]> git.donarmstrong.com Git - mothur.git/blobdiff - getseqscommand.cpp
added otu.association command. added calcSpearman, calcKendall and calcPearson functi...
[mothur.git] / getseqscommand.cpp
index 04c3bd325edf89638503cdcb49c2842c75ed1d17..9bf188db3d25fa4ac16b82973a2802c3b1e6ad75 100644 (file)
@@ -25,7 +25,8 @@ vector<string> GetSeqsCommand::setParameters(){
                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 paccnos2("accnos2", "InputTypes", "", "", "none", "none", "none",false,true); parameters.push_back(paccnos2);
+
                vector<string> myArray;
                for (int i = 0; i < parameters.size(); i++) {   myArray.push_back(parameters[i].name);          }
                return myArray;
@@ -81,6 +82,7 @@ GetSeqsCommand::GetSeqsCommand(string option)  {
                                
                //allow user to run help
                if(option == "help") { help(); abort = true; calledHelp = true; }
+               else if(option == "citation") { citation(); abort = true; calledHelp = true;}
                
                else {
                        vector<string> myArray = setParameters();
@@ -199,21 +201,24 @@ GetSeqsCommand::GetSeqsCommand(string option)  {
                                        m->mothurOut("You have no valid accnos file and accnos is required."); m->mothurOutEndLine(); 
                                        abort = true;
                                } 
-                       }       
+                       }else { m->setAccnosFile(accnosfile); } 
                        
                        if (accnosfile2 == "not found") { accnosfile2 = ""; }
                        
                        fastafile = validParameter.validFile(parameters, "fasta", true);
-                       if (fastafile == "not open") { abort = true; }
-                       else if (fastafile == "not found") {  fastafile = "";  }        
+                       if (fastafile == "not open") { fastafile = ""; abort = true; }
+                       else if (fastafile == "not found") {  fastafile = "";  }
+                       else { m->setFastaFile(fastafile); }
                        
                        namefile = validParameter.validFile(parameters, "name", true);
-                       if (namefile == "not open") { abort = true; }
+                       if (namefile == "not open") { namefile = ""; abort = true; }
                        else if (namefile == "not found") {  namefile = "";  }  
+                       else { m->setNameFile(namefile); }
                        
                        groupfile = validParameter.validFile(parameters, "group", true);
                        if (groupfile == "not open") { abort = true; }
                        else if (groupfile == "not found") {  groupfile = "";  }        
+                       else { m->setGroupFile(groupfile); }
                        
                        alignfile = validParameter.validFile(parameters, "alignreport", true);
                        if (alignfile == "not open") { abort = true; }
@@ -222,20 +227,33 @@ GetSeqsCommand::GetSeqsCommand(string option)  {
                        listfile = validParameter.validFile(parameters, "list", true);
                        if (listfile == "not open") { abort = true; }
                        else if (listfile == "not found") {  listfile = "";  }
+                       else { m->setListFile(listfile); }
                        
                        taxfile = validParameter.validFile(parameters, "taxonomy", true);
-                       if (taxfile == "not open") { abort = true; }
+                       if (taxfile == "not open") { taxfile = ""; abort = true; }
                        else if (taxfile == "not found") {  taxfile = "";  }
+                       else { m->setTaxonomyFile(taxfile); }
                        
                        qualfile = validParameter.validFile(parameters, "qfile", true);
                        if (qualfile == "not open") { abort = true; }
                        else if (qualfile == "not found") {  qualfile = "";  }
+                       else { m->setQualFile(qualfile); }
+                       
+                       accnosfile2 = validParameter.validFile(parameters, "accnos2", true);
+                       if (accnosfile2 == "not open") { abort = true; }
+                       else if (accnosfile2 == "not found") {  accnosfile2 = "";  }
+                       
                        
                        string usedDups = "true";
                        string temp = validParameter.validFile(parameters, "dups", false);      if (temp == "not found") { temp = "true"; usedDups = ""; }
                        dups = m->isTrue(temp);
                        
                        if ((fastafile == "") && (namefile == "") && (groupfile == "") && (alignfile == "") && (listfile == "") && (taxfile == "") && (qualfile == "") && (accnosfile2 == ""))  { m->mothurOut("You must provide one of the following: fasta, name, group, alignreport, taxonomy, quality or listfile."); m->mothurOutEndLine(); abort = true; }
+               
+                       if ((namefile == "") && ((fastafile != "") || (taxfile != ""))){
+                               vector<string> files; files.push_back(fastafile); files.push_back(taxfile);
+                               parser.getNameFile(files);
+                       }
                }
 
        }
@@ -266,9 +284,8 @@ int GetSeqsCommand::execute(){
                if (qualfile != "")                     {               readQual();                     }
                if (accnosfile2 != "")          {               compareAccnos();        }
                
-               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) { outputTypes.clear(); for (int i = 0; i < outputNames.size(); i++) {   m->mothurRemove(outputNames[i]);  } return 0; }
                
-               m->mothurOut("Selected " + toString(names.size()) + " sequences."); m->mothurOutEndLine();
                
                if (outputNames.size() != 0) {
                        m->mothurOutEndLine();
@@ -334,10 +351,11 @@ int GetSeqsCommand::readFasta(){
                string name;
                
                bool wroteSomething = false;
+               int selectedCount = 0;
                
                while(!in.eof()){
                
-                       if (m->control_pressed) { in.close(); out.close(); remove(outputFileName.c_str());  return 0; }
+                       if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName);  return 0; }
                        
                        Sequence currSeq(in);
                        name = currSeq.getName();
@@ -348,6 +366,7 @@ int GetSeqsCommand::readFasta(){
                                        wroteSomething = true;
                                        
                                        currSeq.printSequence(out);
+                                       selectedCount++;
                                }
                        }
                        m->gobble(in);
@@ -359,6 +378,8 @@ int GetSeqsCommand::readFasta(){
                if (wroteSomething == false) { m->mothurOut("Your file does not contain any sequence from the .accnos file."); m->mothurOutEndLine();  }
                outputNames.push_back(outputFileName);  outputTypes["fasta"].push_back(outputFileName); 
                
+               m->mothurOut("Selected " + toString(selectedCount) + " sequences from your fasta file."); m->mothurOutEndLine();
+               
                return 0;
 
        }
@@ -382,6 +403,7 @@ int GetSeqsCommand::readQual(){
                string name;
                
                bool wroteSomething = false;
+               int selectedCount = 0;
                
                
                while(!in.eof()){       
@@ -413,6 +435,7 @@ int GetSeqsCommand::readQual(){
                                wroteSomething = true;
                                                
                                out << name << endl << scores;
+                               selectedCount++;
                        }
                        
                        m->gobble(in);
@@ -424,6 +447,9 @@ int GetSeqsCommand::readQual(){
                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); 
                
+               m->mothurOut("Selected " + toString(selectedCount) + " sequences from your quality file."); m->mothurOutEndLine();
+
+               
                return 0;
                
        }
@@ -445,10 +471,13 @@ int GetSeqsCommand::readList(){
                m->openInputFile(listfile, in);
                
                bool wroteSomething = false;
+               int selectedCount = 0;
                
                while(!in.eof()){
                        
-                       if (m->control_pressed) { in.close(); out.close(); remove(outputFileName.c_str());  return 0; }
+                       selectedCount = 0;
+                       
+                       if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName);  return 0; }
 
                        //read in list vector
                        ListVector list(in);
@@ -469,11 +498,11 @@ int GetSeqsCommand::readList(){
                                        binnames = binnames.substr(binnames.find_first_of(',')+1, binnames.length());
                                        
                                        //if that name is in the .accnos file, add it
-                                       if (names.count(name) != 0) {  newNames += name + ",";  }
+                                       if (names.count(name) != 0) {  newNames += name + ",";  selectedCount++; }
                                }
                        
                                //get last name
-                               if (names.count(binnames) != 0) {  newNames += binnames + ",";  }
+                               if (names.count(binnames) != 0) {  newNames += binnames + ",";  selectedCount++; }
 
                                //if there are names in this bin add to new list
                                if (newNames != "") { 
@@ -496,6 +525,8 @@ int GetSeqsCommand::readList(){
                if (wroteSomething == false) { m->mothurOut("Your file does not contain any sequence from the .accnos file."); m->mothurOutEndLine();  }
                outputNames.push_back(outputFileName); outputTypes["list"].push_back(outputFileName);
                
+               m->mothurOut("Selected " + toString(selectedCount) + " sequences from your list file."); m->mothurOutEndLine();
+               
                return 0;
 
        }
@@ -519,11 +550,11 @@ int GetSeqsCommand::readName(){
                string name, firstCol, secondCol;
                
                bool wroteSomething = false;
-               
+               int selectedCount = 0;
                
                while(!in.eof()){
                
-                       if (m->control_pressed) { in.close(); out.close(); remove(outputFileName.c_str());  return 0; }
+                       if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName);  return 0; }
 
                        in >> firstCol;                         
                        in >> secondCol;
@@ -545,7 +576,10 @@ int GetSeqsCommand::readName(){
                                for (int i = 0; i < parsedNames.size(); i++) {  names.insert(parsedNames[i]);  }
                                out << firstCol << '\t' << hold << endl;
                                wroteSomething = true;
+                               selectedCount += parsedNames.size();
                        }else {
+                               selectedCount += validSecond.size();
+                               
                                //if the name in the first column is in the set then print it and any other names in second column also in set
                                if (names.count(firstCol) != 0) {
                                
@@ -581,6 +615,8 @@ int GetSeqsCommand::readName(){
                if (wroteSomething == false) { m->mothurOut("Your file does not contain any sequence from the .accnos file."); m->mothurOutEndLine();  }
                outputNames.push_back(outputFileName); outputTypes["name"].push_back(outputFileName);
                
+               m->mothurOut("Selected " + toString(selectedCount) + " sequences from your name file."); m->mothurOutEndLine();
+               
                return 0;
                
        }
@@ -605,10 +641,11 @@ int GetSeqsCommand::readGroup(){
                string name, group;
                
                bool wroteSomething = false;
+               int selectedCount = 0;
                
                while(!in.eof()){
 
-                       if (m->control_pressed) { in.close(); out.close(); remove(outputFileName.c_str());  return 0; }
+                       if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName);  return 0; }
 
 
                        in >> name;                             //read from first column
@@ -619,6 +656,7 @@ int GetSeqsCommand::readGroup(){
                                wroteSomething = true;
                                
                                out << name << '\t' << group << endl;
+                               selectedCount++;
                        }
                                        
                        m->gobble(in);
@@ -629,6 +667,9 @@ int GetSeqsCommand::readGroup(){
                if (wroteSomething == false) { m->mothurOut("Your file does not contain any sequence from the .accnos file."); m->mothurOutEndLine();  }
                outputNames.push_back(outputFileName);  outputTypes["group"].push_back(outputFileName);
                
+               m->mothurOut("Selected " + toString(selectedCount) + " sequences from your group file."); m->mothurOutEndLine();
+
+               
                return 0;
 
        }
@@ -651,10 +692,11 @@ int GetSeqsCommand::readTax(){
                string name, tax;
                
                bool wroteSomething = false;
+               int selectedCount = 0;
                
                while(!in.eof()){
 
-                       if (m->control_pressed) { in.close(); out.close(); remove(outputFileName.c_str());  return 0; }
+                       if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName);  return 0; }
 
                        in >> name;                             //read from first column
                        in >> tax;                      //read from second column
@@ -664,6 +706,7 @@ int GetSeqsCommand::readTax(){
                                wroteSomething = true;
                                
                                out << name << '\t' << tax << endl;
+                               selectedCount++;
                        }
                                        
                        m->gobble(in);
@@ -673,6 +716,8 @@ int GetSeqsCommand::readTax(){
                
                if (wroteSomething == false) { m->mothurOut("Your file does not contain any sequence from the .accnos file."); m->mothurOutEndLine();  }
                outputNames.push_back(outputFileName);  outputTypes["taxonomy"].push_back(outputFileName);
+               
+               m->mothurOut("Selected " + toString(selectedCount) + " sequences from your taxonomy file."); m->mothurOutEndLine();
                        
                return 0;
 
@@ -698,6 +743,7 @@ int GetSeqsCommand::readAlign(){
                string name, junk;
                
                bool wroteSomething = false;
+               int selectedCount = 0;
                
                //read column headers
                for (int i = 0; i < 16; i++) {  
@@ -708,7 +754,7 @@ int GetSeqsCommand::readAlign(){
                
                while(!in.eof()){
                
-                       if (m->control_pressed) { in.close(); out.close(); remove(outputFileName.c_str());  return 0; }
+                       if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName);  return 0; }
 
 
                        in >> name;                             //read from first column
@@ -716,6 +762,7 @@ int GetSeqsCommand::readAlign(){
                        //if this name is in the accnos file
                        if (names.count(name) != 0) {
                                wroteSomething = true;
+                               selectedCount++;
                                
                                out << name << '\t';
                                
@@ -742,6 +789,8 @@ int GetSeqsCommand::readAlign(){
                if (wroteSomething == false) { m->mothurOut("Your file does not contain any sequence from the .accnos file."); m->mothurOutEndLine();  }
                outputNames.push_back(outputFileName);  outputTypes["alignreport"].push_back(outputFileName);
                
+               m->mothurOut("Selected " + toString(selectedCount) + " sequences from your alignreport file."); m->mothurOutEndLine();
+               
                return 0;
                
        }
@@ -823,7 +872,15 @@ int GetSeqsCommand::compareAccnos(){
                        in >> name;
                        
                        if (namesAccnos.count(name) == 0){ //name unique to accnos2
-                               namesAccnos2.insert(name);
+                               int pos = name.find_last_of('_');
+                               string tempName = name;
+                               if (pos != string::npos) {  tempName = tempName.substr(pos+1); cout << tempName << endl; }
+                               if (namesAccnos.count(tempName) == 0){
+                                       namesAccnos2.insert(name);
+                               }else { //you are in both so erase
+                                       namesAccnos.erase(name);
+                                       namesDups.insert(name);
+                               }
                        }else { //you are in both so erase
                                namesAccnos.erase(name);
                                namesDups.insert(name);