#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", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(pname);
- CommandParameter pgroup("group", "InputTypes", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(pgroup);
+ 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);
string GetSeqsCommand::getHelpString(){
try {
string helpString = "";
- helpString += "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";
+ helpString += "The get.seqs command reads an .accnos file and any of the following file types: fasta, name, group, count, list, taxonomy, quality or alignreport file.\n";
helpString += "It outputs a file containing only the sequences in the .accnos file.\n";
helpString += "The get.seqs command parameters are accnos, fasta, name, group, list, taxonomy, qfile, alignreport and dups. You must provide accnos unless you have a valid current accnos file, and at least one of the other parameters.\n";
helpString += "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";
outputTypes["alignreport"] = tempOutNames;
outputTypes["list"] = tempOutNames;
outputTypes["qfile"] = tempOutNames;
+ outputTypes["count"] = tempOutNames;
outputTypes["accnosreport"] = tempOutNames;
}
catch(exception& e) {
}
}
//**********************************************************************************************************************
+string GetSeqsCommand::getOutputFileNameTag(string type, string inputName=""){
+ try {
+ string outputFileName = "";
+ map<string, vector<string> >::iterator it;
+
+ //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);
+ }
+}
+//**********************************************************************************************************************
GetSeqsCommand::GetSeqsCommand(string option) {
try {
abort = false; calledHelp = false;
outputTypes["list"] = tempOutNames;
outputTypes["qfile"] = tempOutNames;
outputTypes["accnosreport"] = tempOutNames;
+ outputTypes["count"] = 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 = ""; }
//if the user has not given a path then, add inputdir. else leave path alone.
if (path == "") { parameters["qfile"] = 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; }
+ }
}
if (accnosfile2 == "not open") { abort = true; }
else if (accnosfile2 == "not found") { accnosfile2 = ""; }
+ countfile = validParameter.validFile(parameters, "count", true);
+ if (countfile == "not open") { countfile = ""; abort = true; }
+ else if (countfile == "not found") { countfile = ""; }
+ else { m->setCountTableFile(countfile); }
+
+ if ((namefile != "") && (countfile != "")) {
+ m->mothurOut("[ERROR]: you may only use one of the following: name or count."); m->mothurOutEndLine(); abort = true;
+ }
+
+ if ((groupfile != "") && (countfile != "")) {
+ m->mothurOut("[ERROR]: you may only use one of the following: group or count."); m->mothurOutEndLine(); abort=true;
+ }
+
string usedDups = "true";
string temp = validParameter.validFile(parameters, "dups", false); if (temp == "not found") { temp = "true"; usedDups = ""; }
dups = m->isTrue(temp);
- 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 ((namefile == "") && ((fastafile != "") || (taxfile != ""))){
- vector<string> files; files.push_back(fastafile); files.push_back(taxfile);
- parser.getNameFile(files);
- }
+ if ((fastafile == "") && (namefile == "") && (groupfile == "") && (alignfile == "") && (listfile == "") && (taxfile == "") && (qualfile == "") && (accnosfile2 == "") && (countfile == "")) { m->mothurOut("You must provide one of the following: fasta, name, group, count, alignreport, taxonomy, quality or listfile."); m->mothurOutEndLine(); abort = true; }
+
+ if (countfile == "") {
+ if ((namefile == "") && ((fastafile != "") || (taxfile != ""))){
+ vector<string> files; files.push_back(fastafile); files.push_back(taxfile);
+ parser.getNameFile(files);
+ }
+ }
}
}
if (abort == true) { if (calledHelp) { return 0; } return 2; }
//get names you want to keep
- readAccnos();
+ names = m->readAccnos(accnosfile);
if (m->control_pressed) { return 0; }
+
+ if (countfile != "") {
+ if ((fastafile != "") || (listfile != "") || (taxfile != "")) {
+ m->mothurOut("\n[NOTE]: The count file should contain only unique names, so mothur assumes your fasta, list and taxonomy files also contain only uniques.\n\n");
+ }
+ }
//read through the correct file and output lines you want to keep
if (namefile != "") { readName(); }
if (fastafile != "") { readFasta(); }
if (groupfile != "") { readGroup(); }
+ if (countfile != "") { readCount(); }
if (alignfile != "") { readAlign(); }
if (listfile != "") { readList(); }
if (taxfile != "") { readTax(); }
if (qualfile != "") { readQual(); }
if (accnosfile2 != "") { compareAccnos(); }
+
+ if (m->debug) { runSanityCheck(); }
if (m->control_pressed) { outputTypes.clear(); for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; }
if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setQualFile(current); }
}
+ itTypes = outputTypes.find("count");
+ if (itTypes != outputTypes.end()) {
+ if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setCountTableFile(current); }
+ }
}
return 0;
try {
string thisOutputDir = outputDir;
if (outputDir == "") { thisOutputDir += m->hasPath(fastafile); }
- string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(fastafile)) + "pick" + m->getExtension(fastafile);
+ string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(fastafile)) + getOutputFileNameTag("fasta", fastafile);
ofstream out;
m->openOutputFile(outputFileName, out);
bool wroteSomething = false;
int selectedCount = 0;
+
+ if (m->debug) { set<string> temp; sanity["fasta"] = temp; }
while(!in.eof()){
currSeq.printSequence(out);
selectedCount++;
+
+ if (m->debug) { sanity["fasta"].insert(name); }
}
}
m->gobble(in);
try {
string thisOutputDir = outputDir;
if (outputDir == "") { thisOutputDir += m->hasPath(qualfile); }
- string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(qualfile)) + "pick" + m->getExtension(qualfile);
+ string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(qualfile)) + getOutputFileNameTag("qfile", qualfile);
ofstream out;
m->openOutputFile(outputFileName, out);
bool wroteSomething = false;
int selectedCount = 0;
+ if (m->debug) { set<string> temp; sanity["qual"] = temp; }
while(!in.eof()){
string saveName = "";
out << name << endl << scores;
selectedCount++;
+ if (m->debug) { sanity["qual"].insert(name); }
}
m->gobble(in);
exit(1);
}
}
+//**********************************************************************************************************************
+int GetSeqsCommand::readCount(){
+ try {
+ string thisOutputDir = outputDir;
+ if (outputDir == "") { thisOutputDir += m->hasPath(countfile); }
+ string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(countfile)) + getOutputFileNameTag("count", countfile);
+
+ ofstream out;
+ m->openOutputFile(outputFileName, out);
+
+ ifstream in;
+ m->openInputFile(countfile, in);
+
+ bool wroteSomething = false;
+ int selectedCount = 0;
+
+ string headers = m->getline(in); m->gobble(in);
+ out << headers << endl;
+
+ string name, rest; int thisTotal;
+ while (!in.eof()) {
+
+ if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; }
+
+ in >> name; m->gobble(in);
+ in >> thisTotal; m->gobble(in);
+ rest = m->getline(in); m->gobble(in);
+ if (m->debug) { m->mothurOut("[DEBUG]: " + name + '\t' + rest + "\n"); }
+
+ if (names.count(name) != 0) {
+ out << name << '\t' << thisTotal << '\t' << rest << endl;
+ wroteSomething = true;
+ selectedCount+= thisTotal;
+ }
+ }
+ in.close();
+ out.close();
+
+ //check for groups that have been eliminated
+ CountTable ct;
+ if (ct.testGroups(outputFileName)) {
+ ct.readTable(outputFileName);
+ 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);
+
+ m->mothurOut("Selected " + toString(selectedCount) + " sequences from your count file."); m->mothurOutEndLine();
+
+ return 0;
+ }
+ catch(exception& e) {
+ m->errorOut(e, "GetSeqsCommand", "readCount");
+ exit(1);
+ }
+}
+
//**********************************************************************************************************************
int GetSeqsCommand::readList(){
try {
string thisOutputDir = outputDir;
if (outputDir == "") { thisOutputDir += m->hasPath(listfile); }
- string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(listfile)) + "pick" + m->getExtension(listfile);
+ string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(listfile)) + getOutputFileNameTag("list", listfile);
ofstream out;
m->openOutputFile(outputFileName, out);
bool wroteSomething = false;
int selectedCount = 0;
+
+ if (m->debug) { set<string> temp; sanity["list"] = temp; }
while(!in.eof()){
//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 (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 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)) + "pick" + m->getExtension(namefile);
+ string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(namefile)) + getOutputFileNameTag("name", namefile);
ofstream out;
m->openOutputFile(outputFileName, out);
bool wroteSomething = false;
int selectedCount = 0;
+
+ if (m->debug) { set<string> temp; sanity["name"] = temp; }
+ if (m->debug) { set<string> temp; sanity["dupname"] = temp; }
while(!in.eof()){
for (int i = 0; i < parsedNames.size(); i++) {
if (names.count(parsedNames[i]) != 0) {
validSecond.push_back(parsedNames[i]);
+ if (m->debug) { sanity["dupname"].insert(parsedNames[i]); }
}
}
if ((dups) && (validSecond.size() != 0)) { //dups = true and we want to add someone, then add everyone
- for (int i = 0; i < parsedNames.size(); i++) { names.insert(parsedNames[i]); }
+ for (int i = 0; i < parsedNames.size(); i++) { names.insert(parsedNames[i]); if (m->debug) { sanity["dupname"].insert(parsedNames[i]); } }
out << firstCol << '\t' << hold << endl;
wroteSomething = true;
selectedCount += parsedNames.size();
+ if (m->debug) { sanity["name"].insert(firstCol); }
}else {
selectedCount += validSecond.size();
//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;
+
+ if (m->debug) { sanity["name"].insert(firstCol); }
//make first name in set you come to first column and then add the remaining names to second column
//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;
+
+ if (m->debug) { sanity["name"].insert(validSecond[0]); }
}
}
}
try {
string thisOutputDir = outputDir;
if (outputDir == "") { thisOutputDir += m->hasPath(groupfile); }
- string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(groupfile)) + "pick" + m->getExtension(groupfile);
+ string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(groupfile)) + getOutputFileNameTag("group", groupfile);
ofstream out;
m->openOutputFile(outputFileName, out);
bool wroteSomething = false;
int selectedCount = 0;
+
+ if (m->debug) { set<string> temp; sanity["group"] = temp; }
while(!in.eof()){
out << name << '\t' << group << endl;
selectedCount++;
+
+ if (m->debug) { sanity["group"].insert(name); }
}
m->gobble(in);
try {
string thisOutputDir = outputDir;
if (outputDir == "") { thisOutputDir += m->hasPath(taxfile); }
- string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(taxfile)) + "pick" + m->getExtension(taxfile);
+ string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(taxfile)) + getOutputFileNameTag("taxonomy", taxfile);
ofstream out;
m->openOutputFile(outputFileName, out);
bool wroteSomething = false;
int selectedCount = 0;
+
+ if (m->debug) { set<string> temp; sanity["tax"] = temp; }
while(!in.eof()){
out << name << '\t' << tax << endl;
selectedCount++;
+
+ if (m->debug) { sanity["tax"].insert(name); }
}
m->gobble(in);
try {
string thisOutputDir = outputDir;
if (outputDir == "") { thisOutputDir += m->hasPath(alignfile); }
- string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(alignfile)) + "pick.align.report";
+ string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(alignfile)) + getOutputFileNameTag("alignreport");
ofstream out;
m->openOutputFile(outputFileName, out);
}
}
//**********************************************************************************************************************
-
-int GetSeqsCommand::readAccnos(){
+//just looking at common mistakes.
+int GetSeqsCommand::runSanityCheck(){
try {
-
- ifstream in;
- m->openInputFile(accnosfile, in);
- string name;
-
- while(!in.eof()){
- in >> name;
-
- names.insert(name);
-
- m->gobble(in);
- }
- in.close();
-
- return 0;
+ string thisOutputDir = outputDir;
+ if (outputDir == "") { thisOutputDir += m->hasPath(fastafile); }
+ string filename = outputDir + "get.seqs.debug.report";
+
+ ofstream out;
+ m->openOutputFile(filename, out);
+
+
+ //compare fasta, name, qual and taxonomy if given to make sure they contain the same seqs
+ if (fastafile != "") {
+ if (namefile != "") { //compare with fasta
+ if (sanity["fasta"] != sanity["name"]) { //create mismatch file
+ createMisMatchFile(out, fastafile, namefile, sanity["fasta"], sanity["name"]);
+ }
+ }
+ if (qualfile != "") {
+ if (sanity["fasta"] != sanity["qual"]) { //create mismatch file
+ createMisMatchFile(out, fastafile, qualfile, sanity["fasta"], sanity["qual"]);
+ }
+ }
+ if (taxfile != "") {
+ if (sanity["fasta"] != sanity["tax"]) { //create mismatch file
+ createMisMatchFile(out, fastafile, taxfile, sanity["fasta"], sanity["tax"]);
+ }
+ }
+ }
+
+ //compare dupnames, groups and list if given to make sure they match
+ if (namefile != "") {
+ if (groupfile != "") {
+ if (sanity["dupname"] != sanity["group"]) { //create mismatch file
+ createMisMatchFile(out, namefile, groupfile, sanity["dupname"], sanity["group"]);
+ }
+ }
+ if (listfile != "") {
+ if (sanity["dupname"] != sanity["list"]) { //create mismatch file
+ createMisMatchFile(out, namefile, listfile, sanity["dupname"], sanity["list"]);
+ }
+ }
+ }else{
+ if ((groupfile != "") && (fastafile != "")) {
+ if (sanity["fasta"] != sanity["group"]) { //create mismatch file
+ createMisMatchFile(out, fastafile, groupfile, sanity["fasta"], sanity["group"]);
+ }
+ }
+ }
+
+ out.close();
+
+ if (m->isBlank(filename)) { m->mothurRemove(filename); }
+ else { m->mothurOut("\n[DEBUG]: " + filename + " contains the file mismatches.\n");outputNames.push_back(filename); outputTypes["debug"].push_back(filename); }
+
+ return 0;
+ }
+ catch(exception& e) {
+ m->errorOut(e, "GetSeqsCommand", "runSanityCheck");
+ exit(1);
}
+}
+//**********************************************************************************************************************
+//just looking at common mistakes.
+int GetSeqsCommand::createMisMatchFile(ofstream& out, string filename1, string filename2, set<string> set1, set<string> set2){
+ try {
+ out << "****************************************" << endl << endl;
+ out << "Names unique to " << filename1 << ":\n";
+
+ //remove names in set1 that are also in set2
+ for (set<string>::iterator it = set1.begin(); it != set1.end();) {
+ string name = *it;
+
+ if (set2.count(name) == 0) { out << name << endl; } //name unique to set1
+ else { set2.erase(name); } //you are in both so erase
+ set1.erase(it++);
+ }
+
+ out << "\nNames unique to " << filename2 << ":\n";
+ //output results
+ for (set<string>::iterator it = set2.begin(); it != set2.end(); it++) { out << *it << endl; }
+
+ out << "****************************************" << endl << endl;
+
+ return 0;
+ }
catch(exception& e) {
- m->errorOut(e, "GetSeqsCommand", "readAccnos");
+ m->errorOut(e, "GetSeqsCommand", "runSanityCheck");
exit(1);
}
}
string thisOutputDir = outputDir;
if (outputDir == "") { thisOutputDir += m->hasPath(accnosfile); }
- string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(accnosfile)) + "accnos.report";
+ string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(accnosfile)) + getOutputFileNameTag("accnosreport");
ofstream out;
m->openOutputFile(outputFileName, out);
}
catch(exception& e) {
- m->errorOut(e, "GetSeqsCommand", "readAccnos");
+ m->errorOut(e, "GetSeqsCommand", "compareAccnos");
exit(1);
}
}