-/*\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
-\r
-//**********************************************************************************************************************\r
-\r
-SffInfoCommand::SffInfoCommand(string option) {\r
- try {\r
- abort = false;\r
- hasAccnos = false;\r
- \r
- //allow user to run help\r
- if(option == "help") { help(); abort = true; }\r
- \r
- else {\r
- //valid paramters for this command\r
- string Array[] = {"sff","qfile","fasta","flow","trim","accnos","sfftxt","outputdir","inputdir", "outputdir"};\r
- vector<string> myArray (Array, Array+(sizeof(Array)/sizeof(string)));\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
- //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") { m->mothurOut("sff is a required parameter for the sffinfo command."); m->mothurOutEndLine(); abort = true; }\r
- else { \r
- 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
- if (inputDir != "") {\r
- string path = 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 = 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() + getSimpleName(filenames[i]);\r
- m->mothurOut("Unable to open " + filenames[i] + ". Trying default " + tryPath); m->mothurOutEndLine();\r
- ableToOpen = openInputFile(tryPath, in, "noerror");\r
- filenames[i] = tryPath;\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
- }\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
- 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
- if (inputDir != "") {\r
- string path = 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 = 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() + getSimpleName(accnosFileNames[i]);\r
- m->mothurOut("Unable to open " + accnosFileNames[i] + ". Trying default " + tryPath); m->mothurOutEndLine();\r
- ableToOpen = openInputFile(tryPath, in, "noerror");\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
- //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
- 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 = isTrue(temp); \r
- \r
- temp = validParameter.validFile(parameters, "fasta", false); if (temp == "not found"){ temp = "T"; }\r
- fasta = isTrue(temp); \r
- \r
- temp = validParameter.validFile(parameters, "flow", false); if (temp == "not found"){ temp = "F"; }\r
- flow = isTrue(temp); \r
- \r
- temp = validParameter.validFile(parameters, "trim", false); if (temp == "not found"){ temp = "T"; }\r
- trim = isTrue(temp); \r
- \r
- temp = validParameter.validFile(parameters, "sfftxt", false); if (temp == "not found"){ temp = "F"; }\r
- sfftxt = isTrue(temp); \r
- }\r
- }\r
- catch(exception& e) {\r
- m->errorOut(e, "SffInfoCommand", "SffInfoCommand");\r
- exit(1);\r
- }\r
-}\r
-//**********************************************************************************************************************\r
-\r
-void SffInfoCommand::help(){\r
- try {\r
- m->mothurOut("The sffinfo command reads a sff file and extracts the sequence data.\n");\r
- m->mothurOut("The sffinfo command parameters are sff, fasta, qfile, accnos, flow, sfftxt, and trim. sff is required. \n");\r
- 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");\r
- m->mothurOut("The fasta parameter allows you to indicate if you would like a fasta formatted file generated. Default=True. \n");\r
- m->mothurOut("The qfile parameter allows you to indicate if you would like a quality file generated. Default=True. \n");\r
- m->mothurOut("The flow parameter allows you to indicate if you would like a flowgram file generated. Default=False. \n");\r
- m->mothurOut("The sfftxt parameter allows you to indicate if you would like a sff.txt file generated. Default=False. \n");\r
- 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");\r
- 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");\r
- m->mothurOut("Example sffinfo(sff=mySffFile.sff, trim=F).\n");\r
- m->mothurOut("Note: No spaces between parameter labels (i.e. sff), '=' and parameters (i.e.yourSffFileName).\n\n");\r
- }\r
- catch(exception& e) {\r
- m->errorOut(e, "SffInfoCommand", "help");\r
- exit(1);\r
- }\r
-}\r
-//**********************************************************************************************************************\r
-\r
-SffInfoCommand::~SffInfoCommand(){}\r
-\r
-//**********************************************************************************************************************\r
-int SffInfoCommand::execute(){\r
- try {\r
- \r
- if (abort == true) { return 0; }\r
- \r
- for (int s = 0; s < filenames.size(); s++) {\r
- \r
- if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; }\r
- \r
- int start = time(NULL);\r
- \r
- m->mothurOut("Extracting info from " + filenames[s] + " ..." ); m->mothurOutEndLine();\r
- \r
- string accnos = "";\r
- if (hasAccnos) { accnos = accnosFileNames[s]; }\r
- \r
- int numReads = extractSffInfo(filenames[s], accnos);\r
-\r
- m->mothurOut("It took " + toString(time(NULL) - start) + " secs to extract " + toString(numReads) + ".");\r
- }\r
- \r
- if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; }\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){\r
- try {\r
- \r
- if (outputDir == "") { outputDir += hasPath(input); }\r
- \r
- if (accnos != "") { readAccnosFile(accnos); }\r
- else { seqNames.clear(); }\r
-\r
- ofstream outSfftxt, outFasta, outQual, outFlow;\r
- string outFastaFileName, outQualFileName;\r
- string sfftxtFileName = outputDir + getRootName(getSimpleName(input)) + "sff.txt";\r
- string outFlowFileName = outputDir + getRootName(getSimpleName(input)) + "flow";\r
- if (trim) {\r
- outFastaFileName = outputDir + getRootName(getSimpleName(input)) + "fasta";\r
- outQualFileName = outputDir + getRootName(getSimpleName(input)) + "qual";\r
- }else{\r
- outFastaFileName = outputDir + getRootName(getSimpleName(input)) + "raw.fasta";\r
- outQualFileName = outputDir + getRootName(getSimpleName(input)) + "raw.qual";\r
- }\r
- \r
- if (sfftxt) { openOutputFile(sfftxtFileName, outSfftxt); outSfftxt.setf(ios::fixed, ios::floatfield); outSfftxt.setf(ios::showpoint); outputNames.push_back(sfftxtFileName); }\r
- if (fasta) { openOutputFile(outFastaFileName, outFasta); outputNames.push_back(outFastaFileName); }\r
- if (qual) { openOutputFile(outQualFileName, outQual); outputNames.push_back(outQualFileName); }\r
- if (flow) { openOutputFile(outFlowFileName, outFlow); outputNames.push_back(outFlowFileName); }\r
- \r
- ifstream in;\r
- in.open(input.c_str(), ios::binary);\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
- \r
- //read through the sff file\r
- while (!in.eof()) {\r
- \r
- bool print = true;\r
- \r
- //read header\r
- Header readheader;\r
- readHeader(in, readheader);\r
- \r
- //read data\r
- seqRead read; \r
- readSeqData(in, read, header.numFlowsPerRead, readheader.numBases);\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
- 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 int *)(&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
- //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 int spotInFile = in.tellg();\r
- unsigned long int 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
- catch(exception& e) {\r
- m->errorOut(e, "SffInfoCommand", "readCommonHeader");\r
- exit(1);\r
- }\r
-}\r
-//**********************************************************************************************************************\r
-int SffInfoCommand::readHeader(ifstream& in, Header& header){\r
- try {\r
- \r
- if (!in.eof()) {\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
- //read clip qual left\r
- char buffer4 [2];\r
- in.read(buffer4, 2);\r
- header.clipQualLeft = be_int2(*(unsigned short *)(&buffer4));\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
- //read clipAdapterLeft\r
- char buffer6 [2];\r
- in.read(buffer6, 2);\r
- header.clipAdapterLeft = be_int2(*(unsigned short *)(&buffer6));\r
-\r
- //read clipAdapterRight\r
- char buffer7 [2];\r
- in.read(buffer7, 2);\r
- header.clipAdapterRight = be_int2(*(unsigned short *)(&buffer7));\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
- delete[] tempBuffer;\r
- \r
- /* Pad to 8 chars */\r
- unsigned long int spotInFile = in.tellg();\r
- unsigned long int spot = (spotInFile + 7)& ~7;\r
- in.seekg(spot);\r
- \r
- }else{\r
- m->mothurOut("Error reading sff header info."); m->mothurOutEndLine();\r
- }\r
-\r
- return 0;\r
- }\r
- catch(exception& e) {\r
- m->errorOut(e, "SffInfoCommand", "readHeader");\r
- exit(1);\r
- }\r
-}\r
-//**********************************************************************************************************************\r
-int SffInfoCommand::readSeqData(ifstream& in, seqRead& read, int numFlowReads, int numBases){\r
- try {\r
- \r
- if (!in.eof()) {\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(numBases);\r
- for (int i = 0; i < 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* tempBuffer = new char[numBases];\r
- in.read(&(*tempBuffer), numBases);\r
- read.bases = tempBuffer;\r
- if (read.bases.length() > numBases) { read.bases = read.bases.substr(0, numBases); }\r
- delete[] tempBuffer;\r
-\r
- //read qual scores\r
- read.qualScores.resize(numBases);\r
- for (int i = 0; i < 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
- unsigned long int spotInFile = in.tellg();\r
- unsigned long int spot = (spotInFile + 7)& ~7;\r
- in.seekg(spot);\r
- \r
- }else{\r
- m->mothurOut("Error reading."); m->mothurOutEndLine();\r
- }\r
-\r
- return 0;\r
- }\r
- catch(exception& e) {\r
- m->errorOut(e, "SffInfoCommand", "readSeqData");\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: " << endl;\r
- out << "Region #: " << endl;\r
- out << "XY Location: " << 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
-//**********************************************************************************************************************\r
-int SffInfoCommand::printSffTxtSeqData(ofstream& out, seqRead& read, Header& header) {\r
- try {\r
- \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
- for (int i = 0; i < header.clipQualLeft; i++) { read.bases[i] = tolower(read.bases[i]); }\r
- for (int i = header.clipQualLeft; i < (header.clipQualRight-header.clipQualLeft); i++) { read.bases[i] = toupper(read.bases[i]); }\r
- for (int i = (header.clipQualRight-header.clipQualLeft); 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
- \r
- string seq = read.bases;\r
- \r
- \r
- if (trim) {\r
- seq = seq.substr(header.clipQualLeft, (header.clipQualRight-header.clipQualLeft));\r
- }else{\r
- //if you wanted the sfftxt then you already converted the bases to the right case\r
- if (!sfftxt) {\r
- //make the bases you want to clip lowercase and the bases you want to keep upper case\r
- for (int i = 0; i < header.clipQualLeft; i++) { seq[i] = tolower(seq[i]); }\r
- for (int i = header.clipQualLeft; i < (header.clipQualRight-header.clipQualLeft); i++) { seq[i] = toupper(seq[i]); }\r
- for (int i = (header.clipQualRight-header.clipQualLeft); i < seq.length(); i++) { seq[i] = tolower(seq[i]); }\r
- }\r
- }\r
- \r
- out << ">" << header.name << 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
- out << ">" << header.name << " length=" << (header.clipQualRight-header.clipQualLeft) << endl;\r
- for (int i = header.clipQualLeft; i < (header.clipQualRight-header.clipQualLeft); i++) { out << read.qualScores[i] << '\t'; }\r
- }else{\r
- out << ">" << header.name << " 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
- out << ">" << header.name << endl;\r
- for (int i = 0; i < read.flowgram.size(); i++) { out << setprecision(2) << (read.flowgram[i]/(float)100) << '\t'; }\r
- out << endl;\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
- openInputFile(filename, in);\r
- string name;\r
- \r
- while(!in.eof()){\r
- in >> name; 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
+/*
+ * sffinfocommand.cpp
+ * Mothur
+ *
+ * Created by westcott on 7/7/10.
+ * Copyright 2010 Schloss Lab. All rights reserved.
+ *
+ */
+
+#include "sffinfocommand.h"
+#include "endiannessmacros.h"
+
+//**********************************************************************************************************************
+vector<string> SffInfoCommand::getValidParameters(){
+ try {
+ string Array[] = {"sff","qfile","fasta","flow","trim","accnos","sfftxt","outputdir","inputdir", "outputdir"};
+ vector<string> myArray (Array, Array+(sizeof(Array)/sizeof(string)));
+ return myArray;
+ }
+ catch(exception& e) {
+ m->errorOut(e, "SffInfoCommand", "getValidParameters");
+ exit(1);
+ }
+}
+//**********************************************************************************************************************
+SffInfoCommand::SffInfoCommand(){
+ try {
+ abort = true;
+ //initialize outputTypes
+ vector<string> tempOutNames;
+ outputTypes["fasta"] = tempOutNames;
+ outputTypes["flow"] = tempOutNames;
+ outputTypes["sfftxt"] = tempOutNames;
+ outputTypes["qual"] = tempOutNames;
+ }
+ catch(exception& e) {
+ m->errorOut(e, "SffInfoCommand", "SffInfoCommand");
+ exit(1);
+ }
+}
+//**********************************************************************************************************************
+vector<string> SffInfoCommand::getRequiredParameters(){
+ try {
+ string Array[] = {"sff"};
+ vector<string> myArray (Array, Array+(sizeof(Array)/sizeof(string)));
+ return myArray;
+ }
+ catch(exception& e) {
+ m->errorOut(e, "SffInfoCommand", "getRequiredParameters");
+ exit(1);
+ }
+}
+//**********************************************************************************************************************
+vector<string> SffInfoCommand::getRequiredFiles(){
+ try {
+ vector<string> myArray;
+ return myArray;
+ }
+ catch(exception& e) {
+ m->errorOut(e, "SffInfoCommand", "getRequiredFiles");
+ exit(1);
+ }
+}
+//**********************************************************************************************************************
+
+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; }
+ }
+
+ //initialize outputTypes
+ vector<string> tempOutNames;
+ outputTypes["fasta"] = tempOutNames;
+ outputTypes["flow"] = tempOutNames;
+ outputTypes["sfftxt"] = tempOutNames;
+ outputTypes["qual"] = tempOutNames;
+
+ //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 {
+ m->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 = m->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 = m->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() + m->getSimpleName(filenames[i]);
+ m->mothurOut("Unable to open " + filenames[i] + ". Trying default " + tryPath); m->mothurOutEndLine();
+ ifstream in2;
+ ableToOpen = m->openInputFile(tryPath, in2, "noerror");
+ in2.close();
+ filenames[i] = tryPath;
+ }
+ }
+
+ //if you can't open it, try default location
+ if (ableToOpen == 1) {
+ if (m->getOutputDir() != "") { //default path is set
+ string tryPath = m->getOutputDir() + m->getSimpleName(filenames[i]);
+ m->mothurOut("Unable to open " + filenames[i] + ". Trying output directory " + tryPath); m->mothurOutEndLine();
+ ifstream in2;
+ ableToOpen = m->openInputFile(tryPath, in2, "noerror");
+ in2.close();
+ 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;
+ m->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 = m->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 = m->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() + m->getSimpleName(accnosFileNames[i]);
+ m->mothurOut("Unable to open " + accnosFileNames[i] + ". Trying default " + tryPath); m->mothurOutEndLine();
+ ifstream in2;
+ ableToOpen = m->openInputFile(tryPath, in2, "noerror");
+ in2.close();
+ accnosFileNames[i] = tryPath;
+ }
+ }
+ //if you can't open it, try default location
+ if (ableToOpen == 1) {
+ if (m->getOutputDir() != "") { //default path is set
+ string tryPath = m->getOutputDir() + m->getSimpleName(accnosFileNames[i]);
+ m->mothurOut("Unable to open " + accnosFileNames[i] + ". Trying output directory " + tryPath); m->mothurOutEndLine();
+ ifstream in2;
+ ableToOpen = m->openInputFile(tryPath, in2, "noerror");
+ in2.close();
+ 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 = m->isTrue(temp);
+
+ temp = validParameter.validFile(parameters, "fasta", false); if (temp == "not found"){ temp = "T"; }
+ fasta = m->isTrue(temp);
+
+ temp = validParameter.validFile(parameters, "flow", false); if (temp == "not found"){ temp = "F"; }
+ flow = m->isTrue(temp);
+
+ temp = validParameter.validFile(parameters, "trim", false); if (temp == "not found"){ temp = "T"; }
+ trim = m->isTrue(temp);
+
+ temp = validParameter.validFile(parameters, "sfftxt", false); if (temp == "not found"){ temp = "F"; }
+ sfftxt = m->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 += m->hasPath(input); }
+
+ if (accnos != "") { readAccnosFile(accnos); }
+ else { seqNames.clear(); }
+
+ ofstream outSfftxt, outFasta, outQual, outFlow;
+ string outFastaFileName, outQualFileName;
+ string sfftxtFileName = outputDir + m->getRootName(m->getSimpleName(input)) + "sff.txt";
+ string outFlowFileName = outputDir + m->getRootName(m->getSimpleName(input)) + "flow";
+ if (trim) {
+ outFastaFileName = outputDir + m->getRootName(m->getSimpleName(input)) + "fasta";
+ outQualFileName = outputDir + m->getRootName(m->getSimpleName(input)) + "qual";
+ }else{
+ outFastaFileName = outputDir + m->getRootName(m->getSimpleName(input)) + "raw.fasta";
+ outQualFileName = outputDir + m->getRootName(m->getSimpleName(input)) + "raw.qual";
+ }
+
+ 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); }
+ if (fasta) { m->openOutputFile(outFastaFileName, outFasta); outputNames.push_back(outFastaFileName); outputTypes["fasta"].push_back(outFastaFileName); }
+ if (qual) { m->openOutputFile(outQualFileName, outQual); outputNames.push_back(outQualFileName); outputTypes["qual"].push_back(outQualFileName); }
+ if (flow) { m->openOutputFile(outFlowFileName, outFlow); outputNames.push_back(outFlowFileName); outputTypes["flow"].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));
+ header.clipQualLeft = 5;
+
+ //read clip qual right
+ char buffer5 [2];
+ in.read(buffer5, 2);
+ header.clipQualRight = be_int2(*(unsigned short *)(&buffer5));
+
+ //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
+ if(header.clipQualRight == 0){ header.clipQualRight = read.bases.length(); }
+ 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) {
+ if(header.clipQualRight < header.clipQualLeft){
+ seq = "NNNN";
+ }
+ else if((header.clipQualRight != 0) && ((header.clipQualRight-header.clipQualLeft) >= 0)){
+ seq = seq.substr((header.clipQualLeft-1), (header.clipQualRight-header.clipQualLeft));
+ }
+ else {
+ seq = seq.substr(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
+ if(header.clipQualRight == 0){ header.clipQualRight = seq.length(); }
+ 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) {
+ if(header.clipQualRight < header.clipQualLeft){
+ out << "0\t0\t0\t0";
+ }
+ else if((header.clipQualRight != 0) && ((header.clipQualRight-header.clipQualLeft) >= 0)){
+ out << ">" << header.name << " length=" << (header.clipQualRight-header.clipQualLeft) << endl;
+ for (int i = (header.clipQualLeft-1); i < (header.clipQualRight-1); i++) { out << read.qualScores[i] << '\t'; }
+ }
+ else{
+ out << ">" << header.name << " length=" << (header.clipQualRight-header.clipQualLeft) << endl;
+ for (int i = (header.clipQualLeft-1); i < read.qualScores.size(); 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;
+ m->openInputFile(filename, in);
+ string name;
+
+ while(!in.eof()){
+ in >> name; m->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);
+ }
+}
+//**********************************************************************************************************************/