]> git.donarmstrong.com Git - mothur.git/blobdiff - removeseqscommand.cpp
done testing 1.14.0
[mothur.git] / removeseqscommand.cpp
index 5f5fe6535d6e159850694204efc83253387b9d4c..f1804ed8b826d00b4993a708804733335bb1b194 100644 (file)
 #include "listvector.hpp"
 
 //**********************************************************************************************************************
-
+vector<string> RemoveSeqsCommand::getValidParameters(){        
+       try {
+               string Array[] =  {"fasta","name", "group", "alignreport", "accnos", "list","taxonomy","outputdir","inputdir", "dups" };
+               vector<string> myArray (Array, Array+(sizeof(Array)/sizeof(string)));
+               return myArray;
+       }
+       catch(exception& e) {
+               m->errorOut(e, "RemoveSeqsCommand", "getValidParameters");
+               exit(1);
+       }
+}
+//**********************************************************************************************************************
+RemoveSeqsCommand::RemoveSeqsCommand(){        
+       try {
+               abort = true;
+               //initialize outputTypes
+               vector<string> tempOutNames;
+               outputTypes["fasta"] = tempOutNames;
+               outputTypes["taxonomy"] = tempOutNames;
+               outputTypes["name"] = tempOutNames;
+               outputTypes["group"] = tempOutNames;
+               outputTypes["alignreport"] = tempOutNames;
+               outputTypes["list"] = tempOutNames;
+       }
+       catch(exception& e) {
+               m->errorOut(e, "RemoveSeqsCommand", "RemoveSeqsCommand");
+               exit(1);
+       }
+}
+//**********************************************************************************************************************
+vector<string> RemoveSeqsCommand::getRequiredParameters(){     
+       try {
+               string Array[] =  {"accnos"};
+               vector<string> myArray (Array, Array+(sizeof(Array)/sizeof(string)));
+               return myArray;
+       }
+       catch(exception& e) {
+               m->errorOut(e, "RemoveSeqsCommand", "getRequiredParameters");
+               exit(1);
+       }
+}
+//**********************************************************************************************************************
+vector<string> RemoveSeqsCommand::getRequiredFiles(){  
+       try {
+               vector<string> myArray;
+               return myArray;
+       }
+       catch(exception& e) {
+               m->errorOut(e, "RemoveSeqsCommand", "getRequiredFiles");
+               exit(1);
+       }
+}
+//**********************************************************************************************************************
 RemoveSeqsCommand::RemoveSeqsCommand(string option)  {
        try {
                abort = false;
@@ -36,6 +88,15 @@ RemoveSeqsCommand::RemoveSeqsCommand(string option)  {
                                if (validParameter.isValidParameter(it->first, myArray, it->second) != true) {  abort = true;  }
                        }
                        
+                       //initialize outputTypes
+                       vector<string> tempOutNames;
+                       outputTypes["fasta"] = tempOutNames;
+                       outputTypes["taxonomy"] = tempOutNames;
+                       outputTypes["name"] = tempOutNames;
+                       outputTypes["group"] = tempOutNames;
+                       outputTypes["alignreport"] = tempOutNames;
+                       outputTypes["list"] = tempOutNames;
+                       
                        //if the user changes the output directory command factory will send this info to us in the output parameter 
                        outputDir = validParameter.validFile(parameters, "outputdir", false);           if (outputDir == "not found"){  outputDir = "";         }
                        
@@ -47,7 +108,7 @@ RemoveSeqsCommand::RemoveSeqsCommand(string option)  {
                                it = parameters.find("alignreport");
                                //user has given a template file
                                if(it != parameters.end()){ 
-                                       path = hasPath(it->second);
+                                       path = m->hasPath(it->second);
                                        //if the user has not given a path then, add inputdir. else leave path alone.
                                        if (path == "") {       parameters["alignreport"] = inputDir + it->second;              }
                                }
@@ -55,7 +116,7 @@ RemoveSeqsCommand::RemoveSeqsCommand(string option)  {
                                it = parameters.find("fasta");
                                //user has given a template file
                                if(it != parameters.end()){ 
-                                       path = hasPath(it->second);
+                                       path = m->hasPath(it->second);
                                        //if the user has not given a path then, add inputdir. else leave path alone.
                                        if (path == "") {       parameters["fasta"] = inputDir + it->second;            }
                                }
@@ -63,7 +124,7 @@ RemoveSeqsCommand::RemoveSeqsCommand(string option)  {
                                it = parameters.find("accnos");
                                //user has given a template file
                                if(it != parameters.end()){ 
-                                       path = hasPath(it->second);
+                                       path = m->hasPath(it->second);
                                        //if the user has not given a path then, add inputdir. else leave path alone.
                                        if (path == "") {       parameters["accnos"] = inputDir + it->second;           }
                                }
@@ -71,7 +132,7 @@ RemoveSeqsCommand::RemoveSeqsCommand(string option)  {
                                it = parameters.find("list");
                                //user has given a template file
                                if(it != parameters.end()){ 
-                                       path = hasPath(it->second);
+                                       path = m->hasPath(it->second);
                                        //if the user has not given a path then, add inputdir. else leave path alone.
                                        if (path == "") {       parameters["list"] = inputDir + it->second;             }
                                }
@@ -79,7 +140,7 @@ RemoveSeqsCommand::RemoveSeqsCommand(string option)  {
                                it = parameters.find("name");
                                //user has given a template file
                                if(it != parameters.end()){ 
-                                       path = hasPath(it->second);
+                                       path = m->hasPath(it->second);
                                        //if the user has not given a path then, add inputdir. else leave path alone.
                                        if (path == "") {       parameters["name"] = inputDir + it->second;             }
                                }
@@ -87,7 +148,7 @@ RemoveSeqsCommand::RemoveSeqsCommand(string option)  {
                                it = parameters.find("group");
                                //user has given a template file
                                if(it != parameters.end()){ 
-                                       path = hasPath(it->second);
+                                       path = m->hasPath(it->second);
                                        //if the user has not given a path then, add inputdir. else leave path alone.
                                        if (path == "") {       parameters["group"] = inputDir + it->second;            }
                                }
@@ -95,7 +156,7 @@ RemoveSeqsCommand::RemoveSeqsCommand(string option)  {
                                it = parameters.find("taxonomy");
                                //user has given a template file
                                if(it != parameters.end()){ 
-                                       path = hasPath(it->second);
+                                       path = m->hasPath(it->second);
                                        //if the user has not given a path then, add inputdir. else leave path alone.
                                        if (path == "") {       parameters["taxonomy"] = inputDir + it->second;         }
                                }
@@ -133,8 +194,12 @@ RemoveSeqsCommand::RemoveSeqsCommand(string option)  {
 
                        
                        string usedDups = "true";
-                       string temp = validParameter.validFile(parameters, "dups", false);      if (temp == "not found") { temp = "false"; usedDups = ""; }
-                       dups = isTrue(temp);
+                       string temp = validParameter.validFile(parameters, "dups", false);      
+                       if (temp == "not found") { 
+                               if (namefile != "") {  temp = "true";                                   }
+                               else                            {  temp = "false"; usedDups = "";       }
+                       }
+                       dups = m->isTrue(temp);
                        
                        if ((fastafile == "") && (namefile == "") && (groupfile == "") && (alignfile == "") && (listfile == "") && (taxfile == ""))  { m->mothurOut("You must provide at least one of the following: fasta, name, group, taxonomy, alignreport or list."); m->mothurOutEndLine(); abort = true; }
                        
@@ -154,7 +219,7 @@ void RemoveSeqsCommand::help(){
                m->mothurOut("The remove.seqs command reads an .accnos file and at least one of the following file types: fasta, name, group, list, taxonomy or alignreport file.\n");
                m->mothurOut("It outputs a file containing the sequences NOT in the .accnos file.\n");
                m->mothurOut("The remove.seqs command parameters are accnos, fasta, name, group, list, taxonomy, alignreport and dups.  You must provide accnos and at least one of the file parameters.\n");
-               m->mothurOut("The dups parameter allows you to remove the entire line from a name file if you remove any name from the line. default=false. \n");
+               m->mothurOut("The dups parameter allows you to remove the entire line from a name file if you remove any name from the line. default=true. \n");
                m->mothurOut("The remove.seqs command should be in the following format: remove.seqs(accnos=yourAccnos, fasta=yourFasta).\n");
                m->mothurOut("Example remove.seqs(accnos=amazon.accnos, fasta=amazon.fasta).\n");
                m->mothurOut("Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFasta).\n\n");
@@ -206,13 +271,15 @@ int RemoveSeqsCommand::execute(){
 //**********************************************************************************************************************
 int RemoveSeqsCommand::readFasta(){
        try {
-               if (outputDir == "") {  outputDir += hasPath(fastafile);  }
-               string outputFileName = outputDir + getRootName(getSimpleName(fastafile)) + "pick" + getExtension(fastafile);
+               string thisOutputDir = outputDir;
+               if (outputDir == "") {  thisOutputDir += m->hasPath(fastafile);  }
+               string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(fastafile)) + "pick" + m->getExtension(fastafile);
+               
                ofstream out;
-               openOutputFile(outputFileName, out);
+               m->openOutputFile(outputFileName, out);
                
                ifstream in;
-               openInputFile(fastafile, in);
+               m->openInputFile(fastafile, in);
                string name;
                
                bool wroteSomething = false;
@@ -231,15 +298,13 @@ int RemoveSeqsCommand::readFasta(){
                                        currSeq.printSequence(out);
                                }
                        }
-                       gobble(in);
+                       m->gobble(in);
                }
                in.close();     
                out.close();
                
-               if (wroteSomething == false) {
-                       m->mothurOut("Your file contains only sequences from the .accnos file."); m->mothurOutEndLine();
-                       remove(outputFileName.c_str()); 
-               }else { outputNames.push_back(outputFileName); }
+               if (wroteSomething == false) {  m->mothurOut("Your file contains only sequences from the .accnos file."); m->mothurOutEndLine();  }
+               outputTypes["fasta"].push_back(outputFileName); 
                
                return 0;
                
@@ -252,13 +317,15 @@ int RemoveSeqsCommand::readFasta(){
 //**********************************************************************************************************************
 int RemoveSeqsCommand::readList(){
        try {
-               if (outputDir == "") {  outputDir += hasPath(listfile);  }
-               string outputFileName = outputDir + getRootName(getSimpleName(listfile)) + "pick" +  getExtension(listfile);
+               string thisOutputDir = outputDir;
+               if (outputDir == "") {  thisOutputDir += m->hasPath(listfile);  }
+               string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(listfile)) + "pick" +  m->getExtension(listfile);
+               
                ofstream out;
-               openOutputFile(outputFileName, out);
+               m->openOutputFile(outputFileName, out);
                
                ifstream in;
-               openInputFile(listfile, in);
+               m->openInputFile(listfile, in);
                
                bool wroteSomething = false;
                
@@ -302,16 +369,14 @@ int RemoveSeqsCommand::readList(){
                                newList.print(out);
                        }
                        
-                       gobble(in);
+                       m->gobble(in);
                }
                in.close();     
                out.close();
                
-               if (wroteSomething == false) {
-                       m->mothurOut("Your file contains only sequences from the .accnos file."); m->mothurOutEndLine();
-                       remove(outputFileName.c_str()); 
-               }else { outputNames.push_back(outputFileName); }
-               
+               if (wroteSomething == false) {  m->mothurOut("Your file contains only sequences from the .accnos file."); m->mothurOutEndLine();  }
+               outputTypes["list"].push_back(outputFileName); 
+                               
                return 0;
 
        }
@@ -323,14 +388,15 @@ int RemoveSeqsCommand::readList(){
 //**********************************************************************************************************************
 int RemoveSeqsCommand::readName(){
        try {
-               if (outputDir == "") {  outputDir += hasPath(namefile);  }
-               string outputFileName = outputDir + getRootName(getSimpleName(namefile)) + "pick" + getExtension(namefile);
+               string thisOutputDir = outputDir;
+               if (outputDir == "") {  thisOutputDir += m->hasPath(namefile);  }
+               string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(namefile)) + "pick" + m->getExtension(namefile);
 
                ofstream out;
-               openOutputFile(outputFileName, out);
+               m->openOutputFile(outputFileName, out);
 
                ifstream in;
-               openInputFile(namefile, in);
+               m->openInputFile(namefile, in);
                string name, firstCol, secondCol;
                
                bool wroteSomething = false;
@@ -338,7 +404,7 @@ int RemoveSeqsCommand::readName(){
                while(!in.eof()){
                        if (m->control_pressed) { in.close();  out.close();  remove(outputFileName.c_str());  return 0; }
 
-                       in >> firstCol;                         
+                       in >> firstCol;         m->gobble(in);          
                        in >> secondCol;                        
 
                        vector<string> parsedNames;
@@ -347,7 +413,6 @@ int RemoveSeqsCommand::readName(){
                                name = secondCol.substr(0,secondCol.find_first_of(','));
                                secondCol = secondCol.substr(secondCol.find_first_of(',')+1, secondCol.length());
                                parsedNames.push_back(name);
-
                        }
                        
                        //get name after last ,
@@ -390,16 +455,14 @@ int RemoveSeqsCommand::readName(){
                                        }
                                }
                        }
-                       gobble(in);
+                       m->gobble(in);
                }
                in.close();
                out.close();
-               
-               if (wroteSomething == false) {
-                       m->mothurOut("Your file contains only sequences from the .accnos file."); m->mothurOutEndLine();
-                       remove(outputFileName.c_str()); 
-               }else { outputNames.push_back(outputFileName); }
-               
+
+               if (wroteSomething == false) {  m->mothurOut("Your file contains only sequences from the .accnos file."); m->mothurOutEndLine();  }
+               outputTypes["name"].push_back(outputFileName);
+                               
                return 0;
        }
        catch(exception& e) {
@@ -411,13 +474,15 @@ int RemoveSeqsCommand::readName(){
 //**********************************************************************************************************************
 int RemoveSeqsCommand::readGroup(){
        try {
-               if (outputDir == "") {  outputDir += hasPath(groupfile);  }
-               string outputFileName = outputDir + getRootName(getSimpleName(groupfile)) + "pick" + getExtension(groupfile);
+               string thisOutputDir = outputDir;
+               if (outputDir == "") {  thisOutputDir += m->hasPath(groupfile);  }
+               string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(groupfile)) + "pick" + m->getExtension(groupfile);
+               
                ofstream out;
-               openOutputFile(outputFileName, out);
+               m->openOutputFile(outputFileName, out);
 
                ifstream in;
-               openInputFile(groupfile, in);
+               m->openInputFile(groupfile, in);
                string name, group;
                
                bool wroteSomething = false;
@@ -434,15 +499,13 @@ int RemoveSeqsCommand::readGroup(){
                                out << name << '\t' << group << endl;
                        }
                                        
-                       gobble(in);
+                       m->gobble(in);
                }
                in.close();
                out.close();
                
-               if (wroteSomething == false) {
-                       m->mothurOut("Your file contains only sequences from the .accnos file."); m->mothurOutEndLine();
-                       remove(outputFileName.c_str()); 
-               }else { outputNames.push_back(outputFileName); }
+               if (wroteSomething == false) {  m->mothurOut("Your file contains only sequences from the .accnos file."); m->mothurOutEndLine();  }
+               outputTypes["group"].push_back(outputFileName); 
                
                return 0;
        }
@@ -454,13 +517,14 @@ int RemoveSeqsCommand::readGroup(){
 //**********************************************************************************************************************
 int RemoveSeqsCommand::readTax(){
        try {
-               if (outputDir == "") {  outputDir += hasPath(taxfile);  }
-               string outputFileName = outputDir + getRootName(getSimpleName(taxfile)) + "pick" + getExtension(taxfile);
+               string thisOutputDir = outputDir;
+               if (outputDir == "") {  thisOutputDir += m->hasPath(taxfile);  }
+               string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(taxfile)) + "pick" + m->getExtension(taxfile);
                ofstream out;
-               openOutputFile(outputFileName, out);
+               m->openOutputFile(outputFileName, out);
 
                ifstream in;
-               openInputFile(taxfile, in);
+               m->openInputFile(taxfile, in);
                string name, tax;
                
                bool wroteSomething = false;
@@ -477,15 +541,13 @@ int RemoveSeqsCommand::readTax(){
                                out << name << '\t' << tax << endl;
                        }
                                        
-                       gobble(in);
+                       m->gobble(in);
                }
                in.close();
                out.close();
                
-               if (wroteSomething == false) {
-                       m->mothurOut("Your file contains only sequences from the .accnos file."); m->mothurOutEndLine();
-                       remove(outputFileName.c_str()); 
-               }else { outputNames.push_back(outputFileName); }
+               if (wroteSomething == false) {  m->mothurOut("Your file contains only sequences from the .accnos file."); m->mothurOutEndLine();  }
+               outputTypes["taxonomy"].push_back(outputFileName);
                
                return 0;
        }
@@ -498,13 +560,15 @@ int RemoveSeqsCommand::readTax(){
 //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 RemoveSeqsCommand::readAlign(){
        try {
-               if (outputDir == "") {  outputDir += hasPath(alignfile);  }
-               string outputFileName = outputDir + getRootName(getSimpleName(alignfile)) + "pick.align.report";
+               string thisOutputDir = outputDir;
+               if (outputDir == "") {  thisOutputDir += m->hasPath(alignfile);  }
+               string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(alignfile)) + "pick.align.report";
+               
                ofstream out;
-               openOutputFile(outputFileName, out);
+               m->openOutputFile(outputFileName, out);
 
                ifstream in;
-               openInputFile(alignfile, in);
+               m->openInputFile(alignfile, in);
                string name, junk;
                
                bool wroteSomething = false;
@@ -543,15 +607,13 @@ int RemoveSeqsCommand::readAlign(){
                                }
                        }
                        
-                       gobble(in);
+                       m->gobble(in);
                }
                in.close();
                out.close();
                
-               if (wroteSomething == false) {
-                       m->mothurOut("Your file contains only sequences from the .accnos file."); m->mothurOutEndLine();
-                       remove(outputFileName.c_str()); 
-               }else { outputNames.push_back(outputFileName); }
+               if (wroteSomething == false) {  m->mothurOut("Your file contains only sequences from the .accnos file."); m->mothurOutEndLine();  }
+               outputTypes["alignreport"].push_back(outputFileName);
                
                return 0;
                
@@ -566,7 +628,7 @@ void RemoveSeqsCommand::readAccnos(){
        try {
                
                ifstream in;
-               openInputFile(accnosfile, in);
+               m->openInputFile(accnosfile, in);
                string name;
                
                while(!in.eof()){
@@ -574,7 +636,7 @@ void RemoveSeqsCommand::readAccnos(){
                                                
                        names.insert(name);
                        
-                       gobble(in);
+                       m->gobble(in);
                }
                in.close();