]> git.donarmstrong.com Git - mothur.git/blobdiff - readtreecommand.cpp
fixed cluster.classic and added weighted method to hcluster
[mothur.git] / readtreecommand.cpp
index 09f899b947bf9bb4b455de86479d34ffa709d46f..edfdf3b77e0d85ff51afce83323d0204ab987a66 100644 (file)
 #include "readtreecommand.h"
 
 //**********************************************************************************************************************
-ReadTreeCommand::ReadTreeCommand(string option){
+vector<string> ReadTreeCommand::getValidParameters(){  
+       try {
+               string Array[] =  {"tree","group","name","outputdir","inputdir"};
+               vector<string> myArray (Array, Array+(sizeof(Array)/sizeof(string)));
+               return myArray;
+       }
+       catch(exception& e) {
+               m->errorOut(e, "ReadTreeCommand", "getValidParameters");
+               exit(1);
+       }
+}
+//**********************************************************************************************************************
+vector<string> ReadTreeCommand::getRequiredParameters(){       
+       try {
+               string Array[] =  {"tree"};
+               vector<string> myArray (Array, Array+(sizeof(Array)/sizeof(string)));
+               return myArray;
+       }
+       catch(exception& e) {
+               m->errorOut(e, "ReadTreeCommand", "getRequiredParameters");
+               exit(1);
+       }
+}
+//**********************************************************************************************************************
+vector<string> ReadTreeCommand::getRequiredFiles(){    
+       try {
+               vector<string> myArray;
+               return myArray;
+       }
+       catch(exception& e) {
+               m->errorOut(e, "ReadTreeCommand", "getRequiredFiles");
+               exit(1);
+       }
+}
+//**********************************************************************************************************************
+ReadTreeCommand::ReadTreeCommand(string option)  {
        try {
                globaldata = GlobalData::getInstance();
                abort = false;
-               
+                               
                //allow user to run help
                if(option == "help") { help(); abort = true; }
                
@@ -44,7 +79,7 @@ ReadTreeCommand::ReadTreeCommand(string option){
                                it = parameters.find("tree");
                                //user has given a template file
                                if(it != parameters.end()){ 
-                                       path = hasPath(it->second);
+                                       path = m->hasPath(it->second);
                                        //if the user has not given a path then, add inputdir. else leave path alone.
                                        if (path == "") {       parameters["tree"] = inputDir + it->second;             }
                                }
@@ -52,7 +87,7 @@ ReadTreeCommand::ReadTreeCommand(string option){
                                it = parameters.find("group");
                                //user has given a template file
                                if(it != parameters.end()){ 
-                                       path = hasPath(it->second);
+                                       path = m->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;            }
                                }
@@ -60,7 +95,7 @@ ReadTreeCommand::ReadTreeCommand(string option){
                                it = parameters.find("name");
                                //user has given a template file
                                if(it != parameters.end()){ 
-                                       path = hasPath(it->second);
+                                       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;             }
                                }
@@ -71,13 +106,25 @@ ReadTreeCommand::ReadTreeCommand(string option){
                        //check for required parameters
                        treefile = validParameter.validFile(parameters, "tree", true);
                        if (treefile == "not open") { abort = true; }
-                       else if (treefile == "not found") { treefile = ""; mothurOut("tree is a required parameter for the read.tree command."); mothurOutEndLine(); abort = true;  }   
+                       else if (treefile == "not found") { treefile = ""; m->mothurOut("tree is a required parameter for the read.tree command."); m->mothurOutEndLine(); abort = true;  }     
                        else {  globaldata->setTreeFile(treefile);  globaldata->setFormat("tree");      }
                        
                        groupfile = validParameter.validFile(parameters, "group", true);
                        if (groupfile == "not open") { abort = true; }  
-                       else if (groupfile == "not found") { groupfile = ""; mothurOut("group is a required parameter for the read.tree command."); mothurOutEndLine(); abort = true;   }
-                       else {  
+                       else if (groupfile == "not found") { 
+                               groupfile = ""; 
+                               
+                               m->mothurOut("You have not provided a group file. I am assumming all sequence are from the same group."); m->mothurOutEndLine();        
+                               
+                               if (treefile != "") {  Tree* tree = new Tree(treefile); delete tree;  } //extracts names from tree to make faked out groupmap
+                               
+                               globaldata->setGroupFile(groupfile); 
+                               //read in group map info.
+                               treeMap = new TreeMap();
+                               for (int i = 0; i < globaldata->Treenames.size(); i++) { treeMap->addSeq(globaldata->Treenames[i], "Group1"); }
+                               globaldata->gTreemap = treeMap;
+                                       
+                       }else {  
                                globaldata->setGroupFile(groupfile); 
                                //read in group map info.
                                treeMap = new TreeMap(groupfile);
@@ -87,7 +134,7 @@ ReadTreeCommand::ReadTreeCommand(string option){
                        
                        namefile = validParameter.validFile(parameters, "name", true);
                        if (namefile == "not open") { abort = true; }
-                       else if (namefile == "not found") { treefile = ""; }
+                       else if (namefile == "not found") { namefile = ""; }
                        else { readNamesFile(); }       
                        
                        if (abort == false) {
@@ -98,7 +145,7 @@ ReadTreeCommand::ReadTreeCommand(string option){
                }
        }
        catch(exception& e) {
-               errorOut(e, "ReadTreeCommand", "ReadTreeCommand");              
+               m->errorOut(e, "ReadTreeCommand", "ReadTreeCommand");           
                exit(1);
        }
 }
@@ -106,14 +153,16 @@ ReadTreeCommand::ReadTreeCommand(string option){
 
 void ReadTreeCommand::help(){
        try {
-               mothurOut("The read.tree command must be run before you execute a unifrac.weighted, unifrac.unweighted. \n");
-               mothurOut("It also must be run before using the parsimony command, unless you are using the randomtree parameter.\n");
-               mothurOut("The read.tree command should be in the following format: read.tree(tree=yourTreeFile, group=yourGroupFile).\n");
-               mothurOut("The tree and group parameters are both required.\n");
-               mothurOut("Note: No spaces between parameter labels (i.e. tree), '=' and parameters (i.e.yourTreefile).\n\n");
+               m->mothurOut("The read.tree command must be run before you execute a unifrac.weighted, unifrac.unweighted. \n");
+               m->mothurOut("It also must be run before using the parsimony command, unless you are using the randomtree parameter.\n");
+               m->mothurOut("The read.tree command parameters are tree, group and name.\n");
+               m->mothurOut("The read.tree command should be in the following format: read.tree(tree=yourTreeFile, group=yourGroupFile).\n");
+               m->mothurOut("The tree and group parameters are both required, if no group file is given then one group is assumed.\n");
+               m->mothurOut("The name parameter allows you to enter a namefile.\n");
+               m->mothurOut("Note: No spaces between parameter labels (i.e. tree), '=' and parameters (i.e.yourTreefile).\n\n");
        }
        catch(exception& e) {
-               errorOut(e, "ReadTreeCommand", "help"); 
+               m->errorOut(e, "ReadTreeCommand", "help");      
                exit(1);
        }
 }
@@ -135,17 +184,33 @@ int ReadTreeCommand::execute(){
                
                readOk = read->read(); 
                
-               if (readOk != 0) { mothurOut("Read Terminated."); mothurOutEndLine(); globaldata->gTree.clear(); delete globaldata->gTreemap; return 0; }
+               if (readOk != 0) { m->mothurOut("Read Terminated."); m->mothurOutEndLine(); globaldata->gTree.clear(); delete globaldata->gTreemap; return 0; }
                
                vector<Tree*> T = globaldata->gTree;
 
                //assemble users trees
                for (int i = 0; i < T.size(); i++) {
+                       if (m->control_pressed) {  
+                               for (int i = 0; i < T.size(); i++) {  delete T[i];  }
+                               globaldata->gTree.clear();
+                               delete globaldata->gTreemap;
+                               return 0;
+                       }
+       
                        T[i]->assembleTree();
                }
 
+               
+               //if you provide a namefile we will use the numNames in the namefile as long as the number of unique match the tree names size.
+               int numNamesInTree;
+               if (namefile != "")  {  
+                       if (numUniquesInName == globaldata->Treenames.size()) {  numNamesInTree = nameMap.size();  }
+                       else {   numNamesInTree = globaldata->Treenames.size();  }
+               }else {  numNamesInTree = globaldata->Treenames.size();  }
+               
+               
                //output any names that are in group file but not in tree
-               if (globaldata->Treenames.size() < treeMap->getNumSeqs()) {
+               if (numNamesInTree < treeMap->getNumSeqs()) {
                        for (int i = 0; i < treeMap->namesOfSeqs.size(); i++) {
                                //is that name in the tree?
                                int count = 0;
@@ -154,23 +219,33 @@ int ReadTreeCommand::execute(){
                                        count++;
                                }
                                
+                               if (m->control_pressed) {  
+                                       for (int i = 0; i < T.size(); i++) {  delete T[i];  }
+                                       globaldata->gTree.clear();
+                                       delete globaldata->gTreemap;
+                                       return 0;
+                               }
+                               
                                //then you did not find it so report it 
                                if (count == globaldata->Treenames.size()) { 
                                        //if it is in your namefile then don't remove
                                        map<string, string>::iterator it = nameMap.find(treeMap->namesOfSeqs[i]);
                                        
                                        if (it == nameMap.end()) {
-                                               mothurOut(treeMap->namesOfSeqs[i] + " is in your groupfile and not in your tree. It will be disregarded."); mothurOutEndLine();
+                                               m->mothurOut(treeMap->namesOfSeqs[i] + " is in your groupfile and not in your tree. It will be disregarded."); m->mothurOutEndLine();
                                                treeMap->removeSeq(treeMap->namesOfSeqs[i]);
+                                               i--; //need this because removeSeq removes name from namesOfSeqs
                                        }
                                }
                        }
+                       
+                       globaldata->gTreemap = treeMap;
                }
-               
+
                return 0;
        }
        catch(exception& e) {
-               errorOut(e, "ReadTreeCommand", "execute");      
+               m->errorOut(e, "ReadTreeCommand", "execute");   
                exit(1);
        }
 }
@@ -178,33 +253,36 @@ int ReadTreeCommand::execute(){
 int ReadTreeCommand::readNamesFile() {
        try {
                globaldata->names.clear();
+               numUniquesInName = 0;
                
                ifstream in;
-               openInputFile(namefile, in);
+               m->openInputFile(namefile, in);
                
                string first, second;
                map<string, string>::iterator itNames;
                
                while(!in.eof()) {
-                       in >> first >> second; gobble(in);
+                       in >> first >> second; m->gobble(in);
                        
+                       numUniquesInName++;
+
                        itNames = globaldata->names.find(first);
                        if (itNames == globaldata->names.end()) {  
                                globaldata->names[first] = second; 
                                
                                //we need a list of names in your namefile to use above when removing extra seqs above so we don't remove them
                                vector<string> dupNames;
-                               splitAtComma(second, dupNames);
+                               m->splitAtComma(second, dupNames);
                                
-                               for (int i = 0; i < dupNames.size(); i++) {     nameMap[dupNames[i]] = dupNames[i];  }
-                       }else {  mothurOut(first + " has already been seen in namefile, disregarding names file."); mothurOutEndLine(); in.close(); globaldata->names.clear(); return 1; }                      
+                               for (int i = 0; i < dupNames.size(); i++) {     nameMap[dupNames[i]] = dupNames[i];  if ((groupfile == "") && (i != 0)) { globaldata->gTreemap->addSeq(dupNames[i], "Group1"); }  }
+                       }else {  m->mothurOut(first + " has already been seen in namefile, disregarding names file."); m->mothurOutEndLine(); in.close(); globaldata->names.clear(); namefile = ""; return 1; }                 
                }
                in.close();
                
                return 0;
        }
        catch(exception& e) {
-               errorOut(e, "ReadTreeCommand", "readNamesFile");
+               m->errorOut(e, "ReadTreeCommand", "readNamesFile");
                exit(1);
        }
 }