]> git.donarmstrong.com Git - mothur.git/blobdiff - getseqscommand.cpp
added get.groups and remove.groups commands
[mothur.git] / getseqscommand.cpp
index ef0a1ac36de925af45e66c1c9420272272b32f2e..39c4fe001c8b9b19ef31c5a9a7f3ad98213301d6 100644 (file)
 #include "listvector.hpp"
 
 //**********************************************************************************************************************
-
+vector<string> GetSeqsCommand::getValidParameters(){   
+       try {
+               string Array[] =  {"fasta","name", "group", "qfile","alignreport", "accnos", "dups", "list","taxonomy","outputdir","inputdir"};
+               vector<string> myArray (Array, Array+(sizeof(Array)/sizeof(string)));
+               return myArray;
+       }
+       catch(exception& e) {
+               m->errorOut(e, "GetSeqsCommand", "getValidParameters");
+               exit(1);
+       }
+}
+//**********************************************************************************************************************
+GetSeqsCommand::GetSeqsCommand(){      
+       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;
+               outputTypes["qfile"] = tempOutNames;
+       }
+       catch(exception& e) {
+               m->errorOut(e, "GetSeqsCommand", "GetSeqsCommand");
+               exit(1);
+       }
+}
+//**********************************************************************************************************************
+vector<string> GetSeqsCommand::getRequiredParameters(){        
+       try {
+               string Array[] =  {"accnos"};
+               vector<string> myArray (Array, Array+(sizeof(Array)/sizeof(string)));
+               return myArray;
+       }
+       catch(exception& e) {
+               m->errorOut(e, "GetSeqsCommand", "getRequiredParameters");
+               exit(1);
+       }
+}
+//**********************************************************************************************************************
+vector<string> GetSeqsCommand::getRequiredFiles(){     
+       try {
+               vector<string> myArray;
+               return myArray;
+       }
+       catch(exception& e) {
+               m->errorOut(e, "GetSeqsCommand", "getRequiredFiles");
+               exit(1);
+       }
+}
+//**********************************************************************************************************************
 GetSeqsCommand::GetSeqsCommand(string option)  {
        try {
                abort = false;
@@ -22,7 +75,7 @@ GetSeqsCommand::GetSeqsCommand(string option)  {
                
                else {
                        //valid paramters for this command
-                       string Array[] =  {"fasta","name", "group", "alignreport", "accnos", "dups", "list","taxonomy","outputdir","inputdir"};
+                       string Array[] =  {"fasta","name", "group", "alignreport", "qfile", "accnos", "dups", "list","taxonomy","outputdir","inputdir"};
                        vector<string> myArray (Array, Array+(sizeof(Array)/sizeof(string)));
                        
                        OptionParser parser(option);
@@ -36,6 +89,16 @@ GetSeqsCommand::GetSeqsCommand(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;
+                       outputTypes["qfile"] = 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 +110,7 @@ GetSeqsCommand::GetSeqsCommand(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 +118,7 @@ GetSeqsCommand::GetSeqsCommand(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 +126,7 @@ GetSeqsCommand::GetSeqsCommand(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 +134,7 @@ GetSeqsCommand::GetSeqsCommand(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 +142,7 @@ GetSeqsCommand::GetSeqsCommand(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 +150,7 @@ GetSeqsCommand::GetSeqsCommand(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;            }
                                }
@@ -95,10 +158,18 @@ GetSeqsCommand::GetSeqsCommand(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;         }
                                }
+                               
+                               it = parameters.find("qfile");
+                               //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["qfile"] = inputDir + it->second;            }
+                               }
                        }
 
                        
@@ -131,11 +202,15 @@ GetSeqsCommand::GetSeqsCommand(string option)  {
                        if (taxfile == "not open") { abort = true; }
                        else if (taxfile == "not found") {  taxfile = "";  }
                        
+                       qualfile = validParameter.validFile(parameters, "qfile", true);
+                       if (qualfile == "not open") { abort = true; }
+                       else if (qualfile == "not found") {  qualfile = "";  }
+                       
                        string usedDups = "true";
                        string temp = validParameter.validFile(parameters, "dups", false);      if (temp == "not found") { temp = "false"; usedDups = ""; }
-                       dups = isTrue(temp);
+                       dups = m->isTrue(temp);
                        
-                       if ((fastafile == "") && (namefile == "") && (groupfile == "") && (alignfile == "") && (listfile == "") && (taxfile == ""))  { m->mothurOut("You must provide one of the following: fasta, name, group, alignreport, taxonomy or listfile."); m->mothurOutEndLine(); abort = true; }
+                       if ((fastafile == "") && (namefile == "") && (groupfile == "") && (alignfile == "") && (listfile == "") && (taxfile == "") && (qualfile == ""))  { m->mothurOut("You must provide one of the following: fasta, name, group, alignreport, taxonomy, quality or listfile."); m->mothurOutEndLine(); abort = true; }
                
                        if ((usedDups != "") && (namefile == "")) {  m->mothurOut("You may only use dups with the name option."); m->mothurOutEndLine();  abort = true; }                       
 
@@ -151,9 +226,9 @@ GetSeqsCommand::GetSeqsCommand(string option)  {
 
 void GetSeqsCommand::help(){
        try {
-               m->mothurOut("The get.seqs command reads an .accnos file and any of the following file types: fasta, name, group, list, taxonomy or alignreport file.\n");
+               m->mothurOut("The get.seqs command reads an .accnos file and any of the following file types: fasta, name, group, list, taxonomy, quality or alignreport file.\n");
                m->mothurOut("It outputs a file containing only the sequences in the .accnos file.\n");
-               m->mothurOut("The get.seqs command parameters are accnos, fasta, name, group, list, taxonomy, alignreport and dups.  You must provide accnos and at least one of the other parameters.\n");
+               m->mothurOut("The get.seqs command parameters are accnos, fasta, name, group, list, taxonomy, qfile, alignreport and dups.  You must provide accnos and at least one of the other parameters.\n");
                m->mothurOut("The dups parameter allows you to add the entire line from a name file if you add any name from the line. default=false. \n");
                m->mothurOut("The get.seqs command should be in the following format: get.seqs(accnos=yourAccnos, fasta=yourFasta).\n");
                m->mothurOut("Example get.seqs(accnos=amazon.accnos, fasta=amazon.fasta).\n");
@@ -184,8 +259,11 @@ int GetSeqsCommand::execute(){
                if (alignfile != "")            {               readAlign();    }
                if (listfile != "")                     {               readList();             }
                if (taxfile != "")                      {               readTax();              }
+               if (qualfile != "")                     {               readQual();             }
+               
+               if (m->control_pressed) { outputTypes.clear(); for (int i = 0; i < outputNames.size(); i++) {   remove(outputNames[i].c_str());  } return 0; }
                
-               if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) {        remove(outputNames[i].c_str());  } return 0; }
+               m->mothurOut("Selected " + toString(names.size()) + " sequences."); m->mothurOutEndLine();
                
                if (outputNames.size() != 0) {
                        m->mothurOutEndLine();
@@ -206,14 +284,15 @@ int GetSeqsCommand::execute(){
 //**********************************************************************************************************************
 int GetSeqsCommand::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;
@@ -233,13 +312,14 @@ int GetSeqsCommand::readFasta(){
                                        currSeq.printSequence(out);
                                }
                        }
-                       gobble(in);
+                       m->gobble(in);
                }
                in.close();     
                out.close();
                
+               
                if (wroteSomething == false) { m->mothurOut("Your file does not contain any sequence from the .accnos file."); m->mothurOutEndLine();  }
-               outputNames.push_back(outputFileName); 
+               outputNames.push_back(outputFileName);  outputTypes["fasta"].push_back(outputFileName); 
                
                return 0;
 
@@ -250,15 +330,81 @@ int GetSeqsCommand::readFasta(){
        }
 }
 //**********************************************************************************************************************
+int GetSeqsCommand::readQual(){
+       try {
+               string thisOutputDir = outputDir;
+               if (outputDir == "") {  thisOutputDir += m->hasPath(qualfile);  }
+               string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(qualfile)) + "pick" +  m->getExtension(qualfile);
+               ofstream out;
+               m->openOutputFile(outputFileName, out);
+               
+               
+               ifstream in;
+               m->openInputFile(qualfile, in);
+               string name;
+               
+               bool wroteSomething = false;
+               
+               
+               while(!in.eof()){       
+                       string saveName = "";
+                       string name = "";
+                       string scores = "";
+                       
+                       in >> name; 
+                               
+                       if (name.length() != 0) { 
+                               saveName = name.substr(1);
+                               while (!in.eof())       {       
+                                       char c = in.get(); 
+                                       if (c == 10 || c == 13){        break;  }
+                                       else { name += c; }     
+                               } 
+                               m->gobble(in);
+                       }
+                       
+                       while(in){
+                               char letter= in.get();
+                               if(letter == '>'){      in.putback(letter);     break;  }
+                               else{ scores += letter; }
+                       }
+                       
+                       m->gobble(in);
+                       
+                       if (names.count(saveName) != 0) {
+                               wroteSomething = true;
+                                               
+                               out << name << endl << scores;
+                       }
+                       
+                       m->gobble(in);
+               }
+               in.close();
+               out.close();
+               
+               
+               if (wroteSomething == false) { m->mothurOut("Your file does not contain any sequence from the .accnos file."); m->mothurOutEndLine();  }
+               outputNames.push_back(outputFileName);  outputTypes["qfile"].push_back(outputFileName); 
+               
+               return 0;
+               
+       }
+       catch(exception& e) {
+               m->errorOut(e, "GetSeqsCommand", "readQual");
+               exit(1);
+       }
+}
+//**********************************************************************************************************************
 int GetSeqsCommand::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;
                
@@ -304,13 +450,13 @@ int GetSeqsCommand::readList(){
                                newList.print(out);
                        }
                        
-                       gobble(in);
+                       m->gobble(in);
                }
                in.close();     
                out.close();
                
                if (wroteSomething == false) { m->mothurOut("Your file does not contain any sequence from the .accnos file."); m->mothurOutEndLine();  }
-               outputNames.push_back(outputFileName); 
+               outputNames.push_back(outputFileName); outputTypes["list"].push_back(outputFileName);
                
                return 0;
 
@@ -323,14 +469,15 @@ int GetSeqsCommand::readList(){
 //**********************************************************************************************************************
 int GetSeqsCommand::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;
@@ -396,13 +543,13 @@ int GetSeqsCommand::readName(){
                                        }
                                }
                        }
-                       gobble(in);
+                       m->gobble(in);
                }
                in.close();
                out.close();
                
                if (wroteSomething == false) { m->mothurOut("Your file does not contain any sequence from the .accnos file."); m->mothurOutEndLine();  }
-               outputNames.push_back(outputFileName); 
+               outputNames.push_back(outputFileName); outputTypes["name"].push_back(outputFileName);
                
                return 0;
                
@@ -416,14 +563,15 @@ int GetSeqsCommand::readName(){
 //**********************************************************************************************************************
 int GetSeqsCommand::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;
@@ -443,13 +591,13 @@ int GetSeqsCommand::readGroup(){
                                out << name << '\t' << group << endl;
                        }
                                        
-                       gobble(in);
+                       m->gobble(in);
                }
                in.close();
                out.close();
                
                if (wroteSomething == false) { m->mothurOut("Your file does not contain any sequence from the .accnos file."); m->mothurOutEndLine();  }
-               outputNames.push_back(outputFileName); 
+               outputNames.push_back(outputFileName);  outputTypes["group"].push_back(outputFileName);
                
                return 0;
 
@@ -462,13 +610,14 @@ int GetSeqsCommand::readGroup(){
 //**********************************************************************************************************************
 int GetSeqsCommand::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;
@@ -487,13 +636,13 @@ int GetSeqsCommand::readTax(){
                                out << name << '\t' << tax << endl;
                        }
                                        
-                       gobble(in);
+                       m->gobble(in);
                }
                in.close();
                out.close();
                
                if (wroteSomething == false) { m->mothurOut("Your file does not contain any sequence from the .accnos file."); m->mothurOutEndLine();  }
-               outputNames.push_back(outputFileName); 
+               outputNames.push_back(outputFileName);  outputTypes["taxonomy"].push_back(outputFileName);
                        
                return 0;
 
@@ -507,14 +656,15 @@ int GetSeqsCommand::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 GetSeqsCommand::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;
@@ -554,13 +704,13 @@ int GetSeqsCommand::readAlign(){
                                }
                        }
                        
-                       gobble(in);
+                       m->gobble(in);
                }
                in.close();
                out.close();
                
                if (wroteSomething == false) { m->mothurOut("Your file does not contain any sequence from the .accnos file."); m->mothurOutEndLine();  }
-               outputNames.push_back(outputFileName); 
+               outputNames.push_back(outputFileName);  outputTypes["alignreport"].push_back(outputFileName);
                
                return 0;
                
@@ -576,7 +726,7 @@ int GetSeqsCommand::readAccnos(){
        try {
                
                ifstream in;
-               openInputFile(accnosfile, in);
+               m->openInputFile(accnosfile, in);
                string name;
                
                while(!in.eof()){
@@ -584,7 +734,7 @@ int GetSeqsCommand::readAccnos(){
                                                
                        names.insert(name);
                        
-                       gobble(in);
+                       m->gobble(in);
                }
                in.close();