[`pylint`] Fix unicode handling in `PLE2515` (#3898)

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

@@ -184,16 +184,20 @@ pub fn invalid_string_characters(
     let text = locator.slice(Range::new(start, end));
 
     for (row, line) in UniversalNewlineIterator::from(text).enumerate() {
-        for (column, match_) in line.match_indices(&['\x08', '\x1A', '\x1B', '\0', '\u{200b}']) {
+        let mut char_offset = 0;
-            let (replacement, rule): (&str, DiagnosticKind) = match match_.chars().next().unwrap() {
+        for char in line.chars() {
+            let (replacement, rule): (&str, DiagnosticKind) = match char {
                 '\x08' => ("\\b", InvalidCharacterBackspace.into()),
                 '\x1A' => ("\\x1A", InvalidCharacterSub.into()),
                 '\x1B' => ("\\x1B", InvalidCharacterEsc.into()),
                 '\0' => ("\\0", InvalidCharacterNul.into()),
                 '\u{200b}' => ("\\u200b", InvalidCharacterZeroWidthSpace.into()),
-                _ => unreachable!(),
+                _ => {
+                    char_offset += 1;
+                    continue;
+                }
             };
-            let location = helpers::to_absolute(Location::new(row + 1, column), start);
+            let location = helpers::to_absolute(Location::new(row + 1, char_offset), start);
             let end_location = Location::new(location.row(), location.column() + 1);
             let mut diagnostic = Diagnostic::new(rule, Range::new(location, end_location));
             if autofix {
@@ -204,6 +208,7 @@ pub fn invalid_string_characters(
                 ));
             }
             diagnostics.push(diagnostic);
+            char_offset += 1;
         }
     }
 

crates/ruff/src/rules/pylint/snapshots/ruff__rules__pylint__tests__PLE2515_invalid_characters.py.snap

@@ -23,4 +23,67 @@ expression: diagnostics
           row: 34
           column: 13
   parent: ~
+- kind:
+    name: InvalidCharacterZeroWidthSpace
+    body: "Invalid unescaped character zero-width-space, use \"\\u200B\" instead"
+    suggestion: Replace with escape sequence
+    fixable: true
+  location:
+    row: 38
+    column: 35
+  end_location:
+    row: 38
+    column: 36
+  fix:
+    edits:
+      - content: "\\u200b"
+        location:
+          row: 38
+          column: 35
+        end_location:
+          row: 38
+          column: 36
+  parent: ~
+- kind:
+    name: InvalidCharacterZeroWidthSpace
+    body: "Invalid unescaped character zero-width-space, use \"\\u200B\" instead"
+    suggestion: Replace with escape sequence
+    fixable: true
+  location:
+    row: 39
+    column: 59
+  end_location:
+    row: 39
+    column: 60
+  fix:
+    edits:
+      - content: "\\u200b"
+        location:
+          row: 39
+          column: 59
+        end_location:
+          row: 39
+          column: 60
+  parent: ~
+- kind:
+    name: InvalidCharacterZeroWidthSpace
+    body: "Invalid unescaped character zero-width-space, use \"\\u200B\" instead"
+    suggestion: Replace with escape sequence
+    fixable: true
+  location:
+    row: 39
+    column: 60
+  end_location:
+    row: 39
+    column: 61
+  fix:
+    edits:
+      - content: "\\u200b"
+        location:
+          row: 39
+          column: 60
+        end_location:
+          row: 39
+          column: 61
+  parent: ~