-/*
- * 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;
-
- //allow user to run help
- if(option == "help") { help(); abort = true; }
-
- else {
- //valid paramters for this command
- string Array[] = {"sff","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);
- in.close();
-
- if (ableToOpen == 1) {
- m->mothurOut(filenames[i] + " 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; }
- }
- }
- }
- catch(exception& e) {
- m->errorOut(e, "SffInfoCommand", "SffInfoCommand");
- exit(1);
- }
-}
-//**********************************************************************************************************************
-
-void SffInfoCommand::help(){
- try {
- m->mothurOut("The sffinfo command reads a sff file and outputs a .sff.txt file.\n");
-
- m->mothurOut("Example sffinfo(sff=...).\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; }
-
- m->mothurOut("Extracting info from " + filenames[s] + " ..." ); m->mothurOutEndLine();
-
- if (outputDir == "") { outputDir += hasPath(filenames[s]); }
- string outputFileName = outputDir + getRootName(getSimpleName(filenames[s])) + "sff.txt";
-
- extractSffInfo(filenames[s], outputFileName);
-
- outputNames.push_back(outputFileName);
-
- m->mothurOut("Done."); m->mothurOutEndLine();
- }
-
- 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 output){
- try {
- ofstream out;
- openOutputFile(output, out);
-
- ifstream in;
- in.open(input.c_str(), ios::binary);
-
- CommonHeader* header = new CommonHeader();
- readCommonHeader(in, header);
-
- cout << strlen(header->flowChars) << endl;
- //cout << "magic = " << header->magicNumber << endl << "version = " << header->version << endl << "index offset = " << header->indexOffset << endl << "index length = "<< header->indexLength << endl << "numreads = " << header->numReads << endl << "header length = " << header->headerLength << endl << "key length = " << header->keyLength << endl;
-//cout << "numflowreads = "<< header->numFlowsPerRead << endl << "flow format code = "<< header->flogramFormatCode << endl << "flow chars = " << header->flowChars << endl << "key sequence = " << header->keySequence << endl << endl;
- cout << in.tellg() << endl;
- //read through the sff file
- while (!in.eof()) {
- //print common header
- printCommonHeader(out, header, true);
-
- //read header
- Header* readheader = new Header();
- readHeader(in, readheader);
-
- cout << in.tellg() << endl;
-
- //print header
- printHeader(out, readheader, true);
-
- //read data
- seqRead* read = new seqRead();
- readSeqData(in, read, header->numFlowsPerRead, readheader->numBases);
-
- cout << in.tellg() << endl;
-
- //print data
- printSeqData(out, read, true);
-
- }
-
-
- in.close();
- out.close();
-
- return 0;
- }
- 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 = new char(sizeof(header->magicNumber));
- in.read(buffer, sizeof(header->magicNumber));
- header->magicNumber = be_int4(*(unsigned int *)(buffer));
- delete[] buffer;
- //cout << "here " << header->magicNumber << '\t' << in.tellg() << endl;
- //read version
- header->version = new char(4);
- in.read(header->version, 4);
- string tempBuf0 = header->version; //this is in here because the read sometimes tacks on extra chars, not sure why?
- if (tempBuf0.length() > 4) { tempBuf0 = tempBuf0.substr(0, 4); strcpy(header->version, tempBuf0.c_str()); }
- //memcpy(header->version, buffer+4, 4);
- //cout << "here " << header->version << '\t' << in.tellg() << endl;
- //read offset
- buffer = new char(sizeof(header->indexOffset));
- in.read(buffer, sizeof(header->indexOffset));
- header->indexOffset = be_int8(*(unsigned long int *)(buffer));
- delete[] buffer;
- //cout << "here " << header->indexOffset << '\t' << in.tellg() << endl;
- //read index length
- buffer = new char(sizeof(header->indexLength));
- in.read(buffer, sizeof(header->indexLength));
- header->indexLength = be_int4(*(unsigned int *)(buffer));
- delete[] buffer;
- //cout << "here " << header->indexLength << '\t' << in.tellg() << endl;
- //read num reads
- buffer = new char(sizeof(header->numReads));
- in.read(buffer, sizeof(header->numReads));
- header->numReads = be_int4(*(unsigned int *)(buffer));
- delete[] buffer;
- //cout << "here " << header->numReads << '\t' << in.tellg() << endl;
- //read header length
- buffer = new char(sizeof(header->headerLength));
- in.read(buffer, sizeof(header->headerLength));
- header->headerLength = be_int2(*(unsigned short *)(buffer));
- delete[] buffer;
- //cout << "here " << header->headerLength << '\t' << in.tellg() << endl;
- //read key length
- buffer = new char(sizeof(header->keyLength));
- in.read(buffer, sizeof(header->keyLength));
- header->keyLength = be_int2(*(unsigned short *)(buffer));
- delete[] buffer;
-
-//cout << "here " << header->keyLength << '\t' << in.tellg() << endl;
- //read number of flow reads
- buffer = new char(sizeof(header->numFlowsPerRead));
- in.read(buffer, sizeof(header->numFlowsPerRead));
- header->numFlowsPerRead = be_int2(*(unsigned short *)(buffer));
- delete[] buffer;
- //cout << "here " << header->numFlowsPerRead << '\t' << in.tellg() << endl;
- //read format code
- buffer = new char(sizeof(header->flogramFormatCode));
- in.read(buffer, sizeof(header->flogramFormatCode));
- header->flogramFormatCode = be_int1(*(char *)(buffer));
- delete[] buffer;
- //cout << "here " << header->flogramFormatCode << '\t' << in.tellg() << endl;
-
- //read flow chars
- //header->numFlowsPerRead = 800;
- header->flowChars = new char(header->numFlowsPerRead);
- buffer = new char(header->numFlowsPerRead);
- //cout << "here" << endl;
- //in.read(header->flowChars, header->numFlowsPerRead);
- in.read(buffer, header->numFlowsPerRead);
- memcpy(header->flowChars, buffer, header->numFlowsPerRead);
- delete[] buffer;
- //cout << "here" << endl;
- //string tempBuf1 = header->flowChars;
- //cout << "here " << in.tellg() << endl;
- //if (tempBuf1.length() > header->numFlowsPerRead) { tempBuf1 = tempBuf1.substr(0, header->numFlowsPerRead); strcpy(header->flowChars, tempBuf1.c_str()); }
-
- // cout << "here " << header->flowChars << '\t' << in.tellg() << endl;
- //read key
- //header->keyLength = 4;
- //char* myAlloc2 = new char(4); cout << "alloced" << endl;
- header->keySequence = new char(header->keyLength);
- //char* myAlloc = new char(4);
- // cout << "here " << endl;
- in.read(header->keySequence, header->keyLength);
- string tempBuf2 = header->keySequence;
- if (tempBuf2.length() > header->keyLength) { tempBuf2 = tempBuf2.substr(0, header->keyLength); strcpy(header->keySequence, tempBuf2.c_str()); }
- //cout << "here " << header->keySequence << '\t' << in.tellg() << endl;
-
- /* Pad to 8 chars */
- int spotInFile = in.tellg();
- //cout << spotInFile << endl;
- int spot = floor((spotInFile + 7) /(float) 8) * 8;
- //cout << spot << endl;
- in.seekg(spot);
-
- //exit(1);
-
- }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()) {
- string tempBuf = "";
-
- //read header length
- char* buffer = new char(sizeof(header->headerLength));
- in.read(buffer, sizeof(header->headerLength));
- header->headerLength = be_int2(*(unsigned short *)(buffer));
- delete[] buffer;
-
- //read name length
- buffer = new char(sizeof(header->nameLength));
- in.read(buffer, sizeof(header->nameLength));
- header->nameLength = be_int2(*(unsigned short *)(buffer));
- delete[] buffer;
-
- //read num bases
- buffer = new char(sizeof(header->numBases));
- in.read(buffer, sizeof(header->numBases));
- header->numBases = be_int4(*(unsigned int *)(buffer));
- delete[] buffer;
-
- //read clip qual left
- buffer = new char(sizeof(header->clipQualLeft));
- in.read(buffer, sizeof(header->clipQualLeft));
- header->clipQualLeft = be_int2(*(unsigned short *)(buffer));
- delete[] buffer;
-
- //read clip qual right
- buffer = new char(sizeof(header->clipQualRight));
- in.read(buffer, sizeof(header->clipQualRight));
- header->clipQualRight = be_int2(*(unsigned short *)(buffer));
- delete[] buffer;
-
- //read clipAdapterLeft
- buffer = new char(sizeof(header->clipAdapterLeft));
- in.read(buffer, sizeof(header->clipAdapterLeft));
- header->clipAdapterLeft = be_int2(*(unsigned short *)(buffer));
- delete[] buffer;
-
- //read clipAdapterRight
- buffer = new char(sizeof(header->clipAdapterRight));
- in.read(buffer, sizeof(header->clipAdapterRight));
- header->clipAdapterRight = be_int2(*(unsigned short *)(buffer));
- delete[] buffer;
-
- //read name
- header->name = new char(header->nameLength);
- //buffer = new char(header->nameLength);
- in.read(header->name, header->nameLength);
- //memcpy(header->name, buffer, header->nameLength);
- //delete[] buffer;
-
- }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()) {
-
- string tempBuf = "";
- char* buffer;
-
- //read flowgram
- read->flowgram.resize(numFlowReads);
- for (int i = 0; i < numFlowReads; i++) {
- buffer = new char((sizeof(unsigned short)));
- in.read(buffer, (sizeof(unsigned short)));
- read->flowgram[i] = be_int2(*(unsigned short *)(buffer));
- delete[] buffer;
- }
-
- //read flowgram
- read->flowIndex.resize(numBases);
- for (int i = 0; i < numBases; i++) {
- buffer = new char(1);
- in.read(buffer, 1);
- read->flowgram[i] = be_int1(*(unsigned int *)(buffer));
- delete[] buffer;
- }
-
- //read bases
- read->bases = new char(numBases);
- in.read(read->bases, numBases);
- tempBuf = buffer;
- if (tempBuf.length() > numBases) { tempBuf = tempBuf.substr(0, numBases); strcpy(read->bases, tempBuf.c_str()); }
-
-
- //read flowgram
- read->qualScores.resize(numBases);
- for (int i = 0; i < numBases; i++) {
- buffer = new char(1);
- in.read(buffer, 1);
- read->qualScores[i] = be_int1(*(unsigned int *)(buffer));
- delete[] buffer;
- }
-
- /* Pad to 8 chars */
- int spotInFile = in.tellg();
- cout << spotInFile << endl;
- int spot = floor((spotInFile + 7) /(float) 8) * 8;
- cout << spot << endl;
- 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, bool debug) {
- try {
-
- string output = "Common Header:\nMagic Number: ";
- output += toString(header->magicNumber) + '\n';
- output += "Version: " + toString(header->version) + '\n';
- output += "Index Offset: " + toString(header->indexOffset) + '\n';
- output += "Index Length: " + toString(header->indexLength) + '\n';
- output += "Number of Reads: " + toString(header->numReads) + '\n';
- output += "Header Length: " + toString(header->headerLength) + '\n';
- output += "Key Length: " + toString(header->keyLength) + '\n';
- output += "Number of Flows: " + toString(header->numFlowsPerRead) + '\n';
- output += "Format Code: " + toString(header->flogramFormatCode) + '\n';
- output += "Flow Chars: " + toString(header->flowChars) + '\n';
- output += "Key Sequence: " + toString(header->keySequence) + '\n';
-
- out << output << endl;
-
- if (debug) { cout << output << endl; }
-
- return 0;
- }
- catch(exception& e) {
- m->errorOut(e, "SffInfoCommand", "printCommonHeader");
- exit(1);
- }
-}
-//**********************************************************************************************************************
-int SffInfoCommand::printHeader(ofstream& out, Header* header, bool debug) {
- try {
- string name = header->name;
- string output = ">" + name + "\nRead Header Length: " + toString(header->headerLength) + '\n';
- output += "Name Length: " + toString(header->nameLength) + '\n';
- output += "Number of Bases: " + toString(header->numBases) + '\n';
- output += "Clip Qual Left: " + toString(header->clipQualLeft) + '\n';
- output += "Clip Qual Right: " + toString(header->clipQualLeft) + '\n';
- output += "Clip Adap Left: " + toString(header->clipQualLeft) + '\n';
- output += "Clip Adap Right: " + toString(header->clipQualLeft) + '\n';
-
- out << output << endl;
-
- if (debug) { cout << output << endl; }
-
- return 0;
- }
- catch(exception& e) {
- m->errorOut(e, "SffInfoCommand", "printHeader");
- exit(1);
- }
-}
-
-//**********************************************************************************************************************
-int SffInfoCommand::printSeqData(ofstream& out, seqRead* read, bool debug) {
- try {
-
- string output = "FlowGram: ";
- for (int i = 0; i < read->flowgram.size(); i++) { output += toString(read->flowgram[i]) +'\t'; }
- output += "\nFlow Indexes: ";
- for (int i = 0; i < read->flowIndex.size(); i++) { output += toString(read->flowIndex[i]) +'\t'; }
- string bases = read->bases;
- output += "\nBases: " + bases + '\n';
- for (int i = 0; i < read->qualScores.size(); i++) { output += toString(read->qualScores[i]) +'\t'; }
- output += '\n';
-
- out << output << endl;
-
- if (debug) { cout << output << endl; }
-
- return 0;
- }
- catch(exception& e) {
- m->errorOut(e, "SffInfoCommand", "printSeqData");
- 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
+\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