*/
#include "screenseqscommand.h"
+#include "sequence.hpp"
//***************************************************************************************************************
-ScreenSeqsCommand::ScreenSeqsCommand(){
+ScreenSeqsCommand::ScreenSeqsCommand(string option){
try {
- globaldata = GlobalData::getInstance();
+ abort = false;
- if(globaldata->getFastaFile() != "") { readSeqs = new ReadFasta(globaldata->inputFileName); }
- else if(globaldata->getNexusFile() != "") { readSeqs = new ReadNexus(globaldata->inputFileName); }
- else if(globaldata->getClustalFile() != "") { readSeqs = new ReadClustal(globaldata->inputFileName); }
- else if(globaldata->getPhylipFile() != "") { readSeqs = new ReadPhylip(globaldata->inputFileName); }
+ //allow user to run help
+ if(option == "help") { help(); abort = true; }
- readSeqs->read();
- db = readSeqs->getDB();
- numSeqs = db->size();
+ else {
+ //valid paramters for this command
+ string AlignArray[] = {"fasta", "start", "end", "maxambig", "maxhomop", "minlength", "maxlength",
+ "name", "group", "alignreport"};
+ vector<string> myArray (AlignArray, AlignArray+(sizeof(AlignArray)/sizeof(string)));
+
+ OptionParser parser(option);
+ map<string,string> parameters = parser.getParameters();
+
+ ValidParameters validParameter;
+
+ //check to make sure all parameters are valid for command
+ for (map<string,string>::iterator it = parameters.begin(); it != parameters.end(); it++) {
+ if (validParameter.isValidParameter(it->first, myArray, it->second) != true) { abort = true; }
+ }
+
+ //check for required parameters
+ fastafile = validParameter.validFile(parameters, "fasta", true);
+ if (fastafile == "not found") { mothurOut("fasta is a required parameter for the screen.seqs command."); mothurOutEndLine(); abort = true; }
+ else if (fastafile == "not open") { abort = true; }
+
+ groupfile = validParameter.validFile(parameters, "group", true);
+ if (groupfile == "not open") { abort = true; }
+ else if (groupfile == "not found") { groupfile = ""; }
+
+ namefile = validParameter.validFile(parameters, "name", true);
+ if (namefile == "not open") { abort = true; }
+ else if (namefile == "not found") { namefile = ""; }
+
+ alignreport = validParameter.validFile(parameters, "alignreport", true);
+ if (alignreport == "not open") { abort = true; }
+ else if (alignreport == "not found") { alignreport = ""; }
+
+ //check for optional parameter and set defaults
+ // ...at some point should added some additional type checking...
+ string temp;
+ temp = validParameter.validFile(parameters, "start", false); if (temp == "not found") { temp = "-1"; }
+ convert(temp, startPos);
+
+ temp = validParameter.validFile(parameters, "end", false); if (temp == "not found") { temp = "-1"; }
+ convert(temp, endPos);
+
+ temp = validParameter.validFile(parameters, "maxambig", false); if (temp == "not found") { temp = "-1"; }
+ convert(temp, maxAmbig);
+
+ temp = validParameter.validFile(parameters, "maxhomop", false); if (temp == "not found") { temp = "-1"; }
+ convert(temp, maxHomoP);
+
+ temp = validParameter.validFile(parameters, "minlength", false); if (temp == "not found") { temp = "-1"; }
+ convert(temp, minLength);
+
+ temp = validParameter.validFile(parameters, "maxlength", false); if (temp == "not found") { temp = "-1"; }
+ convert(temp, maxLength);
+ }
+
}
catch(exception& e) {
- cout << "Standard Error: " << e.what() << " has occurred in the SeqCoordCommand class Function SeqCoordCommand. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n";
+ errorOut(e, "ScreenSeqsCommand", "ScreenSeqsCommand");
exit(1);
}
- catch(...) {
- cout << "An unknown error has occurred in the SeqCoordCommand class function SeqCoordCommand. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n";
+}
+//**********************************************************************************************************************
+
+void ScreenSeqsCommand::help(){
+ try {
+ mothurOut("The screen.seqs command reads a fastafile and creates .....\n");
+ mothurOut("The screen.seqs command parameters are fasta, start, end, maxambig, maxhomop, minlength, maxlength, name, and group.\n");
+ mothurOut("The fasta parameter is required.\n");
+ mothurOut("The start parameter .... The default is -1.\n");
+ mothurOut("The end parameter .... The default is -1.\n");
+ mothurOut("The maxambig parameter .... The default is -1.\n");
+ mothurOut("The maxhomop parameter .... The default is -1.\n");
+ mothurOut("The minlength parameter .... The default is -1.\n");
+ mothurOut("The maxlength parameter .... The default is -1.\n");
+ mothurOut("The name parameter allows you to provide a namesfile, and the group parameter allows you to provide a groupfile.\n");
+ mothurOut("The screen.seqs command should be in the following format: \n");
+ mothurOut("screen.seqs(fasta=yourFastaFile, name=youNameFile, group=yourGroupFIle, start=yourStart, end=yourEnd, maxambig=yourMaxambig, \n");
+ mothurOut("maxhomop=yourMaxhomop, minlength=youMinlength, maxlength=yourMaxlength) \n");
+ mothurOut("Example screen.seqs(fasta=abrecovery.fasta, name=abrecovery.names, group=abrecovery.groups, start=..., end=..., maxambig=..., maxhomop=..., minlength=..., maxlength=...).\n");
+ mothurOut("Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFasta).\n\n");
+
+ }
+ catch(exception& e) {
+ errorOut(e, "ScreenSeqsCommand", "help");
exit(1);
- }
+ }
}
//***************************************************************************************************************
-ScreenSeqsCommand::~ScreenSeqsCommand(){
- delete readSeqs;
-}
+ScreenSeqsCommand::~ScreenSeqsCommand(){ /* do nothing */ }
//***************************************************************************************************************
int ScreenSeqsCommand::execute(){
try{
- int startPos, endPos, maxAmbig, maxHomoP, minLength, maxLength;
- convert(globaldata->getStartPos(), startPos);
- convert(globaldata->getEndPos(), endPos);
- convert(globaldata->getMaxAmbig(), maxAmbig);
- convert(globaldata->getMaxHomoPolymer(), maxHomoP);
- convert(globaldata->getMinLength(), minLength);
- convert(globaldata->getMaxLength(), maxLength);
+
+ if (abort == true) { return 0; }
+
+ ifstream inFASTA;
+ openInputFile(fastafile, inFASTA);
set<string> badSeqNames;
- string goodSeqFile = getRootName(globaldata->inputFileName) + "good" + getExtension(globaldata->inputFileName);
- string badSeqFile = getRootName(globaldata->inputFileName) + "bad" + getExtension(globaldata->inputFileName);
+ string goodSeqFile = getRootName(fastafile) + "good" + getExtension(fastafile);
+ string badSeqFile = getRootName(fastafile) + "bad" + getExtension(fastafile);
ofstream goodSeqOut; openOutputFile(goodSeqFile, goodSeqOut);
ofstream badSeqOut; openOutputFile(badSeqFile, badSeqOut);
-
- for(int i=0;i<numSeqs;i++){
- Sequence currSeq = db->get(i);
+
+ while(!inFASTA.eof()){
+ Sequence currSeq(inFASTA);
bool goodSeq = 1; // innocent until proven guilty
- if(goodSeq == 1 && startPos != -1 && startPos < currSeq.getStartPos()) { goodSeq = 0; }
- if(goodSeq == 1 && endPos != -1 && endPos > currSeq.getEndPos()) { goodSeq = 0; }
- if(goodSeq == 1 && maxAmbig != -1 && maxAmbig < currSeq.getAmbigBases()) { goodSeq = 0; }
- if(goodSeq == 1 && maxHomoP != -1 && maxHomoP < currSeq.getLongHomoPolymer()){ goodSeq = 0; }
- if(goodSeq == 1 && minLength != -1 && minLength > currSeq.getNumBases()) { goodSeq = 0; }
- if(goodSeq == 1 && maxLength != -1 && maxLength < currSeq.getNumBases()) { goodSeq = 0; }
+ if(goodSeq == 1 && startPos != -1 && startPos < currSeq.getStartPos()) { goodSeq = 0; }
+ if(goodSeq == 1 && endPos != -1 && endPos > currSeq.getEndPos()) { goodSeq = 0; }
+ if(goodSeq == 1 && maxAmbig != -1 && maxAmbig < currSeq.getAmbigBases()) { goodSeq = 0; }
+ if(goodSeq == 1 && maxHomoP != -1 && maxHomoP < currSeq.getLongHomoPolymer()) { goodSeq = 0; }
+ if(goodSeq == 1 && minLength != -1 && minLength > currSeq.getNumBases()) { goodSeq = 0; }
+ if(goodSeq == 1 && maxLength != -1 && maxLength < currSeq.getNumBases()) { goodSeq = 0; }
if(goodSeq == 1){
currSeq.printSequence(goodSeqOut);
currSeq.printSequence(badSeqOut);
badSeqNames.insert(currSeq.getName());
}
- }
-
- if(globaldata->getNameFile() != ""){
- screenNameGroupFile(badSeqNames);
-
- }
+ gobble(inFASTA);
+ }
+ if(namefile != "" && groupfile != "") { screenNameGroupFile(badSeqNames); } // this screens both names and groups
+ else if(groupfile != "") { screenGroupFile(badSeqNames); } // this screens just the groups
+ if(alignreport != "") { screenAlignReport(badSeqNames); }
+ goodSeqOut.close();
+ badSeqOut.close();
+ inFASTA.close();
return 0;
}
catch(exception& e) {
- cout << "Standard Error: " << e.what() << " has occurred in the FilterSeqsCommand class Function execute. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n";
- exit(1);
- }
- catch(...) {
- cout << "An unknown error has occurred in the FilterSeqsCommand class function execute. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n";
+ errorOut(e, "ScreenSeqsCommand", "execute");
exit(1);
}
-
}
//***************************************************************************************************************
void ScreenSeqsCommand::screenNameGroupFile(set<string> badSeqNames){
ifstream inputNames;
- openInputFile(globaldata->getNameFile(), inputNames);
+ openInputFile(namefile, inputNames);
set<string> badSeqGroups;
string seqName, seqList, group;
set<string>::iterator it;
- string goodNameFile = getRootName(globaldata->getNameFile()) + "good" + getExtension(globaldata->getNameFile());
- string badNameFile = getRootName(globaldata->getNameFile()) + "bad" + getExtension(globaldata->getNameFile());
+ string goodNameFile = getRootName(namefile) + "good" + getExtension(namefile);
+ string badNameFile = getRootName(namefile) + "bad" + getExtension(namefile);
ofstream goodNameOut; openOutputFile(goodNameFile, goodNameOut);
ofstream badNameOut; openOutputFile(badNameFile, badNameOut);
if(it != badSeqNames.end()){
badSeqNames.erase(it);
badNameOut << seqName << '\t' << seqList << endl;
- if(globaldata->getNameFile() != ""){
+ if(namefile != ""){
int start = 0;
for(int i=0;i<seqList.length();i++){
if(seqList[i] == ','){
goodNameOut.close();
badNameOut.close();
- if(globaldata->getGroupFile() != ""){
+ if(groupfile != ""){
ifstream inputGroups;
- openInputFile(globaldata->getGroupFile(), inputGroups);
+ openInputFile(groupfile, inputGroups);
- string goodGroupFile = getRootName(globaldata->getGroupFile()) + "good" + getExtension(globaldata->getGroupFile());
- string badGroupFile = getRootName(globaldata->getGroupFile()) + "bad" + getExtension(globaldata->getGroupFile());
+ string goodGroupFile = getRootName(groupfile) + "good" + getExtension(groupfile);
+ string badGroupFile = getRootName(groupfile) + "bad" + getExtension(groupfile);
ofstream goodGroupOut; openOutputFile(goodGroupFile, goodGroupOut);
ofstream badGroupOut; openOutputFile(badGroupFile, badGroupOut);
//***************************************************************************************************************
+void ScreenSeqsCommand::screenGroupFile(set<string> badSeqNames){
+
+ ifstream inputGroups;
+ openInputFile(groupfile, inputGroups);
+ string seqName, group;
+ set<string>::iterator it;
+
+ string goodGroupFile = getRootName(groupfile) + "good" + getExtension(groupfile);
+ string badGroupFile = getRootName(groupfile) + "bad" + getExtension(groupfile);
+
+ ofstream goodGroupOut; openOutputFile(goodGroupFile, goodGroupOut);
+ ofstream badGroupOut; openOutputFile(badGroupFile, badGroupOut);
+
+ while(!inputGroups.eof()){
+ inputGroups >> seqName >> group;
+ it = badSeqNames.find(seqName);
+
+ if(it != badSeqNames.end()){
+ badSeqNames.erase(it);
+ badGroupOut << seqName << '\t' << group << endl;
+ }
+ else{
+ goodGroupOut << seqName << '\t' << group << endl;
+ }
+ gobble(inputGroups);
+ }
+ inputGroups.close();
+ goodGroupOut.close();
+ badGroupOut.close();
+
+}
+
+//***************************************************************************************************************
+
+void ScreenSeqsCommand::screenAlignReport(set<string> badSeqNames){
+
+ ifstream inputAlignReport;
+ openInputFile(alignreport, inputAlignReport);
+ string seqName, group;
+ set<string>::iterator it;
+
+ string goodAlignReportFile = getRootName(alignreport) + "good" + getExtension(alignreport);
+ string badAlignReportFile = getRootName(alignreport) + "bad" + getExtension(alignreport);
+
+ ofstream goodAlignReportOut; openOutputFile(goodAlignReportFile, goodAlignReportOut);
+ ofstream badAlignReportOut; openOutputFile(badAlignReportFile, badAlignReportOut);
+
+ while (!inputAlignReport.eof()) { // need to copy header
+ char c = inputAlignReport.get();
+ goodAlignReportOut << c;
+ badAlignReportOut << c;
+ if (c == 10 || c == 13){ break; }
+ }
+
+ while(!inputAlignReport.eof()){
+ inputAlignReport >> seqName;
+ it = badSeqNames.find(seqName);
+ string line;
+ while (!inputAlignReport.eof()) { // need to copy header
+ char c = inputAlignReport.get();
+ line += c;
+ if (c == 10 || c == 13){ break; }
+ }
+
+ if(it != badSeqNames.end()){
+ badSeqNames.erase(it);
+ badAlignReportOut << seqName << '\t' << line;;
+ }
+ else{
+ goodAlignReportOut << seqName << '\t' << line;
+ }
+ gobble(inputAlignReport);
+ }
+ inputAlignReport.close();
+ goodAlignReportOut.close();
+ badAlignReportOut.close();
+
+}
+
+//***************************************************************************************************************
+