#include "command.hpp"
#include "globaldata.hpp"
-#include "sparsematrix.hpp"
#include "listvector.hpp"
#include "inputdata.h"
#include "readotu.h"
#include "fastamap.h"
#include "groupmap.h"
+#include "readmatrix.hpp"
+#include "formatmatrix.h"
typedef list<PCell>::iterator MatData;
typedef map<int, float> SeqMap;
+struct repStruct {
+ string name;
+ int bin;
+ int size;
+ string group;
+
+ repStruct(){}
+ repStruct(string n, int b, int s, string g) : name(n), bin(b), size(s), group(g) {}
+ ~repStruct() {}
+};
+
class GetOTURepCommand : public Command {
public:
GetOTURepCommand(string);
+ GetOTURepCommand();
~GetOTURepCommand();
+ vector<string> getRequiredParameters();
+ vector<string> getValidParameters();
+ vector<string> getRequiredFiles();
+ map<string, vector<string> > getOutputFiles() { return outputTypes; }
int execute();
void help();
private:
GlobalData* globaldata;
- SparseMatrix* matrix;
ListVector* list;
ReadOTUFile* read;
InputData* input;
FastaMap* fasta;
GroupMap* groupMap;
- string filename, fastafile, listfile, namesfile, groupfile, line, label;
+ ReadMatrix* readMatrix;
+ FormatMatrix* formatMatrix;
+ NameAssignment* nameMap;
+ string filename, fastafile, listfile, namefile, groupfile, label, sorted, phylipfile, columnfile, distFile, format, outputDir, groups;
ofstream out;
- ifstream in, inNames;
- bool groupError;
-
- bool abort, allLines;
- set<int> lines; //hold lines to be used
+ ifstream in, inNames, inRow;
+ bool abort, allLines, groupError, large, weighted;
set<string> labels; //holds labels to be used
map<string, int> nameToIndex; //maps sequence name to index in sparsematrix
-
+ map<string, string> nameFileMap;
+ vector<string> outputNames, Groups;
+ map<string, string> outputNameFiles;
+ float cutoff;
+ int precision;
vector<SeqMap> seqVec; // contains maps with sequence index and distance
// for all distances related to a certain sequence
-
+ vector<int> rowPositions;
+ map<string, vector<string> > outputTypes;
void readNamesFile();
+ void readNamesFile(bool);
int process(ListVector*);
- string findRep(int, string&, ListVector*, int&); // returns the name of the "representative" sequence of given bin,
- // fills a string containing the groups in that bin if a groupfile is given,
- // and returns the number of sequences in the given bin
+ SeqMap getMap(int);
+ string findRep(vector<string>); // returns the name of the "representative" sequence of given bin or subset of a bin, for groups
+ int processNames(string, string);
+
};