From: westcott Date: Wed, 2 Jun 2010 15:00:10 +0000 (+0000) Subject: added taxonomy file to list of files list.seqs, get.seqs and remove.seqs can process X-Git-Url: https://git.donarmstrong.com/?p=mothur.git;a=commitdiff_plain;h=14edc148cb299c5624f72bb681375b704aa74f43 added taxonomy file to list of files list.seqs, get.seqs and remove.seqs can process --- diff --git a/getseqscommand.cpp b/getseqscommand.cpp index 7fdf6ed..a9463a0 100644 --- a/getseqscommand.cpp +++ b/getseqscommand.cpp @@ -22,7 +22,7 @@ GetSeqsCommand::GetSeqsCommand(string option) { else { //valid paramters for this command - string Array[] = {"fasta","name", "group", "alignreport", "accnos", "list","outputdir","inputdir"}; + string Array[] = {"fasta","name", "group", "alignreport", "accnos", "list","taxonomy","outputdir","inputdir"}; vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); OptionParser parser(option); @@ -91,6 +91,14 @@ GetSeqsCommand::GetSeqsCommand(string option) { //if the user has not given a path then, add inputdir. else leave path alone. if (path == "") { parameters["group"] = inputDir + it->second; } } + + it = parameters.find("taxonomy"); + //user has given a template file + if(it != parameters.end()){ + path = hasPath(it->second); + //if the user has not given a path then, add inputdir. else leave path alone. + if (path == "") { parameters["taxonomy"] = inputDir + it->second; } + } } @@ -119,13 +127,12 @@ GetSeqsCommand::GetSeqsCommand(string option) { if (listfile == "not open") { abort = true; } else if (listfile == "not found") { listfile = ""; } - if ((fastafile == "") && (namefile == "") && (groupfile == "") && (alignfile == "") && (listfile == "")) { m->mothurOut("You must provide one of the following: fasta, name, group, alignreport or listfile."); m->mothurOutEndLine(); abort = true; } - - int okay = 2; - if (outputDir != "") { okay++; } - if (inputDir != "") { okay++; } + taxfile = validParameter.validFile(parameters, "taxonomy", true); + if (taxfile == "not open") { abort = true; } + else if (taxfile == "not found") { taxfile = ""; } + - if (parameters.size() > okay) { m->mothurOut("You may only enter one of the following: fasta, name, group, alignreport or listfile."); m->mothurOutEndLine(); abort = true; } + if ((fastafile == "") && (namefile == "") && (groupfile == "") && (alignfile == "") && (listfile == "") && (taxfile == "")) { m->mothurOut("You must provide one of the following: fasta, name, group, alignreport, taxonomy or listfile."); m->mothurOutEndLine(); abort = true; } } } @@ -138,9 +145,9 @@ GetSeqsCommand::GetSeqsCommand(string option) { void GetSeqsCommand::help(){ try { - m->mothurOut("The get.seqs command reads an .accnos file and one of the following file types: fasta, name, group, list or alignreport file.\n"); + m->mothurOut("The get.seqs command reads an .accnos file and any of the following file types: fasta, name, group, list, taxonomy or alignreport file.\n"); m->mothurOut("It outputs a file containing only the sequences in the .accnos file.\n"); - m->mothurOut("The get.seqs command parameters are accnos, fasta, name, group, list and alignreport. You must provide accnos and one of the other parameters.\n"); + m->mothurOut("The get.seqs command parameters are accnos, fasta, name, group, list, taxonomy and alignreport. You must provide accnos and at least one of the other parameters.\n"); m->mothurOut("The get.seqs command should be in the following format: get.seqs(accnos=yourAccnos, fasta=yourFasta).\n"); m->mothurOut("Example get.seqs(accnos=amazon.accnos, fasta=amazon.fasta).\n"); m->mothurOut("Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFasta).\n\n"); @@ -165,12 +172,13 @@ int GetSeqsCommand::execute(){ //read through the correct file and output lines you want to keep if (fastafile != "") { readFasta(); } - else if (namefile != "") { readName(); } - else if (groupfile != "") { readGroup(); } - else if (alignfile != "") { readAlign(); } - else if (listfile != "") { readList(); } + if (namefile != "") { readName(); } + if (groupfile != "") { readGroup(); } + if (alignfile != "") { readAlign(); } + if (listfile != "") { readList(); } + if (taxfile != "") { readTax(); } - if (m->control_pressed) { return 0; } + if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; } if (outputNames.size() != 0) { m->mothurOutEndLine(); @@ -216,8 +224,6 @@ int GetSeqsCommand::readFasta(){ wroteSomething = true; currSeq.printSequence(out); - - names.erase(name); } } gobble(in); @@ -427,8 +433,6 @@ int GetSeqsCommand::readGroup(){ wroteSomething = true; out << name << '\t' << group << endl; - - names.erase(name); } gobble(in); @@ -449,7 +453,52 @@ int GetSeqsCommand::readGroup(){ exit(1); } } +//********************************************************************************************************************** +int GetSeqsCommand::readTax(){ + try { + if (outputDir == "") { outputDir += hasPath(taxfile); } + string outputFileName = outputDir + getRootName(getSimpleName(taxfile)) + "pick" + getExtension(taxfile); + ofstream out; + openOutputFile(outputFileName, out); + + ifstream in; + openInputFile(taxfile, in); + string name, tax; + + bool wroteSomething = false; + + while(!in.eof()){ + + if (m->control_pressed) { in.close(); out.close(); remove(outputFileName.c_str()); return 0; } + in >> name; //read from first column + in >> tax; //read from second column + + //if this name is in the accnos file + if (names.count(name) == 1) { + wroteSomething = true; + + out << name << '\t' << tax << endl; + } + + gobble(in); + } + in.close(); + out.close(); + + if (wroteSomething == false) { + m->mothurOut("Your file does not contain any sequence from the .accnos file."); m->mothurOutEndLine(); + remove(outputFileName.c_str()); + }else { outputNames.push_back(outputFileName); } + + return 0; + + } + catch(exception& e) { + m->errorOut(e, "GetSeqsCommand", "readTax"); + exit(1); + } +} //********************************************************************************************************************** //alignreport file has a column header line then all other lines contain 16 columns. we just want the first column since that contains the name int GetSeqsCommand::readAlign(){ @@ -493,8 +542,6 @@ int GetSeqsCommand::readAlign(){ } out << endl; - names.erase(name); - }else {//still read just don't do anything with it //read rest for (int i = 0; i < 15; i++) { diff --git a/getseqscommand.h b/getseqscommand.h index b574afe..9d8e796 100644 --- a/getseqscommand.h +++ b/getseqscommand.h @@ -24,7 +24,7 @@ class GetSeqsCommand : public Command { private: set names; vector outputNames; - string accnosfile, fastafile, namefile, groupfile, alignfile, listfile, outputDir; + string accnosfile, fastafile, namefile, groupfile, alignfile, listfile, taxfile, outputDir; bool abort; int readFasta(); @@ -33,6 +33,7 @@ class GetSeqsCommand : public Command { int readAlign(); int readAccnos(); int readList(); + int readTax(); }; diff --git a/listseqscommand.cpp b/listseqscommand.cpp index 23c71ec..3200137 100644 --- a/listseqscommand.cpp +++ b/listseqscommand.cpp @@ -22,7 +22,7 @@ ListSeqsCommand::ListSeqsCommand(string option) { else { //valid paramters for this command - string Array[] = {"fasta","name", "group", "alignreport","list","outputdir","inputdir"}; + string Array[] = {"fasta","name", "group", "alignreport","list","taxonomy","outputdir","inputdir"}; vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); OptionParser parser(option); @@ -83,6 +83,14 @@ ListSeqsCommand::ListSeqsCommand(string option) { //if the user has not given a path then, add inputdir. else leave path alone. if (path == "") { parameters["group"] = inputDir + it->second; } } + + it = parameters.find("taxonomy"); + //user has given a template file + if(it != parameters.end()){ + path = hasPath(it->second); + //if the user has not given a path then, add inputdir. else leave path alone. + if (path == "") { parameters["taxonomy"] = inputDir + it->second; } + } } //check for required parameters @@ -106,8 +114,11 @@ ListSeqsCommand::ListSeqsCommand(string option) { if (listfile == "not open") { abort = true; } else if (listfile == "not found") { listfile = ""; } + taxfile = validParameter.validFile(parameters, "taxonomy", true); + if (taxfile == "not open") { abort = true; } + else if (taxfile == "not found") { taxfile = ""; } - if ((fastafile == "") && (namefile == "") && (listfile == "") && (groupfile == "") && (alignfile == "")) { m->mothurOut("You must provide a file."); m->mothurOutEndLine(); abort = true; } + if ((fastafile == "") && (namefile == "") && (listfile == "") && (groupfile == "") && (alignfile == "") && (taxfile == "")) { m->mothurOut("You must provide a file."); m->mothurOutEndLine(); abort = true; } int okay = 1; if (outputDir != "") { okay++; } @@ -126,8 +137,8 @@ ListSeqsCommand::ListSeqsCommand(string option) { void ListSeqsCommand::help(){ try { - m->mothurOut("The list.seqs command reads a fasta, name, group, list or alignreport file and outputs a .accnos file containing sequence names.\n"); - m->mothurOut("The list.seqs command parameters are fasta, name, group and alignreport. You must provide one of these parameters.\n"); + m->mothurOut("The list.seqs command reads a fasta, name, group, list, taxonomy or alignreport file and outputs a .accnos file containing sequence names.\n"); + m->mothurOut("The list.seqs command parameters are fasta, name, group, list, taxonomy and alignreport. You must provide one of these parameters.\n"); m->mothurOut("The list.seqs command should be in the following format: list.seqs(fasta=yourFasta).\n"); m->mothurOut("Example list.seqs(fasta=amazon.fasta).\n"); m->mothurOut("Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFasta).\n\n"); @@ -151,6 +162,7 @@ int ListSeqsCommand::execute(){ else if (groupfile != "") { inputFileName = groupfile; readGroup(); } else if (alignfile != "") { inputFileName = alignfile; readAlign(); } else if (listfile != "") { inputFileName = listfile; readList(); } + else if (taxfile != "") { inputFileName = taxfile; readTax(); } if (m->control_pressed) { return 0; } @@ -364,3 +376,32 @@ int ListSeqsCommand::readAlign(){ } } //********************************************************************************************************************** +int ListSeqsCommand::readTax(){ + try { + + ifstream in; + openInputFile(taxfile, in); + string name, firstCol, secondCol; + + while(!in.eof()){ + + if (m->control_pressed) { in.close(); return 0; } + + in >> firstCol; + in >> secondCol; + + names.push_back(firstCol); + + gobble(in); + } + in.close(); + + return 0; + + } + catch(exception& e) { + m->errorOut(e, "ListSeqsCommand", "readTax"); + exit(1); + } +} +//********************************************************************************************************************** diff --git a/listseqscommand.h b/listseqscommand.h index 391ec9a..6a210a1 100644 --- a/listseqscommand.h +++ b/listseqscommand.h @@ -23,7 +23,7 @@ class ListSeqsCommand : public Command { private: vector names; - string fastafile, namefile, groupfile, alignfile, inputFileName, outputDir, listfile; + string fastafile, namefile, groupfile, alignfile, inputFileName, outputDir, listfile, taxfile; bool abort; int readFasta(); @@ -31,6 +31,7 @@ class ListSeqsCommand : public Command { int readGroup(); int readAlign(); int readList(); + int readTax(); }; diff --git a/removeseqscommand.cpp b/removeseqscommand.cpp index a61e467..da6bc44 100644 --- a/removeseqscommand.cpp +++ b/removeseqscommand.cpp @@ -22,7 +22,7 @@ RemoveSeqsCommand::RemoveSeqsCommand(string option) { else { //valid paramters for this command - string Array[] = {"fasta","name", "group", "alignreport", "accnos", "list","outputdir","inputdir", "dups" }; + string Array[] = {"fasta","name", "group", "alignreport", "accnos", "list","taxonomy","outputdir","inputdir", "dups" }; vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); OptionParser parser(option); @@ -91,6 +91,14 @@ RemoveSeqsCommand::RemoveSeqsCommand(string option) { //if the user has not given a path then, add inputdir. else leave path alone. if (path == "") { parameters["group"] = inputDir + it->second; } } + + it = parameters.find("taxonomy"); + //user has given a template file + if(it != parameters.end()){ + path = hasPath(it->second); + //if the user has not given a path then, add inputdir. else leave path alone. + if (path == "") { parameters["taxonomy"] = inputDir + it->second; } + } } @@ -119,19 +127,18 @@ RemoveSeqsCommand::RemoveSeqsCommand(string option) { if (listfile == "not open") { abort = true; } else if (listfile == "not found") { listfile = ""; } + taxfile = validParameter.validFile(parameters, "taxonomy", true); + if (taxfile == "not open") { abort = true; } + else if (taxfile == "not found") { taxfile = ""; } + + string usedDups = "true"; string temp = validParameter.validFile(parameters, "dups", false); if (temp == "not found") { temp = "false"; usedDups = ""; } dups = isTrue(temp); - if ((fastafile == "") && (namefile == "") && (groupfile == "") && (alignfile == "") && (listfile == "")) { m->mothurOut("You must provide one of the following: fasta, name, group, alignreport or list."); m->mothurOutEndLine(); abort = true; } - - //int okay = 2; - //if (outputDir != "") { okay++; } - //if (usedDups != "") { okay++; } + if ((fastafile == "") && (namefile == "") && (groupfile == "") && (alignfile == "") && (listfile == "") && (taxfile == "")) { m->mothurOut("You must provide at least one of the following: fasta, name, group, taxonomy, alignreport or list."); m->mothurOutEndLine(); abort = true; } - if ((usedDups != "") && (namefile == "")) { m->mothurOut("You may only use dups with the name option."); m->mothurOutEndLine(); abort = true; } - - //if (parameters.size() > okay) { m->mothurOut("You may only enter one of the following: fasta, name, group, alignreport, or list."); m->mothurOutEndLine(); abort = true; } + if ((usedDups != "") && (namefile == "")) { m->mothurOut("You may only use dups with the name option."); m->mothurOutEndLine(); abort = true; } } } @@ -144,9 +151,9 @@ RemoveSeqsCommand::RemoveSeqsCommand(string option) { void RemoveSeqsCommand::help(){ try { - m->mothurOut("The remove.seqs command reads an .accnos file and one of the following file types: fasta, name, group, list or alignreport file.\n"); + m->mothurOut("The remove.seqs command reads an .accnos file and at least one of the following file types: fasta, name, group, list, taxonomy or alignreport file.\n"); m->mothurOut("It outputs a file containing the sequences NOT in the .accnos file.\n"); - m->mothurOut("The remove.seqs command parameters are accnos, fasta, name, group, list, alignreport and dups. You must provide accnos and one of the file parameters.\n"); + m->mothurOut("The remove.seqs command parameters are accnos, fasta, name, group, list, taxonomy, alignreport and dups. You must provide accnos and at least one of the file parameters.\n"); m->mothurOut("The dups parameter allows you to remove the entire line from a name file if you remove any name from the line. default=false. If dups=true, then remove.seqs outputs a new .accnos file containing all the sequences removed. \n"); m->mothurOut("The remove.seqs command should be in the following format: remove.seqs(accnos=yourAccnos, fasta=yourFasta).\n"); m->mothurOut("Example remove.seqs(accnos=amazon.accnos, fasta=amazon.fasta).\n"); @@ -176,6 +183,7 @@ int RemoveSeqsCommand::execute(){ if (groupfile != "") { readGroup(); } if (alignfile != "") { readAlign(); } if (listfile != "") { readList(); } + if (taxfile != "") { readTax(); } if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; } @@ -221,7 +229,7 @@ int RemoveSeqsCommand::readFasta(){ wroteSomething = true; currSeq.printSequence(out); - }//else { names.erase(name); } + } } gobble(in); } @@ -435,7 +443,7 @@ int RemoveSeqsCommand::readGroup(){ if (names.count(name) == 0) { wroteSomething = true; out << name << '\t' << group << endl; - }//else { names.erase(name); } + } gobble(in); } @@ -454,7 +462,49 @@ int RemoveSeqsCommand::readGroup(){ exit(1); } } +//********************************************************************************************************************** +int RemoveSeqsCommand::readTax(){ + try { + if (outputDir == "") { outputDir += hasPath(taxfile); } + string outputFileName = outputDir + getRootName(getSimpleName(taxfile)) + "pick" + getExtension(taxfile); + ofstream out; + openOutputFile(outputFileName, out); + ifstream in; + openInputFile(taxfile, in); + string name, tax; + + bool wroteSomething = false; + + while(!in.eof()){ + if (m->control_pressed) { in.close(); out.close(); remove(outputFileName.c_str()); return 0; } + + in >> name; //read from first column + in >> tax; //read from second column + + //if this name is in the accnos file + if (names.count(name) == 0) { + wroteSomething = true; + out << name << '\t' << tax << endl; + } + + gobble(in); + } + in.close(); + out.close(); + + if (wroteSomething == false) { + m->mothurOut("Your file contains only sequences from the .accnos file."); m->mothurOutEndLine(); + remove(outputFileName.c_str()); + }else { outputNames.push_back(outputFileName); } + + return 0; + } + catch(exception& e) { + m->errorOut(e, "RemoveSeqsCommand", "readTax"); + exit(1); + } +} //********************************************************************************************************************** //alignreport file has a column header line then all other lines contain 16 columns. we just want the first column since that contains the name int RemoveSeqsCommand::readAlign(){ @@ -496,7 +546,6 @@ int RemoveSeqsCommand::readAlign(){ out << endl; }else {//still read just don't do anything with it - //names.erase(name); //read rest for (int i = 0; i < 15; i++) { diff --git a/removeseqscommand.h b/removeseqscommand.h index 1f429d9..8238c64 100644 --- a/removeseqscommand.h +++ b/removeseqscommand.h @@ -23,7 +23,7 @@ class RemoveSeqsCommand : public Command { private: set names; - string accnosfile, fastafile, namefile, groupfile, alignfile, listfile, outputDir; + string accnosfile, fastafile, namefile, groupfile, alignfile, listfile, taxfile, outputDir; bool abort, dups; vector outputNames; @@ -33,6 +33,7 @@ class RemoveSeqsCommand : public Command { int readAlign(); void readAccnos(); int readList(); + int readTax(); };