Improvements to memory pre.cluster

Mothur.xcodeproj/project.pbxproj

@@ -776,12 +776,12 @@
 		};
 		8DD76FAF0486AB0100D96B5E /* CopyFiles */ = {
 			isa = PBXCopyFilesBuildPhase;
-			buildActionMask = 8;
-			dstPath = Users/SarahsWork/desktop/debug;
+			buildActionMask = 12;
+			dstPath = "";
 			dstSubfolderSpec = 16;
 			files = (
 			);
-			runOnlyForDeploymentPostprocessing = 1;
+			runOnlyForDeploymentPostprocessing = 0;
 		};
 /* End PBXCopyFilesBuildPhase section */
 
@@ -3342,10 +3342,10 @@
 				"DYLIB_CURRENT_VERSION[sdk=*]" = "";
 				GCC_DYNAMIC_NO_PIC = NO;
 				GCC_MODEL_TUNING = G5;
-				GCC_OPTIMIZATION_LEVEL = 0;
+				GCC_OPTIMIZATION_LEVEL = 3;
 				GCC_PREPROCESSOR_DEFINITIONS = (
-					"VERSION=\"\\\"1.37.1\\\"\"",
-					"RELEASE_DATE=\"\\\"04/11/2016\\\"\"",
+					"VERSION=\"\\\"1.38.1\\\"\"",
+					"RELEASE_DATE=\"\\\"09/26/2016\\\"\"",
 					"MOTHUR_FILES=\"\\\"/Users/sarahwestcott/desktop/release\\\"\"",
 				);
 				GCC_WARN_ABOUT_MISSING_PROTOTYPES = NO;
@@ -3377,10 +3377,10 @@
 				DEPLOYMENT_LOCATION = YES;
 				DSTROOT = TARGET_BUILD_DIR;
 				GCC_MODEL_TUNING = G5;
-				GCC_OPTIMIZATION_LEVEL = 0;
+				GCC_OPTIMIZATION_LEVEL = 3;
 				GCC_PREPROCESSOR_DEFINITIONS = (
-					"VERSION=\"\\\"1.37.1\\\"\"",
-					"RELEASE_DATE=\"\\\"04/11/2016\\\"\"",
+					"VERSION=\"\\\"1.38.1\\\"\"",
+					"RELEASE_DATE=\"\\\"09/26/2016\\\"\"",
 					"MOTHUR_FILES=\"\\\"/Users/sarahwestcott/desktop/release\\\"\"",
 				);
 				GCC_WARN_ABOUT_MISSING_PROTOTYPES = NO;
@@ -3458,8 +3458,8 @@
 				GCC_MODEL_TUNING = "";
 				GCC_OPTIMIZATION_LEVEL = 3;
 				GCC_PREPROCESSOR_DEFINITIONS = (
-					"VERSION=\"\\\"1.37.6\\\"\"",
-					"RELEASE_DATE=\"\\\"06/20/2016\\\"\"",
+					"VERSION=\"\\\"1.38.1\\\"\"",
+					"RELEASE_DATE=\"\\\"09/26/2016\\\"\"",
 					"MOTHUR_FILES=\"\\\"/Users/sarahwestcott/desktop/release\\\"\"",
 				);
 				GCC_VERSION = "";

source/commands/preclustercommand.h

@@ -38,11 +38,18 @@ struct seqPNode {
 /************************************************************/
 inline bool comparePriorityTopDown(seqPNode first, seqPNode second) {  
     if (first.numIdentical > second.numIdentical) { return true;  }
+    //else if (first.numIdentical == second.numIdentical) {
+        //if (first.seq.getName() > second.seq.getName()) { return true; }
+    //}
+
     return false; 
 }
 /************************************************************/
 inline bool comparePriorityDownTop(seqPNode first, seqPNode second) {  
     if (first.numIdentical < second.numIdentical) { return true;  }
+    //else if (first.numIdentical == second.numIdentical) {
+        //if (first.seq.getName() > second.seq.getName()) { return true; }
+    //}
     return false; 
 }
 //************************************************************/
@@ -81,7 +88,6 @@ class PreClusterCommand : public Command {
 	vector<string> outputNames;
 	
 	int readFASTA();
-	void readNameFile();
 	int calcMisMatches(string, string);
 	void printData(string, string, string); //fasta filename, names file name
 	int process(string);

source/datastructures/sequencecountparser.cpp

@@ -31,18 +31,18 @@ SequenceCountParser::SequenceCountParser(string countfile, string fastafile) {
 		ifstream in;
 		m->openInputFile(fastafile, in);
 		
-        int fastaCount = 0;
+        //int fastaCount = 0;
 		while (!in.eof()) {
 			
 			if (m->control_pressed) { break; }
 			
 			Sequence seq(in); m->gobble(in);
-            fastaCount++;
-            if (m->debug) { if((fastaCount) % 1000 == 0){	m->mothurOut("[DEBUG]: reading seq " + toString(fastaCount) + "\n.");	} }
+            //fastaCount++;
+            //if (m->debug) { if((fastaCount) % 1000 == 0){	m->mothurOut("[DEBUG]: reading seq " + toString(fastaCount) + "\n.");	} }
 			
             if (seq.getName() != "") {
 				
-                allSeqsMap[seq.getName()] = seq.getName();
+                //allSeqsMap[seq.getName()] = seq.getName();
                 vector<int> groupCounts = countTable.getGroupCounts(seq.getName());
                 
                 for (int i = 0; i < namesOfGroups.size(); i++) {
@@ -91,7 +91,7 @@ SequenceCountParser::SequenceCountParser(string fastafile, CountTable& countTabl
                 
                 if (seq.getName() != "") {
                     
-                    allSeqsMap[seq.getName()] = seq.getName();
+                    //allSeqsMap[seq.getName()] = seq.getName();
                     vector<int> groupCounts = countTable.getGroupCounts(seq.getName());
                     
                     for (int i = 0; i < namesOfGroups.size(); i++) {
@@ -138,6 +138,24 @@ int SequenceCountParser::getNumSeqs(string g){
 	}
 }
 /************************************************************/
+map<string, string> SequenceCountParser::getAllSeqsMap(){
+    try {
+        map<string, string > allSeqsMap;
+        map<string, vector<Sequence> >::iterator it;
+        
+        for (it = seqs.begin(); it != seqs.end(); it++) {
+            vector<Sequence> temp = it->second;
+            for (int i = 0; i < temp.size(); i++) {  allSeqsMap[temp[i].getName()] = temp[i].getName(); }
+        }
+        
+        return allSeqsMap;
+    }
+    catch(exception& e) {
+        m->errorOut(e, "SequenceCountParser", "getAllSeqsMap");
+        exit(1);
+    }
+}
+/************************************************************/
 vector<Sequence> SequenceCountParser::getSeqs(string g){ 
 	try {
 		map<string, vector<Sequence> >::iterator it;

source/datastructures/sequencecountparser.h

@@ -41,14 +41,14 @@ class SequenceCountParser {
     int getSeqs(string, string, string, string, bool); //prints unique sequences in a specific group to a file - group, filename, uchimeFormat=false, tag (/ab= or ;size=), tag2(/ or ;)
     int getCountTable(string, string); //print seqName -> numberRedundantSeqs for a specific group - group, filename
     
-    map<string, string> getAllSeqsMap(){ return allSeqsMap; }  //returns map where the key=sequenceName and the value=representativeSequence - helps us remove duplicates after group by group processing
+    map<string, string> getAllSeqsMap(); //returns map where the key=sequenceName and the value=representativeSequence - helps us remove duplicates after group by group processing
 private:
 	
     CountTable countTable;
     MothurOut* m;
 	
     int numSeqs;
-    map<string, string> allSeqsMap;
+    //map<string, string> allSeqsMap;
     map<string, vector<Sequence> > seqs; //a vector for each group
     map<string, map<string, int> > countTablePerGroup; //countTable for each group
     vector<string> namesOfGroups;