Merge branch 'main' of...

Merge branch 'main' of https://gitlab.rrz.uni-hamburg.de/bav1758/ci-s-projekt-verarbeitung into main

verarbeitung/Kanten_Vergleich.py

@@ -9,7 +9,7 @@ def back_to_valid_edges(links_from_json, processed_input_list):
     
     function that deletes edges, if one ore two including nodes are deleted nodes
     '''
-    list_of_valid_edges = links_from_json
+    list_of_valid_edges = links_from_json.copy()
 
 
     #iterates over all edges from old graph
@@ -23,6 +23,8 @@ def back_to_valid_edges(links_from_json, processed_input_list):
                 # increases counter if adjacent node was found
                 if (adj_node == pub.doi_url):
                     found_adj_nodes += 1
+            if (found_adj_nodes == 2):
+                break
 
         #removes the edge if less than 2 adjacent nodes found
         if (found_adj_nodes < 2):

verarbeitung/Processing.py

@@ -13,22 +13,21 @@ __status__ = "Production"
 #__version__ = ""
 #__maintainer__ = ""
 
-from bs4 import BeautifulSoup as bs
-import requests as req
+
 import sys  
 from pathlib import Path
-#sys.path.insert(1, 'C:\Users\Malte\Git\CiS-Projekt\ci-s-projekt-verarbeitung\input')
+from os import error
 sys.path.append("../")
-from input.interface import InputInterface as Input
-#import input
-from input_test import input_test_func
+
+from input.publication import Publication
+from get_pub_from_input import get_pub
 from json_demo import output_to_json
 
 
 def initialize_nodes_list(doi_input_list, search_depth_max, search_height_max, test_var):
     '''
         :param doi_input_list:      input list of doi from UI
-        :type doi_input_list:       list of strings
+        :type doi_input_list:       List[String]
 
         :param search_depth_max:    maximum depth to search for references
         :type search_depth_max:     int
@@ -38,24 +37,19 @@ def initialize_nodes_list(doi_input_list, search_depth_max, search_height_max, t
 
         :param test_var:            variable to differenciate between test and url call
         :type test_var:             boolean
+
+        adds input dois to nodes and retrieves citations and references for input publications
     '''
 
+    # saves found citations and references in lists
     references_pub_obj_list = []
     citations_pub_obj_list = []
 
     for pub_doi in doi_input_list: #iterates over every incoming doi
-        if(test_var): #checks that it is a test and chooses test-input function
-            pub = input_test_func(pub_doi) #creates an object of class Publication
-        else: #checks that it isnt a test and chooses standart-input function
-            #print(pub_doi)
-            inter = Input()
-            try:
-                pub = inter.get_publication(pub_doi) #creates an object of class Publication
-            except ValueError:
-                continue
-            except IndexError:
-                continue
-            
+        pub = get_pub(pub_doi, test_var)
+        if (type(pub) != Publication):
+            print(pub)
+            continue       
 
         # checks if publication already exists in nodes
         not_in_nodes = True #boolean value to check if a node already exists in the set of nodes
@@ -81,34 +75,34 @@ def initialize_nodes_list(doi_input_list, search_depth_max, search_height_max, t
 
     return(references_pub_obj_list, citations_pub_obj_list)
         
-    
+
 
 def complete_inner_edges(test_var):
     '''
         :param test_var:    variable to differenciate between test and url call
         :type test_var:     boolean
+
+        completes inner edges between nodes of group height and depth
     '''
 
     for node in nodes:
         if (node.group == "depth"):
             for citation in node.citations:
                 for cit in nodes:
-                    if (citation.doi_url == cit.doi_url and [citation.doi_url, node.doi_url] not in edges):
-                        edges.append([citation.doi_url, node.doi_url])
+                    if (citation == cit.doi_url and [citation, node.doi_url] not in edges):
+                        edges.append([citation, node.doi_url])
         if (node.group == "height"):
             for reference in node.references:
                 for ref in nodes:
-                    if (reference.doi_url == ref.doi_url and [node.doi_url, reference.doi_url] not in edges):
-                        edges.append([node.doi_url,reference.doi_url])
-
+                    if (reference == ref.doi_url and [node.doi_url, reference] not in edges):
+                        edges.append([node.doi_url,reference])
 
 
-# adds a node for every publication unknown
-# adds edges for references between publications     
+   
 def create_graph_structure_references(pub, search_depth, search_depth_max, test_var):
     '''
         :param pub:                 publication which references will be added
-        :type pub:                  Class Publication
+        :type pub:                  Publication
 
         :param search_depth:        current depth to search for references
         :type search_depth:         int
@@ -118,29 +112,24 @@ def create_graph_structure_references(pub, search_depth, search_depth_max, test_
 
         :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.doi_url == node.doi_url): #determines that the node already exists
+        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
-                if (test_var): #determines that it is a test and chooses the test-input function
-                    reference_pub_obj = input_test_func(reference.doi_url) #creates an Object of Publication Class 
-                else: #determines that it isnt a test and chooses the standart function
-                    #reference_pub_obj = Input(reference.doi_url)
-                    inter = Input()
-                    try:
-                        reference_pub_obj = inter.get_publication(reference.doi_url)
-                    except ValueError:
-                        continue
-                    # nur aus Testzwecken, da noch was bei Input falsch ist
-                    except IndexError:
-                        continue
+                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
@@ -148,19 +137,15 @@ def create_graph_structure_references(pub, search_depth, search_depth_max, test_
                 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.doi_url] not in edges:
-            edges.append([pub.doi_url,reference.doi_url])  
+        elif [pub.doi_url,reference] not in edges:
+            edges.append([pub.doi_url,reference])  
     return references_pub_obj_list 
 
 
-# recursive function to implement height-first-search on references
-# references_pub_obj_list: input list of references as publication objects
-# search_depth: current search_depth of height-first-search
-# search_depth_max: maximal search_depth for dfs
 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 of objects of type Class Publications
+        :type references_pub_obj_list:  List[Publication]
 
         :param search_depth:            current depth to search for references
         :type search_depth:             int
@@ -170,6 +155,8 @@ def process_references_rec(references_pub_obj_list, search_depth, search_depth_m
 
         :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
@@ -180,14 +167,12 @@ def process_references_rec(references_pub_obj_list, search_depth, search_depth_m
         if (search_depth < search_depth_max):
             process_references_rec(new_reference_pub_obj_list, search_depth+1, search_depth_max, test_var)
 
-
-
     
   
 def create_graph_structure_citations(pub, search_height, search_height_max, test_var):
     '''
         :param pub:                 publication which citations will be added
-        :type pub:                  Class Publication
+        :type pub:                  Publication
 
         :param search_height:       current height to search for citations
         :type search_height_max:    int
@@ -197,28 +182,24 @@ def create_graph_structure_citations(pub, search_height, search_height_max, test
 
         :param test_var:            variable to differenciate between test and url call
         :type test_var:             boolean
+
+        adds a node for every citing publication unknown
+        adds edges to added citations
     '''
 
     citations_pub_obj_list = []
     for citation in pub.citations:
         not_in_nodes = True
         for node in nodes: # checks every citation for duplication 
-            if (citation.doi_url == node.doi_url):
+            if (citation == node.doi_url):
                 not_in_nodes = False
                 break
         if (not_in_nodes):
             if (search_height < search_height_max): #checks if its a test and chooses input function accordingly
-                if (test_var):
-                    citation_pub_obj = input_test_func(citation.doi_url)
-                else:
-                    #citation_pub_obj = Input(citation.doi_url)
-                    inter = Input()
-                    try:
-                        citation_pub_obj = inter.get_publication(citation.doi_url)
-                    except ValueError:
-                        continue
-                    except IndexError:
-                        continue
+                citation_pub_obj = get_pub(citation, test_var)
+                if (type(citation_pub_obj) != Publication):
+                    print(pub)
+                    continue 
 
                 citation_pub_obj.group = "height"
                 nodes.append(citation_pub_obj)
@@ -226,20 +207,15 @@ def create_graph_structure_citations(pub, search_height, search_height_max, test
                 citations_pub_obj_list.append(citation_pub_obj)
 
         # adds only edge if citation already exists         
-        elif [citation.doi_url,pub.doi_url] not in edges:
-            edges.append([citation.doi_url,pub.doi_url])   
+        elif [citation,pub.doi_url] not in edges:
+            edges.append([citation,pub.doi_url])   
     return citations_pub_obj_list
 
 
-
-# recursive function to implement height-first-search on citations
-# citations_pub_obj_list: input list of citations as publication objects
-# search_height: current search_height of height-first-search
-# search_height_max: maximal search_height for dfs
 def process_citations_rec(citations_pub_obj_list, search_height, search_height_max, test_var):  
     '''
         :param citations_pub_obj_list:  list of publications which citations will be added
-        :type citations_pub_obj_list:   list of objects of type Class Publications
+        :type citations_pub_obj_list:   List[Publication]
 
         :param search_height:       current height to search for citations
         :type search_height_max:    int
@@ -249,6 +225,8 @@ def process_citations_rec(citations_pub_obj_list, search_height, search_height_m
 
         :param test_var:            variable to differenciate between test and url call
         :type test_var:             boolean
+
+        recursive function to implement depth-first-search on citations
     '''
 
     # adds next level to nodes/edges
@@ -261,8 +239,6 @@ def process_citations_rec(citations_pub_obj_list, search_height, search_height_m
 
 
 
-
-
 def process_main(doi_input_list, search_height, search_depth, test_var = False):
     '''
         :param doi_input_list:  input list of doi from UI
@@ -276,6 +252,8 @@ def process_main(doi_input_list, search_height, search_depth, test_var = False):
 
         :param test_var:        variable to differenciate between test and url call
         :type test_var:         boolean
+
+        main function to start graph generation
     '''
 
     # ERROR-Handling doi_array = NULL
@@ -291,10 +269,10 @@ def process_main(doi_input_list, search_height, search_depth, test_var = False):
         print("Error, search_depth of search must be positive")       
 
     
-    
+    # creates empty lists to save nodes and edges
     global nodes, edges
-    nodes = [] # create empty array for the nodes
-    edges = [] # create empty array for the edges
+    nodes = [] 
+    edges = [] 
 
     # 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(doi_input_list,search_depth, search_height, test_var)
@@ -307,14 +285,6 @@ def process_main(doi_input_list, search_height, search_depth, test_var = False):
     complete_inner_edges(test_var)
 
     # calls a skript to save nodes and edges of graph in .json file
-    output_to_json(nodes,edges)
-
-
-    # only for unit tests
-    if (test_var == True):
-        doi_nodes_list = []
-        for node in nodes:
-            doi_nodes_list.append(node.doi_url)
-        return(doi_nodes_list, edges)
+    output_to_json(nodes,edges, test_var)
 
     return(nodes,edges)

verarbeitung/Processing_unittest.py

 import unittest
+
 from Processing import process_main
+from import_from_json import input_from_json
+from update_graph import check_graph_updates
 
 class ProcessingTest(unittest.TestCase):
+     maxDiff = None
+
+
      def testCycle(self):
          nodes, edges = process_main(['doiz1'],1,1,True)
-         self.assertCountEqual(nodes, ['doiz1', 'doiz2'])
+         doi_nodes = keep_only_dois(nodes)
+         self.assertCountEqual(doi_nodes, ['doiz1', 'doiz2'])
          self.assertCountEqual(edges, [['doiz1', 'doiz2'], ['doiz2', 'doiz1']])
 
          nodes, edges = process_main(['doiz1'],2,2,True)
-         self.assertCountEqual(nodes, ['doiz1', 'doiz2'])
+         doi_nodes = keep_only_dois(nodes)
+         self.assertCountEqual(doi_nodes, ['doiz1', 'doiz2'])
          self.assertCountEqual(edges, [['doiz2', 'doiz1'], ['doiz1', 'doiz2']])
 
     #def testBigCycle(self):
@@ -19,48 +27,88 @@ class ProcessingTest(unittest.TestCase):
 
      def testEmptyDepthHeight(self):
          nodes, edges = process_main(['doi1'],0,0,True)
-         self.assertCountEqual(nodes,['doi1'])
+         doi_nodes = keep_only_dois(nodes)
+         self.assertCountEqual(doi_nodes,['doi1'])
          self.assertCountEqual(edges, [])
 
          nodes, edges = process_main(['doi1', 'doi2'],0,0,True)
-         self.assertCountEqual(nodes, ['doi1','doi2'])
+         doi_nodes = keep_only_dois(nodes)
+         self.assertCountEqual(doi_nodes, ['doi1','doi2'])
          self.assertCountEqual(edges, [['doi1', 'doi2']])
 
          nodes, edges = process_main(['doi1', 'doi2', 'doi3'],0,0,True)
-         self.assertCountEqual(nodes, ['doi1','doi2', 'doi3'])
+         doi_nodes = keep_only_dois(nodes)
+         self.assertCountEqual(doi_nodes, ['doi1','doi2', 'doi3'])
          self.assertCountEqual(edges, [['doi3', 'doi1'], ['doi1', 'doi2']])
 
 
      def testInnerEdges(self):
         nodes, edges = process_main(['doi_ie1'],1,1,True)
-        self.assertCountEqual(nodes,['doi_ie1','doi_ie2','doi_ie3'])
+        doi_nodes = keep_only_dois(nodes)
+        self.assertCountEqual(doi_nodes,['doi_ie1','doi_ie2','doi_ie3'])
         self.assertCountEqual(edges,[['doi_ie1','doi_ie2'],['doi_ie3','doi_ie1'],['doi_ie3','doi_ie2']])
      
      def testRightHeight(self):
           nodes, edges = process_main(['doi_h01'],1,0,True)
-          self.assertCountEqual(nodes,['doi_h01'])
+          doi_nodes = keep_only_dois(nodes)
+          self.assertCountEqual(doi_nodes,['doi_h01'])
           self.assertCountEqual(edges, [])
 
           nodes, edges = process_main(['doi_h02'],1,0,True)
-          self.assertCountEqual(nodes,['doi_h02','doi_h1'])
+          doi_nodes = keep_only_dois(nodes)
+          self.assertCountEqual(doi_nodes,['doi_h02','doi_h1'])
           self.assertCountEqual(edges, [['doi_h1','doi_h02']])
 
           nodes, edges = process_main(['doi_h02'],2,0,True)
-          self.assertCountEqual(nodes,['doi_h02','doi_h1','doi_h2'])
+          doi_nodes = keep_only_dois(nodes)
+          self.assertCountEqual(doi_nodes,['doi_h02','doi_h1','doi_h2'])
           self.assertCountEqual(edges, [['doi_h1','doi_h02'], ['doi_h2','doi_h1']])
 
      def testRightDepth(self):
           nodes, edges = process_main(['doi_d01'],0,1,True)
-          self.assertCountEqual(nodes,['doi_d01'])
+          doi_nodes = keep_only_dois(nodes)
+          self.assertCountEqual(doi_nodes,['doi_d01'])
           self.assertCountEqual(edges, [])
 
           nodes, edges = process_main(['doi_d02'],0,1,True)
-          self.assertCountEqual(nodes,['doi_d02','doi_d1'])
+          doi_nodes = keep_only_dois(nodes)
+          self.assertCountEqual(doi_nodes,['doi_d02','doi_d1'])
           self.assertCountEqual(edges, [['doi_d02','doi_d1']])
 
           nodes, edges = process_main(['doi_d02'],0,2,True)
-          self.assertCountEqual(nodes,['doi_d02','doi_d1','doi_d2'])
+          doi_nodes = keep_only_dois(nodes)
+          self.assertCountEqual(doi_nodes,['doi_d02','doi_d1','doi_d2'])
           self.assertCountEqual(edges, [['doi_d02','doi_d1'], ['doi_d1','doi_d2']])
 
+     def test_import_from_json(self):
+          nodes_old, edges_old = process_main(['doi_lg_1_i'],2,2,True)
+          nodes_new, edges_new = input_from_json('test_output.json')
+          self.assertCountEqual(nodes_old,nodes_new)
+          self.assertCountEqual(edges_old, edges_new)
+
+     def test_deleted_input_dois(self):
+          nodes_old_single, edges_old_single = process_main(['doi_lg_1_i'],2,2,True)
+          nodes_old_both, edges_old_both = process_main(['doi_lg_1_i','doi_lg_2_i'],2,2,True)
+          nodes_new_both, edges_new_both = input_from_json('test_output.json')
+          nodes_new_single, edges_new_single = check_graph_updates(['doi_lg_1_i'], nodes_old_both, edges_old_both, True)
+          self.assertCountEqual(nodes_old_single,nodes_new_single)
+          self.assertCountEqual(edges_old_single, edges_new_single)
+
+
+
+
+def keep_only_dois(nodes):
+     '''
+          :param nodes:  input list of nodes of type Publication
+          :type nodes:   List[Publication]
+
+          gets nodes of type pub and return only their doi
+    '''
+     doi_list = []
+     for node in nodes:
+          doi_list.append(node.doi_url)
+     return doi_list
+
+
 if __name__ == "__main__":
     unittest.main()
\ No newline at end of file

verarbeitung/get_pub_from_input.py

+# -*- coding: utf-8 -*-
+"""
+A function to return an object of Type Publication for a given doi
+
+"""
+
+__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
+sys.path.append("../")
+
+from input.interface import InputInterface as Input
+from input_test import input_test_func
+
+
+def get_pub(pub_doi, test_var):
+    #checks if it's a test and chooses appropiate function
+    if(test_var): 
+            pub = input_test_func(pub_doi) 
+
+    #checks that it isnt a test and chooses standart-input function
+    else: 
+        inter = Input()
+        try:
+            pub = inter.get_publication(pub_doi) #creates an object of class Publication
+        except ValueError:
+            return(ValueError)
+        except IndexError:
+            return(IndexError)
+        except AttributeError:
+            return(AttributeError)
+    return(pub)
\ No newline at end of file

verarbeitung/import_from_json.py

@@ -15,46 +15,19 @@ __status__ = "Production"
 
   
 import json
-#sys.path.insert(1, 'C:\Users\Malte\Git\CiS-Projekt\ci-s-projekt-verarbeitung\input')
 import sys
 sys.path.append("../")
-from input.interface import InputInterface as Input
-
-
-class Publication:
-    #def __init__(self, doi_url, title, contributors, journal, publication_date, references, citations, group):
-    def __init__(self, doi_url, title, contributors, journal, publication_date, group):
-        self.doi_url = doi_url
-        self.title = title
-        self.contributors = contributors
-        self.journal = journal
-        self.publication_date = publication_date
-        self.references = []
-        self.citations = []
-        self.group = group
-
-
-class Citation:
-    def __init__(self,doi_url, title, contributors, journal, publication_date):
-        self.doi_url = doi_url
-        self.title = title
-        self.contributors = contributors
-        self.journal = journal
-        self.publication_date = publication_date
-
-class Reference:
-    def __init__(self,doi_url, title, contributors, journal, publication_date):
-        self.doi_url = doi_url
-        self.title = title
-        self.contributors = contributors
-        self.journal = journal
-        self.publication_date = publication_date
+
+from input.publication import Publication, Citation
+
 
 
 def create_pubs_from_json(input_dict):
     '''
-    :param input_dict: dictionary read from old graph Json File
-    :type json_file: dictionary
+    :param input_dict:  dictionary read from old graph Json File
+    :type json_file:    dictionary
+
+    creates list of publication retrieved from old json file
     '''
     
     #iterates over the list of nodes
@@ -67,29 +40,24 @@ def create_pubs_from_json(input_dict):
 
 def add_ref_and_cit_to_pubs(input_dict):
     '''
-    :param input_dict: dictionary read from old graph Json File
-    :type json_file: dictionary
+    :param input_dict:  dictionary read from old graph Json File
+    :type json_file:    dictionary
+
+    adds references and citations to retrieved publication list
     '''
 
     # iterates over the list of edges
     for edge in input_dict["links"]:
         for source in list_of_nodes_py:
             for target in list_of_nodes_py:
+
+                # when correct dois found, adds then as references/citatons to publication list
                 if ((source.doi_url == edge["source"]) and (target.doi_url == edge["target"])):
-                    new_reference = Reference(target.doi_url, target.title, target.contributors, target.journal, target.publication_date)
+                    new_reference = Citation(target.doi_url, target.title, target.journal, target.contributors, "Reference")
                     source.references.append(new_reference)
 
-                    new_citation = Citation(source.doi_url, source.title, source.contributors, source.journal, source.publication_date)
+                    new_citation = Citation(source.doi_url, source.title, source.journal, source.contributors, "Citation")
                     target.citations.append(new_citation)
-            # adds reference to current node
-            # if (node.doi_url == edge["source"]):
-            #     new_reference = Reference(node.doi_url, node.title, node.contributors, node.journal, node.publication_date)
-            #     node.references.append(new_reference)
-            
-            # # adds citation to current node
-            # if (node.doi_url == edge["target"]):
-            #     new_citation = Citation(node.doi_url, node.title, node.contributors, node.journal, node.publication_date)
-            #     node.citations.append(new_citation)
         
         # adds edge to list
         list_of_edges_py.append([edge["source"],edge["target"]])
@@ -97,8 +65,10 @@ def add_ref_and_cit_to_pubs(input_dict):
 
 def input_from_json(json_file):
     '''
-    :param json_file: Json-Datei for the old graph
-    :type json_file: Json File
+    :param json_file:   Json-Datei for the old graph
+    :type json_file:    String
+
+    retrieves information from old json file to be reused for new graph construction
     '''
 
     # creates global sets for nodes and edges
@@ -117,5 +87,4 @@ def input_from_json(json_file):
     add_ref_and_cit_to_pubs(input_dict)
               
 
-    return(list_of_nodes_py, list_of_edges_py)
-
+    return(list_of_nodes_py, list_of_edges_py)
\ No newline at end of file

verarbeitung/input_test.py

 import sys
 sys.path.append("../")
 
-from input.publication import Publication
-
-
-class Publication:
-    def __init__(self, doi_url, title, contributors, journal, publication_date, references, citations, group):
-        self.doi_url = doi_url
-        self.title = title
-        self.contributors = contributors
-        self.journal = journal
-        self.publication_date = publication_date
-        if references is None:
-            self.references = []
-        else:
-            self.references = ref(references)
-        if citations is None:
-            self.citations = []
-        else: 
-            self.citations = cit(citations)
-        self.group = group
-
-
-class Citation:
-    def __init__(self,doi_url, title, contributors, journal, publication_date):
-        self.doi_url = doi_url
-        self.title = title
-        self.contributors = contributors
-        self.journal = journal
-        self.publication_date = publication_date
-
-class Reference:
-    def __init__(self,doi_url, title, contributors, journal, publication_date):
-        self.doi_url = doi_url
-        self.title = title
-        self.contributors = contributors
-        self.journal = journal
-        self.publication_date = publication_date
+from input.publication import Publication, Citation
+
 
 def input_test_func(pub_doi):
+    '''
+        :param pub_doi: pub doi to find publication in list_of_arrays
+        :type pub_doi:  String
+
+        returns the publication class for given doi
+    '''
+
     for array in list_of_arrays:
         if pub_doi == array[0]:
-            pub = Publication(array[0], array[1], array[2], array[3], array[4], array[5], array[6], array[7], array[8])
+            pub = Publication(array[0], array[1], array[2], array[3], array[4], array[5], array[6], array[7])
             return pub
 
 
 def cit(list_doi):
+    '''
+        :param list_doi list of citation dois to get their Citation Class 
+        :type list_doi: List[String]
+
+        returns a list of citations objects for given doi list
+    '''
+
     cits = []
     for doi_url in list_doi:
         for array in list_of_arrays:
@@ -54,6 +34,13 @@ def cit(list_doi):
     return cits
 
 def ref(list_doi):
+    '''
+        :param list_doi list of reference dois to get their Reference Class 
+        :type list_doi: List[String]
+
+        returns a list of reference objects for given doi list
+    '''
+
     refs = []
     for doi_url in list_doi:
         for array in list_of_arrays:
@@ -62,27 +49,57 @@ def ref(list_doi):
     return refs
 
 
-beispiel1 = ['doi1', 'title1', ['contributor1'], 'journal1', 'date1', ['doi2'], ['doi3'], '']
-beispiel2 = ['doi2', 'title2', ['contributor2'], 'journal2', 'date2', [], ['doi1'], '']
-beispiel3 = ['doi3', 'title3', ['contributor3'], 'journal3', 'date3', ['doi1'], [], '']
-
-zyklus1 = ['doiz1', 'titlez1', ['contributorz1.1', 'contributorz1.2'], 'journalz1', 'datez1', ['doiz2'], ['doiz2'], '']
-zyklus2 = ['doiz2', 'titlez2', ['contributorz2.1', 'contributorz2.2'], 'journalz2', 'datez2', ['doiz1'], ['doiz1'], '']
-
-inner_edge1 = ['doi_ie1', 'title_ie1', ['contributor_ie1.1', 'contributor_ie1.2'], 'journal_ie1', 'date_ie1', ['doi_ie2'], ['doi_ie3'], '']
-inner_edge2 = ['doi_ie2', 'title_ie2', ['contributor_ie2.1', 'contributor_ie2.2'], 'journal_ie2', 'date_ie2', [], ['doi_ie1','doi_ie3'], '']
-inner_edge3 = ['doi_ie3', 'titlez_ie3', ['contributor_ie3.1', 'contributor_ie3.2'], 'journal_ie3', 'date_ie3', ['doi_ie1','doi_ie2'], [], '']
-
-right_height01 = ['doi_h01', 'title_h01', ['contributor_h01'], 'journal_h01', 'date_h01', [], [], '']
-right_height02 = ['doi_h02', 'title_h02', ['contributor_h02'], 'journal_h02', 'date_h02', [], ['doi_h1'], '']
-right_height1 = ['doi_h1', 'title_h1', ['contributor_h1'], 'journal_h1', 'date_h1', [], ['doi_h2'], '']
-right_height2 = ['doi_h2', 'title_h2', ['contributor_h2'], 'journal_h2', 'date_h2', [], ['doi_h3'], '']
-right_height3 = ['doi_h3', 'title_h3', ['contributor_h3'], 'journal_h3', 'date_h3', [], [], '']
-
-right_depth01 = ['doi_d01', 'title_d01', ['contributor_d01'], 'journal_d01', 'date_d01', [], [], '']
-right_depth02 = ['doi_d02', 'title_d02', ['contributor_d02'], 'journal_d02', 'date_d02', ['doi_d1'], [], '']
-right_depth1 = ['doi_d1', 'title_d1', ['contributor_d1'], 'journal_d1', 'date_d1', ['doi_d2'], [], '']
-right_depth2 = ['doi_d2', 'title_d2', ['contributor_d2'], 'journal_d2', 'date_d2', ['doi_d3'], [], '']
-right_depth3 = ['doi_d3', 'title_d3', ['contributor_d3'], 'journal_d3', 'date_d3', [], [], '']
 
-list_of_arrays = [beispiel1, beispiel2, beispiel3, zyklus1, zyklus2, inner_edge1, inner_edge2, inner_edge3, right_height01, right_height02, right_height1, right_height2, right_height3, right_depth01, right_depth02, right_depth1, right_depth2, right_depth3]
+beispiel1 = ['doi1', 'title1', ['contributor1'], 'journal1', 'date1', ['subject1'], ['doi2'], ['doi3']]
+beispiel2 = ['doi2', 'title2', ['contributor2'], 'journal2', 'date2', ['subject2'], [], ['doi1']]
+beispiel3 = ['doi3', 'title3', ['contributor3'], 'journal3', 'date3', ['subject3'], ['doi1'], []]
+
+zyklus1 = ['doiz1', 'titlez1', ['contributorz1.1', 'contributorz1.2'], 'journalz1', 'datez1', ['subjectz1'], ['doiz2'], ['doiz2']]
+zyklus2 = ['doiz2', 'titlez2', ['contributorz2.1', 'contributorz2.2'], 'journalz2', 'datez2', ['subjectz1'], ['doiz1'], ['doiz1']]
+
+inner_edge1 = ['doi_ie1', 'title_ie1', ['contributor_ie1.1', 'contributor_ie1.2'], 'journal_ie1', 'date_ie1', ['subject_ie1'], ['doi_ie2'], ['doi_ie3']]
+inner_edge2 = ['doi_ie2', 'title_ie2', ['contributor_ie2.1', 'contributor_ie2.2'], 'journal_ie2', 'date_ie2', ['subject_ie2'], [], ['doi_ie1','doi_ie3']]
+inner_edge3 = ['doi_ie3', 'titlez_ie3', ['contributor_ie3.1', 'contributor_ie3.2'], 'journal_ie3', 'date_ie3', ['subject_ie3'], ['doi_ie1','doi_ie2'], []]
+
+right_height01 = ['doi_h01', 'title_h01', ['contributor_h01'], 'journal_h01', 'date_h01', ['subject_h01'], [], []]
+right_height02 = ['doi_h02', 'title_h02', ['contributor_h02'], 'journal_h02', 'date_h02', ['subject_h02'], [], ['doi_h1']]
+right_height1 = ['doi_h1', 'title_h1', ['contributor_h1'], 'journal_h1', 'date_h1', ['subject_h1'], [], ['doi_h2']]
+right_height2 = ['doi_h2', 'title_h2', ['contributor_h2'], 'journal_h2', 'date_h2', ['subject_h2'], [], ['doi_h3']]
+right_height3 = ['doi_h3', 'title_h3', ['contributor_h3'], 'journal_h3', 'date_h3', ['subject_h3'], [], []]
+
+right_depth01 = ['doi_d01', 'title_d01', ['contributor_d01'], 'journal_d01', 'date_d01', ['subject_d01'], [], []]
+right_depth02 = ['doi_d02', 'title_d02', ['contributor_d02'], 'journal_d02', 'date_d02', ['subject_d01'], ['doi_d1'], []]
+right_depth1 = ['doi_d1', 'title_d1', ['contributor_d1'], 'journal_d1', 'date_d1', ['subject_d1'], ['doi_d2'], []]
+right_depth2 = ['doi_d2', 'title_d2', ['contributor_d2'], 'journal_d2', 'date_d2', ['subject_d2'], ['doi_d3'], []]
+right_depth3 = ['doi_d3', 'title_d3', ['contributor_d3'], 'journal_d3', 'date_d3', ['subject_d3'], [], []]
+
+large_graph_1_h21 = ['doi_lg_1_h21', 'title_lg_1_h21', ['contributor_lg_1_h21'], 'journal_lg_1_h21', 'date_lg_1_h21', ['subject_lg_1_h21'], ['doi_lg_1_h11'], []]
+large_graph_1_h22 = ['doi_lg_1_h22', 'title_lg_1_h22', ['contributor_lg_1_h22'], 'journal_lg_1_h22', 'date_lg_1_h22', ['subject_lg_1_h22'], ['doi_lg_1_h11','doi_lg_1_h12'], []]
+large_graph_1_h23 = ['doi_lg_1_h23', 'title_lg_1_h23', ['contributor_lg_1_h23'], 'journal_lg_1_h23', 'date_lg_1_h23', ['subject_lg_1_h23'], ['doi_lg_1_h12'], []]
+large_graph_1_h11 = ['doi_lg_1_h11', 'title_lg_1_h11', ['contributor_lg_1_h11'], 'journal_lg_1_h11', 'date_lg_1_h11', ['subject_lg_1_h11'], ['doi_lg_1_h12','doi_lg_1_i'], ['doi_lg_1_h21','doi_lg_1_h22']]
+large_graph_1_h12 = ['doi_lg_1_h12', 'title_lg_1_h12', ['contributor_lg_1_h12'], 'journal_lg_1_h12', 'date_lg_1_h12', ['subject_lg_1_h12'], ['doi_lg_1_i','doi_lg_1_d12'], ['doi_lg_1_h22','doi_lg_1_h23']]
+large_graph_1_i =   ['doi_lg_1_i'  , 'title_lg_1_i'  , ['contributor_lg_1_i']  , 'journal_lg_1_i'  , 'date_lg_1_i'  , ['subject_lg_1_i']  , ['doi_lg_1_d11','doi_lg_1_d12'], ['doi_lg_1_h11','doi_lg_1_h12']]
+large_graph_1_d11 = ['doi_lg_1_d11', 'title_lg_1_d11', ['contributor_lg_1_d11'], 'journal_lg_1_d11', 'date_lg_1_d11', ['subject_lg_1_d11'], ['doi_lg_1_d21','doi_lg_1_d22'], ['doi_lg_1_i']]
+large_graph_1_d12 = ['doi_lg_1_d12', 'title_lg_1_d12', ['contributor_lg_1_d12'], 'journal_lg_1_d12', 'date_lg_1_d12', ['subject_lg_1_d12'], ['doi_lg_1_d23'], ['doi_lg_1_h12','doi_lg_1_i']]
+large_graph_1_d21 = ['doi_lg_1_d21', 'title_lg_1_d21', ['contributor_lg_1_d21'], 'journal_lg_1_d21', 'date_lg_1_d21', ['subject_lg_1_d21'], ['doi_lg_1_d22'], ['doi_lg_1_d11','doi_lg_1_d22']]
+large_graph_1_d22 = ['doi_lg_1_d22', 'title_lg_1_d22', ['contributor_lg_1_d22'], 'journal_lg_1_d22', 'date_lg_1_d22', ['subject_lg_1_d22'], ['doi_lg_1_d21'], ['doi_lg_1_d11','doi_lg_1_d21']]
+large_graph_1_d23 = ['doi_lg_1_d23', 'title_lg_1_d23', ['contributor_lg_1_d23'], 'journal_lg_1_d23', 'date_lg_1_d23', ['subject_lg_1_d23'], [], ['doi_lg_1_d12']]
+
+large_graph_2_h21 = ['doi_lg_2_h21', 'title_lg_2_h21', ['contributor_lg_2_h21'], 'journal_lg_2_h21', 'date_lg_2_h21', ['subject_lg_2_h21'], ['doi_lg_2_h11'], []]
+large_graph_2_h22 = ['doi_lg_2_h22', 'title_lg_2_h22', ['contributor_lg_2_h22'], 'journal_lg_2_h22', 'date_lg_2_h22', ['subject_lg_2_h22'], ['doi_lg_2_h11'], []]
+large_graph_2_h23 = ['doi_lg_2_h23', 'title_lg_2_h23', ['contributor_lg_2_h23'], 'journal_lg_2_h23', 'date_lg_2_h23', ['subject_lg_2_h23'], ['doi_lg_2_h12','doi_lg_2_h24'], ['doi_lg_2_h24']]
+large_graph_2_h24 = ['doi_lg_2_h24', 'title_lg_2_h24', ['contributor_lg_2_h24'], 'journal_lg_2_h24', 'date_lg_2_h24', ['subject_lg_2_h24'], ['doi_lg_2_h12','doi_lg_2_h23','doi_lg_2_d12'], ['doi_lg_2_h23']]
+large_graph_2_h11 = ['doi_lg_2_h11', 'title_lg_2_h11', ['contributor_lg_2_h11'], 'journal_lg_2_h11', 'date_lg_2_h11', ['subject_lg_2_h11'], ['doi_lg_2_i'], ['doi_lg_2_h21','doi_lg_2_h22']]
+large_graph_2_h12 = ['doi_lg_2_h12', 'title_lg_2_h12', ['contributor_lg_2_h12'], 'journal_lg_2_h12', 'date_lg_2_h12', ['subject_lg_2_h12'], ['doi_lg_2_i'], ['doi_lg_2_h23','doi_lg_2_h24']]
+large_graph_2_i =   ['doi_lg_2_i'  , 'title_lg_2_i'  , ['contributor_lg_2_i']  , 'journal_lg_2_i'  , 'date_lg_2_i'  , ['subject_lg_2_i']  , ['doi_lg_2_d11','doi_lg_2_d12'], ['doi_lg_2_h11','doi_lg_2_h12']]
+large_graph_2_d11 = ['doi_lg_2_d11', 'title_lg_2_d11', ['contributor_lg_2_d11'], 'journal_lg_2_d11', 'date_lg_2_d11', ['subject_lg_2_d11'], [], ['doi_lg_2_i']]
+large_graph_2_d12 = ['doi_lg_2_d12', 'title_lg_2_d12', ['contributor_lg_2_d12'], 'journal_lg_2_d12', 'date_lg_2_d12', ['subject_lg_2_d12'], ['doi_lg_2_d21','doi_lg_2_d22'], ['doi_lg_2_h24','doi_lg_2_i']]
+large_graph_2_d21 = ['doi_lg_2_d21', 'title_lg_2_d21', ['contributor_lg_2_d21'], 'journal_lg_2_d21', 'date_lg_2_d21', ['subject_lg_2_d21'], [], ['doi_lg_2_d12']]
+large_graph_2_d22 = ['doi_lg_2_d22', 'title_lg_2_d22', ['contributor_lg_2_d22'], 'journal_lg_2_d22', 'date_lg_2_d22', ['subject_lg_2_d22'], [], ['doi_lg_2_d12']]
+large_graph_2_d23 = ['doi_lg_2_d23', 'title_lg_2_d23', ['contributor_lg_2_d23'], 'journal_lg_2_d23', 'date_lg_2_d23', ['subject_lg_2_d23'], [], ['doi_lg_2_d12']]
+
+list_of_arrays =    [beispiel1, beispiel2, beispiel3, zyklus1, zyklus2, inner_edge1, inner_edge2, inner_edge3, 
+                    right_height01, right_height02, right_height1, right_height2, right_height3, right_depth01, right_depth02, right_depth1, right_depth2, right_depth3,
+                    large_graph_1_h21, large_graph_1_h22, large_graph_1_h23, large_graph_1_h11, large_graph_1_h12, large_graph_1_i, large_graph_1_d11, large_graph_1_d12,
+                    large_graph_1_d21, large_graph_1_d22, large_graph_1_d23, large_graph_2_h21, large_graph_2_h22, large_graph_2_h23, large_graph_2_h24, large_graph_2_h11, large_graph_2_h12, 
+                    large_graph_2_i, large_graph_2_d11, large_graph_2_d12, large_graph_2_d21, large_graph_2_d22, large_graph_2_d23]

verarbeitung/json_demo.py

@@ -12,11 +12,11 @@ def format_nodes(V):
     list_of_node_dicts = list()
     for node in V:
         new_dict = dict()
+        new_dict["doi"] = node.doi_url
         new_dict["name"] = node.title
         new_dict["author"] = node.contributors
         new_dict["year"] = node.publication_date
         new_dict["journal"] = node.journal
-        new_dict["doi"] = node.doi_url
         new_dict["group"] = node.group
         new_dict["citations"] = len(node.citations)
         list_of_node_dicts.append(new_dict)
@@ -34,14 +34,18 @@ def format_edges(E):
     return list_of_edge_dicts
    
 # combine the lists of nodes and edges to a dictionary and saves it to a json file
-def output_to_json(V,E):
+def output_to_json(V,E, test_var):
     dict_of_all = dict()
     list_of_node_dicts = format_nodes(V)
     list_of_edge_dicts = format_edges(E)
     dict_of_all["nodes"] = list_of_node_dicts
     dict_of_all["links"] = list_of_edge_dicts
-    with open('json_text.json','w') as outfile:
-        json.dump(dict_of_all, outfile)
+    if (test_var):
+        with open('test_output.json','w') as outfile:
+            json.dump(dict_of_all, outfile)
+    else:
+        with open('json_text.json','w') as outfile:
+            json.dump(dict_of_all, outfile)
   
 #knoten = ["doi1", "doi2", "doi3"]
 #kanten = [[1,2],[3,4],[5,6]]

verarbeitung/json_text.json

-{"nodes": [{"name": "title_h02", "author": ["contributor_h02"], "year": "date_h02", "journal": "journal_h02", "doi": "doi_h02", "group": "input", "citations": 1}, {"name": "title_h1", "author": ["contributor_h1"], "year": "date_h1", "journal": "journal_h1", "doi": "doi_h1", "group": "height", "citations": 1}, {"name": "title_h2", "author": ["contributor_h2"], "year": "date_h2", "journal": "journal_h2", "doi": "doi_h2", "group": "height", "citations": 1}], "links": [{"source": "doi_h1", "target": "doi_h02"}, {"source": "doi_h2", "target": "doi_h1"}]}
\ No newline at end of file
+{"nodes": [{"doi": "https://doi.org/10.1021/acs.jcim.9b00249", "name": "Comparing Molecular Patterns Using the Example of SMARTS: Applications and Filter Collection Analysis", "author": ["Emanuel S. R. Ehmki", "Robert Schmidt", "Farina Ohm", "Matthias Rarey"], "year": "May 24, 2019", "journal": "Journal of Chemical Information and Modeling", "group": "input", "citations": 5}], "links": []}
\ No newline at end of file

verarbeitung/print_graph_test.py

@@ -51,6 +51,14 @@ def print_extended_graph(nodes, edges):
     print(len(edges))
     print(" ")
 
+def print_simple(nodes, edges):
+    # for node in nodes:
+    #     print(node)
+    # for edge in edges:
+    #     print(edge)
+    print(len(nodes))
+    print(len(edges))
+    print(" ")
 
 # program test with some random dois
 def try_known_publications():
@@ -79,15 +87,15 @@ def try_known_publications():
 def try_delete_nodes():
     doi_list = []
     doi_list.append('https://pubs.acs.org/doi/10.1021/acs.jcim.9b00249')
-    doi_list.append('https://pubs.acs.org/doi/10.1021/acs.jcim.1c00203')
+    #doi_list.append('https://pubs.acs.org/doi/10.1021/acs.jcim.1c00203')
     nodes, edges = process_main(doi_list,1,1)
-    print_graph(nodes, edges)
+    #print_simple(nodes, edges)
 
-    list_of_nodes_py, list_of_edges_py = input_from_json('json_text.json')
-    doi_list = []
-    doi_list.append('https://pubs.acs.org/doi/10.1021/acs.jcim.9b00249')
-    valid_nodes, valid_edges = check_graph_updates(doi_list, list_of_nodes_py, list_of_edges_py)
-    print_graph(valid_nodes, valid_edges)
+    # list_of_nodes_py, list_of_edges_py = input_from_json('json_text.json')
+    # doi_list = []
+    # doi_list.append('https://pubs.acs.org/doi/10.1021/acs.jcim.9b00249')
+    # valid_nodes, valid_edges = check_graph_updates(doi_list, list_of_nodes_py, list_of_edges_py)
+    # print_simple(valid_nodes, valid_edges)
 
 def try_import():
     nodes, edges = input_from_json('json_text.json')

verarbeitung/test_output.json

+{"nodes": [{"doi": "doi_lg_1_i", "name": "title_lg_1_i", "author": ["contributor_lg_1_i"], "year": "date_lg_1_i", "journal": "journal_lg_1_i", "group": "input", "citations": 2}, {"doi": "doi_lg_1_d11", "name": "title_lg_1_d11", "author": ["contributor_lg_1_d11"], "year": "date_lg_1_d11", "journal": "journal_lg_1_d11", "group": "depth", "citations": 1}, {"doi": "doi_lg_1_d12", "name": "title_lg_1_d12", "author": ["contributor_lg_1_d12"], "year": "date_lg_1_d12", "journal": "journal_lg_1_d12", "group": "depth", "citations": 2}, {"doi": "doi_lg_1_h11", "name": "title_lg_1_h11", "author": ["contributor_lg_1_h11"], "year": "date_lg_1_h11", "journal": "journal_lg_1_h11", "group": "height", "citations": 2}, {"doi": "doi_lg_1_h12", "name": "title_lg_1_h12", "author": ["contributor_lg_1_h12"], "year": "date_lg_1_h12", "journal": "journal_lg_1_h12", "group": "height", "citations": 2}, {"doi": "doi_lg_1_h21", "name": "title_lg_1_h21", "author": ["contributor_lg_1_h21"], "year": "date_lg_1_h21", "journal": "journal_lg_1_h21", "group": "height", "citations": 0}, {"doi": "doi_lg_1_h22", "name": "title_lg_1_h22", "author": ["contributor_lg_1_h22"], "year": "date_lg_1_h22", "journal": "journal_lg_1_h22", "group": "height", "citations": 0}, {"doi": "doi_lg_1_h23", "name": "title_lg_1_h23", "author": ["contributor_lg_1_h23"], "year": "date_lg_1_h23", "journal": "journal_lg_1_h23", "group": "height", "citations": 0}, {"doi": "doi_lg_1_d21", "name": "title_lg_1_d21", "author": ["contributor_lg_1_d21"], "year": "date_lg_1_d21", "journal": "journal_lg_1_d21", "group": "depth", "citations": 2}, {"doi": "doi_lg_1_d22", "name": "title_lg_1_d22", "author": ["contributor_lg_1_d22"], "year": "date_lg_1_d22", "journal": "journal_lg_1_d22", "group": "depth", "citations": 2}, {"doi": "doi_lg_1_d23", "name": "title_lg_1_d23", "author": ["contributor_lg_1_d23"], "year": "date_lg_1_d23", "journal": "journal_lg_1_d23", "group": "depth", "citations": 1}], "links": [{"source": "doi_lg_1_i", "target": "doi_lg_1_d11"}, {"source": "doi_lg_1_i", "target": "doi_lg_1_d12"}, {"source": "doi_lg_1_h11", "target": "doi_lg_1_i"}, {"source": "doi_lg_1_h12", "target": "doi_lg_1_i"}, {"source": "doi_lg_1_h21", "target": "doi_lg_1_h11"}, {"source": "doi_lg_1_h22", "target": "doi_lg_1_h11"}, {"source": "doi_lg_1_h22", "target": "doi_lg_1_h12"}, {"source": "doi_lg_1_h23", "target": "doi_lg_1_h12"}, {"source": "doi_lg_1_d11", "target": "doi_lg_1_d21"}, {"source": "doi_lg_1_d11", "target": "doi_lg_1_d22"}, {"source": "doi_lg_1_d21", "target": "doi_lg_1_d22"}, {"source": "doi_lg_1_d22", "target": "doi_lg_1_d21"}, {"source": "doi_lg_1_d12", "target": "doi_lg_1_d23"}, {"source": "doi_lg_1_h12", "target": "doi_lg_1_d12"}, {"source": "doi_lg_1_h11", "target": "doi_lg_1_h12"}]}
\ No newline at end of file

verarbeitung/update_graph.py

@@ -13,17 +13,27 @@ __status__ = "Production"
 #__version__ = ""
 #__maintainer__ = ""
 
+
 import sys  
 from pathlib import Path
-#sys.path.insert(1, 'C:\Users\Malte\Git\CiS-Projekt\ci-s-projekt-verarbeitung\input')
+from os import error
 sys.path.append("../")
-from input.interface import InputInterface as Input
-from input_test import input_test_func
+
+from input.publication import Publication
+from get_pub_from_input import get_pub
 from Knoten_Vergleich import doi_listen_vergleichen
-from Kanten_Vergleich import back_to_valid_edges
+from update_graph_del import delete_nodes_and_edges
 
 
 def get_old_input_dois(old_obj_input_list):
+    '''
+        :param old_obj_input_list:  list of publications retrieved from old json file
+        :type old_obj_input_list:   List[Publication]
+
+        function to return pub dois for old publications of group input retrieved from json file
+    '''
+
+    # new list to save doi_url for each old publication of group input
     old_input_dois = []
     for pub in old_obj_input_list:
         if (pub.group == "input"):
@@ -31,55 +41,65 @@ def get_old_input_dois(old_obj_input_list):
     return old_input_dois
 
 def get_new_input_dois(new_input, test_var):
-    doi_input_list = []
+    '''
+        :param new_input:   input list of doi from UI
+        :type new_input:    list of strings
+
+        :param test_var:    variable to differenciate between test and url call
+        :type test_var:     boolean
+
+        function to return pub dois for input urls
+    '''
+
+    # new list to save doi_url for each new input url
+    new_input_dois = []
     for new_node in new_input:
-        if(test_var):
-            pub = input_test_func(new_node)
-        else:
-            #print(pub_doi)
-            inter = Input()
-            try:
-                pub = inter.get_publication(new_node)
-            except ValueError:
-                continue
-            except IndexError:
-                continue
-        doi_input_list.append(pub.doi_url)
-    return doi_input_list
-
-def delete_ref_nodes_rec(pub):#, old_obj_list):
-    for reference in pub.references:
-        for ref_pub in processed_input_list:
-            if (ref_pub.doi_url == reference.doi_url):
-                delete_ref_nodes_rec(ref_pub)
-    if (pub.group != "input"):
-        processed_input_list.remove(pub)
-
-def delete_cit_nodes_rec(pub):
-    for citation in pub.citations:
-        for cit_pub in processed_input_list:
-            if (cit_pub.doi_url == citation.doi_url):
-                delete_cit_nodes_rec(cit_pub)
-    if (pub.group != "input"):
-        processed_input_list.remove(pub)
+        # retrieves information and adds to new list if successful 
+        pub = get_pub(new_node, test_var)
+        if (type(pub) != Publication):
+            print(pub)
+            continue
+
+        new_input_dois.append(pub.doi_url)
+    return(new_input_dois)
 
 
 def check_graph_updates(new_doi_input_list, old_obj_input_list, old_edges_list, test_var = False):
+    '''
+        :param new_doi_input_list:  input list of doi from UI
+        :type new_doi_input_list:   list of strings
+
+        :param old_obj_input_list:  list of publications retrieved from old json file
+        :type old_obj_input_list:   List[Publication]
+
+        :param old_edges_list:      list of links between publications retrieved from old json file
+        :type old_edges_list:       List[List[String,String]]
+
+        :param test_var:            variable to differenciate between test and url call
+        :type test_var:             boolean
+
+        function to compare old and new input, start node/edge removal and to return updated sets of nodes and edges
+    '''
+
+    # one global list to save the process of removing unneeded publications and one to save valid edges
     global processed_input_list, valid_edges
-    processed_input_list = old_obj_input_list
+    processed_input_list = old_obj_input_list.copy()
     valid_edges = []
 
+    # save the return values of global lists
+    processed_input_list_del = []
+    valid_edges_del = []
+
+    # get dois from lists to compare for differences
     old_doi_input_list = get_old_input_dois(old_obj_input_list)
     new_doi_input_list = get_new_input_dois(new_doi_input_list, test_var)
+
+    # retrieve which publications are already known, removed, inserted
     common_nodes, inserted_nodes, deleted_nodes = doi_listen_vergleichen(old_doi_input_list, new_doi_input_list)
-    if (len(inserted_nodes) == 0):
-        for del_node in deleted_nodes:
-            for pub in processed_input_list:
-                if (del_node == pub.doi_url):
-                    delete_ref_nodes_rec(pub)#, processed_input_list)
-                    delete_cit_nodes_rec(pub)#, processed_input_list)
-                    processed_input_list.remove(pub)
-        valid_edges = back_to_valid_edges(old_edges_list, processed_input_list)
+
+    # deletes publications and edges from node_list if publications can no longer be reached
+    if (len(deleted_nodes) > 0):
+        processed_input_list_del, valid_edges_del = delete_nodes_and_edges(processed_input_list, deleted_nodes, old_doi_input_list, old_edges_list)
 
 
-    return(processed_input_list, valid_edges) 
+    return(processed_input_list_del, valid_edges_del) 

verarbeitung/update_graph_del.py

+# -*- coding: utf-8 -*-
+"""
+Functions to remove publications/links from nodes/edges list, if they can no longer be reached
+
+"""
+
+__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
+sys.path.append("../")
+
+from input.interface import InputInterface as Input
+from Kanten_Vergleich import back_to_valid_edges
+
+
+def delete_ref_nodes_rec(pub):
+    '''
+    :param pub: pub go get deleted after recursive call
+    :type pub:  Publication
+    
+    function that removes nodes of group "height", if they aren't reachable from input nodes
+    '''
+    for reference in pub.references:
+        for ref_pub in processed_list:
+            if (ref_pub.doi_url == reference):
+                
+                # to find a cyclus and avoid recursion error
+                if (reference not in pub.citations):
+                    delete_ref_nodes_rec(ref_pub)
+
+    # removes publication from list after recursion and if it's not of group input
+    if (pub.group != "input"):
+        processed_list.remove(pub)
+
+
+def delete_cit_nodes_rec(pub):
+    '''
+    :param pub: publication to be removed after recursive call
+    :type pub:  Publication
+    
+    function that removes publications of group "depth" from input_list, if they aren't reachable from input nodes
+    '''
+    for citation in pub.citations:
+        for cit_pub in processed_list:
+            if (cit_pub.doi_url == citation):
+
+                # to find a cyclus and avoid recursion error
+                if (citation not in pub.references):
+                    delete_cit_nodes_rec(cit_pub)
+
+    # removes publication from list after recursion and if it's not of group input               
+    if (pub.group != "input"):
+        processed_list.remove(pub)
+
+
+def delete_nodes_and_edges(input_list, deleted_nodes, old_doi_input_list, old_edges_list):
+    '''
+    :param input_list:      list of publications to get reduced
+    :type input_list:       List[Publication]
+
+    :param deleted_nodes:       list of input dois which are not in new call
+    :type deleted_nodes:        List[String]
+
+    :param old_doi_input_list:  list of input dois from old call
+    :type old_doi_input_list:   List[String]
+
+    :param old_edges_list:      list of links between publications from old call
+    :type old_edges_list:       List[List[String,String]]
+    
+    function to start recursive node removal for references and citations and to return edge list to valid state
+    '''
+
+    # global list to save the process of removing unneeded publications
+    global processed_list
+    processed_list = input_list.copy()
+
+    for del_node in deleted_nodes:
+            for pub in processed_list:
+                if (del_node == pub.doi_url):
+
+                    # checks for every reference if it is citet more than once. If not it calls deletion function
+                    for reference in pub.references:
+                        only_reference = True
+                        for ref_cit in processed_list:
+                            if (reference == ref_cit.doi_url):
+                                for citation in ref_cit.citations:
+                                    if ((citation in old_doi_input_list) and (citation != del_node)):
+                                        only_reference = False
+                                        break
+                            if (only_reference == False):
+                                break
+                        if (only_reference):
+                            delete_ref_nodes_rec(pub)
+
+                    # checks for every citation if it cites more than once. If not it calls deletion function
+                    for citation in pub.citations:
+                        only_reference = True
+                        for cit_ref in processed_list:
+                            if (citation == cit_ref.doi_url):
+                                for reference in cit_ref.references:
+                                    if ((reference in old_doi_input_list) and (reference != del_node)):
+                                        only_reference = False
+                                        break
+                            if (only_reference == False):
+                                break
+                        if (only_reference):
+                            delete_cit_nodes_rec(pub)
+
+                    # removes publication of type input after start of recursive call to both directions
+                    processed_list.remove(pub)
+
+    valid_edges = back_to_valid_edges(old_edges_list, processed_list)
+    return(processed_list, valid_edges)
\ No newline at end of file