-/*
- * sffinfocommand.cpp
- * Mothur
- *
- * Created by westcott on 7/7/10.
- * Copyright 2010 Schloss Lab. All rights reserved.
- *
- */
-
-#include "sffinfocommand.h"
-#include "endiannessmacros.h"
-
-//**********************************************************************************************************************
-
-SffInfoCommand::SffInfoCommand(string option) {
- try {
- abort = false;
- hasAccnos = false;
-
- //allow user to run help
- if(option == "help") { help(); abort = true; }
-
- else {
- //valid paramters for this command
- string Array[] = {"sff","qfile","fasta","flow","trim","accnos","sfftxt","outputdir","inputdir", "outputdir"};
- vector<string> myArray (Array, Array+(sizeof(Array)/sizeof(string)));
-
- OptionParser parser(option);
- map<string, string> parameters = parser.getParameters();
-
- ValidParameters validParameter;
- //check to make sure all parameters are valid for command
- for (map<string,string>::iterator it = parameters.begin(); it != parameters.end(); it++) {
- if (validParameter.isValidParameter(it->first, myArray, it->second) != true) { abort = true; }
- }
-
- //if the user changes the output directory command factory will send this info to us in the output parameter
- outputDir = validParameter.validFile(parameters, "outputdir", false); if (outputDir == "not found"){ outputDir = ""; }
-
- //if the user changes the input directory command factory will send this info to us in the output parameter
- string inputDir = validParameter.validFile(parameters, "inputdir", false); if (inputDir == "not found"){ inputDir = ""; }
-
- sffFilename = validParameter.validFile(parameters, "sff", false);
- if (sffFilename == "not found") { m->mothurOut("sff is a required parameter for the sffinfo command."); m->mothurOutEndLine(); abort = true; }
- else {
- splitAtDash(sffFilename, filenames);
-
- //go through files and make sure they are good, if not, then disregard them
- for (int i = 0; i < filenames.size(); i++) {
- if (inputDir != "") {
- string path = hasPath(filenames[i]);
- //if the user has not given a path then, add inputdir. else leave path alone.
- if (path == "") { filenames[i] = inputDir + filenames[i]; }
- }
-
- ifstream in;
- int ableToOpen = openInputFile(filenames[i], in, "noerror");
-
- //if you can't open it, try default location
- if (ableToOpen == 1) {
- if (m->getDefaultPath() != "") { //default path is set
- string tryPath = m->getDefaultPath() + getSimpleName(filenames[i]);
- m->mothurOut("Unable to open " + filenames[i] + ". Trying default " + tryPath); m->mothurOutEndLine();
- ableToOpen = openInputFile(tryPath, in, "noerror");
- filenames[i] = tryPath;
- }
- }
- in.close();
-
- if (ableToOpen == 1) {
- m->mothurOut("Unable to open " + filenames[i] + ". It will be disregarded."); m->mothurOutEndLine();
- //erase from file list
- filenames.erase(filenames.begin()+i);
- i--;
- }
- }
-
- //make sure there is at least one valid file left
- if (filenames.size() == 0) { m->mothurOut("no valid files."); m->mothurOutEndLine(); abort = true; }
- }
-
- accnosName = validParameter.validFile(parameters, "accnos", false);
- if (accnosName == "not found") { accnosName = ""; }
- else {
- hasAccnos = true;
- splitAtDash(accnosName, accnosFileNames);
-
- //go through files and make sure they are good, if not, then disregard them
- for (int i = 0; i < accnosFileNames.size(); i++) {
- if (inputDir != "") {
- string path = hasPath(accnosFileNames[i]);
- //if the user has not given a path then, add inputdir. else leave path alone.
- if (path == "") { accnosFileNames[i] = inputDir + accnosFileNames[i]; }
- }
-
- ifstream in;
- int ableToOpen = openInputFile(accnosFileNames[i], in, "noerror");
-
- //if you can't open it, try default location
- if (ableToOpen == 1) {
- if (m->getDefaultPath() != "") { //default path is set
- string tryPath = m->getDefaultPath() + getSimpleName(accnosFileNames[i]);
- m->mothurOut("Unable to open " + accnosFileNames[i] + ". Trying default " + tryPath); m->mothurOutEndLine();
- ableToOpen = openInputFile(tryPath, in, "noerror");
- accnosFileNames[i] = tryPath;
- }
- }
- in.close();
-
- if (ableToOpen == 1) {
- m->mothurOut("Unable to open " + accnosFileNames[i] + ". It will be disregarded."); m->mothurOutEndLine();
- //erase from file list
- accnosFileNames.erase(accnosFileNames.begin()+i);
- i--;
- }
- }
-
- //make sure there is at least one valid file left
- if (accnosFileNames.size() == 0) { m->mothurOut("no valid files."); m->mothurOutEndLine(); abort = true; }
- }
-
- if (hasAccnos) {
- if (accnosFileNames.size() != filenames.size()) { abort = true; m->mothurOut("If you provide a accnos file, you must have one for each sff file."); m->mothurOutEndLine(); }
- }
-
- string temp = validParameter.validFile(parameters, "qfile", false); if (temp == "not found"){ temp = "T"; }
- qual = isTrue(temp);
-
- temp = validParameter.validFile(parameters, "fasta", false); if (temp == "not found"){ temp = "T"; }
- fasta = isTrue(temp);
-
- temp = validParameter.validFile(parameters, "flow", false); if (temp == "not found"){ temp = "F"; }
- flow = isTrue(temp);
-
- temp = validParameter.validFile(parameters, "trim", false); if (temp == "not found"){ temp = "T"; }
- trim = isTrue(temp);
-
- temp = validParameter.validFile(parameters, "sfftxt", false); if (temp == "not found"){ temp = "F"; }
- sfftxt = isTrue(temp);
- }
- }
- catch(exception& e) {
- m->errorOut(e, "SffInfoCommand", "SffInfoCommand");
- exit(1);
- }
-}
-//**********************************************************************************************************************
-
-void SffInfoCommand::help(){
- try {
- m->mothurOut("The sffinfo command reads a sff file and extracts the sequence data.\n");
- m->mothurOut("The sffinfo command parameters are sff, fasta, qfile, accnos, flow, sfftxt, and trim. sff is required. \n");
- m->mothurOut("The sff parameter allows you to enter the sff file you would like to extract data from. You may enter multiple files by separating them by -'s.\n");
- m->mothurOut("The fasta parameter allows you to indicate if you would like a fasta formatted file generated. Default=True. \n");
- m->mothurOut("The qfile parameter allows you to indicate if you would like a quality file generated. Default=True. \n");
- m->mothurOut("The flow parameter allows you to indicate if you would like a flowgram file generated. Default=False. \n");
- m->mothurOut("The sfftxt parameter allows you to indicate if you would like a sff.txt file generated. Default=False. \n");
- m->mothurOut("The trim parameter allows you to indicate if you would like a sequences and quality scores trimmed to the clipQualLeft and clipQualRight values. Default=True. \n");
- m->mothurOut("The accnos parameter allows you to provide a accnos file containing the names of the sequences you would like extracted. You may enter multiple files by separating them by -'s. \n");
- m->mothurOut("Example sffinfo(sff=mySffFile.sff, trim=F).\n");
- m->mothurOut("Note: No spaces between parameter labels (i.e. sff), '=' and parameters (i.e.yourSffFileName).\n\n");
- }
- catch(exception& e) {
- m->errorOut(e, "SffInfoCommand", "help");
- exit(1);
- }
-}
-//**********************************************************************************************************************
-
-SffInfoCommand::~SffInfoCommand(){}
-
-//**********************************************************************************************************************
-int SffInfoCommand::execute(){
- try {
-
- if (abort == true) { return 0; }
-
- for (int s = 0; s < filenames.size(); s++) {
-
- if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; }
-
- int start = time(NULL);
-
- m->mothurOut("Extracting info from " + filenames[s] + " ..." ); m->mothurOutEndLine();
-
- string accnos = "";
- if (hasAccnos) { accnos = accnosFileNames[s]; }
-
- int numReads = extractSffInfo(filenames[s], accnos);
-
- m->mothurOut("It took " + toString(time(NULL) - start) + " secs to extract " + toString(numReads) + ".");
- }
-
- if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; }
-
- //report output filenames
- m->mothurOutEndLine();
- m->mothurOut("Output File Names: "); m->mothurOutEndLine();
- for (int i = 0; i < outputNames.size(); i++) { m->mothurOut(outputNames[i]); m->mothurOutEndLine(); }
- m->mothurOutEndLine();
-
- return 0;
- }
- catch(exception& e) {
- m->errorOut(e, "SffInfoCommand", "execute");
- exit(1);
- }
-}
-//**********************************************************************************************************************
-int SffInfoCommand::extractSffInfo(string input, string accnos){
- try {
-
- if (outputDir == "") { outputDir += hasPath(input); }
-
- if (accnos != "") { readAccnosFile(accnos); }
- else { seqNames.clear(); }
-
- ofstream outSfftxt, outFasta, outQual, outFlow;
- string outFastaFileName, outQualFileName;
- string sfftxtFileName = outputDir + getRootName(getSimpleName(input)) + "sff.txt";
- string outFlowFileName = outputDir + getRootName(getSimpleName(input)) + "flow";
- if (trim) {
- outFastaFileName = outputDir + getRootName(getSimpleName(input)) + "fasta";
- outQualFileName = outputDir + getRootName(getSimpleName(input)) + "qual";
- }else{
- outFastaFileName = outputDir + getRootName(getSimpleName(input)) + "raw.fasta";
- outQualFileName = outputDir + getRootName(getSimpleName(input)) + "raw.qual";
- }
-
- if (sfftxt) { openOutputFile(sfftxtFileName, outSfftxt); outSfftxt.setf(ios::fixed, ios::floatfield); outSfftxt.setf(ios::showpoint); outputNames.push_back(sfftxtFileName); }
- if (fasta) { openOutputFile(outFastaFileName, outFasta); outputNames.push_back(outFastaFileName); }
- if (qual) { openOutputFile(outQualFileName, outQual); outputNames.push_back(outQualFileName); }
- if (flow) { openOutputFile(outFlowFileName, outFlow); outputNames.push_back(outFlowFileName); }
-
- ifstream in;
- in.open(input.c_str(), ios::binary);
-
- CommonHeader header;
- readCommonHeader(in, header);
-
- int count = 0;
-
- //check magic number and version
- if (header.magicNumber != 779314790) { m->mothurOut("Magic Number is not correct, not a valid .sff file"); m->mothurOutEndLine(); return count; }
- if (header.version != "0001") { m->mothurOut("Version is not supported, only support version 0001."); m->mothurOutEndLine(); return count; }
-
- //print common header
- if (sfftxt) { printCommonHeader(outSfftxt, header); }
-
- //read through the sff file
- while (!in.eof()) {
-
- bool print = true;
-
- //read header
- Header readheader;
- readHeader(in, readheader);
-
- //read data
- seqRead read;
- readSeqData(in, read, header.numFlowsPerRead, readheader.numBases);
-
- //if you have provided an accosfile and this seq is not in it, then dont print
- if (seqNames.size() != 0) { if (seqNames.count(readheader.name) == 0) { print = false; } }
-
- //print
- if (print) {
- if (sfftxt) { printHeader(outSfftxt, readheader); printSffTxtSeqData(outSfftxt, read, readheader); }
- if (fasta) { printFastaSeqData(outFasta, read, readheader); }
- if (qual) { printQualSeqData(outQual, read, readheader); }
- if (flow) { printFlowSeqData(outFlow, read, readheader); }
- }
-
- count++;
-
- //report progress
- if((count+1) % 10000 == 0){ m->mothurOut(toString(count+1)); m->mothurOutEndLine(); }
-
- if (m->control_pressed) { count = 0; break; }
-
- if (count >= header.numReads) { break; }
- }
-
- //report progress
- if (!m->control_pressed) { if((count) % 10000 != 0){ m->mothurOut(toString(count)); m->mothurOutEndLine(); } }
-
- in.close();
-
- if (sfftxt) { outSfftxt.close(); }
- if (fasta) { outFasta.close(); }
- if (qual) { outQual.close(); }
- if (flow) { outFlow.close(); }
-
- return count;
- }
- catch(exception& e) {
- m->errorOut(e, "SffInfoCommand", "extractSffInfo");
- exit(1);
- }
-}
-//**********************************************************************************************************************
-int SffInfoCommand::readCommonHeader(ifstream& in, CommonHeader& header){
- try {
-
- if (!in.eof()) {
-
- //read magic number
- char buffer[4];
- in.read(buffer, 4);
- header.magicNumber = be_int4(*(unsigned int *)(&buffer));
-
- //read version
- char buffer9[4];
- in.read(buffer9, 4);
- header.version = "";
- for (int i = 0; i < 4; i++) { header.version += toString((int)(buffer9[i])); }
-
- //read offset
- char buffer2 [8];
- in.read(buffer2, 8);
- header.indexOffset = be_int8(*(unsigned long int *)(&buffer2));
-
- //read index length
- char buffer3 [4];
- in.read(buffer3, 4);
- header.indexLength = be_int4(*(unsigned int *)(&buffer3));
-
- //read num reads
- char buffer4 [4];
- in.read(buffer4, 4);
- header.numReads = be_int4(*(unsigned int *)(&buffer4));
-
- //read header length
- char buffer5 [2];
- in.read(buffer5, 2);
- header.headerLength = be_int2(*(unsigned short *)(&buffer5));
-
- //read key length
- char buffer6 [2];
- in.read(buffer6, 2);
- header.keyLength = be_int2(*(unsigned short *)(&buffer6));
-
- //read number of flow reads
- char buffer7 [2];
- in.read(buffer7, 2);
- header.numFlowsPerRead = be_int2(*(unsigned short *)(&buffer7));
-
- //read format code
- char buffer8 [1];
- in.read(buffer8, 1);
- header.flogramFormatCode = (int)(buffer8[0]);
-
- //read flow chars
- char* tempBuffer = new char[header.numFlowsPerRead];
- in.read(&(*tempBuffer), header.numFlowsPerRead);
- header.flowChars = tempBuffer;
- if (header.flowChars.length() > header.numFlowsPerRead) { header.flowChars = header.flowChars.substr(0, header.numFlowsPerRead); }
- delete[] tempBuffer;
-
- //read key
- char* tempBuffer2 = new char[header.keyLength];
- in.read(&(*tempBuffer2), header.keyLength);
- header.keySequence = tempBuffer2;
- if (header.keySequence.length() > header.keyLength) { header.keySequence = header.keySequence.substr(0, header.keyLength); }
- delete[] tempBuffer2;
-
- /* Pad to 8 chars */
- unsigned long int spotInFile = in.tellg();
- unsigned long int spot = (spotInFile + 7)& ~7; // ~ inverts
- in.seekg(spot);
-
- }else{
- m->mothurOut("Error reading sff common header."); m->mothurOutEndLine();
- }
-
- return 0;
- }
- catch(exception& e) {
- m->errorOut(e, "SffInfoCommand", "readCommonHeader");
- exit(1);
- }
-}
-//**********************************************************************************************************************
-int SffInfoCommand::readHeader(ifstream& in, Header& header){
- try {
-
- if (!in.eof()) {
-
- //read header length
- char buffer [2];
- in.read(buffer, 2);
- header.headerLength = be_int2(*(unsigned short *)(&buffer));
-
- //read name length
- char buffer2 [2];
- in.read(buffer2, 2);
- header.nameLength = be_int2(*(unsigned short *)(&buffer2));
-
- //read num bases
- char buffer3 [4];
- in.read(buffer3, 4);
- header.numBases = be_int4(*(unsigned int *)(&buffer3));
-
- //read clip qual left
- char buffer4 [2];
- in.read(buffer4, 2);
- header.clipQualLeft = be_int2(*(unsigned short *)(&buffer4));
-
- //read clip qual right
- char buffer5 [2];
- in.read(buffer5, 2);
- header.clipQualRight = be_int2(*(unsigned short *)(&buffer5));
- if(header.clipQualRight == 0){ header.clipQualRight = numBases; }
-
- //read clipAdapterLeft
- char buffer6 [2];
- in.read(buffer6, 2);
- header.clipAdapterLeft = be_int2(*(unsigned short *)(&buffer6));
-
- //read clipAdapterRight
- char buffer7 [2];
- in.read(buffer7, 2);
- header.clipAdapterRight = be_int2(*(unsigned short *)(&buffer7));
-
- //read name
- char* tempBuffer = new char[header.nameLength];
- in.read(&(*tempBuffer), header.nameLength);
- header.name = tempBuffer;
- if (header.name.length() > header.nameLength) { header.name = header.name.substr(0, header.nameLength); }
- delete[] tempBuffer;
-
- /* Pad to 8 chars */
- unsigned long int spotInFile = in.tellg();
- unsigned long int spot = (spotInFile + 7)& ~7;
- in.seekg(spot);
-
- }else{
- m->mothurOut("Error reading sff header info."); m->mothurOutEndLine();
- }
-
- return 0;
- }
- catch(exception& e) {
- m->errorOut(e, "SffInfoCommand", "readHeader");
- exit(1);
- }
-}
-//**********************************************************************************************************************
-int SffInfoCommand::readSeqData(ifstream& in, seqRead& read, int numFlowReads, int numBases){
- try {
-
- if (!in.eof()) {
-
- //read flowgram
- read.flowgram.resize(numFlowReads);
- for (int i = 0; i < numFlowReads; i++) {
- char buffer [2];
- in.read(buffer, 2);
- read.flowgram[i] = be_int2(*(unsigned short *)(&buffer));
- }
-
- //read flowIndex
- read.flowIndex.resize(numBases);
- for (int i = 0; i < numBases; i++) {
- char temp[1];
- in.read(temp, 1);
- read.flowIndex[i] = be_int1(*(unsigned char *)(&temp));
- }
-
- //read bases
- char* tempBuffer = new char[numBases];
- in.read(&(*tempBuffer), numBases);
- read.bases = tempBuffer;
- if (read.bases.length() > numBases) { read.bases = read.bases.substr(0, numBases); }
- delete[] tempBuffer;
-
- //read qual scores
- read.qualScores.resize(numBases);
- for (int i = 0; i < numBases; i++) {
- char temp[1];
- in.read(temp, 1);
- read.qualScores[i] = be_int1(*(unsigned char *)(&temp));
- }
-
- /* Pad to 8 chars */
- unsigned long int spotInFile = in.tellg();
- unsigned long int spot = (spotInFile + 7)& ~7;
- in.seekg(spot);
-
- }else{
- m->mothurOut("Error reading."); m->mothurOutEndLine();
- }
-
- return 0;
- }
- catch(exception& e) {
- m->errorOut(e, "SffInfoCommand", "readSeqData");
- exit(1);
- }
-}
-//**********************************************************************************************************************
-int SffInfoCommand::printCommonHeader(ofstream& out, CommonHeader& header) {
- try {
-
- out << "Common Header:\nMagic Number: " << header.magicNumber << endl;
- out << "Version: " << header.version << endl;
- out << "Index Offset: " << header.indexOffset << endl;
- out << "Index Length: " << header.indexLength << endl;
- out << "Number of Reads: " << header.numReads << endl;
- out << "Header Length: " << header.headerLength << endl;
- out << "Key Length: " << header.keyLength << endl;
- out << "Number of Flows: " << header.numFlowsPerRead << endl;
- out << "Format Code: " << header.flogramFormatCode << endl;
- out << "Flow Chars: " << header.flowChars << endl;
- out << "Key Sequence: " << header.keySequence << endl << endl;
-
- return 0;
- }
- catch(exception& e) {
- m->errorOut(e, "SffInfoCommand", "printCommonHeader");
- exit(1);
- }
-}
-//**********************************************************************************************************************
-int SffInfoCommand::printHeader(ofstream& out, Header& header) {
- try {
-
- out << ">" << header.name << endl;
- out << "Run Prefix: " << endl;
- out << "Region #: " << endl;
- out << "XY Location: " << endl << endl;
-
- out << "Run Name: " << endl;
- out << "Analysis Name: " << endl;
- out << "Full Path: " << endl << endl;
-
- out << "Read Header Len: " << header.headerLength << endl;
- out << "Name Length: " << header.nameLength << endl;
- out << "# of Bases: " << header.numBases << endl;
- out << "Clip Qual Left: " << header.clipQualLeft << endl;
- out << "Clip Qual Right: " << header.clipQualRight << endl;
- out << "Clip Adap Left: " << header.clipAdapterLeft << endl;
- out << "Clip Adap Right: " << header.clipAdapterRight << endl << endl;
-
- return 0;
- }
- catch(exception& e) {
- m->errorOut(e, "SffInfoCommand", "printHeader");
- exit(1);
- }
-}
-
-//**********************************************************************************************************************
-int SffInfoCommand::printSffTxtSeqData(ofstream& out, seqRead& read, Header& header) {
- try {
-
- out << "Flowgram: ";
- for (int i = 0; i < read.flowgram.size(); i++) { out << setprecision(2) << (read.flowgram[i]/(float)100) << '\t'; }
-
- out << endl << "Flow Indexes: ";
- int sum = 0;
- for (int i = 0; i < read.flowIndex.size(); i++) { sum += read.flowIndex[i]; out << sum << '\t'; }
-
- //make the bases you want to clip lowercase and the bases you want to keep upper case
- for (int i = 0; i < (header.clipQualLeft-1); i++) { read.bases[i] = tolower(read.bases[i]); }
- for (int i = (header.clipQualLeft-1); i < (header.clipQualRight-1); i++) { read.bases[i] = toupper(read.bases[i]); }
- for (int i = (header.clipQualRight-1); i < read.bases.length(); i++) { read.bases[i] = tolower(read.bases[i]); }
-
- out << endl << "Bases: " << read.bases << endl << "Quality Scores: ";
- for (int i = 0; i < read.qualScores.size(); i++) { out << read.qualScores[i] << '\t'; }
-
-
- out << endl << endl;
-
- return 0;
- }
- catch(exception& e) {
- m->errorOut(e, "SffInfoCommand", "printSffTxtSeqData");
- exit(1);
- }
-}
-//**********************************************************************************************************************
-int SffInfoCommand::printFastaSeqData(ofstream& out, seqRead& read, Header& header) {
- try {
-
- string seq = read.bases;
-
- if (trim) {
- seq = seq.substr((header.clipQualLeft-1), (header.clipQualRight-header.clipQualLeft+1));
- }else{
- //if you wanted the sfftxt then you already converted the bases to the right case
- if (!sfftxt) {
- //make the bases you want to clip lowercase and the bases you want to keep upper case
- for (int i = 0; i < (header.clipQualLeft-1); i++) { seq[i] = tolower(seq[i]); }
- for (int i = (header.clipQualLeft-1); i < (header.clipQualRight-1); i++) { seq[i] = toupper(seq[i]); }
- for (int i = (header.clipQualRight-1); i < seq.length(); i++) { seq[i] = tolower(seq[i]); }
- }
- }
-
- out << ">" << header.name << endl;
- out << seq << endl;
-
- return 0;
- }
- catch(exception& e) {
- m->errorOut(e, "SffInfoCommand", "printFastaSeqData");
- exit(1);
- }
-}
-
-//**********************************************************************************************************************
-int SffInfoCommand::printQualSeqData(ofstream& out, seqRead& read, Header& header) {
- try {
-
- if (trim) {
- out << ">" << header.name << " length=" << (header.clipQualRight-header.clipQualLeft+1) << endl;
- for (int i = (header.clipQualLeft-1); i < (header.clipQualRight-1); i++) { out << read.qualScores[i] << '\t'; }
- }else{
- out << ">" << header.name << " length=" << read.qualScores.size() << endl;
- for (int i = 0; i < read.qualScores.size(); i++) { out << read.qualScores[i] << '\t'; }
- }
-
- out << endl;
-
- return 0;
- }
- catch(exception& e) {
- m->errorOut(e, "SffInfoCommand", "printQualSeqData");
- exit(1);
- }
-}
-
-//**********************************************************************************************************************
-int SffInfoCommand::printFlowSeqData(ofstream& out, seqRead& read, Header& header) {
- try {
-
- out << ">" << header.name << endl;
- for (int i = 0; i < read.flowgram.size(); i++) { out << setprecision(2) << (read.flowgram[i]/(float)100) << '\t'; }
- out << endl;
-
- return 0;
- }
- catch(exception& e) {
- m->errorOut(e, "SffInfoCommand", "printFlowSeqData");
- exit(1);
- }
-}
-//**********************************************************************************************************************
-int SffInfoCommand::readAccnosFile(string filename) {
- try {
- //remove old names
- seqNames.clear();
-
- ifstream in;
- openInputFile(filename, in);
- string name;
-
- while(!in.eof()){
- in >> name; gobble(in);
-
- seqNames.insert(name);
-
- if (m->control_pressed) { seqNames.clear(); break; }
- }
- in.close();
-
- return 0;
- }
- catch(exception& e) {
- m->errorOut(e, "SffInfoCommand", "readAccnosFile");
- exit(1);
- }
-}
-//**********************************************************************************************************************/
+/*\r
+ * sffinfocommand.cpp\r
+ * Mothur\r
+ *\r
+ * Created by westcott on 7/7/10.\r
+ * Copyright 2010 Schloss Lab. All rights reserved.\r
+ *\r
+ */\r
+\r
+#include "sffinfocommand.h"\r
+#include "endiannessmacros.h"\r
+#include "trimoligos.h"\r
+#include "sequence.hpp"\r
+#include "qualityscores.h"\r
+\r
+//**********************************************************************************************************************\r
+vector<string> SffInfoCommand::setParameters(){ \r
+ try { \r
+ CommandParameter psff("sff", "InputTypes", "", "", "none", "none", "none","",false,false,true); parameters.push_back(psff);\r
+ CommandParameter poligos("oligos", "InputTypes", "", "", "oligosGroup", "none", "none","",false,false); parameters.push_back(poligos);\r
+ CommandParameter pgroup("group", "InputTypes", "", "", "oligosGroup", "none", "none","",false,false); parameters.push_back(pgroup);\r
+ CommandParameter paccnos("accnos", "InputTypes", "", "", "none", "none", "none","",false,false); parameters.push_back(paccnos);\r
+ CommandParameter psfftxt("sfftxt", "String", "", "", "", "", "","",false,false); parameters.push_back(psfftxt);\r
+ CommandParameter pflow("flow", "Boolean", "", "T", "", "", "","flow",false,false); parameters.push_back(pflow);\r
+ CommandParameter ptrim("trim", "Boolean", "", "T", "", "", "","",false,false); parameters.push_back(ptrim);\r
+ CommandParameter pfasta("fasta", "Boolean", "", "T", "", "", "","fasta",false,false); parameters.push_back(pfasta);\r
+ CommandParameter pqfile("qfile", "Boolean", "", "T", "", "", "","qfile",false,false); parameters.push_back(pqfile);\r
+ CommandParameter ppdiffs("pdiffs", "Number", "", "0", "", "", "","",false,false); parameters.push_back(ppdiffs);\r
+ CommandParameter pbdiffs("bdiffs", "Number", "", "0", "", "", "","",false,false); parameters.push_back(pbdiffs);\r
+ CommandParameter pldiffs("ldiffs", "Number", "", "0", "", "", "","",false,false); parameters.push_back(pldiffs);\r
+ CommandParameter psdiffs("sdiffs", "Number", "", "0", "", "", "","",false,false); parameters.push_back(psdiffs);\r
+ CommandParameter ptdiffs("tdiffs", "Number", "", "0", "", "", "","",false,false); parameters.push_back(ptdiffs);\r
+ CommandParameter pinputdir("inputdir", "String", "", "", "", "", "","",false,false); parameters.push_back(pinputdir);\r
+ CommandParameter poutputdir("outputdir", "String", "", "", "", "", "","",false,false); parameters.push_back(poutputdir);\r
+ \r
+ vector<string> myArray;\r
+ for (int i = 0; i < parameters.size(); i++) { myArray.push_back(parameters[i].name); }\r
+ return myArray;\r
+ }\r
+ catch(exception& e) {\r
+ m->errorOut(e, "SffInfoCommand", "setParameters");\r
+ exit(1);\r
+ }\r
+}\r
+//**********************************************************************************************************************\r
+string SffInfoCommand::getHelpString(){ \r
+ try {\r
+ string helpString = "";\r
+ helpString += "The sffinfo command reads a sff file and extracts the sequence data, or you can use it to parse a sfftxt file.\n";\r
+ helpString += "The sffinfo command parameters are sff, fasta, qfile, accnos, flow, sfftxt, oligos, group, bdiffs, tdiffs, ldiffs, sdiffs, pdiffs and trim. sff is required. \n";\r
+ helpString += "The sff parameter allows you to enter the sff file you would like to extract data from. You may enter multiple files by separating them by -'s.\n";\r
+ helpString += "The fasta parameter allows you to indicate if you would like a fasta formatted file generated. Default=True. \n";\r
+ helpString += "The qfile parameter allows you to indicate if you would like a quality file generated. Default=True. \n";\r
+ helpString += "The oligos parameter allows you to provide an oligos file to split your sff file into separate sff files by barcode. \n";\r
+ helpString += "The group parameter allows you to provide a group file to split your sff file into separate sff files by group. \n";\r
+ helpString += "The tdiffs parameter is used to specify the total number of differences allowed in the sequence. The default is pdiffs + bdiffs + sdiffs + ldiffs.\n";\r
+ helpString += "The bdiffs parameter is used to specify the number of differences allowed in the barcode. The default is 0.\n";\r
+ helpString += "The pdiffs parameter is used to specify the number of differences allowed in the primer. The default is 0.\n";\r
+ helpString += "The ldiffs parameter is used to specify the number of differences allowed in the linker. The default is 0.\n";\r
+ helpString += "The sdiffs parameter is used to specify the number of differences allowed in the spacer. The default is 0.\n";\r
+ helpString += "The flow parameter allows you to indicate if you would like a flowgram file generated. Default=True. \n";\r
+ helpString += "The sfftxt parameter allows you to indicate if you would like a sff.txt file generated. Default=False. \n";\r
+ helpString += "If you want to parse an existing sfftxt file into flow, fasta and quality file, enter the file name using the sfftxt parameter. \n";\r
+ helpString += "The trim parameter allows you to indicate if you would like a sequences and quality scores trimmed to the clipQualLeft and clipQualRight values. Default=True. \n";\r
+ helpString += "The accnos parameter allows you to provide a accnos file containing the names of the sequences you would like extracted. You may enter multiple files by separating them by -'s. \n";\r
+ helpString += "Example sffinfo(sff=mySffFile.sff, trim=F).\n";\r
+ helpString += "Note: No spaces between parameter labels (i.e. sff), '=' and parameters (i.e.yourSffFileName).\n";\r
+ return helpString;\r
+ }\r
+ catch(exception& e) {\r
+ m->errorOut(e, "SffInfoCommand", "getHelpString");\r
+ exit(1);\r
+ }\r
+}\r
+\r
+//**********************************************************************************************************************\r
+string SffInfoCommand::getOutputPattern(string type) {\r
+ try {\r
+ string pattern = "";\r
+ \r
+ if (type == "fasta") { pattern = "[filename],fasta-[filename],[tag],fasta"; }\r
+ else if (type == "flow") { pattern = "[filename],flow"; }\r
+ else if (type == "sfftxt") { pattern = "[filename],sff.txt"; }\r
+ else if (type == "sff") { pattern = "[filename],[group],sff"; }\r
+ else if (type == "qfile") { pattern = "[filename],qual-[filename],[tag],qual"; }\r
+ else { m->mothurOut("[ERROR]: No definition for type " + type + " output pattern.\n"); m->control_pressed = true; }\r
+ \r
+ return pattern;\r
+ }\r
+ catch(exception& e) {\r
+ m->errorOut(e, "SffInfoCommand", "getOutputPattern");\r
+ exit(1);\r
+ }\r
+}\r
+//**********************************************************************************************************************\r
+SffInfoCommand::SffInfoCommand(){ \r
+ try {\r
+ abort = true; calledHelp = true; \r
+ setParameters();\r
+ vector<string> tempOutNames;\r
+ outputTypes["fasta"] = tempOutNames;\r
+ outputTypes["flow"] = tempOutNames;\r
+ outputTypes["sfftxt"] = tempOutNames;\r
+ outputTypes["qfile"] = tempOutNames;\r
+ outputTypes["sff"] = tempOutNames;\r
+ }\r
+ catch(exception& e) {\r
+ m->errorOut(e, "SffInfoCommand", "SffInfoCommand");\r
+ exit(1);\r
+ }\r
+}\r
+//**********************************************************************************************************************\r
+\r
+SffInfoCommand::SffInfoCommand(string option) {\r
+ try {\r
+ abort = false; calledHelp = false; \r
+ hasAccnos = false; hasOligos = false; hasGroup = false;\r
+ split = 1;\r
+ \r
+ //allow user to run help\r
+ if(option == "help") { help(); abort = true; calledHelp = true; }\r
+ else if(option == "citation") { citation(); abort = true; calledHelp = true;}\r
+ \r
+ else {\r
+ //valid paramters for this command\r
+ vector<string> myArray = setParameters();\r
+ \r
+ OptionParser parser(option);\r
+ map<string, string> parameters = parser.getParameters();\r
+ \r
+ ValidParameters validParameter;\r
+ //check to make sure all parameters are valid for command\r
+ for (map<string,string>::iterator it = parameters.begin(); it != parameters.end(); it++) { \r
+ if (validParameter.isValidParameter(it->first, myArray, it->second) != true) { abort = true; }\r
+ }\r
+ \r
+ //initialize outputTypes\r
+ vector<string> tempOutNames;\r
+ outputTypes["fasta"] = tempOutNames;\r
+ outputTypes["flow"] = tempOutNames;\r
+ outputTypes["sfftxt"] = tempOutNames;\r
+ outputTypes["qfile"] = tempOutNames;\r
+ outputTypes["sff"] = tempOutNames;\r
+ \r
+ //if the user changes the output directory command factory will send this info to us in the output parameter \r
+ outputDir = validParameter.validFile(parameters, "outputdir", false); if (outputDir == "not found"){ outputDir = ""; }\r
+ \r
+ //if the user changes the input directory command factory will send this info to us in the output parameter \r
+ string inputDir = validParameter.validFile(parameters, "inputdir", false); if (inputDir == "not found"){ inputDir = ""; }\r
+\r
+ sffFilename = validParameter.validFile(parameters, "sff", false);\r
+ if (sffFilename == "not found") { sffFilename = ""; }\r
+ else { \r
+ m->splitAtDash(sffFilename, filenames);\r
+ \r
+ //go through files and make sure they are good, if not, then disregard them\r
+ for (int i = 0; i < filenames.size(); i++) {\r
+ bool ignore = false;\r
+ if (filenames[i] == "current") { \r
+ filenames[i] = m->getSFFFile(); \r
+ if (filenames[i] != "") { m->mothurOut("Using " + filenames[i] + " as input file for the sff parameter where you had given current."); m->mothurOutEndLine(); }\r
+ else { \r
+ m->mothurOut("You have no current sfffile, ignoring current."); m->mothurOutEndLine(); ignore=true; \r
+ //erase from file list\r
+ filenames.erase(filenames.begin()+i);\r
+ i--;\r
+ }\r
+ }\r
+ \r
+ if (!ignore) {\r
+ if (inputDir != "") {\r
+ string path = m->hasPath(filenames[i]);\r
+ //if the user has not given a path then, add inputdir. else leave path alone.\r
+ if (path == "") { filenames[i] = inputDir + filenames[i]; }\r
+ }\r
+ \r
+ ifstream in;\r
+ int ableToOpen = m->openInputFile(filenames[i], in, "noerror");\r
+ \r
+ //if you can't open it, try default location\r
+ if (ableToOpen == 1) {\r
+ if (m->getDefaultPath() != "") { //default path is set\r
+ string tryPath = m->getDefaultPath() + m->getSimpleName(filenames[i]);\r
+ m->mothurOut("Unable to open " + filenames[i] + ". Trying default " + tryPath); m->mothurOutEndLine();\r
+ ifstream in2;\r
+ ableToOpen = m->openInputFile(tryPath, in2, "noerror");\r
+ in2.close();\r
+ filenames[i] = tryPath;\r
+ }\r
+ }\r
+ \r
+ //if you can't open it, try default location\r
+ if (ableToOpen == 1) {\r
+ if (m->getOutputDir() != "") { //default path is set\r
+ string tryPath = m->getOutputDir() + m->getSimpleName(filenames[i]);\r
+ m->mothurOut("Unable to open " + filenames[i] + ". Trying output directory " + tryPath); m->mothurOutEndLine();\r
+ ifstream in2;\r
+ ableToOpen = m->openInputFile(tryPath, in2, "noerror");\r
+ in2.close();\r
+ filenames[i] = tryPath;\r
+ }\r
+ }\r
+ \r
+ in.close();\r
+ \r
+ if (ableToOpen == 1) { \r
+ m->mothurOut("Unable to open " + filenames[i] + ". It will be disregarded."); m->mothurOutEndLine();\r
+ //erase from file list\r
+ filenames.erase(filenames.begin()+i);\r
+ i--;\r
+ }else { m->setSFFFile(filenames[i]); }\r
+ }\r
+ }\r
+ \r
+ //make sure there is at least one valid file left\r
+ if (filenames.size() == 0) { m->mothurOut("no valid files."); m->mothurOutEndLine(); abort = true; }\r
+ }\r
+ \r
+ accnosName = validParameter.validFile(parameters, "accnos", false);\r
+ if (accnosName == "not found") { accnosName = ""; }\r
+ else { \r
+ hasAccnos = true;\r
+ m->splitAtDash(accnosName, accnosFileNames);\r
+ \r
+ //go through files and make sure they are good, if not, then disregard them\r
+ for (int i = 0; i < accnosFileNames.size(); i++) {\r
+ bool ignore = false;\r
+ if (accnosFileNames[i] == "current") { \r
+ accnosFileNames[i] = m->getAccnosFile(); \r
+ if (accnosFileNames[i] != "") { m->mothurOut("Using " + accnosFileNames[i] + " as input file for the accnos parameter where you had given current."); m->mothurOutEndLine(); }\r
+ else { \r
+ m->mothurOut("You have no current accnosfile, ignoring current."); m->mothurOutEndLine(); ignore=true; \r
+ //erase from file list\r
+ accnosFileNames.erase(accnosFileNames.begin()+i);\r
+ i--;\r
+ }\r
+ }\r
+ \r
+ if (!ignore) {\r
+ \r
+ if (inputDir != "") {\r
+ string path = m->hasPath(accnosFileNames[i]);\r
+ //if the user has not given a path then, add inputdir. else leave path alone.\r
+ if (path == "") { accnosFileNames[i] = inputDir + accnosFileNames[i]; }\r
+ }\r
+ \r
+ ifstream in;\r
+ int ableToOpen = m->openInputFile(accnosFileNames[i], in, "noerror");\r
+ \r
+ //if you can't open it, try default location\r
+ if (ableToOpen == 1) {\r
+ if (m->getDefaultPath() != "") { //default path is set\r
+ string tryPath = m->getDefaultPath() + m->getSimpleName(accnosFileNames[i]);\r
+ m->mothurOut("Unable to open " + accnosFileNames[i] + ". Trying default " + tryPath); m->mothurOutEndLine();\r
+ ifstream in2;\r
+ ableToOpen = m->openInputFile(tryPath, in2, "noerror");\r
+ in2.close();\r
+ accnosFileNames[i] = tryPath;\r
+ }\r
+ }\r
+ //if you can't open it, try default location\r
+ if (ableToOpen == 1) {\r
+ if (m->getOutputDir() != "") { //default path is set\r
+ string tryPath = m->getOutputDir() + m->getSimpleName(accnosFileNames[i]);\r
+ m->mothurOut("Unable to open " + accnosFileNames[i] + ". Trying output directory " + tryPath); m->mothurOutEndLine();\r
+ ifstream in2;\r
+ ableToOpen = m->openInputFile(tryPath, in2, "noerror");\r
+ in2.close();\r
+ accnosFileNames[i] = tryPath;\r
+ }\r
+ }\r
+ in.close();\r
+ \r
+ if (ableToOpen == 1) { \r
+ m->mothurOut("Unable to open " + accnosFileNames[i] + ". It will be disregarded."); m->mothurOutEndLine();\r
+ //erase from file list\r
+ accnosFileNames.erase(accnosFileNames.begin()+i);\r
+ i--;\r
+ }\r
+ }\r
+ }\r
+ \r
+ //make sure there is at least one valid file left\r
+ if (accnosFileNames.size() == 0) { m->mothurOut("no valid files."); m->mothurOutEndLine(); abort = true; }\r
+ }\r
+ \r
+ oligosfile = validParameter.validFile(parameters, "oligos", false);\r
+ if (oligosfile == "not found") { oligosfile = ""; }\r
+ else { \r
+ hasOligos = true;\r
+ m->splitAtDash(oligosfile, oligosFileNames);\r
+ \r
+ //go through files and make sure they are good, if not, then disregard them\r
+ for (int i = 0; i < oligosFileNames.size(); i++) {\r
+ bool ignore = false;\r
+ if (oligosFileNames[i] == "current") { \r
+ oligosFileNames[i] = m->getOligosFile(); \r
+ if (oligosFileNames[i] != "") { m->mothurOut("Using " + oligosFileNames[i] + " as input file for the oligos parameter where you had given current."); m->mothurOutEndLine(); }\r
+ else { \r
+ m->mothurOut("You have no current oligosfile, ignoring current."); m->mothurOutEndLine(); ignore=true; \r
+ //erase from file list\r
+ oligosFileNames.erase(oligosFileNames.begin()+i);\r
+ i--;\r
+ }\r
+ }\r
+ \r
+ if (!ignore) {\r
+ \r
+ if (inputDir != "") {\r
+ string path = m->hasPath(oligosFileNames[i]);\r
+ //if the user has not given a path then, add inputdir. else leave path alone.\r
+ if (path == "") { oligosFileNames[i] = inputDir + oligosFileNames[i]; }\r
+ }\r
+ \r
+ ifstream in;\r
+ int ableToOpen = m->openInputFile(oligosFileNames[i], in, "noerror");\r
+ \r
+ //if you can't open it, try default location\r
+ if (ableToOpen == 1) {\r
+ if (m->getDefaultPath() != "") { //default path is set\r
+ string tryPath = m->getDefaultPath() + m->getSimpleName(oligosFileNames[i]);\r
+ m->mothurOut("Unable to open " + oligosFileNames[i] + ". Trying default " + tryPath); m->mothurOutEndLine();\r
+ ifstream in2;\r
+ ableToOpen = m->openInputFile(tryPath, in2, "noerror");\r
+ in2.close();\r
+ oligosFileNames[i] = tryPath;\r
+ }\r
+ }\r
+ //if you can't open it, try default location\r
+ if (ableToOpen == 1) {\r
+ if (m->getOutputDir() != "") { //default path is set\r
+ string tryPath = m->getOutputDir() + m->getSimpleName(oligosFileNames[i]);\r
+ m->mothurOut("Unable to open " + oligosFileNames[i] + ". Trying output directory " + tryPath); m->mothurOutEndLine();\r
+ ifstream in2;\r
+ ableToOpen = m->openInputFile(tryPath, in2, "noerror");\r
+ in2.close();\r
+ oligosFileNames[i] = tryPath;\r
+ }\r
+ }\r
+ in.close();\r
+ \r
+ if (ableToOpen == 1) { \r
+ m->mothurOut("Unable to open " + oligosFileNames[i] + ". It will be disregarded."); m->mothurOutEndLine();\r
+ //erase from file list\r
+ oligosFileNames.erase(oligosFileNames.begin()+i);\r
+ i--;\r
+ }\r
+ }\r
+ }\r
+ \r
+ //make sure there is at least one valid file left\r
+ if (oligosFileNames.size() == 0) { m->mothurOut("no valid oligos files."); m->mothurOutEndLine(); abort = true; }\r
+ }\r
+ \r
+ groupfile = validParameter.validFile(parameters, "group", false);\r
+ if (groupfile == "not found") { groupfile = ""; }\r
+ else {\r
+ hasGroup = true;\r
+ m->splitAtDash(groupfile, groupFileNames);\r
+ \r
+ //go through files and make sure they are good, if not, then disregard them\r
+ for (int i = 0; i < groupFileNames.size(); i++) {\r
+ bool ignore = false;\r
+ if (groupFileNames[i] == "current") {\r
+ groupFileNames[i] = m->getGroupFile();\r
+ if (groupFileNames[i] != "") { m->mothurOut("Using " + groupFileNames[i] + " as input file for the group parameter where you had given current."); m->mothurOutEndLine(); }\r
+ else {\r
+ m->mothurOut("You have no current group file, ignoring current."); m->mothurOutEndLine(); ignore=true;\r
+ //erase from file list\r
+ groupFileNames.erase(groupFileNames.begin()+i);\r
+ i--;\r
+ }\r
+ }\r
+ \r
+ if (!ignore) {\r
+ \r
+ if (inputDir != "") {\r
+ string path = m->hasPath(groupFileNames[i]);\r
+ //if the user has not given a path then, add inputdir. else leave path alone.\r
+ if (path == "") { groupFileNames[i] = inputDir + groupFileNames[i]; }\r
+ }\r
+ \r
+ ifstream in;\r
+ int ableToOpen = m->openInputFile(groupFileNames[i], in, "noerror");\r
+ \r
+ //if you can't open it, try default location\r
+ if (ableToOpen == 1) {\r
+ if (m->getDefaultPath() != "") { //default path is set\r
+ string tryPath = m->getDefaultPath() + m->getSimpleName(groupFileNames[i]);\r
+ m->mothurOut("Unable to open " + groupFileNames[i] + ". Trying default " + tryPath); m->mothurOutEndLine();\r
+ ifstream in2;\r
+ ableToOpen = m->openInputFile(tryPath, in2, "noerror");\r
+ in2.close();\r
+ groupFileNames[i] = tryPath;\r
+ }\r
+ }\r
+ //if you can't open it, try default location\r
+ if (ableToOpen == 1) {\r
+ if (m->getOutputDir() != "") { //default path is set\r
+ string tryPath = m->getOutputDir() + m->getSimpleName(groupFileNames[i]);\r
+ m->mothurOut("Unable to open " + groupFileNames[i] + ". Trying output directory " + tryPath); m->mothurOutEndLine();\r
+ ifstream in2;\r
+ ableToOpen = m->openInputFile(tryPath, in2, "noerror");\r
+ in2.close();\r
+ groupFileNames[i] = tryPath;\r
+ }\r
+ }\r
+ in.close();\r
+ \r
+ if (ableToOpen == 1) {\r
+ m->mothurOut("Unable to open " + groupFileNames[i] + ". It will be disregarded."); m->mothurOutEndLine();\r
+ //erase from file list\r
+ groupFileNames.erase(groupFileNames.begin()+i);\r
+ i--;\r
+ }\r
+ }\r
+ }\r
+ \r
+ //make sure there is at least one valid file left\r
+ if (groupFileNames.size() == 0) { m->mothurOut("no valid group files."); m->mothurOutEndLine(); abort = true; }\r
+ }\r
+\r
+ if (hasGroup) {\r
+ split = 2;\r
+ if (groupFileNames.size() != filenames.size()) { abort = true; m->mothurOut("If you provide a group file, you must have one for each sff file."); m->mothurOutEndLine(); }\r
+ }\r
+ \r
+ if (hasOligos) {\r
+ split = 2;\r
+ if (oligosFileNames.size() != filenames.size()) { abort = true; m->mothurOut("If you provide an oligos file, you must have one for each sff file."); m->mothurOutEndLine(); }\r
+ }\r
+ \r
+ if (hasGroup && hasOligos) { m->mothurOut("You must enter ONLY ONE of the following: oligos or group."); m->mothurOutEndLine(); abort = true;}\r
+ \r
+ if (hasAccnos) {\r
+ if (accnosFileNames.size() != filenames.size()) { abort = true; m->mothurOut("If you provide a accnos file, you must have one for each sff file."); m->mothurOutEndLine(); }\r
+ }\r
+ \r
+ string temp = validParameter.validFile(parameters, "qfile", false); if (temp == "not found"){ temp = "T"; }\r
+ qual = m->isTrue(temp); \r
+ \r
+ temp = validParameter.validFile(parameters, "fasta", false); if (temp == "not found"){ temp = "T"; }\r
+ fasta = m->isTrue(temp); \r
+ \r
+ temp = validParameter.validFile(parameters, "flow", false); if (temp == "not found"){ temp = "T"; }\r
+ flow = m->isTrue(temp); \r
+ \r
+ temp = validParameter.validFile(parameters, "trim", false); if (temp == "not found"){ temp = "T"; }\r
+ trim = m->isTrue(temp); \r
+ \r
+ temp = validParameter.validFile(parameters, "bdiffs", false); if (temp == "not found") { temp = "0"; }\r
+ m->mothurConvert(temp, bdiffs);\r
+ \r
+ temp = validParameter.validFile(parameters, "pdiffs", false); if (temp == "not found") { temp = "0"; }\r
+ m->mothurConvert(temp, pdiffs);\r
+ \r
+ temp = validParameter.validFile(parameters, "ldiffs", false); if (temp == "not found") { temp = "0"; }\r
+ m->mothurConvert(temp, ldiffs);\r
+ \r
+ temp = validParameter.validFile(parameters, "sdiffs", false); if (temp == "not found") { temp = "0"; }\r
+ m->mothurConvert(temp, sdiffs);\r
+ \r
+ temp = validParameter.validFile(parameters, "tdiffs", false); if (temp == "not found") { int tempTotal = pdiffs + bdiffs + ldiffs + sdiffs; temp = toString(tempTotal); }\r
+ m->mothurConvert(temp, tdiffs);\r
+ \r
+ if(tdiffs == 0){ tdiffs = bdiffs + pdiffs + ldiffs + sdiffs; }\r
+ \r
+ temp = validParameter.validFile(parameters, "sfftxt", false); \r
+ if (temp == "not found") { temp = "F"; sfftxt = false; sfftxtFilename = ""; }\r
+ else if (m->isTrue(temp)) { sfftxt = true; sfftxtFilename = ""; }\r
+ else {\r
+ //you are a filename\r
+ if (inputDir != "") {\r
+ map<string,string>::iterator it = parameters.find("sfftxt");\r
+ //user has given a template file\r
+ if(it != parameters.end()){ \r
+ string path = m->hasPath(it->second);\r
+ //if the user has not given a path then, add inputdir. else leave path alone.\r
+ if (path == "") { parameters["sfftxt"] = inputDir + it->second; }\r
+ }\r
+ }\r
+ \r
+ sfftxtFilename = validParameter.validFile(parameters, "sfftxt", true);\r
+ if (sfftxtFilename == "not found") { sfftxtFilename = ""; }\r
+ else if (sfftxtFilename == "not open") { sfftxtFilename = ""; }\r
+ }\r
+ \r
+ if ((sfftxtFilename == "") && (filenames.size() == 0)) { \r
+ //if there is a current sff file, use it\r
+ string filename = m->getSFFFile(); \r
+ if (filename != "") { filenames.push_back(filename); m->mothurOut("Using " + filename + " as input file for the sff parameter."); m->mothurOutEndLine(); }\r
+ else { m->mothurOut("[ERROR]: you must provide a valid sff or sfftxt file."); m->mothurOutEndLine(); abort=true; }\r
+ }\r
+ \r
+ \r
+ }\r
+ }\r
+ catch(exception& e) {\r
+ m->errorOut(e, "SffInfoCommand", "SffInfoCommand");\r
+ exit(1);\r
+ }\r
+}\r
+//**********************************************************************************************************************\r
+int SffInfoCommand::execute(){\r
+ try {\r
+ if (abort == true) { if (calledHelp) { return 0; } return 2; }\r
+ \r
+ for (int s = 0; s < filenames.size(); s++) {\r
+ \r
+ if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; }\r
+ \r
+ int start = time(NULL);\r
+ \r
+ filenames[s] = m->getFullPathName(filenames[s]);\r
+ m->mothurOut("Extracting info from " + filenames[s] + " ..." ); m->mothurOutEndLine();\r
+ \r
+ string accnos = "";\r
+ if (hasAccnos) { accnos = accnosFileNames[s]; }\r
+ \r
+ string oligos = "";\r
+ if (hasOligos) { oligos = oligosFileNames[s]; }\r
+ if (hasGroup) { oligos = groupFileNames[s]; }\r
+ \r
+ int numReads = extractSffInfo(filenames[s], accnos, oligos);\r
+\r
+ m->mothurOut("It took " + toString(time(NULL) - start) + " secs to extract " + toString(numReads) + ".");\r
+ }\r
+ \r
+ if (sfftxtFilename != "") { parseSffTxt(); }\r
+ \r
+ if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; }\r
+ \r
+ //set fasta file as new current fastafile\r
+ string current = "";\r
+ itTypes = outputTypes.find("fasta");\r
+ if (itTypes != outputTypes.end()) {\r
+ if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setFastaFile(current); }\r
+ }\r
+ \r
+ itTypes = outputTypes.find("qfile");\r
+ if (itTypes != outputTypes.end()) {\r
+ if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setQualFile(current); }\r
+ }\r
+ \r
+ itTypes = outputTypes.find("flow");\r
+ if (itTypes != outputTypes.end()) {\r
+ if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setFlowFile(current); }\r
+ }\r
+ \r
+ //report output filenames\r
+ m->mothurOutEndLine();\r
+ m->mothurOut("Output File Names: "); m->mothurOutEndLine();\r
+ for (int i = 0; i < outputNames.size(); i++) { m->mothurOut(outputNames[i]); m->mothurOutEndLine(); }\r
+ m->mothurOutEndLine();\r
+\r
+ return 0;\r
+ }\r
+ catch(exception& e) {\r
+ m->errorOut(e, "SffInfoCommand", "execute");\r
+ exit(1);\r
+ }\r
+}\r
+//**********************************************************************************************************************\r
+int SffInfoCommand::extractSffInfo(string input, string accnos, string oligos){\r
+ try {\r
+ currentFileName = input;\r
+ if (outputDir == "") { outputDir += m->hasPath(input); }\r
+ \r
+ if (accnos != "") { readAccnosFile(accnos); }\r
+ else { seqNames.clear(); }\r
+ \r
+ if (hasOligos) { readOligos(oligos); split = 2; }\r
+ if (hasGroup) { readGroup(oligos); split = 2; }\r
+ \r
+ ofstream outSfftxt, outFasta, outQual, outFlow;\r
+ string outFastaFileName, outQualFileName;\r
+ string rootName = outputDir + m->getRootName(m->getSimpleName(input));\r
+ if(rootName.find_last_of(".") == rootName.npos){ rootName += "."; }\r
+ \r
+ map<string, string> variables; \r
+ variables["[filename]"] = rootName;\r
+ string sfftxtFileName = getOutputFileName("sfftxt",variables);\r
+ string outFlowFileName = getOutputFileName("flow",variables);\r
+ if (!trim) { variables["[tag]"] = "raw"; }\r
+ outFastaFileName = getOutputFileName("fasta",variables);\r
+ outQualFileName = getOutputFileName("qfile",variables);\r
+ \r
+ if (sfftxt) { m->openOutputFile(sfftxtFileName, outSfftxt); outSfftxt.setf(ios::fixed, ios::floatfield); outSfftxt.setf(ios::showpoint); outputNames.push_back(sfftxtFileName); outputTypes["sfftxt"].push_back(sfftxtFileName); }\r
+ if (fasta) { m->openOutputFile(outFastaFileName, outFasta); outputNames.push_back(outFastaFileName); outputTypes["fasta"].push_back(outFastaFileName); }\r
+ if (qual) { m->openOutputFile(outQualFileName, outQual); outputNames.push_back(outQualFileName); outputTypes["qfile"].push_back(outQualFileName); }\r
+ if (flow) { m->openOutputFile(outFlowFileName, outFlow); outputNames.push_back(outFlowFileName); outFlow.setf(ios::fixed, ios::floatfield); outFlow.setf(ios::showpoint); outputTypes["flow"].push_back(outFlowFileName); }\r
+ \r
+ ifstream in;\r
+ m->openInputFileBinary(input, in);\r
+ \r
+ CommonHeader header;\r
+ readCommonHeader(in, header);\r
+ \r
+ int count = 0;\r
+ \r
+ //check magic number and version\r
+ if (header.magicNumber != 779314790) { m->mothurOut("Magic Number is not correct, not a valid .sff file"); m->mothurOutEndLine(); return count; }\r
+ if (header.version != "0001") { m->mothurOut("Version is not supported, only support version 0001."); m->mothurOutEndLine(); return count; }\r
+ \r
+ //print common header\r
+ if (sfftxt) { printCommonHeader(outSfftxt, header); }\r
+ if (flow) { outFlow << header.numFlowsPerRead << endl; }\r
+ \r
+ //read through the sff file\r
+ while (!in.eof()) {\r
+ \r
+ bool print = true;\r
+ \r
+ //read data\r
+ seqRead read; Header readheader;\r
+ readSeqData(in, read, header.numFlowsPerRead, readheader);\r
+ \r
+ bool okay = sanityCheck(readheader, read);\r
+ if (!okay) { break; }\r
+ \r
+ //if you have provided an accosfile and this seq is not in it, then dont print\r
+ if (seqNames.size() != 0) { if (seqNames.count(readheader.name) == 0) { print = false; } }\r
+ \r
+ //print \r
+ if (print) {\r
+ if (sfftxt) { printHeader(outSfftxt, readheader); printSffTxtSeqData(outSfftxt, read, readheader); }\r
+ if (fasta) { printFastaSeqData(outFasta, read, readheader); }\r
+ if (qual) { printQualSeqData(outQual, read, readheader); }\r
+ if (flow) { printFlowSeqData(outFlow, read, readheader); }\r
+ }\r
+ \r
+ count++;\r
+ \r
+ //report progress\r
+ if((count+1) % 10000 == 0){ m->mothurOut(toString(count+1)); m->mothurOutEndLine(); }\r
+ \r
+ if (m->control_pressed) { count = 0; break; }\r
+ \r
+ if (count >= header.numReads) { break; }\r
+ }\r
+ \r
+ //report progress\r
+ if (!m->control_pressed) { if((count) % 10000 != 0){ m->mothurOut(toString(count)); m->mothurOutEndLine(); } }\r
+ \r
+ in.close();\r
+ \r
+ if (sfftxt) { outSfftxt.close(); }\r
+ if (fasta) { outFasta.close(); }\r
+ if (qual) { outQual.close(); }\r
+ if (flow) { outFlow.close(); }\r
+ \r
+ if (split > 1) {\r
+ //create new common headers for each file with the correct number of reads\r
+ adjustCommonHeader(header);\r
+ \r
+ if (hasGroup) { delete groupMap; }\r
+ \r
+ //cout << "here" << endl;\r
+ map<string, string>::iterator it;\r
+ set<string> namesToRemove;\r
+ for(int i=0;i<filehandles.size();i++){\r
+ for(int j=0;j<filehandles[0].size();j++){\r
+ //cout << i << '\t' << '\t' << j << '\t' << filehandles[i][j] << endl;\r
+ if (filehandles[i][j] != "") {\r
+ if (namesToRemove.count(filehandles[i][j]) == 0) {\r
+ if(m->isBlank(filehandles[i][j])){\r
+ //cout << i << '\t' << '\t' << j << '\t' << filehandles[i][j] << " is blank removing" << endl;\r
+ m->mothurRemove(filehandles[i][j]);\r
+ m->mothurRemove(filehandlesHeaders[i][j]);\r
+ namesToRemove.insert(filehandles[i][j]);\r
+ }\r
+ }\r
+ }\r
+ }\r
+ }\r
+ //cout << "here2" << endl;\r
+ //append new header to reads\r
+ for (int i = 0; i < filehandles.size(); i++) {\r
+ for (int j = 0; j < filehandles[i].size(); j++) {\r
+ m->appendBinaryFiles(filehandles[i][j], filehandlesHeaders[i][j]);\r
+ m->renameFile(filehandlesHeaders[i][j], filehandles[i][j]);\r
+ m->mothurRemove(filehandlesHeaders[i][j]);\r
+ //cout << i << '\t' << '\t' << j << '\t' << filehandles[i][j] << " done appending headers and removing " << filehandlesHeaders[i][j] << endl;\r
+ if (numSplitReads[i][j] == 0) { m->mothurRemove(filehandles[i][j]); }\r
+ }\r
+ }\r
+ //cout << "here3" << endl;\r
+ //remove names for outputFileNames, just cleans up the output\r
+ for(int i = 0; i < outputNames.size(); i++) { \r
+ if (namesToRemove.count(outputNames[i]) != 0) {\r
+ //cout << "erasing " << i << '\t' << outputNames[i] << endl;\r
+ outputNames.erase(outputNames.begin()+i);\r
+ i--;\r
+ } \r
+ }\r
+ //cout << "here4" << endl;\r
+ if(m->isBlank(noMatchFile)){ m->mothurRemove(noMatchFile); }\r
+ else { outputNames.push_back(noMatchFile); outputTypes["sff"].push_back(noMatchFile); }\r
+ }\r
+ \r
+ return count;\r
+ }\r
+ catch(exception& e) {\r
+ m->errorOut(e, "SffInfoCommand", "extractSffInfo");\r
+ exit(1);\r
+ }\r
+}\r
+//**********************************************************************************************************************\r
+int SffInfoCommand::readCommonHeader(ifstream& in, CommonHeader& header){\r
+ try {\r
+ \r
+ if (!in.eof()) {\r
+\r
+ //read magic number\r
+ char buffer[4];\r
+ in.read(buffer, 4);\r
+ header.magicNumber = be_int4(*(unsigned int *)(&buffer));\r
+ \r
+ //read version\r
+ char buffer9[4];\r
+ in.read(buffer9, 4);\r
+ header.version = "";\r
+ for (int i = 0; i < 4; i++) { header.version += toString((int)(buffer9[i])); }\r
+ \r
+ //read offset\r
+ char buffer2 [8];\r
+ in.read(buffer2, 8);\r
+ header.indexOffset = be_int8(*(unsigned long long *)(&buffer2));\r
+ \r
+ //read index length\r
+ char buffer3 [4];\r
+ in.read(buffer3, 4);\r
+ header.indexLength = be_int4(*(unsigned int *)(&buffer3));\r
+ \r
+ //read num reads\r
+ char buffer4 [4];\r
+ in.read(buffer4, 4);\r
+ header.numReads = be_int4(*(unsigned int *)(&buffer4));\r
+ \r
+ if (m->debug) { m->mothurOut("[DEBUG]: numReads = " + toString(header.numReads) + "\n"); }\r
+ \r
+ //read header length\r
+ char buffer5 [2];\r
+ in.read(buffer5, 2);\r
+ header.headerLength = be_int2(*(unsigned short *)(&buffer5));\r
+ \r
+ //read key length\r
+ char buffer6 [2];\r
+ in.read(buffer6, 2);\r
+ header.keyLength = be_int2(*(unsigned short *)(&buffer6));\r
+ \r
+ //read number of flow reads\r
+ char buffer7 [2];\r
+ in.read(buffer7, 2);\r
+ header.numFlowsPerRead = be_int2(*(unsigned short *)(&buffer7));\r
+ \r
+ //read format code\r
+ char buffer8 [1];\r
+ in.read(buffer8, 1);\r
+ header.flogramFormatCode = (int)(buffer8[0]);\r
+ \r
+ //read flow chars\r
+ char* tempBuffer = new char[header.numFlowsPerRead];\r
+ in.read(&(*tempBuffer), header.numFlowsPerRead); \r
+ header.flowChars = tempBuffer;\r
+ if (header.flowChars.length() > header.numFlowsPerRead) { header.flowChars = header.flowChars.substr(0, header.numFlowsPerRead); }\r
+ delete[] tempBuffer;\r
+ \r
+ //read key\r
+ char* tempBuffer2 = new char[header.keyLength];\r
+ in.read(&(*tempBuffer2), header.keyLength);\r
+ header.keySequence = tempBuffer2;\r
+ if (header.keySequence.length() > header.keyLength) { header.keySequence = header.keySequence.substr(0, header.keyLength); }\r
+ delete[] tempBuffer2;\r
+ \r
+ /* Pad to 8 chars */\r
+ unsigned long long spotInFile = in.tellg();\r
+ unsigned long long spot = (spotInFile + 7)& ~7; // ~ inverts\r
+ in.seekg(spot);\r
+ \r
+ }else{\r
+ m->mothurOut("Error reading sff common header."); m->mothurOutEndLine();\r
+ }\r
+ \r
+ return 0;\r
+ \r
+ }\r
+ catch(exception& e) {\r
+ m->errorOut(e, "SffInfoCommand", "readCommonHeader");\r
+ exit(1);\r
+ }\r
+}\r
+//**********************************************************************************************************************\r
+int SffInfoCommand::adjustCommonHeader(CommonHeader header){\r
+ try {\r
+ string endian = m->findEdianness();\r
+ char* mybuffer = new char[4];\r
+ ifstream in;\r
+ m->openInputFileBinary(currentFileName, in);\r
+ \r
+ ofstream outNoMatchHeader;\r
+ string tempNoHeader = "tempNoMatchHeader";\r
+ m->openOutputFileBinary(tempNoHeader, outNoMatchHeader);\r
+ \r
+ //magic number\r
+ in.read(mybuffer,4);\r
+ for (int i = 0; i < filehandlesHeaders.size(); i++) { \r
+ for (int j = 0; j < filehandlesHeaders[i].size(); j++) {\r
+ ofstream out;\r
+ m->openOutputFileBinaryAppend(filehandlesHeaders[i][j], out);\r
+ out.write(mybuffer, in.gcount());\r
+ out.close();\r
+ }\r
+ }\r
+ outNoMatchHeader.write(mybuffer, in.gcount());\r
+ delete[] mybuffer;\r
+ \r
+ //version\r
+ mybuffer = new char[4];\r
+ in.read(mybuffer,4);\r
+ for (int i = 0; i < filehandlesHeaders.size(); i++) { \r
+ for (int j = 0; j < filehandlesHeaders[i].size(); j++) {\r
+ ofstream out;\r
+ m->openOutputFileBinaryAppend(filehandlesHeaders[i][j], out);\r
+ out.write(mybuffer, in.gcount());\r
+ out.close();\r
+ }\r
+ }\r
+ outNoMatchHeader.write(mybuffer, in.gcount());\r
+ delete[] mybuffer;\r
+ \r
+ //offset\r
+ mybuffer = new char[8];\r
+ in.read(mybuffer,8);\r
+ unsigned long long offset = 0;\r
+ char* thisbuffer = new char[8];\r
+ thisbuffer[0] = (offset >> 56) & 0xFF;\r
+ thisbuffer[1] = (offset >> 48) & 0xFF;\r
+ thisbuffer[2] = (offset >> 40) & 0xFF;\r
+ thisbuffer[3] = (offset >> 32) & 0xFF;\r
+ thisbuffer[4] = (offset >> 24) & 0xFF;\r
+ thisbuffer[5] = (offset >> 16) & 0xFF;\r
+ thisbuffer[6] = (offset >> 8) & 0xFF;\r
+ thisbuffer[7] = offset & 0xFF;\r
+ for (int i = 0; i < filehandlesHeaders.size(); i++) {\r
+ for (int j = 0; j < filehandlesHeaders[i].size(); j++) {\r
+ ofstream out;\r
+ m->openOutputFileBinaryAppend(filehandlesHeaders[i][j], out);\r
+ out.write(thisbuffer, 8);\r
+ out.close();\r
+ }\r
+ }\r
+ outNoMatchHeader.write(thisbuffer, 8);\r
+ delete[] thisbuffer;\r
+ delete[] mybuffer;\r
+ \r
+ \r
+ //read index length\r
+ mybuffer = new char[4];\r
+ in.read(mybuffer,4);\r
+ offset = 0;\r
+ char* thisbuffer2 = new char[4];\r
+ thisbuffer2[0] = (offset >> 24) & 0xFF;\r
+ thisbuffer2[1] = (offset >> 16) & 0xFF;\r
+ thisbuffer2[2] = (offset >> 8) & 0xFF;\r
+ thisbuffer2[3] = offset & 0xFF;\r
+ for (int i = 0; i < filehandlesHeaders.size(); i++) {\r
+ for (int j = 0; j < filehandlesHeaders[i].size(); j++) {\r
+ ofstream out;\r
+ m->openOutputFileBinaryAppend(filehandlesHeaders[i][j], out);\r
+ out.write(thisbuffer2, 4);\r
+ out.close();\r
+ }\r
+ }\r
+ outNoMatchHeader.write(thisbuffer2, 4);\r
+ delete[] thisbuffer2;\r
+ delete[] mybuffer;\r
+ \r
+ //change num reads\r
+ mybuffer = new char[4];\r
+ in.read(mybuffer,4);\r
+ delete[] mybuffer;\r
+ for (int i = 0; i < filehandlesHeaders.size(); i++) { \r
+ for (int j = 0; j < filehandlesHeaders[i].size(); j++) {\r
+ char* thisbuffer = new char[4];\r
+ if (endian == "BIG_ENDIAN") {\r
+ thisbuffer[0] = (numSplitReads[i][j] >> 24) & 0xFF;\r
+ thisbuffer[1] = (numSplitReads[i][j] >> 16) & 0xFF;\r
+ thisbuffer[2] = (numSplitReads[i][j] >> 8) & 0xFF;\r
+ thisbuffer[3] = numSplitReads[i][j] & 0xFF;\r
+ }else {\r
+ thisbuffer[0] = numSplitReads[i][j] & 0xFF;\r
+ thisbuffer[1] = (numSplitReads[i][j] >> 8) & 0xFF;\r
+ thisbuffer[2] = (numSplitReads[i][j] >> 16) & 0xFF;\r
+ thisbuffer[3] = (numSplitReads[i][j] >> 24) & 0xFF;\r
+ }\r
+ ofstream out;\r
+ m->openOutputFileBinaryAppend(filehandlesHeaders[i][j], out);\r
+ out.write(thisbuffer, 4);\r
+ out.close();\r
+ delete[] thisbuffer;\r
+ }\r
+ }\r
+ char* thisbuffer3 = new char[4];\r
+ if (endian == "BIG_ENDIAN") {\r
+ thisbuffer3[0] = (numNoMatch >> 24) & 0xFF;\r
+ thisbuffer3[1] = (numNoMatch >> 16) & 0xFF;\r
+ thisbuffer3[2] = (numNoMatch >> 8) & 0xFF;\r
+ thisbuffer3[3] = numNoMatch & 0xFF;\r
+ }else {\r
+ thisbuffer3[0] = numNoMatch & 0xFF;\r
+ thisbuffer3[1] = (numNoMatch >> 8) & 0xFF;\r
+ thisbuffer3[2] = (numNoMatch >> 16) & 0xFF;\r
+ thisbuffer3[3] = (numNoMatch >> 24) & 0xFF;\r
+ }\r
+ outNoMatchHeader.write(thisbuffer3, 4);\r
+ delete[] thisbuffer3;\r
+ \r
+ \r
+ //read header length\r
+ mybuffer = new char[2];\r
+ in.read(mybuffer,2);\r
+ for (int i = 0; i < filehandlesHeaders.size(); i++) { \r
+ for (int j = 0; j < filehandlesHeaders[i].size(); j++) {\r
+ ofstream out;\r
+ m->openOutputFileBinaryAppend(filehandlesHeaders[i][j], out);\r
+ out.write(mybuffer, in.gcount());\r
+ out.close();\r
+ }\r
+ }\r
+ outNoMatchHeader.write(mybuffer, in.gcount());\r
+ delete[] mybuffer;\r
+ \r
+ //read key length\r
+ mybuffer = new char[2];\r
+ in.read(mybuffer,2);\r
+ for (int i = 0; i < filehandlesHeaders.size(); i++) { \r
+ for (int j = 0; j < filehandlesHeaders[i].size(); j++) {\r
+ ofstream out;\r
+ m->openOutputFileBinaryAppend(filehandlesHeaders[i][j], out);\r
+ out.write(mybuffer, in.gcount());\r
+ out.close();\r
+ }\r
+ }\r
+ outNoMatchHeader.write(mybuffer, in.gcount());\r
+ delete[] mybuffer;\r
+ \r
+ //read number of flow reads\r
+ mybuffer = new char[2];\r
+ in.read(mybuffer,2);\r
+ for (int i = 0; i < filehandlesHeaders.size(); i++) { \r
+ for (int j = 0; j < filehandlesHeaders[i].size(); j++) {\r
+ ofstream out;\r
+ m->openOutputFileBinaryAppend(filehandlesHeaders[i][j], out);\r
+ out.write(mybuffer, in.gcount());\r
+ out.close();\r
+ }\r
+ }\r
+ outNoMatchHeader.write(mybuffer, in.gcount());\r
+ delete[] mybuffer;\r
+ \r
+ //read format code\r
+ mybuffer = new char[1];\r
+ in.read(mybuffer,1);\r
+ for (int i = 0; i < filehandlesHeaders.size(); i++) { \r
+ for (int j = 0; j < filehandlesHeaders[i].size(); j++) {\r
+ ofstream out;\r
+ m->openOutputFileBinaryAppend(filehandlesHeaders[i][j], out);\r
+ out.write(mybuffer, in.gcount());\r
+ out.close();\r
+ }\r
+ }\r
+ outNoMatchHeader.write(mybuffer, in.gcount());\r
+ delete[] mybuffer;\r
+ \r
+ //read flow chars\r
+ mybuffer = new char[header.numFlowsPerRead];\r
+ in.read(mybuffer,header.numFlowsPerRead);\r
+ for (int i = 0; i < filehandlesHeaders.size(); i++) { \r
+ for (int j = 0; j < filehandlesHeaders[i].size(); j++) {\r
+ ofstream out;\r
+ m->openOutputFileBinaryAppend(filehandlesHeaders[i][j], out);\r
+ out.write(mybuffer, in.gcount());\r
+ out.close();\r
+ }\r
+ }\r
+ outNoMatchHeader.write(mybuffer, in.gcount());\r
+ delete[] mybuffer;\r
+ \r
+ //read key\r
+ mybuffer = new char[header.keyLength];\r
+ in.read(mybuffer,header.keyLength);\r
+ for (int i = 0; i < filehandlesHeaders.size(); i++) { \r
+ for (int j = 0; j < filehandlesHeaders[i].size(); j++) {\r
+ ofstream out;\r
+ m->openOutputFileBinaryAppend(filehandlesHeaders[i][j], out);\r
+ out.write(mybuffer, in.gcount());\r
+ out.close();\r
+ }\r
+ }\r
+ outNoMatchHeader.write(mybuffer, in.gcount());\r
+ delete[] mybuffer;\r
+ \r
+ \r
+ /* Pad to 8 chars */\r
+ unsigned long long spotInFile = in.tellg();\r
+ unsigned long long spot = (spotInFile + 7)& ~7; // ~ inverts\r
+ in.seekg(spot);\r
+ \r
+ mybuffer = new char[spot-spotInFile];\r
+ for (int i = 0; i < filehandlesHeaders.size(); i++) { \r
+ for (int j = 0; j < filehandlesHeaders[i].size(); j++) {\r
+ ofstream out;\r
+ m->openOutputFileBinaryAppend(filehandlesHeaders[i][j], out);\r
+ out.write(mybuffer, spot-spotInFile);\r
+ out.close();\r
+ }\r
+ }\r
+ outNoMatchHeader.write(mybuffer, spot-spotInFile);\r
+ outNoMatchHeader.close();\r
+ delete[] mybuffer;\r
+ in.close();\r
+ \r
+ m->appendBinaryFiles(noMatchFile, tempNoHeader);\r
+ m->renameFile(tempNoHeader, noMatchFile);\r
+ m->mothurRemove(tempNoHeader);\r
+ \r
+ return 0;\r
+ \r
+ }\r
+ catch(exception& e) {\r
+ m->errorOut(e, "SffInfoCommand", "adjustCommonHeader");\r
+ exit(1);\r
+ }\r
+}\r
+//**********************************************************************************************************************\r
+bool SffInfoCommand::readSeqData(ifstream& in, seqRead& read, int numFlowReads, Header& header){\r
+ try {\r
+ unsigned long long startSpotInFile = in.tellg();\r
+ if (!in.eof()) {\r
+ \r
+ /*****************************************/\r
+ //read header\r
+ \r
+ //read header length\r
+ char buffer [2];\r
+ in.read(buffer, 2); \r
+ header.headerLength = be_int2(*(unsigned short *)(&buffer));\r
+ \r
+ //read name length\r
+ char buffer2 [2];\r
+ in.read(buffer2, 2);\r
+ header.nameLength = be_int2(*(unsigned short *)(&buffer2));\r
+ \r
+ //read num bases\r
+ char buffer3 [4];\r
+ in.read(buffer3, 4);\r
+ header.numBases = be_int4(*(unsigned int *)(&buffer3));\r
+ \r
+ \r
+ //read clip qual left\r
+ char buffer4 [2];\r
+ in.read(buffer4, 2);\r
+ header.clipQualLeft = be_int2(*(unsigned short *)(&buffer4));\r
+ header.clipQualLeft = 5;\r
+ \r
+ \r
+ //read clip qual right\r
+ char buffer5 [2];\r
+ in.read(buffer5, 2);\r
+ header.clipQualRight = be_int2(*(unsigned short *)(&buffer5));\r
+ \r
+ \r
+ //read clipAdapterLeft\r
+ char buffer6 [2];\r
+ in.read(buffer6, 2);\r
+ header.clipAdapterLeft = be_int2(*(unsigned short *)(&buffer6));\r
+ \r
+ \r
+ //read clipAdapterRight\r
+ char buffer7 [2];\r
+ in.read(buffer7, 2);\r
+ header.clipAdapterRight = be_int2(*(unsigned short *)(&buffer7));\r
+ \r
+ \r
+ //read name\r
+ char* tempBuffer = new char[header.nameLength];\r
+ in.read(&(*tempBuffer), header.nameLength);\r
+ header.name = tempBuffer;\r
+ if (header.name.length() > header.nameLength) { header.name = header.name.substr(0, header.nameLength); }\r
+ \r
+ delete[] tempBuffer;\r
+ \r
+ //extract info from name\r
+ decodeName(header.timestamp, header.region, header.xy, header.name);\r
+ \r
+ /* Pad to 8 chars */\r
+ unsigned long long spotInFile = in.tellg();\r
+ unsigned long long spot = (spotInFile + 7)& ~7;\r
+ in.seekg(spot);\r
+\r
+ /*****************************************/\r
+ //sequence read \r
+ \r
+ //read flowgram\r
+ read.flowgram.resize(numFlowReads);\r
+ for (int i = 0; i < numFlowReads; i++) { \r
+ char buffer [2];\r
+ in.read(buffer, 2);\r
+ read.flowgram[i] = be_int2(*(unsigned short *)(&buffer));\r
+ }\r
+ \r
+ //read flowIndex\r
+ read.flowIndex.resize(header.numBases);\r
+ for (int i = 0; i < header.numBases; i++) { \r
+ char temp[1];\r
+ in.read(temp, 1);\r
+ read.flowIndex[i] = be_int1(*(unsigned char *)(&temp));\r
+ }\r
+ \r
+ //read bases\r
+ char* tempBuffer6 = new char[header.numBases];\r
+ in.read(&(*tempBuffer6), header.numBases);\r
+ read.bases = tempBuffer6;\r
+ if (read.bases.length() > header.numBases) { read.bases = read.bases.substr(0, header.numBases); }\r
+ delete[] tempBuffer6;\r
+\r
+ //read qual scores\r
+ read.qualScores.resize(header.numBases);\r
+ for (int i = 0; i < header.numBases; i++) { \r
+ char temp[1];\r
+ in.read(temp, 1);\r
+ read.qualScores[i] = be_int1(*(unsigned char *)(&temp));\r
+ }\r
+ \r
+ /* Pad to 8 chars */\r
+ spotInFile = in.tellg();\r
+ spot = (spotInFile + 7)& ~7;\r
+ in.seekg(spot);\r
+ \r
+ if (split > 1) { \r
+ \r
+ int barcodeIndex, primerIndex, trashCodeLength;\r
+ \r
+ if (hasOligos) { trashCodeLength = findGroup(header, read, barcodeIndex, primerIndex); }\r
+ else if (hasGroup) { trashCodeLength = findGroup(header, read, barcodeIndex, primerIndex, "groupMode"); }\r
+ else { m->mothurOut("[ERROR]: uh oh, we shouldn't be here...\n"); }\r
+\r
+ char * mybuffer;\r
+ mybuffer = new char [spot-startSpotInFile];\r
+ \r
+ ifstream in2;\r
+ m->openInputFileBinary(currentFileName, in2);\r
+ in2.seekg(startSpotInFile);\r
+ in2.read(mybuffer,spot-startSpotInFile);\r
+ \r
+ \r
+ if(trashCodeLength == 0){\r
+ ofstream out;\r
+ m->openOutputFileBinaryAppend(filehandles[barcodeIndex][primerIndex], out);\r
+ out.write(mybuffer, in2.gcount());\r
+ out.close();\r
+ numSplitReads[barcodeIndex][primerIndex]++;\r
+ }\r
+ else{\r
+ ofstream out;\r
+ m->openOutputFileBinaryAppend(noMatchFile, out);\r
+ out.write(mybuffer, in2.gcount());\r
+ out.close();\r
+ numNoMatch++;\r
+ }\r
+ delete[] mybuffer;\r
+ in2.close();\r
+ } \r
+ \r
+ }else{\r
+ m->mothurOut("Error reading."); m->mothurOutEndLine();\r
+ }\r
+ \r
+ if (in.eof()) { return true; }\r
+ \r
+ return false;\r
+ }\r
+ catch(exception& e) {\r
+ m->errorOut(e, "SffInfoCommand", "readSeqData");\r
+ exit(1);\r
+ }\r
+}\r
+//**********************************************************************************************************************\r
+int SffInfoCommand::findGroup(Header header, seqRead read, int& barcode, int& primer) {\r
+ try {\r
+ //find group read belongs to\r
+ TrimOligos trimOligos(pdiffs, bdiffs, ldiffs, sdiffs, primers, barcodes, revPrimer, linker, spacer);\r
+ \r
+ int success = 1;\r
+ string trashCode = "";\r
+ int currentSeqsDiffs = 0;\r
+ \r
+ string seq = read.bases;\r
+ \r
+ if (trim) {\r
+ if(header.clipQualRight < header.clipQualLeft){\r
+ if (header.clipQualRight == 0) { //don't trim right\r
+ seq = seq.substr(header.clipQualLeft-1);\r
+ }else {\r
+ seq = "NNNN";\r
+ }\r
+ }\r
+ else if((header.clipQualRight != 0) && ((header.clipQualRight-header.clipQualLeft) >= 0)){\r
+ seq = seq.substr((header.clipQualLeft-1), (header.clipQualRight-header.clipQualLeft));\r
+ }\r
+ else {\r
+ seq = seq.substr(header.clipQualLeft-1);\r
+ }\r
+ }else{\r
+ //if you wanted the sfftxt then you already converted the bases to the right case\r
+ if (!sfftxt) {\r
+ int endValue = header.clipQualRight;\r
+ //make the bases you want to clip lowercase and the bases you want to keep upper case\r
+ if(endValue == 0){ endValue = seq.length(); }\r
+ for (int i = 0; i < (header.clipQualLeft-1); i++) { seq[i] = tolower(seq[i]); }\r
+ for (int i = (header.clipQualLeft-1); i < (endValue-1); i++) { seq[i] = toupper(seq[i]); }\r
+ for (int i = (endValue-1); i < seq.length(); i++) { seq[i] = tolower(seq[i]); }\r
+ }\r
+ }\r
+ \r
+ Sequence currSeq(header.name, seq);\r
+ QualityScores currQual;\r
+ \r
+ if(numLinkers != 0){\r
+ success = trimOligos.stripLinker(currSeq, currQual);\r
+ if(success > ldiffs) { trashCode += 'k'; }\r
+ else{ currentSeqsDiffs += success; }\r
+ \r
+ }\r
+ \r
+ if(barcodes.size() != 0){\r
+ success = trimOligos.stripBarcode(currSeq, currQual, barcode);\r
+ if(success > bdiffs) { trashCode += 'b'; }\r
+ else{ currentSeqsDiffs += success; }\r
+ }\r
+ \r
+ if(numSpacers != 0){\r
+ success = trimOligos.stripSpacer(currSeq, currQual);\r
+ if(success > sdiffs) { trashCode += 's'; }\r
+ else{ currentSeqsDiffs += success; }\r
+ \r
+ }\r
+ \r
+ if(numFPrimers != 0){\r
+ success = trimOligos.stripForward(currSeq, currQual, primer, true);\r
+ if(success > pdiffs) { trashCode += 'f'; }\r
+ else{ currentSeqsDiffs += success; }\r
+ }\r
+ \r
+ if (currentSeqsDiffs > tdiffs) { trashCode += 't'; }\r
+ \r
+ if(revPrimer.size() != 0){\r
+ success = trimOligos.stripReverse(currSeq, currQual);\r
+ if(!success) { trashCode += 'r'; }\r
+ }\r
+\r
+ \r
+ return trashCode.length();\r
+ }\r
+ catch(exception& e) {\r
+ m->errorOut(e, "SffInfoCommand", "findGroup");\r
+ exit(1);\r
+ }\r
+}\r
+//**********************************************************************************************************************\r
+int SffInfoCommand::findGroup(Header header, seqRead read, int& barcode, int& primer, string groupMode) {\r
+ try {\r
+ string trashCode = "";\r
+ primer = 0;\r
+ \r
+ string group = groupMap->getGroup(header.name);\r
+ if (group == "not found") { trashCode += "g"; } //scrap for group\r
+ else { //find file group\r
+ map<string, int>::iterator it = barcodes.find(group);\r
+ if (it != barcodes.end()) {\r
+ barcode = it->second;\r
+ }else { trashCode += "g"; }\r
+ }\r
+ \r
+ return trashCode.length();\r
+ }\r
+ catch(exception& e) {\r
+ m->errorOut(e, "SffInfoCommand", "findGroup");\r
+ exit(1);\r
+ }\r
+}\r
+//**********************************************************************************************************************\r
+int SffInfoCommand::decodeName(string& timestamp, string& region, string& xy, string name) {\r
+ try {\r
+ \r
+ if (name.length() >= 6) {\r
+ string time = name.substr(0, 6);\r
+ unsigned int timeNum = m->fromBase36(time);\r
+ \r
+ int q1 = timeNum / 60;\r
+ int sec = timeNum - 60 * q1;\r
+ int q2 = q1 / 60;\r
+ int minute = q1 - 60 * q2;\r
+ int q3 = q2 / 24;\r
+ int hr = q2 - 24 * q3;\r
+ int q4 = q3 / 32;\r
+ int day = q3 - 32 * q4;\r
+ int q5 = q4 / 13;\r
+ int mon = q4 - 13 * q5;\r
+ int year = 2000 + q5;\r
+ \r
+ timestamp = toString(year) + "_" + toString(mon) + "_" + toString(day) + "_" + toString(hr) + "_" + toString(minute) + "_" + toString(sec);\r
+ }\r
+ \r
+ if (name.length() >= 9) {\r
+ region = name.substr(7, 2);\r
+ \r
+ string xyNum = name.substr(9);\r
+ unsigned int myXy = m->fromBase36(xyNum);\r
+ int x = myXy >> 12;\r
+ int y = myXy & 4095;\r
+ \r
+ xy = toString(x) + "_" + toString(y);\r
+ }\r
+ \r
+ return 0;\r
+ }\r
+ catch(exception& e) {\r
+ m->errorOut(e, "SffInfoCommand", "decodeName");\r
+ exit(1);\r
+ }\r
+}\r
+//**********************************************************************************************************************\r
+int SffInfoCommand::printCommonHeader(ofstream& out, CommonHeader& header) {\r
+ try {\r
+ \r
+ out << "Common Header:\nMagic Number: " << header.magicNumber << endl;\r
+ out << "Version: " << header.version << endl;\r
+ out << "Index Offset: " << header.indexOffset << endl;\r
+ out << "Index Length: " << header.indexLength << endl;\r
+ out << "Number of Reads: " << header.numReads << endl;\r
+ out << "Header Length: " << header.headerLength << endl;\r
+ out << "Key Length: " << header.keyLength << endl;\r
+ out << "Number of Flows: " << header.numFlowsPerRead << endl;\r
+ out << "Format Code: " << header.flogramFormatCode << endl;\r
+ out << "Flow Chars: " << header.flowChars << endl;\r
+ out << "Key Sequence: " << header.keySequence << endl << endl;\r
+ \r
+ return 0;\r
+ }\r
+ catch(exception& e) {\r
+ m->errorOut(e, "SffInfoCommand", "printCommonHeader");\r
+ exit(1);\r
+ }\r
+}\r
+//**********************************************************************************************************************\r
+int SffInfoCommand::printHeader(ofstream& out, Header& header) {\r
+ try {\r
+ \r
+ out << ">" << header.name << endl;\r
+ out << "Run Prefix: " << header.timestamp << endl;\r
+ out << "Region #: " << header.region << endl;\r
+ out << "XY Location: " << header.xy << endl << endl;\r
+ \r
+ out << "Run Name: " << endl;\r
+ out << "Analysis Name: " << endl;\r
+ out << "Full Path: " << endl << endl;\r
+ \r
+ out << "Read Header Len: " << header.headerLength << endl;\r
+ out << "Name Length: " << header.nameLength << endl;\r
+ out << "# of Bases: " << header.numBases << endl;\r
+ out << "Clip Qual Left: " << header.clipQualLeft << endl;\r
+ out << "Clip Qual Right: " << header.clipQualRight << endl;\r
+ out << "Clip Adap Left: " << header.clipAdapterLeft << endl;\r
+ out << "Clip Adap Right: " << header.clipAdapterRight << endl << endl;\r
+ \r
+ return 0;\r
+ }\r
+ catch(exception& e) {\r
+ m->errorOut(e, "SffInfoCommand", "printHeader");\r
+ exit(1);\r
+ }\r
+}\r
+//**********************************************************************************************************************\r
+bool SffInfoCommand::sanityCheck(Header& header, seqRead& read) {\r
+ try {\r
+ bool okay = true;\r
+ string message = "[WARNING]: Your sff file may be corrupted! Sequence: " + header.name + "\n";\r
+ \r
+ if (header.clipQualLeft > read.bases.length()) {\r
+ okay = false; message += "Clip Qual Left = " + toString(header.clipQualLeft) + ", but we only read " + toString(read.bases.length()) + " bases.\n";\r
+ }\r
+ if (header.clipQualRight > read.bases.length()) {\r
+ okay = false; message += "Clip Qual Right = " + toString(header.clipQualRight) + ", but we only read " + toString(read.bases.length()) + " bases.\n";\r
+ }\r
+ if (header.clipQualLeft > read.qualScores.size()) {\r
+ okay = false; message += "Clip Qual Left = " + toString(header.clipQualLeft) + ", but we only read " + toString(read.qualScores.size()) + " quality scores.\n";\r
+ }\r
+ if (header.clipQualRight > read.qualScores.size()) {\r
+ okay = false; message += "Clip Qual Right = " + toString(header.clipQualRight) + ", but we only read " + toString(read.qualScores.size()) + " quality scores.\n";\r
+ }\r
+ \r
+ if (okay == false) {\r
+ m->mothurOut(message); m->mothurOutEndLine();\r
+ }\r
+ \r
+ return okay;\r
+ }\r
+ catch(exception& e) {\r
+ m->errorOut(e, "SffInfoCommand", "sanityCheck");\r
+ exit(1);\r
+ }\r
+}\r
+//**********************************************************************************************************************\r
+int SffInfoCommand::printSffTxtSeqData(ofstream& out, seqRead& read, Header& header) {\r
+ try {\r
+ out << "Flowgram: ";\r
+ for (int i = 0; i < read.flowgram.size(); i++) { out << setprecision(2) << (read.flowgram[i]/(float)100) << '\t'; }\r
+ \r
+ out << endl << "Flow Indexes: ";\r
+ int sum = 0;\r
+ for (int i = 0; i < read.flowIndex.size(); i++) { sum += read.flowIndex[i]; out << sum << '\t'; }\r
+ \r
+ //make the bases you want to clip lowercase and the bases you want to keep upper case\r
+ int endValue = header.clipQualRight;\r
+ if(endValue == 0){ endValue = read.bases.length(); }\r
+ for (int i = 0; i < (header.clipQualLeft-1); i++) { read.bases[i] = tolower(read.bases[i]); }\r
+ for (int i = (header.clipQualLeft-1); i < (endValue-1); i++) { read.bases[i] = toupper(read.bases[i]); }\r
+ for (int i = (endValue-1); i < read.bases.length(); i++) { read.bases[i] = tolower(read.bases[i]); }\r
+ \r
+ out << endl << "Bases: " << read.bases << endl << "Quality Scores: ";\r
+ for (int i = 0; i < read.qualScores.size(); i++) { out << read.qualScores[i] << '\t'; }\r
+ \r
+ \r
+ out << endl << endl;\r
+ \r
+ return 0;\r
+ }\r
+ catch(exception& e) {\r
+ m->errorOut(e, "SffInfoCommand", "printSffTxtSeqData");\r
+ exit(1);\r
+ }\r
+}\r
+//**********************************************************************************************************************\r
+int SffInfoCommand::printFastaSeqData(ofstream& out, seqRead& read, Header& header) {\r
+ try {\r
+ string seq = read.bases;\r
+ \r
+ if (trim) {\r
+ if(header.clipQualRight < header.clipQualLeft){\r
+ if (header.clipQualRight == 0) { //don't trim right\r
+ seq = seq.substr(header.clipQualLeft-1);\r
+ }else {\r
+ seq = "NNNN";\r
+ }\r
+ }\r
+ else if((header.clipQualRight != 0) && ((header.clipQualRight-header.clipQualLeft) >= 0)){\r
+ seq = seq.substr((header.clipQualLeft-1), (header.clipQualRight-header.clipQualLeft));\r
+ }\r
+ else {\r
+ seq = seq.substr(header.clipQualLeft-1);\r
+ }\r
+ }else{\r
+ //if you wanted the sfftxt then you already converted the bases to the right case\r
+ if (!sfftxt) {\r
+ int endValue = header.clipQualRight;\r
+ //make the bases you want to clip lowercase and the bases you want to keep upper case\r
+ if(endValue == 0){ endValue = seq.length(); }\r
+ for (int i = 0; i < (header.clipQualLeft-1); i++) { seq[i] = tolower(seq[i]); }\r
+ for (int i = (header.clipQualLeft-1); i < (endValue-1); i++) { seq[i] = toupper(seq[i]); }\r
+ for (int i = (endValue-1); i < seq.length(); i++) { seq[i] = tolower(seq[i]); }\r
+ }\r
+ }\r
+ \r
+ out << ">" << header.name << " xy=" << header.xy << endl;\r
+ out << seq << endl;\r
+ \r
+ return 0;\r
+ }\r
+ catch(exception& e) {\r
+ m->errorOut(e, "SffInfoCommand", "printFastaSeqData");\r
+ exit(1);\r
+ }\r
+}\r
+\r
+//**********************************************************************************************************************\r
+int SffInfoCommand::printQualSeqData(ofstream& out, seqRead& read, Header& header) {\r
+ try {\r
+ \r
+ if (trim) {\r
+ if(header.clipQualRight < header.clipQualLeft){\r
+ if (header.clipQualRight == 0) { //don't trim right\r
+ out << ">" << header.name << " xy=" << header.xy << " length=" << (read.qualScores.size()-header.clipQualLeft) << endl;\r
+ for (int i = (header.clipQualLeft-1); i < read.qualScores.size(); i++) { out << read.qualScores[i] << '\t'; } \r
+ }else {\r
+ out << ">" << header.name << " xy=" << header.xy << endl;\r
+ out << "0\t0\t0\t0";\r
+ }\r
+ }\r
+ else if((header.clipQualRight != 0) && ((header.clipQualRight-header.clipQualLeft) >= 0)){\r
+ out << ">" << header.name << " xy=" << header.xy << " length=" << (header.clipQualRight-header.clipQualLeft) << endl;\r
+ for (int i = (header.clipQualLeft-1); i < (header.clipQualRight-1); i++) { out << read.qualScores[i] << '\t'; }\r
+ }\r
+ else{\r
+ out << ">" << header.name << " xy=" << header.xy << " length=" << (header.clipQualRight-header.clipQualLeft) << endl;\r
+ for (int i = (header.clipQualLeft-1); i < read.qualScores.size(); i++) { out << read.qualScores[i] << '\t'; } \r
+ }\r
+ }else{\r
+ out << ">" << header.name << " xy=" << header.xy << " length=" << read.qualScores.size() << endl;\r
+ for (int i = 0; i < read.qualScores.size(); i++) { out << read.qualScores[i] << '\t'; }\r
+ }\r
+ \r
+ out << endl;\r
+ \r
+ return 0;\r
+ }\r
+ catch(exception& e) {\r
+ m->errorOut(e, "SffInfoCommand", "printQualSeqData");\r
+ exit(1);\r
+ }\r
+}\r
+\r
+//**********************************************************************************************************************\r
+int SffInfoCommand::printFlowSeqData(ofstream& out, seqRead& read, Header& header) {\r
+ try {\r
+ \r
+ int endValue = header.clipQualRight;\r
+ if (header.clipQualRight == 0) {\r
+ endValue = read.flowIndex.size();\r
+ if (m->debug) { m->mothurOut("[DEBUG]: " + header.name + " has clipQualRight=0.\n"); }\r
+ }\r
+ if(endValue > header.clipQualLeft){\r
+ \r
+ int rightIndex = 0;\r
+ for (int i = 0; i < endValue; i++) { rightIndex += read.flowIndex[i]; }\r
+ \r
+ out << header.name << ' ' << rightIndex;\r
+ for (int i = 0; i < read.flowgram.size(); i++) { out << setprecision(2) << ' ' << (read.flowgram[i]/(float)100); }\r
+ out << endl;\r
+ }\r
+ \r
+ \r
+ return 0;\r
+ }\r
+ catch(exception& e) {\r
+ m->errorOut(e, "SffInfoCommand", "printFlowSeqData");\r
+ exit(1);\r
+ }\r
+}\r
+//**********************************************************************************************************************\r
+int SffInfoCommand::readAccnosFile(string filename) {\r
+ try {\r
+ //remove old names\r
+ seqNames.clear();\r
+ \r
+ ifstream in;\r
+ m->openInputFile(filename, in);\r
+ string name;\r
+ \r
+ while(!in.eof()){\r
+ in >> name; m->gobble(in);\r
+ \r
+ seqNames.insert(name);\r
+ \r
+ if (m->control_pressed) { seqNames.clear(); break; }\r
+ }\r
+ in.close(); \r
+ \r
+ return 0;\r
+ }\r
+ catch(exception& e) {\r
+ m->errorOut(e, "SffInfoCommand", "readAccnosFile");\r
+ exit(1);\r
+ }\r
+}\r
+//**********************************************************************************************************************\r
+int SffInfoCommand::parseSffTxt() {\r
+ try {\r
+ \r
+ ifstream inSFF;\r
+ m->openInputFile(sfftxtFilename, inSFF);\r
+ \r
+ if (outputDir == "") { outputDir += m->hasPath(sfftxtFilename); }\r
+ \r
+ //output file names\r
+ ofstream outFasta, outQual, outFlow;\r
+ string outFastaFileName, outQualFileName;\r
+ string fileRoot = m->getRootName(m->getSimpleName(sfftxtFilename));\r
+ if (fileRoot.length() > 0) {\r
+ //rip off last .\r
+ fileRoot = fileRoot.substr(0, fileRoot.length()-1);\r
+ fileRoot = m->getRootName(fileRoot);\r
+ }\r
+ \r
+ map<string, string> variables; \r
+ variables["[filename]"] = fileRoot;\r
+ string sfftxtFileName = getOutputFileName("sfftxt",variables);\r
+ string outFlowFileName = getOutputFileName("flow",variables);\r
+ if (!trim) { variables["[tag]"] = "raw"; }\r
+ outFastaFileName = getOutputFileName("fasta",variables);\r
+ outQualFileName = getOutputFileName("qfile",variables);\r
+ \r
+ if (fasta) { m->openOutputFile(outFastaFileName, outFasta); outputNames.push_back(outFastaFileName); outputTypes["fasta"].push_back(outFastaFileName); }\r
+ if (qual) { m->openOutputFile(outQualFileName, outQual); outputNames.push_back(outQualFileName); outputTypes["qfile"].push_back(outQualFileName); }\r
+ if (flow) { m->openOutputFile(outFlowFileName, outFlow); outputNames.push_back(outFlowFileName); outFlow.setf(ios::fixed, ios::floatfield); outFlow.setf(ios::showpoint); outputTypes["flow"].push_back(outFlowFileName); }\r
+ \r
+ //read common header\r
+ string commonHeader = m->getline(inSFF);\r
+ string magicNumber = m->getline(inSFF); \r
+ string version = m->getline(inSFF);\r
+ string indexOffset = m->getline(inSFF);\r
+ string indexLength = m->getline(inSFF);\r
+ int numReads = parseHeaderLineToInt(inSFF);\r
+ string headerLength = m->getline(inSFF);\r
+ string keyLength = m->getline(inSFF);\r
+ int numFlows = parseHeaderLineToInt(inSFF);\r
+ string flowgramCode = m->getline(inSFF);\r
+ string flowChars = m->getline(inSFF);\r
+ string keySequence = m->getline(inSFF);\r
+ m->gobble(inSFF);\r
+ \r
+ string seqName;\r
+ \r
+ if (flow) { outFlow << numFlows << endl; }\r
+ \r
+ for(int i=0;i<numReads;i++){\r
+ \r
+ //sanity check\r
+ if (inSFF.eof()) { m->mothurOut("[ERROR]: Expected " + toString(numReads) + " but reached end of file at " + toString(i+1) + "."); m->mothurOutEndLine(); break; }\r
+ \r
+ Header header;\r
+ \r
+ //parse read header\r
+ inSFF >> seqName;\r
+ seqName = seqName.substr(1);\r
+ m->gobble(inSFF);\r
+ header.name = seqName;\r
+ \r
+ string runPrefix = parseHeaderLineToString(inSFF); header.timestamp = runPrefix;\r
+ string regionNumber = parseHeaderLineToString(inSFF); header.region = regionNumber;\r
+ string xyLocation = parseHeaderLineToString(inSFF); header.xy = xyLocation;\r
+ m->gobble(inSFF);\r
+ \r
+ string runName = parseHeaderLineToString(inSFF);\r
+ string analysisName = parseHeaderLineToString(inSFF);\r
+ string fullPath = parseHeaderLineToString(inSFF);\r
+ m->gobble(inSFF);\r
+ \r
+ string readHeaderLen = parseHeaderLineToString(inSFF); convert(readHeaderLen, header.headerLength);\r
+ string nameLength = parseHeaderLineToString(inSFF); convert(nameLength, header.nameLength);\r
+ int numBases = parseHeaderLineToInt(inSFF); header.numBases = numBases;\r
+ string clipQualLeft = parseHeaderLineToString(inSFF); convert(clipQualLeft, header.clipQualLeft);\r
+ int clipQualRight = parseHeaderLineToInt(inSFF); header.clipQualRight = clipQualRight;\r
+ string clipAdapLeft = parseHeaderLineToString(inSFF); convert(clipAdapLeft, header.clipAdapterLeft);\r
+ string clipAdapRight = parseHeaderLineToString(inSFF); convert(clipAdapRight, header.clipAdapterRight);\r
+ m->gobble(inSFF);\r
+ \r
+ seqRead read;\r
+ \r
+ //parse read\r
+ vector<unsigned short> flowVector = parseHeaderLineToFloatVector(inSFF, numFlows); read.flowgram = flowVector;\r
+ vector<unsigned int> flowIndices = parseHeaderLineToIntVector(inSFF, numBases); \r
+ \r
+ //adjust for print\r
+ vector<unsigned int> flowIndicesAdjusted; flowIndicesAdjusted.push_back(flowIndices[0]);\r
+ for (int j = 1; j < flowIndices.size(); j++) { flowIndicesAdjusted.push_back(flowIndices[j] - flowIndices[j-1]); }\r
+ read.flowIndex = flowIndicesAdjusted;\r
+ \r
+ string bases = parseHeaderLineToString(inSFF); read.bases = bases;\r
+ vector<unsigned int> qualityScores = parseHeaderLineToIntVector(inSFF, numBases); read.qualScores = qualityScores;\r
+ m->gobble(inSFF);\r
+ \r
+ //if you have provided an accosfile and this seq is not in it, then dont print\r
+ bool print = true;\r
+ if (seqNames.size() != 0) { if (seqNames.count(header.name) == 0) { print = false; } }\r
+ \r
+ //print \r
+ if (print) {\r
+ if (fasta) { printFastaSeqData(outFasta, read, header); }\r
+ if (qual) { printQualSeqData(outQual, read, header); }\r
+ if (flow) { printFlowSeqData(outFlow, read, header); }\r
+ }\r
+ \r
+ //report progress\r
+ if((i+1) % 10000 == 0){ m->mothurOut(toString(i+1)); m->mothurOutEndLine(); }\r
+ \r
+ if (m->control_pressed) { break; }\r
+ }\r
+ \r
+ //report progress\r
+ if (!m->control_pressed) { if((numReads) % 10000 != 0){ m->mothurOut(toString(numReads)); m->mothurOutEndLine(); } }\r
+ \r
+ inSFF.close();\r
+ \r
+ if (fasta) { outFasta.close(); }\r
+ if (qual) { outQual.close(); }\r
+ if (flow) { outFlow.close(); }\r
+ \r
+ return 0;\r
+ }\r
+ catch(exception& e) {\r
+ m->errorOut(e, "SffInfoCommand", "parseSffTxt");\r
+ exit(1);\r
+ }\r
+}\r
+//**********************************************************************************************************************\r
+\r
+int SffInfoCommand::parseHeaderLineToInt(ifstream& file){\r
+ try {\r
+ int number;\r
+ \r
+ while (!file.eof()) {\r
+ \r
+ char c = file.get(); \r
+ if (c == ':'){\r
+ file >> number;\r
+ break;\r
+ }\r
+ \r
+ }\r
+ m->gobble(file);\r
+ return number;\r
+ }\r
+ catch(exception& e) {\r
+ m->errorOut(e, "SffInfoCommand", "parseHeaderLineToInt");\r
+ exit(1);\r
+ }\r
+ \r
+}\r
+\r
+//**********************************************************************************************************************\r
+\r
+string SffInfoCommand::parseHeaderLineToString(ifstream& file){\r
+ try {\r
+ string text;\r
+ \r
+ while (!file.eof()) {\r
+ char c = file.get(); \r
+ \r
+ if (c == ':'){\r
+ //m->gobble(file);\r
+ //text = m->getline(file); \r
+ file >> text;\r
+ break;\r
+ }\r
+ }\r
+ m->gobble(file);\r
+ \r
+ return text;\r
+ }\r
+ catch(exception& e) {\r
+ m->errorOut(e, "SffInfoCommand", "parseHeaderLineToString");\r
+ exit(1);\r
+ }\r
+}\r
+\r
+//**********************************************************************************************************************\r
+\r
+vector<unsigned short> SffInfoCommand::parseHeaderLineToFloatVector(ifstream& file, int length){\r
+ try {\r
+ vector<unsigned short> floatVector(length);\r
+ \r
+ while (!file.eof()) {\r
+ char c = file.get(); \r
+ if (c == ':'){\r
+ float temp;\r
+ for(int i=0;i<length;i++){\r
+ file >> temp;\r
+ floatVector[i] = temp * 100;\r
+ }\r
+ break;\r
+ }\r
+ }\r
+ m->gobble(file); \r
+ return floatVector;\r
+ }\r
+ catch(exception& e) {\r
+ m->errorOut(e, "SffInfoCommand", "parseHeaderLineToFloatVector");\r
+ exit(1);\r
+ }\r
+}\r
+\r
+//**********************************************************************************************************************\r
+\r
+vector<unsigned int> SffInfoCommand::parseHeaderLineToIntVector(ifstream& file, int length){\r
+ try {\r
+ vector<unsigned int> intVector(length);\r
+ \r
+ while (!file.eof()) {\r
+ char c = file.get(); \r
+ if (c == ':'){\r
+ for(int i=0;i<length;i++){\r
+ file >> intVector[i];\r
+ }\r
+ break;\r
+ }\r
+ }\r
+ m->gobble(file); \r
+ return intVector;\r
+ }\r
+ catch(exception& e) {\r
+ m->errorOut(e, "SffInfoCommand", "parseHeaderLineToIntVector");\r
+ exit(1);\r
+ }\r
+}\r
+//***************************************************************************************************************\r
+\r
+bool SffInfoCommand::readOligos(string oligoFile){\r
+ try {\r
+ filehandles.clear();\r
+ numSplitReads.clear();\r
+ filehandlesHeaders.clear();\r
+ \r
+ ifstream inOligos;\r
+ m->openInputFile(oligoFile, inOligos);\r
+ \r
+ string type, oligo, group;\r
+ \r
+ int indexPrimer = 0;\r
+ int indexBarcode = 0;\r
+ \r
+ while(!inOligos.eof()){\r
+ \r
+ inOligos >> type;\r
+ \r
+ if(type[0] == '#'){\r
+ while (!inOligos.eof()) { char c = inOligos.get(); if (c == 10 || c == 13){ break; } } // get rest of line if there's any crap there\r
+ m->gobble(inOligos);\r
+ }\r
+ else{\r
+ m->gobble(inOligos);\r
+ //make type case insensitive\r
+ for(int i=0;i<type.length();i++){ type[i] = toupper(type[i]); }\r
+ \r
+ inOligos >> oligo;\r
+ \r
+ for(int i=0;i<oligo.length();i++){\r
+ oligo[i] = toupper(oligo[i]);\r
+ if(oligo[i] == 'U') { oligo[i] = 'T'; }\r
+ }\r
+ \r
+ if(type == "FORWARD"){\r
+ group = "";\r
+ \r
+ // get rest of line in case there is a primer name\r
+ while (!inOligos.eof()) {\r
+ char c = inOligos.get();\r
+ if (c == 10 || c == 13 || c == -1){ break; }\r
+ else if (c == 32 || c == 9){;} //space or tab\r
+ else { group += c; }\r
+ }\r
+ \r
+ //check for repeat barcodes\r
+ map<string, int>::iterator itPrime = primers.find(oligo);\r
+ if (itPrime != primers.end()) { m->mothurOut("primer " + oligo + " is in your oligos file already."); m->mothurOutEndLine(); }\r
+ \r
+ primers[oligo]=indexPrimer; indexPrimer++;\r
+ primerNameVector.push_back(group);\r
+ \r
+ }else if(type == "REVERSE"){\r
+ //Sequence oligoRC("reverse", oligo);\r
+ //oligoRC.reverseComplement();\r
+ string oligoRC = reverseOligo(oligo);\r
+ revPrimer.push_back(oligoRC);\r
+ }\r
+ else if(type == "BARCODE"){\r
+ inOligos >> group;\r
+ \r
+ \r
+ //check for repeat barcodes\r
+ map<string, int>::iterator itBar = barcodes.find(oligo);\r
+ if (itBar != barcodes.end()) { m->mothurOut("barcode " + oligo + " is in your oligos file already."); m->mothurOutEndLine(); }\r
+ \r
+ barcodes[oligo]=indexBarcode; indexBarcode++;\r
+ barcodeNameVector.push_back(group);\r
+ }else if(type == "LINKER"){\r
+ linker.push_back(oligo);\r
+ }else if(type == "SPACER"){\r
+ spacer.push_back(oligo);\r
+ }\r
+ else{ m->mothurOut("[WARNING]: " + type + " is not recognized as a valid type. Choices are forward, reverse, and barcode. Ignoring " + oligo + "."); m->mothurOutEndLine(); }\r
+ }\r
+ m->gobble(inOligos);\r
+ }\r
+ inOligos.close();\r
+ \r
+ if(barcodeNameVector.size() == 0 && primerNameVector[0] == ""){ split = 1; }\r
+ \r
+ //add in potential combos\r
+ if(barcodeNameVector.size() == 0){\r
+ barcodes[""] = 0;\r
+ barcodeNameVector.push_back("");\r
+ }\r
+ \r
+ if(primerNameVector.size() == 0){\r
+ primers[""] = 0;\r
+ primerNameVector.push_back("");\r
+ }\r
+ \r
+ filehandles.resize(barcodeNameVector.size());\r
+ for(int i=0;i<filehandles.size();i++){\r
+ filehandles[i].assign(primerNameVector.size(), "");\r
+ }\r
+ \r
+ if(split > 1){\r
+ set<string> uniqueNames; //used to cleanup outputFileNames\r
+ for(map<string, int>::iterator itBar = barcodes.begin();itBar != barcodes.end();itBar++){\r
+ for(map<string, int>::iterator itPrimer = primers.begin();itPrimer != primers.end(); itPrimer++){\r
+ \r
+ string primerName = primerNameVector[itPrimer->second];\r
+ string barcodeName = barcodeNameVector[itBar->second];\r
+ \r
+ string comboGroupName = "";\r
+ string fastaFileName = "";\r
+ string qualFileName = "";\r
+ string nameFileName = "";\r
+ \r
+ if(primerName == ""){\r
+ comboGroupName = barcodeNameVector[itBar->second];\r
+ }\r
+ else{\r
+ if(barcodeName == ""){\r
+ comboGroupName = primerNameVector[itPrimer->second];\r
+ }\r
+ else{\r
+ comboGroupName = barcodeNameVector[itBar->second] + "." + primerNameVector[itPrimer->second];\r
+ }\r
+ }\r
+ \r
+ ofstream temp;\r
+ map<string, string> variables;\r
+ variables["[filename]"] = outputDir + m->getRootName(m->getSimpleName(currentFileName));\r
+ variables["[group]"] = comboGroupName;\r
+ string thisFilename = getOutputFileName("sff",variables);\r
+ if (uniqueNames.count(thisFilename) == 0) {\r
+ outputNames.push_back(thisFilename);\r
+ outputTypes["sff"].push_back(thisFilename);\r
+ uniqueNames.insert(thisFilename);\r
+ }\r
+ \r
+ filehandles[itBar->second][itPrimer->second] = thisFilename;\r
+ temp.open(thisFilename.c_str(), ios::binary); temp.close();\r
+ }\r
+ }\r
+ }\r
+ numFPrimers = primers.size();\r
+ numLinkers = linker.size();\r
+ numSpacers = spacer.size();\r
+ map<string, string> variables;\r
+ variables["[filename]"] = outputDir + m->getRootName(m->getSimpleName(currentFileName));\r
+ variables["[group]"] = "scrap";\r
+ noMatchFile = getOutputFileName("sff",variables);\r
+ m->mothurRemove(noMatchFile);\r
+ numNoMatch = 0;\r
+ \r
+ \r
+ bool allBlank = true;\r
+ for (int i = 0; i < barcodeNameVector.size(); i++) {\r
+ if (barcodeNameVector[i] != "") {\r
+ allBlank = false;\r
+ break;\r
+ }\r
+ }\r
+ for (int i = 0; i < primerNameVector.size(); i++) {\r
+ if (primerNameVector[i] != "") {\r
+ allBlank = false;\r
+ break;\r
+ }\r
+ }\r
+ \r
+ filehandlesHeaders.resize(filehandles.size());\r
+ numSplitReads.resize(filehandles.size());\r
+ for (int i = 0; i < filehandles.size(); i++) {\r
+ numSplitReads[i].resize(filehandles[i].size(), 0);\r
+ for (int j = 0; j < filehandles[i].size(); j++) {\r
+ filehandlesHeaders[i].push_back(filehandles[i][j]+"headers");\r
+ }\r
+ }\r
+ \r
+ if (allBlank) {\r
+ m->mothurOut("[WARNING]: your oligos file does not contain any group names. mothur will not create a split the sff file."); m->mothurOutEndLine();\r
+ split = 1;\r
+ return false;\r
+ }\r
+ \r
+ return true;\r
+ \r
+ }\r
+ catch(exception& e) {\r
+ m->errorOut(e, "SffInfoCommand", "readOligos");\r
+ exit(1);\r
+ }\r
+}\r
+//***************************************************************************************************************\r
+\r
+bool SffInfoCommand::readGroup(string oligoFile){\r
+ try {\r
+ filehandles.clear();\r
+ numSplitReads.clear();\r
+ filehandlesHeaders.clear();\r
+ barcodes.clear();\r
+ \r
+ groupMap = new GroupMap();\r
+ groupMap->readMap(oligoFile);\r
+ \r
+ //like barcodeNameVector - no primer names\r
+ vector<string> groups = groupMap->getNamesOfGroups();\r
+ \r
+ filehandles.resize(groups.size());\r
+ for (int i = 0; i < filehandles.size(); i++) {\r
+ for (int j = 0; j < 1; j++) {\r
+ \r
+ map<string, string> variables;\r
+ variables["[filename]"] = outputDir + m->getRootName(m->getSimpleName(currentFileName));\r
+ variables["[group]"] = groups[i];\r
+ string thisFilename = getOutputFileName("sff",variables);\r
+ outputNames.push_back(thisFilename);\r
+ outputTypes["sff"].push_back(thisFilename);\r
+ \r
+ ofstream temp;\r
+ m->openOutputFileBinary(thisFilename, temp); temp.close();\r
+ filehandles[i].push_back(thisFilename);\r
+ barcodes[groups[i]] = i;\r
+ }\r
+ }\r
+ \r
+ map<string, string> variables;\r
+ variables["[filename]"] = outputDir + m->getRootName(m->getSimpleName(currentFileName));\r
+ variables["[group]"] = "scrap";\r
+ noMatchFile = getOutputFileName("sff",variables);\r
+ m->mothurRemove(noMatchFile);\r
+ numNoMatch = 0;\r
+ \r
+ \r
+ filehandlesHeaders.resize(groups.size());\r
+ numSplitReads.resize(filehandles.size());\r
+ for (int i = 0; i < filehandles.size(); i++) {\r
+ numSplitReads[i].resize(filehandles[i].size(), 0);\r
+ for (int j = 0; j < filehandles[i].size(); j++) {\r
+ ofstream temp ;\r
+ string thisHeader = filehandles[i][j]+"headers";\r
+ m->openOutputFileBinary(thisHeader, temp); temp.close();\r
+ filehandlesHeaders[i].push_back(thisHeader);\r
+ }\r
+ }\r
+ \r
+ return true;\r
+ \r
+ }\r
+ catch(exception& e) {\r
+ m->errorOut(e, "SffInfoCommand", "readGroup");\r
+ exit(1);\r
+ }\r
+}\r
+\r
+//********************************************************************/\r
+string SffInfoCommand::reverseOligo(string oligo){\r
+ try {\r
+ string reverse = "";\r
+ \r
+ for(int i=oligo.length()-1;i>=0;i--){\r
+ \r
+ if(oligo[i] == 'A') { reverse += 'T'; }\r
+ else if(oligo[i] == 'T'){ reverse += 'A'; }\r
+ else if(oligo[i] == 'U'){ reverse += 'A'; }\r
+ \r
+ else if(oligo[i] == 'G'){ reverse += 'C'; }\r
+ else if(oligo[i] == 'C'){ reverse += 'G'; }\r
+ \r
+ else if(oligo[i] == 'R'){ reverse += 'Y'; }\r
+ else if(oligo[i] == 'Y'){ reverse += 'R'; }\r
+ \r
+ else if(oligo[i] == 'M'){ reverse += 'K'; }\r
+ else if(oligo[i] == 'K'){ reverse += 'M'; }\r
+ \r
+ else if(oligo[i] == 'W'){ reverse += 'W'; }\r
+ else if(oligo[i] == 'S'){ reverse += 'S'; }\r
+ \r
+ else if(oligo[i] == 'B'){ reverse += 'V'; }\r
+ else if(oligo[i] == 'V'){ reverse += 'B'; }\r
+ \r
+ else if(oligo[i] == 'D'){ reverse += 'H'; }\r
+ else if(oligo[i] == 'H'){ reverse += 'D'; }\r
+ \r
+ else { reverse += 'N'; }\r
+ }\r
+ \r
+ \r
+ return reverse;\r
+ }\r
+ catch(exception& e) {\r
+ m->errorOut(e, "SffInfoCommand", "reverseOligo");\r
+ exit(1);\r
+ }\r
+}\r
+\r
+//**********************************************************************************************************************\r
+\r
+\r
+ \r
+ \r
projects / mothur.git / blobdiff