]> git.donarmstrong.com Git - mothur.git/blobdiff - summarytaxcommand.cpp
fixes while testing 1.33.0
[mothur.git] / summarytaxcommand.cpp
index a19986aba92ffeae80d3786c2322dc3d7d5bb461..9741e666e8c939d42ad4a6a5ec2001ea8a6004f2 100644 (file)
 //**********************************************************************************************************************
 vector<string> SummaryTaxCommand::setParameters(){     
        try {
-               CommandParameter ptaxonomy("taxonomy", "InputTypes", "", "", "none", "none", "none",false,true); parameters.push_back(ptaxonomy);
-               CommandParameter pname("name", "InputTypes", "", "", "none", "none", "none",false,false); parameters.push_back(pname);
-               CommandParameter pgroup("group", "InputTypes", "", "", "none", "none", "none",false,false); parameters.push_back(pgroup);
-               CommandParameter preftaxonomy("reftaxonomy", "InputTypes", "", "", "none", "none", "none",false,false); parameters.push_back(preftaxonomy);
-               CommandParameter pinputdir("inputdir", "String", "", "", "", "", "",false,false); parameters.push_back(pinputdir);
-               CommandParameter poutputdir("outputdir", "String", "", "", "", "", "",false,false); parameters.push_back(poutputdir);
+               CommandParameter ptaxonomy("taxonomy", "InputTypes", "", "", "none", "none", "none","summary",false,true,true); parameters.push_back(ptaxonomy);
+        CommandParameter pname("name", "InputTypes", "", "", "NameCount", "none", "none","",false,false,true); parameters.push_back(pname);
+        CommandParameter pcount("count", "InputTypes", "", "", "NameCount-CountGroup", "none", "none","",false,false,true); parameters.push_back(pcount);
+               CommandParameter pgroup("group", "InputTypes", "", "", "CountGroup", "none", "none","",false,false,true); parameters.push_back(pgroup);
+               CommandParameter preftaxonomy("reftaxonomy", "InputTypes", "", "", "none", "none", "none","",false,false); parameters.push_back(preftaxonomy);
+        CommandParameter prelabund("relabund", "Boolean", "", "F", "", "", "","",false,false); parameters.push_back(prelabund);
+
+               CommandParameter pinputdir("inputdir", "String", "", "", "", "", "","",false,false); parameters.push_back(pinputdir);
+               CommandParameter poutputdir("outputdir", "String", "", "", "", "", "","",false,false); parameters.push_back(poutputdir);
                
                vector<string> myArray;
                for (int i = 0; i < parameters.size(); i++) {   myArray.push_back(parameters[i].name);          }
@@ -34,10 +37,12 @@ string SummaryTaxCommand::getHelpString(){
        try {
                string helpString = "";
                helpString += "The summary.tax command reads a taxonomy file and an optional name file, and summarizes the taxonomy information.\n";
-               helpString += "The summary.tax command parameters are taxonomy, group and name. taxonomy is required, unless you have a valid current taxonomy file.\n";
+               helpString += "The summary.tax command parameters are taxonomy, count, group, name and relabund. taxonomy is required, unless you have a valid current taxonomy file.\n";
                helpString += "The name parameter allows you to enter a name file associated with your taxonomy file. \n";
                helpString += "The group parameter allows you add a group file so you can have the summary totals broken up by group.\n";
+        helpString += "The count parameter allows you add a count file so you can have the summary totals broken up by group.\n";
                helpString += "The reftaxonomy parameter allows you give the name of the reference taxonomy file used when you classified your sequences. It is not required, but providing it will keep the rankIDs in the summary file static.\n";
+        helpString += "The relabund parameter allows you to indicate you want the summary file values to be relative abundances rather than raw abundances. Default=F. \n";
                helpString += "The summary.tax command should be in the following format: \n";
                helpString += "summary.tax(taxonomy=yourTaxonomyFile) \n";
                helpString += "Note: No spaces between parameter labels (i.e. taxonomy), '=' and parameters (i.e.yourTaxonomyFile).\n"; 
@@ -48,7 +53,21 @@ string SummaryTaxCommand::getHelpString(){
                exit(1);
        }
 }
-
+//**********************************************************************************************************************
+string SummaryTaxCommand::getOutputPattern(string type) {
+    try {
+        string pattern = "";
+        
+        if (type == "summary") {  pattern = "[filename],tax.summary"; } 
+        else { m->mothurOut("[ERROR]: No definition for type " + type + " output pattern.\n"); m->control_pressed = true;  }
+        
+        return pattern;
+    }
+    catch(exception& e) {
+        m->errorOut(e, "SummaryTaxCommand", "getOutputPattern");
+        exit(1);
+    }
+}
 //**********************************************************************************************************************
 SummaryTaxCommand::SummaryTaxCommand(){        
        try {
@@ -123,6 +142,14 @@ SummaryTaxCommand::SummaryTaxCommand(string option)  {
                                        if (path == "") {       parameters["reftaxonomy"] = inputDir + it->second;              }
                                }
                                
+                it = parameters.find("count");
+                               //user has given a template file
+                               if(it != parameters.end()){ 
+                                       path = m->hasPath(it->second);
+                                       //if the user has not given a path then, add inputdir. else leave path alone.
+                                       if (path == "") {       parameters["count"] = inputDir + it->second;            }
+                               }
+
                        }
                        
                        //initialize outputTypes
@@ -147,7 +174,20 @@ SummaryTaxCommand::SummaryTaxCommand(string option)  {
                        if (groupfile == "not open") { groupfile = ""; abort = true; }
                        else if (groupfile == "not found") { groupfile = ""; }
                        else { m->setGroupFile(groupfile); }
+            
+            countfile = validParameter.validFile(parameters, "count", true);
+                       if (countfile == "not open") { countfile = ""; abort = true; }
+                       else if (countfile == "not found") { countfile = "";  } 
+                       else { m->setCountTableFile(countfile); }
+            
+            if ((namefile != "") && (countfile != "")) {
+                m->mothurOut("[ERROR]: you may only use one of the following: name or count."); m->mothurOutEndLine(); abort = true;
+            }
                        
+            if ((groupfile != "") && (countfile != "")) {
+                m->mothurOut("[ERROR]: you may only use one of the following: group or count."); m->mothurOutEndLine(); abort=true;
+            }
+            
                        refTaxonomy = validParameter.validFile(parameters, "reftaxonomy", true);
                        if (refTaxonomy == "not found") { refTaxonomy = ""; m->mothurOut("reftaxonomy is not required, but if given will keep the rankIDs in the summary file static."); m->mothurOutEndLine(); }
                        else if (refTaxonomy == "not open") { refTaxonomy = ""; abort = true; }
@@ -157,6 +197,16 @@ SummaryTaxCommand::SummaryTaxCommand(string option)  {
                                outputDir = ""; 
                                outputDir += m->hasPath(taxfile); //if user entered a file with a path then preserve it 
                        }
+            
+            string temp = validParameter.validFile(parameters, "relabund", false);             if (temp == "not found"){       temp = "false";                 }
+                       relabund = m->isTrue(temp);
+                       
+            if (countfile == "") {
+                if (namefile == "") {
+                    vector<string> files; files.push_back(taxfile);
+                    parser.getNameFile(files);
+                }
+                       }
                }
        }
        catch(exception& e) {
@@ -172,23 +222,35 @@ int SummaryTaxCommand::execute(){
                if (abort == true) { if (calledHelp) { return 0; }  return 2;   }
                int start = time(NULL);
                
-               PhyloSummary* taxaSum;
-               if (refTaxonomy != "") {
-                       taxaSum = new PhyloSummary(refTaxonomy, groupfile);
-               }else {
-                       taxaSum = new PhyloSummary(groupfile);
-               }
+        GroupMap* groupMap = NULL;
+        CountTable* ct = NULL;
+        if (groupfile != "") {
+            groupMap = new GroupMap(groupfile);
+            groupMap->readMap();
+        }else if (countfile != "") {
+            ct = new CountTable();
+            ct->readTable(countfile, true, false);
+        }
                
-               if (m->control_pressed) { delete taxaSum; return 0; }
+        PhyloSummary* taxaSum;
+        if (countfile != "") {
+            if (refTaxonomy != "") { taxaSum = new PhyloSummary(refTaxonomy, ct, relabund); }
+            else { taxaSum = new PhyloSummary(ct, relabund); }
+        }else {
+            if (refTaxonomy != "") { taxaSum = new PhyloSummary(refTaxonomy, groupMap, relabund); }
+            else { taxaSum = new PhyloSummary(groupMap, relabund); }
+               }
+        
+               if (m->control_pressed) { if (groupMap != NULL) { delete groupMap; } if (ct != NULL) { delete ct; } delete taxaSum; return 0; }
                
                int numSeqs = 0;
-               if (namefile == "") { numSeqs = taxaSum->summarize(taxfile);  }
-               else {
+               if ((namefile == "") || (countfile != "")) { numSeqs = taxaSum->summarize(taxfile);  }
+               else if (namefile != "") {
                        map<string, vector<string> > nameMap;
                        map<string, vector<string> >::iterator itNames;
                        m->readNames(namefile, nameMap);
                        
-                       if (m->control_pressed) { delete taxaSum; return 0; }
+                       if (m->control_pressed) { if (groupMap != NULL) { delete groupMap; } if (ct != NULL) { delete ct; } delete taxaSum; return 0; }
                        
                        ifstream in;
                        m->openInputFile(taxfile, in);
@@ -197,6 +259,9 @@ int SummaryTaxCommand::execute(){
                        string name, taxon;
                        
                        while(!in.eof()){
+                
+                if (m->control_pressed) { break; }
+                
                                in >> name >> taxon; m->gobble(in);
                                
                                itNames = nameMap.find(name);
@@ -213,25 +278,28 @@ int SummaryTaxCommand::execute(){
                                }
                        }
                        in.close();
-               }
+               }else { numSeqs = taxaSum->summarize(taxfile);  }
                
-               if (m->control_pressed) {  delete taxaSum; return 0; }
+               if (m->control_pressed) {  if (groupMap != NULL) { delete groupMap; } if (ct != NULL) { delete ct; } delete taxaSum; return 0; }
                
                //print summary file
                ofstream outTaxTree;
-               string summaryFile = outputDir + m->getRootName(m->getSimpleName(taxfile)) + "tax.summary";
+        map<string, string> variables; 
+               variables["[filename]"] = outputDir + m->getRootName(m->getSimpleName(taxfile));
+               string summaryFile = getOutputFileName("summary",variables);
                m->openOutputFile(summaryFile, outTaxTree);
                taxaSum->print(outTaxTree);
                outTaxTree.close();
                
                delete taxaSum;
+        if (groupMap != NULL) { delete groupMap; } if (ct != NULL) { delete ct; }
                
                if (m->control_pressed) {  m->mothurRemove(summaryFile); return 0; }
                
                m->mothurOutEndLine();
                m->mothurOut("It took " + toString(time(NULL) - start) + " secs to create the summary file for " + toString(numSeqs) + " sequences."); m->mothurOutEndLine(); m->mothurOutEndLine();
                m->mothurOutEndLine();
-               m->mothurOut("Output File Name: "); m->mothurOutEndLine();
+               m->mothurOut("Output File Names: "); m->mothurOutEndLine();
                m->mothurOut(summaryFile); m->mothurOutEndLine();       outputNames.push_back(summaryFile); outputTypes["summary"].push_back(summaryFile);
                m->mothurOutEndLine();