Presentation Form For Vertical Ideographic Full Stop", "."),

    ('՝', "Armenian Comma", "\'"),
    (''', "Fullwidth Apostrophe", "\'"),
    ('‘', "Left Single Quotation Mark", "\'"),
    ('’', "Right Single Quotation Mark", "\'"),
    ('‛', "Single High-Reversed-9 Quotation Mark", "\'"),
    ('′', "Prime", "\'"),
    ('‵', "Reversed Prime", "\'"),
    ('՚', "Armenian Apostrophe", "\'"),
    ('׳', "Hebrew Punctuation Geresh", "\'"),
    ('`', "Grave Accent", "\'"),
    ('`', "Greek Varia", "\'"),
    ('`', "Fullwidth Grave Accent", "\'"),
    ('´', "Acute Accent", "\'"),
    ('΄', "Greek Tonos", "\'"),
    ('´', "Greek Oxia", "\'"),
    ('᾽', "Greek Koronis", "\'"),
    ('᾿', "Greek Psili", "\'"),
    ('῾', "Greek Dasia", "\'"),
    ('ʹ', "Modifier Letter Prime", "\'"),
    ('ʹ', "Greek Numeral Sign", "\'"),
    ('ˈ', "Modifier Letter Vertical Line", "\'"),
    ('ˊ', "Modifier Letter Acute Accent", "\'"),
    ('ˋ', "Modifier Letter Grave Accent", "\'"),
    ('˴', "Modifier Letter Middle Grave Accent", "\'"),
    ('ʻ', "Modifier Letter Turned Comma", "\'"),
    ('ʽ', "Modifier Letter Reversed Comma", "\'"),
    ('ʼ', "Modifier Letter Apostrophe", "\'"),
    ('ʾ', "Modifier Letter Right Half Ring", "\'"),
    ('ꞌ', "Latin Small Letter Saltillo", "\'"),
    ('י', "Hebrew Letter Yod", "\'"),
    ('ߴ', "Nko High Tone Apostrophe", "\'"),
    ('ߵ', "Nko Low Tone Apostrophe", "\'"),
    ('ᑊ', "Canadian Syllabics West-Cree P", "\'"),
    ('ᛌ', "Runic Letter Short-Twig-Sol S", "\'"),
    ('𖽑', "Miao Sign Aspiration", "\'"),
    ('𖽒', "Miao Sign Reformed Voicing", "\'"),

    ('᳓', "Vedic Sign Nihshvasa", "\""),
    ('"', "Fullwidth Quotation Mark", "\""),
    ('“', "Left Double Quotation Mark", "\""),
    ('”', "Right Double Quotation Mark", "\""),
    ('‟', "Double High-Reversed-9 Quotation Mark", "\""),
    ('″', "Double Prime", "\""),
    ('‶', "Reversed Double Prime", "\""),
    ('〃', "Ditto Mark", "\""),
    ('״', "Hebrew Punctuation Gershayim", "\""),
    ('˝', "Double Acute Accent", "\""),
    ('ʺ', "Modifier Letter Double Prime", "\""),
    ('˶', "Modifier Letter Middle Double Acute Accent", "\""),
    ('˵', "Modifier Letter Middle Double Grave Accent", "\""),
    ('ˮ', "Modifier Letter Double Apostrophe", "\""),
    ('ײ', "Hebrew Ligature Yiddish Double Yod", "\""),
    ('❞', "Heavy Double Comma Quotation Mark Ornament", "\""),
    ('❝', "Heavy Double Turned Comma Quotation Mark Ornament", "\""),

    ('(', "Fullwidth Left Parenthesis", "("),
    ('❨', "Medium Left Parenthesis Ornament", "("),
    ('﴾', "Ornate Left Parenthesis", "("),

    (')', "Fullwidth Right Parenthesis", ")"),
    ('❩', "Medium Right Parenthesis Ornament", ")"),
    ('﴿', "Ornate Right Parenthesis", ")"),

    ('[', "Fullwidth Left Square Bracket", "["),
    ('❲', "Light Left Tortoise Shell Bracket Ornament", "["),
    ('「', "Left Corner Bracket", "["),
    ('『', "Left White Corner Bracket", "["),
    ('【', "Left Black Lenticular Bracket", "["),
    ('〔', "Left Tortoise Shell Bracket", "["),
    ('〖', "Left White Lenticular Bracket", "["),
    ('〘', "Left White Tortoise Shell Bracket", "["),
    ('〚', "Left White Square Bracket", "["),

    (']', "Fullwidth Right Square Bracket", "]"),
    ('❳', "Light Right Tortoise Shell Bracket Ornament", "]"),
    ('」', "Right Corner Bracket", "]"),
    ('』', "Right White Corner Bracket", "]"),
    ('】', "Right Black Lenticular Bracket", "]"),
    ('〕', "Right Tortoise Shell Bracket", "]"),
    ('〗', "Right White Lenticular Bracket", "]"),
    ('〙', "Right White Tortoise Shell Bracket", "]"),
    ('〛', "Right White Square Bracket", "]"),

    ('❴', "Medium Left Curly Bracket Ornament", "{"),
    ('𝄔', "Musical Symbol Brace", "{"),
    ('{', "Fullwidth Left Curly Bracket", "{"),

    ('❵', "Medium Right Curly Bracket Ornament", "}"),
    ('}', "Fullwidth Right Curly Bracket", "}"),

    ('⁎', "Low Asterisk", "*"),
    ('٭', "Arabic Five Pointed Star", "*"),
    ('∗', "Asterisk Operator", "*"),
    ('𐌟', "Old Italic Letter Ess", "*"),
    ('*', "Fullwidth Asterisk", "*"),

    ('᜵', "Philippine Single Punctuation", "/"),
    ('⁁', "Caret Insertion Point", "/"),
    ('∕', "Division Slash", "/"),
    ('⁄', "Fraction Slash", "/"),
    ('╱', "Box Drawings Light Diagonal Upper Right To Lower Left", "/"),
    ('⟋', "Mathematical Rising Diagonal", "/"),
    ('⧸', "Big Solidus", "/"),
    ('𝈺', "Greek Instrumental Notation Symbol-47", "/"),
    ('㇓', "CJK Stroke Sp", "/"),
    ('〳', "Vertical Kana Repeat Mark Upper Half", "/"),
    ('Ⳇ', "Coptic Capital Letter Old Coptic Esh", "/"),
    ('ノ', "Katakana Letter No", "/"),
    ('丿', "CJK Unified Ideograph-4E3F", "/"),
    ('⼃', "Kangxi Radical Slash", "/"),
    ('/', "Fullwidth Solidus", "/"),

    ('\', "Fullwidth Reverse Solidus", "\\"),
    ('﹨', "Small Reverse Solidus", "\\"),
    ('∖', "Set Minus", "\\"),
    ('⟍', "Mathematical Falling Diagonal", "\\"),
    ('⧵', "Reverse Solidus Operator", "\\"),
    ('⧹', "Big Reverse Solidus", "\\"),
    ('⧹', "Greek Vocal Notation Symbol-16", "\\"),
    ('⧹', "Greek Instrumental Symbol-48", "\\"),
    ('㇔', "CJK Stroke D", "\\"),
    ('丶', "CJK Unified Ideograph-4E36", "\\"),
    ('⼂', "Kangxi Radical Dot", "\\"),
    ('、', "Ideographic Comma", "\\"),
    ('ヽ', "Katakana Iteration Mark", "\\"),

    ('ꝸ', "Latin Small Letter Um", "&"),
    ('&', "Fullwidth Ampersand", "&"),

    ('᛭', "Runic Cross Punctuation", "+"),
    ('➕', "Heavy Plus Sign", "+"),
    ('𐊛', "Lycian Letter H", "+"),
    ('﬩', "Hebrew Letter Alternative Plus Sign", "+"),
    ('+', "Fullwidth Plus Sign", "+"),

    ('‹', "Single Left-Pointing Angle Quotation Mark", "<"),
    ('❮', "Heavy Left-Pointing Angle Quotation Mark Ornament", "<"),
    ('˂', "Modifier Letter Left Arrowhead", "<"),
    ('𝈶', "Greek Instrumental Symbol-40", "<"),
    ('ᐸ', "Canadian Syllabics Pa", "<"),
    ('ᚲ', "Runic Letter Kauna", "<"),
    ('❬', "Medium Left-Pointing Angle Bracket Ornament", "<"),
    ('⟨', "Mathematical Left Angle Bracket", "<"),
    ('〈', "Left-Pointing Angle Bracket", "<"),
    ('〈', "Left Angle Bracket", "<"),
    ('㇛', "CJK Stroke Pd", "<"),
    ('く', "Hiragana Letter Ku", "<"),
    ('𡿨', "CJK Unified Ideograph-21FE8", "<"),
    ('《', "Left Double Angle Bracket", "<"),
    ('<', "Fullwidth Less-Than Sign", "<"),

    ('᐀', "Canadian Syllabics Hyphen", "="),
    ('⹀', "Double Hyphen", "="),
    ('゠', "Katakana-Hiragana Double Hyphen", "="),
    ('꓿', "Lisu Punctuation Full Stop", "="),
    ('=', "Fullwidth Equals Sign", "="),

    ('›', "Single Right-Pointing Angle Quotation Mark", ">"),
    ('❯', "Heavy Right-Pointing Angle Quotation Mark Ornament", ">"),
    ('˃', "Modifier Letter Right Arrowhead", ">"),
    ('𝈷', "Greek Instrumental Symbol-42", ">"),
    ('ᐳ', "Canadian Syllabics Po", ">"),
    ('𖼿', "Miao Letter Archaic Zza", ">"),
    ('❭', "Medium Right-Pointing Angle Bracket Ornament", ">"),
    ('⟩', "Mathematical Right Angle Bracket", ">"),
    ('〉', "Right-Pointing Angle Bracket", ">"),
    ('〉', "Right Angle Bracket", ">"),
    ('》', "Right Double Angle Bracket", ">"),
    ('>', "Fullwidth Greater-Than Sign", ">"),
    ('⩵', "Two Consecutive Equals Signs", "==")
];

// FIXME: the lexer could be used to turn the ASCII version of unicode homoglyphs, instead of
// keeping the substitution token in this table. Ideally, this should be inside `rustc_lexer`.
// However, we should first remove compound tokens like `<<` from `rustc_lexer`, and then add
// fancier error recovery to it, as there will be less overall work to do this way.
const ASCII_ARRAY: &[(&str, &str, Option<token::TokenKind>)] = &[
    (" ", "Space", None),
    ("_", "Underscore", Some(token::Ident(kw::Underscore, false))),
    ("-", "Minus/Hyphen", Some(token::BinOp(token::Minus))),
    (",", "Comma", Some(token::Comma)),
    (";", "Semicolon", Some(token::Semi)),
    (":", "Colon", Some(token::Colon)),
    ("!", "Exclamation Mark", Some(token::Not)),
    ("?", "Question Mark", Some(token::Question)),
    (".", "Period", Some(token::Dot)),
    ("(", "Left Parenthesis", Some(token::OpenDelim(Delimiter::Parenthesis))),
    (")", "Right Parenthesis", Some(token::CloseDelim(Delimiter::Parenthesis))),
    ("[", "Left Square Bracket", Some(token::OpenDelim(Delimiter::Bracket))),
    ("]", "Right Square Bracket", Some(token::CloseDelim(Delimiter::Bracket))),
    ("{", "Left Curly Brace", Some(token::OpenDelim(Delimiter::Brace))),
    ("}", "Right Curly Brace", Some(token::CloseDelim(Delimiter::Brace))),
    ("*", "Asterisk", Some(token::BinOp(token::Star))),
    ("/", "Slash", Some(token::BinOp(token::Slash))),
    ("\\", "Backslash", None),
    ("&", "Ampersand", Some(token::BinOp(token::And))),
    ("+", "Plus Sign", Some(token::BinOp(token::Plus))),
    ("<", "Less-Than Sign", Some(token::Lt)),
    ("=", "Equals Sign", Some(token::Eq)),
    ("==", "Double Equals Sign", Some(token::EqEq)),
    (">", "Greater-Than Sign", Some(token::Gt)),
    // FIXME: Literals are already lexed by this point, so we can't recover gracefully just by
    // spitting the correct token out.
    ("\'", "Single Quote", None),
    ("\"", "Quotation Mark", None),
];

pub(super) fn check_for_substitution(
    reader: &StringReader<'_>,
    pos: BytePos,
    ch: char,
    count: usize,
) -> (Option<token::TokenKind>, Option<TokenSubstitution>) {
    let Some(&(_, u_name, ascii_str)) = UNICODE_ARRAY.iter().find(|&&(c, _, _)| c == ch) else {
        return (None, None);
    };

    let span = Span::with_root_ctxt(pos, pos + Pos::from_usize(ch.len_utf8() * count));

    let Some((_, ascii_name, token)) = ASCII_ARRAY.iter().find(|&&(s, _, _)| s == ascii_str) else {
        let msg = format!("substitution character not found for '{ch}'");
        reader.sess.span_diagnostic.span_bug_no_panic(span, msg);
        return (None, None);
    };

    // special help suggestion for "directed" double quotes
    let sugg = if let Some(s) = peek_delimited(&reader.src[reader.src_index(pos)..], '“', '”') {
        let span = Span::with_root_ctxt(
            pos,
            pos + Pos::from_usize('“'.len_utf8() + s.len() + '”'.len_utf8()),
        );
        Some(TokenSubstitution::DirectedQuotes {
            span,
            suggestion: format!("\"{s}\""),
            ascii_str,
            ascii_name,
        })
    } else {
        let suggestion = ascii_str.to_string().repeat(count);
        Some(TokenSubstitution::Other {
            span,
            suggestion,
            ch: ch.to_string(),
            u_name,
            ascii_str,
            ascii_name,
        })
    };
    (token.clone(), sugg)
}

/// Extract string if found at current position with given delimiters
fn peek_delimited(text: &str, from_ch: char, to_ch: char) -> Option<&str> {
    let mut chars = text.chars();
    let first_char = chars.next()?;
    if first_char != from_ch {
        return None;
    }
    let last_char_idx = chars.as_str().find(to_ch)?;
    Some(&chars.as_str()[..last_char_idx])
}