tools: non-Ascii linter for /lib only

Non-ASCII characters in /lib get compiled into the node binary,
and may bloat the binary size unnecessarily. A linter rule may
help prevent this.

PR-URL: #18043
Fixes: #11209
Reviewed-By: Anna Henningsen <anna@addaleax.net>
Reviewed-By: Ruben Bridgewater <ruben@bridgewater.de>
Reviewed-By: Teddy Katz <teddy.katz@gmail.com>

lib/.eslintrc.yaml

@@ -6,3 +6,4 @@ rules:
   buffer-constructor: error
   no-let-in-for-declaration: error
   lowercase-name-for-primitive: error
+  non-ascii-character: error

lib/internal/process.js

@@ -150,7 +150,7 @@ function setupConfig(_source) {
     };
     Object.defineProperty(Intl, 'v8BreakIterator', des);
   }
-  // Don’t let icu_data_dir leak through.
+  // Don't let icu_data_dir leak through.
   delete process.icu_data_dir;
 }
 

lib/repl.js

@@ -324,7 +324,7 @@ function REPLServer(prompt,
       let previouslyInRawMode;
       if (self.breakEvalOnSigint) {
         // Start the SIGINT watchdog before entering raw mode so that a very
-        // quick Ctrl+C doesn’t lead to aborting the process completely.
+        // quick Ctrl+C doesn't lead to aborting the process completely.
         utilBinding.startSigintWatchdog();
         previouslyInRawMode = self._setRawMode(false);
       }

lib/timers.js

@@ -43,6 +43,7 @@ const TIMEOUT_MAX = 2147483647; // 2^31-1
 // TimerWrap C++ handle, which makes the call after the duration to process the
 // list it is attached to.
 //
+/* eslint-disable non-ascii-character */
 //
 // ╔════ > Object Map
 // ║
@@ -64,6 +65,7 @@ const TIMEOUT_MAX = 2147483647; // 2^31-1
 // ║
 // ╚════ > Linked List
 //
+/* eslint-enable non-ascii-character */
 //
 // With this, virtually constant-time insertion (append), removal, and timeout
 // is possible in the JavaScript layer. Any one list of timers is able to be

tools/eslint-rules/non-ascii-character.js

@@ -0,0 +1,61 @@
+/**
+ * @fileOverview Any non-ASCII characters in lib/ will increase the size
+ *               of the compiled node binary. This linter rule ensures that
+ *               any such character is reported.
+ * @author Sarat Addepalli <sarat.addepalli@gmail.com>
+ */
+
+'use strict';
+
+//------------------------------------------------------------------------------
+// Rule Definition
+//------------------------------------------------------------------------------
+
+const nonAsciiRegexPattern = /[^\r\n\x20-\x7e]/;
+const suggestions = {
+  '’': '\'',
+  '‛': '\'',
+  '‘': '\'',
+  '“': '"',
+  '‟': '"',
+  '”': '"',
+  '«': '"',
+  '»': '"',
+  '—': '-'
+};
+
+module.exports = (context) => {
+
+  const reportIfError = (node, sourceCode) => {
+
+    const matches = sourceCode.text.match(nonAsciiRegexPattern);
+
+    if (!matches) return;
+
+    const offendingCharacter = matches[0];
+    const offendingCharacterPosition = matches.index;
+    const suggestion = suggestions[offendingCharacter];
+
+    let message = `Non-ASCII character '${offendingCharacter}' detected.`;
+
+    message = suggestion ?
+      `${message} Consider replacing with: ${suggestion}` :
+      message;
+
+    context.report({
+      node,
+      message,
+      loc: sourceCode.getLocFromIndex(offendingCharacterPosition),
+      fix: (fixer) => {
+        return fixer.replaceText(
+          node,
+          suggestion ? `${suggestion}` : ''
+        );
+      }
+    });
+  };
+
+  return {
+    Program: (node) => reportIfError(node, context.getSourceCode())
+  };
+};