#include "listseqscommand.h"
#include "sequence.hpp"
#include "listvector.hpp"
+#include "counttable.h"
//**********************************************************************************************************************
vector<string> ListSeqsCommand::setParameters(){
try {
- CommandParameter pfasta("fasta", "InputTypes", "", "", "FNGLT", "FNGLT", "none",false,false); parameters.push_back(pfasta);
- CommandParameter pname("name", "InputTypes", "", "", "FNGLT", "FNGLT", "none",false,false); parameters.push_back(pname);
- CommandParameter pgroup("group", "InputTypes", "", "", "FNGLT", "FNGLT", "none",false,false); parameters.push_back(pgroup);
- CommandParameter plist("list", "InputTypes", "", "", "FNGLT", "FNGLT", "none",false,false); parameters.push_back(plist);
- CommandParameter ptaxonomy("taxonomy", "InputTypes", "", "", "FNGLT", "FNGLT", "none",false,false); parameters.push_back(ptaxonomy);
- CommandParameter palignreport("alignreport", "InputTypes", "", "", "FNGLT", "FNGLT", "none",false,false); parameters.push_back(palignreport);
- CommandParameter pinputdir("inputdir", "String", "", "", "", "", "",false,false); parameters.push_back(pinputdir);
- CommandParameter poutputdir("outputdir", "String", "", "", "", "", "",false,false); parameters.push_back(poutputdir);
+ CommandParameter pfastq("fastq", "InputTypes", "", "", "FNGLT", "FNGLT", "none","accnos",false,false,true); parameters.push_back(pfastq);
+ CommandParameter pfasta("fasta", "InputTypes", "", "", "FNGLT", "FNGLT", "none","accnos",false,false,true); parameters.push_back(pfasta);
+ CommandParameter pname("name", "InputTypes", "", "", "FNGLT", "FNGLT", "none","accnos",false,false,true); parameters.push_back(pname);
+ CommandParameter pcount("count", "InputTypes", "", "", "FNGLT", "FNGLT", "none","accnos",false,false,true); parameters.push_back(pcount);
+ CommandParameter pgroup("group", "InputTypes", "", "", "FNGLT", "FNGLT", "none","accnos",false,false,true); parameters.push_back(pgroup);
+ CommandParameter plist("list", "InputTypes", "", "", "FNGLT", "FNGLT", "none","accnos",false,false,true); parameters.push_back(plist);
+ CommandParameter ptaxonomy("taxonomy", "InputTypes", "", "", "FNGLT", "FNGLT", "none","accnos",false,false,true); parameters.push_back(ptaxonomy);
+ CommandParameter palignreport("alignreport", "InputTypes", "", "", "FNGLT", "FNGLT", "none","accnos",false,false); parameters.push_back(palignreport);
+ 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 ListSeqsCommand::getHelpString(){
try {
string helpString = "";
- helpString += "The list.seqs command reads a fasta, name, group, list, taxonomy or alignreport file and outputs a .accnos file containing sequence names.\n";
- helpString += "The list.seqs command parameters are fasta, name, group, list, taxonomy and alignreport. You must provide one of these parameters.\n";
+ helpString += "The list.seqs command reads a fasta, name, group, count, list, taxonomy, fastq or alignreport file and outputs a .accnos file containing sequence names.\n";
+ helpString += "The list.seqs command parameters are fasta, name, group, count, list, taxonomy, fastq and alignreport. You must provide one of these parameters.\n";
helpString += "The list.seqs command should be in the following format: list.seqs(fasta=yourFasta).\n";
helpString += "Example list.seqs(fasta=amazon.fasta).\n";
helpString += "Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFasta).\n";
}
}
//**********************************************************************************************************************
-string ListSeqsCommand::getOutputFileNameTag(string type, string inputName=""){
- try {
- string outputFileName = "";
- map<string, vector<string> >::iterator it;
+string ListSeqsCommand::getOutputPattern(string type) {
+ try {
+ string pattern = "";
- //is this a type this command creates
- it = outputTypes.find(type);
- if (it == outputTypes.end()) { m->mothurOut("[ERROR]: this command doesn't create a " + type + " output file.\n"); }
- else {
- if (type == "accnos") { outputFileName = "accnos"; }
- else { m->mothurOut("[ERROR]: No definition for type " + type + " output file tag.\n"); m->control_pressed = true; }
- }
- return outputFileName;
- }
- catch(exception& e) {
- m->errorOut(e, "ListSeqsCommand", "getOutputFileNameTag");
- exit(1);
- }
+ if (type == "accnos") { pattern = "[filename],accnos"; }
+ else { m->mothurOut("[ERROR]: No definition for type " + type + " output pattern.\n"); m->control_pressed = true; }
+
+ return pattern;
+ }
+ catch(exception& e) {
+ m->errorOut(e, "ListSeqsCommand", "getOutputPattern");
+ exit(1);
+ }
}
//**********************************************************************************************************************
ListSeqsCommand::ListSeqsCommand(){
//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("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; }
+ }
+
+ it = parameters.find("fastq");
+ //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["fastq"] = inputDir + it->second; }
+ }
}
//check for required parameters
if (taxfile == "not open") { abort = true; }
else if (taxfile == "not found") { taxfile = ""; }
else { m->setTaxonomyFile(taxfile); }
+
+ countfile = validParameter.validFile(parameters, "count", true);
+ if (countfile == "not open") { abort = true; }
+ else if (countfile == "not found") { countfile = ""; }
+ else { m->setCountTableFile(countfile); }
+
+ fastqfile = validParameter.validFile(parameters, "fastq", true);
+ if (fastqfile == "not open") { abort = true; }
+ else if (fastqfile == "not found") { fastqfile = ""; }
- if ((fastafile == "") && (namefile == "") && (listfile == "") && (groupfile == "") && (alignfile == "") && (taxfile == "")) { m->mothurOut("You must provide a file."); m->mothurOutEndLine(); abort = true; }
+ if ((fastqfile == "") && (countfile == "") && (fastafile == "") && (namefile == "") && (listfile == "") && (groupfile == "") && (alignfile == "") && (taxfile == "")) { m->mothurOut("You must provide a file."); m->mothurOutEndLine(); abort = true; }
int okay = 1;
if (outputDir != "") { okay++; }
//read functions fill names vector
if (fastafile != "") { inputFileName = fastafile; readFasta(); }
+ else if (fastqfile != "") { inputFileName = fastqfile; readFastq(); }
else if (namefile != "") { inputFileName = namefile; readName(); }
else if (groupfile != "") { inputFileName = groupfile; readGroup(); }
else if (alignfile != "") { inputFileName = alignfile; readAlign(); }
else if (listfile != "") { inputFileName = listfile; readList(); }
else if (taxfile != "") { inputFileName = taxfile; readTax(); }
+ else if (countfile != "") { inputFileName = countfile; readCount(); }
if (m->control_pressed) { outputTypes.clear(); return 0; }
if (outputDir == "") { outputDir += m->hasPath(inputFileName); }
- string outputFileName = outputDir + m->getRootName(m->getSimpleName(inputFileName)) + getOutputFileNameTag("accnos");
+ map<string, string> variables;
+ variables["[filename]"] = outputDir + m->getRootName(m->getSimpleName(inputFileName));
+ string outputFileName = getOutputFileName("accnos", variables);
ofstream out;
m->openOutputFile(outputFileName, out);
m->setAccnosFile(outputFileName);
m->mothurOutEndLine();
- m->mothurOut("Output File Name: "); m->mothurOutEndLine();
+ m->mothurOut("Output File Names: "); m->mothurOutEndLine();
m->mothurOut(outputFileName); m->mothurOutEndLine();
m->mothurOutEndLine();
exit(1);
}
}
+//**********************************************************************************************************************
+int ListSeqsCommand::readFastq(){
+ try {
+
+ ifstream in;
+ m->openInputFile(fastqfile, in);
+ string name;
+
+ //ofstream out;
+ //string newFastaName = outputDir + m->getRootName(m->getSimpleName(fastafile)) + "numsAdded.fasta";
+ //m->openOutputFile(newFastaName, out);
+ int count = 1;
+ //string lastName = "";
+
+ while(!in.eof()){
+
+ if (m->control_pressed) { in.close(); return 0; }
+
+ //read sequence name
+ string name = m->getline(in); m->gobble(in);
+
+ if (name[0] == '@') {
+ vector<string> splits = m->splitWhiteSpace(name);
+ name = splits[0];
+ name = name.substr(1);
+ m->checkName(name);
+ names.push_back(name);
+ //get rest of lines
+ name = m->getline(in); m->gobble(in);
+ name = m->getline(in); m->gobble(in);
+ name = m->getline(in); m->gobble(in);
+ }
+
+ m->gobble(in);
+ if (m->debug) { count++; cout << "[DEBUG]: count = " + toString(count) + ", name = " + name + "\n"; }
+ }
+ in.close();
+ //out.close();
+
+ return 0;
+
+ }
+ catch(exception& e) {
+ m->errorOut(e, "ListSeqsCommand", "readFastq");
+ exit(1);
+ }
+}
//**********************************************************************************************************************
int ListSeqsCommand::readFasta(){
//ofstream out;
//string newFastaName = outputDir + m->getRootName(m->getSimpleName(fastafile)) + "numsAdded.fasta";
//m->openOutputFile(newFastaName, out);
- //int count = 1;
+ int count = 1;
//string lastName = "";
while(!in.eof()){
Sequence currSeq(in);
name = currSeq.getName();
- //if (lastName == "") { lastName = name; }
- //if (name != lastName) { count = 1; }
- // lastName = name;
-
- //Sequence newSeq(name+"_"+toString(count), currSeq.getAligned());
- //newSeq.printSequence(out);
if (name != "") { names.push_back(name); }
m->gobble(in);
- //count++;
+ if (m->debug) { count++; cout << "[DEBUG]: count = " + toString(count) + ", name = " + currSeq.getName() + "\n"; }
}
in.close();
//out.close();
exit(1);
}
}
-
+//**********************************************************************************************************************
+int ListSeqsCommand::readCount(){
+ try {
+ CountTable ct;
+ ct.readTable(countfile, false, false);
+
+ if (m->control_pressed) { return 0; }
+
+ names = ct.getNamesOfSeqs();
+
+ return 0;
+
+ }
+ catch(exception& e) {
+ m->errorOut(e, "ListSeqsCommand", "readCount");
+ 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 ListSeqsCommand::readAlign(){