feat: no-empty-character-class support v flag (#17419)

Reports nested character classes Refs #17223
eslint · Jul 27, 2023 · ee68d1d · ee68d1d
1 parent 853d32b
commit ee68d1d
Show file tree

Hide file tree

Showing 3 changed files with 75 additions and 14 deletions.
diff --git a/docs/src/rules/no-empty-character-class.md b/docs/src/rules/no-empty-character-class.md
@@ -24,6 +24,23 @@ Examples of **incorrect** code for this rule:
 
 /^abc[]/.test("abcdefg"); // false
 "abcdefg".match(/^abc[]/); // null
+
+/^abc[[]]/v.test("abcdefg"); // false
+"abcdefg".match(/^abc[[]]/v); // null
+
+/^abc[[]--[x]]/v.test("abcdefg"); // false
+"abcdefg".match(/^abc[[]--[x]]/v); // null
+
+/^abc[[d]&&[]]/v.test("abcdefg"); // false
+"abcdefg".match(/^abc[[d]&&[]]/v); // null
+
+const regex = /^abc[d[]]/v;
+regex.test("abcdefg"); // true, the nested `[]` has no effect
+"abcdefg".match(regex); // ["abcd"]
+regex.test("abcefg"); // false, the nested `[]` has no effect
+"abcefg".match(regex); // null
+regex.test("abc"); // false, the nested `[]` has no effect
+"abc".match(regex); // null
 ```
 
 :::
@@ -40,6 +57,9 @@ Examples of **correct** code for this rule:
 
 /^abc[a-z]/.test("abcdefg"); // true
 "abcdefg".match(/^abc[a-z]/); // ["abcd"]
+
+/^abc[^]/.test("abcdefg"); // true
+"abcdefg".match(/^abc[^]/); // ["abcd"]
 ```
 
 :::

diff --git a/lib/rules/no-empty-character-class.js b/lib/rules/no-empty-character-class.js
@@ -5,20 +5,18 @@
 
 "use strict";
 
+//------------------------------------------------------------------------------
+// Requirements
+//------------------------------------------------------------------------------
+
+const { RegExpParser, visitRegExpAST } = require("@eslint-community/regexpp");
+
 //------------------------------------------------------------------------------
 // Helpers
 //------------------------------------------------------------------------------
 
-/*
- * plain-English description of the following regexp:
- * 0. `^` fix the match at the beginning of the string
- * 1. `([^\\[]|\\.|\[([^\\\]]|\\.)+\])*`: regexp contents; 0 or more of the following
- * 1.0. `[^\\[]`: any character that's not a `\` or a `[` (anything but escape sequences and character classes)
- * 1.1. `\\.`: an escape sequence
- * 1.2. `\[([^\\\]]|\\.)+\]`: a character class that isn't empty
- * 2. `$`: fix the match at the end of the string
- */
-const regex = /^([^\\[]|\\.|\[([^\\\]]|\\.)+\])*$/u;
+const parser = new RegExpParser();
+const QUICK_TEST_REGEX = /\[\]/u;
 
 //------------------------------------------------------------------------------
 // Rule Definition
@@ -45,9 +43,32 @@ module.exports = {
     create(context) {
         return {
             "Literal[regex]"(node) {
-                if (!regex.test(node.regex.pattern)) {
-                    context.report({ node, messageId: "unexpected" });
+                const { pattern, flags } = node.regex;
+
+                if (!QUICK_TEST_REGEX.test(pattern)) {
+                    return;
                 }
+
+                let regExpAST;
+
+                try {
+                    regExpAST = parser.parsePattern(pattern, 0, pattern.length, {
+                        unicode: flags.includes("u"),
+                        unicodeSets: flags.includes("v")
+                    });
+                } catch {
+
+                    // Ignore regular expressions that regexpp cannot parse
+                    return;
+                }
+
+                visitRegExpAST(regExpAST, {
+                    onCharacterClassEnter(characterClass) {
+                        if (!characterClass.negate && characterClass.elements.length === 0) {
+                            context.report({ node, messageId: "unexpected" });
+                        }
+                    }
+                });
             }
         };
 

diff --git a/tests/lib/rules/no-empty-character-class.js b/tests/lib/rules/no-empty-character-class.js
@@ -25,15 +25,26 @@ ruleTester.run("no-empty-character-class", rule, {
         "var foo = /^abc/;",
         "var foo = /[\\[]/;",
         "var foo = /[\\]]/;",
+        "var foo = /\\[][\\]]/;",
         "var foo = /[a-zA-Z\\[]/;",
         "var foo = /[[]/;",
         "var foo = /[\\[a-z[]]/;",
         "var foo = /[\\-\\[\\]\\/\\{\\}\\(\\)\\*\\+\\?\\.\\\\^\\$\\|]/g;",
         "var foo = /\\s*:\\s*/gim;",
+        "var foo = /[^]/;", // this rule allows negated empty character classes
+        "var foo = /\\[][^]/;",
         { code: "var foo = /[\\]]/uy;", parserOptions: { ecmaVersion: 6 } },
         { code: "var foo = /[\\]]/s;", parserOptions: { ecmaVersion: 2018 } },
         { code: "var foo = /[\\]]/d;", parserOptions: { ecmaVersion: 2022 } },
-        "var foo = /\\[]/"
+        "var foo = /\\[]/",
+        { code: "var foo = /[[^]]/v;", parserOptions: { ecmaVersion: 2024 } },
+        { code: "var foo = /[[\\]]]/v;", parserOptions: { ecmaVersion: 2024 } },
+        { code: "var foo = /[[\\[]]/v;", parserOptions: { ecmaVersion: 2024 } },
+        { code: "var foo = /[a--b]/v;", parserOptions: { ecmaVersion: 2024 } },
+        { code: "var foo = /[a&&b]/v;", parserOptions: { ecmaVersion: 2024 } },
+        { code: "var foo = /[[a][b]]/v;", parserOptions: { ecmaVersion: 2024 } },
+        { code: "var foo = /[\\q{}]/v;", parserOptions: { ecmaVersion: 2024 } },
+        { code: "var foo = /[[^]--\\p{ASCII}]/v;", parserOptions: { ecmaVersion: 2024 } }
     ],
     invalid: [
         { code: "var foo = /^abc[]/;", errors: [{ messageId: "unexpected", type: "Literal" }] },
@@ -43,6 +54,15 @@ ruleTester.run("no-empty-character-class", rule, {
         { code: "var foo = /[]]/;", errors: [{ messageId: "unexpected", type: "Literal" }] },
         { code: "var foo = /\\[[]/;", errors: [{ messageId: "unexpected", type: "Literal" }] },
         { code: "var foo = /\\[\\[\\]a-z[]/;", errors: [{ messageId: "unexpected", type: "Literal" }] },
-        { code: "var foo = /[]]/d;", parserOptions: { ecmaVersion: 2022 }, errors: [{ messageId: "unexpected", type: "Literal" }] }
+        { code: "var foo = /[]]/d;", parserOptions: { ecmaVersion: 2022 }, errors: [{ messageId: "unexpected", type: "Literal" }] },
+        { code: "var foo = /[(]\\u{0}*[]/u;", parserOptions: { ecmaVersion: 2015 }, errors: [{ messageId: "unexpected", type: "Literal" }] },
+        { code: "var foo = /[]/v;", parserOptions: { ecmaVersion: 2024 }, errors: [{ messageId: "unexpected", type: "Literal" }] },
+        { code: "var foo = /[[]]/v;", parserOptions: { ecmaVersion: 2024 }, errors: [{ messageId: "unexpected", type: "Literal" }] },
+        { code: "var foo = /[[a][]]/v;", parserOptions: { ecmaVersion: 2024 }, errors: [{ messageId: "unexpected", type: "Literal" }] },
+        { code: "var foo = /[a[[b[]c]]d]/v;", parserOptions: { ecmaVersion: 2024 }, errors: [{ messageId: "unexpected", type: "Literal" }] },
+        { code: "var foo = /[a--[]]/v;", parserOptions: { ecmaVersion: 2024 }, errors: [{ messageId: "unexpected", type: "Literal" }] },
+        { code: "var foo = /[[]--b]/v;", parserOptions: { ecmaVersion: 2024 }, errors: [{ messageId: "unexpected", type: "Literal" }] },
+        { code: "var foo = /[a&&[]]/v;", parserOptions: { ecmaVersion: 2024 }, errors: [{ messageId: "unexpected", type: "Literal" }] },
+        { code: "var foo = /[[]&&b]/v;", parserOptions: { ecmaVersion: 2024 }, errors: [{ messageId: "unexpected", type: "Literal" }] }
     ]
 });