X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=phylotree.cpp;h=3dde18680c625eb816230a8d13774ccfc47032cf;hb=fdfbfe59134dd7dd3e49d90609d129128ba2d370;hp=e430fb9e85622dcd1d425534857fe37dff600da9;hpb=d0051dc9939d3477bd92b42c86bcd3eda743b955;p=mothur.git diff --git a/phylotree.cpp b/phylotree.cpp index e430fb9..3dde186 100644 --- a/phylotree.cpp +++ b/phylotree.cpp @@ -20,6 +20,7 @@ PhyloTree::PhyloTree(){ tree[0].heirarchyID = "0"; maxLevel = 0; calcTotals = true; + addSeqToTree("unknown", "unknown;"); } catch(exception& e) { m->errorOut(e, "PhyloTree", "PhyloTree"); @@ -127,7 +128,6 @@ PhyloTree::PhyloTree(string tfile){ maxLevel = 0; calcTotals = true; string name, tax; - #ifdef USE_MPI int pid, num, processors; @@ -178,20 +178,26 @@ PhyloTree::PhyloTree(string tfile){ MPI_Barrier(MPI_COMM_WORLD); //make everyone wait - just in case #else - ifstream in; - m->openInputFile(tfile, in); - - //read in users taxonomy file and add sequences to tree - while(!in.eof()){ - in >> name >> tax; m->gobble(in); - - addSeqToTree(name, tax); - } - in.close(); + map temp; + m->readTax(tfile, temp); + + for (map::iterator itTemp = temp.begin(); itTemp != temp.end();) { + addSeqToTree(itTemp->first, itTemp->second); + temp.erase(itTemp++); + } #endif assignHeirarchyIDs(0); - + + + string unknownTax = "unknown;"; + //added last taxon until you get desired level + for (int i = 1; i < maxLevel; i++) { + unknownTax += "unclassfied;"; + } + + addSeqToTree("unknown", unknownTax); + //create file for summary if needed setUp(tfile); } @@ -232,7 +238,6 @@ string PhyloTree::getNextTaxon(string& heirarchy, string seqname){ int PhyloTree::addSeqToTree(string seqName, string seqTaxonomy){ try { - numSeqs++; map::iterator childPointer; @@ -375,7 +380,7 @@ void PhyloTree::binUnclassified(string file){ map::iterator childPointer; vector copy = tree; - + //fill out tree fillOutTree(0, copy); @@ -484,16 +489,16 @@ string PhyloTree::getFullTaxonomy(string seqName) { void PhyloTree::print(ofstream& out, vector& copy){ try { - + //output mothur version out << "#" << m->getVersion() << endl; out << copy.size() << endl; out << maxLevel << endl; - + for (int i = 0; i < copy.size(); i++) { - + out << copy[i].level << '\t'<< copy[i].name << '\t' << copy[i].children.size() << '\t'; map::iterator it; @@ -606,17 +611,20 @@ bool PhyloTree::ErrorCheck(vector templateFileNames){ try { bool okay = true; + templateFileNames.push_back("unknown"); map::iterator itFind; map taxonomyFileNames = name2Taxonomy; + if (m->debug) { m->mothurOut("[DEBUG]: in error check. Numseqs in template = " + toString(templateFileNames.size()) + ". Numseqs in taxonomy = " + toString(taxonomyFileNames.size()) + ".\n"); } + for (int i = 0; i < templateFileNames.size(); i++) { itFind = taxonomyFileNames.find(templateFileNames[i]); if (itFind != taxonomyFileNames.end()) { //found it so erase it taxonomyFileNames.erase(itFind); }else { - m->mothurOut(templateFileNames[i] + " is in your template file and is not in your taxonomy file. Please correct."); m->mothurOutEndLine(); + m->mothurOut("'" +templateFileNames[i] + "' is in your template file and is not in your taxonomy file. Please correct."); m->mothurOutEndLine(); okay = false; }