Merge branch 'main' into 'output'

please

See merge request bax9187/projekt-cis-biochemie-2021-22!6

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 verarbeitung.test.input_test import input_test_func
+
+
+def get_pub(pub_doi, test_var):
+    '''
+        :param pub_doi:  input doi to get Publication object for
+        :type pub_doi:   String
+
+        :param test_var:        variable to differenciate between test and url call
+        :type test_var:         boolean
+
+        function to return an object of type Publication for given input doi depending on whether its a test or url doi
+    '''
+    #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 AttributeError:
+            pub = inter.get_publication(pub_doi)
+        except ValueError:
+            return(ValueError)
+        except IndexError:
+            return(IndexError)
+    return(pub)
\ No newline at end of file

verarbeitung/input_test.py

-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
-
-def input_test_func(pub_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])
-            return pub
-
-
-def cit(list_doi):
-    cits = []
-    for doi_url in list_doi:
-        for array in list_of_arrays:
-            if doi_url == array[0]:
-                cits.append(Citation(array[0], array[1], array[2], array[3], array[4]))
-    return cits
-
-def ref(list_doi):
-    refs = []
-    for doi_url in list_doi:
-        for array in list_of_arrays:
-            if doi_url == array[0]:
-                refs.append(Citation(array[0], array[1], array[2], array[3], array[4]))
-    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]

verarbeitung/new_height.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", "depth": 0, "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": "Reference", "depth": -1, "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": "Reference", "depth": -1, "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": "Citedby", "depth": 1, "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": "Citedby", "depth": 1, "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": "Citedby", "depth": 2, "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": "Citedby", "depth": 2, "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": "Citedby", "depth": 2, "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": "Reference", "depth": -2, "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": "Reference", "depth": -2, "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": "Reference", "depth": -2, "citations": 2}], "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"}]}
\ No newline at end of file

verarbeitung/process_main.py

+# -*- coding: utf-8 -*-
+"""
+main function to call to generate 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 verarbeitung.construct_new_graph.export_to_json import output_to_json
+from verarbeitung.construct_new_graph.initialize_graph import init_graph_construction
+from verarbeitung.update_graph.update_graph import update_graph
+
+def Processing(url_list, search_depth, search_height, json_file = 'json_text.json'):
+    '''
+        :param url_list:        list of urls to construct publication graph for
+        :type url_list:         List[String]
+        
+        :param search_depth:    maximum depth to search for references
+        :type search_depth:     int
+
+        :param search_height:   maximum height to search for citations
+        :type search_height:    int
+
+        :param json_file:       file to export graph to
+        :type json_file:        String
+
+        main function to construct new or updated publication graphs
+    '''
+
+    # updates graph if json file is known in directory otherwise starts new graph construction
+    try:
+        with open(json_file) as f:
+            nodes, edges = update_graph(url_list, json_file, search_depth, search_height)
+            
+    except IOError:
+        nodes, edges = init_graph_construction(url_list, search_depth, search_height)
+    
+    # exports graph to given json file name
+    output_to_json(nodes, edges, json_file)
+    
\ No newline at end of file

verarbeitung/start_script.py

+import sys
+from pathlib import Path
+from verarbeitung.process_main import Processing
+from verarbeitung.dev_files.print_graph_test import try_known_publications, try_delete_nodes
+
+
+doi_list = []
+doi_list.append('https://pubs.acs.org/doi/10.1021/acs.jcim.9b00249')
+#doi_list.append('https://doi.org/10.1021/acs.jcim.9b00249')
+doi_list.append('https://pubs.acs.org/doi/10.1021/acs.jcim.1c00203')
+Processing(doi_list, 2, 2, 'test.json')
\ No newline at end of file

verarbeitung/test/README.md

+# Projekt CiS-Projekt 2021/22
+
+Directory to contain unittests for construction and update of publication graph
+
+## Files in directory
+
+input_test.py 
+
+- 	Immitiert die Arbeit der Input Gruppe auf eine sehr einfache Weise.
+	Beispielhafte Informationen werden aus Strings herausgelesen und als Klassenobjekt gespeichert.
+
+construct_graph_unittest.py 
+
+- 	Führt diverse Tests zur Konstruktion des Graphen ohne Vorkenntnisse mit eigenen Beispielen und 
+	unserer Input_test Funktion aus.
+
+update_graph_unittest.py
+
+-	Führt diverse Tests zum Updaten eines alten Graphs mit aktualisierter Input Liste mit eigenen 
+	Beispielen und unserer Input_test Funktion aus.
+
+## Authors
+- Donna Löding
+- Alina Molkentin
+- Xinyi Tang
+- Judith Große
+- Malte Schokolowski
\ No newline at end of file

verarbeitung/test/construct_graph_unittest.py

+import unittest
+
+import sys  
+from pathlib import Path
+sys.path.append("../")
+
+from verarbeitung.construct_new_graph.initialize_graph import init_graph_construction
+
+class ConstructionTest(unittest.TestCase):
+     maxDiff = None
+
+
+     def testCycle(self):
+         nodes, edges = init_graph_construction(['doiz1'],1,1,True)
+         doi_nodes = keep_only_dois(nodes)
+         self.assertCountEqual(doi_nodes, ['doiz1', 'doiz2'])
+         self.assertCountEqual(edges, [['doiz1', 'doiz2'], ['doiz2', 'doiz1']])
+
+         nodes, edges = init_graph_construction(['doiz1'],2,2,True)
+         doi_nodes = keep_only_dois(nodes)
+         self.assertCountEqual(doi_nodes, ['doiz1', 'doiz2'])
+         self.assertCountEqual(edges, [['doiz2', 'doiz1'], ['doiz1', 'doiz2']])
+
+    #def testBigCycle(self):
+
+    #def testEmptyHeight(self):
+
+    #def testEmptyDepth(self):
+
+     def testEmptyDepthHeight(self):
+         nodes, edges = init_graph_construction(['doi1'],0,0,True)
+         doi_nodes = keep_only_dois(nodes)
+         self.assertCountEqual(doi_nodes,['doi1'])
+         self.assertCountEqual(edges, [])
+
+         nodes, edges = init_graph_construction(['doi1', 'doi2'],0,0,True)
+         doi_nodes = keep_only_dois(nodes)
+         self.assertCountEqual(doi_nodes, ['doi1','doi2'])
+         self.assertCountEqual(edges, [['doi1', 'doi2']])
+
+         nodes, edges = init_graph_construction(['doi1', 'doi2', 'doi3'],0,0,True)
+         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 = init_graph_construction(['doi_ie1'],1,1,True)
+        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 = init_graph_construction(['doi_h01'],1,0,True)
+          doi_nodes = keep_only_dois(nodes)
+          self.assertCountEqual(doi_nodes,['doi_h01'])
+          self.assertCountEqual(edges, [])
+
+          nodes, edges = init_graph_construction(['doi_h02'],1,0,True)
+          doi_nodes = keep_only_dois(nodes)
+          self.assertCountEqual(doi_nodes,['doi_h02','doi_h1'])
+          self.assertCountEqual(edges, [['doi_h1','doi_h02']])
+
+          nodes, edges = init_graph_construction(['doi_h02'],2,0,True)
+          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 = init_graph_construction(['doi_d01'],0,1,True)
+          doi_nodes = keep_only_dois(nodes)
+          self.assertCountEqual(doi_nodes,['doi_d01'])
+          self.assertCountEqual(edges, [])
+
+          nodes, edges = init_graph_construction(['doi_d02'],0,1,True)
+          doi_nodes = keep_only_dois(nodes)
+          self.assertCountEqual(doi_nodes,['doi_d02','doi_d1'])
+          self.assertCountEqual(edges, [['doi_d02','doi_d1']])
+
+          nodes, edges = init_graph_construction(['doi_d02'],0,2,True)
+          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 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/test/input_test.py

+import sys
+sys.path.append("../")
+
+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], [], [])
+            pub.citations = cit(array[7], "Citation")
+            pub.references = cit(array[6], "Reference")
+            return pub
+
+
+def cit(list_doi, cit_type):
+    '''
+        :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:
+            if doi_url == array[0]:
+                cits.append(Citation(array[0], array[1], array[2], array[3], cit_type))
+    return cits
+
+
+
+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','doi_cg_i'], []]
+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_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','doi_cg_d11']]
+
+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_cg_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','doi_cg_i','doi_lg_2_h11']]
+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','doi_lg_2_d21'], ['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_d22','doi_lg_2_d23','doi_lg_2_d24'], ['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_d11']]
+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']]
+large_graph_2_d24 = ['doi_lg_2_d24', 'title_lg_2_d24', ['contributor_lg_2_d24'], 'journal_lg_2_d24', 'date_lg_2_d24', ['subject_lg_2_d24'], [], ['doi_lg_2_d12']]
+
+crossed_graph_h21 = ['doi_cg_h21', 'title_cg_h21', ['contributor_cg_h21'], 'journal_cg_h21', 'date_cg_h21', ['subject_cg_h21'], ['doi_cg_h11'], []]
+crossed_graph_h22 = ['doi_cg_h22', 'title_cg_h22', ['contributor_cg_h22'], 'journal_cg_h22', 'date_cg_h22', ['subject_cg_h22'], ['doi_cg_h11'], []]
+crossed_graph_h11 = ['doi_cg_h11', 'title_cg_h11', ['contributor_cg_h11'], 'journal_cg_h11', 'date_cg_h11', ['subject_cg_h11'], ['doi_cg_i'], ['doi_cg_h21','doi_cg_h22']]
+crossed_graph_i =   ['doi_cg_i', 'title_cg_i', ['contributor_cg_i'], 'journal_cg_i', 'date_cg_i', ['subject_cg_i'], ['doi_lg_2_i','doi_cg_d11','doi_cg_d12'], ['doi_lg_1_h23','doi_cg_h11','doi_lg_2_h11']]
+crossed_graph_d11 = ['doi_cg_d11', 'title_cg_d11', ['contributor_cg_d11'], 'journal_cg_d11', 'date_cg_d11', ['subject_cg_d11'], ['doi_lg_1_d23','doi_cg_d21'], ['doi_cg_i']]
+crossed_graph_d12 = ['doi_cg_d12', 'title_cg_d12', ['contributor_cg_d12'], 'journal_cg_d12', 'date_cg_d12', ['subject_cg_d12'], ['doi_cg_d22'], ['doi_cg_i']]
+crossed_graph_d21 = ['doi_cg_d21', 'title_cg_d21', ['contributor_cg_d21'], 'journal_cg_d21', 'date_cg_d21', ['subject_cg_d21'], [], ['doi_cg_d11']]
+crossed_graph_d22 = ['doi_cg_d22', 'title_cg_d22', ['contributor_cg_d22'], 'journal_cg_d22', 'date_cg_d22', ['subject_cg_d22'], [], ['doi_cg_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, crossed_graph_h21, crossed_graph_h22, crossed_graph_h11,
+                    crossed_graph_i, crossed_graph_d11, crossed_graph_d12, crossed_graph_d21, crossed_graph_d22]

verarbeitung/test/update_graph_unittest.py

+import unittest
+
+import sys  
+from pathlib import Path
+
+sys.path.append("../")
+
+from verarbeitung.construct_new_graph.initialize_graph import init_graph_construction
+from verarbeitung.construct_new_graph.export_to_json import output_to_json
+from verarbeitung.update_graph.import_from_json import input_from_json
+from verarbeitung.update_graph.update_graph import update_graph
+
+class UpdatingTest(unittest.TestCase):
+     maxDiff = None
+
+     # def test_import_from_json(self):
+     #      nodes_old, edges_old = init_graph_construction(['doi_lg_1_i'],2,2,True)
+     #      output_to_json(nodes_old, edges_old, test_var = 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 = init_graph_construction(['doi_lg_1_i'],2,2,True)
+     #      nodes_old_both, edges_old_both = init_graph_construction(['doi_lg_1_i','doi_lg_2_i'],2,2,True)
+     #      output_to_json(nodes_old_both, edges_old_both, test_var=True)
+     #      nodes_new_single, edges_new_single = update_graph(['doi_lg_1_i'], 'test_output.json', 2, 2, True)
+     #      self.assertCountEqual(nodes_old_single,nodes_new_single)
+     #      self.assertCountEqual(edges_old_single, edges_new_single)
+
+     #      nodes_old_single, edges_old_single = init_graph_construction(['doi_cg_i'],3,3,True)
+     #      nodes_old_two, edges_old_two = init_graph_construction(['doi_lg_1_i','doi_cg_i'],3,3,True)
+     #      nodes_old_three, edges_old_three = init_graph_construction(['doi_lg_1_i','doi_lg_2_i','doi_cg_i'],3,3,True)
+
+     def test_new_height(self):
+          nodes_height_0, edges_height_0 = init_graph_construction(['doi_lg_1_i'],2,0,True)
+          nodes_height_1, edges_height_1 = init_graph_construction(['doi_lg_1_i'],2,1,True)
+          nodes_height_2, edges_height_2 = init_graph_construction(['doi_lg_1_i'],2,2,True)
+
+          output_to_json(nodes_height_2, edges_height_2, 'new_height.json', True)
+          nodes_new_height_1, edges_new_height_1 = update_graph(['doi_lg_1_i'], 'new_height.json', 2, 1, True)
+          self.assertCountEqual(nodes_height_1, nodes_new_height_1)
+          self.assertCountEqual(edges_height_1, edges_new_height_1)
+
+          nodes_height_2, edges_height_2 = init_graph_construction(['doi_lg_1_i'],2,2,True)
+          output_to_json(nodes_height_2, edges_height_2, 'new_height.json', True)
+          nodes_new_height_0, edges_new_height_0 = update_graph(['doi_lg_1_i'], 'new_height.json', 2, 0, True)
+          self.assertCountEqual(nodes_height_0, nodes_new_height_0)
+          self.assertCountEqual(edges_height_0, edges_new_height_0)
+
+
+
+
+
+          
+
+
+
+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/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", "depth": 0, "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": "Reference", "depth": -1, "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": "Reference", "depth": -1, "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": "Citedby", "depth": 1, "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": "Citedby", "depth": 1, "citations": 2}, {"doi": "doi_lg_2_i", "name": "title_lg_2_i", "author": ["contributor_lg_2_i"], "year": "date_lg_2_i", "journal": "journal_lg_2_i", "group": "Input", "depth": 0, "citations": 4}, {"doi": "doi_lg_2_d11", "name": "title_lg_2_d11", "author": ["contributor_lg_2_d11"], "year": "date_lg_2_d11", "journal": "journal_lg_2_d11", "group": "Reference", "depth": -1, "citations": 1}, {"doi": "doi_lg_2_d12", "name": "title_lg_2_d12", "author": ["contributor_lg_2_d12"], "year": "date_lg_2_d12", "journal": "journal_lg_2_d12", "group": "Reference", "depth": -1, "citations": 2}, {"doi": "doi_lg_2_h11", "name": "title_lg_2_h11", "author": ["contributor_lg_2_h11"], "year": "date_lg_2_h11", "journal": "journal_lg_2_h11", "group": "Citedby", "depth": 1, "citations": 2}, {"doi": "doi_lg_2_h12", "name": "title_lg_2_h12", "author": ["contributor_lg_2_h12"], "year": "date_lg_2_h12", "journal": "journal_lg_2_h12", "group": "Citedby", "depth": 1, "citations": 2}, {"doi": "doi_cg_i", "name": "title_cg_i", "author": ["contributor_cg_i"], "year": "date_cg_i", "journal": "journal_cg_i", "group": "Citedby", "depth": 1, "citations": 3}, {"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": "Citedby", "depth": 2, "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": "Citedby", "depth": 2, "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": "Citedby", "depth": 2, "citations": 0}, {"doi": "doi_lg_2_h21", "name": "title_lg_2_h21", "author": ["contributor_lg_2_h21"], "year": "date_lg_2_h21", "journal": "journal_lg_2_h21", "group": "Citedby", "depth": 2, "citations": 0}, {"doi": "doi_lg_2_h22", "name": "title_lg_2_h22", "author": ["contributor_lg_2_h22"], "year": "date_lg_2_h22", "journal": "journal_lg_2_h22", "group": "Citedby", "depth": 2, "citations": 0}, {"doi": "doi_lg_2_h23", "name": "title_lg_2_h23", "author": ["contributor_lg_2_h23"], "year": "date_lg_2_h23", "journal": "journal_lg_2_h23", "group": "Citedby", "depth": 2, "citations": 1}, {"doi": "doi_lg_2_h24", "name": "title_lg_2_h24", "author": ["contributor_lg_2_h24"], "year": "date_lg_2_h24", "journal": "journal_lg_2_h24", "group": "Citedby", "depth": 2, "citations": 1}, {"doi": "doi_cg_h11", "name": "title_cg_h11", "author": ["contributor_cg_h11"], "year": "date_cg_h11", "journal": "journal_cg_h11", "group": "Citedby", "depth": 2, "citations": 2}, {"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": "Reference", "depth": -2, "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": "Reference", "depth": -2, "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": "Reference", "depth": -2, "citations": 2}, {"doi": "doi_lg_2_d21", "name": "title_lg_2_d21", "author": ["contributor_lg_2_d21"], "year": "date_lg_2_d21", "journal": "journal_lg_2_d21", "group": "Reference", "depth": -2, "citations": 1}, {"doi": "doi_lg_2_d22", "name": "title_lg_2_d22", "author": ["contributor_lg_2_d22"], "year": "date_lg_2_d22", "journal": "journal_lg_2_d22", "group": "Reference", "depth": -2, "citations": 1}, {"doi": "doi_lg_2_d23", "name": "title_lg_2_d23", "author": ["contributor_lg_2_d23"], "year": "date_lg_2_d23", "journal": "journal_lg_2_d23", "group": "Reference", "depth": -2, "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_2_i", "target": "doi_lg_2_d11"}, {"source": "doi_lg_2_i", "target": "doi_lg_2_d12"}, {"source": "doi_lg_2_h11", "target": "doi_lg_2_i"}, {"source": "doi_lg_2_h12", "target": "doi_lg_2_i"}, {"source": "doi_cg_i", "target": "doi_lg_2_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_2_h21", "target": "doi_lg_2_h11"}, {"source": "doi_lg_2_h22", "target": "doi_lg_2_h11"}, {"source": "doi_lg_2_h23", "target": "doi_lg_2_h12"}, {"source": "doi_lg_2_h24", "target": "doi_lg_2_h12"}, {"source": "doi_lg_2_h24", "target": "doi_lg_2_h23"}, {"source": "doi_lg_2_h23", "target": "doi_lg_2_h24"}, {"source": "doi_lg_1_h23", "target": "doi_cg_i"}, {"source": "doi_cg_h11", "target": "doi_cg_i"}, {"source": "doi_lg_2_h11", "target": "doi_cg_i"}, {"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_2_d11", "target": "doi_lg_2_i"}, {"source": "doi_lg_2_d11", "target": "doi_lg_2_d21"}, {"source": "doi_lg_2_d12", "target": "doi_lg_2_d22"}, {"source": "doi_lg_2_d12", "target": "doi_lg_2_d23"}, {"source": "doi_lg_1_h12", "target": "doi_lg_1_d12"}, {"source": "doi_lg_1_h11", "target": "doi_lg_1_h12"}, {"source": "doi_lg_2_h24", "target": "doi_lg_2_d12"}]}
\ No newline at end of file

verarbeitung/update_graph/Kanten_Vergleich.py

+#!/usr/bin/env python3
+
+def back_to_valid_edges(links_from_json, processed_input_list):
+    '''
+    :param links_from_json: list of edges from the old graph
+    :type links_from_json:  list
+    :param processed_input_list:   list pubs still in graph
+    :type processed_input_list:    list
+    
+    function that deletes edges, if one ore two including nodes are deleted nodes
+    '''
+    list_of_valid_edges = links_from_json.copy()
+
+
+    #iterates over all edges from old graph
+    for edge in list_of_valid_edges:
+
+        # counter for adjacent nodes
+        found_adj_nodes = 0
+        for pub in processed_input_list: 
+            # checks for both adjacent nodes of edge if pub is source/target node
+            for adj_node in edge:
+                # 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):
+            links_from_json.remove(edge) 
+
+#Kanten_Menge_Ganz = [["doi_1","doi_2"],["doi_3","doi_4"],["doi_5","doi_6"]]
+#Geloeschte = ["doi_2","doi_1","doi_4"]
+#print(back_to_valid_edges(Kanten_Menge_Ganz,Geloeschte))
+
+#Im Anschluss muss mit den Hinzugefügten Knoten Processing aufgerufen werden

verarbeitung/update_graph/Knoten_Vergleich.py

+#!/usr/bin/env python3
+from collections import Counter
+
+def doi_listen_vergleichen(alte,neue):
+    '''
+    :param alte: list of dois from old graph
+    :type alte: list
+    :param neue: list of dois from new graph
+    :type neue: list
+    
+    function to calculate, which nodes from the old graph are deleted and which are added
+    '''
+    dois_from_old_graph = alte #WICHTIG: Keine doppelten DOIs
+    dois_from_new_graph = neue
+    deleted_nodes = []
+    common_nodes = []
+    inserted_nodes = []
+    all_dois = dois_from_old_graph + dois_from_new_graph
+
+    for doi in all_dois: # iterates over the merged list of new and old dois 
+        if ((all_dois.count(doi) == 2) & (doi not in common_nodes)): # If the doi occurs twice the node is in the old and the new graph
+            common_nodes.append(doi) #appends the doi to common ones, if its not alredy in it
+        elif ((doi in dois_from_old_graph) & (doi not in dois_from_new_graph)): #If the doi occurs once and it is from old graph it is a deleted node
+            deleted_nodes.append(doi) #appends the doi to deleted ones
+        elif ((doi in dois_from_new_graph) & (doi not in dois_from_old_graph)): #if the doi occurs ince and it is from new graph it is a inserted node
+            inserted_nodes.append(doi) #appends the doi to the inserted ones
+    return(common_nodes, inserted_nodes, deleted_nodes)
+
+
+#Test Prints
+	#liste_1 = ["doi_1","doi_2","doi_3","doi_4","doi_5"]
+	#liste_2 = ["doi_1","doi_2","doi_3","doi_6","doi_7"]
+	#print("gemeinsame Elemente: ",doi_listen_vergleichen(liste_1,liste_2)[0])
+	#print("hinzugefügte Elemente: ",doi_listen_vergleichen(liste_1,liste_2)[1])
+	#print("gelöschte Elemente: ",doi_listen_vergleichen(liste_1,liste_2)[2])
+

verarbeitung/update_graph/README.md

+# Projekt CiS-Projekt 2021/22
+
+Directory for functions to adjust a publication graph to updated input lists and changed citation/reference depths. For minimal use of the time consuming Input function, a reinterpretation of the exported json file is implemented.
+
+## Files in directory
+
+import_from_json.py 
+
+- 	Stellt die alte Knoten-und Kantenmenge aus der Json Datei wieder her.
+
+Knoten_Vergleich.py 
+
+- 	Überprüft welche Knoten neu hinzugekommen sind und welche enfternt wurden.
+
+Kanten_Vergleich.py 
+
+- 	Stellt nach der Löschung eines Knotens wieder eine valide Kantenmenge her.
+
+update_graph_del.py 
+
+- 	Führt die Löschung eines Knotens durch
+
+connect_new_input.py 
+
+- 	Verbindet den alten Graphen aus der Json Datei mit den neuen DOIs zu dem neuen Graphen.
+
+update_graph.py 
+
+- 	Überprüft welche Änderungen der Benutzer vorgenommen hat (Löschen oder hinzufügen von DOIs) 
+	und führt diese aus.
+
+## Authors
+- Donna Löding
+- Alina Molkentin
+- Xinyi Tang
+- Judith Große
+- Malte Schokolowski
\ No newline at end of file

verarbeitung/update_graph/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.initialize_graph 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"
+
+

verarbeitung/update_graph/delete_nodes_edges.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 .Kanten_Vergleich import back_to_valid_edges
+
+
+def search_ref_graph_rec(pub):
+    '''
+    :param pub: pub go get appended to usable_nodes
+    :type pub:  Publication
+    
+    function that appends nodes of group "reference" to list usable_nodes, if they are reachable from input nodes
+    '''
+    for reference in pub.references:
+        for ref_pub in input_obj_list:
+            if ((reference.doi_url == ref_pub.doi_url) and (ref_pub not in usable_nodes)):
+                usable_nodes.append(ref_pub)
+
+                # to find a cyclus and avoid recursion error
+                not_in_citations = True
+                for citation in pub.citations:
+                    if (reference.doi_url == citation.doi_url):
+                        not_in_citations = False
+                        break
+                if (not_in_citations):  
+                    search_ref_graph_rec(ref_pub)
+
+
+def search_cit_graph_rec(pub):  
+    '''
+    :param pub: pub go get appended to usable_nodes
+    :type pub:  Publication
+    
+    function that appends nodes of group "citation" to list usable_nodes, if they are reachable from input nodes
+    '''  
+    for citation in pub.citations:
+        for cit_pub in input_obj_list:
+            if ((citation.doi_url == cit_pub.doi_url) and (cit_pub not in usable_nodes)):
+                usable_nodes.append(cit_pub)
+
+                # to find a cyclus and avoid recursion error
+                not_in_references = True
+                for reference in pub.references:
+                    if (citation.doi_url == reference.doi_url):
+                        not_in_references = False
+                        break
+                if (not_in_references):  
+                    search_cit_graph_rec(cit_pub)
+
+
+
+def delete_nodes_and_edges(input_list, common_nodes, old_edges_list):
+    '''
+    :param input_list:      list of publications to get reduced
+    :type input_list:       List[Publication]
+
+    :param common_nodes:        list of input dois which are in old and new input call
+    :type common_nodes:         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 change edge list to valid state
+    '''
+    global usable_nodes, input_obj_list
+    usable_nodes = []
+    input_obj_list = input_list
+
+    # starts for every common input node a tree-search and adds found nodes to usable_nodes
+    for common in common_nodes:
+        for pub in input_obj_list:
+            if (common == pub.doi_url):
+                usable_nodes.append(pub)
+                search_ref_graph_rec(pub)
+                search_cit_graph_rec(pub)
+
+    valid_edges = back_to_valid_edges(old_edges_list, usable_nodes)
+
+    return(usable_nodes, valid_edges)
\ No newline at end of file