Reviewed and landed by Darin

        Get rid of some misuses of |islower| and |tolower| for non-ASCII characters.
        http://bugs.webkit.org/show_bug.cgi?id=13138

        * platform/StringImpl.cpp:
        (WebCore::StringImpl::isLower):
        (WebCore::StringImpl::lower):
        (WebCore::StringImpl::equalIgnoringCase):

git-svn-id: https://svn.webkit.org/repository/webkit/trunk@20559 268f45cc-cd09-0410-ab3c-d52691b4dbfc

diff --git a/WebCore/ChangeLog b/WebCore/ChangeLog
index 1755c0b672ea2c91ffb089c6f3e8629b1d0e6e01..ac30131e7bf299a98ee16e62f4d13963541562c5 100644 (file)
--- a/WebCore/ChangeLog
+++ b/WebCore/ChangeLog
@@ -1,3 +1,15 @@
+2007-03-28  Jungshik Shin  <jungshik.shin@gmail.com>
+
+        Reviewed  and landed by Darin
+
+        Get rid of some misuses of |islower| and |tolower| for non-ASCII characters.
+        http://bugs.webkit.org/show_bug.cgi?id=13138
+
+        * platform/StringImpl.cpp:
+        (WebCore::StringImpl::isLower):
+        (WebCore::StringImpl::lower):
+        (WebCore::StringImpl::equalIgnoringCase):
+
 2007-03-28  Antti Koivisto  <antti@apple.com>
 
         Reviewed by Hyatt.

diff --git a/WebCore/platform/StringImpl.cpp b/WebCore/platform/StringImpl.cpp
index 6ecd1cddf0564018cdbe11394f6fddaf664d2fce..a80bbb5450c4305fe38d7def041115f1d7913103 100644 (file)
--- a/WebCore/platform/StringImpl.cpp
+++ b/WebCore/platform/StringImpl.cpp
@@ -1,6 +1,4 @@
 /**
- * This file is part of the DOM implementation for KDE.
- *
  * Copyright (C) 1999 Lars Knoll (knoll@kde.org)
  *           (C) 1999 Antti Koivisto (koivisto@kde.org)
  *           (C) 2001 Dirk Mueller ( mueller@kde.org )
@@ -390,13 +388,17 @@ bool StringImpl::isLower() const
     UChar ored = 0;
     for (unsigned i = 0; i < m_length; i++) {
         UChar c = m_data[i];
-        allLower &= islower(c);
+        // The islower function is only guaranteed to work correctly and 
+        // locale-independently for ASCII characters.
+        allLower &= islower(c & 0x7F);
         ored |= c;
     }
     if (!(ored & ~0x7F))
         return allLower;
 
     // Do a slower check for the other cases.
+    // FIXME : still broken for non-BMP characters 
+    // (e.g. Deseret and Mathematical alphanumeric symbols)
     bool allLower2 = true;
     for (unsigned i = 0; i < m_length; i++)
         allLower2 &= Unicode::isLower(m_data[i]);
@@ -420,7 +422,10 @@ StringImpl* StringImpl::lower() const
     for (int i = 0; i < length; i++) {
         UChar c = m_data[i];
         ored |= c;
-        data[i] = tolower(c);
+        // The tolower function is only guaranteed to work correctly and 
+        // locale-independently for ASCII characters. If it's not all ASCII,
+        // we'll take a slower but correct path after the loop.
+        data[i] = tolower(c & 0x7F);
     }
     if (!(ored & ~0x7F))
         return c;
@@ -1036,7 +1041,10 @@ bool equalIgnoringCase(const StringImpl* a, const char* b)
             return false;
         UChar ac = as[i];
         ored |= ac;
-        equal &= tolower(ac) == tolower(bc);
+        // The tolower function is only guaranteed to work correctly and 
+        // locale-independently for ASCII characters. If it's not all ASCII,
+        // we'll take a slower but correct path after the loop.
+        equal &= tolower(ac & 0x7F) == tolower(bc);
     }
 
     if (ored & ~0x7F) {