connect_new_input.py

# -*- coding: utf-8 -*-
"""
Functions to update a graph representing citations between multiple ACS/Nature journals

"""

__authors__ = "Donna Löding, Alina Molkentin, Xinyi Tang, Judith Große, Malte Schokolowski"
__email__ = "cis-project2021@zbh.uni-hamburg.de"
__status__ = "Production"
#__copyright__ = ""
#__credits__ = ["", "", "", ""]
#__license__ = ""
#__version__ = ""
#__maintainer__ = ""

import sys  
from pathlib import Path
from os import error
sys.path.append("../")

from .import_from_json import input_from_json
from verarbeitung.construct_new_graph.Processing import initialize_nodes_list, complete_inner_edges
from verarbeitung.construct_new_graph.add_citations_rec import add_citations
from verarbeitung.construct_new_graph.export_to_json import output_to_json

def connect_old_and_new_input(json_file, new_doi_list, search_depth, search_height, test_var = False):
    '''
        :param json_file:       json file with old graph
        :type json_file:        json file

        :param new_doi_list:    additional dois which has to be connected to the old graph
        :type new_doi_list:     list of strings

        :param search_depth:    depth to search for references
        :type search_depth:     int

        :param search_height:   height to search for citations
        :type search_height:    int

        :param test_var:        variable to differenciate between test and url call
        :type test_var:         boolean

        connetcs the old graph and the new input dois to a complete new graph
    '''
    global nodes, edges
    nodes = []
    edges = []

    nodes, edges = input_from_json(json_file)

    complete_changed_group_nodes(new_doi_list, search_depth, search_height, test_var)
    
    # initializes nodes/edges from input and gets a list with publication objects for citations and references returned
    references_obj_list, citations_obj_list = initialize_nodes_list(new_doi_list,search_depth, search_height, test_var)

    # function calls to begin recursive processing up to max depth/height
    add_citations(nodes, edges, citations_obj_list, 1, search_height, "Citation", test_var)
    add_citations(nodes, edges, references_obj_list, 1, search_depth, "Reference", test_var)

    # adds edges between reference group and citation group of known publications
    complete_inner_edges(test_var)

    # calls a skript to save nodes and edges of graph in .json file
    output_to_json(nodes,edges, test_var)

    return(nodes, edges)


def complete_changed_group_nodes(new_doi_list, search_depth_max, search_height_max, test_var):
    '''
    work in progress
    '''
    changed_group_node_citations = []
    changed_group_node_references = []

    for node in nodes:
        if (node.group < 0) and (node.doi in new_doi_list):
            node.group = "input"
            

        elif (node.group > 0) and (node.doi in new_doi_list):
            node.group = "input"