]> git.donarmstrong.com Git - mothur.git/blobdiff - removelineagecommand.cpp
sffinfo bug with flow grams right index when clipQualRight=0
[mothur.git] / removelineagecommand.cpp
index a3fd1b83ee5025adb340922df226895230a464ed..5b6fc252c4ae8c78619d0f3ad76afbb9792cbddd 100644 (file)
 #include "removelineagecommand.h"
 #include "sequence.hpp"
 #include "listvector.hpp"
+#include "counttable.h"
 
 //**********************************************************************************************************************
 vector<string> RemoveLineageCommand::setParameters(){  
        try {
-               CommandParameter pfasta("fasta", "InputTypes", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(pfasta);
-        CommandParameter pname("name", "InputTypes", "", "", "NameCount", "FNGLT", "none",false,false); parameters.push_back(pname);
-        CommandParameter pcount("count", "InputTypes", "", "", "NameCount-CountGroup", "FNGLT", "none",false,false); parameters.push_back(pcount);
-               CommandParameter pgroup("group", "InputTypes", "", "", "CountGroup", "FNGLT", "none",false,false); parameters.push_back(pgroup);
-               CommandParameter plist("list", "InputTypes", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(plist);
-               CommandParameter ptaxonomy("taxonomy", "InputTypes", "", "", "none", "FNGLT", "none",false,true); parameters.push_back(ptaxonomy);
-               CommandParameter palignreport("alignreport", "InputTypes", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(palignreport);
-               CommandParameter ptaxon("taxon", "String", "", "", "", "", "",false,true); parameters.push_back(ptaxon);
-               CommandParameter pdups("dups", "Boolean", "", "T", "", "", "",false,false); parameters.push_back(pdups);
-               CommandParameter pinputdir("inputdir", "String", "", "", "", "", "",false,false); parameters.push_back(pinputdir);
-               CommandParameter poutputdir("outputdir", "String", "", "", "", "", "",false,false); parameters.push_back(poutputdir);
+               CommandParameter pfasta("fasta", "InputTypes", "", "", "none", "FNGLT", "none","fasta",false,false,true); parameters.push_back(pfasta);
+        CommandParameter pname("name", "InputTypes", "", "", "NameCount", "FNGLT", "none","name",false,false,true); parameters.push_back(pname);
+        CommandParameter pcount("count", "InputTypes", "", "", "NameCount-CountGroup", "FNGLT", "none","count",false,false,true); parameters.push_back(pcount);
+               CommandParameter pgroup("group", "InputTypes", "", "", "CountGroup", "FNGLT", "none","group",false,false,true); parameters.push_back(pgroup);
+               CommandParameter plist("list", "InputTypes", "", "", "none", "FNGLT", "none","list",false,false,true); parameters.push_back(plist);
+               CommandParameter ptaxonomy("taxonomy", "InputTypes", "", "", "none", "FNGLT", "none","taxonomy",false,true,true); parameters.push_back(ptaxonomy);
+               CommandParameter palignreport("alignreport", "InputTypes", "", "", "none", "FNGLT", "none","alignreport",false,false); parameters.push_back(palignreport);
+               CommandParameter ptaxon("taxon", "String", "", "", "", "", "","",false,true,true); parameters.push_back(ptaxon);
+               CommandParameter pdups("dups", "Boolean", "", "T", "", "", "","",false,false); parameters.push_back(pdups);
+               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);          }
@@ -59,31 +60,27 @@ string RemoveLineageCommand::getHelpString(){
        }
 }
 //**********************************************************************************************************************
-string RemoveLineageCommand::getOutputFileNameTag(string type, string inputName=""){   
-       try {
-        string outputFileName = "";
-               map<string, vector<string> >::iterator it;
+string RemoveLineageCommand::getOutputPattern(string type) {
+    try {
+        string pattern = "";
         
-        //is this a type this command creates
-        it = outputTypes.find(type);
-        if (it == outputTypes.end()) {  m->mothurOut("[ERROR]: this command doesn't create a " + type + " output file.\n"); }
-        else {
-            if (type == "fasta")            {   outputFileName =  "pick" + m->getExtension(inputName);   }
-            else if (type == "taxonomy")    {   outputFileName =  "pick" + m->getExtension(inputName);   }
-            else if (type == "name")        {   outputFileName =  "pick" + m->getExtension(inputName);   }
-            else if (type == "group")       {   outputFileName =  "pick" + m->getExtension(inputName);   }
-            else if (type == "list")        {   outputFileName =  "pick" + m->getExtension(inputName);   }
-            else if (type == "count")       {   outputFileName =  "pick.count.table";   }
-            else if (type == "alignreport")      {   outputFileName =  "pick.align.report";   }
-            else { m->mothurOut("[ERROR]: No definition for type " + type + " output file tag.\n"); m->control_pressed = true;  }
-        }
-        return outputFileName;
-       }
-       catch(exception& e) {
-               m->errorOut(e, "RemoveLineageCommand", "getOutputFileNameTag");
-               exit(1);
-       }
+        if (type == "fasta")            {   pattern = "[filename],pick,[extension]";    }
+        else if (type == "taxonomy")    {   pattern = "[filename],pick,[extension]";    }
+        else if (type == "name")        {   pattern = "[filename],pick,[extension]";    }
+        else if (type == "group")       {   pattern = "[filename],pick,[extension]";    }
+        else if (type == "count")       {   pattern = "[filename],pick,[extension]";    }
+        else if (type == "list")        {   pattern = "[filename],pick,[extension]";    }
+        else if (type == "alignreport")      {   pattern = "[filename],pick.align.report";    }
+        else { m->mothurOut("[ERROR]: No definition for type " + type + " output pattern.\n"); m->control_pressed = true;  }
+        
+        return pattern;
+    }
+    catch(exception& e) {
+        m->errorOut(e, "RemoveLineageCommand", "getOutputPattern");
+        exit(1);
+    }
 }
+
 //**********************************************************************************************************************
 RemoveLineageCommand::RemoveLineageCommand(){  
        try {
@@ -364,7 +361,10 @@ int RemoveLineageCommand::readFasta(){
        try {
                string thisOutputDir = outputDir;
                if (outputDir == "") {  thisOutputDir += m->hasPath(fastafile);  }
-               string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(fastafile)) + getOutputFileNameTag("fasta", fastafile);         
+               map<string, string> variables; 
+        variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(fastafile));
+        variables["[extension]"] = m->getExtension(fastafile);
+               string outputFileName = getOutputFileName("fasta", variables);  
                ofstream out;
                m->openOutputFile(outputFileName, out);
                
@@ -409,7 +409,10 @@ int RemoveLineageCommand::readList(){
        try {
                string thisOutputDir = outputDir;
                if (outputDir == "") {  thisOutputDir += m->hasPath(listfile);  }
-               string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(listfile)) + getOutputFileNameTag("list", listfile);            
+               map<string, string> variables; 
+        variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(listfile));
+        variables["[extension]"] = m->getExtension(listfile);
+               string outputFileName = getOutputFileName("list", variables);   
                ofstream out;
                m->openOutputFile(outputFileName, out);
                
@@ -479,7 +482,10 @@ int RemoveLineageCommand::readName(){
        try {
                string thisOutputDir = outputDir;
                if (outputDir == "") {  thisOutputDir += m->hasPath(namefile);  }
-               string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(namefile)) + getOutputFileNameTag("name", namefile);
+               map<string, string> variables; 
+               variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(namefile));
+        variables["[extension]"] = m->getExtension(namefile);
+               string outputFileName = getOutputFileName("name", variables);
                ofstream out;
                m->openOutputFile(outputFileName, out);
 
@@ -555,7 +561,11 @@ int RemoveLineageCommand::readCount(){
        try {
                string thisOutputDir = outputDir;
                if (outputDir == "") {  thisOutputDir += m->hasPath(countfile);  }
-               string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(countfile)) + getOutputFileNameTag("count", countfile);
+               map<string, string> variables; 
+               variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(countfile));
+        variables["[extension]"] = m->getExtension(countfile);
+               string outputFileName = getOutputFileName("count", variables);
+
                
                ofstream out;
                m->openOutputFile(outputFileName, out);
@@ -585,6 +595,13 @@ int RemoveLineageCommand::readCount(){
         }
         in.close();
                out.close();
+        
+        //check for groups that have been eliminated
+        CountTable ct;
+        if (ct.testGroups(outputFileName)) {
+            ct.readTable(outputFileName);
+            ct.printTable(outputFileName);
+        }
                
                if (wroteSomething == false) {  m->mothurOut("Your group file contains only sequences from " + taxons + "."); m->mothurOutEndLine();  }
                outputTypes["count"].push_back(outputFileName); outputNames.push_back(outputFileName);
@@ -601,7 +618,11 @@ int RemoveLineageCommand::readGroup(){
        try {
                string thisOutputDir = outputDir;
                if (outputDir == "") {  thisOutputDir += m->hasPath(groupfile);  }
-               string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(groupfile)) + getOutputFileNameTag("group", groupfile);         
+               map<string, string> variables; 
+               variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(groupfile));
+        variables["[extension]"] = m->getExtension(groupfile);
+               string outputFileName = getOutputFileName("group", variables);
+       
                ofstream out;
                m->openOutputFile(outputFileName, out);
 
@@ -643,7 +664,10 @@ int RemoveLineageCommand::readTax(){
        try {
                string thisOutputDir = outputDir;
                if (outputDir == "") {  thisOutputDir += m->hasPath(taxfile);  }
-               string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(taxfile)) + getOutputFileNameTag("taxonomy", taxfile);
+               map<string, string> variables; 
+               variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(taxfile));
+        variables["[extension]"] = m->getExtension(taxfile);
+               string outputFileName = getOutputFileName("taxonomy", variables);
                ofstream out;
                m->openOutputFile(outputFileName, out);
                
@@ -678,15 +702,17 @@ int RemoveLineageCommand::readTax(){
                        
                        bool remove = false;
                        
+            string noQuotesTax = m->removeQuotes(tax);
+            
                        for (int j = 0; j < listOfTaxons.size(); j++) {
-                               string newtax = tax;
+                               string newtax = noQuotesTax;
                                
                                //if the users file contains confidence scores we want to ignore them when searching for the taxons, unless the taxon has them
                                if (!taxonsHasConfidence[j]) {
                                        
-                                       int hasConfidences = tax.find_first_of('(');
+                                       int hasConfidences = noQuotesTax.find_first_of('(');
                                        if (hasConfidences != string::npos) { 
-                                               newtax = tax;
+                                               newtax = noQuotesTax;
                                                m->removeConfidences(newtax);
                                        }
                                        
@@ -701,7 +727,7 @@ int RemoveLineageCommand::readTax(){
                                        }
                                        
                                }else{//if taxons has them and you don't them remove taxons
-                                       int hasConfidences = tax.find_first_of('(');
+                                       int hasConfidences = noQuotesTax.find_first_of('(');
                                        if (hasConfidences == string::npos) { 
                                                
                                                int pos = newtax.find(noConfidenceTaxons[j]);
@@ -716,10 +742,10 @@ int RemoveLineageCommand::readTax(){
                                        }else { //both have confidences so we want to make sure the users confidences are greater then or equal to the taxons
                                                //first remove confidences from both and see if the taxonomy exists
                                                
-                                               string noNewTax = tax;
-                                               int hasConfidences = tax.find_first_of('(');
+                                               string noNewTax = noQuotesTax;
+                                               int hasConfidences = noQuotesTax.find_first_of('(');
                                                if (hasConfidences != string::npos) { 
-                                                       noNewTax = tax;
+                                                       noNewTax = noQuotesTax;
                                                        m->removeConfidences(noNewTax);
                                                }
                                                
@@ -804,25 +830,30 @@ vector< map<string, float> > RemoveLineageCommand::getTaxons(string tax) {
                int taxLength = tax.length();
                for(int i=0;i<taxLength;i++){
                        if(tax[i] == ';'){
-                               
-                               int openParen = taxon.find_first_of('(');
+                
+                               int openParen = taxon.find_last_of('(');
                                int closeParen = taxon.find_last_of(')');
                                
                                string newtaxon, confidence;
                                if ((openParen != string::npos) && (closeParen != string::npos)) {
-                                       newtaxon = taxon.substr(0, openParen); //rip off confidence
-                                       confidence = taxon.substr((openParen+1), (closeParen-openParen-1));  
+                    string confidenceScore = taxon.substr(openParen+1, (closeParen-(openParen+1)));
+                    if (m->isNumeric1(confidenceScore)) {  //its a confidence
+                        newtaxon = taxon.substr(0, openParen); //rip off confidence
+                        confidence = taxon.substr((openParen+1), (closeParen-openParen-1));  
+                    }else { //its part of the taxon
+                        newtaxon = taxon;
+                        confidence = "0";
+                    }
                                }else{
                                        newtaxon = taxon;
                                        confidence = "0";
-                               }
+                               } 
                                float con = 0;
                                convert(confidence, con);
                                
                                map<string, float> temp;
                                temp[newtaxon] = con;
                                t.push_back(temp);
-                               
                                taxon = "";
                        }
                        else{
@@ -843,7 +874,10 @@ int RemoveLineageCommand::readAlign(){
        try {
                string thisOutputDir = outputDir;
                if (outputDir == "") {  thisOutputDir += m->hasPath(alignfile);  }
-               string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(alignfile)) + getOutputFileNameTag("alignreport");
+        map<string, string> variables; 
+               variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(alignfile));
+        variables["[extension]"] = m->getExtension(alignfile);
+               string outputFileName = getOutputFileName("alignreport", variables);
                
                ofstream out;
                m->openOutputFile(outputFileName, out);