X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=preclustercommand.h;h=64efc7fc1d43aca03d17497e28bee2fdb61cc74a;hb=91a27e0483827c06c21c4fe89558923bbfe86573;hp=2868004825b8336ab1c4e4feb25dc415103b1881;hpb=192b4636345c51d962d4711206535e34cb2fd97c;p=mothur.git diff --git a/preclustercommand.h b/preclustercommand.h index 2868004..64efc7f 100644 --- a/preclustercommand.h +++ b/preclustercommand.h @@ -22,8 +22,9 @@ struct seqPNode { Sequence seq; string names; bool active; + int diffs; seqPNode() {} - seqPNode(int n, Sequence s, string nm) : numIdentical(n), seq(s), names(nm), active(1) {} + seqPNode(int n, Sequence s, string nm) : numIdentical(n), seq(s), names(nm), active(1) { diffs = 0; } ~seqPNode() {} }; /************************************************************/ @@ -72,34 +73,36 @@ private: //int readNamesFASTA(); int calcMisMatches(string, string); void printData(string, string); //fasta filename, names file name - int process(); + int process(string); int loadSeqs(map&, vector&); - int driverGroups(SequenceParser*, string, string, int, int, vector groups); - int createProcessesGroups(SequenceParser*, string, string, vector); + int driverGroups(SequenceParser*, string, string, string, int, int, vector groups); + int createProcessesGroups(SequenceParser*, string, string, string, vector); }; /**************************************************************************************************/ //custom data structure for threads to use. // This is passed by void pointer so it can be any data type // that can be passed using a single void pointer (LPVOID). -typedef struct preClusterData { +struct preClusterData { string fastafile; string namefile; string groupfile; - string newFName, newNName; + string newFName, newNName, newMName; MothurOut* m; int start; int end; int diffs, threadID; vector groups; + vector mapFileNames; preClusterData(){} - preClusterData(string f, string n, string g, string nff, string nnf, vector gr, MothurOut* mout, int st, int en, int d, int tid) { + preClusterData(string f, string n, string g, string nff, string nnf, string nmf, vector gr, MothurOut* mout, int st, int en, int d, int tid) { fastafile = f; namefile = n; groupfile = g; newFName = nff; newNName = nnf; + newMName = nmf; m = mout; start = st; end = en; @@ -110,7 +113,7 @@ typedef struct preClusterData { }; /**************************************************************************************************/ -#if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) +#if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) || (__linux__) || (__unix__) || (__unix) #else static DWORD WINAPI MyPreclusterThreadFunction(LPVOID lpParam){ preClusterData* pDataArray; @@ -193,6 +196,10 @@ static DWORD WINAPI MyPreclusterThreadFunction(LPVOID lpParam){ //////////////////////////////////////////////////// //int count = process(); - same function below + ofstream out; + pDataArray->m->openOutputFile(pDataArray->newMName+pDataArray->groups[k]+".map", out); + pDataArray->mapFileNames.push_back(pDataArray->newMName+pDataArray->groups[k]+".map"); + //sort seqs by number of identical seqs sort(alignSeqs.begin(), alignSeqs.end(), comparePriority); @@ -206,6 +213,8 @@ static DWORD WINAPI MyPreclusterThreadFunction(LPVOID lpParam){ if (alignSeqs[i].active) { //this sequence has not been merged yet + string chunk = alignSeqs[i].seq.getName() + "\t" + toString(alignSeqs[i].numIdentical) + "\t" + toString(0) + "\t" + alignSeqs[i].seq.getAligned() + "\n"; + //try to merge it with all smaller seqs for (int j = i+1; j < numSeqs; j++) { @@ -229,18 +238,22 @@ static DWORD WINAPI MyPreclusterThreadFunction(LPVOID lpParam){ alignSeqs[j].active = 0; alignSeqs[j].numIdentical = 0; + alignSeqs[j].diffs = mismatch; count++; + chunk += alignSeqs[j].seq.getName() + "\t" + toString(alignSeqs[j].numIdentical) + "\t" + toString(mismatch) + "\t" + alignSeqs[j].seq.getAligned() + "\n"; } }//end if j active - }//end if i != j + }//end for loop j //remove from active list alignSeqs[i].active = 0; + out << "ideal_seq_" << (i+1) << '\t' << alignSeqs[i].numIdentical << endl << chunk << endl; + }//end if active i if(i % 100 == 0) { pDataArray->m->mothurOut(toString(i) + "\t" + toString(numSeqs - count) + "\t" + toString(count)); pDataArray->m->mothurOutEndLine(); } } - + out.close(); if(numSeqs % 100 != 0) { pDataArray->m->mothurOut(toString(numSeqs) + "\t" + toString(numSeqs - count) + "\t" + toString(count)); pDataArray->m->mothurOutEndLine(); } //////////////////////////////////////////////////// @@ -277,7 +290,7 @@ static DWORD WINAPI MyPreclusterThreadFunction(LPVOID lpParam){ } catch(exception& e) { - pDataArray->m->errorOut(e, "AlignCommand", "MyPreclusterThreadFunction"); + pDataArray->m->errorOut(e, "PreClusterCommand", "MyPreclusterThreadFunction"); exit(1); } }