treebank_collection_processor.hpp

/*********************************************************************
 *
 *  Linear Arrangement Library - A library that implements a collection
 *  algorithms for linear arrangments of graphs.
 *
 *  Copyright (C) 2019 - 2021
 *
 *  This file is part of Linear Arrangement Library. To see the full code
 *  visit the webpage:
 *      https://github.com/lluisalemanypuig/linear-arrangement-library.git
 *
 *  Linear Arrangement Library is free software: you can redistribute it
 *  and/or modify it under the terms of the GNU Affero General Public License
 *  as published by the Free Software Foundation, either version 3 of the
 *  License, or (at your option) any later version.
 *
 *  Linear Arrangement Library is distributed in the hope that it will be
 *  useful, but WITHOUT ANY WARRANTY; without even the implied warranty of
 *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
 *  GNU Affero General Public License for more details.
 *
 *  You should have received a copy of the GNU Affero General Public License
 *  along with Linear Arrangement Library.  If not, see <http://www.gnu.org/licenses/>.
 *
 *  Contact:
 *
 *      Lluís Alemany Puig (lalemany@cs.upc.edu)
 *          LARCA (Laboratory for Relational Algorithmics, Complexity and Learning)
 *          CQL (Complexity and Quantitative Linguistics Lab)
 *          Jordi Girona St 1-3, Campus Nord UPC, 08034 Barcelona.   CATALONIA, SPAIN
 *          Webpage: https://cqllab.upc.edu/people/lalemany/
 *
 *      Ramon Ferrer i Cancho (rferrericancho@cs.upc.edu)
 *          LARCA (Laboratory for Relational Algorithmics, Complexity and Learning)
 *          CQL (Complexity and Quantitative Linguistics Lab)
 *          Office S124, Omega building
 *          Jordi Girona St 1-3, Campus Nord UPC, 08034 Barcelona.   CATALONIA, SPAIN
 *          Webpage: https://cqllab.upc.edu/people/rferrericancho/
 *
 ********************************************************************/
 
#pragma once
 
// C++ includes
#if defined DEBUG
#include <cassert>
#endif
#include <vector>
#include <string>
#include <tuple>
#include <array>
 
// lal includes
#include <lal/io/treebank_error.hpp>
#include <lal/io/process_treebank_base.hpp>
 
namespace lal {
namespace io {
 
class treebank_collection_processor : public _process_treebank_base {
public:
    // SETTERS
 
    void set_join_files(bool v) noexcept { m_join_files = v; }
 
    inline void set_number_threads(size_t n_threads) noexcept {
#if defined DEBUG
        assert(n_threads != 0);
#endif
        m_num_threads = n_threads;
    }
 
    // GETTERS
 
    size_t get_num_errors() const noexcept
    { return m_errors_from_processing.size(); }
 
    const treebank_error& get_error_type(size_t i) const noexcept
    { return std::get<0>(m_errors_from_processing[i]); }
 
    const std::string& get_error_treebank_filename(size_t i) const noexcept
    { return std::get<1>(m_errors_from_processing[i]); }
 
    const std::string& get_error_treebank_name(size_t i) const noexcept
    { return std::get<2>(m_errors_from_processing[i]); }
 
    // PROCESS THE TREEBANK COLLECTION
 
    treebank_error init(
        const std::string& main_file,
        const std::string& output_directory
    )
    noexcept;
 
    treebank_error process(const std::string& result_filename = "") noexcept;
 
private:
    std::vector<std::string> m_all_individual_treebank_names;
 
    bool m_join_files = true;
 
    size_t m_num_threads = 1;
 
    std::vector<std::tuple<treebank_error, std::string, std::string>>
    m_errors_from_processing;
 
private:
    treebank_error join_all_files(const std::string& resname) const
    noexcept;
 
private:
    std::string m_out_dir = "none";
    std::string m_main_file = "none";
};
 
inline
treebank_error process_treebank_collection(
    const std::string& treebank_collection_main_file,
    const std::string& output_directory,
    std::size_t num_threads = 1
)
noexcept
{
    treebank_collection_processor tbcolproc;
    auto err = tbcolproc.init(treebank_collection_main_file, output_directory);
    tbcolproc.set_number_threads(num_threads);
    if (err.get_error_type() != treebank_error_type::no_error) {
        return err;
    }
    return tbcolproc.process();
}
 
} // -- namespace io
} // -- namespace lal