X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=classifyseqscommand.h;h=3dbf06ee5bf18c5f6c5ee96e717ec4348c919310;hb=65b6a38d00b3a72021611211e7c25392022c69ed;hp=2223593c4e7758ac48844dbf7d5093b20f361b5d;hpb=315e38cf393c82be238da5b32574f225a020d25c;p=mothur.git

diff --git a/classifyseqscommand.h b/classifyseqscommand.h
index 2223593..3dbf06e 100644
--- a/classifyseqscommand.h
+++ b/classifyseqscommand.h
@@ -12,8 +12,8 @@
 
 #include "mothur.h"
 #include "command.hpp"
-#include "alignment.hpp"
 #include "classify.h"
+#include "referencedb.h"
 
 //KNN and Bayesian methods modeled from algorithms in
 //Naı¨ve Bayesian Classifier for Rapid Assignment of rRNA Sequences 
@@ -28,35 +28,55 @@
 class ClassifySeqsCommand : public Command {
 	
 public:
-	ClassifySeqsCommand(string);	
+	ClassifySeqsCommand(string);
+	ClassifySeqsCommand();
 	~ClassifySeqsCommand();
+	
+	vector<string> setParameters();
+	string getCommandName()			{ return "classify.seqs";		}
+	string getCommandCategory()		{ return "Phylotype Analysis";	}
+	string getHelpString();	
+	string getCitation() { return "Wang Q, Garrity GM, Tiedje JM, Cole JR (2007). Naive Bayesian classifier for rapid assignment of rRNA sequences into the new bacterial taxonomy. Appl Environ Microbiol 73: 5261-7. [ for Bayesian classifier ] \nAltschul SF, Madden TL, Schaffer AA, Zhang J, Zhang Z, Miller W, Lipman DJ (1997). Gapped BLAST and PSI-BLAST: a new generation of protein database search programs. Nucleic Acids Res 25: 3389-402. [ for BLAST ] \nDeSantis TZ, Hugenholtz P, Larsen N, Rojas M, Brodie EL, Keller K, Huber T, Dalevi D, Hu P, Andersen GL (2006). Greengenes, a chimera-checked 16S rRNA gene database and workbench compatible with ARB. Appl Environ Microbiol 72: 5069-72. [ for kmer ] \nhttp://www.mothur.org/wiki/Classify.seqs"; }
+	string getDescription()		{ return "classify sequences"; }
+	
 	int execute(); 
-	void help();	
+	void help() { m->mothurOut(getHelpString()); }	
+	
+	
 	
 private:
 	struct linePair {
-		int start;
-		int numSeqs;
-		linePair(int i, int j) : start(i), numSeqs(j) {}
+		unsigned long int start;
+		unsigned long int end;
+		linePair(unsigned long int i, unsigned long int j) : start(i), end(j) {}
 	};
+
 	vector<int> processIDS;   //processid
 	vector<linePair*> lines;
 	vector<string> fastaFileNames;
 	vector<string> namefileNames;
-	map<string, int> nameMap;
-	map<string, int>::iterator itNames;
+	vector<string> groupfileNames;
+	vector<string> outputNames;
+	map<string, vector<string> > nameMap;
+	map<string,  vector<string> >::iterator itNames;
 	
 	Classify* classify;
+	ReferenceDB* rdb;
 	
-	string fastaFileName, templateFileName, distanceFileName, namefile, search, method, taxonomyFileName, outputDir;
+	string fastaFileName, templateFileName, distanceFileName, namefile, search, method, taxonomyFileName, outputDir, groupfile;
 	int processors, kmerSize, numWanted, cutoff, iters;
 	float match, misMatch, gapOpen, gapExtend;
-	bool abort, probs;
+	bool abort, probs, save;
 	
 	int driver(linePair*, string, string, string);
 	void appendTaxFiles(string, string);
-	void createProcesses(string, string, string); 
+	int createProcesses(string, string, string); 
 	string addUnclassifieds(string, int);
+	
+	int MPIReadNamesFile(string);
+	#ifdef USE_MPI
+	int driverMPI(int, int, MPI_File&, MPI_File&, MPI_File&, vector<unsigned long int>&);
+	#endif
 };
 
 #endif