]> git.donarmstrong.com Git - mothur.git/blobdiff - secondarystructurecommand.cpp
rewrote metastats command in c++, added mothurRemove function to handle ~ error....
[mothur.git] / secondarystructurecommand.cpp
index 36e0f609ca67bd3cd37e7c0d33a98e88cee65e6f..fe80b7810e716264152835060f25d1f2e45c1fed 100644 (file)
 #include "sequence.hpp"
 
 //**********************************************************************************************************************
-vector<string> AlignCheckCommand::getValidParameters(){        
+vector<string> AlignCheckCommand::setParameters(){     
        try {
-               string Array[] =  {"fasta","map", "outputdir","inputdir"};
-               vector<string> myArray (Array, Array+(sizeof(Array)/sizeof(string)));
+               CommandParameter pfasta("fasta", "InputTypes", "", "", "none", "none", "none",false,true); parameters.push_back(pfasta);
+               CommandParameter pmap("map", "InputTypes", "", "", "none", "none", "none",false,true); parameters.push_back(pmap);
+               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);          }
                return myArray;
        }
        catch(exception& e) {
-               m->errorOut(e, "AlignCheckCommand", "getValidParameters");
-               exit(1);
-       }
-}
-//**********************************************************************************************************************
-AlignCheckCommand::AlignCheckCommand(){        
-       try {
-               //initialize outputTypes
-               vector<string> tempOutNames;
-               outputTypes["aligncheck"] = tempOutNames;
-       }
-       catch(exception& e) {
-               m->errorOut(e, "AlignCheckCommand", "AlignCheckCommand");
+               m->errorOut(e, "AlignCheckCommand", "setParameters");
                exit(1);
        }
 }
 //**********************************************************************************************************************
-vector<string> AlignCheckCommand::getRequiredParameters(){     
+string AlignCheckCommand::getHelpString(){     
        try {
-               string Array[] =  {"fasta","map"};
-               vector<string> myArray (Array, Array+(sizeof(Array)/sizeof(string)));
-               return myArray;
+               string helpString = "";
+               helpString += "The align.check command reads a fasta file and map file.\n";
+               helpString += "It outputs a file containing the secondary structure matches in the .align.check file.\n";
+               helpString += "The align.check command parameters are fasta and map, both are required.\n";
+               helpString += "The align.check command should be in the following format: align.check(fasta=yourFasta, map=yourMap).\n";
+               helpString += "Example align.check(map=silva.ss.map, fasta=amazon.fasta).\n";
+               helpString += "Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFasta).\n";
+               return helpString;
        }
        catch(exception& e) {
-               m->errorOut(e, "AlignCheckCommand", "getRequiredParameters");
+               m->errorOut(e, "AlignCheckCommand", "getHelpString");
                exit(1);
        }
 }
 //**********************************************************************************************************************
-vector<string> AlignCheckCommand::getRequiredFiles(){  
+AlignCheckCommand::AlignCheckCommand(){        
        try {
-               vector<string> myArray;
-               return myArray;
+               abort = true; calledHelp = true; 
+               setParameters();
+               vector<string> tempOutNames;
+               outputTypes["aligncheck"] = tempOutNames;
        }
        catch(exception& e) {
-               m->errorOut(e, "AlignCheckCommand", "getRequiredFiles");
+               m->errorOut(e, "AlignCheckCommand", "AlignCheckCommand");
                exit(1);
        }
 }
@@ -61,16 +61,15 @@ vector<string> AlignCheckCommand::getRequiredFiles(){
 
 AlignCheckCommand::AlignCheckCommand(string option)  {
        try {
-               abort = false;
+               abort = false; calledHelp = false;   
                haderror = 0;
                        
                //allow user to run help
-               if(option == "help") { help(); abort = true; }
+               if(option == "help") { help(); abort = true; calledHelp = true; }
+               else if(option == "citation") { citation(); abort = true; calledHelp = true;}
                
                else {
-                       //valid paramters for this command
-                       string Array[] =  {"fasta","map", "outputdir","inputdir"};
-                       vector<string> myArray (Array, Array+(sizeof(Array)/sizeof(string)));
+                       vector<string> myArray = setParameters();
                        
                        OptionParser parser(option);
                        map<string,string> parameters = parser.getParameters();
@@ -107,6 +106,14 @@ AlignCheckCommand::AlignCheckCommand(string option)  {
                                        //if the user has not given a path then, add inputdir. else leave path alone.
                                        if (path == "") {       parameters["map"] = inputDir + it->second;              }
                                }
+                               
+                               it = parameters.find("name");
+                               //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["name"] = inputDir + it->second;             }
+                               }
                        }
 
                        //check for required parameters
@@ -116,7 +123,16 @@ AlignCheckCommand::AlignCheckCommand(string option)  {
                        
                        fastafile = validParameter.validFile(parameters, "fasta", true);
                        if (fastafile == "not open") { abort = true; }
-                       else if (fastafile == "not found") {  fastafile = "";  m->mothurOut("You must provide an fasta file."); m->mothurOutEndLine(); abort = true;  } 
+                       else if (fastafile == "not found") {                            
+                               fastafile = m->getFastaFile(); 
+                               if (fastafile != "") { m->mothurOut("Using " + fastafile + " as input file for the fasta parameter."); m->mothurOutEndLine(); }
+                               else {  m->mothurOut("You have no current fastafile and the fasta parameter is required."); m->mothurOutEndLine(); abort = true; }
+                       }else { m->setFastaFile(fastafile); }   
+                       
+                       namefile = validParameter.validFile(parameters, "name", true);
+                       if (namefile == "not open") { namefile = ""; abort = true; }
+                       else if (namefile == "not found") { namefile = "";  }   
+                       else { m->setNameFile(namefile); }
                        
                        //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"){  
@@ -128,37 +144,24 @@ AlignCheckCommand::AlignCheckCommand(string option)  {
 
        }
        catch(exception& e) {
-               m->errorOut(e, "AlignCheckCommand", "RemoveSeqsCommand");
-               exit(1);
-       }
-}
-//**********************************************************************************************************************
-
-void AlignCheckCommand::help(){
-       try {
-               m->mothurOut("The align.check command reads a fasta file and map file.\n");
-               m->mothurOut("It outputs a file containing the secondary structure matches in the .align.check file.\n");
-               m->mothurOut("The align.check command parameters are fasta and map, both are required.\n");
-               m->mothurOut("The align.check command should be in the following format: align.check(fasta=yourFasta, map=yourMap).\n");
-               m->mothurOut("Example align.check(map=silva.ss.map, fasta=amazon.fasta).\n");
-               m->mothurOut("Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFasta).\n\n");
-       }
-       catch(exception& e) {
-               m->errorOut(e, "AlignCheckCommand", "help");
+               m->errorOut(e, "AlignCheckCommand", "AlignCheckCommand");
                exit(1);
        }
 }
-
 //**********************************************************************************************************************
 
 int AlignCheckCommand::execute(){
        try {
                
-               if (abort == true) { return 0; }
+               if (abort == true) { if (calledHelp) { return 0; }  return 2;   }
                
                //get secondary structure info.
                readMap();
                
+               if (namefile != "") { nameMap = m->readNames(namefile); }
+               
+               if (m->control_pressed) { return 0; }
+               
                ifstream in;
                m->openInputFile(fastafile, in);
                
@@ -166,28 +169,89 @@ int AlignCheckCommand::execute(){
                string outfile = outputDir + m->getRootName(m->getSimpleName(fastafile)) + "align.check";
                m->openOutputFile(outfile, out);
                
+                               
                out << "name" << '\t' << "pound" << '\t' << "dash" << '\t' << "plus" << '\t' << "equal" << '\t';
-               out << "loop" << '\t' << "tilde" << '\t' << "total" << endl;
+               out << "loop" << '\t' << "tilde" << '\t' << "total"  << '\t' << "numseqs" << endl;
 
+               vector<int> pound;
+               vector<int> dash;
+               vector<int> plus;
+               vector<int> equal;
+               vector<int> loop;
+               vector<int> tilde;
+               vector<int> total;
                
+               int count = 0;
                while(!in.eof()){
-                       if (m->control_pressed) { in.close(); out.close(); remove(outfile.c_str()); return 0; }
+                       if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outfile); return 0; }
                        
                        Sequence seq(in);  m->gobble(in);
                        if (seq.getName() != "") {
                                statData data = getStats(seq.getAligned());
                                
-                               if (haderror == 1) { break; }
+                               if (haderror == 1) { m->control_pressed = true; break; }
+                               
+                               int num = 1;
+                               if (namefile != "") {
+                                       //make sure this sequence is in the namefile, else error 
+                                       map<string, int>::iterator it = nameMap.find(seq.getName());
+                                       
+                                       if (it == nameMap.end()) { m->mothurOut("[ERROR]: " + seq.getName() + " is not in your namefile, please correct."); m->mothurOutEndLine(); m->control_pressed = true; }
+                                       else { num = it->second; }
+                               }
+                               
+                               //for each sequence this sequence represents
+                               for (int i = 0; i < num; i++) {
+                                       pound.push_back(data.pound);
+                                       dash.push_back(data.dash);
+                                       plus.push_back(data.plus);
+                                       equal.push_back(data.equal);
+                                       loop.push_back(data.loop);
+                                       tilde.push_back(data.tilde);
+                                       total.push_back(data.total);
+                               }       
+                               count++;
                                
                                out << seq.getName() << '\t' << data.pound << '\t' << data.dash << '\t' << data.plus << '\t' << data.equal << '\t';
-                               out << data.loop << '\t' << data.tilde << '\t' << data.total << endl;
+                               out << data.loop << '\t' << data.tilde << '\t' << data.total << '\t' << num << endl;
                        }
                }
 
                in.close();
                out.close();
                
-               if (m->control_pressed) {  remove(outfile.c_str()); return 0; }
+               if (m->control_pressed) {  m->mothurRemove(outfile); return 0; }
+               
+               sort(pound.begin(), pound.end());
+               sort(dash.begin(), dash.end());
+               sort(plus.begin(), plus.end());
+               sort(equal.begin(), equal.end());
+               sort(loop.begin(), loop.end());
+               sort(tilde.begin(), tilde.end());
+               sort(total.begin(), total.end());
+               int size = pound.size();
+               
+               int ptile0_25   = int(size * 0.025);
+               int ptile25             = int(size * 0.250);
+               int ptile50             = int(size * 0.500);
+               int ptile75             = int(size * 0.750);
+               int ptile97_5   = int(size * 0.975);
+               int ptile100    = size - 1;
+               
+               if (m->control_pressed) {  m->mothurRemove(outfile); return 0; }
+               
+               m->mothurOutEndLine();
+               m->mothurOut("\t\tPound\tDash\tPlus\tEqual\tLoop\tTilde\tTotal"); m->mothurOutEndLine();
+               m->mothurOut("Minimum:\t" + toString(pound[0]) + "\t" + toString(dash[0]) + "\t" + toString(plus[0]) + "\t" + toString(equal[0]) + "\t" + toString(loop[0]) + "\t" + toString(tilde[0]) + "\t" + toString(total[0])); m->mothurOutEndLine();
+               m->mothurOut("2.5%-tile:\t" + toString(pound[ptile0_25]) + "\t" + toString(dash[ptile0_25]) + "\t" + toString(plus[ptile0_25]) + "\t" + toString(equal[ptile0_25]) + "\t"+ toString(loop[ptile0_25]) + "\t"+ toString(tilde[ptile0_25]) + "\t"+ toString(total[ptile0_25])); m->mothurOutEndLine();
+               m->mothurOut("25%-tile:\t" + toString(pound[ptile25]) + "\t" + toString(dash[ptile25]) + "\t" + toString(plus[ptile25]) + "\t" + toString(equal[ptile25]) + "\t" + toString(loop[ptile25]) + "\t" + toString(tilde[ptile25]) + "\t" + toString(total[ptile25])); m->mothurOutEndLine();
+               m->mothurOut("Median: \t" + toString(pound[ptile50]) + "\t" + toString(dash[ptile50]) + "\t" + toString(plus[ptile50]) + "\t" + toString(equal[ptile50]) + "\t" + toString(loop[ptile50]) + "\t" + toString(tilde[ptile50]) + "\t" + toString(total[ptile50])); m->mothurOutEndLine();
+               m->mothurOut("75%-tile:\t" + toString(pound[ptile75]) + "\t" + toString(dash[ptile75]) + "\t" + toString(plus[ptile75]) + "\t" + toString(equal[ptile75]) + "\t" + toString(loop[ptile75]) + "\t" + toString(tilde[ptile75]) + "\t" + toString(total[ptile75])); m->mothurOutEndLine();
+               m->mothurOut("97.5%-tile:\t" + toString(pound[ptile97_5]) + "\t" + toString(dash[ptile97_5]) + "\t" + toString(plus[ptile97_5]) + "\t" + toString(equal[ptile97_5]) + "\t" + toString(loop[ptile97_5]) + "\t" + toString(tilde[ptile97_5]) + "\t" + toString(total[ptile97_5])); m->mothurOutEndLine();
+               m->mothurOut("Maximum:\t" + toString(pound[ptile100]) + "\t" + toString(dash[ptile100]) + "\t" + toString(plus[ptile100]) + "\t" + toString(equal[ptile100]) + "\t" + toString(loop[ptile100]) + "\t" + toString(tilde[ptile100]) + "\t" + toString(total[ptile100])); m->mothurOutEndLine();
+               if (namefile == "") {  m->mothurOut("# of Seqs:\t" + toString(count)); m->mothurOutEndLine(); }
+               else { m->mothurOut("# of unique seqs:\t" + toString(count)); m->mothurOutEndLine(); m->mothurOut("total # of seqs:\t" + toString(size)); m->mothurOutEndLine(); }
+               
                
                m->mothurOutEndLine();
                m->mothurOut("Output File Name: "); m->mothurOutEndLine();
@@ -305,6 +369,4 @@ statData AlignCheckCommand::getStats(string sequence){
                exit(1);
        }
 }
-
-
 //**********************************************************************************************************************