ENH: String-to-number cast was made more robust using Boost.

src/CSVReader/CSVReader.cpp

@@ -7,10 +7,14 @@
 #include <sstream>
 #include <filesystem>
 #include <regex>
+#include <algorithm>
+#include <boost/lexical_cast.hpp>
+#include <boost/algorithm/string/erase.hpp>
 
 #include "CSVReader.h"
 #include "../exceptions.h"
 
+
 namespace lib4neuro {
     CSVReader::CSVReader(std::string file_path, std::string delimiter, bool ignore_first_line) {
         if(!std::filesystem::exists(file_path)) {
@@ -79,17 +83,29 @@ namespace lib4neuro {
             //TODO check empty values in data
             std::vector<double> input;
             for(auto ind : *input_col_indices) {
+                std::string s;
+
                 try {
+                    /* Remove remaining spaces */
+                    s = line.at(ind);
+                    boost::algorithm::erase_all(s, " ");
+
+                    /* Strip BOM */
+                    // TODO solve in another way - work properly with different encodings!
+                    boost::algorithm::erase_all(s, "\uEFBBBF");  // UTF-8
+                    boost::algorithm::erase_all(s, "\uFEFF");  // UTF-16
+
                     /* Check, if the string is a number */
-                    if(!std::regex_match( line.at(ind), std::regex( ( "((\\+|-)?[[:digit:]]+)(\\.(([[:digit:]]+)?))?" ) ))) {
-                        THROW_RUNTIME_ERROR(std::string("Value \"") + line.at(ind) + "\" is not numerical and so it cannot be used in Data Set!");
-                    }
+                    double tmp = boost::lexical_cast<double>(s);
 
                     /* Add loaded number to the vector of inputs */
-                    input.push_back(std::stod(line.at(ind)));
+                    input.push_back(tmp);
 
                 } catch(const std::out_of_range& e) {
                     THROW_OUT_OF_RANGE_ERROR("Non-existing index specified (" + std::to_string(ind) + ")!");
+
+                } catch (const boost::bad_lexical_cast& e) {
+                    THROW_RUNTIME_ERROR("Value \"" + s + "\" is not numerical and so it cannot be used in Data Set!");
                 }
             }