/// <summary>
/// Identifies Alphabet for the sepecified sequence.
/// </summary>
/// <param name="currentAlphabet">Currently known alphabet of the sequence, null if alphabet is unknown.</param>
/// <param name="sequence">Sequence data.</param>
/// <returns>Returns appropriate alphabet for the specified sequence and considering the specified current alphabet.
/// Returns null if any character in the sequence is unrecognized by DNA, RNA and Protien Alphabets.</returns>
protected IAlphabet IdentifyAlphabet(IAlphabet currentAlphabet, string sequence)
{
if (string.IsNullOrEmpty(sequence))
{
return(null);
}
// Alphabets use upper case characters so to prevent parsing errors ensure the sequence
// is all upper case.
sequence = sequence.ToUpperInvariant();
// This is much faster than performing sequence.ToCharArray().Distinct()
int characters = 0;
if (currentAlphabet != null)
{
characters = Alphabets.GetHighestChar(currentAlphabet) + 1;
}
else
{
foreach (var item in Alphabets.All)
{
characters = Math.Max(characters, Alphabets.GetHighestChar(item) + 1);
}
}
var characterExists = new bool[characters];
for (int i = 0; i < characterExists.Length; i++)
{
characterExists[i] = false;
}
var uniqueValues = new StringBuilder();
for (int i = 0; i < sequence.Length; i++)
{
char sequenceChar = sequence[i];
if (!characterExists[sequenceChar])
{
characterExists[sequenceChar] = true;
uniqueValues.Append(sequenceChar);
}
}
bool canClearDistinctSymbol = false;
if (_distinctSymbols != null)
{
_distinctSymbols = _distinctSymbols.Union(uniqueValues.ToString()).ToList();
}
else
{
canClearDistinctSymbol = true;
_distinctSymbols = uniqueValues.ToString().ToCharArray().ToList();
}
IAlphabet alphabet = null;
if (currentAlphabet == Alphabets.Protein)
{
alphabet = StartCheckFromProtein();
}
else if (currentAlphabet == Alphabets.RNA)
{
alphabet = StartCheckFromRna();
}
else
{
alphabet = StartCheckFromDna();
}
if (canClearDistinctSymbol)
{
_distinctSymbols = null;
}
return(alphabet);
}
