#include "config.h"
#include "TextEncoding.h"
#include "DecodeEscapeSequences.h"
#include "TextCodec.h"
#include "TextEncodingRegistry.h"
#include <wtf/NeverDestroyed.h>
#include <wtf/StdLibExtras.h>
#include <wtf/text/StringView.h>
namespace WebCore {
static const TextEncoding& UTF7Encoding()
{
static NeverDestroyed<TextEncoding> globalUTF7Encoding("UTF-7");
return globalUTF7Encoding;
}
TextEncoding::TextEncoding(const char* name)
: m_name(atomCanonicalTextEncodingName(name))
, m_backslashAsCurrencySymbol(backslashAsCurrencySymbol())
{
if (equalLettersIgnoringASCIICase(name, "replacement"))
m_name = nullptr;
}
TextEncoding::TextEncoding(const String& name)
: m_name(atomCanonicalTextEncodingName(name))
, m_backslashAsCurrencySymbol(backslashAsCurrencySymbol())
{
if (equalLettersIgnoringASCIICase(name, "replacement"))
m_name = nullptr;
}
String TextEncoding::decode(const char* data, size_t length, bool stopOnError, bool& sawError) const
{
if (!m_name)
return String();
return newTextCodec(*this)->decode(data, length, true, stopOnError, sawError);
}
Vector<uint8_t> TextEncoding::encode(StringView string, UnencodableHandling handling) const
{
if (!m_name || string.isEmpty())
return { };
auto normalizedString = normalizedNFC(string);
return newTextCodec(*this)->encode(normalizedString.view, handling);
}
const char* TextEncoding::domName() const
{
if (noExtendedTextEncodingNameUsed())
return m_name;
static const char* const a = atomCanonicalTextEncodingName("windows-949");
if (m_name == a)
return "EUC-KR";
return m_name;
}
bool TextEncoding::usesVisualOrdering() const
{
if (noExtendedTextEncodingNameUsed())
return false;
static const char* const a = atomCanonicalTextEncodingName("ISO-8859-8");
return m_name == a;
}
bool TextEncoding::isJapanese() const
{
return isJapaneseEncoding(m_name);
}
UChar TextEncoding::backslashAsCurrencySymbol() const
{
return shouldShowBackslashAsCurrencySymbolIn(m_name) ? 0x00A5 : '\\';
}
bool TextEncoding::isNonByteBasedEncoding() const
{
return *this == UTF16LittleEndianEncoding() || *this == UTF16BigEndianEncoding();
}
bool TextEncoding::isUTF7Encoding() const
{
if (noExtendedTextEncodingNameUsed())
return false;
return *this == UTF7Encoding();
}
const TextEncoding& TextEncoding::closestByteBasedEquivalent() const
{
if (isNonByteBasedEncoding())
return UTF8Encoding();
return *this;
}
const TextEncoding& TextEncoding::encodingForFormSubmissionOrURLParsing() const
{
if (isNonByteBasedEncoding() || isUTF7Encoding())
return UTF8Encoding();
return *this;
}
const TextEncoding& ASCIIEncoding()
{
static NeverDestroyed<TextEncoding> globalASCIIEncoding("ASCII");
return globalASCIIEncoding;
}
const TextEncoding& Latin1Encoding()
{
static NeverDestroyed<TextEncoding> globalLatin1Encoding("latin1");
return globalLatin1Encoding;
}
const TextEncoding& UTF16BigEndianEncoding()
{
static NeverDestroyed<TextEncoding> globalUTF16BigEndianEncoding("UTF-16BE");
return globalUTF16BigEndianEncoding;
}
const TextEncoding& UTF16LittleEndianEncoding()
{
static NeverDestroyed<TextEncoding> globalUTF16LittleEndianEncoding("UTF-16LE");
return globalUTF16LittleEndianEncoding;
}
const TextEncoding& UTF8Encoding()
{
static NeverDestroyed<TextEncoding> globalUTF8Encoding("UTF-8");
ASSERT(globalUTF8Encoding.get().isValid());
return globalUTF8Encoding;
}
const TextEncoding& WindowsLatin1Encoding()
{
static NeverDestroyed<TextEncoding> globalWindowsLatin1Encoding("WinLatin-1");
return globalWindowsLatin1Encoding;
}
String decodeURLEscapeSequences(StringView string, const TextEncoding& encoding)
{
if (string.isEmpty())
return string.toString();
return decodeEscapeSequences<URLEscapeSequence>(string, encoding);
}
}