bool TextEncoding::isUTF7Encoding() const
{
if (noExtendedTextEncodingNameUsed())
return false;
return *this == UTF7Encoding();
}
bool TextEncoding::usesVisualOrdering() const
{
if (noExtendedTextEncodingNameUsed())
return false;
static const char* const a = atomicCanonicalTextEncodingName("ISO-8859-8");
return m_name == a;
}
UChar TextEncoding::backslashAsCurrencySymbol() const
{
if (noExtendedTextEncodingNameUsed())
return '\\';
// The text encodings below treat backslash as a currency symbol.
// See http://blogs.msdn.com/michkap/archive/2005/09/17/469941.aspx for more information.
static const char* const a = atomicCanonicalTextEncodingName("Shift_JIS_X0213-2000");
static const char* const b = atomicCanonicalTextEncodingName("EUC-JP");
return (m_name == a || m_name == b) ? 0x00A5 : '\\';
}
bool TextEncoding::isNonByteBasedEncoding() const
{
if (noExtendedTextEncodingNameUsed()) {
return *this == UTF16LittleEndianEncoding()
|| *this == UTF16BigEndianEncoding();
}
return *this == UTF16LittleEndianEncoding()
|| *this == UTF16BigEndianEncoding()
|| *this == UTF32BigEndianEncoding()
|| *this == UTF32LittleEndianEncoding();
}
const char* TextEncoding::domName() const
{
if (noExtendedTextEncodingNameUsed())
return m_name;
// We treat EUC-KR as windows-949 (its superset), but need to expose
// the name 'EUC-KR' because the name 'windows-949' is not recognized by
// most Korean web servers even though they do use the encoding
// 'windows-949' with the name 'EUC-KR'.
// FIXME: This is not thread-safe. At the moment, this function is
// only accessed in a single thread, but eventually has to be made
// thread-safe along with usesVisualOrdering().
static const char* const a = atomicCanonicalTextEncodingName("windows-949");
if (m_name == a)
return "EUC-KR";
return m_name;
}
bool TextEncoding::isJapanese() const
{
if (noExtendedTextEncodingNameUsed())
return false;
static HashSet<const char*> set;
if (set.isEmpty()) {
addEncodingName(set, "x-mac-japanese");
addEncodingName(set, "cp932");
addEncodingName(set, "JIS_X0201");
addEncodingName(set, "JIS_X0208-1983");
addEncodingName(set, "JIS_X0208-1990");
addEncodingName(set, "JIS_X0212-1990");
addEncodingName(set, "JIS_C6226-1978");
addEncodingName(set, "Shift_JIS_X0213-2000");
addEncodingName(set, "ISO-2022-JP");
addEncodingName(set, "ISO-2022-JP-2");
addEncodingName(set, "ISO-2022-JP-1");
addEncodingName(set, "ISO-2022-JP-3");
addEncodingName(set, "EUC-JP");
addEncodingName(set, "Shift_JIS");
}
return m_name && set.contains(m_name);
}
