merge verarbeitung to main repo

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

verarbeitung/Processing.py

@@ -24,22 +24,32 @@ from input.interface import InputInterface as Input
 from input_test import input_test_func
 from json_demo import output_to_json
 
-# adds every publication from input list to graph structure
-# doi_input_list: list of publication dois from user
+
 def initialize_nodes_list(doi_input_list, search_depth_max, search_height_max, test_var):
+    '''
+    :param doi_input_list: Liste mit DOIs, die der User eingegeben hat
+    :type doi_input_list: Liste
+    :param search_depth_max: Rekusionstiefe - Referenzen
+    :type search_depth_max: Integer
+    :param search_height_max: Rekursionstiefe - Citations
+    :type search_height_max: Integer
+    :param test_var: Wert, um zu entscheiden, ob die Test-Input-Funktion oder die Standartversion gewählt werden soll
+    :type test_var: Boolscher Wert (True = Test-Funkion, False = Standart-Funktion)
+    
+	# adds every publication from input list to graph structure
+	# doi_input_list: list of publication dois from user
+    '''
     references_pub_obj_list = []
     citations_pub_obj_list = []
 
-    for pub_doi in doi_input_list:
-
-        #checks if its a test and chooses input function accordingly
-        if(test_var):
-            pub = input_test_func(pub_doi)
-        else:
+    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)
+                pub = inter.get_publication(pub_doi) #creates an object of class Publication
             except ValueError:
                 continue
             except IndexError:
@@ -47,16 +57,16 @@ def initialize_nodes_list(doi_input_list, search_depth_max, search_height_max, t
             
 
         # checks if publication already exists in nodes
-        not_in_nodes = True
-        for node in nodes:                                              # checks if a pub is already in nodes
-            if (pub.doi_url == node.doi_url):
-                not_in_nodes = False
+        not_in_nodes = True #boolean value to check if a node already exists in the set of nodes
+        for node in nodes: #iterates over every node in the set of nodes
+            if (pub.doi_url == node.doi_url): #determines that a node with this doi already is in the set
+                not_in_nodes = False #false --> node will not be created
                 break
-        if (not_in_nodes):
-            nodes.append(pub)
+        if (not_in_nodes): #there is no node with this doi in the set
+            nodes.append(pub) #appends Publication Object
             pub.group = "input"
         else:
-            doi_input_list.remove(pub_doi)
+            doi_input_list.remove(pub_doi) #deletes the doi-dublicate from input list
 
         # inserts references as publication objects into list and 
         # inserts first depth references into nodes/edges if maximum search depth > 0
@@ -71,40 +81,55 @@ def initialize_nodes_list(doi_input_list, search_depth_max, search_height_max, t
     return(references_pub_obj_list, citations_pub_obj_list)
         
     
-# adds edges between citation and reference group
+
 def complete_inner_edges(test_var):
-    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 (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])
-
-
-
-# adds a node for every publication unknown
-# adds edges for references between publications     
+    '''
+    :param test_var: Wert, um zu entscheiden, ob die Test-Input-Funktion oder die Standartversion gewählt werden soll
+    :type test_var: Boolscher Wert (True = Test-Funkion, False = Standart-Funktion)
+    
+	# adds edges between citation and reference group
+    '''
+    for node in nodes: #iterates over all nodes in the set of nodes
+        if (node.group == "depth"): #checks if the node has group depth (=is a reference from a paper)
+            for citation in node.citations: #iterates over the papers that this paper is cited by 
+                for cit in nodes: #iterates over all nodes in set of nodes 
+                    if (citation.doi_url == cit.doi_url and [citation.doi_url, node.doi_url] not in edges): #checks if there is already a related node that is in the set of nodes
+                        edges.append([citation.doi_url, node.doi_url]) # creates an edge between them
+        if (node.group == "height"): #checks if the node has group height (=is a citation from a paper)
+            for reference in node.references: #iterates over the papers that this is paper references
+                for ref in nodes: #iterates over all nodes in set of nodes
+                    if (reference.doi_url == ref.doi_url and [node.doi_url, reference.doi_url] not in edges): #checks if there is already a related node that is in the set of nodes
+                        edges.append([node.doi_url,reference.doi_url]) #creates an edge between them
+
+
+
+  
 def create_graph_structure_references(pub, search_depth, search_depth_max, test_var):
+    '''
+    :param pub: Paper
+    :type pub: Onbject of class Publication
+    :param search_depth: current recursion step
+    :type search_depth: integer
+    :param search_depth_max: recursion limit
+    :type search_depth_max: integer
+    :param test_var: Wert, um zu entscheiden, ob die Test-Input-Funktion oder die Standartversion gewählt werden soll
+    :type test_var: Boolscher Wert (True = Test-Funkion, False = Standart-Funktion)
+	# adds a node for every publication unknown
+	# adds edges for references between publications   
+	# returs a list of nodes
+    '''
     references_pub_obj_list = []
-    for reference in pub.references:
-        not_in_nodes = True
-        for node in nodes:
-            # checks every reference for duplication 
-            if (reference.doi_url == node.doi_url):
-                not_in_nodes = False
+    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
+                not_in_nodes = False #boolean false --> node will not be created
                 break
-        if (not_in_nodes):
-            if (search_depth < search_depth_max):
-
-                #checks if its a test and chooses input function accordingly
-                if (test_var):
-                    reference_pub_obj = input_test_func(reference.doi_url)
-                else:
+        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:
@@ -116,9 +141,9 @@ def create_graph_structure_references(pub, search_depth, search_depth_max, test_
                         continue
 
                 reference_pub_obj.group = "depth"
-                nodes.append(reference_pub_obj)
-                edges.append([pub.doi_url,reference_pub_obj.doi_url])
-                references_pub_obj_list.append(reference_pub_obj)
+                nodes.append(reference_pub_obj) # appends the object to the set of nodes
+                edges.append([pub.doi_url,reference_pub_obj.doi_url]) #appends the edge to the set of edges
+                references_pub_obj_list.append(reference_pub_obj) #appends the node to the set of references
 
         # adds edge only if citation already exists           
         elif [pub.doi_url,reference.doi_url] not in edges:
@@ -126,11 +151,20 @@ def create_graph_structure_references(pub, search_depth, search_depth_max, test_
     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):  
+
+def process_references_rec(references_pub_obj_list, search_depth, search_depth_max, test_var):
+    '''
+    :param references_pub_obj_list: input list of references as publication objects
+    :type references_pub_obj_list: liste
+    :param search_depth: current search_depth of height-first-search
+    :type search_depth: integer
+    :param search_depth_max: maximal search_depth for dfs
+    :type search_depth_max: integer
+    :param test_var: Wert, um zu entscheiden, ob die Test-Input-Funktion oder die Standartversion gewählt werden soll
+    :type test_var: Boolscher Wert (True = Test-Funkion, False = Standart-Funktion)
+    
+	# recursive function to implement height-first-search on references
+    '''  
     # adds next level to nodes/edges
     for pub in references_pub_obj_list:
         new_reference_pub_obj_list = create_graph_structure_references(pub, search_depth, search_depth_max, test_var)    
@@ -142,21 +176,30 @@ def process_references_rec(references_pub_obj_list, search_depth, search_depth_m
 
 
     
-# adds a node for every publication unknown
-# adds edges for citations between publications     
+  
 def create_graph_structure_citations(pub, search_height, search_height_max, test_var):
+    '''
+    :param pub: Paper
+    :type pub: Onbject of class Publication
+    :param search_height: current recursion step
+    :type search_height: integer
+    :param search_height_max: recursion limit
+    :type search_height_max: integer
+    :param test_var: Wert, um zu entscheiden, ob die Test-Input-Funktion oder die Standartversion gewählt werden soll
+    :type test_var: Boolscher Wert (True = Test-Funkion, False = Standart-Funktion)
+	# adds a node for every publication unknown
+	# adds edges for citations between publications 
+	# returns list of nodes  
+    '''
     citations_pub_obj_list = []
     for citation in pub.citations:
         not_in_nodes = True
-        for node in nodes:
-            # checks every citation for duplication 
+        for node in nodes: # checks every citation for duplication 
             if (citation.doi_url == 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 (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:
@@ -181,11 +224,20 @@ def create_graph_structure_citations(pub, search_height, search_height_max, test
 
 
 
-# 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):  
+
+def process_citations_rec(citations_pub_obj_list, search_height, search_height_max, test_var): 
+    '''
+    :param references_pub_obj_list: input list of citations as publication objects
+    :type references_pub_obj_list: liste
+    :param search_height: current search_height of height-first-search
+    :type search_height: integer
+    :param search_height_max: maximal search_height for dfs
+    :type search_height_max: integer
+    :param test_var: Wert, um zu entscheiden, ob die Test-Input-Funktion oder die Standartversion gewählt werden soll
+    :type test_var: Boolscher Wert (True = Test-Funkion, False = Standart-Funktion)
+    
+	# recursive function to implement height-first-search on citations
+    ''' 
     # adds next level to nodes/edges
     for pub in citations_pub_obj_list:
         new_citation_pub_obj_list = create_graph_structure_citations(pub, search_height, search_height_max, test_var)   
@@ -197,12 +249,20 @@ def process_citations_rec(citations_pub_obj_list, search_height, search_height_m
 
 
 
-# main function to call. Needs as input:
-# doi_input_list:   input list of dois
-# search_height:    max search height to process to
-# search_depth:     max search depth to process to
-# test_var:         only needed for unit test as True, default is False
+
 def process_main(doi_input_list, search_height, search_depth, test_var = False):
+    '''
+    :param doi_input_list: list with dois from user
+    :type doi_input_list: list
+    :param search_height: recursion height
+    :type search_height: integer
+    :param search_depth: recursion depth
+    :type search_depth: integer
+    :param test_var: Wert, um zu entscheiden, ob die Test-Input-Funktion oder die Standartversion gewählt werden soll
+    :type test_var: Boolscher Wert (True = Test-Funkion, False = Standart-Funktion)
+    
+	# main function to call. Needs as input:
+    '''
     # ERROR-Handling doi_array = NULL
     if (len(doi_input_list) == 0):
         print("Error, no input data")
@@ -215,11 +275,11 @@ def process_main(doi_input_list, search_height, search_depth, test_var = False):
     if (search_depth < 0):
         print("Error, search_depth of search must be positive")       
 
-    # create empty array for the nodes
-    # create empty array for the edges
+    
+    
     global nodes, edges
-    nodes = []
-    edges = []
+    nodes = [] # create empty array for the nodes
+    edges = [] # create empty array for the 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)
@@ -242,4 +302,4 @@ def process_main(doi_input_list, search_height, search_depth, test_var = False):
             doi_nodes_list.append(node.doi_url)
         return(doi_nodes_list, edges)
 
-    return(nodes,edges)
\ No newline at end of file
+    return(nodes,edges)