private void DoText(string text)
{
var list = new List <Unicode.Summary>(text.Length);
bool after_high_surrogate = false;
foreach (var c in text)
{
if (IsCancelled())
{
return;
}
int code = c;
if (after_high_surrogate && Unicode.IsLowSurrogate(code))
{
var high = list[list.Count - 1];
code = Unicode.DecodeSurrogatePair((int)high.Code, code);
list[list.Count - 1] = Unicode.GetSummary(code);
}
else
{
list.Add(Unicode.GetSummary(c));
}
after_high_surrogate = Unicode.IsHighSurroate(code);
}
OnUpdated(list.ToArray());
}
private void DoCode(string text)
{
var list = new List <Unicode.Summary>(text.Length);
bool after_high_surrogate = false;
var a = text
.Replace(";", "; ").Replace("\\", " \\").Replace("&#", " &#")
.Split((char[])null, StringSplitOptions.RemoveEmptyEntries);
foreach (var s in a)
{
if (IsCancelled())
{
return;
}
int code = ParseCodepointNotation(s);
if (after_high_surrogate && Unicode.IsLowSurrogate(code) && !s.StartsWith("&#"))
{
var high = list[list.Count - 1] as UnicodeSummaryEx;
code = Unicode.DecodeSurrogatePair((int)high.Code, code);
list[list.Count - 1] = new UnicodeSummaryEx(Unicode.GetSummary(code), high.Orig + " " + s);
}
else
{
list.Add(new UnicodeSummaryEx(Unicode.GetSummary(code), s));
}
after_high_surrogate = Unicode.IsHighSurroate(code) && !s.StartsWith("&#");
}
OnUpdated(list.ToArray());
}
public void DecodeSurrogatePair()
{
uint codepoint;
Assert.False(Unicode.DecodeSurrogatePair('\0', '\0', out codepoint));
Assert.AreEqual(0, codepoint);
Assert.False(Unicode.DecodeSurrogatePair('a', '\0', out codepoint));
Assert.AreEqual((uint)'a', codepoint);
Assert.False(Unicode.DecodeSurrogatePair('a', 'b', out codepoint));
Assert.AreEqual((uint)'a', codepoint);
Assert.True(Unicode.DecodeSurrogatePair("\U0002F8B6"[0], "\U0002F8B6"[1], out codepoint));
Assert.AreEqual((uint)0x2F8B6, codepoint);
Assert.False(Unicode.DecodeSurrogatePair("\U0002F8B6"[0], '\0', out codepoint));
Assert.AreEqual(0xFFFD, codepoint);
}