#include "removeseqscommand.h"
#include "sequence.hpp"
+#include "listvector.hpp"
//**********************************************************************************************************************
-RemoveSeqsCommand::RemoveSeqsCommand(string option){
+RemoveSeqsCommand::RemoveSeqsCommand(string option) {
try {
abort = false;
else {
//valid paramters for this command
- string Array[] = {"fasta","name", "group", "alignreport", "accnos" };
+ string Array[] = {"fasta","name", "group", "alignreport", "accnos", "list","taxonomy","outputdir","inputdir", "dups" };
vector<string> myArray (Array, Array+(sizeof(Array)/sizeof(string)));
OptionParser parser(option);
map<string,string> parameters = parser.getParameters();
ValidParameters validParameter;
+ map<string,string>::iterator it;
//check to make sure all parameters are valid for command
- for (map<string,string>::iterator it = parameters.begin(); it != parameters.end(); it++) {
+ for (it = parameters.begin(); it != parameters.end(); it++) {
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 = ""; }
+
+ //if the user changes the input directory command factory will send this info to us in the output parameter
+ string inputDir = validParameter.validFile(parameters, "inputdir", false);
+ if (inputDir == "not found"){ inputDir = ""; }
+ else {
+ string path;
+ it = parameters.find("alignreport");
+ //user has given a template file
+ if(it != parameters.end()){
+ path = 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);
+ //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);
+ //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);
+ //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);
+ //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);
+ //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);
+ //if the user has not given a path then, add inputdir. else leave path alone.
+ if (path == "") { parameters["taxonomy"] = 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 = ""; mothurOut("You must provide an accnos file."); mothurOutEndLine(); abort = true; }
+ else if (accnosfile == "not found") { accnosfile = ""; m->mothurOut("You must provide an accnos file."); m->mothurOutEndLine(); abort = true; }
fastafile = validParameter.validFile(parameters, "fasta", true);
if (fastafile == "not open") { abort = true; }
if (alignfile == "not open") { abort = true; }
else if (alignfile == "not found") { alignfile = ""; }
- if ((fastafile == "") && (namefile == "") && (groupfile == "") && (alignfile == "")) { mothurOut("You must provide one of the following: fasta, name, group, alignreport."); mothurOutEndLine(); abort = true; }
+ listfile = validParameter.validFile(parameters, "list", true);
+ if (listfile == "not open") { abort = true; }
+ else if (listfile == "not found") { 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);
- if (parameters.size() > 2) { mothurOut("You may only enter one of the following: fasta, name, group, alignreport."); mothurOutEndLine(); abort = true; }
+ 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; }
+
+ if ((usedDups != "") && (namefile == "")) { m->mothurOut("You may only use dups with the name option."); m->mothurOutEndLine(); abort = true; }
}
}
catch(exception& e) {
- errorOut(e, "RemoveSeqsCommand", "RemoveSeqsCommand");
+ m->errorOut(e, "RemoveSeqsCommand", "RemoveSeqsCommand");
exit(1);
}
}
void RemoveSeqsCommand::help(){
try {
- mothurOut("The remove.seqs command reads an .accnos file and one of the following file types: fasta, name, group or alignreport file.\n");
- mothurOut("It outputs a file containing the sequences NOT in the .accnos file.\n");
- mothurOut("The remove.seqs command parameters are accnos, fasta, name, group and alignreport. You must provide accnos and one of the other parameters.\n");
- mothurOut("The remove.seqs command should be in the following format: remove.seqs(accnos=yourAccnos, fasta=yourFasta).\n");
- mothurOut("Example remove.seqs(accnos=amazon.accnos, fasta=amazon.fasta).\n");
- mothurOut("Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFasta).\n\n");
+ 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. \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) {
- errorOut(e, "RemoveSeqsCommand", "help");
+ m->errorOut(e, "RemoveSeqsCommand", "help");
exit(1);
}
}
//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(); }
- else if (namefile != "") { readName(); }
- else if (groupfile != "") { readGroup(); }
- else if (alignfile != "") { readAlign(); }
+ if (groupfile != "") { readGroup(); }
+ if (alignfile != "") { readAlign(); }
+ if (listfile != "") { readList(); }
+ if (taxfile != "") { readTax(); }
+
+ if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } 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();
+ }
return 0;
}
catch(exception& e) {
- errorOut(e, "RemoveSeqsCommand", "execute");
+ m->errorOut(e, "RemoveSeqsCommand", "execute");
exit(1);
}
}
//**********************************************************************************************************************
-void RemoveSeqsCommand::readFasta(){
+int RemoveSeqsCommand::readFasta(){
try {
- string outputFileName = getRootName(fastafile) + "pick" + getExtension(fastafile);
+ if (outputDir == "") { outputDir += hasPath(fastafile); }
+ string outputFileName = outputDir + getRootName(getSimpleName(fastafile)) + "pick" + getExtension(fastafile);
ofstream out;
openOutputFile(outputFileName, out);
bool wroteSomething = false;
while(!in.eof()){
+ if (m->control_pressed) { in.close(); out.close(); remove(outputFileName.c_str()); return 0; }
+
Sequence currSeq(in);
name = currSeq.getName();
wroteSomething = true;
currSeq.printSequence(out);
- }else { names.erase(name); }
+ }
}
gobble(in);
}
in.close();
out.close();
- if (wroteSomething == false) {
- mothurOut("Your file contains only sequences from the .accnos file."); mothurOutEndLine();
- remove(outputFileName.c_str());
+ if (wroteSomething == false) { m->mothurOut("Your file contains only sequences from the .accnos file."); m->mothurOutEndLine(); }
+ outputNames.push_back(outputFileName);
+
+ return 0;
+
+ }
+ catch(exception& e) {
+ m->errorOut(e, "RemoveSeqsCommand", "readFasta");
+ exit(1);
+ }
+}
+//**********************************************************************************************************************
+int RemoveSeqsCommand::readList(){
+ try {
+ if (outputDir == "") { outputDir += hasPath(listfile); }
+ string outputFileName = outputDir + getRootName(getSimpleName(listfile)) + "pick" + getExtension(listfile);
+ ofstream out;
+ openOutputFile(outputFileName, out);
+
+ ifstream in;
+ openInputFile(listfile, in);
+
+ bool wroteSomething = false;
+
+ while(!in.eof()){
+ //read in list vector
+ ListVector list(in);
+
+ //make a new list vector
+ ListVector newList;
+ newList.setLabel(list.getLabel());
+
+ //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; }
+
+ //parse out names that are in accnos file
+ string binnames = list.get(i);
+
+ string newNames = "";
+ while (binnames.find_first_of(',') != -1) {
+ string name = binnames.substr(0,binnames.find_first_of(','));
+ binnames = binnames.substr(binnames.find_first_of(',')+1, binnames.length());
+
+ //if that name is in the .accnos file, add it
+ if (names.count(name) == 0) { newNames += name + ","; }
+ }
+
+ //get last name
+ if (names.count(binnames) == 0) { newNames += binnames + ","; }
+
+ //if there are names in this bin add to new list
+ if (newNames != "") {
+ newNames = newNames.substr(0, newNames.length()-1); //rip off extra comma
+ newList.push_back(newNames);
+ }
+ }
+
+ //print new listvector
+ if (newList.getNumBins() != 0) {
+ wroteSomething = true;
+ newList.print(out);
+ }
+
+ 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);
+
+ return 0;
}
catch(exception& e) {
- errorOut(e, "RemoveSeqsCommand", "readFasta");
+ m->errorOut(e, "RemoveSeqsCommand", "readList");
exit(1);
}
}
-
//**********************************************************************************************************************
-void RemoveSeqsCommand::readName(){
+int RemoveSeqsCommand::readName(){
try {
-
- string outputFileName = getRootName(namefile) + "pick" + getExtension(namefile);
+ if (outputDir == "") { outputDir += hasPath(namefile); }
+ string outputFileName = outputDir + getRootName(getSimpleName(namefile)) + "pick" + getExtension(namefile);
ofstream out;
openOutputFile(outputFileName, out);
bool wroteSomething = false;
while(!in.eof()){
+ if (m->control_pressed) { in.close(); out.close(); remove(outputFileName.c_str()); return 0; }
in >> firstCol;
in >> secondCol;
}
}
- //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;
-
- out << firstCol << '\t';
-
- //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] << ','; }
- out << validSecond[validSecond.size()-1] << endl;
-
- //make first name in set you come to first column and then add the remaining names to second column
+ 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]); }
}else {
-
- //you want part of this row
- if (validSecond.size() != 0) {
-
+ //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;
- out << validSecond[0] << '\t';
-
+ out << firstCol << '\t';
+
//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] << ','; }
out << validSecond[validSecond.size()-1] << endl;
+
+ //make first name in set you come to first column and then add the remaining names to second column
+ }else {
+
+ //you want part of this row
+ if (validSecond.size() != 0) {
+
+ wroteSomething = true;
+
+ out << validSecond[0] << '\t';
+
+ //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] << ','; }
+ out << validSecond[validSecond.size()-1] << endl;
+ }
}
}
-
gobble(in);
}
in.close();
out.close();
-
- if (wroteSomething == false) {
- mothurOut("Your file contains only sequences from the .accnos file."); mothurOutEndLine();
- remove(outputFileName.c_str());
- }
-
+
+ if (wroteSomething == false) { m->mothurOut("Your file contains only sequences from the .accnos file."); m->mothurOutEndLine(); }
+ outputNames.push_back(outputFileName);
+
+ return 0;
}
catch(exception& e) {
- errorOut(e, "RemoveSeqsCommand", "readName");
+ m->errorOut(e, "RemoveSeqsCommand", "readName");
exit(1);
}
}
//**********************************************************************************************************************
-void RemoveSeqsCommand::readGroup(){
+int RemoveSeqsCommand::readGroup(){
try {
-
- string outputFileName = getRootName(groupfile) + "pick" + getExtension(groupfile);
+ if (outputDir == "") { outputDir += hasPath(groupfile); }
+ string outputFileName = outputDir + getRootName(getSimpleName(groupfile)) + "pick" + getExtension(groupfile);
ofstream out;
openOutputFile(outputFileName, out);
bool wroteSomething = false;
while(!in.eof()){
-
+ if (m->control_pressed) { in.close(); out.close(); remove(outputFileName.c_str()); 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 { names.erase(name); }
+ }
gobble(in);
}
in.close();
out.close();
- if (wroteSomething == false) {
- mothurOut("Your file contains only sequences from the .accnos file."); mothurOutEndLine();
- remove(outputFileName.c_str());
- }
-
+ if (wroteSomething == false) { m->mothurOut("Your file contains only sequences from the .accnos file."); m->mothurOutEndLine(); }
+ outputNames.push_back(outputFileName);
+
+ return 0;
}
catch(exception& e) {
- errorOut(e, "RemoveSeqsCommand", "readGroup");
+ m->errorOut(e, "RemoveSeqsCommand", "readGroup");
exit(1);
}
}
+//**********************************************************************************************************************
+int RemoveSeqsCommand::readTax(){
+ try {
+ if (outputDir == "") { outputDir += hasPath(taxfile); }
+ string outputFileName = outputDir + getRootName(getSimpleName(taxfile)) + "pick" + getExtension(taxfile);
+ ofstream out;
+ openOutputFile(outputFileName, out);
+ ifstream in;
+ openInputFile(taxfile, in);
+ string name, tax;
+
+ bool wroteSomething = false;
+
+ while(!in.eof()){
+ if (m->control_pressed) { in.close(); out.close(); remove(outputFileName.c_str()); return 0; }
+
+ in >> name; //read from first column
+ in >> tax; //read from second column
+
+ //if this name is in the accnos file
+ if (names.count(name) == 0) {
+ wroteSomething = true;
+ out << name << '\t' << tax << endl;
+ }
+
+ 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);
+
+ return 0;
+ }
+ catch(exception& e) {
+ m->errorOut(e, "RemoveSeqsCommand", "readTax");
+ exit(1);
+ }
+}
//**********************************************************************************************************************
//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
-void RemoveSeqsCommand::readAlign(){
+int RemoveSeqsCommand::readAlign(){
try {
- string outputFileName = getRootName(getRootName(alignfile)) + "pick.align.report";
+ if (outputDir == "") { outputDir += hasPath(alignfile); }
+ string outputFileName = outputDir + getRootName(getSimpleName(alignfile)) + "pick.align.report";
ofstream out;
openOutputFile(outputFileName, out);
out << endl;
while(!in.eof()){
-
+ if (m->control_pressed) { in.close(); out.close(); remove(outputFileName.c_str()); return 0; }
+
in >> name; //read from first column
//if this name is in the accnos file
out << endl;
}else {//still read just don't do anything with it
- names.erase(name);
//read rest
for (int i = 0; i < 15; i++) {
in.close();
out.close();
- if (wroteSomething == false) {
- mothurOut("Your file contains only sequences from the .accnos file."); mothurOutEndLine();
- remove(outputFileName.c_str());
- }
+ if (wroteSomething == false) { m->mothurOut("Your file contains only sequences from the .accnos file."); m->mothurOutEndLine(); }
+ outputNames.push_back(outputFileName);
+
+ return 0;
}
catch(exception& e) {
- errorOut(e, "RemoveSeqsCommand", "readAlign");
+ m->errorOut(e, "RemoveSeqsCommand", "readAlign");
exit(1);
}
}
}
catch(exception& e) {
- errorOut(e, "RemoveSeqsCommand", "readAccnos");
+ m->errorOut(e, "RemoveSeqsCommand", "readAccnos");
exit(1);
}
}