public virtual void TestEmpty()
{
IntsRef i = new IntsRef();
Assert.AreEqual(IntsRef.EMPTY_INTS, i.Ints);
Assert.AreEqual(0, i.Offset);
Assert.AreEqual(0, i.Length);
}
/// <summary>
/// <p>this method assumes valid UTF8 input. this method
/// <strong>does not perform</strong> full UTF8 validation, it will check only the
/// first byte of each codepoint (for multi-byte sequences any bytes after
/// the head are skipped).
/// </summary>
/// <exception cref="IllegalArgumentException"> If invalid codepoint header byte occurs or the
/// content is prematurely truncated. </exception>
public static void UTF8toUTF32(BytesRef utf8, IntsRef utf32)
{
// TODO: broken if incoming result.offset != 0
// pre-alloc for worst case
// TODO: ints cannot be null, should be an assert
if (utf32.Ints == null || utf32.Ints.Length < utf8.Length)
{
utf32.Ints = new int[utf8.Length];
}
int utf32Count = 0;
int utf8Upto = utf8.Offset;
int[] ints = utf32.Ints;
var bytes = utf8.Bytes;
int utf8Limit = utf8.Offset + utf8.Length;
while (utf8Upto < utf8Limit)
{
int numBytes = Utf8CodeLength[bytes[utf8Upto] & 0xFF];
int v = 0;
switch (numBytes)
{
case 1:
ints[utf32Count++] = bytes[utf8Upto++];
continue;
case 2:
// 5 useful bits
v = bytes[utf8Upto++] & 31;
break;
case 3:
// 4 useful bits
v = bytes[utf8Upto++] & 15;
break;
case 4:
// 3 useful bits
v = bytes[utf8Upto++] & 7;
break;
default:
throw new System.ArgumentException("invalid utf8");
}
// TODO: this may read past utf8's limit.
int limit = utf8Upto + numBytes - 1;
while (utf8Upto < limit)
{
v = v << 6 | bytes[utf8Upto++] & 63;
}
ints[utf32Count++] = v;
}
utf32.Offset = 0;
utf32.Length = utf32Count;
}
public virtual void TestFromInts()
{
int[] ints = new int[] { 1, 2, 3, 4 };
IntsRef i = new IntsRef(ints, 0, 4);
Assert.AreEqual(ints, i.Ints);
Assert.AreEqual(0, i.Offset);
Assert.AreEqual(4, i.Length);
IntsRef i2 = new IntsRef(ints, 1, 3);
Assert.AreEqual(new IntsRef(new int[] { 2, 3, 4 }, 0, 3), i2);
Assert.IsFalse(i.Equals(i2));
}
public virtual void TestUTF8toUTF32()
{
BytesRef utf8 = new BytesRef(20);
IntsRef utf32 = new IntsRef(20);
int[] codePoints = new int[20];
int num = AtLeast(50000);
for (int i = 0; i < num; i++)
{
string s = TestUtil.RandomUnicodeString(Random());
UnicodeUtil.UTF16toUTF8(s.ToCharArray(), 0, s.Length, utf8);
UnicodeUtil.UTF8toUTF32(utf8, utf32);
int charUpto = 0;
int intUpto = 0;
while (charUpto < s.Length)
{
int cp = Character.CodePointAt(s, charUpto);
codePoints[intUpto++] = cp;
charUpto += Character.CharCount(cp);
}
if (!ArrayUtil.Equals(codePoints, 0, utf32.Ints, utf32.Offset, intUpto))
{
Console.WriteLine("FAILED");
for (int j = 0; j < s.Length; j++)
{
Console.WriteLine(" char[" + j + "]=" + ((int)s[j]).ToString("x"));
}
Console.WriteLine();
Assert.AreEqual(intUpto, utf32.Length);
for (int j = 0; j < intUpto; j++)
{
Console.WriteLine(" " + utf32.Ints[j].ToString("x") + " vs " + codePoints[j].ToString("x"));
}
Assert.Fail("mismatch");
}
}
}
