diff options
| author | clubby789 <jamie@hill-daniel.co.uk> | 2023-01-19 02:25:24 +0000 |
|---|---|---|
| committer | clubby789 <jamie@hill-daniel.co.uk> | 2023-01-19 02:25:55 +0000 |
| commit | 1487aa9f9d7edbe660272f7adb5e57ef31deab9d (patch) | |
| tree | 05a579961df45a8491fa8942b89bc0f6af3bc7e8 | |
| parent | 3520bba13690e843704e77bd2ada89131b81051e (diff) | |
| download | rust-1487aa9f9d7edbe660272f7adb5e57ef31deab9d.tar.gz rust-1487aa9f9d7edbe660272f7adb5e57ef31deab9d.zip | |
Add double-equals homoglyph
| -rw-r--r-- | compiler/rustc_parse/src/lexer/unicode_chars.rs | 2 | ||||
| -rw-r--r-- | tests/ui/parser/unicode-chars.rs | 3 | ||||
| -rw-r--r-- | tests/ui/parser/unicode-chars.stderr | 13 |
3 files changed, 17 insertions, 1 deletions
diff --git a/compiler/rustc_parse/src/lexer/unicode_chars.rs b/compiler/rustc_parse/src/lexer/unicode_chars.rs index 2332216f09b..34d003ccfa7 100644 --- a/compiler/rustc_parse/src/lexer/unicode_chars.rs +++ b/compiler/rustc_parse/src/lexer/unicode_chars.rs @@ -296,6 +296,7 @@ pub(crate) const UNICODE_ARRAY: &[(char, &str, &str)] = &[ ('〉', "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 @@ -325,6 +326,7 @@ const ASCII_ARRAY: &[(&str, &str, Option<token::TokenKind>)] = &[ ("+", "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. diff --git a/tests/ui/parser/unicode-chars.rs b/tests/ui/parser/unicode-chars.rs index f0122561f46..cd25c756689 100644 --- a/tests/ui/parser/unicode-chars.rs +++ b/tests/ui/parser/unicode-chars.rs @@ -6,4 +6,7 @@ fn main() { //~^ ERROR unknown start of token: \u{a0} //~^^ NOTE character appears 3 more times //~^^^ HELP Unicode character ' ' (No-Break Space) looks like ' ' (Space), but it is not + let _ = 1 ⩵ 2; + //~^ ERROR unknown start of token + //~^^ HELP Unicode character '⩵' (Two Consecutive Equals Signs) looks like '==' (Double Equals Sign), but it is not } diff --git a/tests/ui/parser/unicode-chars.stderr b/tests/ui/parser/unicode-chars.stderr index b1d4a0af711..086de5ec099 100644 --- a/tests/ui/parser/unicode-chars.stderr +++ b/tests/ui/parser/unicode-chars.stderr @@ -21,5 +21,16 @@ help: Unicode character ' ' (No-Break Space) looks like ' ' (Space), but it is LL | let x = 0; | ++++ -error: aborting due to 2 previous errors +error: unknown start of token: \u{2a75} + --> $DIR/unicode-chars.rs:9:15 + | +LL | let _ = 1 ⩵ 2; + | ^ + | +help: Unicode character '⩵' (Two Consecutive Equals Signs) looks like '==' (Double Equals Sign), but it is not + | +LL | let _ = 1 == 2; + | ~~ + +error: aborting due to 3 previous errors |