X-Git-Url: http://woldlab.caltech.edu/gitweb/?p=mussa.git;a=blobdiff_plain;f=alg%2Fmussa.cpp;h=9a5935e19947cbd68e28e7c7a3f88b267816030f;hp=82b1d4a6585e49c1a946e9093413b0be357ab570;hb=6d25d4d945af696134bdf788b111f38b197b1a15;hpb=02adcab9918657891638e68580b8b88e6d935875 diff --git a/alg/mussa.cpp b/alg/mussa.cpp index 82b1d4a..9a5935e 100644 --- a/alg/mussa.cpp +++ b/alg/mussa.cpp @@ -21,9 +21,11 @@ namespace fs = boost::filesystem; #include #include "mussa_exceptions.hpp" -#include "alg/flp.hpp" -#include "alg/mussa.hpp" -#include "alg/motif_parser.hpp" + +#include "flp.hpp" +#include "io.hpp" +#include "mussa.hpp" +#include "motif_parser.hpp" using namespace std; @@ -350,10 +352,35 @@ void Mussa::load_sequence(fs::path seq_file, fs::path annot_file, set_dirty(true); } +void Mussa::load_mupa_file(std::string para_file_path) { + load_mupa_file(boost::filesystem::path(para_file_path)); +} + void Mussa::load_mupa_file(fs::path para_file_path) { - fs::ifstream para_file; + if (not fs::exists(para_file_path)) + { + throw mussa_load_error("Config File: " + para_file_path.string() + " not found"); + } else if (fs::is_directory(para_file_path)) { + throw mussa_load_error("Config File: " + para_file_path.string() + " is a directory."); + } else if (fs::is_empty(para_file_path)) { + throw mussa_load_error("Config File: " + para_file_path.string() + " is empty"); + } else { + // what directory is the mupa file in? + fs::path file_path_base( para_file_path.branch_path()) ; + + fs::ifstream para_file; + para_file.open(para_file_path, ios::in); + + load_mupa_stream(para_file, file_path_base); + para_file.close(); + } +} + +void +Mussa::load_mupa_stream(std::istream& para_file, fs::path& file_path_base) +{ string file_data_line; string param, value; fs::path annot_file; @@ -367,101 +394,84 @@ Mussa::load_mupa_file(fs::path para_file_path) // initialize values clear(); - // if file was opened, read the parameter values - if (not fs::exists(para_file_path)) + // setup loop by getting file's first line + getline(para_file, file_data_line); + split_index = file_data_line.find(" "); + param = file_data_line.substr(0,split_index); + value = file_data_line.substr(split_index+1); + + while (para_file) { - throw mussa_load_error("Config File: " + para_file_path.string() + " not found"); - } else if (fs::is_directory(para_file_path)) { - throw mussa_load_error("Config File: " + para_file_path.string() + " is a directory."); - } else if (fs::is_empty(para_file_path)) { - throw mussa_load_error("Config File: " + para_file_path.string() + " is empty"); - } else { - para_file.open(para_file_path, ios::in); - - // what directory is the mupa file in? - fs::path file_path_base = para_file_path.branch_path(); - - // setup loop by getting file's first line - getline(para_file,file_data_line); - split_index = file_data_line.find(" "); - param = file_data_line.substr(0,split_index); - value = file_data_line.substr(split_index+1); - - while (para_file) + did_seq = false; + if (param == "ANA_NAME") + analysis_name = value; + else if (param == "APPEND_WIN") + win_append = true; + else if (param == "APPEND_THRES") + thres_append = true; + else if (param == "SEQUENCE_NUM") + ; // ignore sequence_num now + else if (param == "WINDOW") + window = atoi(value.c_str()); + else if (param == "THRESHOLD") + threshold = atoi(value.c_str()); + else if (param == "SEQUENCE") { - did_seq = false; - if (param == "ANA_NAME") - analysis_name = value; - else if (param == "APPEND_WIN") - win_append = true; - else if (param == "APPEND_THRES") - thres_append = true; - else if (param == "SEQUENCE_NUM") - ; // ignore sequence_num now - else if (param == "WINDOW") - window = atoi(value.c_str()); - else if (param == "THRESHOLD") - threshold = atoi(value.c_str()); - else if (param == "SEQUENCE") - { - fs::path seq_file = file_path_base / value; - //cout << "seq_file_name " << seq_files.back() << endl; - fasta_index = 1; - annot_file = ""; - sub_seq_start = 0; - sub_seq_end = 0; - seq_params = true; - - while (para_file && seq_params) - { - getline(para_file,file_data_line); - split_index = file_data_line.find(" "); - param = file_data_line.substr(0,split_index); - value = file_data_line.substr(split_index+1); - - if (param == "FASTA_INDEX") - fasta_index = atoi(value.c_str()); - else if (param == "ANNOTATION") - annot_file = file_path_base / value; - else if (param == "SEQ_START") - sub_seq_start = atoi(value.c_str()); - else if (param == "SEQ_END") - { - sub_seq_end = atoi(value.c_str()); - } - //ignore empty lines or that start with '#' - else if ((param == "") || (param == "#")) {} - else seq_params = false; - } - load_sequence(seq_file, annot_file, fasta_index, sub_seq_start, - sub_seq_end); - did_seq = true; - } - //ignore empty lines or that start with '#' - else if ((param == "") || (param == "#")) {} - else - { - clog << "Illegal/misplaced mussa parameter in file\n"; - clog << param << "\n"; - } - - if (!did_seq) + fs::path seq_file = file_path_base / value; + //cout << "seq_file_name " << seq_files.back() << endl; + fasta_index = 1; + annot_file = ""; + sub_seq_start = 0; + sub_seq_end = 0; + seq_params = true; + + while (para_file && seq_params) { - getline(para_file,file_data_line); + multiplatform_getline(para_file,file_data_line); split_index = file_data_line.find(" "); param = file_data_line.substr(0,split_index); value = file_data_line.substr(split_index+1); - did_seq = false; + + if (param == "FASTA_INDEX") + fasta_index = atoi(value.c_str()); + else if (param == "ANNOTATION") + annot_file = file_path_base / value; + else if (param == "SEQ_START") + sub_seq_start = atoi(value.c_str()); + else if (param == "SEQ_END") + { + sub_seq_end = atoi(value.c_str()); + } + //ignore empty lines or that start with '#' + else if ((param == "") || (param == "#")) { + // pass + } else { + seq_params = false; + } } + load_sequence(seq_file, annot_file, fasta_index, sub_seq_start, + sub_seq_end); + did_seq = true; + } + //ignore empty lines or that start with '#' + else if ((param == "") || (param == "#")) {} + else + { + clog << "Illegal/misplaced mussa parameter in file\n"; + clog << param << "\n"; } - para_file.close(); - - soft_thres = threshold; - //cout << "nway mupa: analysis_name = " << analysis_name - // << " window = " << window - // << " threshold = " << threshold << endl; + if (!did_seq) + { + multiplatform_getline(para_file,file_data_line); + split_index = file_data_line.find(" "); + param = file_data_line.substr(0,split_index); + value = file_data_line.substr(split_index+1); + did_seq = false; + } } + + soft_thres = threshold; // no file was loaded, signal error set_dirty(true); }