#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)));
+ return myArray;
+ }
+ catch(exception& e) {
+ m->errorOut(e, "SplitAbundCommand", "getValidParameters");
+ exit(1);
+ }
+}
+//**********************************************************************************************************************
+SplitAbundCommand::SplitAbundCommand(){
+ try {
+ abort = true;
+ //initialize outputTypes
+ 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);
+ }
+}
+//**********************************************************************************************************************
+vector<string> SplitAbundCommand::getRequiredParameters(){
+ try {
+ string Array[] = {"fasta","list","name","or"};
+ vector<string> myArray (Array, Array+(sizeof(Array)/sizeof(string)));
+ return myArray;
+ }
+ catch(exception& e) {
+ m->errorOut(e, "SplitAbundCommand", "getRequiredParameters");
+ exit(1);
+ }
+}
+//**********************************************************************************************************************
+vector<string> SplitAbundCommand::getRequiredFiles(){
+ try {
+ vector<string> myArray;
+ return myArray;
+ }
+ catch(exception& e) {
+ m->errorOut(e, "SplitAbundCommand", "getRequiredFiles");
+ exit(1);
+ }
+}
//**********************************************************************************************************************
SplitAbundCommand::SplitAbundCommand(string option) {
try {
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 = ""; }
it = parameters.find("list");
//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["list"] = inputDir + it->second; }
}
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; }
}
it = parameters.find("fasta");
//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["fasta"] = inputDir + it->second; }
}
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; }
}
if (groupfile != "") { Groups = groupMap->namesOfGroups; }
else { m->mothurOut("You cannot select groups without a valid groupfile, I will disregard your groups selection. "); m->mothurOutEndLine(); groups = ""; }
}else {
- splitAtDash(groups, Groups);
+ 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(); }
label = validParameter.validFile(parameters, "label", false);
if (label == "not found") { label = ""; allLines = 1; }
else {
- if(label != "all") { splitAtDash(label, labels); allLines = 0; }
+ if(label != "all") { m->splitAtDash(label, labels); allLines = 0; }
else { allLines = 1; }
}
string temp = validParameter.validFile(parameters, "accnos", false); if (temp == "not found") { temp = "F"; }
- accnos = isTrue(temp);
+ accnos = m->isTrue(temp);
temp = validParameter.validFile(parameters, "cutoff", false); if (temp == "not found") { temp = "0"; }
convert(temp, cutoff);
if (abort == true) { return 0; }
if (listfile != "") { //you are using a listfile to determine abundance
- if (outputDir == "") { outputDir = hasPath(listfile); }
-
- //remove old files so you can append later....
- string fileroot = outputDir + getRootName(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 (outputDir == "") { outputDir = m->hasPath(listfile); }
//if the users enters label "0.06" and there is no "0.06" in their file use the next lowest label.
set<string> processedLabels;
userLabels.erase(list->getLabel());
}
- if ((anyLabelsToProcess(list->getLabel(), userLabels, "") == true) && (processedLabels.count(lastLabel) != 1)) {
+ if ((m->anyLabelsToProcess(list->getLabel(), userLabels, "") == true) && (processedLabels.count(lastLabel) != 1)) {
string saveLabel = list->getLabel();
delete list;
if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; }
}else { //you are using the namefile to determine abundance
- if (outputDir == "") { outputDir = hasPath(namefile); }
+ if (outputDir == "") { outputDir = m->hasPath(namefile); }
splitNames();
writeNames();
string bin = thisList->get(i);
vector<string> names;
- splitAtComma(bin, names); //parses bin into individual sequence names
+ m->splitAtComma(bin, names); //parses bin into individual sequence names
int size = names.size();
if (size <= cutoff) {
}
}//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 + getRootName(getSimpleName(listfile)) + "rare.list";
- 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 + getRootName(getSimpleName(listfile)) + "abund.list";
- 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'; }
string bin = list->get(i);
- int size = getNumNames(bin);
+ int size = m->getNumNames(bin);
if (size <= cutoff) { rout << bin << '\t'; }
else { aout << bin << '\t'; }
aout.close();
}else{ //parse names by abundance and group
- string fileroot = outputDir + getRootName(getSimpleName(listfile));
+ string fileroot = outputDir + m->getRootName(m->getSimpleName(listfile));
ofstream* temp;
ofstream* temp2;
//map<string, bool> wroteFile;
temp2 = new ofstream;
filehandles[Groups[i]+".abund"] = temp2;
- openOutputFileAppend(fileroot + Groups[i] + ".rare.list", *(filehandles[Groups[i]+".rare"]));
- 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 bin = list->get(i);
vector<string> names;
- splitAtComma(bin, names); //parses bin into individual sequence names
+ m->splitAtComma(bin, names); //parses bin into individual sequence names
//parse bin into list of sequences in each group
for (int j = 0; j < names.size(); j++) {
string group = groupMap->getGroup(names[j]);
- if (inUsersGroups(group, Groups)) { //only add if this is in a group we want
+ if (m->inUsersGroups(group, Groups)) { //only add if this is in a group we want
itGroup = groupBins.find(group+rareAbund);
if(itGroup == groupBins.end()) {
groupBins[group+rareAbund] = names[j]; //add first name
//open input file
ifstream in;
- openInputFile(namefile, in);
+ m->openInputFile(namefile, in);
while (!in.eof()) {
if (m->control_pressed) { break; }
string firstCol, secondCol;
- in >> firstCol >> secondCol; gobble(in);
+ in >> firstCol >> secondCol; m->gobble(in);
nameMap[firstCol] = secondCol;
- int size = getNumNames(secondCol);
+ int size = m->getNumNames(secondCol);
if (size <= cutoff) {
rareNames.insert(firstCol);
try {
//open input file
ifstream in;
- openInputFile(namefile, in);
+ m->openInputFile(namefile, in);
while (!in.eof()) {
if (m->control_pressed) { break; }
string firstCol, secondCol;
- in >> firstCol >> secondCol; gobble(in);
+ in >> firstCol >> secondCol; m->gobble(in);
nameMap[firstCol] = secondCol;
}
string bin = thisList->get(i);
vector<string> names;
- splitAtComma(bin, names); //parses bin into individual sequence names
+ m->splitAtComma(bin, names); //parses bin into individual sequence names
for (int j = 0; j < names.size(); j++) { nameMap[names[j]] = names[j]; }
}//end for
ofstream aout;
ofstream rout;
- string rare = outputDir + getRootName(getSimpleName(namefile)) + "rare.names";
- openOutputFile(rare, rout);
- outputNames.push_back(rare);
+ string rare = outputDir + m->getRootName(m->getSimpleName(namefile)) + "rare.names";
+ m->openOutputFile(rare, rout);
+ outputNames.push_back(rare); outputTypes["name"].push_back(rare);
- string abund = outputDir + getRootName(getSimpleName(namefile)) + "abund.names";
- openOutputFile(abund, aout);
- outputNames.push_back(abund);
+ string abund = outputDir + m->getRootName(m->getSimpleName(namefile)) + "abund.names";
+ m->openOutputFile(abund, aout);
+ outputNames.push_back(abund); outputTypes["name"].push_back(abund);
if (rareNames.size() != 0) {
for (set<string>::iterator itRare = rareNames.begin(); itRare != rareNames.end(); itRare++) {
aout.close();
}else{ //parse names by abundance and group
- string fileroot = outputDir + getRootName(getSimpleName(namefile));
+ string fileroot = outputDir + m->getRootName(m->getSimpleName(namefile));
ofstream* temp;
ofstream* temp2;
map<string, ofstream*> filehandles;
temp2 = new ofstream;
filehandles[Groups[i]+".abund"] = temp2;
- openOutputFile(fileroot + Groups[i] + ".rare.names", *(filehandles[Groups[i]+".rare"]));
- openOutputFile(fileroot + Groups[i] + ".abund.names", *(filehandles[Groups[i]+".abund"]));
+ m->openOutputFile(fileroot + Groups[i] + ".rare.names", *(filehandles[Groups[i]+".rare"]));
+ m->openOutputFile(fileroot + Groups[i] + ".abund.names", *(filehandles[Groups[i]+".abund"]));
}
for (map<string, string>::iterator itName = nameMap.begin(); itName != nameMap.end(); itName++) {
vector<string> names;
- splitAtComma(itName->second, names); //parses bin into individual sequence names
+ m->splitAtComma(itName->second, names); //parses bin into individual sequence names
string rareAbund;
if (rareNames.count(itName->first) != 0) { //you are a rare name
string group = groupMap->getGroup(names[i]);
- if (inUsersGroups(group, Groups)) { //only add if this is in a group we want
+ if (m->inUsersGroups(group, Groups)) { //only add if this is in a group we want
itout = outputStrings.find(group+rareAbund);
if (itout == outputStrings.end()) {
outputStrings[group+rareAbund] = names[i] + '\t' + names[i];
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;
}
}
ofstream rout;
- string rare = outputDir + getRootName(getSimpleName(inputFile)) + tag + "rare.accnos";
- openOutputFile(rare, rout);
- outputNames.push_back(rare);
+ string rare = outputDir + m->getRootName(m->getSimpleName(inputFile)) + tag + "rare.accnos";
+ m->openOutputFile(rare, rout);
+ outputNames.push_back(rare); outputTypes["accnos"].push_back(rare);
for (set<string>::iterator itRare = rareNames.begin(); itRare != rareNames.end(); itRare++) {
rout << (*itRare) << endl;
}
rout.close();
- string abund = outputDir + getRootName(getSimpleName(inputFile)) + tag + "abund.accnos";
- openOutputFile(abund, aout);
- outputNames.push_back(abund);
+ string abund = outputDir + m->getRootName(m->getSimpleName(inputFile)) + tag + "abund.accnos";
+ m->openOutputFile(abund, aout);
+ outputNames.push_back(abund); outputTypes["accnos"].push_back(abund);
for (set<string>::iterator itAbund = abundNames.begin(); itAbund != abundNames.end(); itAbund++) {
aout << (*itAbund) << endl;
aout.close();
}else{ //parse names by abundance and group
- string fileroot = outputDir + getRootName(getSimpleName(inputFile));
+ string fileroot = outputDir + m->getRootName(m->getSimpleName(inputFile));
ofstream* temp;
ofstream* temp2;
map<string, ofstream*> filehandles;
temp2 = new ofstream;
filehandles[Groups[i]+".abund"] = temp2;
- openOutputFile(fileroot + tag + Groups[i] + ".rare.accnos", *(filehandles[Groups[i]+".rare"]));
- openOutputFile(fileroot + tag + Groups[i] + ".abund.accnos", *(filehandles[Groups[i]+".abund"]));
+ m->openOutputFile(fileroot + tag + Groups[i] + ".rare.accnos", *(filehandles[Groups[i]+".rare"]));
+ m->openOutputFile(fileroot + tag + Groups[i] + ".abund.accnos", *(filehandles[Groups[i]+".abund"]));
}
//write rare
for (set<string>::iterator itRare = rareNames.begin(); itRare != rareNames.end(); itRare++) {
string group = groupMap->getGroup(*itRare);
- if (inUsersGroups(group, Groups)) { //only add if this is in a group we want
+ if (m->inUsersGroups(group, Groups)) { //only add if this is in a group we want
*(filehandles[group+".rare"]) << *itRare << endl;
}
}
for (set<string>::iterator itAbund = abundNames.begin(); itAbund != abundNames.end(); itAbund++) {
string group = groupMap->getGroup(*itAbund);
- if (inUsersGroups(group, Groups)) { //only add if this is in a group we want
+ if (m->inUsersGroups(group, Groups)) { //only add if this is in a group we want
*(filehandles[group+".abund"]) << *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;
}
}
ofstream aout;
ofstream rout;
- string rare = outputDir + getRootName(getSimpleName(groupfile)) + tag + "rare.groups";
- openOutputFile(rare, rout);
- outputNames.push_back(rare);
+ string rare = outputDir + m->getRootName(m->getSimpleName(groupfile)) + tag + "rare.groups";
+ m->openOutputFile(rare, rout);
+ outputNames.push_back(rare); outputTypes["group"].push_back(rare);
- string abund = outputDir + getRootName(getSimpleName(groupfile)) + tag + "abund.groups";
- openOutputFile(abund, aout);
- outputNames.push_back(abund);
+ string abund = outputDir + m->getRootName(m->getSimpleName(groupfile)) + tag + "abund.groups";
+ m->openOutputFile(abund, aout);
+ outputNames.push_back(abund); outputTypes["group"].push_back(abund);
for (map<string, string>::iterator itName = nameMap.begin(); itName != nameMap.end(); itName++) {
vector<string> names;
- splitAtComma(itName->second, names); //parses bin into individual sequence names
+ m->splitAtComma(itName->second, names); //parses bin into individual sequence names
for (int i = 0; i < names.size(); i++) {
aout.close();
}else{ //parse names by abundance and group
- string fileroot = outputDir + getRootName(getSimpleName(groupfile));
+ string fileroot = outputDir + m->getRootName(m->getSimpleName(groupfile));
ofstream* temp;
ofstream* temp2;
map<string, ofstream*> filehandles;
temp2 = new ofstream;
filehandles[Groups[i]+".abund"] = temp2;
- openOutputFile(fileroot + tag + Groups[i] + ".rare.groups", *(filehandles[Groups[i]+".rare"]));
- openOutputFile(fileroot + tag + Groups[i] + ".abund.groups", *(filehandles[Groups[i]+".abund"]));
+ m->openOutputFile(fileroot + tag + Groups[i] + ".rare.groups", *(filehandles[Groups[i]+".rare"]));
+ m->openOutputFile(fileroot + tag + Groups[i] + ".abund.groups", *(filehandles[Groups[i]+".abund"]));
}
for (map<string, string>::iterator itName = nameMap.begin(); itName != nameMap.end(); itName++) {
vector<string> names;
- splitAtComma(itName->second, names); //parses bin into individual sequence names
+ m->splitAtComma(itName->second, names); //parses bin into individual sequence names
string rareAbund;
if (rareNames.count(itName->first) != 0) { //you are a rare name
string group = groupMap->getGroup(names[i]);
- if (inUsersGroups(group, Groups)) { //only add if this is in a group we want
+ if (m->inUsersGroups(group, Groups)) { //only add if this is in a group we want
*(filehandles[group+rareAbund]) << names[i] << '\t' << group << endl;
}
}
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;
}
}
ofstream aout;
ofstream rout;
- string rare = outputDir + getRootName(getSimpleName(fastafile)) + tag + "rare.fasta";
- openOutputFile(rare, rout);
- outputNames.push_back(rare);
+ string rare = outputDir + m->getRootName(m->getSimpleName(fastafile)) + tag + "rare.fasta";
+ m->openOutputFile(rare, rout);
+ outputNames.push_back(rare); outputTypes["fasta"].push_back(rare);
- string abund = outputDir + getRootName(getSimpleName(fastafile)) + tag + "abund.fasta";
- openOutputFile(abund, aout);
- outputNames.push_back(abund);
+ string abund = outputDir + m->getRootName(m->getSimpleName(fastafile)) + tag + "abund.fasta";
+ m->openOutputFile(abund, aout);
+ outputNames.push_back(abund); outputTypes["fasta"].push_back(abund);
//open input file
ifstream in;
- openInputFile(fastafile, in);
+ m->openInputFile(fastafile, in);
while (!in.eof()) {
if (m->control_pressed) { break; }
- Sequence seq(in); gobble(in);
+ Sequence seq(in); m->gobble(in);
if (seq.getName() != "") {
aout.close();
}else{ //parse names by abundance and group
- string fileroot = outputDir + getRootName(getSimpleName(fastafile));
+ string fileroot = outputDir + m->getRootName(m->getSimpleName(fastafile));
ofstream* temp;
ofstream* temp2;
map<string, ofstream*> filehandles;
temp2 = new ofstream;
filehandles[Groups[i]+".abund"] = temp2;
- openOutputFile(fileroot + tag + Groups[i] + ".rare.fasta", *(filehandles[Groups[i]+".rare"]));
- openOutputFile(fileroot + tag + Groups[i] + ".abund.fasta", *(filehandles[Groups[i]+".abund"]));
+ m->openOutputFile(fileroot + tag + Groups[i] + ".rare.fasta", *(filehandles[Groups[i]+".rare"]));
+ m->openOutputFile(fileroot + tag + Groups[i] + ".abund.fasta", *(filehandles[Groups[i]+".abund"]));
}
//open input file
ifstream in;
- openInputFile(fastafile, in);
+ m->openInputFile(fastafile, in);
while (!in.eof()) {
if (m->control_pressed) { break; }
- Sequence seq(in); gobble(in);
+ Sequence seq(in); m->gobble(in);
if (seq.getName() != "") {
map<string, string>::iterator itNames = nameMap.find(seq.getName());
m->mothurOut(seq.getName() + " is not in your namesfile, ignoring."); m->mothurOutEndLine();
}else{
vector<string> names;
- splitAtComma(itNames->second, names); //parses bin into individual sequence names
+ m->splitAtComma(itNames->second, names); //parses bin into individual sequence names
string rareAbund;
if (rareNames.count(itNames->first) != 0) { //you are a rare name
string group = groupMap->getGroup(seq.getName());
- if (inUsersGroups(group, Groups)) { //only add if this is in a group we want
+ if (m->inUsersGroups(group, Groups)) { //only add if this is in a group we want
seq.printSequence(*(filehandles[group+rareAbund]));
}else if(group == "not found") {
m->mothurOut(seq.getName() + " is not in your groupfile. Ignoring."); m->mothurOutEndLine();
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