treebank_processor.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 <string>
 
// lal includes
#include <lal/linear_arrangement.hpp>
#include <lal/io/treebank_file_error.hpp>
#include <lal/io/treebank_processor_base.hpp>
 
namespace lal {
namespace io {
 
class treebank_processor : public _treebank_processor_base {
public:
    // PROCESS THE TREEBANK collection
 
    treebank_file_error init
    (
        const std::string& treebank_input_file,
        const std::string& output_file,
        const std::string& treebank_id = ""
    )
    noexcept;
 
    [[nodiscard]] treebank_file_error process() noexcept;
 
private:
    template <class TREE, class OUT_STREAM>
    void process_tree
    (
        const TREE& rT,
        double * const props,
        char * const prop_set,
        OUT_STREAM& out_lab_file
    )
    noexcept;
 
    // HEADER
 
    template <class OUT_STREAM>
    void output_tree_type_header(OUT_STREAM& out_lab_file)
    const noexcept;
 
    template <class OUT_STREAM>
    void output_syndepstruct_type_header(OUT_STREAM& out_lab_file)
    const noexcept;
 
    // VALUES
 
    template <class TREE_TYPE, class OUT_STREAM>
    void output_tree_type_values(TREE_TYPE& t, OUT_STREAM& out_lab_file)
    const noexcept;
 
    template <class TREE_TYPE, class OUT_STREAM>
    void output_syndepstruct_type_values
    (
        const TREE_TYPE& t,
        const uint64_t C,
        OUT_STREAM& out_lab_file
    )
    const noexcept;
 
private:
    std::string m_treebank_filename = "none";
    std::string m_output_file = "none";
    std::string m_treebank_id = "";
 
    static constexpr std::size_t n_idx = treebank_feature_to_index(treebank_feature_type::num_nodes);
    static constexpr std::size_t k2_idx = treebank_feature_to_index(treebank_feature_type::second_moment_degree);
    static constexpr std::size_t k2_out_idx = treebank_feature_to_index(treebank_feature_type::second_moment_degree_out);
    static constexpr std::size_t k3_idx = treebank_feature_to_index(treebank_feature_type::third_moment_degree);
    static constexpr std::size_t k3_out_idx = treebank_feature_to_index(treebank_feature_type::third_moment_degree_out);
    static constexpr std::size_t SK2_idx = treebank_feature_to_index(treebank_feature_type::sum_squared_degrees);
    static constexpr std::size_t SK2_out_idx = treebank_feature_to_index(treebank_feature_type::sum_squared_out_degrees);
    static constexpr std::size_t SK3_idx = treebank_feature_to_index(treebank_feature_type::sum_cubed_degrees);
    static constexpr std::size_t SK3_out_idx = treebank_feature_to_index(treebank_feature_type::sum_cubed_out_degrees);
    static constexpr std::size_t num_pairs_independent_edges_idx = treebank_feature_to_index(treebank_feature_type::num_pairs_independent_edges);
    static constexpr std::size_t head_initial_idx = treebank_feature_to_index(treebank_feature_type::head_initial);
    static constexpr std::size_t hubiness_idx = treebank_feature_to_index(treebank_feature_type::hubiness);
    static constexpr std::size_t sum_hierarchical_distance_idx = treebank_feature_to_index(treebank_feature_type::sum_hierarchical_distances);
    static constexpr std::size_t mean_hierarchical_distance_idx = treebank_feature_to_index(treebank_feature_type::mean_hierarchical_distance);
    static constexpr std::size_t tree_centre_idx = treebank_feature_to_index(treebank_feature_type::tree_centre);
    static constexpr std::size_t tree_centroid_idx = treebank_feature_to_index(treebank_feature_type::tree_centroid);
    static constexpr std::size_t tree_diameter_idx = treebank_feature_to_index(treebank_feature_type::tree_diameter);
    static constexpr std::size_t tree_caterpillar_distance_idx = treebank_feature_to_index(treebank_feature_type::tree_caterpillar_distance);
    static constexpr std::size_t C_idx = treebank_feature_to_index(treebank_feature_type::num_crossings);
    static constexpr std::size_t C_predicted_idx = treebank_feature_to_index(treebank_feature_type::predicted_num_crossings);
    static constexpr std::size_t C_expected_idx = treebank_feature_to_index(treebank_feature_type::exp_num_crossings);
    static constexpr std::size_t C_variance_idx = treebank_feature_to_index(treebank_feature_type::var_num_crossings);
    static constexpr std::size_t C_z_score_idx = treebank_feature_to_index(treebank_feature_type::z_score_num_crossings);
    static constexpr std::size_t D_idx = treebank_feature_to_index(treebank_feature_type::sum_edge_lengths);
    static constexpr std::size_t D_expected_idx = treebank_feature_to_index(treebank_feature_type::exp_sum_edge_lengths);
    static constexpr std::size_t D_expected_bipartite_idx = treebank_feature_to_index(treebank_feature_type::exp_sum_edge_lengths_bipartite);
    static constexpr std::size_t D_expected_projective_idx = treebank_feature_to_index(treebank_feature_type::exp_sum_edge_lengths_projective);
    static constexpr std::size_t D_expected_planar_idx = treebank_feature_to_index(treebank_feature_type::exp_sum_edge_lengths_planar);
    static constexpr std::size_t D_variance_idx = treebank_feature_to_index(treebank_feature_type::var_sum_edge_lengths);
    static constexpr std::size_t D_z_score_idx = treebank_feature_to_index(treebank_feature_type::z_score_sum_edge_lengths);
    static constexpr std::size_t Dmin_Unconstrained_idx = treebank_feature_to_index(treebank_feature_type::min_sum_edge_lengths);
    static constexpr std::size_t Dmin_Bipartite_idx = treebank_feature_to_index(treebank_feature_type::min_sum_edge_lengths_bipartite);
    static constexpr std::size_t Dmin_Planar_idx = treebank_feature_to_index(treebank_feature_type::min_sum_edge_lengths_planar);
    static constexpr std::size_t Dmin_Projective_idx = treebank_feature_to_index(treebank_feature_type::min_sum_edge_lengths_projective);
    static constexpr std::size_t DMax_Unconstrained_idx = treebank_feature_to_index(treebank_feature_type::max_sum_edge_lengths);
    static constexpr std::size_t DMax_1_thistle_idx = treebank_feature_to_index(treebank_feature_type::max_sum_edge_lengths_1_thistle);
    static constexpr std::size_t DMax_Bipartite_idx = treebank_feature_to_index(treebank_feature_type::max_sum_edge_lengths_bipartite);
    static constexpr std::size_t DMax_Planar_idx = treebank_feature_to_index(treebank_feature_type::max_sum_edge_lengths_planar);
    static constexpr std::size_t DMax_Projective_idx = treebank_feature_to_index(treebank_feature_type::max_sum_edge_lengths_projective);
    static constexpr std::size_t mean_dependency_distance_idx = treebank_feature_to_index(treebank_feature_type::mean_dependency_distance);
    static constexpr std::size_t flux_max_weight_idx = treebank_feature_to_index(treebank_feature_type::flux_max_weight);
    static constexpr std::size_t flux_mean_weight_idx = treebank_feature_to_index(treebank_feature_type::flux_mean_weight);
    static constexpr std::size_t flux_min_weight_idx = treebank_feature_to_index(treebank_feature_type::flux_min_weight);
    static constexpr std::size_t flux_max_left_span_idx = treebank_feature_to_index(treebank_feature_type::flux_max_left_span);
    static constexpr std::size_t flux_mean_left_span_idx = treebank_feature_to_index(treebank_feature_type::flux_mean_left_span);
    static constexpr std::size_t flux_min_left_span_idx = treebank_feature_to_index(treebank_feature_type::flux_min_left_span);
    static constexpr std::size_t flux_max_right_span_idx = treebank_feature_to_index(treebank_feature_type::flux_max_right_span);
    static constexpr std::size_t flux_mean_right_span_idx = treebank_feature_to_index(treebank_feature_type::flux_mean_right_span);
    static constexpr std::size_t flux_min_right_span_idx = treebank_feature_to_index(treebank_feature_type::flux_min_right_span);
    static constexpr std::size_t flux_max_RL_ratio_idx = treebank_feature_to_index(treebank_feature_type::flux_max_RL_ratio);
    static constexpr std::size_t flux_mean_RL_ratio_idx = treebank_feature_to_index(treebank_feature_type::flux_mean_RL_ratio);
    static constexpr std::size_t flux_min_RL_ratio_idx = treebank_feature_to_index(treebank_feature_type::flux_min_RL_ratio);
    static constexpr std::size_t flux_max_WS_ratio_idx = treebank_feature_to_index(treebank_feature_type::flux_max_WS_ratio);
    static constexpr std::size_t flux_mean_WS_ratio_idx = treebank_feature_to_index(treebank_feature_type::flux_mean_WS_ratio);
    static constexpr std::size_t flux_min_WS_ratio_idx = treebank_feature_to_index(treebank_feature_type::flux_min_WS_ratio);
    static constexpr std::size_t flux_max_size_idx = treebank_feature_to_index(treebank_feature_type::flux_max_size);
    static constexpr std::size_t flux_mean_size_idx = treebank_feature_to_index(treebank_feature_type::flux_mean_size);
    static constexpr std::size_t flux_min_size_idx = treebank_feature_to_index(treebank_feature_type::flux_min_size);
};
 
[[nodiscard]] inline treebank_file_error process_treebank
(const std::string& treebank_file, const std::string& output_file)
noexcept
{
    treebank_processor tbproc;
    auto err = tbproc.init(treebank_file, output_file);
    if (not err.is_error()) { return err; }
    return tbproc.process();
}
 
} // -- namespace io
} // -- namespace lal