[pylint]: bidirectional-unicode (#2589)

crates/ruff/resources/test/fixtures/pylint/bidirectional_unicode.py

@@ -0,0 +1,24 @@
+# E2502
+print("\u202B\u202E\u05e9\u05DC\u05D5\u05DD\u202C")
+
+# E2502
+print("שלום‬")
+
+# E2502
+example = "x‏" * 100  #    "‏x" is assigned
+
+# E2502
+if access_level != "none‮⁦":  # Check if admin ⁩⁦' and access_level != 'user
+    print("You are an admin.")
+
+
+# E2502
+def subtract_funds(account: str, amount: int):
+    """Subtract funds from bank account then ⁧"""
+    return
+    bank[account] -= amount
+    return
+
+
+# OK
+print("Hello World")

crates/ruff/src/checkers/ast.rs

@@ -3107,6 +3107,9 @@ where
                 if self.settings.rules.enabled(&Rule::RewriteUnicodeLiteral) {
                     pyupgrade::rules::rewrite_unicode_literal(self, expr, kind.as_deref());
                 }
+                if self.settings.rules.enabled(&Rule::BidirectionalUnicode) {
+                    pylint::rules::bidirectional_unicode(self, expr, value);
+                }
             }
             ExprKind::Lambda { args, body, .. } => {
                 if self.settings.rules.enabled(&Rule::PreferListBuiltin) {

crates/ruff/src/registry.rs

@@ -107,6 +107,7 @@ ruff_macros::define_rule_mapping!(
     // pylint
     PLE0604 => rules::pylint::rules::InvalidAllObject,
     PLE0605 => rules::pylint::rules::InvalidAllFormat,
+    PLE2502 => rules::pylint::rules::BidirectionalUnicode,
     PLE1310 => rules::pylint::rules::BadStrStripCall,
     PLC0414 => rules::pylint::rules::UselessImportAlias,
     PLC3002 => rules::pylint::rules::UnnecessaryDirectLambdaCall,

crates/ruff/src/rules/pylint/mod.rs

@@ -40,6 +40,7 @@ mod tests {
     #[test_case(Rule::TooManyArguments, Path::new("too_many_arguments.py"); "PLR0913")]
     #[test_case(Rule::TooManyBranches, Path::new("too_many_branches.py"); "PLR0912")]
     #[test_case(Rule::TooManyStatements, Path::new("too_many_statements.py"); "PLR0915")]
+    #[test_case(Rule::BidirectionalUnicode, Path::new("bidirectional_unicode.py"); "PLE2502")]
     #[test_case(Rule::BadStrStripCall, Path::new("bad_str_strip_call.py"); "PLE01310")]
     fn rules(rule_code: Rule, path: &Path) -> Result<()> {
         let snapshot = format!("{}_{}", rule_code.code(), path.to_string_lossy());

crates/ruff/src/rules/pylint/rules/bidirectional_unicode.rs

@@ -0,0 +1,49 @@
+use rustpython_ast::Expr;
+
+use ruff_macros::derive_message_formats;
+
+use crate::ast::types::Range;
+use crate::checkers::ast::Checker;
+use crate::define_violation;
+use crate::registry::Diagnostic;
+use crate::violation::Violation;
+
+const BIDI_UNICODE: [char; 10] = [
+    '\u{202A}', //{LEFT-TO-RIGHT EMBEDDING}
+    '\u{202B}', //{RIGHT-TO-LEFT EMBEDDING}
+    '\u{202C}', //{POP DIRECTIONAL FORMATTING}
+    '\u{202D}', //{LEFT-TO-RIGHT OVERRIDE}
+    '\u{202E}', //{RIGHT-TO-LEFT OVERRIDE}
+    '\u{2066}', //{LEFT-TO-RIGHT ISOLATE}
+    '\u{2067}', //{RIGHT-TO-LEFT ISOLATE}
+    '\u{2068}', //{FIRST STRONG ISOLATE}
+    '\u{2069}', //{POP DIRECTIONAL ISOLATE}
+    // The following was part of PEP 672:
+    // https://www.python.org/dev/peps/pep-0672/
+    // so the list above might not be complete
+    '\u{200F}', //{RIGHT-TO-LEFT MARK}
+                // We don't use
+                //   "\u200E" # \n{LEFT-TO-RIGHT MARK}
+                // as this is the default for latin files and can't be used
+                // to hide code
+];
+
+define_violation!(
+    pub struct BidirectionalUnicode;
+);
+impl Violation for BidirectionalUnicode {
+    #[derive_message_formats]
+    fn message(&self) -> String {
+        format!("Avoid using bidirectional unicode")
+    }
+}
+
+/// PLE2502
+pub fn bidirectional_unicode(checker: &mut Checker, expr: &Expr, value: &str) {
+    if value.contains(BIDI_UNICODE) {
+        checker.diagnostics.push(Diagnostic::new(
+            BidirectionalUnicode,
+            Range::from_located(expr),
+        ));
+    }
+}

crates/ruff/src/rules/pylint/rules/mod.rs

@@ -1,5 +1,6 @@
 pub use await_outside_async::{await_outside_async, AwaitOutsideAsync};
 pub use bad_str_strip_call::{bad_str_strip_call, BadStrStripCall};
+pub use bidirectional_unicode::{bidirectional_unicode, BidirectionalUnicode};
 pub use comparison_of_constant::{comparison_of_constant, ComparisonOfConstant};
 pub use consider_using_sys_exit::{consider_using_sys_exit, ConsiderUsingSysExit};
 pub use global_variable_not_assigned::GlobalVariableNotAssigned;
@@ -25,6 +26,7 @@ pub use useless_import_alias::{useless_import_alias, UselessImportAlias};
 
 mod await_outside_async;
 mod bad_str_strip_call;
+mod bidirectional_unicode;
 mod comparison_of_constant;
 mod consider_using_sys_exit;
 mod global_variable_not_assigned;

crates/ruff/src/rules/pylint/snapshots/ruff__rules__pylint__tests__PLE2402_bidirectional_unicode.py.snap

@@ -0,0 +1,55 @@
+---
+source: src/rules/pylint/mod.rs
+expression: diagnostics
+---
+- kind:
+    BidirectionalUnicode: ~
+  location:
+    row: 2
+    column: 6
+  end_location:
+    row: 2
+    column: 50
+  fix: ~
+  parent: ~
+- kind:
+    BidirectionalUnicode: ~
+  location:
+    row: 3
+    column: 6
+  end_location:
+    row: 3
+    column: 13
+  fix: ~
+  parent: ~
+- kind:
+    BidirectionalUnicode: ~
+  location:
+    row: 5
+    column: 10
+  end_location:
+    row: 5
+    column: 14
+  fix: ~
+  parent: ~
+- kind:
+    BidirectionalUnicode: ~
+  location:
+    row: 7
+    column: 19
+  end_location:
+    row: 7
+    column: 27
+  fix: ~
+  parent: ~
+- kind:
+    BidirectionalUnicode: ~
+  location:
+    row: 11
+    column: 4
+  end_location:
+    row: 11
+    column: 49
+  fix: ~
+  parent: ~
+

crates/ruff/src/rules/pylint/snapshots/ruff__rules__pylint__tests__PLE2502_bidirectional_unicode.py.snap

@@ -0,0 +1,55 @@
+---
+source: crates/ruff/src/rules/pylint/mod.rs
+expression: diagnostics
+---
+- kind:
+    BidirectionalUnicode: ~
+  location:
+    row: 2
+    column: 6
+  end_location:
+    row: 2
+    column: 50
+  fix: ~
+  parent: ~
+- kind:
+    BidirectionalUnicode: ~
+  location:
+    row: 5
+    column: 6
+  end_location:
+    row: 5
+    column: 13
+  fix: ~
+  parent: ~
+- kind:
+    BidirectionalUnicode: ~
+  location:
+    row: 8
+    column: 10
+  end_location:
+    row: 8
+    column: 14
+  fix: ~
+  parent: ~
+- kind:
+    BidirectionalUnicode: ~
+  location:
+    row: 11
+    column: 19
+  end_location:
+    row: 11
+    column: 27
+  fix: ~
+  parent: ~
+- kind:
+    BidirectionalUnicode: ~
+  location:
+    row: 17
+    column: 4
+  end_location:
+    row: 17
+    column: 49
+  fix: ~
+  parent: ~
+