#include "removeseqscommand.h"
#include "sequence.hpp"
#include "listvector.hpp"
+#include "counttable.h"
//**********************************************************************************************************************
-
+vector<string> RemoveSeqsCommand::setParameters(){
+ try {
+ CommandParameter pfasta("fasta", "InputTypes", "", "", "none", "FNGLT", "none","fasta",false,false,true); parameters.push_back(pfasta);
+ CommandParameter pname("name", "InputTypes", "", "", "NameCount", "FNGLT", "none","name",false,false,true); parameters.push_back(pname);
+ CommandParameter pcount("count", "InputTypes", "", "", "NameCount-CountGroup", "FNGLT", "none","count",false,false,true); parameters.push_back(pcount);
+ CommandParameter pgroup("group", "InputTypes", "", "", "CountGroup", "FNGLT", "none","group",false,false,true); parameters.push_back(pgroup);
+ CommandParameter plist("list", "InputTypes", "", "", "none", "FNGLT", "none","list",false,false,true); parameters.push_back(plist);
+ CommandParameter ptaxonomy("taxonomy", "InputTypes", "", "", "none", "FNGLT", "none","taxonomy",false,false,true); parameters.push_back(ptaxonomy);
+ CommandParameter palignreport("alignreport", "InputTypes", "", "", "none", "FNGLT", "none","alignreport",false,false); parameters.push_back(palignreport);
+ CommandParameter pqfile("qfile", "InputTypes", "", "", "none", "FNGLT", "none","qfile",false,false); parameters.push_back(pqfile);
+ CommandParameter paccnos("accnos", "InputTypes", "", "", "none", "none", "none","",false,true,true); parameters.push_back(paccnos);
+ CommandParameter pdups("dups", "Boolean", "", "T", "", "", "","",false,false); parameters.push_back(pdups);
+ 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, "RemoveSeqsCommand", "setParameters");
+ exit(1);
+ }
+}
+//**********************************************************************************************************************
+string RemoveSeqsCommand::getHelpString(){
+ try {
+ string helpString = "";
+ helpString += "The remove.seqs command reads an .accnos file and at least one of the following file types: fasta, name, group, count, list, taxonomy, quality or alignreport file.\n";
+ helpString += "It outputs a file containing the sequences NOT in the .accnos file.\n";
+ helpString += "The remove.seqs command parameters are accnos, fasta, name, group, count, list, taxonomy, qfile, alignreport and dups. You must provide accnos and at least one of the file parameters.\n";
+ helpString += "The dups parameter allows you to remove the entire line from a name file if you remove any name from the line. default=true. \n";
+ helpString += "The remove.seqs command should be in the following format: remove.seqs(accnos=yourAccnos, fasta=yourFasta).\n";
+ helpString += "Example remove.seqs(accnos=amazon.accnos, fasta=amazon.fasta).\n";
+ helpString += "Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFasta).\n";
+ return helpString;
+ }
+ catch(exception& e) {
+ m->errorOut(e, "RemoveSeqsCommand", "getHelpString");
+ exit(1);
+ }
+}
+//**********************************************************************************************************************
+string RemoveSeqsCommand::getOutputPattern(string type) {
+ try {
+ string pattern = "";
+
+ if (type == "fasta") { pattern = "[filename],pick,[extension]"; }
+ else if (type == "taxonomy") { pattern = "[filename],pick,[extension]"; }
+ else if (type == "name") { pattern = "[filename],pick,[extension]"; }
+ else if (type == "group") { pattern = "[filename],pick,[extension]"; }
+ else if (type == "count") { pattern = "[filename],pick,[extension]"; }
+ else if (type == "list") { pattern = "[filename],pick,[extension]"; }
+ else if (type == "qfile") { pattern = "[filename],pick,[extension]"; }
+ else if (type == "alignreport") { pattern = "[filename],pick.align.report"; }
+ else { m->mothurOut("[ERROR]: No definition for type " + type + " output pattern.\n"); m->control_pressed = true; }
+
+ return pattern;
+ }
+ catch(exception& e) {
+ m->errorOut(e, "GetSeqsCommand", "getOutputPattern");
+ exit(1);
+ }
+}
+//**********************************************************************************************************************
+RemoveSeqsCommand::RemoveSeqsCommand(){
+ try {
+ abort = true; calledHelp = true;
+ setParameters();
+ vector<string> tempOutNames;
+ outputTypes["fasta"] = tempOutNames;
+ outputTypes["taxonomy"] = tempOutNames;
+ outputTypes["name"] = tempOutNames;
+ outputTypes["group"] = tempOutNames;
+ outputTypes["alignreport"] = tempOutNames;
+ outputTypes["list"] = tempOutNames;
+ outputTypes["qfile"] = tempOutNames;
+ outputTypes["count"] = tempOutNames;
+ }
+ catch(exception& e) {
+ m->errorOut(e, "RemoveSeqsCommand", "RemoveSeqsCommand");
+ exit(1);
+ }
+}
+//**********************************************************************************************************************
RemoveSeqsCommand::RemoveSeqsCommand(string option) {
try {
- abort = false;
+ abort = false; calledHelp = false;
//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 Array[] = {"fasta","name", "group", "alignreport", "accnos", "list","taxonomy","outputdir","inputdir", "dups" };
- vector<string> myArray (Array, Array+(sizeof(Array)/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; }
}
+ //initialize outputTypes
+ vector<string> tempOutNames;
+ outputTypes["fasta"] = tempOutNames;
+ outputTypes["taxonomy"] = tempOutNames;
+ outputTypes["name"] = tempOutNames;
+ outputTypes["group"] = tempOutNames;
+ outputTypes["alignreport"] = tempOutNames;
+ outputTypes["list"] = tempOutNames;
+ outputTypes["qfile"] = tempOutNames;
+ outputTypes["count"] = tempOutNames;
+
//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 = ""; }
it = parameters.find("alignreport");
//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["alignreport"] = 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("accnos");
//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["accnos"] = inputDir + it->second; }
}
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("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; }
}
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("taxonomy");
//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["taxonomy"] = inputDir + it->second; }
}
+
+ it = parameters.find("qfile");
+ //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["qfile"] = 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
accnosfile = validParameter.validFile(parameters, "accnos", true);
if (accnosfile == "not open") { abort = true; }
- else if (accnosfile == "not found") { accnosfile = ""; m->mothurOut("You must provide an accnos file."); m->mothurOutEndLine(); abort = true; }
+ else if (accnosfile == "not found") {
+ accnosfile = m->getAccnosFile();
+ if (accnosfile != "") { m->mothurOut("Using " + accnosfile + " as input file for the accnos parameter."); m->mothurOutEndLine(); }
+ else {
+ m->mothurOut("You have no valid accnos file and accnos is required."); m->mothurOutEndLine();
+ abort = true;
+ }
+ }else { m->setAccnosFile(accnosfile); }
fastafile = validParameter.validFile(parameters, "fasta", true);
- if (fastafile == "not open") { abort = true; }
+ if (fastafile == "not open") { fastafile = ""; abort = true; }
else if (fastafile == "not found") { fastafile = ""; }
-
+ else { m->setFastaFile(fastafile); }
+
namefile = validParameter.validFile(parameters, "name", true);
- if (namefile == "not open") { abort = true; }
+ if (namefile == "not open") { namefile = ""; abort = true; }
else if (namefile == "not found") { namefile = ""; }
-
+ else { m->setNameFile(namefile); }
+
groupfile = validParameter.validFile(parameters, "group", true);
if (groupfile == "not open") { abort = true; }
- else if (groupfile == "not found") { groupfile = ""; }
+ else if (groupfile == "not found") { groupfile = ""; }
+ else { m->setGroupFile(groupfile); }
alignfile = validParameter.validFile(parameters, "alignreport", true);
if (alignfile == "not open") { abort = true; }
listfile = validParameter.validFile(parameters, "list", true);
if (listfile == "not open") { abort = true; }
else if (listfile == "not found") { listfile = ""; }
+ else { m->setListFile(listfile); }
taxfile = validParameter.validFile(parameters, "taxonomy", true);
if (taxfile == "not open") { abort = true; }
else if (taxfile == "not found") { taxfile = ""; }
-
-
- string usedDups = "true";
- string temp = validParameter.validFile(parameters, "dups", false); if (temp == "not found") { temp = "false"; usedDups = ""; }
- dups = isTrue(temp);
+ else { m->setTaxonomyFile(taxfile); }
- if ((fastafile == "") && (namefile == "") && (groupfile == "") && (alignfile == "") && (listfile == "") && (taxfile == "")) { m->mothurOut("You must provide at least one of the following: fasta, name, group, taxonomy, alignreport or list."); m->mothurOutEndLine(); abort = true; }
+ qualfile = validParameter.validFile(parameters, "qfile", true);
+ if (qualfile == "not open") { abort = true; }
+ else if (qualfile == "not found") { qualfile = ""; }
+ else { m->setQualFile(qualfile); }
- if ((usedDups != "") && (namefile == "")) { m->mothurOut("You may only use dups with the name option."); m->mothurOutEndLine(); abort = true; }
+ string usedDups = "true";
+ string temp = validParameter.validFile(parameters, "dups", false);
+ if (temp == "not found") {
+ if (namefile != "") { temp = "true"; }
+ else { temp = "false"; usedDups = ""; }
+ }
+ dups = m->isTrue(temp);
+
+ countfile = validParameter.validFile(parameters, "count", true);
+ if (countfile == "not open") { countfile = ""; abort = true; }
+ else if (countfile == "not found") { countfile = ""; }
+ else { m->setCountTableFile(countfile); }
+
+ if ((namefile != "") && (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 == "") && (fastafile == "") && (namefile == "") && (groupfile == "") && (alignfile == "") && (listfile == "") && (taxfile == "") && (qualfile == "")) { m->mothurOut("You must provide at least one of the following: fasta, name, group, taxonomy, quality, alignreport or list."); m->mothurOutEndLine(); abort = true; }
+
+ if (countfile == "") {
+ if ((fastafile != "") && (namefile == "")) {
+ vector<string> files; files.push_back(fastafile);
+ parser.getNameFile(files);
+ }
+ }
}
}
}
//**********************************************************************************************************************
-void RemoveSeqsCommand::help(){
- try {
- m->mothurOut("The remove.seqs command reads an .accnos file and at least one of the following file types: fasta, name, group, list, taxonomy or alignreport file.\n");
- m->mothurOut("It outputs a file containing the sequences NOT in the .accnos file.\n");
- m->mothurOut("The remove.seqs command parameters are accnos, fasta, name, group, list, taxonomy, alignreport and dups. You must provide accnos and at least one of the file parameters.\n");
- m->mothurOut("The dups parameter allows you to remove the entire line from a name file if you remove any name from the line. default=false. If dups=true, then remove.seqs outputs a new .accnos file containing all the sequences removed. \n");
- m->mothurOut("The remove.seqs command should be in the following format: remove.seqs(accnos=yourAccnos, fasta=yourFasta).\n");
- m->mothurOut("Example remove.seqs(accnos=amazon.accnos, fasta=amazon.fasta).\n");
- m->mothurOut("Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFasta).\n\n");
- }
- catch(exception& e) {
- m->errorOut(e, "RemoveSeqsCommand", "help");
- exit(1);
- }
-}
-
-//**********************************************************************************************************************
-
int RemoveSeqsCommand::execute(){
try {
- if (abort == true) { return 0; }
+ if (abort == true) { if (calledHelp) { return 0; } return 2; }
//get names you want to keep
- readAccnos();
+ names = m->readAccnos(accnosfile);
if (m->control_pressed) { return 0; }
+
+ if (countfile != "") {
+ if ((fastafile != "") || (listfile != "") || (taxfile != "")) {
+ m->mothurOut("\n[NOTE]: The count file should contain only unique names, so mothur assumes your fasta, list and taxonomy files also contain only uniques.\n\n");
+ }
+ }
//read through the correct file and output lines you want to keep
- if (fastafile != "") { readFasta(); }
if (namefile != "") { readName(); }
+ if (fastafile != "") { readFasta(); }
if (groupfile != "") { readGroup(); }
if (alignfile != "") { readAlign(); }
if (listfile != "") { readList(); }
if (taxfile != "") { readTax(); }
+ if (qualfile != "") { readQual(); }
+ if (countfile != "") { readCount(); }
- 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; }
+
if (outputNames.size() != 0) {
m->mothurOutEndLine();
m->mothurOut("Output File Names: "); m->mothurOutEndLine();
for (int i = 0; i < outputNames.size(); i++) { m->mothurOut(outputNames[i]); m->mothurOutEndLine(); }
m->mothurOutEndLine();
+
+ //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("taxonomy");
+ if (itTypes != outputTypes.end()) {
+ if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setTaxonomyFile(current); }
+ }
+
+ itTypes = outputTypes.find("qfile");
+ if (itTypes != outputTypes.end()) {
+ if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setQualFile(current); }
+ }
+
+ itTypes = outputTypes.find("count");
+ if (itTypes != outputTypes.end()) {
+ if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setCountTableFile(current); }
+ }
}
return 0;
//**********************************************************************************************************************
int RemoveSeqsCommand::readFasta(){
try {
- if (outputDir == "") { outputDir += hasPath(fastafile); }
- string outputFileName = outputDir + getRootName(getSimpleName(fastafile)) + "pick" + getExtension(fastafile);
+ string thisOutputDir = outputDir;
+ if (outputDir == "") { thisOutputDir += m->hasPath(fastafile); }
+ map<string, string> variables;
+ variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(fastafile));
+ variables["[extension]"] = m->getExtension(fastafile);
+ string outputFileName = getOutputFileName("fasta", variables);
+
ofstream out;
- openOutputFile(outputFileName, out);
+ m->openOutputFile(outputFileName, out);
ifstream in;
- openInputFile(fastafile, in);
+ m->openInputFile(fastafile, in);
string name;
bool wroteSomething = false;
+ int removedCount = 0;
while(!in.eof()){
- if (m->control_pressed) { in.close(); out.close(); remove(outputFileName.c_str()); return 0; }
+ if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; }
Sequence currSeq(in);
+
+ if (!dups) {//adjust name if needed
+ map<string, string>::iterator it = uniqueMap.find(currSeq.getName());
+ if (it != uniqueMap.end()) { currSeq.setName(it->second); }
+ }
+
name = currSeq.getName();
if (name != "") {
if (names.count(name) == 0) {
wroteSomething = true;
- currSeq.printSequence(out);
- }
+ currSeq.printSequence(out);
+ }else { removedCount++; }
}
- gobble(in);
+ m->gobble(in);
}
in.close();
out.close();
- if (wroteSomething == false) {
- m->mothurOut("Your file contains only sequences from the .accnos file."); m->mothurOutEndLine();
- remove(outputFileName.c_str());
- }else { outputNames.push_back(outputFileName); }
+ if (wroteSomething == false) { m->mothurOut("Your file contains only sequences from the .accnos file."); m->mothurOutEndLine(); }
+ outputTypes["fasta"].push_back(outputFileName); outputNames.push_back(outputFileName);
+
+ m->mothurOut("Removed " + toString(removedCount) + " sequences from your fasta file."); m->mothurOutEndLine();
return 0;
}
}
//**********************************************************************************************************************
+int RemoveSeqsCommand::readQual(){
+ try {
+ string thisOutputDir = outputDir;
+ if (outputDir == "") { thisOutputDir += m->hasPath(qualfile); }
+ map<string, string> variables;
+ variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(qualfile));
+ variables["[extension]"] = m->getExtension(qualfile);
+ string outputFileName = getOutputFileName("qfile", variables);
+ ofstream out;
+ m->openOutputFile(outputFileName, out);
+
+
+ ifstream in;
+ m->openInputFile(qualfile, in);
+ string name;
+
+ bool wroteSomething = false;
+ int removedCount = 0;
+
+
+ while(!in.eof()){
+ string saveName = "";
+ string name = "";
+ string scores = "";
+
+ in >> name;
+
+ if (name.length() != 0) {
+ saveName = name.substr(1);
+ while (!in.eof()) {
+ char c = in.get();
+ if (c == 10 || c == 13){ break; }
+ else { name += c; }
+ }
+ m->gobble(in);
+ }
+
+ while(in){
+ char letter= in.get();
+ if(letter == '>'){ in.putback(letter); break; }
+ else{ scores += letter; }
+ }
+
+ m->gobble(in);
+
+ if (!dups) {//adjust name if needed
+ map<string, string>::iterator it = uniqueMap.find(saveName);
+ if (it != uniqueMap.end()) { name = ">" + it->second; saveName = it->second; }
+ }
+
+ if (names.count(saveName) == 0) {
+ wroteSomething = true;
+
+ out << name << endl << scores;
+ }else { removedCount++; }
+
+ m->gobble(in);
+ }
+ in.close();
+ out.close();
+
+
+ if (wroteSomething == false) { m->mothurOut("Your file contains only sequences from the .accnos file."); m->mothurOutEndLine(); }
+ outputNames.push_back(outputFileName); outputTypes["qfile"].push_back(outputFileName);
+
+ m->mothurOut("Removed " + toString(removedCount) + " sequences from your quality file."); m->mothurOutEndLine();
+
+ return 0;
+
+ }
+ catch(exception& e) {
+ m->errorOut(e, "RemoveSeqsCommand", "readQual");
+ exit(1);
+ }
+}
+//**********************************************************************************************************************
+int RemoveSeqsCommand::readCount(){
+ try {
+
+ string thisOutputDir = outputDir;
+ if (outputDir == "") { thisOutputDir += m->hasPath(countfile); }
+ map<string, string> variables;
+ variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(countfile));
+ variables["[extension]"] = m->getExtension(countfile);
+ string outputFileName = getOutputFileName("count", variables);
+
+ ofstream out;
+ m->openOutputFile(outputFileName, out);
+
+ ifstream in;
+ m->openInputFile(countfile, in);
+
+ bool wroteSomething = false;
+ int removedCount = 0;
+
+ string headers = m->getline(in); m->gobble(in);
+ out << headers << endl;
+
+ string name, rest; int thisTotal;
+ while (!in.eof()) {
+
+ if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; }
+
+ in >> name; m->gobble(in);
+ in >> thisTotal; m->gobble(in);
+ rest = m->getline(in); m->gobble(in);
+ if (m->debug) { m->mothurOut("[DEBUG]: " + name + '\t' + rest + "\n"); }
+
+ if (names.count(name) == 0) {
+ out << name << '\t' << thisTotal << '\t' << rest << endl;
+ wroteSomething = true;
+ }else { removedCount += thisTotal; }
+ }
+ in.close();
+ out.close();
+
+ //check for groups that have been eliminated
+ CountTable ct;
+ if (ct.testGroups(outputFileName)) {
+ ct.readTable(outputFileName);
+ ct.printTable(outputFileName);
+ }
+
+
+ if (wroteSomething == false) { m->mothurOut("Your file contains only sequences from the .accnos file."); m->mothurOutEndLine(); }
+ outputTypes["count"].push_back(outputFileName); outputNames.push_back(outputFileName);
+
+ m->mothurOut("Removed " + toString(removedCount) + " sequences from your count file."); m->mothurOutEndLine();
+
+ return 0;
+ }
+ catch(exception& e) {
+ m->errorOut(e, "RemoveSeqsCommand", "readCount");
+ exit(1);
+ }
+}
+//**********************************************************************************************************************
int RemoveSeqsCommand::readList(){
try {
- if (outputDir == "") { outputDir += hasPath(listfile); }
- string outputFileName = outputDir + getRootName(getSimpleName(listfile)) + "pick" + getExtension(listfile);
+ string thisOutputDir = outputDir;
+ if (outputDir == "") { thisOutputDir += m->hasPath(listfile); }
+ map<string, string> variables;
+ variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(listfile));
+ variables["[extension]"] = m->getExtension(listfile);
+ string outputFileName = getOutputFileName("list", variables);
ofstream out;
- openOutputFile(outputFileName, out);
+ m->openOutputFile(outputFileName, out);
ifstream in;
- openInputFile(listfile, in);
+ m->openInputFile(listfile, in);
bool wroteSomething = false;
+ int removedCount = 0;
while(!in.eof()){
+
+ removedCount = 0;
+
//read in list vector
ListVector list(in);
//for each bin
for (int i = 0; i < list.getNumBins(); i++) {
- if (m->control_pressed) { in.close(); out.close(); remove(outputFileName.c_str()); return 0; }
+ if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; }
//parse out names that are in accnos file
string binnames = list.get(i);
//if that name is in the .accnos file, add it
if (names.count(name) == 0) { newNames += name + ","; }
+ else { removedCount++; }
}
//get last name
if (names.count(binnames) == 0) { newNames += binnames + ","; }
+ else { removedCount++; }
//if there are names in this bin add to new list
if (newNames != "") {
newList.print(out);
}
- gobble(in);
+ m->gobble(in);
}
in.close();
out.close();
- if (wroteSomething == false) {
- m->mothurOut("Your file contains only sequences from the .accnos file."); m->mothurOutEndLine();
- remove(outputFileName.c_str());
- }else { outputNames.push_back(outputFileName); }
+ if (wroteSomething == false) { m->mothurOut("Your file contains only sequences from the .accnos file."); m->mothurOutEndLine(); }
+ outputTypes["list"].push_back(outputFileName); outputNames.push_back(outputFileName);
+
+ m->mothurOut("Removed " + toString(removedCount) + " sequences from your list file."); m->mothurOutEndLine();
return 0;
//**********************************************************************************************************************
int RemoveSeqsCommand::readName(){
try {
- if (outputDir == "") { outputDir += hasPath(namefile); }
- string outputFileName = outputDir + getRootName(getSimpleName(namefile)) + "pick" + getExtension(namefile);
- string outputFileName2 = outputDir + getRootName(getSimpleName(namefile)) + "dups.accnos";
-
- ofstream out2;
- if (dups) { openOutputFile(outputFileName2, out2); }
- bool wroteDups = false;
-
+ string thisOutputDir = outputDir;
+ if (outputDir == "") { thisOutputDir += m->hasPath(namefile); }
+ map<string, string> variables;
+ variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(namefile));
+ variables["[extension]"] = m->getExtension(namefile);
+ string outputFileName = getOutputFileName("name", variables);
ofstream out;
- openOutputFile(outputFileName, out);
+ m->openOutputFile(outputFileName, out);
ifstream in;
- openInputFile(namefile, in);
+ m->openInputFile(namefile, in);
string name, firstCol, secondCol;
bool wroteSomething = false;
+ int removedCount = 0;
while(!in.eof()){
- if (m->control_pressed) { in.close(); out.close(); remove(outputFileName.c_str()); if (dups) { out2.close(); remove(outputFileName2.c_str()); } return 0; }
-
- in >> firstCol;
+ if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; }
+
+ in >> firstCol; m->gobble(in);
in >> secondCol;
-
+
vector<string> parsedNames;
- //parse second column saving each name
- while (secondCol.find_first_of(',') != -1) {
- name = secondCol.substr(0,secondCol.find_first_of(','));
- secondCol = secondCol.substr(secondCol.find_first_of(',')+1, secondCol.length());
- parsedNames.push_back(name);
-
- }
+ m->splitAtComma(secondCol, parsedNames);
- //get name after last ,
- parsedNames.push_back(secondCol);
-
vector<string> validSecond; validSecond.clear();
for (int i = 0; i < parsedNames.size(); i++) {
if (names.count(parsedNames[i]) == 0) {
}
}
- if ((dups) && (validSecond.size() != parsedNames.size())) {
- wroteDups = true;
- for (int i = 0; i < parsedNames.size(); i++) { out2 << parsedNames[i] << endl; }
+ if ((dups) && (validSecond.size() != parsedNames.size())) { //if dups is true and we want to get rid of anyone, get rid of everyone
+ for (int i = 0; i < parsedNames.size(); i++) { names.insert(parsedNames[i]); }
+ removedCount += parsedNames.size();
}else {
- //if the name in the first column is in the set then print it and any other names in second column also in set
+ removedCount += parsedNames.size()-validSecond.size();
+ //if the name in the first column is in the set then print it and any other names in second column also in set
if (names.count(firstCol) == 0) {
wroteSomething = true;
wroteSomething = true;
out << validSecond[0] << '\t';
+ //we are changing the unique name in the fasta file
+ uniqueMap[firstCol] = validSecond[0];
//you know you have at least one valid second since first column is valid
for (int i = 0; i < validSecond.size()-1; i++) { out << validSecond[i] << ','; }
}
}
}
- gobble(in);
+ m->gobble(in);
}
in.close();
out.close();
- if (dups) { out2.close(); }
- if (wroteDups == false) {
- remove(outputFileName2.c_str());
- }else { outputNames.push_back(outputFileName2); }
+ if (wroteSomething == false) { m->mothurOut("Your file contains only sequences from the .accnos file."); m->mothurOutEndLine(); }
+ outputTypes["name"].push_back(outputFileName); outputNames.push_back(outputFileName);
- if (wroteSomething == false) {
- m->mothurOut("Your file contains only sequences from the .accnos file."); m->mothurOutEndLine();
- remove(outputFileName.c_str());
- }else { outputNames.push_back(outputFileName); }
+ m->mothurOut("Removed " + toString(removedCount) + " sequences from your name file."); m->mothurOutEndLine();
return 0;
}
//**********************************************************************************************************************
int RemoveSeqsCommand::readGroup(){
try {
- if (outputDir == "") { outputDir += hasPath(groupfile); }
- string outputFileName = outputDir + getRootName(getSimpleName(groupfile)) + "pick" + getExtension(groupfile);
+ string thisOutputDir = outputDir;
+ if (outputDir == "") { thisOutputDir += m->hasPath(groupfile); }
+ map<string, string> variables;
+ variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(groupfile));
+ variables["[extension]"] = m->getExtension(groupfile);
+ string outputFileName = getOutputFileName("group", variables);
ofstream out;
- openOutputFile(outputFileName, out);
+ m->openOutputFile(outputFileName, out);
ifstream in;
- openInputFile(groupfile, in);
+ m->openInputFile(groupfile, in);
string name, group;
bool wroteSomething = false;
+ int removedCount = 0;
while(!in.eof()){
- if (m->control_pressed) { in.close(); out.close(); remove(outputFileName.c_str()); return 0; }
+ if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; }
in >> name; //read from first column
in >> group; //read from second column
if (names.count(name) == 0) {
wroteSomething = true;
out << name << '\t' << group << endl;
- }
+ }else { removedCount++; }
- gobble(in);
+ m->gobble(in);
}
in.close();
out.close();
- if (wroteSomething == false) {
- m->mothurOut("Your file contains only sequences from the .accnos file."); m->mothurOutEndLine();
- remove(outputFileName.c_str());
- }else { outputNames.push_back(outputFileName); }
+ if (wroteSomething == false) { m->mothurOut("Your file contains only sequences from the .accnos file."); m->mothurOutEndLine(); }
+ outputTypes["group"].push_back(outputFileName); outputNames.push_back(outputFileName);
+
+ m->mothurOut("Removed " + toString(removedCount) + " sequences from your group file."); m->mothurOutEndLine();
+
return 0;
}
//**********************************************************************************************************************
int RemoveSeqsCommand::readTax(){
try {
- if (outputDir == "") { outputDir += hasPath(taxfile); }
- string outputFileName = outputDir + getRootName(getSimpleName(taxfile)) + "pick" + getExtension(taxfile);
+ string thisOutputDir = outputDir;
+ if (outputDir == "") { thisOutputDir += m->hasPath(taxfile); }
+ map<string, string> variables;
+ variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(taxfile));
+ variables["[extension]"] = m->getExtension(taxfile);
+ string outputFileName = getOutputFileName("taxonomy", variables);
ofstream out;
- openOutputFile(outputFileName, out);
+ m->openOutputFile(outputFileName, out);
ifstream in;
- openInputFile(taxfile, in);
+ m->openInputFile(taxfile, in);
string name, tax;
bool wroteSomething = false;
+ int removedCount = 0;
while(!in.eof()){
- if (m->control_pressed) { in.close(); out.close(); remove(outputFileName.c_str()); return 0; }
+ if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; }
in >> name; //read from first column
in >> tax; //read from second column
+ if (!dups) {//adjust name if needed
+ map<string, string>::iterator it = uniqueMap.find(name);
+ if (it != uniqueMap.end()) { name = it->second; }
+ }
+
//if this name is in the accnos file
if (names.count(name) == 0) {
wroteSomething = true;
+
out << name << '\t' << tax << endl;
- }
+ }else { removedCount++; }
- gobble(in);
+ m->gobble(in);
}
in.close();
out.close();
- if (wroteSomething == false) {
- m->mothurOut("Your file contains only sequences from the .accnos file."); m->mothurOutEndLine();
- remove(outputFileName.c_str());
- }else { outputNames.push_back(outputFileName); }
+ if (wroteSomething == false) { m->mothurOut("Your file contains only sequences from the .accnos file."); m->mothurOutEndLine(); }
+ outputTypes["taxonomy"].push_back(outputFileName); outputNames.push_back(outputFileName);
+
+ m->mothurOut("Removed " + toString(removedCount) + " sequences from your taxonomy file."); m->mothurOutEndLine();
return 0;
}
//alignreport file has a column header line then all other lines contain 16 columns. we just want the first column since that contains the name
int RemoveSeqsCommand::readAlign(){
try {
- if (outputDir == "") { outputDir += hasPath(alignfile); }
- string outputFileName = outputDir + getRootName(getSimpleName(alignfile)) + "pick.align.report";
+ string thisOutputDir = outputDir;
+ if (outputDir == "") { thisOutputDir += m->hasPath(alignfile); }
+ map<string, string> variables;
+ variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(alignfile));
+ string outputFileName = getOutputFileName("alignreport", variables);
+
ofstream out;
- openOutputFile(outputFileName, out);
+ m->openOutputFile(outputFileName, out);
ifstream in;
- openInputFile(alignfile, in);
+ m->openInputFile(alignfile, in);
string name, junk;
bool wroteSomething = false;
+ int removedCount = 0;
//read column headers
for (int i = 0; i < 16; i++) {
out << endl;
while(!in.eof()){
- if (m->control_pressed) { in.close(); out.close(); remove(outputFileName.c_str()); return 0; }
+ if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; }
in >> name; //read from first column
+
+ if (!dups) {//adjust name if needed
+ map<string, string>::iterator it = uniqueMap.find(name);
+ if (it != uniqueMap.end()) { name = it->second; }
+ }
//if this name is in the accnos file
if (names.count(name) == 0) {
out << endl;
}else {//still read just don't do anything with it
+ removedCount++;
//read rest
for (int i = 0; i < 15; i++) {
}
}
- gobble(in);
+ m->gobble(in);
}
in.close();
out.close();
- if (wroteSomething == false) {
- m->mothurOut("Your file contains only sequences from the .accnos file."); m->mothurOutEndLine();
- remove(outputFileName.c_str());
- }else { outputNames.push_back(outputFileName); }
+ if (wroteSomething == false) { m->mothurOut("Your file contains only sequences from the .accnos file."); m->mothurOutEndLine(); }
+ outputTypes["alignreport"].push_back(outputFileName); outputNames.push_back(outputFileName);
+
+ m->mothurOut("Removed " + toString(removedCount) + " sequences from your alignreport file."); m->mothurOutEndLine();
+
return 0;
}
}
//**********************************************************************************************************************
-void RemoveSeqsCommand::readAccnos(){
- try {
-
- ifstream in;
- openInputFile(accnosfile, in);
- string name;
-
- while(!in.eof()){
- in >> name;
-
- names.insert(name);
-
- gobble(in);
- }
- in.close();
-
- }
- catch(exception& e) {
- m->errorOut(e, "RemoveSeqsCommand", "readAccnos");
- exit(1);
- }
-}
-
-//**********************************************************************************************************************