/// <summary>Encode characters from this String, starting at offset
/// for length characters. Returns the number of bytes
/// written to bytesOut.
/// </summary>
public static void UTF16toUTF8(System.String s, int offset, int length, UTF8Result result)
{
int end = offset + length;
byte[] out_Renamed = result.result;
int upto = 0;
for (int i = offset; i < end; i++)
{
int code = (int) s[i];
if (upto + 4 > out_Renamed.Length)
{
byte[] newOut = new byte[2 * out_Renamed.Length];
System.Diagnostics.Debug.Assert(newOut.Length >= upto + 4);
Array.Copy(out_Renamed, 0, newOut, 0, upto);
result.result = out_Renamed = newOut;
}
if (code < 0x80)
out_Renamed[upto++] = (byte) code;
else if (code < 0x800)
{
out_Renamed[upto++] = (byte) (0xC0 | (code >> 6));
out_Renamed[upto++] = (byte) (0x80 | (code & 0x3F));
}
else if (code < 0xD800 || code > 0xDFFF)
{
out_Renamed[upto++] = (byte) (0xE0 | (code >> 12));
out_Renamed[upto++] = (byte) (0x80 | ((code >> 6) & 0x3F));
out_Renamed[upto++] = (byte) (0x80 | (code & 0x3F));
}
else
{
// surrogate pair
// confirm valid high surrogate
if (code < 0xDC00 && (i < end - 1))
{
int utf32 = (int) s[i + 1];
// confirm valid low surrogate and write pair
if (utf32 >= 0xDC00 && utf32 <= 0xDFFF)
{
utf32 = ((code - 0xD7C0) << 10) + (utf32 & 0x3FF);
i++;
out_Renamed[upto++] = (byte) (0xF0 | (utf32 >> 18));
out_Renamed[upto++] = (byte) (0x80 | ((utf32 >> 12) & 0x3F));
out_Renamed[upto++] = (byte) (0x80 | ((utf32 >> 6) & 0x3F));
out_Renamed[upto++] = (byte) (0x80 | (utf32 & 0x3F));
continue;
}
}
// replace unpaired surrogate or out-of-order low surrogate
// with substitution character
out_Renamed[upto++] = (byte) (0xEF);
out_Renamed[upto++] = (byte) (0xBF);
out_Renamed[upto++] = (byte) (0xBD);
}
}
//assert matches(s, offset, length, out, upto);
result.length = upto;
}
/// <summary>Encode characters from a char[] source, starting at
/// offset and stopping when the character 0xffff is seen.
/// Returns the number of bytes written to bytesOut.
/// </summary>
public static void UTF16toUTF8(char[] source, int offset, UTF8Result result)
{
int upto = 0;
int i = offset;
byte[] out_Renamed = result.result;
while (true)
{
int code = (int)source[i++];
if (upto + 4 > out_Renamed.Length)
{
byte[] newOut = new byte[2 * out_Renamed.Length];
System.Diagnostics.Debug.Assert(newOut.Length >= upto + 4);
Array.Copy(out_Renamed, 0, newOut, 0, upto);
result.result = out_Renamed = newOut;
}
if (code < 0x80)
{
out_Renamed[upto++] = (byte)code;
}
else if (code < 0x800)
{
out_Renamed[upto++] = (byte)(0xC0 | (code >> 6));
out_Renamed[upto++] = (byte)(0x80 | (code & 0x3F));
}
else if (code < 0xD800 || code > 0xDFFF)
{
if (code == 0xffff)
{
// END
break;
}
out_Renamed[upto++] = (byte)(0xE0 | (code >> 12));
out_Renamed[upto++] = (byte)(0x80 | ((code >> 6) & 0x3F));
out_Renamed[upto++] = (byte)(0x80 | (code & 0x3F));
}
else
{
// surrogate pair
// confirm valid high surrogate
if (code < 0xDC00 && source[i] != 0xffff)
{
int utf32 = (int)source[i];
// confirm valid low surrogate and write pair
if (utf32 >= 0xDC00 && utf32 <= 0xDFFF)
{
utf32 = ((code - 0xD7C0) << 10) + (utf32 & 0x3FF);
i++;
out_Renamed[upto++] = (byte)(0xF0 | (utf32 >> 18));
out_Renamed[upto++] = (byte)(0x80 | ((utf32 >> 12) & 0x3F));
out_Renamed[upto++] = (byte)(0x80 | ((utf32 >> 6) & 0x3F));
out_Renamed[upto++] = (byte)(0x80 | (utf32 & 0x3F));
continue;
}
}
// replace unpaired surrogate or out-of-order low surrogate
// with substitution character
out_Renamed[upto++] = (byte)(0xEF);
out_Renamed[upto++] = (byte)(0xBF);
out_Renamed[upto++] = (byte)(0xBD);
}
}
//assert matches(source, offset, i-offset-1, out, upto);
result.length = upto;
}
/** Encode characters from this String, starting at offset
* for length characters. Returns the number of bytes
* written to bytesOut. */
public static void UTF16toUTF8(/* in */ string s, /* in */ int offset, /* in */ int length, UTF8Result result)
{
int end = offset + length;
byte[] out_Renamed = result.result;
int upto = 0;
for (int i = offset; i < end; i++)
{
int code = (int)s[i];
if (upto + 4 > out_Renamed.Length)
{
byte[] newOut = new byte[2 * out_Renamed.Length];
System.Diagnostics.Debug.Assert(newOut.Length >= upto + 4);
System.Array.Copy(out_Renamed, 0, newOut, 0, upto);
result.result = out_Renamed = newOut;
}
if (code < 0x80)
{
out_Renamed[upto++] = (byte)code;
}
else if (code < 0x800)
{
out_Renamed[upto++] = (byte)(0xC0 | (code >> 6));
out_Renamed[upto++] = (byte)(0x80 | (code & 0x3F));
}
else if (code < 0xD800 || code > 0xDFFF)
{
out_Renamed[upto++] = (byte)(0xE0 | (code >> 12));
out_Renamed[upto++] = (byte)(0x80 | ((code >> 6) & 0x3F));
out_Renamed[upto++] = (byte)(0x80 | (code & 0x3F));
}
else
{
// surrogate pair
// confirm valid high surrogate
if (code < 0xDC00 && (i < end - 1))
{
int utf32 = (int)s[i + 1];
// confirm valid low surrogate and write pair
if (utf32 >= 0xDC00 && utf32 <= 0xDFFF)
{
utf32 = ((code - 0xD7C0) << 10) + (utf32 & 0x3FF);
i++;
out_Renamed[upto++] = (byte)(0xF0 | (utf32 >> 18));
out_Renamed[upto++] = (byte)(0x80 | ((utf32 >> 12) & 0x3F));
out_Renamed[upto++] = (byte)(0x80 | ((utf32 >> 6) & 0x3F));
out_Renamed[upto++] = (byte)(0x80 | (utf32 & 0x3F));
continue;
}
}
// replace unpaired surrogate or out_Renamed-of-order low surrogate
// with substitution character
out_Renamed[upto++] = (byte)0xEF;
out_Renamed[upto++] = (byte)0xBF;
out_Renamed[upto++] = (byte)0xBD;
}
}
//System.Diagnostics.Debug.Assert(matches(s, offset, length, out_Renamed, upto);
result.length = upto;
}
/** Encode characters from a char[] source, starting at
* offset and stopping when the character 0xffff is seen.
* Returns the number of bytes written to bytesOut. */
public static void UTF16toUTF8(/* in */ char[] source, /* in */ int offset, UTF8Result result)
{
int upto = 0;
int i = offset;
byte[] out_Renamed = result.result;
while (true)
{
int code = (int)source[i++];
if (upto + 4 > out_Renamed.Length)
{
byte[] newOut = new byte[2 * out_Renamed.Length];
System.Diagnostics.Debug.Assert(newOut.Length >= upto + 4);
System.Array.Copy(out_Renamed, 0, newOut, 0, upto);
result.result = out_Renamed = newOut;
}
if (code < 0x80)
out_Renamed[upto++] = (byte)code;
else if (code < 0x800)
{
out_Renamed[upto++] = (byte)(0xC0 | (code >> 6));
out_Renamed[upto++] = (byte)(0x80 | (code & 0x3F));
}
else if (code < 0xD800 || code > 0xDFFF)
{
if (code == 0xffff)
// END
break;
out_Renamed[upto++] = (byte)(0xE0 | (code >> 12));
out_Renamed[upto++] = (byte)(0x80 | ((code >> 6) & 0x3F));
out_Renamed[upto++] = (byte)(0x80 | (code & 0x3F));
}
else
{
// surrogate pair
// confirm valid high surrogate
if (code < 0xDC00 && source[i] != 0xffff)
{
int utf32 = (int)source[i];
// confirm valid low surrogate and write pair
if (utf32 >= 0xDC00 && utf32 <= 0xDFFF)
{
utf32 = ((code - 0xD7C0) << 10) + (utf32 & 0x3FF);
i++;
out_Renamed[upto++] = (byte)(0xF0 | (utf32 >> 18));
out_Renamed[upto++] = (byte)(0x80 | ((utf32 >> 12) & 0x3F));
out_Renamed[upto++] = (byte)(0x80 | ((utf32 >> 6) & 0x3F));
out_Renamed[upto++] = (byte)(0x80 | (utf32 & 0x3F));
continue;
}
}
// replace unpaired surrogate or out_Renamed-of-order low surrogate
// with substitution character
out_Renamed[upto++] = (byte)0xEF;
out_Renamed[upto++] = (byte)0xBF;
out_Renamed[upto++] = (byte)0xBD;
}
}
//System.Diagnostics.Debug.Assert(matches(source, offset, i-offset-1, out_Renamed, upto);
result.length = upto;
}
