#include "splitabundcommand.h"
//**********************************************************************************************************************
-vector<string> SplitAbundCommand::getValidParameters(){
- try {
- string Array[] = {"name","group","list","label","accnos","groups","fasta","cutoff","outputdir","inputdir"};
- vector<string> myArray (Array, Array+(sizeof(Array)/sizeof(string)));
+vector<string> SplitAbundCommand::setParameters(){
+ try {
+ CommandParameter pfasta("fasta", "InputTypes", "", "", "none", "none", "none",false,true); parameters.push_back(pfasta);
+ CommandParameter pname("name", "InputTypes", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(pname);
+ CommandParameter pgroup("group", "InputTypes", "", "", "none", "none", "none",false,false); parameters.push_back(pgroup);
+ CommandParameter plist("list", "InputTypes", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(plist);
+ CommandParameter plabel("label", "String", "", "", "", "", "",false,false); parameters.push_back(plabel);
+ CommandParameter pcutoff("cutoff", "Number", "", "0", "", "", "",false,true); parameters.push_back(pcutoff);
+ CommandParameter pgroups("groups", "String", "", "", "", "", "",false,false); parameters.push_back(pgroups);
+ CommandParameter paccnos("accnos", "Boolean", "", "F", "", "", "",false,false); parameters.push_back(paccnos);
+ CommandParameter pinputdir("inputdir", "String", "", "", "", "", "",false,false); parameters.push_back(pinputdir);
+ CommandParameter poutputdir("outputdir", "String", "", "", "", "", "",false,false); parameters.push_back(poutputdir);
+
+ vector<string> myArray;
+ for (int i = 0; i < parameters.size(); i++) { myArray.push_back(parameters[i].name); }
return myArray;
}
catch(exception& e) {
- m->errorOut(e, "SplitAbundCommand", "getValidParameters");
+ m->errorOut(e, "SplitAbundCommand", "setParameters");
exit(1);
}
}
//**********************************************************************************************************************
-SplitAbundCommand::SplitAbundCommand(){
+string SplitAbundCommand::getHelpString(){
try {
- abort = true; calledHelp = true;
- vector<string> tempOutNames;
- outputTypes["list"] = tempOutNames;
- outputTypes["name"] = tempOutNames;
- outputTypes["accnos"] = tempOutNames;
- outputTypes["group"] = tempOutNames;
- outputTypes["fasta"] = tempOutNames;
+ string helpString = "";
+ helpString += "The split.abund command reads a fasta file and a list or a names file splits the sequences into rare and abundant groups. \n";
+ helpString += "The split.abund command parameters are fasta, list, name, cutoff, group, label, groups, cutoff and accnos.\n";
+ helpString += "The fasta and a list or name parameter are required, and you must provide a cutoff value.\n";
+ helpString += "The cutoff parameter is used to qualify what is abundant and rare.\n";
+ helpString += "The group parameter allows you to parse a group file into rare and abundant groups.\n";
+ helpString += "The label parameter is used to read specific labels in your listfile you want to use.\n";
+ helpString += "The accnos parameter allows you to output a .rare.accnos and .abund.accnos files to use with the get.seqs and remove.seqs commands.\n";
+ helpString += "The groups parameter allows you to parse the files into rare and abundant files by group. \n";
+ helpString += "For example if you set groups=A-B-C, you will get a .A.abund, .A.rare, .B.abund, .B.rare, .C.abund, .C.rare files. \n";
+ helpString += "If you want .abund and .rare files for all groups, set groups=all. \n";
+ helpString += "The split.abund command should be used in the following format: split.abund(fasta=yourFasta, list=yourListFile, group=yourGroupFile, label=yourLabels, cutoff=yourCutoff).\n";
+ helpString += "Example: split.abund(fasta=abrecovery.fasta, list=abrecovery.fn.list, group=abrecovery.groups, label=0.03, cutoff=2).\n";
+ helpString += "Note: No spaces between parameter labels (i.e. list), '=' and parameters (i.e.yourListfile).\n";
+ return helpString;
}
catch(exception& e) {
- m->errorOut(e, "SplitAbundCommand", "SplitAbundCommand");
+ m->errorOut(e, "SplitAbundCommand", "getHelpString");
exit(1);
}
}
//**********************************************************************************************************************
-vector<string> SplitAbundCommand::getRequiredParameters(){
+string SplitAbundCommand::getOutputFileNameTag(string type, string inputName=""){
try {
- string Array[] = {"fasta","list","name","or"};
- vector<string> myArray (Array, Array+(sizeof(Array)/sizeof(string)));
- return myArray;
+ string outputFileName = "";
+ map<string, vector<string> >::iterator it;
+
+ //is this a type this command creates
+ it = outputTypes.find(type);
+ if (it == outputTypes.end()) { m->mothurOut("[ERROR]: this command doesn't create a " + type + " output file.\n"); }
+ else {
+ if (type == "fasta") { outputFileName = "fasta"; }
+ else if (type == "list") { outputFileName = "list"; }
+ else if (type == "name") { outputFileName = "names"; }
+ else if (type == "group") { outputFileName = "groups"; }
+ else if (type == "accnos") { outputFileName = "accnos"; }
+ else { m->mothurOut("[ERROR]: No definition for type " + type + " output file tag.\n"); m->control_pressed = true; }
+ }
+ return outputFileName;
}
catch(exception& e) {
- m->errorOut(e, "SplitAbundCommand", "getRequiredParameters");
+ m->errorOut(e, "SplitAbundCommand", "getOutputFileNameTag");
exit(1);
}
}
//**********************************************************************************************************************
-vector<string> SplitAbundCommand::getRequiredFiles(){
+SplitAbundCommand::SplitAbundCommand(){
try {
- vector<string> myArray;
- return myArray;
+ abort = true; calledHelp = true;
+ setParameters();
+ vector<string> tempOutNames;
+ outputTypes["list"] = tempOutNames;
+ outputTypes["name"] = tempOutNames;
+ outputTypes["accnos"] = tempOutNames;
+ outputTypes["group"] = tempOutNames;
+ outputTypes["fasta"] = tempOutNames;
}
catch(exception& e) {
- m->errorOut(e, "SplitAbundCommand", "getRequiredFiles");
+ m->errorOut(e, "SplitAbundCommand", "SplitAbundCommand");
exit(1);
}
}
//allow user to run help
if(option == "help") { help(); abort = true; calledHelp = true; }
-
+ else if(option == "citation") { citation(); abort = true; calledHelp = true;}
else {
- //valid paramters for this command
- string Array[] = {"name","group","list","label","accnos","groups","fasta","cutoff","outputdir","inputdir"}; //
- vector<string> myArray (Array, Array+(sizeof(Array)/sizeof(string)));
+ vector<string> myArray = setParameters();
OptionParser parser(option);
map<string, string> parameters = parser.getParameters();
listfile = validParameter.validFile(parameters, "list", true);
if (listfile == "not open") { abort = true; }
else if (listfile == "not found") { listfile = ""; }
- else{ inputFile = listfile; }
+ else{ inputFile = listfile; m->setListFile(listfile); }
namefile = validParameter.validFile(parameters, "name", true);
if (namefile == "not open") { abort = true; }
else if (namefile == "not found") { namefile = ""; }
- else{ inputFile = namefile; }
+ else{ inputFile = namefile; m->setNameFile(namefile); }
fastafile = validParameter.validFile(parameters, "fasta", true);
if (fastafile == "not open") { abort = true; }
- else if (fastafile == "not found") { fastafile = ""; m->mothurOut("fasta is a required parameter for the split.abund command. "); m->mothurOutEndLine(); abort = true; }
+ else if (fastafile == "not found") {
+ fastafile = m->getFastaFile();
+ if (fastafile != "") { m->mothurOut("Using " + fastafile + " as input file for the fasta parameter."); m->mothurOutEndLine(); }
+ else { m->mothurOut("You have no current fastafile and the fasta parameter is required."); m->mothurOutEndLine(); abort = true; }
+ }else { m->setFastaFile(fastafile); }
groupfile = validParameter.validFile(parameters, "group", true);
if (groupfile == "not open") { groupfile = ""; abort = true; }
int error = groupMap->readMap();
if (error == 1) { abort = true; }
-
+ m->setGroupFile(groupfile);
}
groups = validParameter.validFile(parameters, "groups", false);
if (groups == "not found") { groups = ""; }
else if (groups == "all") {
- if (groupfile != "") { Groups = groupMap->namesOfGroups; }
+ if (groupfile != "") { Groups = groupMap->getNamesOfGroups(); }
else { m->mothurOut("You cannot select groups without a valid groupfile, I will disregard your groups selection. "); m->mothurOutEndLine(); groups = ""; }
}else {
m->splitAtDash(groups, Groups);
if ((groupfile == "") && (groups != "")) { m->mothurOut("You cannot select groups without a valid groupfile, I will disregard your groups selection. "); m->mothurOutEndLine(); groups = ""; Groups.clear(); }
//do you have all files needed
- if ((listfile == "") && (namefile == "")) { m->mothurOut("You must either a listfile or a namefile for the split.abund command. "); m->mothurOutEndLine(); abort = true; }
+ if ((listfile == "") && (namefile == "")) {
+ namefile = m->getNameFile();
+ if (namefile != "") { m->mothurOut("Using " + namefile + " as input file for the name parameter."); m->mothurOutEndLine(); }
+ else {
+ listfile = m->getListFile();
+ if (listfile != "") { m->mothurOut("Using " + listfile + " as input file for the list parameter."); m->mothurOutEndLine(); }
+ else { m->mothurOut("You have no current list or namefile and the list or name parameter is required."); m->mothurOutEndLine(); abort = true; }
+ }
+ }
//check for optional parameter and set defaults
// ...at some point should added some additional type checking...
accnos = m->isTrue(temp);
temp = validParameter.validFile(parameters, "cutoff", false); if (temp == "not found") { temp = "0"; }
- convert(temp, cutoff);
+ m->mothurConvert(temp, cutoff);
if (cutoff == 0) { m->mothurOut("You must provide a cutoff to qualify what is abundant for the split.abund command. "); m->mothurOutEndLine(); abort = true; }
-
}
}
}
}
//**********************************************************************************************************************
-void SplitAbundCommand::help(){
- try {
- m->mothurOut("The split.abund command reads a fasta file and a list or a names file splits the sequences into rare and abundant groups. \n");
- m->mothurOut("The split.abund command parameters are fasta, list, name, cutoff, group, label, groups, cutoff and accnos.\n");
- m->mothurOut("The fasta and a list or name parameter are required, and you must provide a cutoff value.\n");
- m->mothurOut("The cutoff parameter is used to qualify what is abundant and rare.\n");
- m->mothurOut("The group parameter allows you to parse a group file into rare and abundant groups.\n");
- m->mothurOut("The label parameter is used to read specific labels in your listfile you want to use.\n");
- m->mothurOut("The accnos parameter allows you to output a .rare.accnos and .abund.accnos files to use with the get.seqs and remove.seqs commands.\n");
- m->mothurOut("The groups parameter allows you to parse the files into rare and abundant files by group. \n");
- m->mothurOut("For example if you set groups=A-B-C, you will get a .A.abund, .A.rare, .B.abund, .B.rare, .C.abund, .C.rare files. \n");
- m->mothurOut("If you want .abund and .rare files for all groups, set groups=all. \n");
- m->mothurOut("The split.abund command should be used in the following format: split.abund(fasta=yourFasta, list=yourListFile, group=yourGroupFile, label=yourLabels, cutoff=yourCutoff).\n");
- m->mothurOut("Example: split.abund(fasta=abrecovery.fasta, list=abrecovery.fn.list, group=abrecovery.groups, label=0.03, cutoff=2).\n");
- m->mothurOut("Note: No spaces between parameter labels (i.e. list), '=' and parameters (i.e.yourListfile).\n\n");
-
- }
- catch(exception& e) {
- m->errorOut(e, "SplitAbundCommand", "help");
- exit(1);
- }
-}
-//**********************************************************************************************************************
SplitAbundCommand::~SplitAbundCommand(){
if (groupfile != "") { delete groupMap; }
}
if (namefile != "") { readNamesFile(); }
else { createNameMap(list); }
- if (m->control_pressed) { delete input; delete list; for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; }
+ if (m->control_pressed) { delete input; delete list; for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; }
while((list != NULL) && ((allLines == 1) || (userLabels.size() != 0))) {
- if (m->control_pressed) { delete input; delete list; for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; }
+ if (m->control_pressed) { delete input; delete list; for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; }
if(allLines == 1 || labels.count(list->getLabel()) == 1){
list = input->getListVector(); //get new list vector to process
}
- if (m->control_pressed) { delete input; for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; }
+ if (m->control_pressed) { delete input; for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; }
//output error messages about any remaining user labels
set<string>::iterator it;
}
- if (m->control_pressed) { delete input; for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; }
+ if (m->control_pressed) { delete input; for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; }
//run last label if you need to
if (needToRun == true) {
delete input;
- if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; }
+ if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; }
}else { //you are using the namefile to determine abundance
if (outputDir == "") { outputDir = m->hasPath(namefile); }
ofstream aout;
ofstream rout;
- string rare = outputDir + m->getRootName(m->getSimpleName(listfile)) + tag + "rare.list";
+ string rare = outputDir + m->getRootName(m->getSimpleName(listfile)) + tag + "rare." + getOutputFileNameTag("list");
m->openOutputFile(rare, rout);
outputNames.push_back(rare); outputTypes["list"].push_back(rare);
- string abund = outputDir + m->getRootName(m->getSimpleName(listfile)) + tag + "abund.list";
+ string abund = outputDir + m->getRootName(m->getSimpleName(listfile)) + tag + "abund." + getOutputFileNameTag("list");
m->openOutputFile(abund, aout);
outputNames.push_back(abund); outputTypes["list"].push_back(abund);
temp2 = new ofstream;
filehandles[Groups[i]+".abund"] = temp2;
- m->openOutputFile(fileroot + Groups[i] + tag + ".rare.list", *(filehandles[Groups[i]+".rare"]));
- m->openOutputFile(fileroot + Groups[i] + tag + ".abund.list", *(filehandles[Groups[i]+".abund"]));
- outputNames.push_back(fileroot + Groups[i] + tag + ".rare.list"); outputTypes["list"].push_back(fileroot + Groups[i] + tag + ".rare.list");
- outputNames.push_back(fileroot + Groups[i] + tag + ".abund.list"); outputTypes["list"].push_back(fileroot + Groups[i] + tag + ".abund.list");
+ string rareGroupFileName = fileroot + Groups[i] + tag + ".rare." + getOutputFileNameTag("list");
+ string abundGroupFileName = fileroot + Groups[i] + tag + ".abund." + getOutputFileNameTag("list");
+ m->openOutputFile(rareGroupFileName, *(filehandles[Groups[i]+".rare"]));
+ m->openOutputFile(abundGroupFileName, *(filehandles[Groups[i]+".abund"]));
+ outputNames.push_back(rareGroupFileName); outputTypes["list"].push_back(rareGroupFileName);
+ outputNames.push_back(abundGroupFileName); outputTypes["list"].push_back(abundGroupFileName);
}
map<string, string> groupVector;
ofstream aout;
ofstream rout;
- string rare = outputDir + m->getRootName(m->getSimpleName(namefile)) + "rare.names";
+ string rare = outputDir + m->getRootName(m->getSimpleName(namefile)) + "rare." + getOutputFileNameTag("name");
m->openOutputFile(rare, rout);
outputNames.push_back(rare); outputTypes["name"].push_back(rare);
- string abund = outputDir + m->getRootName(m->getSimpleName(namefile)) + "abund.names";
+ string abund = outputDir + m->getRootName(m->getSimpleName(namefile)) + "abund." + getOutputFileNameTag("name");
m->openOutputFile(abund, aout);
outputNames.push_back(abund); outputTypes["name"].push_back(abund);
temp2 = new ofstream;
filehandles[Groups[i]+".abund"] = temp2;
- m->openOutputFile(fileroot + Groups[i] + ".rare.names", *(filehandles[Groups[i]+".rare"]));
- m->openOutputFile(fileroot + Groups[i] + ".abund.names", *(filehandles[Groups[i]+".abund"]));
+ string rareGroupFileName = fileroot + Groups[i] + ".rare." + getOutputFileNameTag("name");
+ string abundGroupFileName = fileroot + Groups[i] + ".abund." + getOutputFileNameTag("name");
+ m->openOutputFile(rareGroupFileName, *(filehandles[Groups[i]+".rare"]));
+ m->openOutputFile(abundGroupFileName, *(filehandles[Groups[i]+".abund"]));
}
for (map<string, string>::iterator itName = nameMap.begin(); itName != nameMap.end(); itName++) {
for (it3 = filehandles.begin(); it3 != filehandles.end(); it3++) {
(*(filehandles[it3->first])).close();
- outputNames.push_back(fileroot + it3->first + ".names"); outputTypes["name"].push_back(fileroot + it3->first + ".names");
+ outputNames.push_back(fileroot + it3->first + "." + getOutputFileNameTag("name")); outputTypes["name"].push_back(fileroot + it3->first + "." + getOutputFileNameTag("name"));
delete it3->second;
}
}
ofstream rout;
- string rare = outputDir + m->getRootName(m->getSimpleName(inputFile)) + tag + "rare.accnos";
+ string rare = outputDir + m->getRootName(m->getSimpleName(inputFile)) + tag + "rare." + getOutputFileNameTag("accnos");
m->openOutputFile(rare, rout);
outputNames.push_back(rare); outputTypes["accnos"].push_back(rare);
}
rout.close();
- string abund = outputDir + m->getRootName(m->getSimpleName(inputFile)) + tag + "abund.accnos";
+ string abund = outputDir + m->getRootName(m->getSimpleName(inputFile)) + tag + "abund." + getOutputFileNameTag("accnos");
m->openOutputFile(abund, aout);
outputNames.push_back(abund); outputTypes["accnos"].push_back(abund);
temp2 = new ofstream;
filehandles[Groups[i]+".abund"] = temp2;
- m->openOutputFile(fileroot + tag + Groups[i] + ".rare.accnos", *(filehandles[Groups[i]+".rare"]));
- m->openOutputFile(fileroot + tag + Groups[i] + ".abund.accnos", *(filehandles[Groups[i]+".abund"]));
+ m->openOutputFile(fileroot + tag + Groups[i] + ".rare." + getOutputFileNameTag("accnos"), *(filehandles[Groups[i]+".rare"]));
+ m->openOutputFile(fileroot + tag + Groups[i] + ".abund." + getOutputFileNameTag("accnos"), *(filehandles[Groups[i]+".abund"]));
}
//write rare
//close files
for (it3 = filehandles.begin(); it3 != filehandles.end(); it3++) {
(*(filehandles[it3->first])).close();
- outputNames.push_back(fileroot + tag + it3->first + ".accnos"); outputTypes["accnos"].push_back(fileroot + tag + it3->first + ".accnos");
+ outputNames.push_back(fileroot + tag + it3->first + "." + getOutputFileNameTag("accnos")); outputTypes["accnos"].push_back(fileroot + tag + it3->first + "." + getOutputFileNameTag("accnos"));
delete it3->second;
}
}
ofstream aout;
ofstream rout;
- string rare = outputDir + m->getRootName(m->getSimpleName(groupfile)) + tag + "rare.groups";
+ string rare = outputDir + m->getRootName(m->getSimpleName(groupfile)) + tag + "rare." + getOutputFileNameTag("group");
m->openOutputFile(rare, rout);
outputNames.push_back(rare); outputTypes["group"].push_back(rare);
- string abund = outputDir + m->getRootName(m->getSimpleName(groupfile)) + tag + "abund.groups";
+ string abund = outputDir + m->getRootName(m->getSimpleName(groupfile)) + tag + "abund." + getOutputFileNameTag("group");
+;
m->openOutputFile(abund, aout);
outputNames.push_back(abund); outputTypes["group"].push_back(abund);
temp2 = new ofstream;
filehandles[Groups[i]+".abund"] = temp2;
- m->openOutputFile(fileroot + tag + Groups[i] + ".rare.groups", *(filehandles[Groups[i]+".rare"]));
- m->openOutputFile(fileroot + tag + Groups[i] + ".abund.groups", *(filehandles[Groups[i]+".abund"]));
+ m->openOutputFile(fileroot + tag + Groups[i] + ".rare." + getOutputFileNameTag("group"), *(filehandles[Groups[i]+".rare"]));
+ m->openOutputFile(fileroot + tag + Groups[i] + ".abund." + getOutputFileNameTag("group"), *(filehandles[Groups[i]+".abund"]));
}
for (map<string, string>::iterator itName = nameMap.begin(); itName != nameMap.end(); itName++) {
for (it3 = filehandles.begin(); it3 != filehandles.end(); it3++) {
(*(filehandles[it3->first])).close();
- outputNames.push_back(fileroot + tag + it3->first + ".groups"); outputTypes["group"].push_back(fileroot + tag + it3->first + ".groups");
+ outputNames.push_back(fileroot + tag + it3->first + "." + getOutputFileNameTag("group")); outputTypes["group"].push_back(fileroot + tag + it3->first + "." + getOutputFileNameTag("group"));
delete it3->second;
}
}
ofstream aout;
ofstream rout;
- string rare = outputDir + m->getRootName(m->getSimpleName(fastafile)) + tag + "rare.fasta";
+ string rare = outputDir + m->getRootName(m->getSimpleName(fastafile)) + tag + "rare." + getOutputFileNameTag("fasta");
m->openOutputFile(rare, rout);
outputNames.push_back(rare); outputTypes["fasta"].push_back(rare);
- string abund = outputDir + m->getRootName(m->getSimpleName(fastafile)) + tag + "abund.fasta";
+ string abund = outputDir + m->getRootName(m->getSimpleName(fastafile)) + tag + "abund." + getOutputFileNameTag("fasta");
m->openOutputFile(abund, aout);
outputNames.push_back(abund); outputTypes["fasta"].push_back(abund);
temp2 = new ofstream;
filehandles[Groups[i]+".abund"] = temp2;
- m->openOutputFile(fileroot + tag + Groups[i] + ".rare.fasta", *(filehandles[Groups[i]+".rare"]));
- m->openOutputFile(fileroot + tag + Groups[i] + ".abund.fasta", *(filehandles[Groups[i]+".abund"]));
+ m->openOutputFile(fileroot + tag + Groups[i] + ".rare." + getOutputFileNameTag("fasta"), *(filehandles[Groups[i]+".rare"]));
+ m->openOutputFile(fileroot + tag + Groups[i] + ".abund." + getOutputFileNameTag("fasta"), *(filehandles[Groups[i]+".abund"]));
}
//open input file
for (it3 = filehandles.begin(); it3 != filehandles.end(); it3++) {
(*(filehandles[it3->first])).close();
- outputNames.push_back(fileroot + tag + it3->first + ".fasta"); outputTypes["fasta"].push_back(fileroot + tag + it3->first + ".fasta");
+ outputNames.push_back(fileroot + tag + it3->first + "." + getOutputFileNameTag("fasta")); outputTypes["fasta"].push_back(fileroot + tag + it3->first + "." + getOutputFileNameTag("fasta"));
delete it3->second;
}
}