]> git.donarmstrong.com Git - mothur.git/blobdiff - getgroupscommand.cpp
removing chime source files from mother project.
[mothur.git] / getgroupscommand.cpp
index 5021f4085534cfc84a17d5875e449cf90f9f1d53..5ed31dd84b55ba26ee64a45e9298c84fb60a6be2 100644 (file)
 //**********************************************************************************************************************
 vector<string> GetGroupsCommand::setParameters(){      
        try {
-               CommandParameter pfasta("fasta", "InputTypes", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(pfasta);
-               CommandParameter pshared("shared", "InputTypes", "", "", "none", "FNGLT-sharedGroup", "none",false,false); parameters.push_back(pshared);
-               CommandParameter pname("name", "InputTypes", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(pname);
-               CommandParameter pgroup("group", "InputTypes", "", "", "none", "FNGLT-sharedGroup", "none",false,false); parameters.push_back(pgroup);
-               CommandParameter plist("list", "InputTypes", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(plist);
-               CommandParameter ptaxonomy("taxonomy", "InputTypes", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(ptaxonomy);
+               CommandParameter pfasta("fasta", "InputTypes", "", "", "none", "none", "FNGLT",false,false); parameters.push_back(pfasta);
+               CommandParameter pshared("shared", "InputTypes", "", "", "none", "sharedGroup", "none",false,false); parameters.push_back(pshared);
+               CommandParameter pname("name", "InputTypes", "", "", "none", "none", "none",false,false); parameters.push_back(pname);
+               CommandParameter pgroup("group", "InputTypes", "", "", "none", "sharedGroup", "FNGLT",false,false); parameters.push_back(pgroup);
+        CommandParameter pdesign("design", "InputTypes", "", "", "none", "sharedGroup", "FNGLT",false,false); parameters.push_back(pdesign);
+               CommandParameter plist("list", "InputTypes", "", "", "none", "none", "FNGLT",false,false); parameters.push_back(plist);
+               CommandParameter ptaxonomy("taxonomy", "InputTypes", "", "", "none", "none", "FNGLT",false,false); parameters.push_back(ptaxonomy);
                CommandParameter paccnos("accnos", "InputTypes", "", "", "none", "none", "none",false,false); parameters.push_back(paccnos);
                CommandParameter pgroups("groups", "String", "", "", "", "", "",false,false); parameters.push_back(pgroups);
                CommandParameter pinputdir("inputdir", "String", "", "", "", "", "",false,false); parameters.push_back(pinputdir);
@@ -40,9 +41,9 @@ vector<string> GetGroupsCommand::setParameters(){
 string GetGroupsCommand::getHelpString(){      
        try {
                string helpString = "";
-               helpString += "The get.groups command selects sequences from a specfic group or set of groups from the following file types: fasta, name, group, list, taxonomy or shared file.\n";
+               helpString += "The get.groups command selects sequences from a specfic group or set of groups from the following file types: fasta, name, group, list, taxonomy, design or shared file.\n";
                helpString += "It outputs a file containing the sequences in the those specified groups, or a sharedfile containing only those groups.\n";
-               helpString += "The get.groups command parameters are accnos, fasta, name, group, list, taxonomy, shared and groups. The group parameter is required, unless you have a current group file, or are using a shared file.\n";
+               helpString += "The get.groups command parameters are accnos, fasta, name, group, list, taxonomy, shared, design and groups. The group parameter is required, unless you have a current group file, or are using a shared file.\n";
                helpString += "You must also provide an accnos containing the list of groups to get or set the groups parameter to the groups you wish to select.\n";
                helpString += "The groups parameter allows you to specify which of the groups in your groupfile you would like.  You can separate group names with dashes.\n";
                helpString += "The get.groups command should be in the following format: get.groups(accnos=yourAccnos, fasta=yourFasta, group=yourGroupFile).\n";
@@ -68,6 +69,7 @@ GetGroupsCommand::GetGroupsCommand(){
                outputTypes["group"] = tempOutNames;
                outputTypes["list"] = tempOutNames;
                outputTypes["shared"] = tempOutNames;
+        outputTypes["design"] = tempOutNames;
        }
        catch(exception& e) {
                m->errorOut(e, "GetGroupsCommand", "GetGroupsCommand");
@@ -105,6 +107,7 @@ GetGroupsCommand::GetGroupsCommand(string option)  {
                        outputTypes["group"] = tempOutNames;
                        outputTypes["list"] = tempOutNames;
                        outputTypes["shared"] = tempOutNames;
+            outputTypes["design"] = tempOutNames;
                        
                        
                        //if the user changes the output directory command factory will send this info to us in the output parameter 
@@ -170,6 +173,14 @@ GetGroupsCommand::GetGroupsCommand(string option)  {
                                        //if the user has not given a path then, add inputdir. else leave path alone.
                                        if (path == "") {       parameters["shared"] = inputDir + it->second;           }
                                }
+                
+                it = parameters.find("design");
+                               //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["design"] = inputDir + it->second;           }
+                               }
                        }
                        
                        
@@ -180,22 +191,27 @@ GetGroupsCommand::GetGroupsCommand(string option)  {
                        else { m->setAccnosFile(accnosfile); }
                        
                        fastafile = validParameter.validFile(parameters, "fasta", true);
-                       if (fastafile == "not open") { abort = true; }
+                       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") { groupfile = ""; abort = true; }
+                       else if (groupfile == "not found") {  groupfile = "";                   }
+                       else { m->setGroupFile(groupfile); }    
+                       
                        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); }
                        
@@ -214,9 +230,14 @@ GetGroupsCommand::GetGroupsCommand(string option)  {
                        groupfile = validParameter.validFile(parameters, "group", true);
                        if (groupfile == "not open") { groupfile = ""; abort = true; }
                        else if (groupfile == "not found") {    groupfile = ""; }
-                       else { m->setGroupFile(groupfile); }    
-                       
-                       if ((sharedfile == "") && (groupfile == "")) { 
+                       else { m->setGroupFile(groupfile); }
+            
+            designfile = validParameter.validFile(parameters, "design", true);
+                       if (designfile == "not open") { designfile = ""; abort = true; }
+                       else if (designfile == "not found") {   designfile = "";        }
+                       else { m->setDesignFile(designfile); }
+                       
+                       if ((sharedfile == "") && (groupfile == "") && (designfile == "")) { 
                                //is there are current file available for any of these?
                                if ((namefile != "") || (fastafile != "") || (listfile != "") || (taxfile != "")) {
                                        //give priority to group, then shared
@@ -237,7 +258,11 @@ GetGroupsCommand::GetGroupsCommand(string option)  {
                                                groupfile = m->getGroupFile(); 
                                                if (groupfile != "") { m->mothurOut("Using " + groupfile + " as input file for the group parameter."); m->mothurOutEndLine(); }
                                                else { 
-                                                       m->mothurOut("You have no current groupfile or sharedfile and one is required."); m->mothurOutEndLine(); abort = true;
+                                                       designfile = m->getDesignFile(); 
+                            if (designfile != "") { m->mothurOut("Using " + designfile + " as input file for the design parameter."); m->mothurOutEndLine(); }
+                            else { 
+                                m->mothurOut("You have no current groupfile or sharedfile or designfile and one is required."); m->mothurOutEndLine(); abort = true;
+                            }
                                                }
                                        }
                                }
@@ -245,9 +270,13 @@ GetGroupsCommand::GetGroupsCommand(string option)  {
                        
                        if ((accnosfile == "") && (Groups.size() == 0)) { m->mothurOut("You must provide an accnos file or specify groups using the groups parameter."); m->mothurOutEndLine(); abort = true; }
                        
-                       if ((fastafile == "") && (namefile == "") && (groupfile == "")  && (sharedfile == "") && (listfile == "") && (taxfile == ""))  { m->mothurOut("You must provide at least one of the following: fasta, name, taxonomy, group, shared or list."); m->mothurOutEndLine(); abort = true; }
+                       if ((fastafile == "") && (namefile == "") && (groupfile == "")  && (designfile == "") && (sharedfile == "") && (listfile == "") && (taxfile == ""))  { m->mothurOut("You must provide at least one of the following: fasta, name, taxonomy, group, shared, design or list."); m->mothurOutEndLine(); abort = true; }
                        if ((groupfile == "") && ((namefile != "") || (fastafile != "") || (listfile != "") || (taxfile != "")))  { m->mothurOut("If using a fasta, name, taxonomy, group or list, then you must provide a group file."); m->mothurOutEndLine(); abort = true; }
 
+                       if ((namefile == "") && ((fastafile != "") || (taxfile != ""))){
+                               vector<string> files; files.push_back(fastafile); files.push_back(taxfile);
+                               parser.getNameFile(files);
+                       }
                }
                
        }
@@ -293,6 +322,7 @@ int GetGroupsCommand::execute(){
                if (listfile != "")                     {               readList();             }
                if (taxfile != "")                      {               readTax();              }
                if (sharedfile != "")           {               readShared();   }
+        if (designfile != "")          {               readDesign();   }
                
                if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) {        m->mothurRemove(outputNames[i]); } return 0; }
                
@@ -334,6 +364,11 @@ int GetGroupsCommand::execute(){
                        if (itTypes != outputTypes.end()) {
                                if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setSharedFile(current); }
                        }
+            
+            itTypes = outputTypes.find("design");
+                       if (itTypes != outputTypes.end()) {
+                               if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setDesignFile(current); }
+                       }
                }
                
                return 0;               
@@ -375,6 +410,15 @@ int GetGroupsCommand::readFasta(){
                                        
                                        currSeq.printSequence(out);
                                        selectedCount++;
+                               }else{
+                                       //if you are not in the accnos file check if you are a name that needs to be changed
+                                       map<string, string>::iterator it = uniqueToRedundant.find(name);
+                                       if (it != uniqueToRedundant.end()) {
+                                               wroteSomething = true;
+                                               currSeq.setName(it->second);
+                                               currSeq.printSequence(out);
+                                               selectedCount++;
+                                       }
                                }
                        }
                        m->gobble(in);
@@ -490,10 +534,26 @@ int GetGroupsCommand::readList(){
                                        
                                        //if that name is in the .accnos file, add it
                                        if (names.count(name) != 0) {  newNames += name + ",";  selectedCount++;  }
+                                       else{
+                                               //if you are not in the accnos file check if you are a name that needs to be changed
+                                               map<string, string>::iterator it = uniqueToRedundant.find(name);
+                                               if (it != uniqueToRedundant.end()) {
+                                                       newNames += it->second + ",";
+                                                       selectedCount++;
+                                               }
+                                       }
                                }
                                
                                //get last name
                                if (names.count(binnames) != 0) {  newNames += binnames + ",";  selectedCount++;  }
+                               else{
+                                       //if you are not in the accnos file check if you are a name that needs to be changed
+                                       map<string, string>::iterator it = uniqueToRedundant.find(binnames);
+                                       if (it != uniqueToRedundant.end()) {
+                                               newNames += it->second + ",";
+                                               selectedCount++;
+                                       }
+                               }
                                
                                //if there are names in this bin add to new list
                                if (newNames != "") {  
@@ -585,6 +645,7 @@ int GetGroupsCommand::readName(){
                                        //you know you have at least one valid second since first column is valid
                                        for (int i = 0; i < validSecond.size()-1; i++) {  out << validSecond[i] << ',';  }
                                        out << validSecond[validSecond.size()-1] << endl;
+                                       uniqueToRedundant[firstCol] = validSecond[0];
                                }
                        }
                        
@@ -653,6 +714,56 @@ int GetGroupsCommand::readGroup(){
                exit(1);
        }
 }
+//**********************************************************************************************************************
+int GetGroupsCommand::readDesign(){
+       try {
+               string thisOutputDir = outputDir;
+               if (outputDir == "") {  thisOutputDir += m->hasPath(designfile);  }
+               string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(designfile)) + "pick" + m->getExtension(designfile);
+               
+               ofstream out;
+               m->openOutputFile(outputFileName, out);
+               
+               ifstream in;
+               m->openInputFile(designfile, in);
+               string name, group;
+               
+               bool wroteSomething = false;
+               int selectedCount = 0;
+               
+               while(!in.eof()){
+                       if (m->control_pressed) { in.close();  out.close();  m->mothurRemove(outputFileName);  return 0; }
+                       
+                       in >> name;                             //read from first column
+                       in >> group;                    //read from second column
+                       
+                       //if this name is in the accnos file
+                       if (m->inUsersGroups(name, Groups)) {
+                               wroteSomething = true;
+                               out << name << '\t' << group << endl;
+                selectedCount++;
+                       }
+                       
+                       m->gobble(in);
+               }
+               in.close();
+               out.close();
+               
+               if (wroteSomething == false) {  m->mothurOut("Your file does NOT contain groups from the groups you wish to get."); m->mothurOutEndLine();  }
+               outputTypes["design"].push_back(outputFileName); outputNames.push_back(outputFileName);
+               
+               m->mothurOut("Selected " + toString(selectedCount) + " groups from your design file."); m->mothurOutEndLine();
+        
+               
+               return 0;
+       }
+       catch(exception& e) {
+               m->errorOut(e, "GetGroupsCommand", "readDesign");
+               exit(1);
+       }
+}
+
+
 //**********************************************************************************************************************
 int GetGroupsCommand::readTax(){
        try {
@@ -678,6 +789,13 @@ int GetGroupsCommand::readTax(){
                        if (names.count(name) != 0) {
                                wroteSomething = true;
                                out << name << '\t' << tax << endl;
+                       }else{
+                               //if you are not in the accnos file check if you are a name that needs to be changed
+                               map<string, string>::iterator it = uniqueToRedundant.find(name);
+                               if (it != uniqueToRedundant.end()) {
+                                       wroteSomething = true;
+                                       out << it->second << '\t' << tax << endl;
+                               }
                        }
                        
                        m->gobble(in);