Changeset 29075 in webkit for trunk/JavaScriptCore/kjs/lexer.cpp

Timestamp:

Jan 1, 2008, 10:44:22 PM (17 years ago)

Author:

Darin Adler

Message:

JavaScriptCore:

Reviewed by Eric.

• fix for ​http://bugs.webkit.org/show_bug.cgi?id=16695 JSC allows non-identifier codepoints in identifiers (affects Acid3)

Test: fast/js/kde/parse.html

• kjs/lexer.cpp: (KJS::Lexer::lex): Added additional states to distinguish Unicode escapes at the start of identifiers from ones inside identifiers. Rejected characters that don't pass the isIdentStart and isIdentPart tests. (KJS::Lexer::convertUnicode): Removed incorrect FIXME comment.

• kjs/lexer.h: Added new states to distinguish \u escapes at the start of identifiers from \u escapes inside identifiers.

LayoutTests:

Reviewed by Eric.

• test for ​http://bugs.webkit.org/show_bug.cgi?id=16695 JSC allows non-identifier codepoints in identifiers (affects Acid3)

• fast/js/kde/parse-expected.txt: Updated.
• fast/js/kde/resources/parse.js: Added tests that cover both the non-ASCII characters themselves and the same characters parsed as \u sequences.

File:

• trunk/JavaScriptCore/kjs/lexer.cpp (modified) (4 diffs)

trunk/JavaScriptCore/kjs/lexer.cpp

@@ -213 +213 @@
         state = InIdentifierOrKeyword;
       } else if (current == '\\') {
-        state = InIdentifierUnicodeEscapeStart;
+        state = InIdentifierStartUnicodeEscapeStart;
       } else if (current == '0') {
         record8(current);
@@ -342 +342 @@
         record16(current);
       else if (current == '\\')
-        state = InIdentifierUnicodeEscapeStart;
+        state = InIdentifierPartUnicodeEscapeStart;
       else
         setDone(state == InIdentifierOrKeyword ? IdentifierOrKeyword : Identifier);
@@ -419 +419 @@
         setDone(Number);
       break;
-    case InIdentifierUnicodeEscapeStart:
+    case InIdentifierStartUnicodeEscapeStart:
       if (current == 'u')
-        state = InIdentifierUnicodeEscape;
+        state = InIdentifierStartUnicodeEscape;
       else
         setDone(Bad);
       break;
-    case InIdentifierUnicodeEscape:
-      if (isHexDigit(current) && isHexDigit(next1) && isHexDigit(next2) && isHexDigit(next3)) {
-        record16(convertUnicode(current, next1, next2, next3));
-        shift(3);
-        state = InIdentifier;
-      } else {
+    case InIdentifierPartUnicodeEscapeStart:
+      if (current == 'u')
+        state = InIdentifierPartUnicodeEscape;
+      else
         setDone(Bad);
-      }
+      break;
+    case InIdentifierStartUnicodeEscape:
+      if (!isHexDigit(current) || !isHexDigit(next1) || !isHexDigit(next2) || !isHexDigit(next3)) {
+        setDone(Bad);
+        break;
+      }
+      token = convertUnicode(current, next1, next2, next3).uc;
+      shift(3);
+      if (!isIdentStart(token)) {
+        setDone(Bad);
+        break;
+      }
+      record16(token);
+      state = InIdentifier;
+      break;
+    case InIdentifierPartUnicodeEscape:
+      if (!isHexDigit(current) || !isHexDigit(next1) || !isHexDigit(next2) || !isHexDigit(next3)) {
+        setDone(Bad);
+        break;
+      }
+      token = convertUnicode(current, next1, next2, next3).uc;
+      shift(3);
+      if (!isIdentPart(token)) {
+        setDone(Bad);
+        break;
+      }
+      record16(token);
+      state = InIdentifier;
       break;
     default:
@@ -780 +805 @@
 KJS::UChar Lexer::convertUnicode(int c1, int c2, int c3, int c4)
 {
-  // FIXME: This conversion is lossy. See http://bugs.webkit.org/show_bug.cgi?id=4920.
   return KJS::UChar((convertHex(c1) << 4) + convertHex(c2),
                (convertHex(c3) << 4) + convertHex(c4));