/// <summary>
/// Determine whether this string starts with the provided string.
/// </summary>
public bool StartsWith(string other)
{
var it = new Utf8Enumerator(this);
for (int i = 0; i < other.Length; i++)
{
if (!it.MoveNext())
{
return(false);
}
var c = other[i];
uint codepoint;
if (char.IsSurrogate(c))
{
i++;
codepoint = (uint)char.ConvertToUtf32(c, other[i]);
}
else
{
codepoint = (uint)c;
}
if (codepoint != it.Current.Value)
{
return(false);
}
}
return(true);
}
/// <summary>
/// Check the equality with the given System.String.
/// </summary>
public bool Equals(string s)
{
var it = new Utf8Enumerator(this);
int i = 0;
while (it.MoveNext())
{
if (i >= s.Length)
{
return(false);
}
var c = s[i];
uint a;
if (char.IsSurrogate(c))
{
i++;
a = (uint)char.ConvertToUtf32(c, s[i]);
}
else
{
a = (uint)c;
}
if (a != it.Current.Value)
{
return(false);
}
i++;
}
return(i == s.Length);
}
/// <summary>
/// Create a copy of this string converted to uppercase.
/// </summary>
/// <remarks>
/// This obviously allocates a new array to hold the uppercase data.
///
/// The length of the output is not necessarily the same as the length of the input.
/// </remarks>
public utf8 ToUpper()
{
if (Length == 0)
{
return(Empty);
}
var it = new Utf8Enumerator(this);
int len = 0;
while (it.MoveNext())
{
len += CharInfo.Utf8Length(CharInfo.ToUpper(it.Current.Value));
}
it.Reset();
var buf = new byte[len];
var stream = new MemoryStream(buf);
len = 0;
while (it.MoveNext())
{
Utf8Writer.AppendCodepoint(stream, CharInfo.ToUpper(it.Current.Value));
}
return(new utf8(buf));
}
/// <summary>
/// Create a copy of this string converted to lowercase.
/// </summary>
/// <remarks>
/// This obviously allocates a new array to hold the lowercase data.
///
/// The length of the output is not necessarily the same as the length of the input.
/// </remarks>
public Utf8String ToLower(CultureInfo info)
{
if (Length == 0)
{
return(Empty);
}
var ch = new char[1];
var it = new Utf8Enumerator(this);
int len = 0;
while (it.MoveNext())
{
if (it.Current.Value <= 0x1FFFF)
{
var lc = char.ToLower((char)it.Current.Value);
ch[0] = lc;
len += Encoding.UTF8.GetByteCount(ch);
}
else
{
// We're in emoji land, so no upper/lowercase.
// (This will fail in the future should unicode get codepoints representing
// upper/lowercase characters in this range.)
len += it.Current.EncodedLength;
}
}
it.Reset();
var buf = new byte[len];
while (it.MoveNext())
{
if (it.Current.Value <= 0x1FFFF)
{
var lc = char.ToLower((char)it.Current.Value);
ch[0] = lc;
len += Encoding.UTF8.GetBytes(ch, 0, 1, buf, len);
}
else
{
// We're in emoji land, so no upper/lowercase.
// (This will fail in the future should unicode get codepoints representing
// upper/lowercase characters in this range.)
for (int i = 0; i < it.Current.EncodedLength; i++)
{
buf[len] = this[i + it.Current.Index];
len++;
}
}
}
return(new Utf8String(buf));
}
/// <summary>
/// Locate the given Unicode codepoint in this string.
/// </summary>
/// <remarks>
/// So you can find all the poop emoji.
/// </remarks>
public int IndexOf(uint codepoint)
{
var it = new Utf8Enumerator(this);
while (it.MoveNext())
{
if (it.Current.Value == codepoint)
{
return(it.Current.Index);
}
}
return(-1);
}
/// <summary>
/// Create a string consisting of this one, minus any leading whitespace.
/// </summary>
/// <remarks>
/// This method does not allocate.
/// </remarks>
public Utf8String TrimStart()
{
var it = new Utf8Enumerator(this);
while (it.MoveNext())
{
if (!char.IsWhiteSpace((char)it.Current.Value))
{
return(Substring(it.Current.Index));
}
}
return(Utf8String.Empty);
}
/// <summary>
/// Locate the first instance of a character in the given list within this string.
/// </summary>
public int IndexOfAny(params char[] chars)
{
var it = new Utf8Enumerator(this);
while (it.MoveNext())
{
for (int i = 0; i < chars.Length; i++)
{
if (it.Current.Value == chars[i])
{
return(it.Current.Index);
}
}
}
return(-1);
}
/// <summary>
/// Locate the given System.String in this string.
/// </summary>
public int IndexOf(string other)
{
var it = new Utf8Enumerator(this);
while (it.MoveNext())
{
if (Length - it.Current.Index < other.Length)
{
break;
}
if (Substring(it.Current.Index).StartsWith(other))
{
return(it.Current.Index);
}
}
return(-1);
}
/// <summary>
/// Split this string based on the given separators (UTF codepoints).
/// </summary>
/// <remarks>
/// Want to split a string based on the poop emoji character? Now you can! And not as a string!
///
/// This allocates for the output array, but does not copy string data.
/// </remarks>
public IList <Utf8String> Split(uint[] splitOn)
{
var points = new List <Utf8String>();
var last = 0;
var it = new Utf8Enumerator(this);
while (it.MoveNext())
{
for (int i = 0; i < splitOn.Length; i++)
{
if (it.Current.Value == splitOn[i])
{
points.Add(Substring(last, it.Current.Index - last));
last = it.Current.Index;
}
}
}
points.Add(Substring(last, it.Current.Index - last));
return(points);
}
/// <summary>
/// Split this string based on the given separators (UTF codepoints).
/// </summary>
/// <remarks>
/// You will not be able to split on certain characters (for instance, emoji).
///
/// This allocates for the output array, but does not copy string data.
/// </remarks>
public Utf8String[] Split(char[] splitOn, int maxSplits = int.MaxValue)
{
var points = new List <Utf8String>();
var last = 0;
var it = new Utf8Enumerator(this);
while (it.MoveNext())
{
for (int i = 0; i < splitOn.Length; i++)
{
if (it.Current.Value == (uint)splitOn[i])
{
points.Add(Substring(last, it.Current.Index - last));
last = it.Current.Index + it.Current.EncodedLength;
}
}
if (points.Count >= maxSplits - 1)
{
break;
}
}
points.Add(Substring(last, Length - last));
return(points.ToArray());
}
public bool MoveNext()
{
if (currStart >= str.Length)
{
return(false);
}
currStart = nextStart;
var remaining = str.Substring(nextStart);
var it = new Utf8Enumerator(remaining);
while (it.MoveNext())
{
if (it.Current.Value == codepoint)
{
currEnd = it.Current.Index + currStart;
nextStart = currEnd + it.Current.EncodedLength;
return(true);
}
}
currEnd = nextStart = str.Length;
return(true);
}
