int PreClusterCommand::driverGroups(string newFFile, string newNFile, string newMFile, int start, int end, vector<string> groups){
try {
int numSeqs = 0;
//precluster each group
for (int i = start; i < end; i++) {
start = time(NULL);
if (m->control_pressed) { return 0; }
m->mothurOutEndLine(); m->mothurOut("Processing group " + groups[i] + ":"); m->mothurOutEndLine();
map<string, string> thisNameMap;
vector<Sequence> thisSeqs;
if (groupfile != "") {
thisSeqs = parser->getSeqs(groups[i]);
}else if (countfile != "") {
thisSeqs = cparser->getSeqs(groups[i]);
}
if (namefile != "") { thisNameMap = parser->getNameMap(groups[i]); }
//fill alignSeqs with this groups info.
numSeqs = loadSeqs(thisNameMap, thisSeqs, groups[i]);
if (m->control_pressed) { return 0; }
if (method == "aligned") { if (diffs > length) { m->mothurOut("Error: diffs is greater than your sequence length."); m->mothurOutEndLine(); m->control_pressed = true; return 0; } }
int count= process(newMFile+groups[i]+".map");
outputNames.push_back(newMFile+groups[i]+".map"); outputTypes["map"].push_back(newMFile+groups[i]+".map");
if (m->control_pressed) { return 0; }
m->mothurOut("Total number of sequences before pre.cluster was " + toString(alignSeqs.size()) + "."); m->mothurOutEndLine();
m->mothurOut("pre.cluster removed " + toString(count) + " sequences."); m->mothurOutEndLine(); m->mothurOutEndLine();
printData(newFFile, newNFile, groups[i]);
m->mothurOut("It took " + toString(time(NULL) - start) + " secs to cluster " + toString(numSeqs) + " sequences."); m->mothurOutEndLine();
}
return numSeqs;
}
catch(exception& e) {
m->errorOut(e, "PreClusterCommand", "driverGroups");
exit(1);
}
}
/* void getParams()
* Parses the command line.
*/
void getParams(int argc, char** argv) {
char* outFile = NULL, *inFile = NULL, *primFile = NULL,
*bedFile = NULL, *fwdPos = NULL, *revPos = NULL,
*bedPos = NULL, *logFile = NULL, *wasteFile = NULL,
*corrFile = NULL;
int misAllow = 0, revLen = 0, revMis = 0, revLMis = 0,
revOpt = 0;
// parse argv
for (int i = 1; i < argc; i++) {
if (!strcmp(argv[i], HELP))
usage();
else if (!strcmp(argv[i], REVOPT))
revOpt = 1;
else if (i < argc - 1) {
if (!strcmp(argv[i], OUTFILE))
outFile = argv[++i];
else if (!strcmp(argv[i], INFILE))
inFile = argv[++i];
else if (!strcmp(argv[i], PRIMFILE))
primFile = argv[++i];
else if (!strcmp(argv[i], BEDFILE))
bedFile = argv[++i];
else if (!strcmp(argv[i], FWDPOS))
fwdPos = argv[++i];
else if (!strcmp(argv[i], REVPOS))
revPos = argv[++i];
else if (!strcmp(argv[i], BEDPOS))
bedPos = argv[++i];
else if (!strcmp(argv[i], LOGFILE))
logFile = argv[++i];
else if (!strcmp(argv[i], WASTEFILE))
wasteFile = argv[++i];
else if (!strcmp(argv[i], MISALLOW))
misAllow = getInt(argv[++i]);
else if (!strcmp(argv[i], REVMIS))
revMis = getInt(argv[++i]);
else if (!strcmp(argv[i], REVLENGTH))
revLen = getInt(argv[++i]);
else if (!strcmp(argv[i], REVLMIS))
revLMis = getInt(argv[++i]);
else if (!strcmp(argv[i], CORRFILE))
corrFile = argv[++i];
else
exit(error(argv[i], ERRINVAL));
} else
exit(error(argv[i], ERRINVAL));
}
if (outFile == NULL || inFile == NULL || primFile == NULL)
usage();
int gz = 0;
if (!strcmp(inFile + strlen(inFile) - strlen(GZEXT), GZEXT))
gz = 1;
// open files, load primer sequences
File out, in, waste, corr;
FILE* prim = NULL, *log = NULL, *bed = NULL;
openFiles(outFile, &out, primFile, &prim, inFile, &in,
logFile, &log, bedFile, &bed, wasteFile, &waste,
corrFile, &corr, gz);
int pr = loadSeqs(prim);
// get start and end locations
int fwdSt = 0, fwdEnd = 1, revSt = 0, revEnd = 1,
bedSt = 0, bedEnd = 1;
getPos(fwdPos, &fwdSt, &fwdEnd);
getPos(revPos, &revSt, &revEnd);
if (bed != NULL) {
getLengths(bed);
getPos(bedPos, &bedSt, &bedEnd);
}
// read file
int match = 0, rcmatch = 0; // counting variables
int count = readFile(in, out, misAllow, &match, &rcmatch,
fwdSt, fwdEnd, revSt, revEnd, bedSt, bedEnd,
waste, wasteFile != NULL, revMis, revLen, revLMis,
revOpt, corr, corrFile != NULL, gz);
// print log output
if (log != NULL) {
fprintf(log, "Primer pairs: %d\nRead count: %d\n", pr, count);
fprintf(log, "Primer matches: %d\nBoth primer matches: %d\n\n", match, rcmatch);
fprintf(log, "Matches:\nPrimer\tFwd\tFwd-Both\tRev\tRev-Both\n");
for (Primer* p = primo; p != NULL; p = p->next)
fprintf(log, "%s\t%d\t%d\t%d\t%d\n", p->name, p->fcount, p->fcountr,
p->rcount, p->rcountr);
}
// close files
if ( (gz && (gzclose(in.gzf) != Z_OK || gzclose(out.gzf) != Z_OK ||
(wasteFile != NULL && gzclose(waste.gzf) != Z_OK) ||
(corrFile != NULL && gzclose(corr.gzf) != Z_OK) ) ) ||
( ! gz && (fclose(in.f) || fclose(out.f) ||
(wasteFile != NULL && fclose(waste.f)) ||
(corrFile != NULL && fclose(corr.f)) ) ) ||
fclose(prim) || (log != NULL && fclose(log)) ||
(bed != NULL && fclose(bed)) )
exit(error("", ERRCLOSE));
}
