X-Git-Url: https://git.donarmstrong.com/?p=mothur.git;a=blobdiff_plain;f=countseqscommand.cpp;h=dfa012eeff0f0f49c778c00b2098348a489f1855;hp=210dd9641a1736f8b0ea509f96b210dbbe3bd2e1;hb=1a20e24ee786195ab0e1cccd4f5aede7a88f3f4e;hpb=2ecee16fec29d4c525f740ec19b27962ca09c050 diff --git a/countseqscommand.cpp b/countseqscommand.cpp index 210dd96..dfa012e 100644 --- a/countseqscommand.cpp +++ b/countseqscommand.cpp @@ -10,16 +10,17 @@ #include "countseqscommand.h" #include "groupmap.h" #include "sharedutilities.h" +#include "counttable.h" //********************************************************************************************************************** vector CountSeqsCommand::setParameters(){ try { - CommandParameter pname("name", "InputTypes", "", "", "none", "none", "none",false,true); parameters.push_back(pname); - CommandParameter pgroup("group", "InputTypes", "", "", "none", "none", "none",false,false); parameters.push_back(pgroup); - CommandParameter plarge("large", "Boolean", "", "F", "", "", "",false,false); parameters.push_back(plarge); - CommandParameter pgroups("groups", "String", "", "", "", "", "",false,false); parameters.push_back(pgroups); - CommandParameter pinputdir("inputdir", "String", "", "", "", "", "",false,false); parameters.push_back(pinputdir); - CommandParameter poutputdir("outputdir", "String", "", "", "", "", "",false,false); parameters.push_back(poutputdir); + CommandParameter pname("name", "InputTypes", "", "", "none", "none", "none","count",false,true,true); parameters.push_back(pname); + CommandParameter pgroup("group", "InputTypes", "", "", "none", "none", "none","",false,false,true); parameters.push_back(pgroup); + CommandParameter plarge("large", "Boolean", "", "F", "", "", "","",false,false); parameters.push_back(plarge); + CommandParameter pgroups("groups", "String", "", "", "", "", "","",false,false); parameters.push_back(pgroups); + CommandParameter pinputdir("inputdir", "String", "", "", "", "", "","",false,false); parameters.push_back(pinputdir); + CommandParameter poutputdir("outputdir", "String", "", "", "", "", "","",false,false); parameters.push_back(poutputdir); vector myArray; for (int i = 0; i < parameters.size(); i++) { myArray.push_back(parameters[i].name); } @@ -34,7 +35,7 @@ vector CountSeqsCommand::setParameters(){ string CountSeqsCommand::getHelpString(){ try { string helpString = ""; - helpString += "The count.seqs aka. make.table command reads a name file and outputs a .count.table file. You may also provide a group file to get the counts broken down by group.\n"; + helpString += "The count.seqs aka. make.table command reads a name file and outputs a .count_table file. You may also provide a group file to get the counts broken down by group.\n"; helpString += "The groups parameter allows you to indicate which groups you want to include in the counts, by default all groups in your groupfile are used.\n"; helpString += "The large parameter indicates the name and group files are too large to fit in RAM.\n"; helpString += "When you use the groups parameter and a sequence does not represent any sequences from the groups you specify it is not included in the .count.summary file.\n"; @@ -49,24 +50,19 @@ string CountSeqsCommand::getHelpString(){ } } //********************************************************************************************************************** -string CountSeqsCommand::getOutputFileNameTag(string type, string inputName=""){ - try { - string outputFileName = ""; - map >::iterator it; +string CountSeqsCommand::getOutputPattern(string type) { + try { + string pattern = ""; - //is this a type this command creates - it = outputTypes.find(type); - if (it == outputTypes.end()) { m->mothurOut("[ERROR]: this command doesn't create a " + type + " output file.\n"); } - else { - if (type == "counttable") { outputFileName = "count.table"; } - else { m->mothurOut("[ERROR]: No definition for type " + type + " output file tag.\n"); m->control_pressed = true; } - } - return outputFileName; - } - catch(exception& e) { - m->errorOut(e, "CountSeqsCommand", "getOutputFileNameTag"); - exit(1); - } + if (type == "count") { pattern = "[filename],count_table"; } + else { m->mothurOut("[ERROR]: No definition for type " + type + " output pattern.\n"); m->control_pressed = true; } + + return pattern; + } + catch(exception& e) { + m->errorOut(e, "CountSeqsCommand", "getOutputPattern"); + exit(1); + } } //********************************************************************************************************************** CountSeqsCommand::CountSeqsCommand(){ @@ -74,7 +70,7 @@ CountSeqsCommand::CountSeqsCommand(){ abort = true; calledHelp = true; setParameters(); vector tempOutNames; - outputTypes["counttable"] = tempOutNames; + outputTypes["count"] = tempOutNames; } catch(exception& e) { m->errorOut(e, "CountSeqsCommand", "CountSeqsCommand"); @@ -106,7 +102,7 @@ CountSeqsCommand::CountSeqsCommand(string option) { //initialize outputTypes vector tempOutNames; - outputTypes["counttable"] = tempOutNames; + outputTypes["count"] = tempOutNames; //if the user changes the input directory command factory will send this info to us in the output parameter @@ -170,16 +166,18 @@ int CountSeqsCommand::execute(){ if (abort == true) { if (calledHelp) { return 0; } return 2; } - string outputFileName = outputDir + m->getRootName(m->getSimpleName(namefile)) + getOutputFileNameTag("counttable"); + map variables; + variables["[filename]"] = outputDir + m->getRootName(m->getSimpleName(namefile)); + string outputFileName = getOutputFileName("count", variables); int total = 0; if (!large) { total = processSmall(outputFileName); } else { total = processLarge(outputFileName); } - + if (m->control_pressed) { m->mothurRemove(outputFileName); return 0; } //set rabund file as new current rabundfile - itTypes = outputTypes.find("counttable"); + itTypes = outputTypes.find("count"); if (itTypes != outputTypes.end()) { if ((itTypes->second).size() != 0) { string current = (itTypes->second)[0]; m->setCountTableFile(current); } } @@ -187,7 +185,7 @@ int CountSeqsCommand::execute(){ m->mothurOutEndLine(); m->mothurOut("Total number of sequences: " + toString(total)); m->mothurOutEndLine(); m->mothurOutEndLine(); - m->mothurOut("Output File Name: "); m->mothurOutEndLine(); + m->mothurOut("Output File Names: "); m->mothurOutEndLine(); m->mothurOut(outputFileName); m->mothurOutEndLine(); m->mothurOutEndLine(); @@ -204,8 +202,8 @@ int CountSeqsCommand::execute(){ int CountSeqsCommand::processSmall(string outputFileName){ try { ofstream out; - m->openOutputFile(outputFileName, out); outputTypes["counttable"].push_back(outputFileName); - outputNames.push_back(outputFileName); outputTypes["counttable"].push_back(outputFileName); + m->openOutputFile(outputFileName, out); outputTypes["count"].push_back(outputFileName); + outputNames.push_back(outputFileName); outputTypes["count"].push_back(outputFileName); out << "Representative_Sequence\ttotal\t"; GroupMap* groupMap; @@ -238,7 +236,11 @@ int CountSeqsCommand::processSmall(string outputFileName){ string firstCol, secondCol; in >> firstCol; m->gobble(in); in >> secondCol; m->gobble(in); - + //cout << firstCol << '\t' << secondCol << endl; + m->checkName(firstCol); + m->checkName(secondCol); + //cout << firstCol << '\t' << secondCol << endl; + vector names; m->splitAtChar(secondCol, names, ','); @@ -298,7 +300,7 @@ int CountSeqsCommand::processLarge(string outputFileName){ for (set::iterator it = namesOfGroups.begin(); it != namesOfGroups.end(); it++) { initial[(*it)] = 0; } ofstream out; m->openOutputFile(outputFileName, out); - outputNames.push_back(outputFileName); outputTypes["counttable"].push_back(outputFileName); + outputNames.push_back(outputFileName); outputTypes["count"].push_back(outputFileName); out << "Representative_Sequence\ttotal\t"; if (groupfile == "") { out << endl; } @@ -437,6 +439,8 @@ map CountSeqsCommand::processNameFile(string name) { else { secondCol = pieces[i]; pairDone = true; columnOne=true; } if (pairDone) { + m->checkName(firstCol); + m->checkName(secondCol); //parse names into vector vector theseNames; m->splitAtComma(secondCol, theseNames); @@ -450,6 +454,28 @@ map CountSeqsCommand::processNameFile(string name) { in.close(); out.close(); + if (rest != "") { + vector pieces = m->splitWhiteSpace(rest); + + for (int i = 0; i < pieces.size(); i++) { + if (columnOne) { firstCol = pieces[i]; columnOne=false; } + else { secondCol = pieces[i]; pairDone = true; columnOne=true; } + + if (pairDone) { + m->checkName(firstCol); + m->checkName(secondCol); + //parse names into vector + vector theseNames; + m->splitAtComma(secondCol, theseNames); + for (int i = 0; i < theseNames.size(); i++) { out << theseNames[i] << '\t' << count << endl; } + indexToNames[count] = firstCol; + pairDone = false; + count++; + } + } + + } + return indexToNames; } catch(exception& e) { @@ -489,6 +515,7 @@ map CountSeqsCommand::getGroupNames(string filename, set& n else { secondCol = pieces[i]; pairDone = true; columnOne=true; } if (pairDone) { + m->checkName(firstCol); it = groupIndex.find(secondCol); if (it == groupIndex.end()) { //add group, assigning the group and number so we can use vectors above groupIndex[secondCol] = count; @@ -502,6 +529,27 @@ map CountSeqsCommand::getGroupNames(string filename, set& n } in.close(); out.close(); + + if (rest != "") { + vector pieces = m->splitWhiteSpace(rest); + + for (int i = 0; i < pieces.size(); i++) { + if (columnOne) { firstCol = pieces[i]; columnOne=false; } + else { secondCol = pieces[i]; pairDone = true; columnOne=true; } + + if (pairDone) { + m->checkName(firstCol); + it = groupIndex.find(secondCol); + if (it == groupIndex.end()) { //add group, assigning the group and number so we can use vectors above + groupIndex[secondCol] = count; + count++; + } + out << firstCol << '\t' << groupIndex[secondCol] << endl; + namesOfGroups.insert(secondCol); + pairDone = false; + } + } + } for (it = groupIndex.begin(); it != groupIndex.end(); it++) { indexToGroups[it->second] = it->first; }