]> git.donarmstrong.com Git - mothur.git/blobdiff - removeseqscommand.cpp
cluster.split command
[mothur.git] / removeseqscommand.cpp
index 19a4bc032abbcd1a5a7c9f53cdeac1b1be2c5715..a61e467e0bd5820060c052acffefe5fe7983294f 100644 (file)
@@ -13,7 +13,7 @@
 
 //**********************************************************************************************************************
 
-RemoveSeqsCommand::RemoveSeqsCommand(string option){
+RemoveSeqsCommand::RemoveSeqsCommand(string option)  {
        try {
                abort = false;
                
@@ -97,7 +97,7 @@ RemoveSeqsCommand::RemoveSeqsCommand(string option){
                        //check for required parameters
                        accnosfile = validParameter.validFile(parameters, "accnos", true);
                        if (accnosfile == "not open") { abort = true; }
-                       else if (accnosfile == "not found") {  accnosfile = "";  mothurOut("You must provide an accnos file."); mothurOutEndLine(); abort = true; }     
+                       else if (accnosfile == "not found") {  accnosfile = "";  m->mothurOut("You must provide an accnos file."); m->mothurOutEndLine(); abort = true; }       
                        
                        fastafile = validParameter.validFile(parameters, "fasta", true);
                        if (fastafile == "not open") { abort = true; }
@@ -123,20 +123,20 @@ RemoveSeqsCommand::RemoveSeqsCommand(string option){
                        string temp = validParameter.validFile(parameters, "dups", false);      if (temp == "not found") { temp = "false"; usedDups = ""; }
                        dups = isTrue(temp);
                        
-                       if ((fastafile == "") && (namefile == "") && (groupfile == "") && (alignfile == "") && (listfile == ""))  { mothurOut("You must provide one of the following: fasta, name, group, alignreport or list."); mothurOutEndLine(); abort = true; }
+                       if ((fastafile == "") && (namefile == "") && (groupfile == "") && (alignfile == "") && (listfile == ""))  { m->mothurOut("You must provide one of the following: fasta, name, group, alignreport or list."); m->mothurOutEndLine(); abort = true; }
                        
-                       int okay = 2;
-                       if (outputDir != "") { okay++; }
-                       if (usedDups != "") { okay++;  }
+                       //int okay = 2;
+                       //if (outputDir != "") { okay++; }
+                       //if (usedDups != "") { okay++;  }
                        
-                       if ((usedDups != "") && (namefile == "")) {  mothurOut("You may only use dups with the name option."); mothurOutEndLine();  abort = true; }
+                       if ((usedDups != "") && (namefile == "")) {  m->mothurOut("You may only use dups with the name option."); m->mothurOutEndLine();  abort = true; }
                        
-                       if (parameters.size() > okay) { mothurOut("You may only enter one of the following: fasta, name, group, alignreport, or list."); mothurOutEndLine(); abort = true;  }
+                       //if (parameters.size() > okay) { m->mothurOut("You may only enter one of the following: fasta, name, group, alignreport, or list."); m->mothurOutEndLine(); abort = true;  }
                }
 
        }
        catch(exception& e) {
-               errorOut(e, "RemoveSeqsCommand", "RemoveSeqsCommand");
+               m->errorOut(e, "RemoveSeqsCommand", "RemoveSeqsCommand");
                exit(1);
        }
 }
@@ -144,16 +144,16 @@ RemoveSeqsCommand::RemoveSeqsCommand(string option){
 
 void RemoveSeqsCommand::help(){
        try {
-               mothurOut("The remove.seqs command reads an .accnos file and one of the following file types: fasta, name, group, list or alignreport file.\n");
-               mothurOut("It outputs a file containing the sequences NOT in the .accnos file.\n");
-               mothurOut("The remove.seqs command parameters are accnos, fasta, name, group, list, alignreport and dups.  You must provide accnos and one of the file parameters.\n");
-               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. If dups=true, then remove.seqs outputs a new .accnos file containing all the sequences removed. \n");
-               mothurOut("The remove.seqs command should be in the following format: remove.seqs(accnos=yourAccnos, fasta=yourFasta).\n");
-               mothurOut("Example remove.seqs(accnos=amazon.accnos, fasta=amazon.fasta).\n");
-               mothurOut("Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFasta).\n\n");
+               m->mothurOut("The remove.seqs command reads an .accnos file and one of the following file types: fasta, name, group, list 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, alignreport and dups.  You must provide accnos and 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. If dups=true, then remove.seqs outputs a new .accnos file containing all the sequences removed. \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");
        }
        catch(exception& e) {
-               errorOut(e, "RemoveSeqsCommand", "help");
+               m->errorOut(e, "RemoveSeqsCommand", "help");
                exit(1);
        }
 }
@@ -168,27 +168,38 @@ int RemoveSeqsCommand::execute(){
                //get names you want to keep
                readAccnos();
                
+               if (m->control_pressed) { return 0; }
+               
                //read through the correct file and output lines you want to keep
                if (fastafile != "")            {               readFasta();    }
-               else if (namefile != "")        {               readName();             }
-               else if (groupfile != "")       {               readGroup();    }
-               else if (alignfile != "")       {               readAlign();    }
-               else if (listfile != "")        {               readList();             }
+               if (namefile != "")                     {               readName();             }
+               if (groupfile != "")            {               readGroup();    }
+               if (alignfile != "")            {               readAlign();    }
+               if (listfile != "")                     {               readList();             }
+               
+               if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) {        remove(outputNames[i].c_str()); } return 0; }
+               
+               if (outputNames.size() != 0) {
+                       m->mothurOutEndLine();
+                       m->mothurOut("Output File Names: "); m->mothurOutEndLine();
+                       for (int i = 0; i < outputNames.size(); i++) {  m->mothurOut(outputNames[i]); m->mothurOutEndLine();    }
+                       m->mothurOutEndLine();
+               }
                
                return 0;               
        }
 
        catch(exception& e) {
-               errorOut(e, "RemoveSeqsCommand", "execute");
+               m->errorOut(e, "RemoveSeqsCommand", "execute");
                exit(1);
        }
 }
 
 //**********************************************************************************************************************
-void RemoveSeqsCommand::readFasta(){
+int RemoveSeqsCommand::readFasta(){
        try {
                if (outputDir == "") {  outputDir += hasPath(fastafile);  }
-               string outputFileName = getRootName(fastafile) + "pick" + getExtension(fastafile);
+               string outputFileName = outputDir + getRootName(getSimpleName(fastafile)) + "pick" + getExtension(fastafile);
                ofstream out;
                openOutputFile(outputFileName, out);
                
@@ -199,6 +210,8 @@ void RemoveSeqsCommand::readFasta(){
                bool wroteSomething = false;
                
                while(!in.eof()){
+                       if (m->control_pressed) { in.close();  out.close();  remove(outputFileName.c_str());  return 0; }
+                       
                        Sequence currSeq(in);
                        name = currSeq.getName();
                        
@@ -208,7 +221,7 @@ void RemoveSeqsCommand::readFasta(){
                                        wroteSomething = true;
                                        
                                        currSeq.printSequence(out);
-                               }else {         names.erase(name);              }
+                               }//else {               names.erase(name);              }
                        }
                        gobble(in);
                }
@@ -216,21 +229,23 @@ void RemoveSeqsCommand::readFasta(){
                out.close();
                
                if (wroteSomething == false) {
-                       mothurOut("Your file contains only sequences from the .accnos file."); mothurOutEndLine();
+                       m->mothurOut("Your file contains only sequences from the .accnos file."); m->mothurOutEndLine();
                        remove(outputFileName.c_str()); 
-               }
-
+               }else { outputNames.push_back(outputFileName); }
+               
+               return 0;
+               
        }
        catch(exception& e) {
-               errorOut(e, "RemoveSeqsCommand", "readFasta");
+               m->errorOut(e, "RemoveSeqsCommand", "readFasta");
                exit(1);
        }
 }
 //**********************************************************************************************************************
-void RemoveSeqsCommand::readList(){
+int RemoveSeqsCommand::readList(){
        try {
                if (outputDir == "") {  outputDir += hasPath(listfile);  }
-               string outputFileName = getRootName(listfile) + "pick" +  getExtension(listfile);
+               string outputFileName = outputDir + getRootName(getSimpleName(listfile)) + "pick" +  getExtension(listfile);
                ofstream out;
                openOutputFile(outputFileName, out);
                
@@ -249,6 +264,7 @@ void RemoveSeqsCommand::readList(){
                        
                        //for each bin
                        for (int i = 0; i < list.getNumBins(); i++) {
+                               if (m->control_pressed) { in.close();  out.close();  remove(outputFileName.c_str());  return 0; }
                        
                                //parse out names that are in accnos file
                                string binnames = list.get(i);
@@ -263,10 +279,13 @@ void RemoveSeqsCommand::readList(){
                                }
                        
                                //get last name
-                               if (names.count(binnames) == 0) {  newNames += binnames;  }
+                               if (names.count(binnames) == 0) {  newNames += binnames + ",";  }
 
                                //if there are names in this bin add to new list
-                               if (newNames != "") {  newList.push_back(newNames);     }
+                               if (newNames != "") {  
+                                       newNames = newNames.substr(0, newNames.length()-1); //rip off extra comma
+                                       newList.push_back(newNames);    
+                               }
                        }
                                
                        //print new listvector
@@ -281,22 +300,24 @@ void RemoveSeqsCommand::readList(){
                out.close();
                
                if (wroteSomething == false) {
-                       mothurOut("Your file contains only sequences from the .accnos file."); mothurOutEndLine();
+                       m->mothurOut("Your file contains only sequences from the .accnos file."); m->mothurOutEndLine();
                        remove(outputFileName.c_str()); 
-               }
+               }else { outputNames.push_back(outputFileName); }
+               
+               return 0;
 
        }
        catch(exception& e) {
-               errorOut(e, "RemoveSeqsCommand", "readList");
+               m->errorOut(e, "RemoveSeqsCommand", "readList");
                exit(1);
        }
 }
 //**********************************************************************************************************************
-void RemoveSeqsCommand::readName(){
+int RemoveSeqsCommand::readName(){
        try {
                if (outputDir == "") {  outputDir += hasPath(namefile);  }
-               string outputFileName = getRootName(namefile) + "pick" + getExtension(namefile);
-               string outputFileName2 = getRootName(namefile) + "dups.accnos";
+               string outputFileName = outputDir + getRootName(getSimpleName(namefile)) + "pick" + getExtension(namefile);
+               string outputFileName2 = outputDir + getRootName(getSimpleName(namefile)) + "dups.accnos";
 
                ofstream out2;
                if (dups) {      openOutputFile(outputFileName2, out2); }
@@ -312,6 +333,7 @@ void RemoveSeqsCommand::readName(){
                bool wroteSomething = false;
                
                while(!in.eof()){
+                       if (m->control_pressed) { in.close();  out.close();  remove(outputFileName.c_str()); if (dups) { out2.close(); remove(outputFileName2.c_str()); } return 0; }
 
                        in >> firstCol;                         
                        in >> secondCol;                        
@@ -374,25 +396,26 @@ void RemoveSeqsCommand::readName(){
                if (dups) { out2.close();  }
                if (wroteDups == false) {
                        remove(outputFileName2.c_str()); 
-               }
+               }else { outputNames.push_back(outputFileName2); }
                
                if (wroteSomething == false) {
-                       mothurOut("Your file contains only sequences from the .accnos file."); mothurOutEndLine();
+                       m->mothurOut("Your file contains only sequences from the .accnos file."); m->mothurOutEndLine();
                        remove(outputFileName.c_str()); 
-               }
+               }else { outputNames.push_back(outputFileName); }
                
+               return 0;
        }
        catch(exception& e) {
-               errorOut(e, "RemoveSeqsCommand", "readName");
+               m->errorOut(e, "RemoveSeqsCommand", "readName");
                exit(1);
        }
 }
 
 //**********************************************************************************************************************
-void RemoveSeqsCommand::readGroup(){
+int RemoveSeqsCommand::readGroup(){
        try {
                if (outputDir == "") {  outputDir += hasPath(groupfile);  }
-               string outputFileName = getRootName(groupfile) + "pick" + getExtension(groupfile);
+               string outputFileName = outputDir + getRootName(getSimpleName(groupfile)) + "pick" + getExtension(groupfile);
                ofstream out;
                openOutputFile(outputFileName, out);
 
@@ -403,7 +426,8 @@ void RemoveSeqsCommand::readGroup(){
                bool wroteSomething = false;
                
                while(!in.eof()){
-
+                       if (m->control_pressed) { in.close();  out.close();  remove(outputFileName.c_str());  return 0; }
+                       
                        in >> name;                             //read from first column
                        in >> group;                    //read from second column
                        
@@ -411,7 +435,7 @@ void RemoveSeqsCommand::readGroup(){
                        if (names.count(name) == 0) {
                                wroteSomething = true;
                                out << name << '\t' << group << endl;
-                       }else {         names.erase(name);              }
+                       }//else {               names.erase(name);              }
                                        
                        gobble(in);
                }
@@ -419,23 +443,24 @@ void RemoveSeqsCommand::readGroup(){
                out.close();
                
                if (wroteSomething == false) {
-                       mothurOut("Your file contains only sequences from the .accnos file."); mothurOutEndLine();
+                       m->mothurOut("Your file contains only sequences from the .accnos file."); m->mothurOutEndLine();
                        remove(outputFileName.c_str()); 
-               }
-
+               }else { outputNames.push_back(outputFileName); }
+               
+               return 0;
        }
        catch(exception& e) {
-               errorOut(e, "RemoveSeqsCommand", "readGroup");
+               m->errorOut(e, "RemoveSeqsCommand", "readGroup");
                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
-void RemoveSeqsCommand::readAlign(){
+int RemoveSeqsCommand::readAlign(){
        try {
                if (outputDir == "") {  outputDir += hasPath(alignfile);  }
-               string outputFileName = getRootName(getRootName(alignfile)) + "pick.align.report";
+               string outputFileName = outputDir + getRootName(getSimpleName(alignfile)) + "pick.align.report";
                ofstream out;
                openOutputFile(outputFileName, out);
 
@@ -453,7 +478,8 @@ void RemoveSeqsCommand::readAlign(){
                out << endl;
                
                while(!in.eof()){
-
+                       if (m->control_pressed) { in.close();  out.close();  remove(outputFileName.c_str());  return 0; }
+                       
                        in >> name;                             //read from first column
                        
                        //if this name is in the accnos file
@@ -470,7 +496,7 @@ void RemoveSeqsCommand::readAlign(){
                                out << endl;
                                
                        }else {//still read just don't do anything with it
-                               names.erase(name);      
+                               //names.erase(name);    
                                
                                //read rest
                                for (int i = 0; i < 15; i++) {  
@@ -485,13 +511,15 @@ void RemoveSeqsCommand::readAlign(){
                out.close();
                
                if (wroteSomething == false) {
-                       mothurOut("Your file contains only sequences from the .accnos file."); mothurOutEndLine();
+                       m->mothurOut("Your file contains only sequences from the .accnos file."); m->mothurOutEndLine();
                        remove(outputFileName.c_str()); 
-               }
+               }else { outputNames.push_back(outputFileName); }
+               
+               return 0;
                
        }
        catch(exception& e) {
-               errorOut(e, "RemoveSeqsCommand", "readAlign");
+               m->errorOut(e, "RemoveSeqsCommand", "readAlign");
                exit(1);
        }
 }
@@ -514,7 +542,7 @@ void RemoveSeqsCommand::readAccnos(){
 
        }
        catch(exception& e) {
-               errorOut(e, "RemoveSeqsCommand", "readAccnos");
+               m->errorOut(e, "RemoveSeqsCommand", "readAccnos");
                exit(1);
        }
 }