#include "getseqscommand.h"
#include "sequence.hpp"
#include "listvector.hpp"
+#include "counttable.h"
//**********************************************************************************************************************
vector<string> GetSeqsCommand::setParameters(){
try {
- CommandParameter pfasta("fasta", "InputTypes", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(pfasta);
- CommandParameter pname("name", "InputTypes", "", "", "NameCount", "FNGLT", "none",false,false); parameters.push_back(pname);
- CommandParameter pcount("count", "InputTypes", "", "", "NameCount-CountGroup", "FNGLT", "none",false,false); parameters.push_back(pcount);
- CommandParameter pgroup("group", "InputTypes", "", "", "CountGroup", "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 paccnos2("accnos2", "InputTypes", "", "", "none", "none", "none",false,true); parameters.push_back(paccnos2);
+ 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);
+ CommandParameter paccnos2("accnos2", "InputTypes", "", "", "none", "none", "none","",false,false); parameters.push_back(paccnos2);
vector<string> myArray;
for (int i = 0; i < parameters.size(); i++) { myArray.push_back(parameters[i].name); }
}
}
//**********************************************************************************************************************
-string GetSeqsCommand::getOutputFileNameTag(string type, string inputName=""){
- try {
- string outputFileName = "";
- map<string, vector<string> >::iterator it;
+string GetSeqsCommand::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 == "fasta") { outputFileName = "pick" + m->getExtension(inputName); }
- else if (type == "taxonomy") { outputFileName = "pick" + m->getExtension(inputName); }
- else if (type == "name") { outputFileName = "pick" + m->getExtension(inputName); }
- else if (type == "count") { outputFileName = "pick.count.table"; }
- else if (type == "group") { outputFileName = "pick" + m->getExtension(inputName); }
- else if (type == "list") { outputFileName = "pick" + m->getExtension(inputName); }
- else if (type == "qfile") { outputFileName = "pick" + m->getExtension(inputName); }
- else if (type == "accnosreport"){ outputFileName = "accnos.report"; }
- else if (type == "alignreport") { outputFileName = "pick.align.report"; }
- 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, "GetSeqsCommand", "getOutputFileNameTag");
- exit(1);
- }
+ 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 == "accnosreport") { pattern = "[filename],pick.accnos.report"; }
+ 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);
+ }
}
//**********************************************************************************************************************
GetSeqsCommand::GetSeqsCommand(string option) {
try {
string thisOutputDir = outputDir;
if (outputDir == "") { thisOutputDir += m->hasPath(fastafile); }
- string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(fastafile)) + getOutputFileNameTag("fasta", 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);
Sequence currSeq(in);
name = currSeq.getName();
+
+ if (!dups) {//adjust name if needed
+ map<string, string>::iterator it = uniqueMap.find(name);
+ if (it != uniqueMap.end()) { name = it->second; }
+ }
if (name != "") {
//if this name is in the accnos file
try {
string thisOutputDir = outputDir;
if (outputDir == "") { thisOutputDir += m->hasPath(qualfile); }
- string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(qualfile)) + getOutputFileNameTag("qfile", 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);
string name = "";
string scores = "";
- in >> name;
+ in >> name;
+
+ if (!dups) {//adjust name if needed
+ map<string, string>::iterator it = uniqueMap.find(name);
+ if (it != uniqueMap.end()) { name = it->second; }
+ }
if (name.length() != 0) {
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);
try {
string thisOutputDir = outputDir;
if (outputDir == "") { thisOutputDir += m->hasPath(countfile); }
- string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(countfile)) + getOutputFileNameTag("count", 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);
}
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 does not contain any sequence from the .accnos file."); m->mothurOutEndLine(); }
outputTypes["count"].push_back(outputFileName); outputNames.push_back(outputFileName);
try {
string thisOutputDir = outputDir;
if (outputDir == "") { thisOutputDir += m->hasPath(listfile); }
- string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(listfile)) + getOutputFileNameTag("list", 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);
//parse out names that are in accnos file
string binnames = list.get(i);
+ vector<string> bnames;
+ m->splitAtComma(binnames, bnames);
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());
-
+ for (int i = 0; i < bnames.size(); i++) {
+ string name = bnames[i];
//if that name is in the .accnos file, add it
if (names.count(name) != 0) { newNames += name + ","; selectedCount++; if (m->debug) { sanity["list"].insert(name); } }
}
- //get last name
- if (names.count(binnames) != 0) { newNames += binnames + ","; selectedCount++; if (m->debug) { sanity["list"].insert(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
try {
string thisOutputDir = outputDir;
if (outputDir == "") { thisOutputDir += m->hasPath(namefile); }
- string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(namefile)) + getOutputFileNameTag("name", 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)) + getOutputFileNameTag("group", 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);
in >> name; //read from first column
in >> group; //read from second column
+
//if this name is in the accnos file
if (names.count(name) != 0) {
try {
string thisOutputDir = outputDir;
if (outputDir == "") { thisOutputDir += m->hasPath(taxfile); }
- string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(taxfile)) + getOutputFileNameTag("taxonomy", 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);
in >> name; //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) {
try {
string thisOutputDir = outputDir;
if (outputDir == "") { thisOutputDir += m->hasPath(alignfile); }
- string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(alignfile)) + getOutputFileNameTag("alignreport");
+ map<string, string> variables;
+ variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(alignfile));
+ string outputFileName = getOutputFileName("alignreport", variables);
ofstream out;
m->openOutputFile(outputFileName, out);
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) {
string thisOutputDir = outputDir;
if (outputDir == "") { thisOutputDir += m->hasPath(accnosfile); }
- string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(accnosfile)) + getOutputFileNameTag("accnosreport");
+ map<string, string> variables;
+ variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(accnosfile));
+ string outputFileName = getOutputFileName("accnosreport", variables);
+
ofstream out;
m->openOutputFile(outputFileName, out);