#include "splitabundcommand.h"
+//**********************************************************************************************************************
+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", "setParameters");
+ exit(1);
+ }
+}
+//**********************************************************************************************************************
+string SplitAbundCommand::getHelpString(){
+ try {
+ 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", "getHelpString");
+ exit(1);
+ }
+}
+
+//**********************************************************************************************************************
+SplitAbundCommand::SplitAbundCommand(){
+ try {
+ 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", "SplitAbundCommand");
+ exit(1);
+ }
+}
//**********************************************************************************************************************
SplitAbundCommand::SplitAbundCommand(string option) {
try {
- abort = false;
+ abort = false; calledHelp = false;
allLines = 1;
//allow user to run help
- if(option == "help") { help(); abort = true; }
+ if(option == "help") { help(); 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();
for (it = parameters.begin(); it != parameters.end(); it++) {
if (validParameter.isValidParameter(it->first, myArray, it->second) != true) { abort = true; }
}
-
+
+ //initialize outputTypes
+ vector<string> tempOutNames;
+ outputTypes["list"] = tempOutNames;
+ outputTypes["name"] = tempOutNames;
+ outputTypes["accnos"] = tempOutNames;
+ outputTypes["group"] = tempOutNames;
+ outputTypes["fasta"] = tempOutNames;
+
//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 = ""; }
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; }
+ }
groupfile = validParameter.validFile(parameters, "group", true);
if (groupfile == "not open") { groupfile = ""; abort = true; }
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...
}
}
//**********************************************************************************************************************
-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; }
}
int SplitAbundCommand::execute(){
try {
- if (abort == true) { return 0; }
+ if (abort == true) { if (calledHelp) { return 0; } return 2; }
if (listfile != "") { //you are using a listfile to determine abundance
if (outputDir == "") { outputDir = m->hasPath(listfile); }
-
- //remove old files so you can append later....
- string fileroot = outputDir + m->getRootName(m->getSimpleName(listfile));
- if (Groups.size() == 0) {
- remove((fileroot + "rare.list").c_str());
- remove((fileroot + "abund.list").c_str());
-
- outputNames.push_back((fileroot + "rare.list"));
- outputNames.push_back((fileroot + "abund.list"));
- }else{
- for (int i=0; i<Groups.size(); i++) {
- remove((fileroot + Groups[i] + ".rare.list").c_str());
- remove((fileroot + Groups[i] + ".abund.list").c_str());
-
- outputNames.push_back((fileroot + Groups[i] + ".rare.list"));
- outputNames.push_back((fileroot + Groups[i] + ".abund.list"));
- }
- }
//if the users enters label "0.06" and there is no "0.06" in their file use the next lowest label.
set<string> processedLabels;
if (accnos) { writeAccnos(tag); }
if (fastafile != "") { parseFasta(tag); }
}
-
+
+ //set fasta file as new current fastafile
+ string current = "";
+ itTypes = outputTypes.find("fasta");
+ if (itTypes != outputTypes.end()) {
+ if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setFastaFile(current); }
+ }
+
+ itTypes = outputTypes.find("name");
+ if (itTypes != outputTypes.end()) {
+ if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setNameFile(current); }
+ }
+
+ itTypes = outputTypes.find("group");
+ if (itTypes != outputTypes.end()) {
+ if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setGroupFile(current); }
+ }
+
+ itTypes = outputTypes.find("list");
+ if (itTypes != outputTypes.end()) {
+ if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setListFile(current); }
+ }
+
+ itTypes = outputTypes.find("accnos");
+ if (itTypes != outputTypes.end()) {
+ if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setAccnosFile(current); }
+ }
+
m->mothurOutEndLine();
m->mothurOut("Output File Names: "); m->mothurOutEndLine();
for (int i = 0; i < outputNames.size(); i++) { m->mothurOut(outputNames[i]); m->mothurOutEndLine(); }
}
}//end for
- writeList(thisList);
string tag = thisList->getLabel() + ".";
+
+ writeList(thisList, tag);
+
if (groupfile != "") { parseGroup(tag); }
if (accnos) { writeAccnos(tag); }
if (fastafile != "") { parseFasta(tag); }
}
}
/**********************************************************************************************************************/
-int SplitAbundCommand::writeList(ListVector* thisList) {
+int SplitAbundCommand::writeList(ListVector* thisList, string tag) {
try {
map<string, ofstream*> filehandles;
ofstream aout;
ofstream rout;
- string rare = outputDir + m->getRootName(m->getSimpleName(listfile)) + "rare.list";
- m->openOutputFileAppend(rare, rout);
- //outputNames.push_back(rare);
+ string rare = outputDir + m->getRootName(m->getSimpleName(listfile)) + tag + "rare.list";
+ m->openOutputFile(rare, rout);
+ outputNames.push_back(rare); outputTypes["list"].push_back(rare);
- string abund = outputDir + m->getRootName(m->getSimpleName(listfile)) + "abund.list";
- m->openOutputFileAppend(abund, aout);
- //outputNames.push_back(abund);
+ string abund = outputDir + m->getRootName(m->getSimpleName(listfile)) + tag + "abund.list";
+ m->openOutputFile(abund, aout);
+ outputNames.push_back(abund); outputTypes["list"].push_back(abund);
if (rareNames.size() != 0) { rout << thisList->getLabel() << '\t' << numRareBins << '\t'; }
if (abundNames.size() != 0) { aout << thisList->getLabel() << '\t' << numAbundBins << '\t'; }
temp2 = new ofstream;
filehandles[Groups[i]+".abund"] = temp2;
- m->openOutputFileAppend(fileroot + Groups[i] + ".rare.list", *(filehandles[Groups[i]+".rare"]));
- m->openOutputFileAppend(fileroot + Groups[i] + ".abund.list", *(filehandles[Groups[i]+".abund"]));
+ 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");
}
map<string, string> groupVector;
string rare = outputDir + m->getRootName(m->getSimpleName(namefile)) + "rare.names";
m->openOutputFile(rare, rout);
- outputNames.push_back(rare);
+ outputNames.push_back(rare); outputTypes["name"].push_back(rare);
string abund = outputDir + m->getRootName(m->getSimpleName(namefile)) + "abund.names";
m->openOutputFile(abund, aout);
- outputNames.push_back(abund);
+ outputNames.push_back(abund); outputTypes["name"].push_back(abund);
if (rareNames.size() != 0) {
for (set<string>::iterator itRare = rareNames.begin(); itRare != rareNames.end(); itRare++) {
for (it3 = filehandles.begin(); it3 != filehandles.end(); it3++) {
(*(filehandles[it3->first])).close();
- outputNames.push_back(fileroot + it3->first + ".names");
+ outputNames.push_back(fileroot + it3->first + ".names"); outputTypes["name"].push_back(fileroot + it3->first + ".names");
delete it3->second;
}
}
string rare = outputDir + m->getRootName(m->getSimpleName(inputFile)) + tag + "rare.accnos";
m->openOutputFile(rare, rout);
- outputNames.push_back(rare);
+ outputNames.push_back(rare); outputTypes["accnos"].push_back(rare);
for (set<string>::iterator itRare = rareNames.begin(); itRare != rareNames.end(); itRare++) {
rout << (*itRare) << endl;
string abund = outputDir + m->getRootName(m->getSimpleName(inputFile)) + tag + "abund.accnos";
m->openOutputFile(abund, aout);
- outputNames.push_back(abund);
+ outputNames.push_back(abund); outputTypes["accnos"].push_back(abund);
for (set<string>::iterator itAbund = abundNames.begin(); itAbund != abundNames.end(); itAbund++) {
aout << (*itAbund) << endl;
//close files
for (it3 = filehandles.begin(); it3 != filehandles.end(); it3++) {
(*(filehandles[it3->first])).close();
- outputNames.push_back(fileroot + tag + it3->first + ".accnos");
+ outputNames.push_back(fileroot + tag + it3->first + ".accnos"); outputTypes["accnos"].push_back(fileroot + tag + it3->first + ".accnos");
delete it3->second;
}
}
string rare = outputDir + m->getRootName(m->getSimpleName(groupfile)) + tag + "rare.groups";
m->openOutputFile(rare, rout);
- outputNames.push_back(rare);
+ outputNames.push_back(rare); outputTypes["group"].push_back(rare);
string abund = outputDir + m->getRootName(m->getSimpleName(groupfile)) + tag + "abund.groups";
m->openOutputFile(abund, aout);
- outputNames.push_back(abund);
+ outputNames.push_back(abund); outputTypes["group"].push_back(abund);
for (map<string, string>::iterator itName = nameMap.begin(); itName != nameMap.end(); itName++) {
vector<string> names;
for (it3 = filehandles.begin(); it3 != filehandles.end(); it3++) {
(*(filehandles[it3->first])).close();
- outputNames.push_back(fileroot + tag + it3->first + ".groups");
+ outputNames.push_back(fileroot + tag + it3->first + ".groups"); outputTypes["group"].push_back(fileroot + tag + it3->first + ".groups");
delete it3->second;
}
}
string rare = outputDir + m->getRootName(m->getSimpleName(fastafile)) + tag + "rare.fasta";
m->openOutputFile(rare, rout);
- outputNames.push_back(rare);
+ outputNames.push_back(rare); outputTypes["fasta"].push_back(rare);
string abund = outputDir + m->getRootName(m->getSimpleName(fastafile)) + tag + "abund.fasta";
m->openOutputFile(abund, aout);
- outputNames.push_back(abund);
+ outputNames.push_back(abund); outputTypes["fasta"].push_back(abund);
//open input file
ifstream in;
for (it3 = filehandles.begin(); it3 != filehandles.end(); it3++) {
(*(filehandles[it3->first])).close();
- outputNames.push_back(fileroot + tag + it3->first + ".fasta");
+ outputNames.push_back(fileroot + tag + it3->first + ".fasta"); outputTypes["fasta"].push_back(fileroot + tag + it3->first + ".fasta");
delete it3->second;
}
}
projects / mothur.git / blobdiff