repl: Handle unicode escape sequence

nodejs · Mar 19, 2016 · 9a9c021 · 9a9c021
1 parent 0eb3ed5
commit 9a9c021
Show file tree

Hide file tree

Showing 2 changed files with 102 additions and 0 deletions.
diff --git a/lib/repl.js b/lib/repl.js
@@ -73,6 +73,46 @@ exports._builtinLibs = ['assert', 'buffer', 'child_process', 'cluster',
 const BLOCK_SCOPED_ERROR = 'Block-scoped declarations (let, ' +
     'const, function, class) not yet supported outside strict mode';
 
+class LiteralPattern {
+
+  constructor(prefix, suffixOrMaxLength) {
+    this._prefix = prefix;
+    this._prefixLength = prefix.length;
+    if (typeof suffixOrMaxLength === 'string') {
+      this._suffix = suffixOrMaxLength;
+      this._suffixLength = suffixOrMaxLength.length;
+    } else {
+      this._maxLength = suffixOrMaxLength;
+    }
+    this.lastIndex = 0;
+  }
+
+  exec(input) {
+    input = input.substring(this.lastIndex);
+    const idx = input.indexOf(this._prefix);
+    if (idx !== -1) {
+      const start = this._prefixLength + idx;
+      if (this._suffix) {
+        input = input.substring(start);
+        const end = input.indexOf(this._suffix);
+        if (end !== -1) {
+          this.lastIndex += start + end + this._suffixLength;
+          return input.substring(0, end);
+        }
+      } else {
+        this.lastIndex += start + this._maxLength;
+        return input.substring(this._prefixLength + idx, this._maxLength);
+      }
+    }
+    this.lastIndex = 0;
+    return null;
+  }
+}
+
+const unicodePointLikePattern = new LiteralPattern('\\u{', '}');
+const unicodeLikePattern = new LiteralPattern('\\u', 4);
+const hexLikePattern = new LiteralPattern('\\x', 2);
+const hexPattern = /^[\da-f]+$/i;
 
 class LineParser {
 
@@ -82,17 +122,59 @@ class LineParser {
 
   reset() {
     this._literal = null;
+    this._literalValue = [];
     this.shouldFail = false;
     this.blockComment = false;
     this.regExpLiteral = false;
   }
 
+  parseEscapePattern(literal, pattern, predicate) {
+    let codePoint;
+    while ((codePoint = pattern.exec(literal)) !== null) {
+      if (!predicate(codePoint)) {
+        pattern.lastIndex = 0;
+        return false;
+      }
+    }
+    return true;
+  }
+
+  parseHexSequencePredicate(codePoint) {
+    return codePoint.length === 2 && hexPattern.test(codePoint);
+  }
+
+  parseUnicodePredicate(codePoint) {
+    return codePoint.length === 4 && hexPattern.test(codePoint);
+  }
+
+  parseUnicodePointPredicate(codePoint) {
+    return hexPattern.test(codePoint) && parseInt(codePoint, 16) <= 0x10FFFF;
+  }
+
+  parseEscapeSequence(literal) {
+    return this.parseEscapePattern(literal,
+                                   unicodePointLikePattern,
+                                   this.parseUnicodePointPredicate) &&
+           this.parseEscapePattern(literal,
+                                   unicodeLikePattern,
+                                   this.parseUnicodePredicate) &&
+           this.parseEscapePattern(literal,
+                                   hexLikePattern,
+                                   this.parseHexSequencePredicate);
+  }
+
   parseLine(line) {
     var previous = null;
     this.shouldFail = false;
     const wasWithinStrLiteral = this._literal !== null;
+    if (this._literal) {
+      this._literalValue.push('\n');
+    }
 
     for (const current of line) {
+      if (this._literal && current !== this._literal) {
+        this._literalValue.push(current);
+      }
       if (previous === '\\') {
         // valid escaping, skip processing. previous doesn't matter anymore
         previous = null;
@@ -135,6 +217,13 @@ class LineParser {
 
       if (current === this._literal) {
         this._literal = null;
+        const literal = this._literalValue.join('');
+        this._literalValue = [];
+
+        if (!this.parseEscapeSequence(literal)) {
+          this.shouldFail = true;
+          break;
+        }
       } else if (current === '\'' || current === '"') {
         this._literal = this._literal || current;
       }

diff --git a/test/parallel/test-repl.js b/test/parallel/test-repl.js
@@ -325,6 +325,19 @@ function error_test() {
             'undefined\n' + prompt_unix },
     { client: client_unix, send: '{ var x = 4; }',
       expect: 'undefined\n' + prompt_unix },
+    // REPL should handle invalid escape sequences
+    { client: client_unix, send: "'unicode point \\u{0000000041}'",
+      expect: "'unicode point A'\n" + prompt_unix },
+    { client: client_unix, send: "'unicode \u0041'",
+      expect: "'unicode A'\n" + prompt_unix },
+    { client: client_unix, send: "'hexadecimal \x41'",
+      expect: "'hexadecimal A'\n" + prompt_unix },
+    { client: client_unix, send: "'\\u{10000000041} failure case'",
+      expect: /^SyntaxError: Unexpected token ILLEGAL/ },
+    { client: client_unix, send: "'\\uea failure case'",
+      expect: /^SyntaxError: Unexpected token ILLEGAL/ },
+    { client: client_unix, send: "'\\x1 edge case'",
+      expect: /^SyntaxError: Unexpected token ILLEGAL/ },
   ]);
 }