]> git.donarmstrong.com Git - mothur.git/blobdiff - globaldata.cpp
added smart distance feature and optimized all commands using line by line processing
[mothur.git] / globaldata.cpp
index 67c49bd28c942d5c432538b6f965406c0b592ae6..a8e88c52ffbd9d9fe9bb711d4be2cf0c361c9212 100644 (file)
@@ -1,9 +1,6 @@
 #include "globaldata.hpp"
-#include "sparsematrix.hpp"
 #include "tree.h"
-#include "rabundvector.hpp"
-#include "sabundvector.hpp"
-#include "listvector.hpp"
+#include "sparsematrix.hpp"
 
 /*******************************************************/
 
@@ -29,9 +26,11 @@ void GlobalData::parseGlobalData(string commandString, string optionText){
                if ((commandName == "read.dist") || (commandName == "read.otu") || (commandName == "read.tree")) { 
                        clear();
                        gGroupmap = NULL;
+                       gListVector = NULL;
+                       gSparseMatrix = NULL;
                        gTree.clear();
                        Treenames.clear();
-                       labels.clear(); lines.clear(); groups.clear();
+                       labels.clear(); lines.clear(); Groups.clear();
                        allLines = 1;
                }
                
@@ -45,6 +44,9 @@ void GlobalData::parseGlobalData(string commandString, string optionText){
                        cutoff = "1.0";
                }
                
+               //set default value for cutoff
+               if (commandName == "dist.seqs") {       cutoff = "1.0";         }
+
                string key, value;              
                //reads in parameters and values
                if((optionText != "") && (commandName != "help")){
@@ -57,7 +59,9 @@ void GlobalData::parseGlobalData(string commandString, string optionText){
                                if (key == "list" )             { listfile = value; inputFileName = value; fileroot = value; format = "list";           }
                                if (key == "rabund" )   { rabundfile = value; inputFileName = value; fileroot = value; format = "rabund";       }
                                if (key == "sabund" )   { sabundfile = value; inputFileName = value; fileroot = value; format = "sabund";       } 
-                               if (key == "fasta" )    { fastafile = value; inputFileName = value; fileroot = value; format = "fasta";         } 
+                               if (key == "fasta" )    { fastafile = value; inputFileName = value; fileroot = value; format = "fasta";         }
+                               if (key == "nexus" )    { nexusfile = value; inputFileName = value; fileroot = value; format = "nexus";         } 
+                               if (key == "clustal" )  { clustalfile = value; inputFileName = value; fileroot = value; format = "clustal"; }
                                if (key == "tree" )             { treefile = value; inputFileName = value; fileroot = value; format = "tree";           }
                                if (key == "shared" )   { sharedfile = value; inputFileName = value; fileroot = value; format = "sharedfile";   }
                                if (key == "name" )             { namefile = value;             }
@@ -76,24 +80,39 @@ void GlobalData::parseGlobalData(string commandString, string optionText){
                                if (key == "step")                      { step = value;                 }
                                if (key == "form")                      { form = value;                 }
                                if (key == "sorted")            { sorted = value;               }
+                               if (key == "vertical")          { vertical = value;             }
+                               if (key == "trump")                 { trump = value;            }
+                               if (key == "hard")                      { hard = value;         }
+                               if (key == "soft")                  { soft = value;                 }
+                               if (key == "scale")                     { scale = value;                }
+                               if (key == "countends" )        { countends = value;    }
+                               if (key == "processors" )       { processors = value;   }
+                               if (key == "size" )         { size = value;         }
+                               if (key == "candidate")         { candidatefile = value;        }
+                               if (key == "search")            { search = value;               }
+                               if (key == "ksize")                     { ksize = value;                }
+                               if (key == "align")                 { align = value;            }
+                               if (key == "match")                     { match = value;                }
+                               if (key == "mismatch")          { mismatch = value;         }
+                               if (key == "gapopen")           { gapopen = value;              }
+                               if (key == "gapextend" )        { gapextend = value;    }
                                
-
-                               
-                               if (key == "line") {//stores lines to be used in a set
+                               if (key == "line") {//stores lines to be used in a vector
                                        lines.clear();
                                        labels.clear();
                                        line = value;
                                        label = "";
-                                       splitAtDash(value, lines);
-                                       allLines = 0;
+                                       if (line != "all") {  splitAtDash(value, lines);  allLines = 0;  }
+                                       else { allLines = 1;  }
                                }
-                               if (key == "label") {//stores labels to be used in a set
+                       
+                               if (key == "label") {//stores lines to be used in a vector
                                        labels.clear();
                                        lines.clear();
                                        label = value;
                                        line = "";
-                                       splitAtDash(value, labels);
-                                       allLines = 0;
+                                       if (label != "all") {  splitAtDash(value, labels);  allLines = 0;  }
+                                       else { allLines = 1;  }
                                }
 
                                if (key == "groups") {//stores groups to be used in a vector
@@ -113,6 +132,8 @@ void GlobalData::parseGlobalData(string commandString, string optionText){
                        if (key == "rabund" )   { rabundfile = value; inputFileName = value; fileroot = value; format = "rabund";       }
                        if (key == "sabund" )   { sabundfile = value; inputFileName = value; fileroot = value; format = "sabund";       }
                        if (key == "fasta" )    { fastafile = value; inputFileName = value; fileroot = value; format = "fasta";         }
+                       if (key == "nexus" )    { nexusfile = value; inputFileName = value; fileroot = value; format = "nexus";         }
+                       if (key == "clustal" )  { clustalfile = value; inputFileName = value; fileroot = value; format = "clustal"; } 
                        if (key == "tree" )             { treefile = value; inputFileName = value; fileroot = value; format = "tree";           } 
                        if (key == "shared" )   { sharedfile = value; inputFileName = value; fileroot = value; format = "sharedfile";   } 
                        if (key == "name" )             { namefile = value;             }
@@ -131,6 +152,22 @@ void GlobalData::parseGlobalData(string commandString, string optionText){
                        if (key == "step")                      { step = value;                 }
                        if (key == "form")                      { form = value;                 }
                        if (key == "sorted")            { sorted = value;               }
+                       if (key == "vertical")          { vertical = value;             }
+                       if (key == "trump")                 { trump = value;            }
+                       if (key == "hard")                      { hard = value;         }
+                       if (key == "soft")                  { soft = value;                 }
+                       if (key == "scale")                     { scale = value;                }
+                       if (key == "countends" )        { countends = value;    }
+                       if (key == "processors" )       { processors = value;   }
+                       if (key == "size" )         { size = value;         }
+                       if (key == "candidate")         { candidatefile = value;        }
+                       if (key == "search")            { search = value;               }
+                       if (key == "ksize")                     { ksize = value;                }
+                       if (key == "align")                 { align = value;            }
+                       if (key == "match")                     { match = value;                }
+                       if (key == "mismatch")          { mismatch = value;         }
+                       if (key == "gapopen")           { gapopen = value;              }
+                       if (key == "gapextend" )        { gapextend = value;    }
 
                        if (key == "line") {//stores lines to be used in a vector
                                lines.clear();
@@ -140,6 +177,7 @@ void GlobalData::parseGlobalData(string commandString, string optionText){
                                if (line != "all") {  splitAtDash(value, lines);  allLines = 0;  }
                                else { allLines = 1;  }
                        }
+                       
                        if (key == "label") {//stores lines to be used in a vector
                                labels.clear();
                                lines.clear();
@@ -162,7 +200,8 @@ void GlobalData::parseGlobalData(string commandString, string optionText){
                                
                //input defaults for calculators
                if (commandName == "collect.single") {
-                       if ((calc == "default") || (calc == "")) { calc = "sobs-chao-ace-jack-bootstrap-shannon-npshannon-simpson-geom-qstat-logsd-bergerparker-bstick"; }
+
+                       if ((calc == "default") || (calc == "")) { calc = "sobs-chao-ace-jack-shannon-npshannon-simpson"; }
                        Estimators.clear();
                        splitAtDash(calc, Estimators); 
                }
@@ -172,17 +211,18 @@ void GlobalData::parseGlobalData(string commandString, string optionText){
                        splitAtDash(calc, Estimators); 
                }
                if (commandName == "collect.shared") {
-                       if ((calc == "default") || (calc == "")) { calc = "sharedsobs-sharedchao-sharedace-sharedjabund-sharedsorensonabund-sharedjclass-sharedsorclass-sharedjest-sharedsorest-sharedthetayc-sharedthetan-sharedkstest-sharedbdiversity"; }
+
+                       if ((calc == "default") || (calc == "")) { calc = "sharedsobs-sharedchao-sharedace-jabund-sorabund-jclass-sorclass-jest-sorest-thetayc-thetan"; }
                        Estimators.clear();
                        splitAtDash(calc, Estimators); 
                }
                if (commandName == "summary.single") {
-                       if ((calc == "default") || (calc == "")) { calc = "sobs-chao-ace-jack-bootstrap-shannon-npshannon-simpson-geom-logsd-qstat-bergerparker-bstick"; }
+                       if ((calc == "default") || (calc == "")) { calc = "sobs-chao-ace-jack-shannon-npshannon-simpson"; }
                        Estimators.clear();
                        splitAtDash(calc, Estimators); 
                }
                if (commandName == "summary.shared") {
-                       if ((calc == "default") || (calc == "")) { calc = "sharedsobs-sharedchao-sharedace-sharedjabund-sharedsorensonabund-sharedjclass-sharedsorclass-sharedjest-sharedsorest-sharedthetayc-sharedthetan-sharedkstest-sharedbdiversity"; }
+                       if ((calc == "default") || (calc == "")) { calc = "sharedsobs-sharedchao-sharedace-jabund-sorabund-jclass-sorclass-jest-sorest-thetayc-thetan"; }
                        Estimators.clear();
                        splitAtDash(calc, Estimators); 
                }
@@ -191,6 +231,12 @@ void GlobalData::parseGlobalData(string commandString, string optionText){
                        Estimators.clear();
                        splitAtDash(calc, Estimators); 
                }
+               if (commandName == "dist.seqs") {
+                       if ((calc == "default") || (calc == "")) {  calc = "onegap";    }
+                       if (countends == "")    { countends = "T"; }
+                       Estimators.clear();
+                       splitAtDash(calc, Estimators); 
+               }
                if (commandName == "venn") {
                        if ((calc == "default") || (calc == "")) { 
                                if (format == "list") { calc = "sobs"; }
@@ -199,6 +245,20 @@ void GlobalData::parseGlobalData(string commandString, string optionText){
                        Estimators.clear();
                        splitAtDash(calc, Estimators); 
                }
+               if ((commandName == "tree.shared") || (commandName == "bootstrap.shared") || (commandName == "dist.shared")) {
+                       if ((calc == "default") || (calc == "")) { 
+                               calc = "jclass-thetayc";
+                       }
+                       Estimators.clear();
+                       splitAtDash(calc, Estimators); 
+               }
+               
+               if(commandName == "filter.seqs"){
+                       if(trump == "" && vertical == "" && hard == "" && soft == ""){
+                               trump = '.';
+                       }
+
+               }
 
                //if you have done a read.otu with a groupfile but don't want to use it anymore because you want to do single commands
                if ((commandName == "collect.single") || (commandName == "rarefaction.single") || (commandName == "summary.single")) {
@@ -231,6 +291,8 @@ string GlobalData::getOrderFile()           {       return orderfile;       }
 string GlobalData::getTreeFile()               {       return treefile;        }
 string GlobalData::getSharedFile()             {       return sharedfile;      }
 string GlobalData::getFastaFile()              {       return fastafile;       }
+string GlobalData::getNexusFile()              {       return nexusfile;       }
+string GlobalData::getClustalFile()     {   return clustalfile; }
 string GlobalData::getCutOff()                 {       return cutoff;          }
 string GlobalData::getFormat()                 {       return format;          }
 string GlobalData::getPrecision()              {       return precision;       }
@@ -245,16 +307,39 @@ string GlobalData::getGroups()                    {       return groups;          }
 string GlobalData::getStep()                   {       return step;            }
 string GlobalData::getForm()                   {       return form;            }
 string GlobalData::getSorted()                 {       return sorted;          }
-void GlobalData::setListFile(string file)      {       listfile = file;        inputFileName = file;}
-void GlobalData::setRabundFile(string file)    {       rabundfile = file;      inputFileName = file;}
-void GlobalData::setSabundFile(string file)    {       sabundfile = file;      inputFileName = file;}
-void GlobalData::setPhylipFile(string file)    {       phylipfile = file;    inputFileName = file;}
-void GlobalData::setColumnFile(string file)    {       columnfile = file;    inputFileName = file;}
+string GlobalData::getVertical()               {   return vertical;    }
+string GlobalData::getTrump()                  {   return trump;       }
+string GlobalData::getSoft()                   {   return soft;                }
+string GlobalData::getHard()                   {   return hard;                }
+string GlobalData::getScale()                  {       return scale;           }
+string GlobalData::getCountEnds()              {   return countends;   }
+string GlobalData::getProcessors()             {       return processors;      }
+string GlobalData::getSize()            {   return size;        }
+string GlobalData::getCandidateFile()  {       return candidatefile;}
+string GlobalData::getSearch()                 {       return search;          }
+string GlobalData::getKSize()                  {       return ksize;           }
+string GlobalData::getAlign()                  {       return align;           }
+string GlobalData::getMatch()                  {       return match;           }
+string GlobalData::getMismatch()               {       return mismatch;        }
+string GlobalData::getGapopen()                        {       return gapopen;         }
+string GlobalData::getGapextend()              {       return gapextend;       }
+
+
+void GlobalData::setListFile(string file)              {       listfile = file;        inputFileName = file;                                   }
+void GlobalData::setRabundFile(string file)            {       rabundfile = file;      inputFileName = file;                                   }
+void GlobalData::setSabundFile(string file)            {       sabundfile = file;      inputFileName = file;                                   }
+void GlobalData::setPhylipFile(string file)            {       phylipfile = file;    inputFileName = file;                                     }
+void GlobalData::setColumnFile(string file)            {       columnfile = file;    inputFileName = file;                                     }
+void GlobalData::setGroupFile(string file)             {       groupfile = file;                                                                                       }
+void GlobalData::setSharedFile(string file)            {       sharedfile = file;      inputFileName = file; fileroot = file;  }
 void GlobalData::setNameFile(string file)              {       namefile = file;                }
 void GlobalData::setFormat(string Format)              {       format = Format;                }
 void GlobalData::setRandomTree(string Random)  {       randomtree = Random;    }
 void GlobalData::setGroups(string g)                   {       groups = g;                             }
 void GlobalData::setCalc(string Calc)                  {       calc = Calc;                    }
+void GlobalData::setCountEnds(string e)                        {   countends = e;                      }
+void GlobalData::setProcessors(string p)               {       processors = p;                 }
+
 
 /*******************************************************/
 
@@ -263,6 +348,8 @@ GlobalData::GlobalData() {
        //option definitions should go here...
        helpRequest = "";
        clear();
+       gListVector == NULL;            
+       gSparseMatrix == NULL;  
 }
 /*******************************************************/
 
@@ -278,8 +365,11 @@ void GlobalData::clear() {
        groupfile               =       ""; 
        orderfile               =       "";
        fastafile               =   "";
+       nexusfile               =   "";
+       clustalfile             =   "";
        treefile                =       "";
        sharedfile              =       "";
+       candidatefile   =       "";
        cutoff                  =       "10.00";
        format                  =       "";
        precision               =       "100";
@@ -295,7 +385,22 @@ void GlobalData::clear() {
        abund           =   "10";
        step                    =       "0.01";
        form                    =       "integral";
-       sorted                  =       "1";  //0 means don't sort, 1 means sort.
+       sorted                  =       "T";  //F means don't sort, T means sort.
+       vertical        =   "";         
+       trump           =       "";             
+       hard                    =   "";         
+       soft            =   ""; 
+       scale                   =       "log10";
+       countends               =   "T";  //yes
+       processors              =       "1";
+       size            =   "0";
+       search                  =       "kmer";
+       ksize                   =       "7";
+       align                   =       "needleman";
+       match                   =       "1.0";
+       mismatch                =       "-1.0";
+       gapopen                 =       "-1.0";
+       gapextend               =       "-2.0";
 }
 
 //*******************************************************/
@@ -307,7 +412,7 @@ void GlobalData::reset() {
        iters                   =       "1000"; 
        groups                  =       "";
        jumble                  =       "1";    //0 means don't jumble, 1 means jumble.
-       sorted                  =       "1";  //0 means don't sort, 1 means sort.
+       sorted                  =       "T";  //F means don't sort, T means sort.
        randomtree              =       "";  //"" means user will enter some user trees, "outputfile" means they just want the random tree distribution to be outputted to outputfile.
        freq                    =       "100";
        method                  =       "furthest";
@@ -315,6 +420,21 @@ void GlobalData::reset() {
        abund                   =   "10";
        step                    =       "0.01";
        form                    =       "integral";
+       countends               =   "T";
+       processors              =       "1";
+       size            =   "0";
+       search                  =       "kmer";
+       ksize                   =       "7";
+       align                   =       "needleman";
+       match                   =       "1.0";
+       mismatch                =       "-1.0";
+       gapopen                 =       "-1.0";
+       gapextend               =       "-2.0";
+       vertical        =   "";         
+       trump           =   "";         
+       hard                    =   "";         
+       soft            =   ""; 
+
 }
 /*******************************************************/
 
@@ -382,7 +502,7 @@ void GlobalData::parseTreeFile() {
                        
                        //use nexus translation rather than parsing tree to save time
                        if ((holder == "translate") || (holder == "Translate")) {
-cout << "there is a translate " << endl;
+
                                string number, name, h;
                                h = ""; // so it enters the loop the first time
                                while((h != ";") && (number != ";")) {