Changeset 10933 in webkit for trunk/JavaScriptCore/kjs

Timestamp:

Oct 24, 2005, 2:22:21 PM (20 years ago)

Author:

sullivan

Message:

Reviewed by Darin Adler. Code changes by Alexey Proskuryakov.

• fixed ​http://bugzilla.opendarwin.org/show_bug.cgi?id=4931 Unicode format characters (Cf) should be removed from JavaScript source

• kjs/lexer.cpp: include <unicode/uchar.h> (Lexer::Lexer): use KJS::UChar instead of UChar to avoid ambiguity caused by new include (Lexer::setCode): ditto; also, use shift(4) to skip first 4 chars to take advantage of new logic there. (Lexer::shift): skip chars of type U_FORMAT_CHAR (Lexer::convertUnicode): use KJS::UChar instead of UChar to avoid ambiguity caused by new include (Lexer::record16): ditto (Lexer::makeIdentifier): ditto (Lexer::makeUString): ditto

• tests/mozilla/ecma/Array/15.4.5.1-1.js: updated to skip soft hyphens

File:

• trunk/JavaScriptCore/kjs/lexer.cpp (modified) (9 diffs)

trunk/JavaScriptCore/kjs/lexer.cpp

@@ -40 +40 @@
 #include "lookup.h"
 #include "internal.h"
+#include <unicode/uchar.h>
 
 // we can't specify the namespace in yacc's C output, so do it here
@@ -74 +75 @@
   // allocate space for read buffers
   buffer8 = new char[size8];
-  buffer16 = new UChar[size16];
+  buffer16 = new KJS::UChar[size16];
   currLexer = this;
 }
@@ -102 +103 @@
 #endif
 
-void Lexer::setCode(const UString &sourceURL, int startingLineNumber, const UChar *c, unsigned int len)
+void Lexer::setCode(const UString &sourceURL, int startingLineNumber, const KJS::UChar *c, unsigned int len)
 {
   yylineno = 1 + startingLineNumber;
@@ -122 +123 @@
 
   // read first characters
-  current = (length > 0) ? code[0].uc : 0;
-  next1 = (length > 1) ? code[1].uc : 0;
-  next2 = (length > 2) ? code[2].uc : 0;
-  next3 = (length > 3) ? code[3].uc : 0;
+  shift(4);
 }
 
@@ -131 +129 @@
 {
   while (p--) {
-    pos++;
     current = next1;
     next1 = next2;
     next2 = next3;
-    next3 = (pos + 3 < length) ? code[pos+3].uc : 0;
+    do {
+      if (pos >= length) {
+        next3 = 0;
+        break;
+      }
+      next3 = code[pos++].uc;
+    } while (u_charType(next3) == U_FORMAT_CHAR);
   }
 }
@@ -752 +755 @@
 }
 
-UChar Lexer::convertUnicode(unsigned short c1, unsigned short c2,
+KJS::UChar Lexer::convertUnicode(unsigned short c1, unsigned short c2,
                                      unsigned short c3, unsigned short c4)
 {
-  return UChar((convertHex(c1) << 4) + convertHex(c2),
+  return KJS::UChar((convertHex(c1) << 4) + convertHex(c2),
                (convertHex(c3) << 4) + convertHex(c4));
 }
@@ -775 +778 @@
 }
 
-void Lexer::record16(UChar c)
+void Lexer::record16(KJS::UChar c)
 {
   // enlarge buffer if full
   if (pos16 >= size16 - 1) {
-    UChar *tmp = new UChar[2 * size16];
-    memcpy(tmp, buffer16, size16 * sizeof(UChar));
+    KJS::UChar *tmp = new KJS::UChar[2 * size16];
+    memcpy(tmp, buffer16, size16 * sizeof(KJS::UChar));
     delete [] buffer16;
     buffer16 = tmp;
@@ -852 +855 @@
 const int growthFactor = 2;
 
-Identifier *Lexer::makeIdentifier(UChar *buffer, unsigned int pos)
+Identifier *Lexer::makeIdentifier(KJS::UChar *buffer, unsigned int pos)
 {
   if (numIdentifiers == identifiersCapacity) {
@@ -864 +867 @@
 }
  
-UString *Lexer::makeUString(UChar *buffer, unsigned int pos)
+UString *Lexer::makeUString(KJS::UChar *buffer, unsigned int pos)
 {
   if (numStrings == stringsCapacity) {