#include "listvector.hpp"
//**********************************************************************************************************************
-
+vector<string> GetSeqsCommand::getValidParameters(){
+ try {
+ string Array[] = {"fasta","name", "group", "qfile","alignreport", "accnos", "accnos2","dups", "list","taxonomy","outputdir","inputdir"};
+ vector<string> myArray (Array, Array+(sizeof(Array)/sizeof(string)));
+ return myArray;
+ }
+ catch(exception& e) {
+ m->errorOut(e, "GetSeqsCommand", "getValidParameters");
+ exit(1);
+ }
+}
+//**********************************************************************************************************************
+GetSeqsCommand::GetSeqsCommand(){
+ try {
+ abort = true; calledHelp = true;
+ 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["accnosreport"] = tempOutNames;
+ }
+ catch(exception& e) {
+ m->errorOut(e, "GetSeqsCommand", "GetSeqsCommand");
+ exit(1);
+ }
+}
+//**********************************************************************************************************************
+vector<string> GetSeqsCommand::getRequiredParameters(){
+ try {
+ string Array[] = {"accnos"};
+ vector<string> myArray (Array, Array+(sizeof(Array)/sizeof(string)));
+ return myArray;
+ }
+ catch(exception& e) {
+ m->errorOut(e, "GetSeqsCommand", "getRequiredParameters");
+ exit(1);
+ }
+}
+//**********************************************************************************************************************
+vector<string> GetSeqsCommand::getRequiredFiles(){
+ try {
+ vector<string> myArray;
+ return myArray;
+ }
+ catch(exception& e) {
+ m->errorOut(e, "GetSeqsCommand", "getRequiredFiles");
+ exit(1);
+ }
+}
+//**********************************************************************************************************************
GetSeqsCommand::GetSeqsCommand(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 {
//valid paramters for this command
- string Array[] = {"fasta","name", "group", "alignreport", "accnos", "list","taxonomy","outputdir","inputdir"};
+ string Array[] = {"fasta","name", "group", "alignreport", "qfile", "accnos", "accnos2","dups", "list","taxonomy","outputdir","inputdir"};
vector<string> myArray (Array, Array+(sizeof(Array)/sizeof(string)));
OptionParser parser(option);
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["accnosreport"] = 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("accnos2");
+ //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["accnos2"] = 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; }
+ }
}
if (accnosfile == "not open") { abort = true; }
else if (accnosfile == "not found") { accnosfile = ""; m->mothurOut("You must provide an accnos file."); m->mothurOutEndLine(); abort = true; }
+ if (accnosfile2 == "not found") { accnosfile2 = ""; }
+
fastafile = validParameter.validFile(parameters, "fasta", true);
if (fastafile == "not open") { abort = true; }
else if (fastafile == "not found") { fastafile = ""; }
if (taxfile == "not open") { abort = true; }
else if (taxfile == "not found") { taxfile = ""; }
+ qualfile = validParameter.validFile(parameters, "qfile", true);
+ if (qualfile == "not open") { abort = true; }
+ else if (qualfile == "not found") { qualfile = ""; }
+
string usedDups = "true";
string temp = validParameter.validFile(parameters, "dups", false); if (temp == "not found") { temp = "false"; usedDups = ""; }
- dups = isTrue(temp);
+ dups = m->isTrue(temp);
- if ((fastafile == "") && (namefile == "") && (groupfile == "") && (alignfile == "") && (listfile == "") && (taxfile == "")) { m->mothurOut("You must provide one of the following: fasta, name, group, alignreport, taxonomy or listfile."); m->mothurOutEndLine(); abort = true; }
+ if ((fastafile == "") && (namefile == "") && (groupfile == "") && (alignfile == "") && (listfile == "") && (taxfile == "") && (qualfile == "") && (accnosfile2 == "")) { m->mothurOut("You must provide one of the following: fasta, name, group, alignreport, taxonomy, quality or listfile."); m->mothurOutEndLine(); abort = true; }
if ((usedDups != "") && (namefile == "")) { m->mothurOut("You may only use dups with the name option."); m->mothurOutEndLine(); abort = true; }
void GetSeqsCommand::help(){
try {
- m->mothurOut("The get.seqs command reads an .accnos file and any of the following file types: fasta, name, group, list, taxonomy or alignreport file.\n");
+ m->mothurOut("The get.seqs command reads an .accnos file and any of the following file types: fasta, name, group, list, taxonomy, quality or alignreport file.\n");
m->mothurOut("It outputs a file containing only the sequences in the .accnos file.\n");
- m->mothurOut("The get.seqs command parameters are accnos, fasta, name, group, list, taxonomy, alignreport and dups. You must provide accnos and at least one of the other parameters.\n");
+ m->mothurOut("The get.seqs command parameters are accnos, fasta, name, group, list, taxonomy, qfile, alignreport and dups. You must provide accnos and at least one of the other parameters.\n");
m->mothurOut("The dups parameter allows you to add the entire line from a name file if you add any name from the line. default=false. \n");
m->mothurOut("The get.seqs command should be in the following format: get.seqs(accnos=yourAccnos, fasta=yourFasta).\n");
m->mothurOut("Example get.seqs(accnos=amazon.accnos, fasta=amazon.fasta).\n");
int GetSeqsCommand::execute(){
try {
- if (abort == true) { return 0; }
+ if (abort == true) { if (calledHelp) { return 0; } return 2; }
//get names you want to keep
readAccnos();
if (m->control_pressed) { return 0; }
//read through the correct file and output lines you want to keep
- if (namefile != "") { readName(); }
- if (fastafile != "") { readFasta(); }
- if (groupfile != "") { readGroup(); }
- if (alignfile != "") { readAlign(); }
- if (listfile != "") { readList(); }
- if (taxfile != "") { readTax(); }
+ if (namefile != "") { readName(); }
+ if (fastafile != "") { readFasta(); }
+ if (groupfile != "") { readGroup(); }
+ if (alignfile != "") { readAlign(); }
+ if (listfile != "") { readList(); }
+ if (taxfile != "") { readTax(); }
+ if (qualfile != "") { readQual(); }
+ if (accnosfile2 != "") { compareAccnos(); }
- if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; }
+ if (m->control_pressed) { outputTypes.clear(); for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; }
+
+ m->mothurOut("Selected " + toString(names.size()) + " sequences."); m->mothurOutEndLine();
if (outputNames.size() != 0) {
m->mothurOutEndLine();
//**********************************************************************************************************************
int GetSeqsCommand::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); }
+ string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(fastafile)) + "pick" + m->getExtension(fastafile);
ofstream out;
- openOutputFile(outputFileName, out);
+ m->openOutputFile(outputFileName, out);
ifstream in;
- openInputFile(fastafile, in);
+ m->openInputFile(fastafile, in);
string name;
bool wroteSomething = false;
currSeq.printSequence(out);
}
}
- gobble(in);
+ m->gobble(in);
}
in.close();
out.close();
+
if (wroteSomething == false) { m->mothurOut("Your file does not contain any sequence from the .accnos file."); m->mothurOutEndLine(); }
- outputNames.push_back(outputFileName);
+ outputNames.push_back(outputFileName); outputTypes["fasta"].push_back(outputFileName);
return 0;
}
}
//**********************************************************************************************************************
+int GetSeqsCommand::readQual(){
+ try {
+ string thisOutputDir = outputDir;
+ if (outputDir == "") { thisOutputDir += m->hasPath(qualfile); }
+ string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(qualfile)) + "pick" + m->getExtension(qualfile);
+ ofstream out;
+ m->openOutputFile(outputFileName, out);
+
+
+ ifstream in;
+ m->openInputFile(qualfile, in);
+ string name;
+
+ bool wroteSomething = false;
+
+
+ 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 (names.count(saveName) != 0) {
+ wroteSomething = true;
+
+ out << name << endl << scores;
+ }
+
+ m->gobble(in);
+ }
+ in.close();
+ out.close();
+
+
+ if (wroteSomething == false) { m->mothurOut("Your file does not contain any sequence from the .accnos file."); m->mothurOutEndLine(); }
+ outputNames.push_back(outputFileName); outputTypes["qfile"].push_back(outputFileName);
+
+ return 0;
+
+ }
+ catch(exception& e) {
+ m->errorOut(e, "GetSeqsCommand", "readQual");
+ exit(1);
+ }
+}
+//**********************************************************************************************************************
int GetSeqsCommand::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); }
+ string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(listfile)) + "pick" + m->getExtension(listfile);
ofstream out;
- openOutputFile(outputFileName, out);
+ m->openOutputFile(outputFileName, out);
ifstream in;
- openInputFile(listfile, in);
+ m->openInputFile(listfile, in);
bool wroteSomething = false;
newList.print(out);
}
- gobble(in);
+ m->gobble(in);
}
in.close();
out.close();
if (wroteSomething == false) { m->mothurOut("Your file does not contain any sequence from the .accnos file."); m->mothurOutEndLine(); }
- outputNames.push_back(outputFileName);
+ outputNames.push_back(outputFileName); outputTypes["list"].push_back(outputFileName);
return 0;
//**********************************************************************************************************************
int GetSeqsCommand::readName(){
try {
- if (outputDir == "") { outputDir += hasPath(namefile); }
- string outputFileName = outputDir + getRootName(getSimpleName(namefile)) + "pick" + getExtension(namefile);
+ string thisOutputDir = outputDir;
+ if (outputDir == "") { thisOutputDir += m->hasPath(namefile); }
+ string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(namefile)) + "pick" + m->getExtension(namefile);
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;
}
}
}
- gobble(in);
+ m->gobble(in);
}
in.close();
out.close();
if (wroteSomething == false) { m->mothurOut("Your file does not contain any sequence from the .accnos file."); m->mothurOutEndLine(); }
- outputNames.push_back(outputFileName);
+ outputNames.push_back(outputFileName); outputTypes["name"].push_back(outputFileName);
return 0;
//**********************************************************************************************************************
int GetSeqsCommand::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); }
+ string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(groupfile)) + "pick" + m->getExtension(groupfile);
ofstream out;
- openOutputFile(outputFileName, out);
+ m->openOutputFile(outputFileName, out);
ifstream in;
- openInputFile(groupfile, in);
+ m->openInputFile(groupfile, in);
string name, group;
bool wroteSomething = false;
out << name << '\t' << group << endl;
}
- gobble(in);
+ m->gobble(in);
}
in.close();
out.close();
if (wroteSomething == false) { m->mothurOut("Your file does not contain any sequence from the .accnos file."); m->mothurOutEndLine(); }
- outputNames.push_back(outputFileName);
+ outputNames.push_back(outputFileName); outputTypes["group"].push_back(outputFileName);
return 0;
//**********************************************************************************************************************
int GetSeqsCommand::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); }
+ string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(taxfile)) + "pick" + m->getExtension(taxfile);
ofstream out;
- openOutputFile(outputFileName, out);
+ m->openOutputFile(outputFileName, out);
ifstream in;
- openInputFile(taxfile, in);
+ m->openInputFile(taxfile, in);
string name, tax;
bool wroteSomething = false;
out << name << '\t' << tax << endl;
}
- gobble(in);
+ m->gobble(in);
}
in.close();
out.close();
if (wroteSomething == false) { m->mothurOut("Your file does not contain any sequence from the .accnos file."); m->mothurOutEndLine(); }
- outputNames.push_back(outputFileName);
+ outputNames.push_back(outputFileName); outputTypes["taxonomy"].push_back(outputFileName);
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 GetSeqsCommand::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); }
+ string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(alignfile)) + "pick.align.report";
ofstream out;
- openOutputFile(outputFileName, out);
+ m->openOutputFile(outputFileName, out);
ifstream in;
- openInputFile(alignfile, in);
+ m->openInputFile(alignfile, in);
string name, junk;
bool wroteSomething = false;
}
}
- gobble(in);
+ m->gobble(in);
}
in.close();
out.close();
if (wroteSomething == false) { m->mothurOut("Your file does not contain any sequence from the .accnos file."); m->mothurOutEndLine(); }
- outputNames.push_back(outputFileName);
+ outputNames.push_back(outputFileName); outputTypes["alignreport"].push_back(outputFileName);
return 0;
try {
ifstream in;
- openInputFile(accnosfile, in);
+ m->openInputFile(accnosfile, in);
string name;
while(!in.eof()){
names.insert(name);
- gobble(in);
+ m->gobble(in);
}
in.close();
exit(1);
}
}
+//**********************************************************************************************************************
+
+int GetSeqsCommand::compareAccnos(){
+ try {
+
+ string thisOutputDir = outputDir;
+ if (outputDir == "") { thisOutputDir += m->hasPath(accnosfile); }
+ string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(accnosfile)) + "accnos.report";
+ ofstream out;
+ m->openOutputFile(outputFileName, out);
+
+ ifstream in;
+ m->openInputFile(accnosfile2, in);
+ string name;
+
+ set<string> namesAccnos2;
+ set<string> namesDups;
+ set<string> namesAccnos = names;
+
+ map<string, int> nameCount;
+
+ if (namefile != "") {
+ ifstream inName;
+ m->openInputFile(namefile, inName);
+
+
+ while(!inName.eof()){
+
+ if (m->control_pressed) { inName.close(); return 0; }
+
+ string thisname, repnames;
+
+ inName >> thisname; m->gobble(inName); //read from first column
+ inName >> repnames; //read from second column
+
+ int num = m->getNumNames(repnames);
+ nameCount[thisname] = num;
+
+ m->gobble(inName);
+ }
+ inName.close();
+ }
+
+ while(!in.eof()){
+ in >> name;
+
+ if (namesAccnos.count(name) == 0){ //name unique to accnos2
+ namesAccnos2.insert(name);
+ }else { //you are in both so erase
+ namesAccnos.erase(name);
+ namesDups.insert(name);
+ }
+
+ m->gobble(in);
+ }
+ in.close();
+
+ out << "Names in both files : " + toString(namesDups.size()) << endl;
+ m->mothurOut("Names in both files : " + toString(namesDups.size())); m->mothurOutEndLine();
+
+ for (set<string>::iterator it = namesDups.begin(); it != namesDups.end(); it++) {
+ out << (*it);
+ if (namefile != "") { out << '\t' << nameCount[(*it)]; }
+ out << endl;
+ }
+
+ out << "Names unique to " + accnosfile + " : " + toString(namesAccnos.size()) << endl;
+ m->mothurOut("Names unique to " + accnosfile + " : " + toString(namesAccnos.size())); m->mothurOutEndLine();
+
+ for (set<string>::iterator it = namesAccnos.begin(); it != namesAccnos.end(); it++) {
+ out << (*it);
+ if (namefile != "") { out << '\t' << nameCount[(*it)]; }
+ out << endl;
+ }
+
+ out << "Names unique to " + accnosfile2 + " : " + toString(namesAccnos2.size()) << endl;
+ m->mothurOut("Names unique to " + accnosfile2 + " : " + toString(namesAccnos2.size())); m->mothurOutEndLine();
+
+ for (set<string>::iterator it = namesAccnos2.begin(); it != namesAccnos2.end(); it++) {
+ out << (*it);
+ if (namefile != "") { out << '\t' << nameCount[(*it)]; }
+ out << endl;
+ }
+
+ out.close();
+
+ outputNames.push_back(outputFileName); outputTypes["accnosreport"].push_back(outputFileName);
+
+ return 0;
+
+ }
+ catch(exception& e) {
+ m->errorOut(e, "GetSeqsCommand", "readAccnos");
+ exit(1);
+ }
+}
+
//**********************************************************************************************************************