treebank_reader.hpp

/*********************************************************************
 *
 * Linear Arrangement Library - A library that implements a collection
 * algorithms for linear arrangments of graphs.
 *
 * Copyright (C) 2019 - 2024
 *
 * This file is part of Linear Arrangement Library. The full code is available
 * at:
 *      https://github.com/LAL-project/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 (lluis.alemany.puig@upc.edu)
 *         LQMC (Quantitative, Mathematical, and Computational Linguisitcs)
 *         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)
 *         LQMC (Quantitative, Mathematical, and Computational Linguisitcs)
 *         CQL (Complexity and Quantitative Linguistics Lab)
 *         Office 220, 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
#include <fstream>
#include <string>
 
// lal includes
#include <lal/basic_types.hpp>
#include <lal/graphs/rooted_tree.hpp>
#include <lal/io/treebank_file_error.hpp>
 
namespace lal {
namespace io {
 
class treebank_reader {
public:
    // MODIFIERS
 
    [[nodiscard]] treebank_file_error init
    (const std::string& treebank_filename, const std::string& treebank_id = "")
    noexcept;
 
    [[nodiscard]] bool end() const noexcept { return m_no_more_trees; }
 
    void next_tree() noexcept;
 
    /* GETTERS */
 
    [[nodiscard]] std::size_t get_num_trees() const noexcept
    { return m_num_trees; }
 
    [[nodiscard]] const std::string& get_treebank_identifier() const noexcept
    { return m_treebank_identifier; }
 
    [[nodiscard]] const std::string& get_treebank_filename() const noexcept
    { return m_treebank_file; }
 
    [[nodiscard]] graphs::rooted_tree get_tree() const noexcept;
 
    [[nodiscard]] head_vector get_head_vector() const noexcept
    { return m_current_head_vector; }
 
    [[nodiscard]] bool is_open() const noexcept { return m_treebank.is_open(); }
 
    /* SETTERS */
 
    void set_normalize(const bool v) noexcept {
        m_normalize_tree = v;
    }
 
    void set_calculate_size_subtrees(const bool v) noexcept {
        m_calculate_size_subtrees = v;
    }
 
    void set_calculate_tree_type(const bool v) noexcept {
        m_calculate_tree_type = v;
    }
 
    void set_identifier(const std::string& id) noexcept
    { m_treebank_identifier = id; }
 
private:
    std::string m_treebank_identifier = "none";
    std::string m_treebank_file = "none";
    std::ifstream m_treebank;
 
    std::size_t m_num_trees = 0;
    std::string m_current_line;
    head_vector m_current_head_vector;
 
    bool m_normalize_tree = true;
    bool m_calculate_size_subtrees = true;
    bool m_calculate_tree_type = true;
    bool m_no_more_trees = false;
};
 
} // -- namespace io
} // -- namespace lal