#include "binsequencecommand.h"
+
+//**********************************************************************************************************************
+vector<string> BinSeqCommand::setParameters(){
+ try {
+ CommandParameter plist("list", "InputTypes", "", "", "none", "none", "none","",false,true,true); parameters.push_back(plist);
+ CommandParameter pfasta("fasta", "InputTypes", "", "", "none", "none", "none","fasta",false,true,true); parameters.push_back(pfasta);
+ CommandParameter pname("name", "InputTypes", "", "", "NameCount", "none", "none","",false,false,true); parameters.push_back(pname);
+ CommandParameter pcount("count", "InputTypes", "", "", "NameCount-CountGroup", "none", "none","",false,false,true); parameters.push_back(pcount);
+ CommandParameter pgroup("group", "InputTypes", "", "", "CountGroup", "none", "none","",false,false,true); parameters.push_back(pgroup);
+ CommandParameter plabel("label", "String", "", "", "", "", "","",false,false); parameters.push_back(plabel);
+ 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, "BinSeqCommand", "setParameters");
+ exit(1);
+ }
+}
+//**********************************************************************************************************************
+string BinSeqCommand::getHelpString(){
+ try {
+ string helpString = "";
+ helpString += "The bin.seqs command parameters are list, fasta, name, count, label and group. The fasta and list are required, unless you have a valid current list and fasta file.\n";
+ helpString += "The label parameter allows you to select what distance levels you would like a output files created for, and are separated by dashes.\n";
+ helpString += "The bin.seqs command should be in the following format: bin.seqs(fasta=yourFastaFile, name=yourNamesFile, group=yourGroupFile, label=yourLabels).\n";
+ helpString += "Example bin.seqs(fasta=amazon.fasta, group=amazon.groups, name=amazon.names).\n";
+ helpString += "The default value for label is all lines in your inputfile.\n";
+ helpString += "The bin.seqs command outputs a .fasta file for each distance you specify appending the OTU number to each name.\n";
+ helpString += "If you provide a groupfile, then it also appends the sequences group to the name.\n";
+ helpString += "Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFastaFile).\n";
+ return helpString;
+ }
+ catch(exception& e) {
+ m->errorOut(e, "BinSeqCommand", "getHelpString");
+ exit(1);
+ }
+}
+//**********************************************************************************************************************
+string BinSeqCommand::getOutputPattern(string type) {
+ try {
+ string pattern = "";
+
+ if (type == "fasta") { pattern = "[filename],[distance],fasta"; } //makes file like: amazon.0.03.fasta
+ else { m->mothurOut("[ERROR]: No definition for type " + type + " output pattern.\n"); m->control_pressed = true; }
+
+ return pattern;
+ }
+ catch(exception& e) {
+ m->errorOut(e, "BinSeqCommand", "getOutputPattern");
+ exit(1);
+ }
+}
+//**********************************************************************************************************************
+BinSeqCommand::BinSeqCommand(){
+ try {
+ abort = true; calledHelp = true;
+ setParameters();
+ vector<string> tempOutNames;
+ outputTypes["fasta"] = tempOutNames;
+ }
+ catch(exception& e) {
+ m->errorOut(e, "BinSeqCommand", "BinSeqCommand");
+ exit(1);
+ }
+}
//**********************************************************************************************************************
BinSeqCommand::BinSeqCommand(string option) {
try {
- globaldata = GlobalData::getInstance();
- abort = false;
+ abort = false; calledHelp = false;
allLines = 1;
labels.clear();
//allow user to run help
- if(option == "help") { help(); abort = true; }
+ if(option == "help") { help(); abort = true; calledHelp = true; }
+ else if(option == "citation") { citation(); abort = true; calledHelp = true;}
else {
- //valid paramters for this command
- string AlignArray[] = {"fasta","label","name", "group","outputdir","inputdir"};
- vector<string> myArray (AlignArray, AlignArray+(sizeof(AlignArray)/sizeof(string)));
+ vector<string> myArray = setParameters();
OptionParser parser(option);
map<string, string> parameters = parser.getParameters();
if (validParameter.isValidParameter(it->first, myArray, it->second) != true) { abort = true; }
}
- //if the user changes the output directory command factory will send this info to us in the output parameter
- outputDir = validParameter.validFile(parameters, "outputdir", false); if (outputDir == "not found"){
- outputDir = "";
- outputDir += m->hasPath(globaldata->getListFile()); //if user entered a file with a path then preserve it
- }
-
-
- //make sure the user has already run the read.otu command
- if (globaldata->getListFile() == "") {
- m->mothurOut("You must read a listfile before running the bin.seqs command.");
- m->mothurOutEndLine();
- abort = true;
- }
+ //initialize outputTypes
+ vector<string> 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 (path == "") { parameters["fasta"] = inputDir + it->second; }
}
+ it = parameters.find("list");
+ //user has given a template file
+ if(it != parameters.end()){
+ 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("name");
//user has given a template file
if(it != parameters.end()){
//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("count");
+ //user has given a template file
+ if(it != parameters.end()){
+ path = m->hasPath(it->second);
+ //if the user has not given a path then, add inputdir. else leave path alone.
+ if (path == "") { parameters["count"] = inputDir + it->second; }
+ }
}
//check for required parameters
fastafile = validParameter.validFile(parameters, "fasta", true);
- if (fastafile == "not found") { m->mothurOut("fasta is a required parameter for the bin.seqs command."); m->mothurOutEndLine(); abort = true; }
+ if (fastafile == "not found") { //if there is a current phylip file, use it
+ 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 fasta file and the fasta parameter is required."); m->mothurOutEndLine(); abort = true; }
+ }
else if (fastafile == "not open") { abort = true; }
+ else { m->setFastaFile(fastafile); }
+
+ listfile = validParameter.validFile(parameters, "list", true);
+ if (listfile == "not found") {
+ 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 file and the list parameter is required."); m->mothurOutEndLine(); abort = true; }
+ }
+ else if (listfile == "not open") { listfile = ""; abort = true; }
+ else { m->setListFile(listfile); }
+
+ //if the user changes the output directory command factory will send this info to us in the output parameter
+ outputDir = validParameter.validFile(parameters, "outputdir", false); if (outputDir == "not found"){
+ outputDir = "";
+ outputDir += m->hasPath(listfile); //if user entered a file with a path then preserve it
+ }
+
//check for optional parameter and set defaults
// ...at some point should added some additional type checking...
else { allLines = 1; }
}
- //if the user has not specified any labels use the ones from read.otu
- if (label == "") {
- allLines = globaldata->allLines;
- labels = globaldata->labels;
- }
-
namesfile = validParameter.validFile(parameters, "name", true);
- if (namesfile == "not open") { abort = true; }
+ if (namesfile == "not open") { namesfile = ""; abort = true; }
else if (namesfile == "not found") { namesfile = ""; }
+ else { m->setNameFile(namesfile); }
groupfile = validParameter.validFile(parameters, "group", true);
if (groupfile == "not open") { abort = true; }
else if (groupfile == "not found") { groupfile = ""; }
+ else { m->setGroupFile(groupfile); }
+
+ countfile = validParameter.validFile(parameters, "count", true);
+ if (countfile == "not open") { countfile = ""; abort = true; }
+ else if (countfile == "not found") { countfile = ""; }
+ else { m->setCountTableFile(countfile); }
+
+ if ((namesfile != "") && (countfile != "")) {
+ m->mothurOut("[ERROR]: you may only use one of the following: name or count."); m->mothurOutEndLine(); abort = true;
+ }
+
+ if ((groupfile != "") && (countfile != "")) {
+ m->mothurOut("[ERROR]: you may only use one of the following: group or count."); m->mothurOutEndLine(); abort=true;
+ }
+
+ if (countfile == "") {
+ if (namesfile == ""){
+ vector<string> files; files.push_back(fastafile);
+ parser.getNameFile(files);
+ }
+ }
- if (abort == false) {
-// m->openInputFile(fastafile, in);
- fasta = new FastaMap();
- if (groupfile != "") {
- groupMap = new GroupMap(groupfile);
-
- int error = groupMap->readMap();
- if (error == 1) { delete groupMap; abort = true; }
- }
- }
-
}
}
catch(exception& e) {
}
//**********************************************************************************************************************
-void BinSeqCommand::help(){
- try {
- m->mothurOut("The bin.seqs command can only be executed after a successful read.otu command of a listfile.\n");
- m->mothurOut("The bin.seqs command parameters are fasta, name, label and group. The fasta parameter is required.\n");
- m->mothurOut("The label parameter allows you to select what distance levels you would like a output files created for, and are separated by dashes.\n");
- m->mothurOut("The bin.seqs command should be in the following format: bin.seqs(fasta=yourFastaFile, name=yourNamesFile, group=yourGroupFile, label=yourLabels).\n");
- m->mothurOut("Example bin.seqs(fasta=amazon.fasta, group=amazon.groups, name=amazon.names).\n");
- m->mothurOut("The default value for label is all lines in your inputfile.\n");
- m->mothurOut("The bin.seqs command outputs a .fasta file for each distance you specify appending the OTU number to each name.\n");
- m->mothurOut("If you provide a groupfile, then it also appends the sequences group to the name.\n");
- m->mothurOut("Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFastaFile).\n\n");
- }
- catch(exception& e) {
- m->errorOut(e, "BinSeqCommand", "help");
- exit(1);
- }
-}
-
-//**********************************************************************************************************************
-
-BinSeqCommand::~BinSeqCommand(){
- //made new in execute
- if (abort == false) {
- delete input; globaldata->ginput = NULL;
- delete read;
- globaldata->gListVector = NULL;
- delete fasta;
- if (groupfile != "") { delete groupMap; globaldata->gGroupmap = NULL; }
- }
-}
-
+BinSeqCommand::~BinSeqCommand(){}
//**********************************************************************************************************************
int BinSeqCommand::execute(){
try {
- if (abort == true) { return 0; }
+ if (abort == true) { if (calledHelp) { return 0; } return 2; }
int error = 0;
+ fasta = new FastaMap();
+ if (groupfile != "") {
+ groupMap = new GroupMap(groupfile);
+ groupMap->readMap();
+ }
+
//read fastafile
fasta->readFastaFile(fastafile);
-
- //set format to list so input can get listvector
-// globaldata->setFormat("list");
-
//if user gave a namesfile then use it
- if (namesfile != "") {
- readNamesFile();
- }
+ if (namesfile != "") { readNamesFile(); }
+ if (countfile != "") { ct.readTable(countfile, true); }
- //read list file
- read = new ReadOTUFile(globaldata->getListFile());
- read->read(&*globaldata);
-
- input = globaldata->ginput;
- list = globaldata->gListVector;
+ input = new InputData(listfile, "list");
+ list = input->getListVector();
string lastLabel = list->getLabel();
- if (m->control_pressed) { return 0; }
+ if (m->control_pressed) { delete input; delete fasta; if (groupfile != "") { delete groupMap; } return 0; }
//if the users enters label "0.06" and there is no "0.06" in their file use the next lowest label.
set<string> processedLabels;
while((list != NULL) && ((allLines == 1) || (userLabels.size() != 0))) {
- 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]); } delete input; delete fasta; if (groupfile != "") { delete groupMap; } return 0; }
if(allLines == 1 || labels.count(list->getLabel()) == 1){
error = process(list);
- if (error == 1) { for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; }
+ if (error == 1) { for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } delete input; delete fasta; if (groupfile != "") { delete groupMap; } return 0; }
processedLabels.insert(list->getLabel());
userLabels.erase(list->getLabel());
list = input->getListVector(lastLabel);
error = process(list);
- if (error == 1) { for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; }
+ if (error == 1) { for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } delete input; delete fasta; if (groupfile != "") { delete groupMap; } return 0; }
processedLabels.insert(list->getLabel());
userLabels.erase(list->getLabel());
list = input->getListVector();
}
- 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]); } delete input; delete fasta; if (groupfile != "") { delete groupMap; } return 0; }
//output error messages about any remaining user labels
set<string>::iterator it;
list = input->getListVector(lastLabel);
error = process(list);
- if (error == 1) { for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; }
+ if (error == 1) { for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } delete input; delete fasta; if (groupfile != "") { delete groupMap; } return 0; }
delete list;
}
- if(m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; }
-
+ delete input;
+ delete fasta;
+ if (groupfile != "") { delete groupMap; }
+
+ if(m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; }
+
+ //set align file as new current fastafile
+ string currentFasta = "";
+ itTypes = outputTypes.find("fasta");
+ if (itTypes != outputTypes.end()) {
+ if ((itTypes->second).size() != 0) { currentFasta = (itTypes->second)[0]; m->setFastaFile(currentFasta); }
+ }
+
m->mothurOutEndLine();
m->mothurOut("Output File Names: "); m->mothurOutEndLine();
for (int i = 0; i < outputNames.size(); i++) { m->mothurOut(outputNames[i]); m->mothurOutEndLine(); }
//return 1 if error, 0 otherwise
int BinSeqCommand::process(ListVector* list) {
try {
- string binnames, name, sequence;
-
- string outputFileName = outputDir + m->getRootName(m->getSimpleName(globaldata->getListFile())) + list->getLabel() + ".fasta";
- m->openOutputFile(outputFileName, out);
-
- //save to output list of output file names
- outputNames.push_back(outputFileName);
-
- m->mothurOut(list->getLabel()); m->mothurOutEndLine();
-
- //for each bin in the list vector
- for (int i = 0; i < list->size(); i++) {
-
- if (m->control_pressed) { return 1; }
-
- binnames = list->get(i);
- while (binnames.find_first_of(',') != -1) {
- name = binnames.substr(0,binnames.find_first_of(','));
- binnames = binnames.substr(binnames.find_first_of(',')+1, binnames.length());
-
- //do work for that name
- sequence = fasta->getSequence(name);
- if (sequence != "not found") {
- //if you don't have groups
- if (groupfile == "") {
- name = name + "|" + toString(i+1);
- out << ">" << name << endl;
- out << sequence << endl;
- }else {//if you do have groups
- string group = groupMap->getGroup(name);
- if (group == "not found") {
- m->mothurOut(name + " is missing from your group file. Please correct. "); m->mothurOutEndLine();
- return 1;
- }else{
- name = name + "|" + group + "|" + toString(i+1);
- out << ">" << name << endl;
- out << sequence << endl;
- }
- }
- }else {
- m->mothurOut(name + " is missing from your fasta or name file. Please correct. "); m->mothurOutEndLine();
- return 1;
- }
-
- }
-
- //get last name
- sequence = fasta->getSequence(binnames);
- if (sequence != "not found") {
- //if you don't have groups
- if (groupfile == "") {
- binnames = binnames + "|" + toString(i+1);
- out << ">" << binnames << endl;
- out << sequence << endl;
- }else {//if you do have groups
- string group = groupMap->getGroup(binnames);
- if (group == "not found") {
- m->mothurOut(binnames + " is missing from your group file. Please correct. "); m->mothurOutEndLine();
- return 1;
- }else{
- binnames = binnames + "|" + group + "|" + toString(i+1);
- out << ">" << binnames << endl;
- out << sequence << endl;
- }
- }
- }else {
- m->mothurOut(binnames + " is missing from your fasta or name file. Please correct. "); m->mothurOutEndLine();
- return 1;
- }
- }
-
- out.close();
- return 0;
+ map<string, string> variables;
+ variables["[filename]"] = outputDir + m->getRootName(m->getSimpleName(listfile));
+ variables["[distance]"] = list->getLabel();
+ string outputFileName = getOutputFileName("fasta", variables);
+
+ m->openOutputFile(outputFileName, out);
+ outputNames.push_back(outputFileName); outputTypes["fasta"].push_back(outputFileName);
+
+ m->mothurOut(list->getLabel()); m->mothurOutEndLine();
+
+ //for each bin in the list vector
+ for (int i = 0; i < list->size(); i++) {
+
+ if (m->control_pressed) { return 1; }
+
+ string binnames = list->get(i);
+ vector<string> names;
+ m->splitAtComma(binnames, names);
+ for (int j = 0; j < names.size(); j++) {
+ string name = names[j];
+
+ //do work for that name
+ string sequence = fasta->getSequence(name);
+
+ if (countfile != "") {
+ if (sequence != "not found") {
+ if (ct.hasGroupInfo()) {
+ vector<string> groups = ct.getGroups(name);
+ string groupInfo = "";
+ for (int k = 0; k < groups.size()-1; k++) {
+ groupInfo += groups[k] + "-";
+ }
+ if (groups.size() != 0) { groupInfo += groups[groups.size()-1]; }
+ else { groupInfo = "not found"; }
+ name = name + "\t" + groupInfo + "\t" + toString(i+1)+ "\tNumRep=" + toString(ct.getNumSeqs(name));
+ out << ">" << name << endl;
+ out << sequence << endl;
+ }else {
+ name = name + "\t" + toString(i+1) + "\tNumRep=" + toString(ct.getNumSeqs(name));
+ out << ">" << name << endl;
+ out << sequence << endl;
+ }
+
+ }else { m->mothurOut(name + " is missing from your fasta. Does your list file contain all sequence names or just the uniques?"); m->mothurOutEndLine(); return 1; }
+ }else {
+ if (sequence != "not found") {
+ //if you don't have groups
+ if (groupfile == "") {
+ name = name + "\t" + toString(i+1);
+ out << ">" << name << endl;
+ out << sequence << endl;
+ }else {//if you do have groups
+ string group = groupMap->getGroup(name);
+ if (group == "not found") {
+ m->mothurOut(name + " is missing from your group file. Please correct. "); m->mothurOutEndLine();
+ return 1;
+ }else{
+ name = name + "\t" + group + "\t" + toString(i+1);
+ out << ">" << name << endl;
+ out << sequence << endl;
+ }
+ }
+ }else { m->mothurOut(name + " is missing from your fasta or name file. Please correct. "); m->mothurOutEndLine(); return 1; }
+ }
+ }
+ }
+
+ out.close();
+ return 0;
}
catch(exception& e) {