8 * Created by Sarah Westcott on 1/16/09.
9 * Copyright 2009 Schloss Lab UMASS AMherst. All rights reserved.
16 /* This class represents the fasta file. It reads a fasta file a populates the internal data structure "data".
17 Data is a map where the key is the sequence and the value is a struct containing the sequences groupname,
18 a list of the sequences names who have the same sequence and a number of how many sequence names there are. */
27 string getGroupName(string); //pass a sequence name get its group
28 string getNames(string); //pass a sequence get the string of names in the group separated by ','s.
29 void push_back(string, string); //sequencename, sequence
30 int sizeUnique(); //returns number of unique sequences
31 void printNamesFile(string); //produces a 2 column file with the groupname in the first column and the names in the second column - a names file.
32 void printCondensedFasta(string); //produces a fasta file.
33 void readFastaFile(string);
34 void readFastaFile(string, string);
35 string getSequence(string); //pass it a name of a sequence, it returns the sequence.
39 string groupname; //the group name for identical sequences, will be set to the first sequence found.
40 string names; //the names of the sequence separated by ','.
43 map<string, group> data; //sequence, groupinfo - condensed representation of file
44 map<string, string> seqmap; //name, sequence - uncondensed representation of file