add_references_rec.py

# -*- coding: utf-8 -*-
"""
Functions to add references recursivly for 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 input.publication import Publication
from verarbeitung.get_pub_from_input import get_pub

def create_global_lists_ref(input_nodes, input_edges, pub, search_depth, search_depth_max, test_var):
    '''
        :param input_nodes:         list of nodes from Processing
        :type input_nodes:          List[Publication]

        :param input_edges:         list of edges from Processing
        :type input_edges:          List[String, String]

        :param pub:                 Publication which references will be added
        :type pub:                  Publication

        :param search_height:       current height to search for references
        :type search_height_max:    int

        :param search_height_max:   maximum height to search for references
        :type search_height_max:    int

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

        function to create nodes and edges and call create_graph_structure_references 
    '''

    global nodes, edges
    nodes = input_nodes
    edges = input_edges

    return create_graph_structure_references(pub, search_depth, search_depth_max, test_var)


def create_graph_structure_references(pub, search_depth, search_depth_max, test_var):
    '''
        :param pub:                 publication which references will be added
        :type pub:                  Publication

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

        :param search_depth_max:    maximum depth to search for references
        :type search_depth_max:     int

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

        adds a node for every referenced publication unknown
        adds edges to added references
    '''

    references_pub_obj_list = []
    for reference in pub.references: #iterates over the references of the considered paper
        not_in_nodes = True #boolean Value to ensure that there will be no dublicates in the set of nodes
        for node in nodes: #iterates over all nodes in set of nodes #
            if (reference == node.doi_url): #determines that the node already exists
                not_in_nodes = False #boolean false --> node will not be created
                break
        if (not_in_nodes): #checks that there is no node with this doi 
            if (search_depth < search_depth_max): #checks that the recursion step is smaller than the limit
                reference_pub_obj = get_pub(reference, test_var)
                if (type(reference_pub_obj) != Publication):
                    print(pub)
                    continue 

                reference_pub_obj.group = "depth"
                nodes.append(reference_pub_obj) # appends the object to the set of nodes
                edges.append([pub.doi_url,reference_pub_obj.doi_url]) #appends the edge to the set of edges
                references_pub_obj_list.append(reference_pub_obj) #appends the node to the set of references

        # adds edge only if citation already exists           
        elif [pub.doi_url,reference] not in edges:
            edges.append([pub.doi_url,reference])  
    return references_pub_obj_list 


def process_references_rec(references_pub_obj_list, search_depth, search_depth_max, test_var):  
    '''
        :param references_pub_obj_list: list of publications which references will be added
        :type references_pub_obj_list:  List[Publication]

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

        :param search_depth_max:        maximum depth to search for references
        :type search_depth_max:         int

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

        recursive function to implement height-first-search on references
    '''

    # adds next level to nodes/edges
    for pub in references_pub_obj_list:
        new_reference_pub_obj_list = create_graph_structure_references(pub, search_depth, search_depth_max, test_var)    

        # If the maximum height has not yet been reached, calls function recursivly with increased height     
        if (search_depth < search_depth_max):
            process_references_rec(new_reference_pub_obj_list, search_depth+1, search_depth_max, test_var)


def add_references(input_nodes, input_edges, references_pub_obj_list, search_height, search_height_max, test_var):
    '''
        :param input_nodes:             list of nodes from Processing
        :type input_nodes:              List[Publication]

        :param input_edges:             list of edges from Processing
        :type input_edges:              List[String, String]

        :param references_pub_obj_list:  list of publications which references will be added
        :type references_pub_obj_list:   List[Publication]

        :param search_height:       current height to search for references
        :type search_height_max:    int

        :param search_height_max:   maximum height to search for references
        :type search_height_max:    int

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

        function to call recursive depth-first-search of references
    '''
    global nodes, edges
    nodes = input_nodes
    edges = input_edges

    process_references_rec(references_pub_obj_list, search_height, search_height_max, test_var)
    return(nodes, edges)