#include "trimseqscommand.h"
#include "needlemanoverlap.hpp"
+#include "trimoligos.h"
//**********************************************************************************************************************
-
-vector<string> TrimSeqsCommand::getValidParameters(){
+vector<string> TrimSeqsCommand::setParameters(){
try {
- string Array[] = {"fasta", "flip", "oligos", "maxambig", "maxhomop", "group","minlength", "maxlength", "qfile",
- "qthreshold", "qwindowaverage", "qstepsize", "qwindowsize", "qaverage", "rollaverage",
- "keepfirst", "removelast",
- "allfiles", "qtrim","tdiffs", "pdiffs", "bdiffs", "processors", "outputdir","inputdir"};
- vector<string> myArray (Array, Array+(sizeof(Array)/sizeof(string)));
+ CommandParameter pfasta("fasta", "InputTypes", "", "", "none", "none", "none",false,true); parameters.push_back(pfasta);
+ CommandParameter poligos("oligos", "InputTypes", "", "", "none", "none", "none",false,false); parameters.push_back(poligos);
+ CommandParameter pqfile("qfile", "InputTypes", "", "", "none", "none", "none",false,false); parameters.push_back(pqfile);
+ CommandParameter pname("name", "InputTypes", "", "", "none", "none", "none",false,false); parameters.push_back(pname);
+ CommandParameter pflip("flip", "Boolean", "", "F", "", "", "",false,false); parameters.push_back(pflip);
+ CommandParameter pmaxambig("maxambig", "Number", "", "-1", "", "", "",false,false); parameters.push_back(pmaxambig);
+ CommandParameter pmaxhomop("maxhomop", "Number", "", "0", "", "", "",false,false); parameters.push_back(pmaxhomop);
+ CommandParameter pminlength("minlength", "Number", "", "0", "", "", "",false,false); parameters.push_back(pminlength);
+ CommandParameter pmaxlength("maxlength", "Number", "", "0", "", "", "",false,false); parameters.push_back(pmaxlength);
+ CommandParameter ppdiffs("pdiffs", "Number", "", "0", "", "", "",false,false); parameters.push_back(ppdiffs);
+ CommandParameter pbdiffs("bdiffs", "Number", "", "0", "", "", "",false,false); parameters.push_back(pbdiffs);
+ CommandParameter ptdiffs("tdiffs", "Number", "", "0", "", "", "",false,false); parameters.push_back(ptdiffs);
+ CommandParameter pprocessors("processors", "Number", "", "1", "", "", "",false,false); parameters.push_back(pprocessors);
+ CommandParameter pallfiles("allfiles", "Boolean", "", "F", "", "", "",false,false); parameters.push_back(pallfiles);
+ CommandParameter pqtrim("qtrim", "Boolean", "", "T", "", "", "",false,false); parameters.push_back(pqtrim);
+ CommandParameter pqthreshold("qthreshold", "Number", "", "0", "", "", "",false,false); parameters.push_back(pqthreshold);
+ CommandParameter pqaverage("qaverage", "Number", "", "0", "", "", "",false,false); parameters.push_back(pqaverage);
+ CommandParameter prollaverage("rollaverage", "Number", "", "0", "", "", "",false,false); parameters.push_back(prollaverage);
+ CommandParameter pqwindowaverage("qwindowaverage", "Number", "", "0", "", "", "",false,false); parameters.push_back(pqwindowaverage);
+ CommandParameter pqstepsize("qstepsize", "Number", "", "1", "", "", "",false,false); parameters.push_back(pqstepsize);
+ CommandParameter pqwindowsize("qwindowsize", "Number", "", "50", "", "", "",false,false); parameters.push_back(pqwindowsize);
+ CommandParameter pkeepfirst("keepfirst", "Number", "", "0", "", "", "",false,false); parameters.push_back(pkeepfirst);
+ CommandParameter premovelast("removelast", "Number", "", "0", "", "", "",false,false); parameters.push_back(premovelast);
+ 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); }
return myArray;
}
catch(exception& e) {
- m->errorOut(e, "TrimSeqsCommand", "getValidParameters");
+ m->errorOut(e, "TrimSeqsCommand", "setParameters");
exit(1);
}
}
-
//**********************************************************************************************************************
-
-TrimSeqsCommand::TrimSeqsCommand(){
+string TrimSeqsCommand::getHelpString(){
try {
- abort = true;
- //initialize outputTypes
- vector<string> tempOutNames;
- outputTypes["fasta"] = tempOutNames;
- outputTypes["qual"] = tempOutNames;
- outputTypes["group"] = tempOutNames;
+ string helpString = "";
+ helpString += "The trim.seqs command reads a fastaFile and creates 2 new fasta files, .trim.fasta and scrap.fasta, as well as group files if you provide and oligos file.\n";
+ helpString += "The .trim.fasta contains sequences that meet your requirements, and the .scrap.fasta contains those which don't.\n";
+ helpString += "The trim.seqs command parameters are fasta, name, flip, oligos, maxambig, maxhomop, minlength, maxlength, qfile, qthreshold, qaverage, diffs, qtrim, keepfirst, removelast and allfiles.\n";
+ helpString += "The fasta parameter is required.\n";
+ helpString += "The flip parameter will output the reverse compliment of your trimmed sequence. The default is false.\n";
+ helpString += "The oligos parameter allows you to provide an oligos file.\n";
+ helpString += "The name parameter allows you to provide a names file with your fasta file.\n";
+ helpString += "The maxambig parameter allows you to set the maximum number of ambigious bases allowed. The default is -1.\n";
+ helpString += "The maxhomop parameter allows you to set a maximum homopolymer length. \n";
+ helpString += "The minlength parameter allows you to set and minimum sequence length. \n";
+ helpString += "The maxlength parameter allows you to set and maximum sequence length. \n";
+ helpString += "The tdiffs parameter is used to specify the total number of differences allowed in the sequence. The default is pdiffs + bdiffs.\n";
+ helpString += "The bdiffs parameter is used to specify the number of differences allowed in the barcode. The default is 0.\n";
+ helpString += "The pdiffs parameter is used to specify the number of differences allowed in the primer. The default is 0.\n";
+ helpString += "The qfile parameter allows you to provide a quality file.\n";
+ helpString += "The qthreshold parameter allows you to set a minimum quality score allowed. \n";
+ helpString += "The qaverage parameter allows you to set a minimum average quality score allowed. \n";
+ helpString += "The qwindowsize parameter allows you to set a number of bases in a window. Default=50.\n";
+ helpString += "The qwindowaverage parameter allows you to set a minimum average quality score allowed over a window. \n";
+ helpString += "The rollaverage parameter allows you to set a minimum rolling average quality score allowed over a window. \n";
+ helpString += "The qstepsize parameter allows you to set a number of bases to move the window over. Default=1.\n";
+ helpString += "The allfiles parameter will create separate group and fasta file for each grouping. The default is F.\n";
+ helpString += "The qtrim parameter will trim sequence from the point that they fall below the qthreshold and put it in the .trim file if set to true. The default is T.\n";
+ helpString += "The keepfirst parameter trims the sequence to the first keepfirst number of bases after the barcode or primers are removed, before the sequence is checked to see if it meets the other requirements. \n";
+ helpString += "The removelast removes the last removelast number of bases after the barcode or primers are removed, before the sequence is checked to see if it meets the other requirements.\n";
+ helpString += "The trim.seqs command should be in the following format: \n";
+ helpString += "trim.seqs(fasta=yourFastaFile, flip=yourFlip, oligos=yourOligos, maxambig=yourMaxambig, \n";
+ helpString += "maxhomop=yourMaxhomop, minlength=youMinlength, maxlength=yourMaxlength) \n";
+ helpString += "Example trim.seqs(fasta=abrecovery.fasta, flip=..., oligos=..., maxambig=..., maxhomop=..., minlength=..., maxlength=...).\n";
+ helpString += "Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFasta).\n";
+ helpString += "For more details please check out the wiki http://www.mothur.org/wiki/Trim.seqs .\n";
+ return helpString;
}
catch(exception& e) {
- m->errorOut(e, "TrimSeqsCommand", "TrimSeqsCommand");
+ m->errorOut(e, "TrimSeqsCommand", "getHelpString");
exit(1);
}
}
-//**********************************************************************************************************************
-
-vector<string> TrimSeqsCommand::getRequiredParameters(){
- try {
- string Array[] = {"fasta"};
- vector<string> myArray (Array, Array+(sizeof(Array)/sizeof(string)));
- return myArray;
- }
- catch(exception& e) {
- m->errorOut(e, "TrimSeqsCommand", "getRequiredParameters");
- exit(1);
- }
-}
//**********************************************************************************************************************
-vector<string> TrimSeqsCommand::getRequiredFiles(){
+TrimSeqsCommand::TrimSeqsCommand(){
try {
- vector<string> myArray;
- return myArray;
+ abort = true; calledHelp = true;
+ setParameters();
+ vector<string> tempOutNames;
+ outputTypes["fasta"] = tempOutNames;
+ outputTypes["qfile"] = tempOutNames;
+ outputTypes["group"] = tempOutNames;
+ outputTypes["name"] = tempOutNames;
}
catch(exception& e) {
- m->errorOut(e, "TrimSeqsCommand", "getRequiredFiles");
+ m->errorOut(e, "TrimSeqsCommand", "TrimSeqsCommand");
exit(1);
}
}
-
//***************************************************************************************************************
TrimSeqsCommand::TrimSeqsCommand(string option) {
try {
- abort = false;
+ abort = false; calledHelp = false;
comboStarts = 0;
//allow user to run help
- if(option == "help") { help(); abort = true; }
+ if(option == "help") { help(); abort = true; calledHelp = true; }
+ else if(option == "citation") { citation(); abort = true; calledHelp = true;}
else {
- //valid paramters for this command
- string AlignArray[] = { "fasta", "flip", "oligos", "maxambig", "maxhomop", "group","minlength", "maxlength", "qfile",
- "qthreshold", "qwindowaverage", "qstepsize", "qwindowsize", "qaverage", "rollaverage",
- "keepfirst", "removelast",
- "allfiles", "qtrim","tdiffs", "pdiffs", "bdiffs", "processors", "outputdir","inputdir"};
-
- vector<string> myArray (AlignArray, AlignArray+(sizeof(AlignArray)/sizeof(string)));
+ vector<string> myArray = setParameters();
OptionParser parser(option);
map<string,string> parameters = parser.getParameters();
//initialize outputTypes
vector<string> tempOutNames;
outputTypes["fasta"] = tempOutNames;
- outputTypes["qual"] = tempOutNames;
+ outputTypes["qfile"] = tempOutNames;
outputTypes["group"] = tempOutNames;
+ outputTypes["name"] = tempOutNames;
//if the user changes the input directory command factory will send this info to us in the output parameter
string inputDir = validParameter.validFile(parameters, "inputdir", false);
if (path == "") { parameters["qfile"] = inputDir + it->second; }
}
- it = parameters.find("group");
+ it = parameters.find("name");
//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["group"] = inputDir + it->second; }
+ if (path == "") { parameters["name"] = inputDir + it->second; }
}
+
}
//check for required parameters
fastaFile = validParameter.validFile(parameters, "fasta", true);
- if (fastaFile == "not found") { m->mothurOut("fasta is a required parameter for the trim.seqs command."); m->mothurOutEndLine(); abort = true; }
- else if (fastaFile == "not open") { abort = true; }
+ if (fastaFile == "not found") {
+ fastaFile = m->getFastaFile();
+ if (fastaFile != "") { m->mothurOut("Using " + fastaFile + " as input file for the fasta parameter."); m->mothurOutEndLine(); }
+ else { m->mothurOut("You have no current fastafile and the fasta parameter is required."); m->mothurOutEndLine(); abort = true; }
+ }else if (fastaFile == "not open") { abort = true; }
+ else { m->setFastaFile(fastaFile); }
//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"){
// ...at some point should added some additional type checking...
string temp;
temp = validParameter.validFile(parameters, "flip", false);
- if (temp == "not found"){ flip = 0; }
- else if(m->isTrue(temp)) { flip = 1; }
+ if (temp == "not found") { flip = 0; }
+ else { flip = m->isTrue(temp); }
temp = validParameter.validFile(parameters, "oligos", true);
if (temp == "not found"){ oligoFile = ""; }
else if(temp == "not open"){ abort = true; }
- else { oligoFile = temp; }
+ else { oligoFile = temp; m->setOligosFile(oligoFile); }
- temp = validParameter.validFile(parameters, "group", true);
- if (temp == "not found"){ groupfile = ""; }
- else if(temp == "not open"){ abort = true; }
- else { groupfile = temp; }
temp = validParameter.validFile(parameters, "maxambig", false); if (temp == "not found") { temp = "-1"; }
convert(temp, maxAmbig);
temp = validParameter.validFile(parameters, "qfile", true);
if (temp == "not found") { qFileName = ""; }
else if(temp == "not open") { abort = true; }
- else { qFileName = temp; }
+ else { qFileName = temp; m->setQualFile(qFileName); }
+
+ temp = validParameter.validFile(parameters, "name", true);
+ if (temp == "not found") { nameFile = ""; }
+ else if(temp == "not open") { nameFile = ""; abort = true; }
+ else { nameFile = temp; m->setNameFile(nameFile); }
temp = validParameter.validFile(parameters, "qthreshold", false); if (temp == "not found") { temp = "0"; }
convert(temp, qThreshold);
- temp = validParameter.validFile(parameters, "qtrim", false); if (temp == "not found") { temp = "F"; }
+ temp = validParameter.validFile(parameters, "qtrim", false); if (temp == "not found") { temp = "t"; }
qtrim = m->isTrue(temp);
temp = validParameter.validFile(parameters, "rollaverage", false); if (temp == "not found") { temp = "0"; }
temp = validParameter.validFile(parameters, "allfiles", false); if (temp == "not found") { temp = "F"; }
allFiles = m->isTrue(temp);
- temp = validParameter.validFile(parameters, "processors", false); if (temp == "not found") { temp = "1"; }
+ temp = validParameter.validFile(parameters, "processors", false); if (temp == "not found"){ temp = m->getProcessors(); }
+ m->setProcessors(temp);
convert(temp, processors);
- if ((oligoFile != "") && (groupfile != "")) {
- m->mothurOut("You given both a oligos file and a groupfile, only one is allowed."); m->mothurOutEndLine(); abort = true;
- }
-
- if(allFiles && (oligoFile == "") && (groupfile == "")){
- m->mothurOut("You selected allfiles, but didn't enter an oligos or group file. Ignoring the allfiles request."); m->mothurOutEndLine();
+ if(allFiles && (oligoFile == "")){
+ m->mothurOut("You selected allfiles, but didn't enter an oligos. Ignoring the allfiles request."); m->mothurOutEndLine();
}
if((qAverage != 0 && qThreshold != 0) && qFileName == ""){
m->mothurOut("You didn't provide a quality file name, quality criteria will be ignored."); m->mothurOutEndLine();
exit(1);
}
}
-
-//**********************************************************************************************************************
-
-void TrimSeqsCommand::help(){
- try {
- m->mothurOut("The trim.seqs command reads a fastaFile and creates .....\n");
- m->mothurOut("The trim.seqs command parameters are fasta, flip, oligos, group, maxambig, maxhomop, minlength, maxlength, qfile, qthreshold, qaverage, diffs, qtrim and allfiles.\n");
- m->mothurOut("The fasta parameter is required.\n");
- m->mothurOut("The group parameter allows you to enter a group file for your fasta file.\n");
- m->mothurOut("The flip parameter will output the reverse compliment of your trimmed sequence. The default is false.\n");
- m->mothurOut("The oligos parameter .... The default is "".\n");
- m->mothurOut("The maxambig parameter .... The default is -1.\n");
- m->mothurOut("The maxhomop parameter .... The default is 0.\n");
- m->mothurOut("The minlength parameter .... The default is 0.\n");
- m->mothurOut("The maxlength parameter .... The default is 0.\n");
- m->mothurOut("The tdiffs parameter is used to specify the total number of differences allowed in the sequence. The default is pdiffs + bdiffs.\n");
- m->mothurOut("The bdiffs parameter is used to specify the number of differences allowed in the barcode. The default is 0.\n");
- m->mothurOut("The pdiffs parameter is used to specify the number of differences allowed in the primer. The default is 0.\n");
- m->mothurOut("The qfile parameter .....\n");
- m->mothurOut("The qthreshold parameter .... The default is 0.\n");
- m->mothurOut("The qaverage parameter .... The default is 0.\n");
- m->mothurOut("The allfiles parameter .... The default is F.\n");
- m->mothurOut("The qtrim parameter .... The default is F.\n");
- m->mothurOut("The trim.seqs command should be in the following format: \n");
- m->mothurOut("trim.seqs(fasta=yourFastaFile, flip=yourFlip, oligos=yourOligos, maxambig=yourMaxambig, \n");
- m->mothurOut("maxhomop=yourMaxhomop, minlength=youMinlength, maxlength=yourMaxlength) \n");
- m->mothurOut("Example trim.seqs(fasta=abrecovery.fasta, flip=..., oligos=..., maxambig=..., maxhomop=..., minlength=..., maxlength=...).\n");
- m->mothurOut("Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFasta).\n");
- m->mothurOut("For more details please check out the wiki http://www.mothur.org/wiki/Trim.seqs .\n\n");
-
- }
- catch(exception& e) {
- m->errorOut(e, "TrimSeqsCommand", "help");
- exit(1);
- }
-}
-
-
-//***************************************************************************************************************
-
-TrimSeqsCommand::~TrimSeqsCommand(){ /* do nothing */ }
-
//***************************************************************************************************************
int TrimSeqsCommand::execute(){
try{
- if (abort == true) { return 0; }
+ if (abort == true) { if (calledHelp) { return 0; } return 2; }
numFPrimers = 0; //this needs to be initialized
numRPrimers = 0;
- vector<string> fastaFileNames;
- vector<string> qualFileNames;
+ createGroup = false;
+ vector<vector<string> > fastaFileNames;
+ vector<vector<string> > qualFileNames;
+ vector<vector<string> > nameFileNames;
string trimSeqFile = outputDir + m->getRootName(m->getSimpleName(fastaFile)) + "trim.fasta";
outputNames.push_back(trimSeqFile); outputTypes["fasta"].push_back(trimSeqFile);
+
string scrapSeqFile = outputDir + m->getRootName(m->getSimpleName(fastaFile)) + "scrap.fasta";
outputNames.push_back(scrapSeqFile); outputTypes["fasta"].push_back(scrapSeqFile);
+
string trimQualFile = outputDir + m->getRootName(m->getSimpleName(fastaFile)) + "trim.qual";
string scrapQualFile = outputDir + m->getRootName(m->getSimpleName(fastaFile)) + "scrap.qual";
- if (qFileName != "") { outputNames.push_back(trimQualFile); outputNames.push_back(scrapQualFile); outputTypes["qual"].push_back(trimQualFile); outputTypes["qual"].push_back(scrapQualFile); }
- string groupFile = "";
- if (groupfile == "") { groupFile = outputDir + m->getRootName(m->getSimpleName(fastaFile)) + "groups"; }
- else{
- groupFile = outputDir + m->getRootName(m->getSimpleName(groupfile)) + "trim.groups";
- outputNames.push_back(groupFile); outputTypes["group"].push_back(groupFile);
- groupMap = new GroupMap(groupfile);
- groupMap->readMap();
-
- if(allFiles){
- for (int i = 0; i < groupMap->namesOfGroups.size(); i++) {
- groupToIndex[groupMap->namesOfGroups[i]] = i;
- groupVector.push_back(groupMap->namesOfGroups[i]);
- fastaFileNames.push_back((outputDir + m->getRootName(m->getSimpleName(fastaFile)) + groupMap->namesOfGroups[i] + ".fasta"));
-
- //we append later, so we want to clear file
- ofstream outRemove;
- m->openOutputFile(fastaFileNames[i], outRemove);
- outRemove.close();
- if(qFileName != ""){
- qualFileNames.push_back((outputDir + m->getRootName(m->getSimpleName(qFileName)) + groupMap->namesOfGroups[i] + ".qual"));
- ofstream outRemove2;
- m->openOutputFile(qualFileNames[i], outRemove2);
- outRemove2.close();
- }
- }
- }
- comboStarts = fastaFileNames.size()-1;
+
+ if (qFileName != "") {
+ outputNames.push_back(trimQualFile);
+ outputNames.push_back(scrapQualFile);
+ outputTypes["qfile"].push_back(trimQualFile);
+ outputTypes["qfile"].push_back(scrapQualFile);
+ }
+
+ string trimNameFile = outputDir + m->getRootName(m->getSimpleName(nameFile)) + "trim.names";
+ string scrapNameFile = outputDir + m->getRootName(m->getSimpleName(nameFile)) + "scrap.names";
+
+ if (nameFile != "") {
+ m->readNames(nameFile, nameMap);
+ outputNames.push_back(trimNameFile);
+ outputNames.push_back(scrapNameFile);
+ outputTypes["name"].push_back(trimNameFile);
+ outputTypes["name"].push_back(scrapNameFile);
}
+ if (m->control_pressed) { return 0; }
+
+ string outputGroupFileName;
if(oligoFile != ""){
- outputNames.push_back(groupFile); outputTypes["group"].push_back(groupFile);
- getOligos(fastaFileNames, qualFileNames);
+ createGroup = getOligos(fastaFileNames, qualFileNames, nameFileNames);
+ if (createGroup) {
+ outputGroupFileName = outputDir + m->getRootName(m->getSimpleName(fastaFile)) + "groups";
+ outputNames.push_back(outputGroupFileName); outputTypes["group"].push_back(outputGroupFileName);
+ }
}
-
- vector<unsigned long int> fastaFilePos;
- vector<unsigned long int> qFilePos;
+
+ vector<unsigned long long> fastaFilePos;
+ vector<unsigned long long> qFilePos;
setLines(fastaFile, qFileName, fastaFilePos, qFilePos);
#if defined (__APPLE__) || (__MACH__) || (linux) || (__linux)
if(processors == 1){
- driverCreateTrim(fastaFile, qFileName, trimSeqFile, scrapSeqFile, trimQualFile, scrapQualFile, groupFile, fastaFileNames, qualFileNames, lines[0], qLines[0]);
+ driverCreateTrim(fastaFile, qFileName, trimSeqFile, scrapSeqFile, trimQualFile, scrapQualFile, trimNameFile, scrapNameFile, outputGroupFileName, fastaFileNames, qualFileNames, nameFileNames, lines[0], qLines[0]);
}else{
- createProcessesCreateTrim(fastaFile, qFileName, trimSeqFile, scrapSeqFile, trimQualFile, scrapQualFile, groupFile, fastaFileNames, qualFileNames);
+ createProcessesCreateTrim(fastaFile, qFileName, trimSeqFile, scrapSeqFile, trimQualFile, scrapQualFile, trimNameFile, scrapNameFile, outputGroupFileName, fastaFileNames, qualFileNames, nameFileNames);
}
#else
- driverCreateTrim(fastaFile, qFileName, trimSeqFile, scrapSeqFile, trimQualFile, scrapQualFile, groupFile, fastaFileNames, qualFileNames, lines[0], qLines[0]);
+ driverCreateTrim(fastaFile, qFileName, trimSeqFile, scrapSeqFile, trimQualFile, scrapQualFile, trimNameFile, scrapNameFile, outputGroupFileName, fastaFileNames, qualFileNames, nameFileNames, lines[0], qLines[0]);
#endif
if (m->control_pressed) { return 0; }
+
+ if(allFiles){
+ map<string, string> uniqueFastaNames;// so we don't add the same groupfile multiple times
+ map<string, string>::iterator it;
+ set<string> namesToRemove;
+ for(int i=0;i<fastaFileNames.size();i++){
+ for(int j=0;j<fastaFileNames[0].size();j++){
+ if (fastaFileNames[i][j] != "") {
+ if (namesToRemove.count(fastaFileNames[i][j]) == 0) {
+ if(m->isBlank(fastaFileNames[i][j])){
+ m->mothurRemove(fastaFileNames[i][j]);
+ namesToRemove.insert(fastaFileNames[i][j]);
+
+ if(qFileName != ""){
+ m->mothurRemove(qualFileNames[i][j]);
+ namesToRemove.insert(qualFileNames[i][j]);
+ }
+
+ if(nameFile != ""){
+ m->mothurRemove(nameFileNames[i][j]);
+ namesToRemove.insert(nameFileNames[i][j]);
+ }
+ }else{
+ it = uniqueFastaNames.find(fastaFileNames[i][j]);
+ if (it == uniqueFastaNames.end()) {
+ uniqueFastaNames[fastaFileNames[i][j]] = barcodeNameVector[i];
+ }
+ }
+ }
+ }
+ }
+ }
- set<string> blanks;
- for(int i=0;i<fastaFileNames.size();i++){
- if (m->isBlank(fastaFileNames[i])) { blanks.insert(fastaFileNames[i]); }
- else if (filesToRemove.count(fastaFileNames[i]) > 0) { remove(fastaFileNames[i].c_str()); }
- else {
- ifstream inFASTA;
- string seqName;
- m->openInputFile(fastaFileNames[i], inFASTA);
- ofstream outGroups;
- string outGroupFilename = outputDir + m->getRootName(m->getSimpleName(fastaFileNames[i])) + "groups";
-
- //if the fastafile is on the blanks list then the groups file should be as well
- if (blanks.count(fastaFileNames[i]) != 0) { blanks.insert(outGroupFilename); }
+ //remove names for outputFileNames, just cleans up the output
+ vector<string> outputNames2;
+ for(int i = 0; i < outputNames.size(); i++) { if (namesToRemove.count(outputNames[i]) == 0) { outputNames2.push_back(outputNames[i]); } }
+ outputNames = outputNames2;
+
+ for (it = uniqueFastaNames.begin(); it != uniqueFastaNames.end(); it++) {
+ ifstream in;
+ m->openInputFile(it->first, in);
- m->openOutputFile(outGroupFilename, outGroups);
- outputNames.push_back(outGroupFilename); outputTypes["group"].push_back(outGroupFilename);
+ ofstream out;
+ string thisGroupName = outputDir + m->getRootName(m->getSimpleName(it->first)) + "groups";
+ outputNames.push_back(thisGroupName); outputTypes["group"].push_back(thisGroupName);
+ m->openOutputFile(thisGroupName, out);
- string thisGroup = "";
- if (i > comboStarts) {
- map<string, int>::iterator itCombo;
- for(itCombo=combos.begin();itCombo!=combos.end(); itCombo++){
- if(itCombo->second == i){ thisGroup = itCombo->first; combos.erase(itCombo); break; }
- }
- }else{ thisGroup = groupVector[i]; }
+ while (!in.eof()){
+ if (m->control_pressed) { break; }
- while(!inFASTA.eof()){
- if(inFASTA.get() == '>'){
- inFASTA >> seqName;
- outGroups << seqName << '\t' << thisGroup << endl;
- }
- while (!inFASTA.eof()) { char c = inFASTA.get(); if (c == 10 || c == 13){ break; } }
+ Sequence currSeq(in); m->gobble(in);
+ out << currSeq.getName() << '\t' << it->second << endl;
}
- outGroups.close();
- inFASTA.close();
+ in.close();
+ out.close();
}
}
- for (set<string>::iterator itBlanks = blanks.begin(); itBlanks != blanks.end(); itBlanks++) { remove((*(itBlanks)).c_str()); }
+ if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; }
+
+ //output group counts
+ m->mothurOutEndLine();
+ int total = 0;
+ if (groupCounts.size() != 0) { m->mothurOut("Group count: \n"); }
+ for (map<string, int>::iterator it = groupCounts.begin(); it != groupCounts.end(); it++) {
+ total += it->second; m->mothurOut(it->first + "\t" + toString(it->second)); m->mothurOutEndLine();
+ }
+ if (total != 0) { m->mothurOut("Total of all groups is " + toString(total)); m->mothurOutEndLine(); }
- blanks.clear();
- if(qFileName != ""){
- for(int i=0;i<qualFileNames.size();i++){
- if (m->isBlank(qualFileNames[i])) { blanks.insert(qualFileNames[i]); }
- else if (filesToRemove.count(qualFileNames[i]) > 0) { remove(qualFileNames[i].c_str()); }
- }
+ if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; }
+
+ //set fasta file as new current fastafile
+ string current = "";
+ itTypes = outputTypes.find("fasta");
+ if (itTypes != outputTypes.end()) {
+ if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setFastaFile(current); }
+ }
+
+ itTypes = outputTypes.find("name");
+ if (itTypes != outputTypes.end()) {
+ if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setNameFile(current); }
}
- for (set<string>::iterator itBlanks = blanks.begin(); itBlanks != blanks.end(); itBlanks++) { remove((*(itBlanks)).c_str()); }
+ itTypes = outputTypes.find("qfile");
+ if (itTypes != outputTypes.end()) {
+ if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setQualFile(current); }
+ }
- if (m->control_pressed) {
- for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); }
- return 0;
+ itTypes = outputTypes.find("group");
+ if (itTypes != outputTypes.end()) {
+ if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setGroupFile(current); }
}
m->mothurOutEndLine();
/**************************************************************************************/
-int TrimSeqsCommand::driverCreateTrim(string filename, string qFileName, string trimFile, string scrapFile, string trimQFile, string scrapQFile, string groupFile, vector<string> fastaNames, vector<string> qualNames, linePair* line, linePair* qline) {
+int TrimSeqsCommand::driverCreateTrim(string filename, string qFileName, string trimFileName, string scrapFileName, string trimQFileName, string scrapQFileName, string trimNFileName, string scrapNFileName, string groupFileName, vector<vector<string> > fastaFileNames, vector<vector<string> > qualFileNames, vector<vector<string> > nameFileNames, linePair* line, linePair* qline) {
try {
- ofstream outFASTA;
- m->openOutputFile(trimFile, outFASTA);
+ ofstream trimFASTAFile;
+ m->openOutputFile(trimFileName, trimFASTAFile);
- ofstream scrapFASTA;
- m->openOutputFile(scrapFile, scrapFASTA);
+ ofstream scrapFASTAFile;
+ m->openOutputFile(scrapFileName, scrapFASTAFile);
- ofstream outQual;
- ofstream scrapQual;
+ ofstream trimQualFile;
+ ofstream scrapQualFile;
if(qFileName != ""){
- m->openOutputFile(trimQFile, outQual);
- m->openOutputFile(scrapQFile, scrapQual);
+ m->openOutputFile(trimQFileName, trimQualFile);
+ m->openOutputFile(scrapQFileName, scrapQualFile);
+ }
+
+ ofstream trimNameFile;
+ ofstream scrapNameFile;
+ if(nameFile != ""){
+ m->openOutputFile(trimNFileName, trimNameFile);
+ m->openOutputFile(scrapNFileName, scrapNameFile);
}
- ofstream outGroups;
- if (oligoFile != "") {
- m->openOutputFile(groupFile, outGroups);
+ ofstream outGroupsFile;
+ if (createGroup){ m->openOutputFile(groupFileName, outGroupsFile); }
+ if(allFiles){
+ for (int i = 0; i < fastaFileNames.size(); i++) { //clears old file
+ for (int j = 0; j < fastaFileNames[i].size(); j++) { //clears old file
+ if (fastaFileNames[i][j] != "") {
+ ofstream temp;
+ m->openOutputFile(fastaFileNames[i][j], temp); temp.close();
+ if(qFileName != ""){
+ m->openOutputFile(qualFileNames[i][j], temp); temp.close();
+ }
+
+ if(nameFile != ""){
+ m->openOutputFile(nameFileNames[i][j], temp); temp.close();
+ }
+ }
+ }
+ }
}
ifstream inFASTA;
inFASTA.seekg(line->start);
ifstream qFile;
- if(qFileName != "") { m->openInputFile(qFileName, qFile); qFile.seekg(qline->start); }
-
-
- for (int i = 0; i < fastaNames.size(); i++) { //clears old file
- ofstream temp;
- m->openOutputFile(fastaNames[i], temp);
- temp.close();
- }
- for (int i = 0; i < qualNames.size(); i++) { //clears old file
- ofstream temp;
- m->openOutputFile(qualNames[i], temp);
- temp.close();
+ if(qFileName != "") {
+ m->openInputFile(qFileName, qFile);
+ qFile.seekg(qline->start);
}
-
- bool done = false;
int count = 0;
+ bool moreSeqs = 1;
+ TrimOligos trimOligos(pdiffs, bdiffs, primers, barcodes, revPrimer);
- while (!done) {
+ while (moreSeqs) {
if (m->control_pressed) {
- inFASTA.close(); outFASTA.close(); scrapFASTA.close();
- if (oligoFile != "") { outGroups.close(); }
+ inFASTA.close(); trimFASTAFile.close(); scrapFASTAFile.close();
+ if (createGroup) { outGroupsFile.close(); }
if(qFileName != ""){
qFile.close();
}
- for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); }
+ for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); }
return 0;
}
int success = 1;
-
+ string trashCode = "";
+ int currentSeqsDiffs = 0;
Sequence currSeq(inFASTA); m->gobble(inFASTA);
-
+ //cout << currSeq.getName() << '\t' << currSeq.getUnaligned().length() << endl;
QualityScores currQual;
if(qFileName != ""){
- currQual = QualityScores(qFile, currSeq.getNumBases()); m->gobble(qFile);
+ currQual = QualityScores(qFile); m->gobble(qFile);
}
string origSeq = currSeq.getUnaligned();
if (origSeq != "") {
- int groupBar, groupPrime;
- string trashCode = "";
- int currentSeqsDiffs = 0;
-
+
+ int barcodeIndex = 0;
+ int primerIndex = 0;
+
if(barcodes.size() != 0){
- success = stripBarcode(currSeq, currQual, groupBar);
+ success = trimOligos.stripBarcode(currSeq, currQual, barcodeIndex);
if(success > bdiffs) { trashCode += 'b'; }
else{ currentSeqsDiffs += success; }
}
if(numFPrimers != 0){
- success = stripForward(currSeq, currQual, groupPrime);
+ success = trimOligos.stripForward(currSeq, currQual, primerIndex);
if(success > pdiffs) { trashCode += 'f'; }
else{ currentSeqsDiffs += success; }
}
if (currentSeqsDiffs > tdiffs) { trashCode += 't'; }
if(numRPrimers != 0){
- success = stripReverse(currSeq, currQual);
+ success = trimOligos.stripReverse(currSeq, currQual);
if(!success) { trashCode += 'r'; }
}
else { success = 1; }
//you don't want to trim, if it fails above then scrap it
- if ((!qtrim) && (origLength != currSeq.getNumBases())) { success = 0; }
+ if ((!qtrim) && (origLength != currSeq.getNumBases())) { success = 0; }
if(!success) { trashCode += 'q'; }
}
if(flip){ // should go last
currSeq.reverseComplement();
- currQual.flipQScores();
+ if(qFileName != ""){
+ currQual.flipQScores();
+ }
}
if(trashCode.length() == 0){
currSeq.setAligned(currSeq.getUnaligned());
- currSeq.printSequence(outFASTA);
- currQual.printQScores(outQual);
+ currSeq.printSequence(trimFASTAFile);
- if(barcodes.size() != 0){
- string thisGroup = groupVector[groupBar];
- int indexToFastaFile = groupBar;
- if (primers.size() != 0){
- //does this primer have a group
- if (groupVector[groupPrime] != "") {
- thisGroup += "." + groupVector[groupPrime];
- indexToFastaFile = combos[thisGroup];
+ if(qFileName != ""){
+ currQual.printQScores(trimQualFile);
+ }
+
+ if(nameFile != ""){
+ map<string, string>::iterator itName = nameMap.find(currSeq.getName());
+ if (itName != nameMap.end()) { trimNameFile << itName->first << '\t' << itName->second << endl; }
+ else { m->mothurOut("[ERROR]: " + currSeq.getName() + " is not in your namefile, please correct."); m->mothurOutEndLine(); }
+ }
+
+ if (createGroup) {
+ if(barcodes.size() != 0){
+ string thisGroup = barcodeNameVector[barcodeIndex];
+ if (primers.size() != 0) {
+ if (primerNameVector[primerIndex] != "") {
+ if(thisGroup != "") {
+ thisGroup += "." + primerNameVector[primerIndex];
+ }else {
+ thisGroup = primerNameVector[primerIndex];
+ }
+ }
}
- }
- outGroups << currSeq.getName() << '\t' << thisGroup << endl;
- if(allFiles){
- ofstream outTemp;
- m->openOutputFileAppend(fastaNames[indexToFastaFile], outTemp);
- //currSeq.printSequence(*fastaFileNames[indexToFastaFile]);
- currSeq.printSequence(outTemp);
- outTemp.close();
- if(qFileName != ""){
- //currQual.printQScores(*qualFileNames[indexToFastaFile]);
- ofstream outTemp2;
- m->openOutputFileAppend(qualNames[indexToFastaFile], outTemp2);
- currQual.printQScores(outTemp2);
- outTemp2.close();
+ outGroupsFile << currSeq.getName() << '\t' << thisGroup << endl;
+
+ if (nameFile != "") {
+ map<string, string>::iterator itName = nameMap.find(currSeq.getName());
+ if (itName != nameMap.end()) {
+ vector<string> thisSeqsNames;
+ m->splitAtChar(itName->second, thisSeqsNames, ',');
+ for (int k = 1; k < thisSeqsNames.size(); k++) { //start at 1 to skip self
+ outGroupsFile << thisSeqsNames[k] << '\t' << thisGroup << endl;
+ }
+ }else { m->mothurOut("[ERROR]: " + currSeq.getName() + " is not in your namefile, please correct."); m->mothurOutEndLine(); }
}
+
+ map<string, int>::iterator it = groupCounts.find(thisGroup);
+ if (it == groupCounts.end()) { groupCounts[thisGroup] = 1; }
+ else { groupCounts[it->first]++; }
+
}
}
- if (groupfile != "") {
- string thisGroup = groupMap->getGroup(currSeq.getName());
+ if(allFiles){
+ ofstream output;
+ m->openOutputFileAppend(fastaFileNames[barcodeIndex][primerIndex], output);
+ currSeq.printSequence(output);
+ output.close();
- if (thisGroup != "not found") {
- outGroups << currSeq.getName() << '\t' << thisGroup << endl;
- if (allFiles) {
- ofstream outTemp;
- m->openOutputFileAppend(fastaNames[groupToIndex[thisGroup]], outTemp);
- currSeq.printSequence(outTemp);
- outTemp.close();
- if(qFileName != ""){
- ofstream outTemp2;
- m->openOutputFileAppend(qualNames[groupToIndex[thisGroup]], outTemp2);
- currQual.printQScores(outTemp2);
- outTemp2.close();
- }
- }
- }else{
- m->mothurOut(currSeq.getName() + " is not in your groupfile, adding to group XXX."); m->mothurOutEndLine();
- outGroups << currSeq.getName() << '\t' << "XXX" << endl;
- if (allFiles) {
- m->mothurOut("[ERROR]: " + currSeq.getName() + " will not be added to any .group.fasta or .group.qual file."); m->mothurOutEndLine();
- }
+ if(qFileName != ""){
+ m->openOutputFileAppend(qualFileNames[barcodeIndex][primerIndex], output);
+ currQual.printQScores(output);
+ output.close();
+ }
+
+ if(nameFile != ""){
+ map<string, string>::iterator itName = nameMap.find(currSeq.getName());
+ if (itName != nameMap.end()) {
+ m->openOutputFileAppend(nameFileNames[barcodeIndex][primerIndex], output);
+ output << itName->first << '\t' << itName->second << endl;
+ output.close();
+ }else { m->mothurOut("[ERROR]: " + currSeq.getName() + " is not in your namefile, please correct."); m->mothurOutEndLine(); }
}
}
}
else{
+ if(nameFile != ""){ //needs to be before the currSeq name is changed
+ map<string, string>::iterator itName = nameMap.find(currSeq.getName());
+ if (itName != nameMap.end()) { scrapNameFile << itName->first << '\t' << itName->second << endl; }
+ else { m->mothurOut("[ERROR]: " + currSeq.getName() + " is not in your namefile, please correct."); m->mothurOutEndLine(); }
+ }
currSeq.setName(currSeq.getName() + '|' + trashCode);
currSeq.setUnaligned(origSeq);
currSeq.setAligned(origSeq);
- currSeq.printSequence(scrapFASTA);
- currQual.printQScores(scrapQual);
+ currSeq.printSequence(scrapFASTAFile);
+ if(qFileName != ""){
+ currQual.printQScores(scrapQualFile);
+ }
}
count++;
}
#if defined (__APPLE__) || (__MACH__) || (linux) || (__linux)
- unsigned long int pos = inFASTA.tellg();
+ unsigned long long pos = inFASTA.tellg();
if ((pos == -1) || (pos >= line->end)) { break; }
+
#else
if (inFASTA.eof()) { break; }
#endif
-
+
//report progress
if((count) % 1000 == 0){ m->mothurOut(toString(count)); m->mothurOutEndLine(); }
}
//report progress
if((count) % 1000 != 0){ m->mothurOut(toString(count)); m->mothurOutEndLine(); }
-
+
inFASTA.close();
- outFASTA.close();
- scrapFASTA.close();
- if (oligoFile != "") { outGroups.close(); }
- if(qFileName != "") { qFile.close(); scrapQual.close(); outQual.close(); }
+ trimFASTAFile.close();
+ scrapFASTAFile.close();
+ if (createGroup) { outGroupsFile.close(); }
+ if(qFileName != "") { qFile.close(); scrapQualFile.close(); trimQualFile.close(); }
+ if(nameFile != "") { scrapNameFile.close(); trimNameFile.close(); }
return count;
}
/**************************************************************************************************/
-int TrimSeqsCommand::createProcessesCreateTrim(string filename, string qFileName, string trimFile, string scrapFile, string trimQFile, string scrapQFile, string groupFile, vector<string> fastaNames, vector<string> qualNames) {
+int TrimSeqsCommand::createProcessesCreateTrim(string filename, string qFileName, string trimFASTAFileName, string scrapFASTAFileName, string trimQualFileName, string scrapQualFileName, string trimNameFileName, string scrapNameFileName, string groupFile, vector<vector<string> > fastaFileNames, vector<vector<string> > qualFileNames, vector<vector<string> > nameFileNames) {
try {
#if defined (__APPLE__) || (__MACH__) || (linux) || (__linux)
int process = 1;
processIDS.push_back(pid); //create map from line number to pid so you can append files in correct order later
process++;
}else if (pid == 0){
- for (int i = 0; i < fastaNames.size(); i++) {
- fastaNames[i] = (fastaNames[i] + toString(getpid()) + ".temp");
- //clear old file if it exists
+
+ vector<vector<string> > tempFASTAFileNames = fastaFileNames;
+ vector<vector<string> > tempPrimerQualFileNames = qualFileNames;
+ vector<vector<string> > tempNameFileNames = nameFileNames;
+
+ if(allFiles){
ofstream temp;
- m->openOutputFile(fastaNames[i], temp);
- temp.close();
- if(qFileName != ""){
- qualNames[i] = (qualNames[i] + toString(getpid()) + ".temp");
- //clear old file if it exists
- ofstream temp2;
- m->openOutputFile(qualNames[i], temp2);
- temp2.close();
+
+ for(int i=0;i<tempFASTAFileNames.size();i++){
+ for(int j=0;j<tempFASTAFileNames[i].size();j++){
+ if (tempFASTAFileNames[i][j] != "") {
+ tempFASTAFileNames[i][j] += toString(getpid()) + ".temp";
+ m->openOutputFile(tempFASTAFileNames[i][j], temp); temp.close();
+
+ if(qFileName != ""){
+ tempPrimerQualFileNames[i][j] += toString(getpid()) + ".temp";
+ m->openOutputFile(tempPrimerQualFileNames[i][j], temp); temp.close();
+ }
+ if(nameFile != ""){
+ tempNameFileNames[i][j] += toString(getpid()) + ".temp";
+ m->openOutputFile(tempNameFileNames[i][j], temp); temp.close();
+ }
+ }
+ }
}
}
+
+ driverCreateTrim(filename,
+ qFileName,
+ (trimFASTAFileName + toString(getpid()) + ".temp"),
+ (scrapFASTAFileName + toString(getpid()) + ".temp"),
+ (trimQualFileName + toString(getpid()) + ".temp"),
+ (scrapQualFileName + toString(getpid()) + ".temp"),
+ (trimNameFileName + toString(getpid()) + ".temp"),
+ (scrapNameFileName + toString(getpid()) + ".temp"),
+ (groupFile + toString(getpid()) + ".temp"),
+ tempFASTAFileNames,
+ tempPrimerQualFileNames,
+ tempNameFileNames,
+ lines[process],
+ qLines[process]);
- driverCreateTrim(filename, qFileName, (trimFile + toString(getpid()) + ".temp"), (scrapFile + toString(getpid()) + ".temp"), (trimQFile + toString(getpid()) + ".temp"), (scrapQFile + toString(getpid()) + ".temp"), (groupFile + toString(getpid()) + ".temp"), fastaNames, qualNames, lines[process], qLines[process]);
+ //pass groupCounts to parent
+ if(createGroup){
+ ofstream out;
+ string tempFile = filename + toString(getpid()) + ".num.temp";
+ m->openOutputFile(tempFile, out);
+
+ out << groupCounts.size() << endl;
+
+ for (map<string, int>::iterator it = groupCounts.begin(); it != groupCounts.end(); it++) {
+ out << it->first << '\t' << it->second << endl;
+ }
+ out.close();
+ }
exit(0);
}else {
m->mothurOut("[ERROR]: unable to spawn the necessary processes."); m->mothurOutEndLine();
}
//parent do my part
- for (int i = 0; i < fastaNames.size(); i++) {
- //clear old file if it exists
- ofstream temp;
- m->openOutputFile(fastaNames[i], temp);
- temp.close();
- if(qFileName != ""){
- //clear old file if it exists
- ofstream temp2;
- m->openOutputFile(qualNames[i], temp2);
- temp2.close();
- }
+ ofstream temp;
+ m->openOutputFile(trimFASTAFileName, temp); temp.close();
+ m->openOutputFile(scrapFASTAFileName, temp); temp.close();
+ if(qFileName != ""){
+ m->openOutputFile(trimQualFileName, temp); temp.close();
+ m->openOutputFile(scrapQualFileName, temp); temp.close();
}
-
- driverCreateTrim(filename, qFileName, trimFile, scrapFile, trimQFile, scrapQFile, groupFile, fastaNames, qualNames, lines[0], qLines[0]);
-
+ if (nameFile != "") {
+ m->openOutputFile(trimNameFileName, temp); temp.close();
+ m->openOutputFile(scrapNameFileName, temp); temp.close();
+ }
+
+ driverCreateTrim(filename, qFileName, trimFASTAFileName, scrapFASTAFileName, trimQualFileName, scrapQualFileName, trimNameFileName, scrapNameFileName, groupFile, fastaFileNames, qualFileNames, nameFileNames, lines[0], qLines[0]);
//force parent to wait until all the processes are done
for (int i=0;i<processIDS.size();i++) {
m->mothurOut("Appending files from process " + toString(processIDS[i])); m->mothurOutEndLine();
- m->appendFiles((trimFile + toString(processIDS[i]) + ".temp"), trimFile);
- remove((trimFile + toString(processIDS[i]) + ".temp").c_str());
- m->appendFiles((scrapFile + toString(processIDS[i]) + ".temp"), scrapFile);
- remove((scrapFile + toString(processIDS[i]) + ".temp").c_str());
-
- m->mothurOut("Done with fasta files"); m->mothurOutEndLine();
+ m->appendFiles((trimFASTAFileName + toString(processIDS[i]) + ".temp"), trimFASTAFileName);
+ m->mothurRemove((trimFASTAFileName + toString(processIDS[i]) + ".temp"));
+ m->appendFiles((scrapFASTAFileName + toString(processIDS[i]) + ".temp"), scrapFASTAFileName);
+ m->mothurRemove((scrapFASTAFileName + toString(processIDS[i]) + ".temp"));
if(qFileName != ""){
- m->appendFiles((trimQFile + toString(processIDS[i]) + ".temp"), trimQFile);
- remove((trimQFile + toString(processIDS[i]) + ".temp").c_str());
- m->appendFiles((scrapQFile + toString(processIDS[i]) + ".temp"), scrapQFile);
- remove((scrapQFile + toString(processIDS[i]) + ".temp").c_str());
+ m->appendFiles((trimQualFileName + toString(processIDS[i]) + ".temp"), trimQualFileName);
+ m->mothurRemove((trimQualFileName + toString(processIDS[i]) + ".temp"));
+ m->appendFiles((scrapQualFileName + toString(processIDS[i]) + ".temp"), scrapQualFileName);
+ m->mothurRemove((scrapQualFileName + toString(processIDS[i]) + ".temp"));
+ }
- m->mothurOut("Done with quality files"); m->mothurOutEndLine();
+ if(nameFile != ""){
+ m->appendFiles((trimNameFileName + toString(processIDS[i]) + ".temp"), trimNameFileName);
+ m->mothurRemove((trimNameFileName + toString(processIDS[i]) + ".temp"));
+ m->appendFiles((scrapNameFileName + toString(processIDS[i]) + ".temp"), scrapNameFileName);
+ m->mothurRemove((scrapNameFileName + toString(processIDS[i]) + ".temp"));
}
- m->appendFiles((groupFile + toString(processIDS[i]) + ".temp"), groupFile);
- remove((groupFile + toString(processIDS[i]) + ".temp").c_str());
+ if(createGroup){
+ m->appendFiles((groupFile + toString(processIDS[i]) + ".temp"), groupFile);
+ m->mothurRemove((groupFile + toString(processIDS[i]) + ".temp"));
+ }
- m->mothurOut("Done with group file"); m->mothurOutEndLine();
- for (int j = 0; j < fastaNames.size(); j++) {
- m->appendFiles((fastaNames[j] + toString(processIDS[i]) + ".temp"), fastaNames[j]);
- remove((fastaNames[j] + toString(processIDS[i]) + ".temp").c_str());
+ if(allFiles){
+ for(int j=0;j<fastaFileNames.size();j++){
+ for(int k=0;k<fastaFileNames[j].size();k++){
+ if (fastaFileNames[j][k] != "") {
+ m->appendFiles((fastaFileNames[j][k] + toString(processIDS[i]) + ".temp"), fastaFileNames[j][k]);
+ m->mothurRemove((fastaFileNames[j][k] + toString(processIDS[i]) + ".temp"));
+
+ if(qFileName != ""){
+ m->appendFiles((qualFileNames[j][k] + toString(processIDS[i]) + ".temp"), qualFileNames[j][k]);
+ m->mothurRemove((qualFileNames[j][k] + toString(processIDS[i]) + ".temp"));
+ }
+
+ if(nameFile != ""){
+ m->appendFiles((nameFileNames[j][k] + toString(processIDS[i]) + ".temp"), nameFileNames[j][k]);
+ m->mothurRemove((nameFileNames[j][k] + toString(processIDS[i]) + ".temp"));
+ }
+ }
+ }
+ }
}
- if(qFileName != ""){
- for (int j = 0; j < qualNames.size(); j++) {
- m->appendFiles((qualNames[j] + toString(processIDS[i]) + ".temp"), qualNames[j]);
- remove((qualNames[j] + toString(processIDS[i]) + ".temp").c_str());
+ if(createGroup){
+ ifstream in;
+ string tempFile = filename + toString(processIDS[i]) + ".num.temp";
+ m->openInputFile(tempFile, in);
+ int tempNum;
+ string group;
+
+ in >> tempNum; m->gobble(in);
+
+ if (tempNum != 0) {
+ while (!in.eof()) {
+ in >> group >> tempNum; m->gobble(in);
+
+ map<string, int>::iterator it = groupCounts.find(group);
+ if (it == groupCounts.end()) { groupCounts[group] = tempNum; }
+ else { groupCounts[it->first] += tempNum; }
+ }
}
+ in.close(); m->mothurRemove(tempFile);
}
- if (allFiles) { m->mothurOut("Done with allfiles"); m->mothurOutEndLine(); }
}
return exitCommand;
/**************************************************************************************************/
-int TrimSeqsCommand::setLines(string filename, string qfilename, vector<unsigned long int>& fastaFilePos, vector<unsigned long int>& qfileFilePos) {
+int TrimSeqsCommand::setLines(string filename, string qfilename, vector<unsigned long long>& fastaFilePos, vector<unsigned long long>& qfileFilePos) {
try {
-
+ #if defined (__APPLE__) || (__MACH__) || (linux) || (__linux)
//set file positions for fasta file
fastaFilePos = m->divideFile(filename, processors);
map<string, int>::iterator it = firstSeqNames.find(sname);
if(it != firstSeqNames.end()) { //this is the start of a new chunk
- unsigned long int pos = inQual.tellg();
+ unsigned long long pos = inQual.tellg();
qfileFilePos.push_back(pos - input.length() - 1);
firstSeqNames.erase(it);
}
//get last file position of qfile
FILE * pFile;
- unsigned long int size;
+ unsigned long long size;
//get num bytes in file
pFile = fopen (qfilename.c_str(),"rb");
qfileFilePos.push_back(size);
return processors;
+
+ #else
+
+ fastaFilePos.push_back(0); qfileFilePos.push_back(0);
+ //get last file position of fastafile
+ FILE * pFile;
+ unsigned long long size;
+
+ //get num bytes in file
+ pFile = fopen (filename.c_str(),"rb");
+ if (pFile==NULL) perror ("Error opening file");
+ else{
+ fseek (pFile, 0, SEEK_END);
+ size=ftell (pFile);
+ fclose (pFile);
+ }
+ fastaFilePos.push_back(size);
+
+ //get last file position of fastafile
+ FILE * qFile;
+
+ //get num bytes in file
+ qFile = fopen (qfilename.c_str(),"rb");
+ if (qFile==NULL) perror ("Error opening file");
+ else{
+ fseek (qFile, 0, SEEK_END);
+ size=ftell (qFile);
+ fclose (qFile);
+ }
+ qfileFilePos.push_back(size);
+
+ return 1;
+
+ #endif
}
catch(exception& e) {
m->errorOut(e, "TrimSeqsCommand", "setLines");
//***************************************************************************************************************
-void TrimSeqsCommand::getOligos(vector<string>& outFASTAVec, vector<string>& outQualVec){
+bool TrimSeqsCommand::getOligos(vector<vector<string> >& fastaFileNames, vector<vector<string> >& qualFileNames, vector<vector<string> >& nameFileNames){
try {
ifstream inOligos;
m->openInputFile(oligoFile, inOligos);
ofstream test;
string type, oligo, group;
- int index=0;
- //int indexPrimer = 0;
+
+ int indexPrimer = 0;
+ int indexBarcode = 0;
while(!inOligos.eof()){
- inOligos >> type; m->gobble(inOligos);
+
+ inOligos >> type;
if(type[0] == '#'){
- while (!inOligos.eof()) { char c = inOligos.get(); if (c == 10 || c == 13){ break; } } // get rest of line if there's any crap there
+ while (!inOligos.eof()) { char c = inOligos.get(); if (c == 10 || c == 13){ break; } } // get rest of line if there's any crap there
+ m->gobble(inOligos);
}
else{
+ m->gobble(inOligos);
//make type case insensitive
for(int i=0;i<type.length();i++){ type[i] = toupper(type[i]); }
map<string, int>::iterator itPrime = primers.find(oligo);
if (itPrime != primers.end()) { m->mothurOut("primer " + oligo + " is in your oligos file already."); m->mothurOutEndLine(); }
- primers[oligo]=index; index++;
- groupVector.push_back(group);
-
- if(allFiles){
- outFASTAVec.push_back((outputDir + m->getRootName(m->getSimpleName(fastaFile)) + group + ".fasta"));
- if(qFileName != ""){
- outQualVec.push_back((outputDir + m->getRootName(m->getSimpleName(qFileName)) + group + ".qual"));
- }
- if (group == "") { //if there is not a group for this primer, then this file will not get written to, but we add it to keep the indexes correct
- filesToRemove.insert((outputDir + m->getRootName(m->getSimpleName(fastaFile)) + group + ".fasta"));
- if(qFileName != ""){
- filesToRemove.insert((outputDir + m->getRootName(m->getSimpleName(qFileName)) + group + ".qual"));
- }
- }else {
- outputNames.push_back((outputDir + m->getRootName(m->getSimpleName(fastaFile)) + group + ".fasta"));
- outputTypes["fasta"].push_back((outputDir + m->getRootName(m->getSimpleName(fastaFile)) + group + ".fasta"));
- if(qFileName != ""){
- outputNames.push_back((outputDir + m->getRootName(m->getSimpleName(qFileName)) + group + ".qual"));
- outputTypes["qual"].push_back((outputDir + m->getRootName(m->getSimpleName(qFileName)) + group + ".qual"));
- }
- }
- }
-
+ primers[oligo]=indexPrimer; indexPrimer++;
+ primerNameVector.push_back(group);
}
else if(type == "REVERSE"){
Sequence oligoRC("reverse", oligo);
//check for repeat barcodes
map<string, int>::iterator itBar = barcodes.find(oligo);
if (itBar != barcodes.end()) { m->mothurOut("barcode " + oligo + " is in your oligos file already."); m->mothurOutEndLine(); }
-
- barcodes[oligo]=index; index++;
- groupVector.push_back(group);
- if(allFiles){
- outputNames.push_back((outputDir + m->getRootName(m->getSimpleName(fastaFile)) + group + ".fasta"));
- outputNames.push_back((outputDir + m->getRootName(m->getSimpleName(fastaFile)) + group + ".fasta"));
- outFASTAVec.push_back((outputDir + m->getRootName(m->getSimpleName(fastaFile)) + group + ".fasta"));
- if(qFileName != ""){
- outQualVec.push_back((outputDir + m->getRootName(m->getSimpleName(qFileName)) + group + ".qual"));
- outputNames.push_back((outputDir + m->getRootName(m->getSimpleName(qFileName)) + group + ".qual"));
- outputTypes["qual"].push_back((outputDir + m->getRootName(m->getSimpleName(qFileName)) + group + ".qual"));
- }
- }
-
- }else{ m->mothurOut(type + " is not recognized as a valid type. Choices are forward, reverse, and barcode. Ignoring " + oligo + "."); m->mothurOutEndLine(); }
+ barcodes[oligo]=indexBarcode; indexBarcode++;
+ barcodeNameVector.push_back(group);
+ }
+ else{ m->mothurOut(type + " is not recognized as a valid type. Choices are forward, reverse, and barcode. Ignoring " + oligo + "."); m->mothurOutEndLine(); }
}
m->gobble(inOligos);
- }
-
+ }
inOligos.close();
+ if(barcodeNameVector.size() == 0 && primerNameVector[0] == ""){ allFiles = 0; }
+
//add in potential combos
- if(allFiles){
- comboStarts = outFASTAVec.size()-1;
- for (map<string, int>::iterator itBar = barcodes.begin(); itBar != barcodes.end(); itBar++) {
- for (map<string, int>::iterator itPrime = primers.begin(); itPrime != primers.end(); itPrime++) {
- if (groupVector[itPrime->second] != "") { //there is a group for this primer
- outputNames.push_back((outputDir + m->getRootName(m->getSimpleName(qFileName)) + groupVector[itBar->second] + "." + groupVector[itPrime->second] + ".fasta"));
- outputTypes["fasta"].push_back((outputDir + m->getRootName(m->getSimpleName(qFileName)) + groupVector[itBar->second] + "." + groupVector[itPrime->second] + ".fasta"));
- outFASTAVec.push_back((outputDir + m->getRootName(m->getSimpleName(fastaFile)) + groupVector[itBar->second] + "." + groupVector[itPrime->second] + ".fasta"));
- combos[(groupVector[itBar->second] + "." + groupVector[itPrime->second])] = outFASTAVec.size()-1;
-
- if(qFileName != ""){
- outQualVec.push_back((outputDir + m->getRootName(m->getSimpleName(qFileName)) + groupVector[itBar->second] + "." + groupVector[itPrime->second] + ".qual"));
- outputNames.push_back((outputDir + m->getRootName(m->getSimpleName(qFileName)) + groupVector[itBar->second] + "." + groupVector[itPrime->second] + ".qual"));
- outputTypes["qual"].push_back((outputDir + m->getRootName(m->getSimpleName(qFileName)) + groupVector[itBar->second] + "." + groupVector[itPrime->second] + ".qual"));
- }
- }
- }
- }
+ if(barcodeNameVector.size() == 0){
+ barcodes[""] = 0;
+ barcodeNameVector.push_back("");
}
- numFPrimers = primers.size();
- numRPrimers = revPrimer.size();
-
- }
- catch(exception& e) {
- m->errorOut(e, "TrimSeqsCommand", "getOligos");
- exit(1);
- }
-}
-//***************************************************************************************************************
-
-int TrimSeqsCommand::stripBarcode(Sequence& seq, QualityScores& qual, int& group){
- try {
-
- string rawSequence = seq.getUnaligned();
- int success = bdiffs + 1; //guilty until proven innocent
-
- //can you find the barcode
- for(map<string,int>::iterator it=barcodes.begin();it!=barcodes.end();it++){
- string oligo = it->first;
- if(rawSequence.length() < oligo.length()){ //let's just assume that the barcodes are the same length
- success = bdiffs + 10; //if the sequence is shorter than the barcode then bail out
- break;
- }
-
- if(compareDNASeq(oligo, rawSequence.substr(0,oligo.length()))){
- group = it->second;
- seq.setUnaligned(rawSequence.substr(oligo.length()));
-
- if(qual.getName() != ""){
- qual.trimQScores(oligo.length(), -1);
- }
-
- success = 0;
- break;
- }
+ if(primerNameVector.size() == 0){
+ primers[""] = 0;
+ primerNameVector.push_back("");
}
- //if you found the barcode or if you don't want to allow for diffs
-// cout << success;
- if ((bdiffs == 0) || (success == 0)) { return success; }
+ fastaFileNames.resize(barcodeNameVector.size());
+ for(int i=0;i<fastaFileNames.size();i++){
+ fastaFileNames[i].assign(primerNameVector.size(), "");
+ }
+ if(qFileName != "") { qualFileNames = fastaFileNames; }
+ if(nameFile != "") { nameFileNames = fastaFileNames; }
- else { //try aligning and see if you can find it
-// cout << endl;
-
- int maxLength = 0;
-
- Alignment* alignment;
- if (barcodes.size() > 0) {
- map<string,int>::iterator it=barcodes.begin();
-
- for(it;it!=barcodes.end();it++){
- if(it->first.length() > maxLength){
- maxLength = it->first.length();
+ if(allFiles){
+ set<string> uniqueNames; //used to cleanup outputFileNames
+ for(map<string, int>::iterator itBar = barcodes.begin();itBar != barcodes.end();itBar++){
+ for(map<string, int>::iterator itPrimer = primers.begin();itPrimer != primers.end(); itPrimer++){
+
+ string primerName = primerNameVector[itPrimer->second];
+ string barcodeName = barcodeNameVector[itBar->second];
+
+ string comboGroupName = "";
+ string fastaFileName = "";
+ string qualFileName = "";
+ string nameFileName = "";
+
+ if(primerName == ""){
+ comboGroupName = barcodeNameVector[itBar->second];
}
- }
- alignment = new NeedlemanOverlap(-1.0, 1.0, -1.0, (maxLength+bdiffs+1));
-
- }else{ alignment = NULL; }
-
- //can you find the barcode
- int minDiff = 1e6;
- int minCount = 1;
- int minGroup = -1;
- int minPos = 0;
-
- for(map<string,int>::iterator it=barcodes.begin();it!=barcodes.end();it++){
- string oligo = it->first;
-// int length = oligo.length();
-
- if(rawSequence.length() < maxLength){ //let's just assume that the barcodes are the same length
- success = bdiffs + 10;
- break;
- }
-
- //use needleman to align first barcode.length()+numdiffs of sequence to each barcode
- alignment->align(oligo, rawSequence.substr(0,oligo.length()+bdiffs));
- oligo = alignment->getSeqAAln();
- string temp = alignment->getSeqBAln();
-
- int alnLength = oligo.length();
-
- for(int i=oligo.length()-1;i>=0;i--){
- if(oligo[i] != '-'){ alnLength = i+1; break; }
- }
- oligo = oligo.substr(0,alnLength);
- temp = temp.substr(0,alnLength);
-
- int numDiff = countDiffs(oligo, temp);
-
-// cout << oligo << '\t' << temp << '\t' << numDiff << endl;
-
- if(numDiff < minDiff){
- minDiff = numDiff;
- minCount = 1;
- minGroup = it->second;
- minPos = 0;
- for(int i=0;i<alnLength;i++){
- if(temp[i] != '-'){
- minPos++;
+ else{
+ if(barcodeName == ""){
+ comboGroupName = primerNameVector[itPrimer->second];
+ }
+ else{
+ comboGroupName = barcodeNameVector[itBar->second] + "." + primerNameVector[itPrimer->second];
}
}
- }
- else if(numDiff == minDiff){
- minCount++;
- }
-
- }
-
- if(minDiff > bdiffs) { success = minDiff; } //no good matches
- else if(minCount > 1) { success = bdiffs + 100; } //can't tell the difference between multiple barcodes
- else{ //use the best match
- group = minGroup;
- seq.setUnaligned(rawSequence.substr(minPos));
-
- if(qual.getName() != ""){
- qual.trimQScores(minPos, -1);
- }
- success = minDiff;
- }
-
- if (alignment != NULL) { delete alignment; }
-
- }
-// cout << success << endl;
-
- return success;
-
- }
- catch(exception& e) {
- m->errorOut(e, "TrimSeqsCommand", "stripBarcode");
- exit(1);
- }
-
-}
-
-//***************************************************************************************************************
-
-int TrimSeqsCommand::stripForward(Sequence& seq, QualityScores& qual, int& group){
- try {
- string rawSequence = seq.getUnaligned();
- int success = pdiffs + 1; //guilty until proven innocent
-
- //can you find the primer
- for(map<string,int>::iterator it=primers.begin();it!=primers.end();it++){
- string oligo = it->first;
- if(rawSequence.length() < oligo.length()){ //let's just assume that the primers are the same length
- success = pdiffs + 10; //if the sequence is shorter than the barcode then bail out
- break;
- }
-
- if(compareDNASeq(oligo, rawSequence.substr(0,oligo.length()))){
- group = it->second;
- seq.setUnaligned(rawSequence.substr(oligo.length()));
- if(qual.getName() != ""){
- qual.trimQScores(oligo.length(), -1);
- }
- success = 0;
- break;
- }
- }
-
- //if you found the barcode or if you don't want to allow for diffs
-// cout << success;
- if ((pdiffs == 0) || (success == 0)) { return success; }
-
- else { //try aligning and see if you can find it
-// cout << endl;
-
- int maxLength = 0;
-
- Alignment* alignment;
- if (primers.size() > 0) {
- map<string,int>::iterator it=primers.begin();
-
- for(it;it!=primers.end();it++){
- if(it->first.length() > maxLength){
- maxLength = it->first.length();
+
+
+ ofstream temp;
+ fastaFileName = outputDir + m->getRootName(m->getSimpleName(fastaFile)) + comboGroupName + ".fasta";
+ if (uniqueNames.count(fastaFileName) == 0) {
+ outputNames.push_back(fastaFileName);
+ outputTypes["fasta"].push_back(fastaFileName);
+ uniqueNames.insert(fastaFileName);
}
- }
- alignment = new NeedlemanOverlap(-1.0, 1.0, -1.0, (maxLength+pdiffs+1));
-
- }else{ alignment = NULL; }
-
- //can you find the barcode
- int minDiff = 1e6;
- int minCount = 1;
- int minGroup = -1;
- int minPos = 0;
-
- for(map<string,int>::iterator it=primers.begin();it!=primers.end();it++){
- string oligo = it->first;
-// int length = oligo.length();
-
- if(rawSequence.length() < maxLength){
- success = pdiffs + 100;
- break;
- }
-
- //use needleman to align first barcode.length()+numdiffs of sequence to each barcode
- alignment->align(oligo, rawSequence.substr(0,oligo.length()+pdiffs));
- oligo = alignment->getSeqAAln();
- string temp = alignment->getSeqBAln();
-
- int alnLength = oligo.length();
-
- for(int i=oligo.length()-1;i>=0;i--){
- if(oligo[i] != '-'){ alnLength = i+1; break; }
- }
- oligo = oligo.substr(0,alnLength);
- temp = temp.substr(0,alnLength);
-
- int numDiff = countDiffs(oligo, temp);
-
-// cout << oligo << '\t' << temp << '\t' << numDiff << endl;
-
- if(numDiff < minDiff){
- minDiff = numDiff;
- minCount = 1;
- minGroup = it->second;
- minPos = 0;
- for(int i=0;i<alnLength;i++){
- if(temp[i] != '-'){
- minPos++;
+
+ fastaFileNames[itBar->second][itPrimer->second] = fastaFileName;
+ m->openOutputFile(fastaFileName, temp); temp.close();
+
+ if(qFileName != ""){
+ qualFileName = outputDir + m->getRootName(m->getSimpleName(qFileName)) + comboGroupName + ".qual";
+ if (uniqueNames.count(qualFileName) == 0) {
+ outputNames.push_back(qualFileName);
+ outputTypes["qfile"].push_back(qualFileName);
}
+
+ qualFileNames[itBar->second][itPrimer->second] = qualFileName;
+ m->openOutputFile(qualFileName, temp); temp.close();
}
+
+ if(nameFile != ""){
+ nameFileName = outputDir + m->getRootName(m->getSimpleName(nameFile)) + comboGroupName + ".names";
+ if (uniqueNames.count(nameFileName) == 0) {
+ outputNames.push_back(nameFileName);
+ outputTypes["name"].push_back(nameFileName);
+ }
+
+ nameFileNames[itBar->second][itPrimer->second] = nameFileName;
+ m->openOutputFile(nameFileName, temp); temp.close();
+ }
+
}
- else if(numDiff == minDiff){
- minCount++;
- }
-
- }
-
- if(minDiff > pdiffs) { success = minDiff; } //no good matches
- else if(minCount > 1) { success = pdiffs + 10; } //can't tell the difference between multiple primers
- else{ //use the best match
- group = minGroup;
- seq.setUnaligned(rawSequence.substr(minPos));
- if(qual.getName() != ""){
- qual.trimQScores(minPos, -1);
- }
- success = minDiff;
}
-
- if (alignment != NULL) { delete alignment; }
-
}
+ numFPrimers = primers.size();
+ numRPrimers = revPrimer.size();
- return success;
-
- }
- catch(exception& e) {
- m->errorOut(e, "TrimSeqsCommand", "stripForward");
- exit(1);
- }
-}
-
-//***************************************************************************************************************
-
-bool TrimSeqsCommand::stripReverse(Sequence& seq, QualityScores& qual){
- try {
- string rawSequence = seq.getUnaligned();
- bool success = 0; //guilty until proven innocent
-
- for(int i=0;i<numRPrimers;i++){
- string oligo = revPrimer[i];
-
- if(rawSequence.length() < oligo.length()){
- success = 0;
+ bool allBlank = true;
+ for (int i = 0; i < barcodeNameVector.size(); i++) {
+ if (barcodeNameVector[i] != "") {
+ allBlank = false;
break;
}
-
- if(compareDNASeq(oligo, rawSequence.substr(rawSequence.length()-oligo.length(),oligo.length()))){
- seq.setUnaligned(rawSequence.substr(0,rawSequence.length()-oligo.length()));
- if(qual.getName() != ""){
- qual.trimQScores(-1, rawSequence.length()-oligo.length());
- }
- success = 1;
+ }
+ for (int i = 0; i < primerNameVector.size(); i++) {
+ if (primerNameVector[i] != "") {
+ allBlank = false;
break;
}
- }
- return success;
+ }
+
+ if (allBlank) {
+ m->mothurOut("[WARNING]: your oligos file does not contain any group names. mothur will not create a groupfile."); m->mothurOutEndLine();
+ allFiles = false;
+ return false;
+ }
+
+ return true;
}
catch(exception& e) {
- m->errorOut(e, "TrimSeqsCommand", "stripReverse");
+ m->errorOut(e, "TrimSeqsCommand", "getOligos");
exit(1);
}
}
-
//***************************************************************************************************************
bool TrimSeqsCommand::keepFirstTrim(Sequence& sequence, QualityScores& qscores){
}
}
-
-//***************************************************************************************************************
-
-bool TrimSeqsCommand::compareDNASeq(string oligo, string seq){
- try {
- bool success = 1;
- int length = oligo.length();
-
- for(int i=0;i<length;i++){
-
- if(oligo[i] != seq[i]){
- if(oligo[i] == 'A' || oligo[i] == 'T' || oligo[i] == 'G' || oligo[i] == 'C') { success = 0; }
- else if((oligo[i] == 'N' || oligo[i] == 'I') && (seq[i] == 'N')) { success = 0; }
- else if(oligo[i] == 'R' && (seq[i] != 'A' && seq[i] != 'G')) { success = 0; }
- else if(oligo[i] == 'Y' && (seq[i] != 'C' && seq[i] != 'T')) { success = 0; }
- else if(oligo[i] == 'M' && (seq[i] != 'C' && seq[i] != 'A')) { success = 0; }
- else if(oligo[i] == 'K' && (seq[i] != 'T' && seq[i] != 'G')) { success = 0; }
- else if(oligo[i] == 'W' && (seq[i] != 'T' && seq[i] != 'A')) { success = 0; }
- else if(oligo[i] == 'S' && (seq[i] != 'C' && seq[i] != 'G')) { success = 0; }
- else if(oligo[i] == 'B' && (seq[i] != 'C' && seq[i] != 'T' && seq[i] != 'G')) { success = 0; }
- else if(oligo[i] == 'D' && (seq[i] != 'A' && seq[i] != 'T' && seq[i] != 'G')) { success = 0; }
- else if(oligo[i] == 'H' && (seq[i] != 'A' && seq[i] != 'T' && seq[i] != 'C')) { success = 0; }
- else if(oligo[i] == 'V' && (seq[i] != 'A' && seq[i] != 'C' && seq[i] != 'G')) { success = 0; }
-
- if(success == 0) { break; }
- }
- else{
- success = 1;
- }
- }
-
- return success;
- }
- catch(exception& e) {
- m->errorOut(e, "TrimSeqsCommand", "compareDNASeq");
- exit(1);
- }
-
-}
-
-//***************************************************************************************************************
-
-int TrimSeqsCommand::countDiffs(string oligo, string seq){
- try {
-
- int length = oligo.length();
- int countDiffs = 0;
-
- for(int i=0;i<length;i++){
-
- if(oligo[i] != seq[i]){
- if(oligo[i] == 'A' || oligo[i] == 'T' || oligo[i] == 'G' || oligo[i] == 'C' || oligo[i] == '-' || oligo[i] == '.') { countDiffs++; }
- else if((oligo[i] == 'N' || oligo[i] == 'I') && (seq[i] == 'N')) { countDiffs++; }
- else if(oligo[i] == 'R' && (seq[i] != 'A' && seq[i] != 'G')) { countDiffs++; }
- else if(oligo[i] == 'Y' && (seq[i] != 'C' && seq[i] != 'T')) { countDiffs++; }
- else if(oligo[i] == 'M' && (seq[i] != 'C' && seq[i] != 'A')) { countDiffs++; }
- else if(oligo[i] == 'K' && (seq[i] != 'T' && seq[i] != 'G')) { countDiffs++; }
- else if(oligo[i] == 'W' && (seq[i] != 'T' && seq[i] != 'A')) { countDiffs++; }
- else if(oligo[i] == 'S' && (seq[i] != 'C' && seq[i] != 'G')) { countDiffs++; }
- else if(oligo[i] == 'B' && (seq[i] != 'C' && seq[i] != 'T' && seq[i] != 'G')) { countDiffs++; }
- else if(oligo[i] == 'D' && (seq[i] != 'A' && seq[i] != 'T' && seq[i] != 'G')) { countDiffs++; }
- else if(oligo[i] == 'H' && (seq[i] != 'A' && seq[i] != 'T' && seq[i] != 'C')) { countDiffs++; }
- else if(oligo[i] == 'V' && (seq[i] != 'A' && seq[i] != 'C' && seq[i] != 'G')) { countDiffs++; }
- }
-
- }
-
- return countDiffs;
- }
- catch(exception& e) {
- m->errorOut(e, "TrimSeqsCommand", "countDiffs");
- exit(1);
- }
-
-}
-
//***************************************************************************************************************
projects / mothur.git / blobdiff