#include "removeseqscommand.h"
#include "sequence.hpp"
#include "listvector.hpp"
+#include "counttable.h"
//**********************************************************************************************************************
vector<string> RemoveSeqsCommand::setParameters(){
try {
- CommandParameter pfasta("fasta", "InputTypes", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(pfasta);
- CommandParameter pname("name", "InputTypes", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(pname);
- CommandParameter pgroup("group", "InputTypes", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(pgroup);
- CommandParameter plist("list", "InputTypes", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(plist);
- CommandParameter ptaxonomy("taxonomy", "InputTypes", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(ptaxonomy);
- CommandParameter palignreport("alignreport", "InputTypes", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(palignreport);
- CommandParameter pqfile("qfile", "InputTypes", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(pqfile);
- CommandParameter paccnos("accnos", "InputTypes", "", "", "none", "none", "none",false,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);
+ 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); }
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, list, taxonomy, quality or alignreport file.\n";
+ 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, list, taxonomy, qfile, alignreport and dups. You must provide accnos and at least one of the file parameters.\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";
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 {
outputTypes["alignreport"] = tempOutNames;
outputTypes["list"] = tempOutNames;
outputTypes["qfile"] = tempOutNames;
+ outputTypes["count"] = tempOutNames;
}
catch(exception& e) {
m->errorOut(e, "RemoveSeqsCommand", "RemoveSeqsCommand");
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 = ""; }
//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; }
+ }
}
else { temp = "false"; usedDups = ""; }
}
dups = m->isTrue(temp);
-
- if ((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 ((fastafile != "") && (namefile == "")) {
- vector<string> files; files.push_back(fastafile);
- parser.getNameFile(files);
- }
+
+ 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);
+ }
+ }
}
}
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 (namefile != "") { readName(); }
if (listfile != "") { readList(); }
if (taxfile != "") { readTax(); }
if (qualfile != "") { readQual(); }
+ if (countfile != "") { readCount(); }
if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; }
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;
try {
string thisOutputDir = outputDir;
if (outputDir == "") { thisOutputDir += m->hasPath(fastafile); }
- string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(fastafile)) + "pick" + m->getExtension(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;
m->openOutputFile(outputFileName, out);
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++; }
}
m->gobble(in);
try {
string thisOutputDir = outputDir;
if (outputDir == "") { thisOutputDir += m->hasPath(qualfile); }
- string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(qualfile)) + "pick" + m->getExtension(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);
saveName = name.substr(1);
while (!in.eof()) {
char c = in.get();
- if (c == 10 || c == 13){ break; }
+ if (c == 10 || c == 13 || c == -1){ break; }
else { name += c; }
}
m->gobble(in);
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;
}
}
//**********************************************************************************************************************
+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, true);
+ 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 {
string thisOutputDir = outputDir;
if (outputDir == "") { thisOutputDir += m->hasPath(listfile); }
- string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(listfile)) + "pick" + m->getExtension(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;
m->openOutputFile(outputFileName, out);
try {
string thisOutputDir = outputDir;
if (outputDir == "") { thisOutputDir += m->hasPath(namefile); }
- string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(namefile)) + "pick" + m->getExtension(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;
m->openOutputFile(outputFileName, out);
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] << ','; }
try {
string thisOutputDir = outputDir;
if (outputDir == "") { thisOutputDir += m->hasPath(groupfile); }
- string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(groupfile)) + "pick" + m->getExtension(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;
m->openOutputFile(outputFileName, out);
try {
string thisOutputDir = outputDir;
if (outputDir == "") { thisOutputDir += m->hasPath(taxfile); }
- string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(taxfile)) + "pick" + m->getExtension(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;
m->openOutputFile(outputFileName, out);
while(!in.eof()){
if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; }
- in >> name; //read from first column
+ in >> name; m->gobble(in); //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++; }
try {
string thisOutputDir = outputDir;
if (outputDir == "") { thisOutputDir += m->hasPath(alignfile); }
- string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(alignfile)) + "pick.align.report";
+ map<string, string> variables;
+ variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(alignfile));
+ string outputFileName = getOutputFileName("alignreport", variables);
ofstream out;
m->openOutputFile(outputFileName, out);
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) {
}
}
//**********************************************************************************************************************
-void RemoveSeqsCommand::readAccnos(){
- try {
-
- ifstream in;
- m->openInputFile(accnosfile, in);
- string name;
-
- while(!in.eof()){
- in >> name;
-
- names.insert(name);
-
- m->gobble(in);
- }
- in.close();
-
- }
- catch(exception& e) {
- m->errorOut(e, "RemoveSeqsCommand", "readAccnos");
- exit(1);
- }
-}
-
-//**********************************************************************************************************************