Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Split Diagnostics for Uncommon Codepoints: Add List to Display Characters Involved #120259

Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 8 additions & 0 deletions compiler/rustc_errors/src/diagnostic_impls.rs
Original file line number Diff line number Diff line change
Expand Up @@ -110,6 +110,14 @@ impl IntoDiagnosticArg for char {
}
}

impl IntoDiagnosticArg for Vec<char> {
fn into_diagnostic_arg(self) -> DiagnosticArgValue<'static> {
DiagnosticArgValue::StrListSepByAnd(
self.into_iter().map(|c| Cow::Owned(format!("{c:?}"))).collect(),
)
}
}

impl IntoDiagnosticArg for Symbol {
fn into_diagnostic_arg(self) -> DiagnosticArgValue<'static> {
self.to_ident_string().into_diagnostic_arg()
Expand Down
5 changes: 4 additions & 1 deletion compiler/rustc_lint/messages.ftl
Original file line number Diff line number Diff line change
Expand Up @@ -240,7 +240,10 @@ lint_hidden_unicode_codepoints = unicode codepoint changing visible direction of

lint_identifier_non_ascii_char = identifier contains non-ASCII characters

lint_identifier_uncommon_codepoints = identifier contains uncommon Unicode codepoints
lint_identifier_uncommon_codepoints = identifier contains {$codepoints_len ->
[one] an uncommon Unicode codepoint
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

praise: well done with pluralization

*[other] uncommon Unicode codepoints
}: {$codepoints}

lint_ignored_unless_crate_specified = {$level}({$name}) is ignored unless specified at crate level

Expand Down
5 changes: 4 additions & 1 deletion compiler/rustc_lint/src/lints.rs
Original file line number Diff line number Diff line change
Expand Up @@ -1107,7 +1107,10 @@ pub struct IdentifierNonAsciiChar;

#[derive(LintDiagnostic)]
#[diag(lint_identifier_uncommon_codepoints)]
pub struct IdentifierUncommonCodepoints;
pub struct IdentifierUncommonCodepoints {
pub codepoints: Vec<char>,
pub codepoints_len: usize,
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

cc @davidtwco would be nice to autogenerate _len parameters for vector fields

}

#[derive(LintDiagnostic)]
#[diag(lint_confusable_identifier_pair)]
Expand Down
12 changes: 11 additions & 1 deletion compiler/rustc_lint/src/non_ascii_idents.rs
Original file line number Diff line number Diff line change
Expand Up @@ -190,7 +190,17 @@ impl EarlyLintPass for NonAsciiIdents {
if check_uncommon_codepoints
&& !symbol_str.chars().all(GeneralSecurityProfile::identifier_allowed)
{
cx.emit_span_lint(UNCOMMON_CODEPOINTS, sp, IdentifierUncommonCodepoints);
let codepoints: Vec<_> = symbol_str
.chars()
.filter(|c| !GeneralSecurityProfile::identifier_allowed(*c))
.collect();
let codepoints_len = codepoints.len();

cx.emit_span_lint(
UNCOMMON_CODEPOINTS,
sp,
IdentifierUncommonCodepoints { codepoints, codepoints_len },
);
}
}

Expand Down
2 changes: 1 addition & 1 deletion tests/ui/lexer/lex-emoji-identifiers.rs
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,7 @@ fn invalid_emoji_usages() {
let wireless🛜 = "basic emoji"; //~ ERROR: identifiers cannot contain emoji
// FIXME
let key1️⃣ = "keycap sequence"; //~ ERROR: unknown start of token
//~^ WARN: identifier contains uncommon Unicode codepoints
//~^ WARN: identifier contains an uncommon Unicode codepoint
let flag🇺🇳 = "flag sequence"; //~ ERROR: identifiers cannot contain emoji
let wales🏴 = "tag sequence"; //~ ERROR: identifiers cannot contain emoji
let folded🙏🏿 = "modifier sequence"; //~ ERROR: identifiers cannot contain emoji
Expand Down
2 changes: 1 addition & 1 deletion tests/ui/lexer/lex-emoji-identifiers.stderr
Original file line number Diff line number Diff line change
Expand Up @@ -40,7 +40,7 @@ error: identifiers cannot contain emoji: `folded🙏🏿`
LL | let folded🙏🏿 = "modifier sequence";
| ^^^^^^^^^^

warning: identifier contains uncommon Unicode codepoints
warning: identifier contains an uncommon Unicode codepoint: '\u{fe0f}'
--> $DIR/lex-emoji-identifiers.rs:6:9
|
LL | let key1️⃣ = "keycap sequence";
Expand Down
Original file line number Diff line number Diff line change
@@ -1,9 +1,9 @@
#![deny(uncommon_codepoints)]

const µ: f64 = 0.000001; //~ ERROR identifier contains uncommon Unicode codepoints
const µ: f64 = 0.000001; //~ ERROR identifier contains an uncommon Unicode codepoint
//~| WARNING should have an upper case name

fn dijkstra() {} //~ ERROR identifier contains uncommon Unicode codepoints
fn dijkstra() {} //~ ERROR identifier contains an uncommon Unicode codepoint

fn main() {
let ㇻㇲㇳ = "rust"; //~ ERROR identifier contains uncommon Unicode codepoints
Expand Down
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
error: identifier contains uncommon Unicode codepoints
error: identifier contains an uncommon Unicode codepoint: 'µ'
--> $DIR/lint-uncommon-codepoints.rs:3:7
|
LL | const µ: f64 = 0.000001;
Expand All @@ -10,13 +10,13 @@ note: the lint level is defined here
LL | #![deny(uncommon_codepoints)]
| ^^^^^^^^^^^^^^^^^^^

error: identifier contains uncommon Unicode codepoints
error: identifier contains an uncommon Unicode codepoint: 'ij'
--> $DIR/lint-uncommon-codepoints.rs:6:4
|
LL | fn dijkstra() {}
| ^^^^^^^

error: identifier contains uncommon Unicode codepoints
error: identifier contains uncommon Unicode codepoints: 'ㇻ', 'ㇲ', and 'ㇳ'
--> $DIR/lint-uncommon-codepoints.rs:9:9
|
LL | let ㇻㇲㇳ = "rust";
Expand Down
Loading