]> git.donarmstrong.com Git - mothur.git/blobdiff - listseqscommand.cpp
changed random forest output filename
[mothur.git] / listseqscommand.cpp
index 833ac952a8db761b16ba59d9b53b561bef07ad0b..cf884705cb26f341ef08713b118af32fd49c5bdf 100644 (file)
 #include "listseqscommand.h"
 #include "sequence.hpp"
 #include "listvector.hpp"
+#include "counttable.h"
 
 
 //**********************************************************************************************************************
 vector<string> ListSeqsCommand::setParameters(){       
        try {
-               CommandParameter pfasta("fasta", "InputTypes", "", "", "FNGLT", "FNGLT", "none",false,false); parameters.push_back(pfasta);
-               CommandParameter pname("name", "InputTypes", "", "", "FNGLT", "FNGLT", "none",false,false); parameters.push_back(pname);
-               CommandParameter pgroup("group", "InputTypes", "", "", "FNGLT", "FNGLT", "none",false,false); parameters.push_back(pgroup);
-               CommandParameter plist("list", "InputTypes", "", "", "FNGLT", "FNGLT", "none",false,false); parameters.push_back(plist);
-               CommandParameter ptaxonomy("taxonomy", "InputTypes", "", "", "FNGLT", "FNGLT", "none",false,false); parameters.push_back(ptaxonomy);
-               CommandParameter palignreport("alignreport", "InputTypes", "", "", "FNGLT", "FNGLT", "none",false,false); parameters.push_back(palignreport);
-               CommandParameter pinputdir("inputdir", "String", "", "", "", "", "",false,false); parameters.push_back(pinputdir);
-               CommandParameter poutputdir("outputdir", "String", "", "", "", "", "",false,false); parameters.push_back(poutputdir);
+               CommandParameter pfasta("fasta", "InputTypes", "", "", "FNGLT", "FNGLT", "none","accnos",false,false,true); parameters.push_back(pfasta);
+               CommandParameter pname("name", "InputTypes", "", "", "FNGLT", "FNGLT", "none","accnos",false,false,true); parameters.push_back(pname);
+        CommandParameter pcount("count", "InputTypes", "", "", "FNGLT", "FNGLT", "none","accnos",false,false,true); parameters.push_back(pcount);
+               CommandParameter pgroup("group", "InputTypes", "", "", "FNGLT", "FNGLT", "none","accnos",false,false,true); parameters.push_back(pgroup);
+               CommandParameter plist("list", "InputTypes", "", "", "FNGLT", "FNGLT", "none","accnos",false,false,true); parameters.push_back(plist);
+               CommandParameter ptaxonomy("taxonomy", "InputTypes", "", "", "FNGLT", "FNGLT", "none","accnos",false,false,true); parameters.push_back(ptaxonomy);
+               CommandParameter palignreport("alignreport", "InputTypes", "", "", "FNGLT", "FNGLT", "none","accnos",false,false); parameters.push_back(palignreport);
+               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);          }
@@ -37,8 +39,8 @@ vector<string> ListSeqsCommand::setParameters(){
 string ListSeqsCommand::getHelpString(){       
        try {
                string helpString = "";
-               helpString += "The list.seqs command reads a fasta, name, group, list, taxonomy or alignreport file and outputs a .accnos file containing sequence names.\n";
-               helpString += "The list.seqs command parameters are fasta, name, group, list, taxonomy and alignreport.  You must provide one of these parameters.\n";
+               helpString += "The list.seqs command reads a fasta, name, group, count, list, taxonomy or alignreport file and outputs a .accnos file containing sequence names.\n";
+               helpString += "The list.seqs command parameters are fasta, name, group, count, list, taxonomy and alignreport.  You must provide one of these parameters.\n";
                helpString += "The list.seqs command should be in the following format: list.seqs(fasta=yourFasta).\n";
                helpString += "Example list.seqs(fasta=amazon.fasta).\n";
                helpString += "Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFasta).\n";
@@ -49,7 +51,21 @@ string ListSeqsCommand::getHelpString(){
                exit(1);
        }
 }
-
+//**********************************************************************************************************************
+string ListSeqsCommand::getOutputPattern(string type) {
+    try {
+        string pattern = "";
+        
+        if (type == "accnos") {  pattern = "[filename],accnos"; } 
+        else { m->mothurOut("[ERROR]: No definition for type " + type + " output pattern.\n"); m->control_pressed = true;  }
+        
+        return pattern;
+    }
+    catch(exception& e) {
+        m->errorOut(e, "ListSeqsCommand", "getOutputPattern");
+        exit(1);
+    }
+}
 //**********************************************************************************************************************
 ListSeqsCommand::ListSeqsCommand(){    
        try {
@@ -145,6 +161,14 @@ ListSeqsCommand::ListSeqsCommand(string option)  {
                                        //if the user has not given a path then, add inputdir. else leave path alone.
                                        if (path == "") {       parameters["taxonomy"] = 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;            }
+                               }
                        }
 
                        //check for required parameters
@@ -176,8 +200,13 @@ ListSeqsCommand::ListSeqsCommand(string option)  {
                        if (taxfile == "not open") { abort = true; }
                        else if (taxfile == "not found") {  taxfile = "";  }
                        else { m->setTaxonomyFile(taxfile); }
+            
+            countfile = validParameter.validFile(parameters, "count", true);
+                       if (countfile == "not open") { abort = true; }
+                       else if (countfile == "not found") {  countfile = "";  }
+                       else { m->setCountTableFile(countfile); }
                        
-                       if ((fastafile == "") && (namefile == "") && (listfile == "") && (groupfile == "") && (alignfile == "") && (taxfile == ""))  { m->mothurOut("You must provide a file."); m->mothurOutEndLine(); abort = true; }
+                       if ((countfile == "") && (fastafile == "") && (namefile == "") && (listfile == "") && (groupfile == "") && (alignfile == "") && (taxfile == ""))  { m->mothurOut("You must provide a file."); m->mothurOutEndLine(); abort = true; }
                        
                        int okay = 1;
                        if (outputDir != "") { okay++; }
@@ -206,6 +235,7 @@ int ListSeqsCommand::execute(){
                else if (alignfile != "")       {       inputFileName = alignfile;      readAlign();    }
                else if (listfile != "")        {       inputFileName = listfile;       readList();             }
                else if (taxfile != "")         {       inputFileName = taxfile;        readTax();              }
+        else if (countfile != "")      {       inputFileName = countfile;      readCount();    }
                
                if (m->control_pressed) { outputTypes.clear();  return 0; }
                
@@ -214,7 +244,9 @@ int ListSeqsCommand::execute(){
                
                if (outputDir == "") {  outputDir += m->hasPath(inputFileName);  }
                
-               string outputFileName = outputDir + m->getRootName(m->getSimpleName(inputFileName)) + "accnos";
+        map<string, string> variables; 
+        variables["[filename]"] = outputDir + m->getRootName(m->getSimpleName(inputFileName));
+               string outputFileName = getOutputFileName("accnos", variables);
 
                ofstream out;
                m->openOutputFile(outputFileName, out);
@@ -234,7 +266,7 @@ int ListSeqsCommand::execute(){
                m->setAccnosFile(outputFileName);
                
                m->mothurOutEndLine();
-               m->mothurOut("Output File Name: "); m->mothurOutEndLine();
+               m->mothurOut("Output File Names: "); m->mothurOutEndLine();
                m->mothurOut(outputFileName); m->mothurOutEndLine();    
                m->mothurOutEndLine();
                
@@ -265,7 +297,7 @@ int ListSeqsCommand::readFasta(){
                //ofstream out;
                //string newFastaName = outputDir + m->getRootName(m->getSimpleName(fastafile)) + "numsAdded.fasta";
                //m->openOutputFile(newFastaName, out);
-               //int count = 1;
+               int count = 1;
                //string lastName = "";
                
                while(!in.eof()){
@@ -274,17 +306,11 @@ int ListSeqsCommand::readFasta(){
                        
                        Sequence currSeq(in);
                        name = currSeq.getName();
-                       //if (lastName == "") { lastName = name; }
-                       //if (name != lastName) { count = 1; }
-               //      lastName = name;
-                       
-                       //Sequence newSeq(name+"_"+toString(count), currSeq.getAligned());
-                       //newSeq.printSequence(out);
                        
                        if (name != "") {  names.push_back(name);  }
                        
                        m->gobble(in);
-                       //count++;
+                       if (m->debug) { count++; cout << "[DEBUG]: count = " + toString(count) + ", name = " + currSeq.getName() + "\n"; }
                }
                in.close();     
                //out.close();
@@ -385,7 +411,24 @@ int ListSeqsCommand::readGroup(){
                exit(1);
        }
 }
-
+//**********************************************************************************************************************
+int ListSeqsCommand::readCount(){
+       try {
+               CountTable ct;
+               ct.readTable(countfile, false);
+        
+        if (m->control_pressed) { return 0; }
+        
+        names = ct.getNamesOfSeqs();
+        
+        return 0;
+        
+       }
+       catch(exception& e) {
+               m->errorOut(e, "ListSeqsCommand", "readCount");
+               exit(1);
+       }
+}
 //**********************************************************************************************************************
 //alignreport file has a column header line then all other lines contain 16 columns.  we just want the first column since that contains the name
 int ListSeqsCommand::readAlign(){
@@ -400,14 +443,14 @@ int ListSeqsCommand::readAlign(){
                        if (!in.eof())  {       in >> junk;             }
                        else                    {       break;                  }
                }
-               
+               //m->getline(in);
                
                while(!in.eof()){
                
                        if (m->control_pressed) { in.close(); return 0; }
 
                        in >> name;                             //read from first column
-                       
+                       //m->getline(in);
                        //read rest
                        for (int i = 0; i < 15; i++) {  
                                if (!in.eof())  {       in >> junk;             }