else {
//valid paramters for this command
- string Array[] = {"fasta","name", "group", "alignreport", "accnos", "list","outputdir","inputdir"};
+ string Array[] = {"fasta","name", "group", "alignreport", "accnos", "list","taxonomy","outputdir","inputdir"};
vector<string> myArray (Array, Array+(sizeof(Array)/sizeof(string)));
OptionParser parser(option);
//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; }
+ }
}
if (listfile == "not open") { abort = true; }
else if (listfile == "not found") { listfile = ""; }
- if ((fastafile == "") && (namefile == "") && (groupfile == "") && (alignfile == "") && (listfile == "")) { m->mothurOut("You must provide one of the following: fasta, name, group, alignreport or listfile."); m->mothurOutEndLine(); abort = true; }
-
- int okay = 2;
- if (outputDir != "") { okay++; }
- if (inputDir != "") { okay++; }
+ taxfile = validParameter.validFile(parameters, "taxonomy", true);
+ if (taxfile == "not open") { abort = true; }
+ else if (taxfile == "not found") { taxfile = ""; }
+
- if (parameters.size() > okay) { m->mothurOut("You may only enter one of the following: fasta, name, group, alignreport or listfile."); m->mothurOutEndLine(); abort = true; }
+ 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; }
}
}
void GetSeqsCommand::help(){
try {
- m->mothurOut("The get.seqs command reads an .accnos file and one of the following file types: fasta, name, group, list 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 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 and alignreport. You must provide accnos and one of the other parameters.\n");
+ m->mothurOut("The get.seqs command parameters are accnos, fasta, name, group, list, taxonomy and alignreport. You must provide accnos and at least one of the other parameters.\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");
m->mothurOut("Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFasta).\n\n");
//read through the correct file and output lines you want to keep
if (fastafile != "") { readFasta(); }
- else if (namefile != "") { readName(); }
- else if (groupfile != "") { readGroup(); }
- else if (alignfile != "") { readAlign(); }
- else if (listfile != "") { readList(); }
+ if (namefile != "") { readName(); }
+ if (groupfile != "") { readGroup(); }
+ if (alignfile != "") { readAlign(); }
+ if (listfile != "") { readList(); }
+ if (taxfile != "") { readTax(); }
- if (m->control_pressed) { return 0; }
+ 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();
wroteSomething = true;
currSeq.printSequence(out);
-
- names.erase(name);
}
}
gobble(in);
wroteSomething = true;
out << name << '\t' << group << endl;
-
- names.erase(name);
}
gobble(in);
exit(1);
}
}
+//**********************************************************************************************************************
+int GetSeqsCommand::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) == 1) {
+ wroteSomething = true;
+
+ out << name << '\t' << tax << endl;
+ }
+
+ gobble(in);
+ }
+ in.close();
+ out.close();
+
+ if (wroteSomething == false) {
+ m->mothurOut("Your file does not contain any sequence from the .accnos file."); m->mothurOutEndLine();
+ remove(outputFileName.c_str());
+ }else { outputNames.push_back(outputFileName); }
+
+ return 0;
+
+ }
+ catch(exception& e) {
+ m->errorOut(e, "GetSeqsCommand", "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
int GetSeqsCommand::readAlign(){
}
out << endl;
- names.erase(name);
-
}else {//still read just don't do anything with it
//read rest
for (int i = 0; i < 15; i++) {
private:
set<string> names;
vector<string> outputNames;
- string accnosfile, fastafile, namefile, groupfile, alignfile, listfile, outputDir;
+ string accnosfile, fastafile, namefile, groupfile, alignfile, listfile, taxfile, outputDir;
bool abort;
int readFasta();
int readAlign();
int readAccnos();
int readList();
+ int readTax();
};
else {
//valid paramters for this command
- string Array[] = {"fasta","name", "group", "alignreport","list","outputdir","inputdir"};
+ string Array[] = {"fasta","name", "group", "alignreport","list","taxonomy","outputdir","inputdir"};
vector<string> myArray (Array, Array+(sizeof(Array)/sizeof(string)));
OptionParser parser(option);
//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
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 = ""; }
- if ((fastafile == "") && (namefile == "") && (listfile == "") && (groupfile == "") && (alignfile == "")) { m->mothurOut("You must provide a file."); m->mothurOutEndLine(); abort = true; }
+ if ((fastafile == "") && (namefile == "") && (listfile == "") && (groupfile == "") && (alignfile == "") && (taxfile == "")) { m->mothurOut("You must provide a file."); m->mothurOutEndLine(); abort = true; }
int okay = 1;
if (outputDir != "") { okay++; }
void ListSeqsCommand::help(){
try {
- m->mothurOut("The list.seqs command reads a fasta, name, group, list or alignreport file and outputs a .accnos file containing sequence names.\n");
- m->mothurOut("The list.seqs command parameters are fasta, name, group and alignreport. You must provide one of these parameters.\n");
+ m->mothurOut("The list.seqs command reads a fasta, name, group, list, taxonomy or alignreport file and outputs a .accnos file containing sequence names.\n");
+ m->mothurOut("The list.seqs command parameters are fasta, name, group, list, taxonomy and alignreport. You must provide one of these parameters.\n");
m->mothurOut("The list.seqs command should be in the following format: list.seqs(fasta=yourFasta).\n");
m->mothurOut("Example list.seqs(fasta=amazon.fasta).\n");
m->mothurOut("Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFasta).\n\n");
else if (groupfile != "") { inputFileName = groupfile; readGroup(); }
else if (alignfile != "") { inputFileName = alignfile; readAlign(); }
else if (listfile != "") { inputFileName = listfile; readList(); }
+ else if (taxfile != "") { inputFileName = taxfile; readTax(); }
if (m->control_pressed) { return 0; }
}
}
//**********************************************************************************************************************
+int ListSeqsCommand::readTax(){
+ try {
+
+ ifstream in;
+ openInputFile(taxfile, in);
+ string name, firstCol, secondCol;
+
+ while(!in.eof()){
+
+ if (m->control_pressed) { in.close(); return 0; }
+
+ in >> firstCol;
+ in >> secondCol;
+
+ names.push_back(firstCol);
+
+ gobble(in);
+ }
+ in.close();
+
+ return 0;
+
+ }
+ catch(exception& e) {
+ m->errorOut(e, "ListSeqsCommand", "readTax");
+ exit(1);
+ }
+}
+//**********************************************************************************************************************
private:
vector<string> names;
- string fastafile, namefile, groupfile, alignfile, inputFileName, outputDir, listfile;
+ string fastafile, namefile, groupfile, alignfile, inputFileName, outputDir, listfile, taxfile;
bool abort;
int readFasta();
int readGroup();
int readAlign();
int readList();
+ int readTax();
};
else {
//valid paramters for this command
- string Array[] = {"fasta","name", "group", "alignreport", "accnos", "list","outputdir","inputdir", "dups" };
+ string Array[] = {"fasta","name", "group", "alignreport", "accnos", "list","taxonomy","outputdir","inputdir", "dups" };
vector<string> myArray (Array, Array+(sizeof(Array)/sizeof(string)));
OptionParser parser(option);
//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; }
+ }
}
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 ((fastafile == "") && (namefile == "") && (groupfile == "") && (alignfile == "") && (listfile == "")) { m->mothurOut("You must provide one of the following: fasta, name, group, alignreport or list."); m->mothurOutEndLine(); abort = true; }
-
- //int okay = 2;
- //if (outputDir != "") { okay++; }
- //if (usedDups != "") { okay++; }
+ 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; }
-
- //if (parameters.size() > okay) { m->mothurOut("You may only enter one of the following: fasta, name, group, 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; }
}
}
void RemoveSeqsCommand::help(){
try {
- m->mothurOut("The remove.seqs command reads an .accnos file and one of the following file types: fasta, name, group, list or alignreport file.\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, alignreport and dups. You must provide accnos and one of the file parameters.\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");
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; }
wroteSomething = true;
currSeq.printSequence(out);
- }//else { names.erase(name); }
+ }
}
gobble(in);
}
if (names.count(name) == 0) {
wroteSomething = true;
out << name << '\t' << group << endl;
- }//else { names.erase(name); }
+ }
gobble(in);
}
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();
+ remove(outputFileName.c_str());
+ }else { 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
int RemoveSeqsCommand::readAlign(){
out << endl;
}else {//still read just don't do anything with it
- //names.erase(name);
//read rest
for (int i = 0; i < 15; i++) {
private:
set<string> names;
- string accnosfile, fastafile, namefile, groupfile, alignfile, listfile, outputDir;
+ string accnosfile, fastafile, namefile, groupfile, alignfile, listfile, taxfile, outputDir;
bool abort, dups;
vector<string> outputNames;
int readAlign();
void readAccnos();
int readList();
+ int readTax();
};