]> git.donarmstrong.com Git - mothur.git/blobdiff - binsequencecommand.cpp
added sort parameter to get.otulist
[mothur.git] / binsequencecommand.cpp
index 08ae6b607a13e3406aa4fe42d8a1f5025a41bbc0..1d4f8c6694c570bbb7075c4150ae5125d29cc18e 100644 (file)
@@ -10,7 +10,7 @@
 #include "binsequencecommand.h"
 
 //**********************************************************************************************************************
-BinSeqCommand::BinSeqCommand(string option){
+BinSeqCommand::BinSeqCommand(string option) {
        try {
                globaldata = GlobalData::getInstance();
                abort = false;
@@ -22,30 +22,68 @@ BinSeqCommand::BinSeqCommand(string option){
                
                else {
                        //valid paramters for this command
-                       string AlignArray[] =  {"fasta","label","name", "group"};
+                       string AlignArray[] =  {"fasta","label","name", "group","outputdir","inputdir"};
                        vector<string> myArray (AlignArray, AlignArray+(sizeof(AlignArray)/sizeof(string)));
                        
                        OptionParser parser(option);
                        map<string, string> parameters = parser.getParameters();
                        
                        ValidParameters validParameter;
+                       map<string, string>::iterator it;
                
                        //check to make sure all parameters are valid for command
-                       for (map<string, string>::iterator it = parameters.begin(); it != parameters.end(); it++) { 
+                       for (it = parameters.begin(); it != parameters.end(); it++) { 
                                if (validParameter.isValidParameter(it->first, myArray, it->second) != true) {  abort = true;  }
                        }
                        
+                       //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 = ""; 
+                               outputDir += hasPath(globaldata->getListFile()); //if user entered a file with a path then preserve it  
+                       }
+
+                       
                        //make sure the user has already run the read.otu command
                        if (globaldata->getListFile() == "") { 
-                               mothurOut("You must read a listfile before running the bin.seqs command."); 
-                               mothurOutEndLine(); 
+                               m->mothurOut("You must read a listfile before running the bin.seqs command."); 
+                               m->mothurOutEndLine(); 
                                abort = true; 
                        }
                        
+                       //if the user changes the input directory command factory will send this info to us in the output parameter 
+                       string inputDir = validParameter.validFile(parameters, "inputdir", false);              
+                       if (inputDir == "not found"){   inputDir = "";          }
+                       else {
+                               string path;
+                               it = parameters.find("fasta");
+                               //user has given a template file
+                               if(it != parameters.end()){ 
+                                       path = 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;            }
+                               }
+                               
+                               it = parameters.find("name");
+                               //user has given a template file
+                               if(it != parameters.end()){ 
+                                       path = 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;             }
+                               }
+                               
+                               it = parameters.find("group");
+                               //user has given a template file
+                               if(it != parameters.end()){ 
+                                       path = 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;            }
+                               }
+                       }
+
                        
                        //check for required parameters
                        fastafile = validParameter.validFile(parameters, "fasta", true);
-                       if (fastafile == "not found") { mothurOut("fasta is a required parameter for the bin.seqs command.");  mothurOutEndLine(); abort = true; }
+                       if (fastafile == "not found") { m->mothurOut("fasta is a required parameter for the bin.seqs command.");  m->mothurOutEndLine(); abort = true; }
                        else if (fastafile == "not open") { abort = true; }     
                
                        //check for optional parameter and set defaults
@@ -77,14 +115,16 @@ BinSeqCommand::BinSeqCommand(string option){
                                fasta = new FastaMap();
                                if (groupfile != "") {
                                        groupMap = new GroupMap(groupfile);
-                                       groupMap->readMap();
+                                       
+                                       int error = groupMap->readMap();
+                                       if (error == 1) { delete groupMap; abort = true; }
                                }
                        }
        
                }
        }
        catch(exception& e) {
-               errorOut(e, "BinSeqCommand", "BinSeqCommand");
+               m->errorOut(e, "BinSeqCommand", "BinSeqCommand");
                exit(1);
        }
 }
@@ -92,18 +132,18 @@ BinSeqCommand::BinSeqCommand(string option){
 
 void BinSeqCommand::help(){
        try {
-               mothurOut("The bin.seqs command can only be executed after a successful read.otu command of a listfile.\n");
-               mothurOut("The bin.seqs command parameters are fasta, name, label and group.  The fasta parameter is required.\n");
-               mothurOut("The label parameter allows you to select what distance levels you would like a output files created for, and are separated by dashes.\n");
-               mothurOut("The bin.seqs command should be in the following format: bin.seqs(fasta=yourFastaFile, name=yourNamesFile, group=yourGroupFile, label=yourLabels).\n");
-               mothurOut("Example bin.seqs(fasta=amazon.fasta, group=amazon.groups, name=amazon.names).\n");
-               mothurOut("The default value for label is all lines in your inputfile.\n");
-               mothurOut("The bin.seqs command outputs a .fasta file for each distance you specify appending the OTU number to each name.\n");
-               mothurOut("If you provide a groupfile, then it also appends the sequences group to the name.\n");
-               mothurOut("Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFastaFile).\n\n");
+               m->mothurOut("The bin.seqs command can only be executed after a successful read.otu command of a listfile.\n");
+               m->mothurOut("The bin.seqs command parameters are fasta, name, label and group.  The fasta parameter is required.\n");
+               m->mothurOut("The label parameter allows you to select what distance levels you would like a output files created for, and are separated by dashes.\n");
+               m->mothurOut("The bin.seqs command should be in the following format: bin.seqs(fasta=yourFastaFile, name=yourNamesFile, group=yourGroupFile, label=yourLabels).\n");
+               m->mothurOut("Example bin.seqs(fasta=amazon.fasta, group=amazon.groups, name=amazon.names).\n");
+               m->mothurOut("The default value for label is all lines in your inputfile.\n");
+               m->mothurOut("The bin.seqs command outputs a .fasta file for each distance you specify appending the OTU number to each name.\n");
+               m->mothurOut("If you provide a groupfile, then it also appends the sequences group to the name.\n");
+               m->mothurOut("Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFastaFile).\n\n");
        }
        catch(exception& e) {
-               errorOut(e, "BinSeqCommand", "help");
+               m->errorOut(e, "BinSeqCommand", "help");
                exit(1);
        }
 }
@@ -149,6 +189,8 @@ int BinSeqCommand::execute(){
                list = globaldata->gListVector;
                string lastLabel = list->getLabel();
                
+               if (m->control_pressed) {  return 0; }
+               
                //if the users enters label "0.06" and there is no "0.06" in their file use the next lowest label.
                set<string> processedLabels;
                set<string> userLabels = labels;
@@ -156,24 +198,31 @@ int BinSeqCommand::execute(){
                                
                while((list != NULL) && ((allLines == 1) || (userLabels.size() != 0))) {
                        
+                       if(m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str());         } return 0; }   
+                       
                        if(allLines == 1 || labels.count(list->getLabel()) == 1){
                                
                                error = process(list);  
-                               if (error == 1) { return 0; }   
+                               if (error == 1) { for (int i = 0; i < outputNames.size(); i++) {        remove(outputNames[i].c_str());         } return 0; }   
                                                        
                                processedLabels.insert(list->getLabel());
                                userLabels.erase(list->getLabel());
                        }
                        
                        if ((anyLabelsToProcess(list->getLabel(), userLabels, "") == true) && (processedLabels.count(lastLabel) != 1)) {
+                               string saveLabel = list->getLabel();
+                               
                                delete list;
                                list = input->getListVector(lastLabel);
                                
                                error = process(list);  
-                               if (error == 1) { return 0; }
+                               if (error == 1) { for (int i = 0; i < outputNames.size(); i++) {        remove(outputNames[i].c_str());         } return 0; }
                                                                                                        
                                processedLabels.insert(list->getLabel());
                                userLabels.erase(list->getLabel());
+                               
+                               //restore real lastlabel to save below
+                               list->setLabel(saveLabel);
                        }
                        
                        lastLabel = list->getLabel();                   
@@ -182,17 +231,18 @@ int BinSeqCommand::execute(){
                        list = input->getListVector();
                }
                
-               
+               if(m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str());         } return 0; }   
+
                //output error messages about any remaining user labels
                set<string>::iterator it;
                bool needToRun = false;
                for (it = userLabels.begin(); it != userLabels.end(); it++) {  
-                       mothurOut("Your file does not include the label " + *it); 
+                       m->mothurOut("Your file does not include the label " + *it); 
                        if (processedLabels.count(lastLabel) != 1) {
-                               mothurOut(". I will use " + lastLabel + "."); mothurOutEndLine();
+                               m->mothurOut(". I will use " + lastLabel + "."); m->mothurOutEndLine();
                                needToRun = true;
                        }else {
-                               mothurOut(". Please refer to " + lastLabel + ".");  mothurOutEndLine();
+                               m->mothurOut(". Please refer to " + lastLabel + ".");  m->mothurOutEndLine();
                        }
                }
                
@@ -202,15 +252,23 @@ int BinSeqCommand::execute(){
                        list = input->getListVector(lastLabel);
                                
                        error = process(list);  
-                       if (error == 1) { return 0; }
+                       if (error == 1) { for (int i = 0; i < outputNames.size(); i++) {        remove(outputNames[i].c_str());         } return 0; }
                        
                        delete list;  
                }
                
+               if(m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str());         } return 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, "BinSeqCommand", "execute");
+               m->errorOut(e, "BinSeqCommand", "execute");
                exit(1);
        }
 }
@@ -244,7 +302,7 @@ void BinSeqCommand::readNamesFile() {
 
        }
        catch(exception& e) {
-               errorOut(e, "BinSeqCommand", "readNamesFile");
+               m->errorOut(e, "BinSeqCommand", "readNamesFile");
                exit(1);
        }
 }
@@ -253,14 +311,20 @@ void BinSeqCommand::readNamesFile() {
 int BinSeqCommand::process(ListVector* list) {
        try {
                                string binnames, name, sequence;
-                               string outputFileName = getRootName(globaldata->getListFile()) + list->getLabel() + ".fasta";
+                               
+                               string outputFileName = outputDir + getRootName(getSimpleName(globaldata->getListFile())) + list->getLabel() + ".fasta";
                                openOutputFile(outputFileName, out);
+                               
+                               //save to output list of output file names
+                               outputNames.push_back(outputFileName);
 
-                               mothurOut(list->getLabel()); mothurOutEndLine();
+                               m->mothurOut(list->getLabel()); m->mothurOutEndLine();
                                
                                //for each bin in the list vector
                                for (int i = 0; i < list->size(); i++) {
-
+                                       
+                                       if (m->control_pressed) {  return 1; }
+                                       
                                        binnames = list->get(i);
                                        while (binnames.find_first_of(',') != -1) { 
                                                name = binnames.substr(0,binnames.find_first_of(','));
@@ -277,8 +341,7 @@ int BinSeqCommand::process(ListVector* list) {
                                                        }else {//if you do have groups
                                                                string group = groupMap->getGroup(name);
                                                                if (group == "not found") {  
-                                                                       mothurOut(name + " is missing from your group file. Please correct. ");  mothurOutEndLine();
-                                                                       remove(outputFileName.c_str());
+                                                                       m->mothurOut(name + " is missing from your group file. Please correct. ");  m->mothurOutEndLine();
                                                                        return 1;
                                                                }else{
                                                                        name = name + "|" + group + "|" + toString(i+1);
@@ -287,8 +350,7 @@ int BinSeqCommand::process(ListVector* list) {
                                                                }
                                                        }
                                                }else { 
-                                                       mothurOut(name + " is missing from your fasta or name file. Please correct. "); mothurOutEndLine();
-                                                       remove(outputFileName.c_str());
+                                                       m->mothurOut(name + " is missing from your fasta or name file. Please correct. "); m->mothurOutEndLine();
                                                        return 1;
                                                }
                                                
@@ -305,8 +367,7 @@ int BinSeqCommand::process(ListVector* list) {
                                                }else {//if you do have groups
                                                        string group = groupMap->getGroup(binnames);
                                                        if (group == "not found") {  
-                                                               mothurOut(binnames + " is missing from your group file. Please correct. "); mothurOutEndLine();
-                                                               remove(outputFileName.c_str());
+                                                               m->mothurOut(binnames + " is missing from your group file. Please correct. "); m->mothurOutEndLine();
                                                                return 1;
                                                        }else{
                                                                binnames = binnames + "|" + group + "|" + toString(i+1);
@@ -315,8 +376,7 @@ int BinSeqCommand::process(ListVector* list) {
                                                        }
                                                }
                                        }else { 
-                                               mothurOut(binnames + " is missing from your fasta or name file. Please correct. "); mothurOutEndLine();
-                                               remove(outputFileName.c_str());
+                                               m->mothurOut(binnames + " is missing from your fasta or name file. Please correct. "); m->mothurOutEndLine();
                                                return 1;
                                        }
                                }
@@ -326,7 +386,7 @@ int BinSeqCommand::process(ListVector* list) {
 
        }
        catch(exception& e) {
-               errorOut(e, "BinSeqCommand", "process");
+               m->errorOut(e, "BinSeqCommand", "process");
                exit(1);
        }
 }