From 97cbb8867e6ee018b73ebeb1cd44dcb3b263d652 Mon Sep 17 00:00:00 2001
From: Donnawetter <8loeding@informatik.uni-hamburg.de>
Date: Fri, 28 Jan 2022 14:15:58 +0100
Subject: [PATCH] fix comments and reformat files from verarbeitung
---
verarbeitung/README.md | 29 +-
verarbeitung/construct_new_graph/README.md | 1 -
.../construct_new_graph/add_citations_rec.py | 85 +-
.../construct_new_graph/export_to_json.py | 30 +-
.../construct_new_graph/initialize_graph.py | 74 +-
verarbeitung/dev_files/README.md | 2 +-
verarbeitung/dev_files/print_graph_test.py | 67 +-
verarbeitung/get_pub_from_input.py | 22 +-
verarbeitung/process_main.py | 4 +-
verarbeitung/test/README.md | 5 +-
verarbeitung/test/construct_graph_unittest.py | 466 ++++++-----
verarbeitung/test/input_test.py | 152 ++--
verarbeitung/test/update_graph_unittest.py | 758 +++++++++---------
verarbeitung/update_graph/README.md | 1 -
.../compare_old_and_new_node_lists.py | 42 +-
.../update_graph/connect_new_input.py | 109 +--
.../update_graph/delete_nodes_edges.py | 17 +-
verarbeitung/update_graph/import_from_json.py | 35 +-
verarbeitung/update_graph/update_depth.py | 16 +-
verarbeitung/update_graph/update_edges.py | 5 +-
verarbeitung/update_graph/update_graph.py | 24 +-
21 files changed, 1032 insertions(+), 912 deletions(-)
diff --git a/verarbeitung/README.md b/verarbeitung/README.md
index 10640cb..3cd6c7e 100644
--- a/verarbeitung/README.md
+++ b/verarbeitung/README.md
@@ -1,6 +1,6 @@
# Projekt CiS-Projekt 2021/22
-Processing-Package to generate theoretical graph for citations and references of given input publications.
+Processing-Package to generate a theoretical graph for citations and references of given input publications.
## Usage/Examples
@@ -9,53 +9,50 @@ from verarbeitung.process_main import Processing
def main(url_list):
- Processing(url_list)
+ Processing(url_list)
```
Grundlegender Prozess:
-Es wird von der UI eine Liste an DOIs an die Verarbeitung übergeben und
-diese wird dann umgewandelt in eine Knoten-und Kantenmenge, welche die Zitierungen darstellen.
-Die Informationen über die Paper und die Zitierungen kommen von der Input Gruppe über den Aufruf
-von der Funktion Publication. Die Knoten- und Kantenmengen werden in Form einer
-Json Datei an den Output übergeben.
+Es wird von der UI eine Liste an DOIs an die Verarbeitung übergeben und diese wird dann umgewandelt in eine Knoten-und
+Kantenmenge, welche die Zitierungen darstellen. Die Informationen über die Paper und die Zitierungen kommen von der
+Input Gruppe über den Aufruf von der Funktion Publication. Die Knoten- und Kantenmengen werden in Form einer Json Datei
+an den Output übergeben.
## Files and functions in directory
-
get_pub_from_input.py:
```python
def get_pub(pub_doi, test_var)
```
-- Gibt für eine DOI ein Klassenobjekt zurück, in dem alle nötigen Informationen gespeichert sind.
+- Gibt für eine DOI ein Klassenobjekt zurück, in dem alle nötigen Informationen gespeichert sind.
process_main.py:
```python
def Processing(url_list)
```
-- Überprüft, ob bereits eine Json Datei existiert und ruft dann entweder die Funktion auf, um
- einen neuen Graphen zu erstellen oder die Funktion um einen Vorhandenen zu updaten.
+- Überprüft, ob bereits eine Json Datei existiert und ruft dann entweder die Funktion auf, um einen neuen Graphen zu
+ erstellen oder die Funktion, um einen Vorhandenen zu updaten.
start.script.py:
- - Wird benötigt, um die Dateien ordnerübergreifend aufzurufen. Nur fürs interne Testen der
- Funktionalität
-
+- Wird benötigt, um die Dateien ordnerübergreifend aufzurufen. Nur fürs interne Testen der
+ Funktionalität
<name>.json:
-- sind momentan Beispiele, die an den Output übergeben werden könnten.
+- sind momentan Beispiele, die an den Output übergeben werden könnten.
## Testing
python -m unittest discover verarbeitung/test -v
## Authors
+
- Donna Löding
- Alina Molkentin
-- Xinyi Tang
- Judith Große
- Malte Schokolowski
\ No newline at end of file
diff --git a/verarbeitung/construct_new_graph/README.md b/verarbeitung/construct_new_graph/README.md
index d73f4eb..8a8bfe1 100644
--- a/verarbeitung/construct_new_graph/README.md
+++ b/verarbeitung/construct_new_graph/README.md
@@ -24,6 +24,5 @@ export_to_json.py
## Authors
- Donna Löding
- Alina Molkentin
-- Xinyi Tang
- Judith Große
- Malte Schokolowski
\ No newline at end of file
diff --git a/verarbeitung/construct_new_graph/add_citations_rec.py b/verarbeitung/construct_new_graph/add_citations_rec.py
index dee665c..9467fe4 100644
--- a/verarbeitung/construct_new_graph/add_citations_rec.py
+++ b/verarbeitung/construct_new_graph/add_citations_rec.py
@@ -1,28 +1,32 @@
# -*- coding: utf-8 -*-
"""
-Functions to add citations recursivly for multiple ACS/Nature journals
+Functions to add citations recursively for multiple ACS/Nature journals
"""
-__authors__ = "Donna Löding, Alina Molkentin, Xinyi Tang, Judith Große, Malte Schokolowski"
+__authors__ = "Donna Löding, Alina Molkentin, Judith Große, Malte Schokolowski"
__email__ = "cis-project2021@zbh.uni-hamburg.de"
__status__ = "Production"
-#__copyright__ = ""
-#__credits__ = ["", "", "", ""]
-#__license__ = ""
-#__version__ = ""
-#__maintainer__ = ""
+# __copyright__ = ""
+# __credits__ = ["", "", "", ""]
+# __license__ = ""
+# __version__ = ""
+# __maintainer__ = ""
-import sys
+
+import sys
from pathlib import Path
from os import error
+
sys.path.append("../")
from input.publication import Publication
from verarbeitung.get_pub_from_input import get_pub
-def create_graph_structure_citations_test(pub, search_depth, search_depth_max, cit_type, test_var, test_nodes, test_edges):
+
+def create_graph_structure_citations_test(pub, search_depth, search_depth_max, cit_type, test_var, test_nodes,
+ test_edges):
'''
:param test_nodes: list of publications from unit test
:type test_nodes: List[Publication]
@@ -35,7 +39,7 @@ def create_graph_structure_citations_test(pub, search_depth, search_depth_max, c
global nodes, edges
nodes = test_nodes
edges = test_edges
- return(nodes, edges, create_graph_structure_citations(pub, search_depth, search_depth_max, cit_type, test_var))
+ return (nodes, edges, create_graph_structure_citations(pub, search_depth, search_depth_max, cit_type, test_var))
def get_cit_type_list(pub, cit_type):
@@ -43,17 +47,18 @@ def get_cit_type_list(pub, cit_type):
:param pub: Publication which citations will be added
:type pub: Publication
- :param cit_type: variable to differenciate citation and reference call
+ :param cit_type: variable to differentiate citation and reference call
:type cit_type: String
function to return citation or reference list for given pub
'''
if cit_type == "Citation":
- return(pub.citations)
+ return (pub.citations)
elif cit_type == "Reference":
- return(pub.references)
+ return (pub.references)
else:
- return(ValueError)
+ return (ValueError)
+
def create_global_lists_cit(input_nodes, input_edges, pub, search_depth, search_depth_max, cit_type, test_var):
'''
@@ -72,10 +77,10 @@ def create_global_lists_cit(input_nodes, input_edges, pub, search_depth, search_
:param search_depth_max: maximum depth to search for citations
:type search_depth_max: int
- :param cit_type: variable to differenciate citation and reference call
+ :param cit_type: variable to differentiate citation and reference call
:type cit_type: String
- :param test_var: variable to differenciate between test and url call
+ :param test_var: variable to differentiate between test and url call
:type test_var: boolean
function to create nodes and edges and call create_graph_structure_citations
@@ -99,10 +104,10 @@ def create_graph_structure_citations(pub, search_depth, search_depth_max, cit_ty
:param search_depth_max: maximum depth to search for citations
:type search_depth_max: int
- :param cit_type: variable to differenciate citation and reference call
+ :param cit_type: variable to differentiate citation and reference call
:type cit_type: String
- :param test_var: variable to differenciate between test and url call
+ :param test_var: variable to differentiate between test and url call
:type test_var: boolean
adds a node for every citing publication unknown
@@ -112,38 +117,38 @@ def create_graph_structure_citations(pub, search_depth, search_depth_max, cit_ty
citations_pub_obj_list = []
for citation in get_cit_type_list(pub, cit_type):
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_depth < search_depth_max): #checks if its a test and chooses input function accordingly
+ if (search_depth < search_depth_max): # checks if its a test and chooses input function accordingly
citation_pub_obj = get_pub(citation.doi_url, test_var)
if (type(citation_pub_obj) != Publication):
- #print(pub)
- continue
-
+ # print(pub)
+ continue
+
if (cit_type == "Citation"):
citation_pub_obj.group = search_depth + 1
- edges.append([citation_pub_obj.doi_url,pub.doi_url])
+ edges.append([citation_pub_obj.doi_url, pub.doi_url])
else:
citation_pub_obj.group = -(search_depth + 1)
- edges.append([pub.doi_url,citation_pub_obj.doi_url])
- nodes.append(citation_pub_obj)
+ edges.append([pub.doi_url, citation_pub_obj.doi_url])
+ nodes.append(citation_pub_obj)
citations_pub_obj_list.append(citation_pub_obj)
# adds just the edge if citation already exists
else:
- if (cit_type == "Citation"):
- if ([citation.doi_url,pub.doi_url] not in edges):
- edges.append([citation.doi_url,pub.doi_url])
+ if (cit_type == "Citation"):
+ if ([citation.doi_url, pub.doi_url] not in edges):
+ edges.append([citation.doi_url, pub.doi_url])
else:
- if ([pub.doi_url,citation.doi_url] not in edges):
- edges.append([pub.doi_url,citation.doi_url])
+ if ([pub.doi_url, citation.doi_url] not in edges):
+ edges.append([pub.doi_url, citation.doi_url])
return citations_pub_obj_list
-def process_citations_rec(citations_pub_obj_list, search_depth, search_depth_max, cit_type, test_var):
+def process_citations_rec(citations_pub_obj_list, search_depth, search_depth_max, cit_type, test_var):
'''
:param citations_pub_obj_list: list of publications which citations will be added
:type citations_pub_obj_list: List[Publication]
@@ -154,10 +159,10 @@ def process_citations_rec(citations_pub_obj_list, search_depth, search_depth_max
:param search_depth_max: maximum depth to search for citations
:type search_depth_max: int
- :param cit_type: variable to differenciate citation and reference call
+ :param cit_type: variable to differentiate citation and reference call
:type cit_type: String
- :param test_var: variable to differenciate between test and url call
+ :param test_var: variable to differentiate between test and url call
:type test_var: boolean
recursive function to implement depth-first-search on citations
@@ -167,13 +172,14 @@ def process_citations_rec(citations_pub_obj_list, search_depth, search_depth_max
new_citation_pub_obj_save_list = []
for pub in citations_pub_obj_list:
- new_citation_pub_obj_list = create_graph_structure_citations(pub, search_depth, search_depth_max, cit_type, test_var)
+ new_citation_pub_obj_list = create_graph_structure_citations(pub, search_depth, search_depth_max, cit_type,
+ test_var)
if len(new_citation_pub_obj_list) > 0:
new_citation_pub_obj_save_list += new_citation_pub_obj_list
- # If the maximum depth has not yet been reached, calls function recursivly with increased depth
+ # If the maximum depth has not yet been reached, calls function recursively with increased depth
if (search_depth < search_depth_max):
- process_citations_rec(new_citation_pub_obj_save_list, search_depth+1, search_depth_max, cit_type, test_var)
+ process_citations_rec(new_citation_pub_obj_save_list, search_depth + 1, search_depth_max, cit_type, test_var)
def add_citations(input_nodes, input_edges, citations_pub_obj_list, search_depth, search_depth_max, cit_type, test_var):
@@ -193,10 +199,10 @@ def add_citations(input_nodes, input_edges, citations_pub_obj_list, search_depth
:param search_depth_max: maximum depth to search for citations
:type search_depth_max: int
- :param cit_type: variable to differenciate citation and reference call
+ :param cit_type: variable to differentiate citation and reference call
:type cit_type: String
- :param test_var: variable to differenciate between test and url call
+ :param test_var: variable to differentiate between test and url call
:type test_var: boolean
function to call recursive depth-first-search of citations
@@ -206,4 +212,3 @@ def add_citations(input_nodes, input_edges, citations_pub_obj_list, search_depth
edges = input_edges
process_citations_rec(citations_pub_obj_list, search_depth, search_depth_max, cit_type, test_var)
- #return(nodes, edges)
\ No newline at end of file
diff --git a/verarbeitung/construct_new_graph/export_to_json.py b/verarbeitung/construct_new_graph/export_to_json.py
index d093f63..00627df 100644
--- a/verarbeitung/construct_new_graph/export_to_json.py
+++ b/verarbeitung/construct_new_graph/export_to_json.py
@@ -4,14 +4,15 @@ Functions that format the computed graph to match the interface to the output-pa
"""
-__authors__ = "Donna Löding, Alina Molkentin, Xinyi Tang, Judith Große, Malte Schokolowski"
+__authors__ = "Donna Löding, Alina Molkentin, Judith Große, Malte Schokolowski"
__email__ = "cis-project2021@zbh.uni-hamburg.de"
__status__ = "Production"
-#__copyright__ = ""
-#__credits__ = ["", "", "", ""]
-#__license__ = ""
-#__version__ = ""
-#__maintainer__ = ""
+
+# __copyright__ = ""
+# __credits__ = ["", "", "", ""]
+# __license__ = ""
+# __version__ = ""
+# __maintainer__ = ""
import json
@@ -42,8 +43,9 @@ def format_nodes(nodes):
new_dict["citations"] = len(node.citations)
list_of_node_dicts.append(new_dict)
return list_of_node_dicts
-
-# creates a list that contains a disctionary for each edge
+
+
+# creates a list that contains a dictionary for each edge
# the dictionaries contain the source as keys and the target as values
def format_edges(edges):
'''
@@ -59,9 +61,9 @@ def format_edges(edges):
new_dict_2["target"] = edge[1]
list_of_edge_dicts.append(new_dict_2)
return list_of_edge_dicts
-
-def output_to_json(nodes, edges, search_depth, search_height, json_file = 'json_text.json', test_var = False):
+
+def output_to_json(nodes, edges, search_depth, search_height, json_file='json_text.json', test_var=False):
'''
:param nodes: list of publications to export to json
:type nodes: List[Publication]
@@ -69,7 +71,7 @@ def output_to_json(nodes, edges, search_depth, search_height, json_file = 'json_
:param edges: list of links to export to json
:type edges: List[String,String]
- :param test_var: variable to differenciate between test and url call
+ :param test_var: variable to differentiate between test and url call
:type test_var: boolean
function to export nodes and links as a dictionary to json file
@@ -82,11 +84,11 @@ def output_to_json(nodes, edges, search_depth, search_height, json_file = 'json_
dict_of_all["depth_height"] = [search_depth, search_height]
if (test_var):
if json_file != 'json_text.json':
- with open(json_file,'w') as outfile:
+ with open(json_file, 'w') as outfile:
json.dump(dict_of_all, outfile)
else:
- with open('test_output.json','w') as outfile:
+ with open('test_output.json', 'w') as outfile:
json.dump(dict_of_all, outfile)
else:
- with open(json_file,'w') as outfile:
+ with open(json_file, 'w') as outfile:
json.dump(dict_of_all, outfile)
diff --git a/verarbeitung/construct_new_graph/initialize_graph.py b/verarbeitung/construct_new_graph/initialize_graph.py
index 4615d5e..81571db 100644
--- a/verarbeitung/construct_new_graph/initialize_graph.py
+++ b/verarbeitung/construct_new_graph/initialize_graph.py
@@ -4,20 +4,22 @@ Functions to generate a graph representing citations between multiple ACS/Nature
"""
-__authors__ = "Donna Löding, Alina Molkentin, Xinyi Tang, Judith Große, Malte Schokolowski"
+__authors__ = "Donna Löding, Alina Molkentin, Judith Große, Malte Schokolowski"
__email__ = "cis-project2021@zbh.uni-hamburg.de"
__status__ = "Production"
-#__copyright__ = ""
-#__credits__ = ["", "", "", ""]
-#__license__ = ""
-#__version__ = ""
-#__maintainer__ = ""
+# __copyright__ = ""
+# __credits__ = ["", "", "", ""]
+# __license__ = ""
+# __version__ = ""
+# __maintainer__ = ""
-import sys
+
+import sys
import gc
from pathlib import Path
from os import error
+
sys.path.append("../")
from input.publication import Publication
@@ -25,6 +27,7 @@ from verarbeitung.get_pub_from_input import get_pub
from .export_to_json import output_to_json
from .add_citations_rec import add_citations, create_global_lists_cit
+
def initialize_nodes_list_test(doi_input_list, search_depth_max, search_height_max, test_var):
'''
for unit test purposes only
@@ -32,7 +35,8 @@ def initialize_nodes_list_test(doi_input_list, search_depth_max, search_height_m
global nodes, edges
nodes = []
edges = []
- return(initialize_nodes_list(doi_input_list, search_depth_max, search_height_max, test_var))
+ return (initialize_nodes_list(doi_input_list, search_depth_max, search_height_max, test_var))
+
def complete_inner_edges_test(test_nodes, test_edges):
'''
@@ -44,12 +48,13 @@ def complete_inner_edges_test(test_nodes, test_edges):
for unit test purposes only
'''
-
+
global nodes, edges
nodes = test_nodes
edges = test_edges
complete_inner_edges()
- return(nodes, edges)
+ return (nodes, edges)
+
def initialize_nodes_list(doi_input_list, search_depth_max, search_height_max, test_var):
'''
@@ -62,36 +67,36 @@ def initialize_nodes_list(doi_input_list, search_depth_max, search_height_max, t
:param search_height_max: maximum height to search for citations
:type search_height_max: int
- :param test_var: variable to differenciate between test and url call
+ :param test_var: variable to differentiate between test and url call
:type test_var: boolean
- adds input dois to nodes and retrieves citations and references for input publications
+ 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
+ for pub_doi in doi_input_list: # iterates over every incoming doi
pub = get_pub(pub_doi, test_var)
if (type(pub) != Publication):
- #print(pub)
+ # print(pub)
error_doi_list.append(pub_doi)
- continue
+ 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
+ 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
+ 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
node.group = 0
break
- if (not_in_nodes): #there is no node with this doi in the set
- nodes.append(pub) #appends Publication Object
+ if (not_in_nodes): # there is no node with this DOI in the set
+ nodes.append(pub) # appends Publication Object
pub.group = 0
else:
- doi_input_list.remove(pub_doi) #deletes the doi-dublicate from input list
+ doi_input_list.remove(pub_doi) # deletes the DOI-duplicate from input list
# inserts references as publication objects into list and
# inserts first depth references into nodes/edges if maximum search depth > 0
@@ -103,11 +108,10 @@ def initialize_nodes_list(doi_input_list, search_depth_max, search_height_max, t
for citation in create_global_lists_cit(nodes, edges, pub, 0, search_height_max, "Citation", test_var):
citations_pub_obj_list.append(citation)
- return(references_pub_obj_list, citations_pub_obj_list)
-
+ return (references_pub_obj_list, citations_pub_obj_list)
-def complete_inner_edges(update_var = False, input_nodes = [], input_edges = []):
+def complete_inner_edges(update_var=False, input_nodes=[], input_edges=[]):
'''
:param update_var: variable to check if call is from update_graph with known nodes and edges or fresh construction
:type update_var: boolean
@@ -122,7 +126,7 @@ def complete_inner_edges(update_var = False, input_nodes = [], input_edges = [])
'''
if update_var:
global nodes, edges
-
+
nodes = input_nodes
edges = input_edges
@@ -136,10 +140,11 @@ def complete_inner_edges(update_var = False, input_nodes = [], input_edges = [])
for reference in node.references:
for pub in nodes:
if ((pub.doi_url == reference.doi_url) and ([node.doi_url, reference.doi_url] not in edges)):
- edges.append([node.doi_url,reference.doi_url])
+ edges.append([node.doi_url, reference.doi_url])
-def init_graph_construction(doi_input_list, search_depth, search_height, test_var = False, update_var = False, input_nodes = [], input_edges = []):
+def init_graph_construction(doi_input_list, search_depth, search_height, test_var=False, update_var=False,
+ input_nodes=[], input_edges=[]):
'''
:param doi_input_list: input list of doi from UI
:type doi_input_list: List[String]
@@ -150,7 +155,7 @@ def init_graph_construction(doi_input_list, search_depth, search_height, test_va
:param search_depth: maximum depth to search for references
:type search_depth: int
- :param test_var: variable to differenciate between test and url call
+ :param test_var: variable to differentiate between test and url call
:type test_var: boolean
:param update_var: variable to check if call is from update_graph with known nodes and edges or fresh construction
@@ -175,21 +180,21 @@ def init_graph_construction(doi_input_list, search_depth, search_height, test_va
# ERROR- if a negative number is entered for depth
if (search_depth < 0):
- print("Error, search_depth of search must be positive")
+ print("Error, search_depth of search must be positive")
-
# creates empty lists to save nodes and edges
global nodes, edges, error_doi_list
if update_var:
nodes = input_nodes
- edges = input_edges
+ edges = input_edges
else:
nodes = []
edges = []
error_doi_list = []
# 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)
+ references_obj_list, citations_obj_list = initialize_nodes_list(doi_input_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)
@@ -205,5 +210,4 @@ def init_graph_construction(doi_input_list, search_depth, search_height, test_va
del edges
gc.collect()
-
- return(new_nodes, new_edges, error_doi_list)
+ return (new_nodes, new_edges, error_doi_list)
diff --git a/verarbeitung/dev_files/README.md b/verarbeitung/dev_files/README.md
index 53ccd02..f42d3f9 100644
--- a/verarbeitung/dev_files/README.md
+++ b/verarbeitung/dev_files/README.md
@@ -1 +1 @@
-Dieser Ordner ist nur für uns intern, um Testläufe mir echten DOIs zu starten.
\ No newline at end of file
+Dieser Ordner ist nur für uns intern, um Testläufe mit echten DOIs zu starten.
\ No newline at end of file
diff --git a/verarbeitung/dev_files/print_graph_test.py b/verarbeitung/dev_files/print_graph_test.py
index b45e909..9fa8441 100644
--- a/verarbeitung/dev_files/print_graph_test.py
+++ b/verarbeitung/dev_files/print_graph_test.py
@@ -4,24 +4,26 @@ Functions to test and print the nodes and edges sets
"""
-__authors__ = "Donna Löding, Alina Molkentin, Xinyi Tang, Judith Große, Malte Schokolowski"
+__authors__ = "Donna Löding, Alina Molkentin, Judith Große, Malte Schokolowski"
__email__ = "cis-project2021@zbh.uni-hamburg.de"
__status__ = "Production"
-#__copyright__ = ""
-#__credits__ = ["", "", "", ""]
-#__license__ = ""
-#__version__ = ""
-#__maintainer__ = ""
+
+# __copyright__ = ""
+# __credits__ = ["", "", "", ""]
+# __license__ = ""
+# __version__ = ""
+# __maintainer__ = ""
import sys
-#sys.path.insert(1, 'C:\Users\Malte\Git\CiS-Projekt\ci-s-projekt-verarbeitung\input')
+# sys.path.insert(1, 'C:\Users\Malte\Git\CiS-Projekt\ci-s-projekt-verarbeitung\input')
sys.path.append("../../")
from verarbeitung.construct_new_graph.initialize_graph import init_graph_construction
from verarbeitung.update_graph.import_from_json import input_from_json
from verarbeitung.update_graph.update_graph import update_graph
+
# a function to print nodes and edges from a graph
def print_graph(nodes, edges):
print("Knoten:\n")
@@ -29,11 +31,12 @@ def print_graph(nodes, edges):
print(node.title, "\n")
print("\nKanten:\n")
for edge in edges:
- print(edge,"\n")
+ print(edge, "\n")
print(len(nodes))
print(len(edges))
print(" ")
+
def print_extended_graph(nodes, edges):
print("Knoten:\n")
for node in nodes:
@@ -45,11 +48,12 @@ def print_extended_graph(nodes, edges):
print(citation.doi_url)
print("\nKanten:\n")
for edge in edges:
- print(edge,"\n")
+ print(edge, "\n")
print(len(nodes))
print(len(edges))
print(" ")
+
def print_simple(nodes, edges):
# for node in nodes:
# print(node)
@@ -59,36 +63,37 @@ def print_simple(nodes, edges):
print(len(edges))
print(" ")
-# program test with some random dois
+
+# program test with some random DOIs
def try_known_publications():
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://doi.org/10.1021/acs.jcim.9b00249')
doi_list.append('https://pubs.acs.org/doi/10.1021/acs.jcim.1c00203')
- #arr.append('https://pubs.acs.org/doi/10.1021/acs.jcim.9b00249')
+ # arr.append('https://pubs.acs.org/doi/10.1021/acs.jcim.9b00249')
doi_list.append('https://doi.org/10.1021/acs.jmedchem.0c01332')
- #arr.append('https://doi.org/10.1021/acs.jcim.0c00741')
+ # arr.append('https://doi.org/10.1021/acs.jcim.0c00741')
+
+ # arr.append('https://doi.org/10.1021/ci700007b')
+ # doi_list.append('https://doi.org/10.1021/acs.jcim.5b00292')
- #arr.append('https://doi.org/10.1021/ci700007b')
- #doi_list.append('https://doi.org/10.1021/acs.jcim.5b00292')
-
- #doi_list.append('https://pubs.acs.org/doi/10.1021/acs.jcim.0c00675')
- #url = sys.argv[1]
- #arr.append[url]
+ # doi_list.append('https://pubs.acs.org/doi/10.1021/acs.jcim.0c00675')
+ # url = sys.argv[1]
+ # arr.append[url]
+ nodes, edges = init_graph_construction(doi_list, 2, 2)
- nodes, edges = init_graph_construction(doi_list,2,2)
+ print_graph(nodes, edges)
- print_graph(nodes, edges)
+ return (nodes, edges)
- return(nodes, edges)
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')
- nodes, edges = init_graph_construction(doi_list,1,1)
- #print_simple(nodes, edges)
+ # doi_list.append('https://pubs.acs.org/doi/10.1021/acs.jcim.1c00203')
+ nodes, edges = init_graph_construction(doi_list, 1, 1)
+ # print_simple(nodes, edges)
# list_of_nodes_py, list_of_edges_py = input_from_json('json_text.json')
# doi_list = []
@@ -96,13 +101,15 @@ def try_delete_nodes():
# valid_nodes, valid_edges = update_graph(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')
- print_extended_graph(nodes,edges)
+ print_extended_graph(nodes, edges)
+
-#nodes, edges = try_known_publications()
-#nodes_new, edges_new = input_from_json("json_text.json")
-#print_graph(nodes_new, edges_new)
+# nodes, edges = try_known_publications()
+# nodes_new, edges_new = input_from_json("json_text.json")
+# print_graph(nodes_new, edges_new)
try_delete_nodes()
-#try_import()
\ No newline at end of file
+# try_import()
diff --git a/verarbeitung/get_pub_from_input.py b/verarbeitung/get_pub_from_input.py
index 6bdce3b..f27b72d 100644
--- a/verarbeitung/get_pub_from_input.py
+++ b/verarbeitung/get_pub_from_input.py
@@ -1,10 +1,10 @@
# -*- coding: utf-8 -*-
"""
-A function to return an object of Type Publication for a given doi
+A function to return an object of Type Publication for a given DOI
"""
-__authors__ = "Donna Löding, Alina Molkentin, Xinyi Tang, Judith Große, Malte Schokolowski"
+__authors__ = "Donna Löding, Alina Molkentin, Judith Große, Malte Schokolowski"
__email__ = "cis-project2021@zbh.uni-hamburg.de"
__status__ = "Production"
#__copyright__ = ""
@@ -14,7 +14,7 @@ __status__ = "Production"
#__maintainer__ = ""
-import sys
+import sys
from pathlib import Path
sys.path.append("../")
@@ -27,20 +27,20 @@ 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
+ :param test_var: variable to differentiate 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
+ 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 if it's a test and chooses appropriate function
+ if(test_var):
+ pub = input_test_func(pub_doi)
- #checks that it isnt a test and chooses standart-input function
- else:
+ # checks that it isn't a test and chooses standard-input function
+ else:
inter = Input()
try:
- pub = inter.get_publication(pub_doi) #creates an object of class Publication)
+ pub = inter.get_publication(pub_doi) # creates an object of class Publication)
except ValueError:
return(ValueError)
except IndexError:
diff --git a/verarbeitung/process_main.py b/verarbeitung/process_main.py
index 581c426..2567c24 100644
--- a/verarbeitung/process_main.py
+++ b/verarbeitung/process_main.py
@@ -4,7 +4,7 @@ main function to call to generate a graph representing citations between multipl
"""
-__authors__ = "Donna Löding, Alina Molkentin, Xinyi Tang, Judith Große, Malte Schokolowski"
+__authors__ = "Donna Löding, Alina Molkentin, Judith Große, Malte Schokolowski"
__email__ = "cis-project2021@zbh.uni-hamburg.de"
__status__ = "Production"
#__copyright__ = ""
@@ -24,6 +24,7 @@ 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
@@ -53,4 +54,3 @@ def Processing(url_list, search_depth, search_height, json_file = 'json_text.jso
output_to_json(nodes, edges, search_depth, search_height, json_file)
return error_doi_list
-
\ No newline at end of file
diff --git a/verarbeitung/test/README.md b/verarbeitung/test/README.md
index 91a9193..f457927 100644
--- a/verarbeitung/test/README.md
+++ b/verarbeitung/test/README.md
@@ -11,15 +11,14 @@ input_test.py
construct_graph_unittest.py
-- Führt diverse Tests zur Konstruktion des Graphen ohne Vorkenntnisse mit eigenen Beispielen und unserer Input_test Funktion aus.
+- 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.
+- Führt diverse Tests zum Updaten eines alten Graphen 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
diff --git a/verarbeitung/test/construct_graph_unittest.py b/verarbeitung/test/construct_graph_unittest.py
index d188727..1cef0dd 100644
--- a/verarbeitung/test/construct_graph_unittest.py
+++ b/verarbeitung/test/construct_graph_unittest.py
@@ -1,245 +1,279 @@
import unittest
-import sys
+import sys
sys.path.append("../")
-from verarbeitung.construct_new_graph.initialize_graph import init_graph_construction, initialize_nodes_list_test, complete_inner_edges_test
+from verarbeitung.construct_new_graph.initialize_graph import init_graph_construction, initialize_nodes_list_test, \
+ complete_inner_edges_test
from verarbeitung.construct_new_graph.add_citations_rec import get_cit_type_list, create_graph_structure_citations_test
from verarbeitung.construct_new_graph.export_to_json import format_nodes, format_edges
from verarbeitung.get_pub_from_input import input_test_func
+
class ConstructionTest(unittest.TestCase):
- maxDiff = None
+ maxDiff = None
+
+ def testCycle(self):
+ nodes, edges, err_list = init_graph_construction(['doiz1'], 1, 1, True, False)
+ doi_nodes = keep_only_dois(nodes)
+ self.assertCountEqual(doi_nodes, ['doiz1', 'doiz2'])
+ self.assertCountEqual(edges, [['doiz1', 'doiz2'], ['doiz2', 'doiz1']])
+ nodes, edges, err_list = init_graph_construction(['doiz1'], 2, 2, True, False)
+ doi_nodes = keep_only_dois(nodes)
+ self.assertCountEqual(doi_nodes, ['doiz1', 'doiz2'])
+ self.assertCountEqual(edges, [['doiz2', 'doiz1'], ['doiz1', 'doiz2']])
- def testCycle(self):
- nodes, edges, err_list = init_graph_construction(['doiz1'],1,1,True,False)
- doi_nodes = keep_only_dois(nodes)
- self.assertCountEqual(doi_nodes, ['doiz1', 'doiz2'])
- self.assertCountEqual(edges, [['doiz1', 'doiz2'], ['doiz2', 'doiz1']])
+ def testEmptyDepthHeight(self):
+ nodes, edges, err_list = init_graph_construction(['doi1'], 0, 0, True, False)
+ doi_nodes = keep_only_dois(nodes)
+ self.assertCountEqual(doi_nodes, ['doi1'])
+ self.assertCountEqual(edges, [])
- nodes, edges, err_list = init_graph_construction(['doiz1'],2,2,True,False)
- doi_nodes = keep_only_dois(nodes)
- self.assertCountEqual(doi_nodes, ['doiz1', 'doiz2'])
- self.assertCountEqual(edges, [['doiz2', 'doiz1'], ['doiz1', 'doiz2']])
+ nodes, edges, err_list = init_graph_construction(['doi1', 'doi2'], 0, 0, True, False)
+ doi_nodes = keep_only_dois(nodes)
+ self.assertCountEqual(doi_nodes, ['doi1', 'doi2'])
+ self.assertCountEqual(edges, [['doi1', 'doi2']])
+ nodes, edges, err_list = init_graph_construction(['doi1', 'doi2', 'doi3'], 0, 0, True, False)
+ doi_nodes = keep_only_dois(nodes)
+ self.assertCountEqual(doi_nodes, ['doi1', 'doi2', 'doi3'])
+ self.assertCountEqual(edges, [['doi3', 'doi1'], ['doi1', 'doi2']])
- def testEmptyDepthHeight(self):
- nodes, edges, err_list = init_graph_construction(['doi1'],0,0,True,False)
- doi_nodes = keep_only_dois(nodes)
- self.assertCountEqual(doi_nodes,['doi1'])
- self.assertCountEqual(edges, [])
+ def testInnerEdges(self):
+ nodes, edges, err_list = init_graph_construction(['doi_ie1'], 1, 1, True, False)
+ 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']])
- nodes, edges, err_list = init_graph_construction(['doi1', 'doi2'],0,0,True,False)
- doi_nodes = keep_only_dois(nodes)
- self.assertCountEqual(doi_nodes, ['doi1','doi2'])
- self.assertCountEqual(edges, [['doi1', 'doi2']])
+ def testRightHeight(self):
+ nodes, edges, err_list = init_graph_construction(['doi_h01'], 0, 1, True, False)
+ doi_nodes = keep_only_dois(nodes)
+ self.assertCountEqual(doi_nodes, ['doi_h01'])
+ self.assertCountEqual(edges, [])
- nodes, edges, err_list = init_graph_construction(['doi1', 'doi2', 'doi3'],0,0,True,False)
- doi_nodes = keep_only_dois(nodes)
- self.assertCountEqual(doi_nodes, ['doi1','doi2', 'doi3'])
- self.assertCountEqual(edges, [['doi3', 'doi1'], ['doi1', 'doi2']])
+ nodes, edges, err_list = init_graph_construction(['doi_h02'], 0, 1, True, False)
+ doi_nodes = keep_only_dois(nodes)
+ self.assertCountEqual(doi_nodes, ['doi_h02', 'doi_h1'])
+ self.assertCountEqual(edges, [['doi_h1', 'doi_h02']])
+ nodes, edges, err_list = init_graph_construction(['doi_h02'], 0, 2, True, False)
+ 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 testInnerEdges(self):
- nodes, edges, err_list = init_graph_construction(['doi_ie1'],1,1,True,False)
+ def testRightDepth(self):
+ nodes, edges, err_list = init_graph_construction(['doi_d01'], 1, 0, True, False)
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, err_list = init_graph_construction(['doi_h01'],0,1,True,False)
- doi_nodes = keep_only_dois(nodes)
- self.assertCountEqual(doi_nodes,['doi_h01'])
- self.assertCountEqual(edges, [])
-
- nodes, edges, err_list = init_graph_construction(['doi_h02'],0,1,True,False)
- doi_nodes = keep_only_dois(nodes)
- self.assertCountEqual(doi_nodes,['doi_h02','doi_h1'])
- self.assertCountEqual(edges, [['doi_h1','doi_h02']])
-
- nodes, edges, err_list = init_graph_construction(['doi_h02'],0,2,True,False)
- 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, err_list = init_graph_construction(['doi_d01'],1,0,True,False)
- doi_nodes = keep_only_dois(nodes)
- self.assertCountEqual(doi_nodes,['doi_d01'])
- self.assertCountEqual(edges, [])
-
- nodes, edges, err_list = init_graph_construction(['doi_d02'],1,0,True,False)
- doi_nodes = keep_only_dois(nodes)
- self.assertCountEqual(doi_nodes,['doi_d02','doi_d1'])
- self.assertCountEqual(edges, [['doi_d02','doi_d1']])
-
- nodes, edges, err_list = init_graph_construction(['doi_d02'],2,0,True,False)
- 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_incorrect_input_dois(self):
- nodes, edges, err_list = init_graph_construction(['doi1ic', 'doi2ic'],1,1, True, False)
- doi_nodes = keep_only_dois(nodes)
- self.assertCountEqual(doi_nodes, [])
- self.assertCountEqual(edges, [])
- self.assertCountEqual(err_list, ['doi1ic', 'doi2ic'])
-
- nodes, edges, err_list = init_graph_construction(['doi1ic', 'doi2ic'],2,2, True, False)
- doi_nodes = keep_only_dois(nodes)
- self.assertCountEqual(doi_nodes, [])
- self.assertCountEqual(edges, [])
- self.assertCountEqual(err_list, ['doi1ic', 'doi2ic'])
-
- nodes, edges, err_list = init_graph_construction(['doi1', 'doi2ic'],1,1, True, False)
- doi_nodes = keep_only_dois(nodes)
- self.assertCountEqual(doi_nodes, ['doi1', 'doi2', 'doi3'])
- self.assertCountEqual(edges, [['doi1', 'doi2'], ['doi3', 'doi1']])
- self.assertCountEqual(err_list, ['doi2ic'])
-
-
- ## Ab hier die Tests für die einzelnen Funktionen ##
-
- # initialize_graph.py:
-
- def test_initialize_nodes_list(self):
- references_pub_obj_list, citations_pub_obj_list = initialize_nodes_list_test(['doi_lg_1_i','doi_lg_2_i'], 0, 0, True)
- doi_references = keep_only_dois(references_pub_obj_list)
- doi_citations = keep_only_dois(citations_pub_obj_list)
- self.assertCountEqual(doi_references, [])
- self.assertCountEqual(doi_citations, [])
-
- references_pub_obj_list, citations_pub_obj_list = initialize_nodes_list_test(['doi_lg_1_i','doi_lg_2_i'], 1, 1, True)
- doi_references = keep_only_dois(references_pub_obj_list)
- doi_citations = keep_only_dois(citations_pub_obj_list)
- self.assertCountEqual(doi_references, ['doi_lg_1_d11','doi_lg_1_d12','doi_lg_2_d11','doi_lg_2_d12'])
- self.assertCountEqual(doi_citations, ['doi_lg_1_h11','doi_lg_1_h12','doi_cg_i','doi_lg_2_h11','doi_lg_2_h12'])
-
- def test_complete_inner_edges(self):
- pub_lg_1_i = input_test_func('doi_lg_1_i')
- pub_lg_1_i.group = 0
- pub_lg_1_h_12 = input_test_func('doi_lg_1_h12')
- pub_lg_1_h_12.group = 1
- pub_lg_1_d_12 = input_test_func('doi_lg_1_d12')
- pub_lg_1_d_12.group = -1
- nodes = [pub_lg_1_i, pub_lg_1_h_12, pub_lg_1_d_12]
- edges = [['doi_lg_1_i','doi_lg_1_d12'],['doi_lg_1_h12','doi_lg_1_i']]
- processed_nodes, processed_edges = complete_inner_edges_test(nodes, edges)
- self.assertCountEqual(processed_nodes, [pub_lg_1_i, pub_lg_1_h_12, pub_lg_1_d_12])
- self.assertCountEqual(processed_edges, [['doi_lg_1_i','doi_lg_1_d12'],['doi_lg_1_h12','doi_lg_1_i'],['doi_lg_1_h12','doi_lg_1_d12']])
-
- # add_citations_rec.py:
-
- def test_get_type_list(self):
- pub_lg_1_i = input_test_func('doi_lg_1_i')
- pub_lg_1_i.group = 0
- self.assertEqual(get_cit_type_list(pub_lg_1_i, "Hallo"), ValueError)
-
- pub_lg_1_h_12 = input_test_func('doi_lg_1_h12')
- pub_lg_1_h_12.group = 1
- pub_lg_1_h_12_refs = get_cit_type_list(pub_lg_1_h_12, "Reference")
- pub_lg_1_h_12_cits = get_cit_type_list(pub_lg_1_h_12, "Citation")
- self.assertCountEqual(keep_only_dois(pub_lg_1_h_12_refs), keep_only_dois(pub_lg_1_h_12.references))
- self.assertCountEqual(keep_only_dois(pub_lg_1_h_12_cits), keep_only_dois(pub_lg_1_h_12.citations))
-
- pub_lg_1_d_12 = input_test_func('doi_lg_1_d12')
- pub_lg_1_d_12.group = -1
- pub_lg_1_d_12_refs = get_cit_type_list(pub_lg_1_d_12, "Reference")
- pub_lg_1_d_12_cits = get_cit_type_list(pub_lg_1_d_12, "Citation")
- self.assertCountEqual(keep_only_dois(pub_lg_1_d_12_refs), keep_only_dois(pub_lg_1_d_12.references))
- self.assertCountEqual(keep_only_dois(pub_lg_1_d_12_cits), keep_only_dois(pub_lg_1_d_12.citations))
-
- def test_create_graph_structure_citations(self):
- pub_lg_1_i = input_test_func('doi_lg_1_i')
- pub_lg_1_i.group = 0
- pub_lg_1_h_11 = input_test_func('doi_lg_1_h11')
- pub_lg_1_h_11.group = 1
- pub_lg_1_h_12 = input_test_func('doi_lg_1_h12')
- pub_lg_1_h_12.group = 1
- pub_lg_1_d_11 = input_test_func('doi_lg_1_d11')
- pub_lg_1_d_11.group = -1
- pub_lg_1_d_12 = input_test_func('doi_lg_1_d12')
- pub_lg_1_d_12.group = -1
-
- # checks if citations/references are found and added
- return_nodes, return_edges, cit_list = create_graph_structure_citations_test(pub_lg_1_i, 1, 2, "Citation", True, [pub_lg_1_i, pub_lg_1_d_11, pub_lg_1_d_12],[['doi_lg_1_i','doi_lg_1_d11'],['doi_lg_1_i','doi_lg_1_d12']])
- self.assertCountEqual(return_nodes, [pub_lg_1_i, pub_lg_1_h_11, pub_lg_1_h_12, pub_lg_1_d_11, pub_lg_1_d_12])
- self.assertCountEqual(return_edges, [['doi_lg_1_i','doi_lg_1_d11'],['doi_lg_1_i','doi_lg_1_d12'],['doi_lg_1_h11','doi_lg_1_i'],['doi_lg_1_h12','doi_lg_1_i']])
- self.assertCountEqual(cit_list, [pub_lg_1_h_11, pub_lg_1_h_12])
-
- return_nodes, return_edges, cit_list = create_graph_structure_citations_test(pub_lg_1_i, 1, 2, "Reference", True, [pub_lg_1_i, pub_lg_1_h_11, pub_lg_1_h_12],[['doi_lg_1_h11','doi_lg_1_i'],['doi_lg_1_h12','doi_lg_1_i']])
- self.assertCountEqual(return_nodes, [pub_lg_1_i, pub_lg_1_h_11, pub_lg_1_h_12, pub_lg_1_d_11, pub_lg_1_d_12])
- self.assertCountEqual(return_edges, [['doi_lg_1_i','doi_lg_1_d11'],['doi_lg_1_i','doi_lg_1_d12'],['doi_lg_1_h11','doi_lg_1_i'],['doi_lg_1_h12','doi_lg_1_i']])
- self.assertCountEqual(cit_list, [pub_lg_1_d_11, pub_lg_1_d_12])
-
- # checks if max depth/height is checked before added
- return_nodes, return_edges, cit_list = create_graph_structure_citations_test(pub_lg_1_i, 1, 1, "Citation", True, [pub_lg_1_i, pub_lg_1_d_11, pub_lg_1_d_12],[['doi_lg_1_i','doi_lg_1_d11'],['doi_lg_1_i','doi_lg_1_d12']])
- self.assertCountEqual(return_nodes, [pub_lg_1_i, pub_lg_1_d_11, pub_lg_1_d_12])
- self.assertCountEqual(return_edges, [['doi_lg_1_i','doi_lg_1_d11'],['doi_lg_1_i','doi_lg_1_d12']])
- self.assertCountEqual(cit_list, [])
-
- return_nodes, return_edges, cit_list = create_graph_structure_citations_test(pub_lg_1_i, 1, 1, "Reference", True, [pub_lg_1_i, pub_lg_1_h_11, pub_lg_1_h_12],[['doi_lg_1_h11','doi_lg_1_i'],['doi_lg_1_h12','doi_lg_1_i']])
- self.assertCountEqual(return_nodes, [pub_lg_1_i, pub_lg_1_h_11, pub_lg_1_h_12])
- self.assertCountEqual(return_edges, [['doi_lg_1_h11','doi_lg_1_i'],['doi_lg_1_h12','doi_lg_1_i']])
- self.assertCountEqual(cit_list, [])
-
- # checks if max depth/height is checked before added but citation/reference from max depth/height found and added
- return_nodes, return_edges, cit_list = create_graph_structure_citations_test(pub_lg_1_i, 1, 1, "Citation", True, [pub_lg_1_i, pub_lg_1_d_11, pub_lg_1_d_12, pub_lg_1_h_11],[['doi_lg_1_i','doi_lg_1_d11'],['doi_lg_1_i','doi_lg_1_d12']])
- self.assertCountEqual(return_nodes, [pub_lg_1_i, pub_lg_1_d_11, pub_lg_1_d_12, pub_lg_1_h_11])
- self.assertCountEqual(return_edges, [['doi_lg_1_i','doi_lg_1_d11'],['doi_lg_1_i','doi_lg_1_d12'],['doi_lg_1_h11','doi_lg_1_i']])
- self.assertCountEqual(cit_list, [])
-
- return_nodes, return_edges, cit_list = create_graph_structure_citations_test(pub_lg_1_i, 1, 1, "Reference", True, [pub_lg_1_i, pub_lg_1_h_11, pub_lg_1_h_12, pub_lg_1_d_11],[['doi_lg_1_h11','doi_lg_1_i'],['doi_lg_1_h12','doi_lg_1_i']])
- self.assertCountEqual(return_nodes, [pub_lg_1_i, pub_lg_1_h_11, pub_lg_1_h_12, pub_lg_1_d_11])
- self.assertCountEqual(return_edges, [['doi_lg_1_h11','doi_lg_1_i'],['doi_lg_1_h12','doi_lg_1_i'],['doi_lg_1_i','doi_lg_1_d11']])
- self.assertCountEqual(cit_list, [])
-
-
-
- ## export_to_json.py:
-
- def test_format_nodes(self):
- pub_lg_1_i = input_test_func('doi_lg_1_i')
- pub_lg_1_i.group = 0
- pub_lg_1_h_11 = input_test_func('doi_lg_1_h11')
- pub_lg_1_h_11.group = 1
- pub_lg_1_d_11 = input_test_func('doi_lg_1_d11')
- pub_lg_1_d_11.group = -1
-
- return_list_of_node_dicts = format_nodes([pub_lg_1_i, pub_lg_1_h_11, pub_lg_1_d_11])
- check_list_of_node_dicts = [ {"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', "abstract": None, "group": 'Input', "depth": 0, "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', "abstract": None, "group": 'Citedby', "depth": 1, "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', "abstract": None, "group": 'Reference', "depth": -1, "citations": 1}]
-
- self.assertCountEqual(return_list_of_node_dicts, check_list_of_node_dicts)
-
-
- def test_format_edges(self):
- return_list_of_edges = format_edges([['doi_lg_1_i','doi_lg_1_d11'],['doi_lg_1_i','doi_lg_1_d12'],['doi_lg_1_h11','doi_lg_1_i'],['doi_lg_1_h12','doi_lg_1_i']])
- check_list_of_edges = [{"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'}]
-
- self.assertCountEqual(return_list_of_edges, check_list_of_edges)
-
-
-
-
-
+ self.assertCountEqual(doi_nodes, ['doi_d01'])
+ self.assertCountEqual(edges, [])
+
+ nodes, edges, err_list = init_graph_construction(['doi_d02'], 1, 0, True, False)
+ doi_nodes = keep_only_dois(nodes)
+ self.assertCountEqual(doi_nodes, ['doi_d02', 'doi_d1'])
+ self.assertCountEqual(edges, [['doi_d02', 'doi_d1']])
+
+ nodes, edges, err_list = init_graph_construction(['doi_d02'], 2, 0, True, False)
+ 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_incorrect_input_dois(self):
+ nodes, edges, err_list = init_graph_construction(['doi1ic', 'doi2ic'], 1, 1, True, False)
+ doi_nodes = keep_only_dois(nodes)
+ self.assertCountEqual(doi_nodes, [])
+ self.assertCountEqual(edges, [])
+ self.assertCountEqual(err_list, ['doi1ic', 'doi2ic'])
+
+ nodes, edges, err_list = init_graph_construction(['doi1ic', 'doi2ic'], 2, 2, True, False)
+ doi_nodes = keep_only_dois(nodes)
+ self.assertCountEqual(doi_nodes, [])
+ self.assertCountEqual(edges, [])
+ self.assertCountEqual(err_list, ['doi1ic', 'doi2ic'])
+
+ nodes, edges, err_list = init_graph_construction(['doi1', 'doi2ic'], 1, 1, True, False)
+ doi_nodes = keep_only_dois(nodes)
+ self.assertCountEqual(doi_nodes, ['doi1', 'doi2', 'doi3'])
+ self.assertCountEqual(edges, [['doi1', 'doi2'], ['doi3', 'doi1']])
+ self.assertCountEqual(err_list, ['doi2ic'])
+
+ ## From here the tests for the individual functions ##
+
+ # initialize_graph.py:
+
+ def test_initialize_nodes_list(self):
+ references_pub_obj_list, citations_pub_obj_list = initialize_nodes_list_test(['doi_lg_1_i', 'doi_lg_2_i'], 0, 0,
+ True)
+ doi_references = keep_only_dois(references_pub_obj_list)
+ doi_citations = keep_only_dois(citations_pub_obj_list)
+ self.assertCountEqual(doi_references, [])
+ self.assertCountEqual(doi_citations, [])
+
+ references_pub_obj_list, citations_pub_obj_list = initialize_nodes_list_test(['doi_lg_1_i', 'doi_lg_2_i'], 1, 1,
+ True)
+ doi_references = keep_only_dois(references_pub_obj_list)
+ doi_citations = keep_only_dois(citations_pub_obj_list)
+ self.assertCountEqual(doi_references, ['doi_lg_1_d11', 'doi_lg_1_d12', 'doi_lg_2_d11', 'doi_lg_2_d12'])
+ self.assertCountEqual(doi_citations,
+ ['doi_lg_1_h11', 'doi_lg_1_h12', 'doi_cg_i', 'doi_lg_2_h11', 'doi_lg_2_h12'])
+
+ def test_complete_inner_edges(self):
+ pub_lg_1_i = input_test_func('doi_lg_1_i')
+ pub_lg_1_i.group = 0
+ pub_lg_1_h_12 = input_test_func('doi_lg_1_h12')
+ pub_lg_1_h_12.group = 1
+ pub_lg_1_d_12 = input_test_func('doi_lg_1_d12')
+ pub_lg_1_d_12.group = -1
+ nodes = [pub_lg_1_i, pub_lg_1_h_12, pub_lg_1_d_12]
+ edges = [['doi_lg_1_i', 'doi_lg_1_d12'], ['doi_lg_1_h12', 'doi_lg_1_i']]
+ processed_nodes, processed_edges = complete_inner_edges_test(nodes, edges)
+ self.assertCountEqual(processed_nodes, [pub_lg_1_i, pub_lg_1_h_12, pub_lg_1_d_12])
+ self.assertCountEqual(processed_edges, [['doi_lg_1_i', 'doi_lg_1_d12'], ['doi_lg_1_h12', 'doi_lg_1_i'],
+ ['doi_lg_1_h12', 'doi_lg_1_d12']])
+
+ # add_citations_rec.py:
+
+ def test_get_type_list(self):
+ pub_lg_1_i = input_test_func('doi_lg_1_i')
+ pub_lg_1_i.group = 0
+ self.assertEqual(get_cit_type_list(pub_lg_1_i, "Hallo"), ValueError)
+
+ pub_lg_1_h_12 = input_test_func('doi_lg_1_h12')
+ pub_lg_1_h_12.group = 1
+ pub_lg_1_h_12_refs = get_cit_type_list(pub_lg_1_h_12, "Reference")
+ pub_lg_1_h_12_cits = get_cit_type_list(pub_lg_1_h_12, "Citation")
+ self.assertCountEqual(keep_only_dois(pub_lg_1_h_12_refs), keep_only_dois(pub_lg_1_h_12.references))
+ self.assertCountEqual(keep_only_dois(pub_lg_1_h_12_cits), keep_only_dois(pub_lg_1_h_12.citations))
+
+ pub_lg_1_d_12 = input_test_func('doi_lg_1_d12')
+ pub_lg_1_d_12.group = -1
+ pub_lg_1_d_12_refs = get_cit_type_list(pub_lg_1_d_12, "Reference")
+ pub_lg_1_d_12_cits = get_cit_type_list(pub_lg_1_d_12, "Citation")
+ self.assertCountEqual(keep_only_dois(pub_lg_1_d_12_refs), keep_only_dois(pub_lg_1_d_12.references))
+ self.assertCountEqual(keep_only_dois(pub_lg_1_d_12_cits), keep_only_dois(pub_lg_1_d_12.citations))
+
+ def test_create_graph_structure_citations(self):
+ pub_lg_1_i = input_test_func('doi_lg_1_i')
+ pub_lg_1_i.group = 0
+ pub_lg_1_h_11 = input_test_func('doi_lg_1_h11')
+ pub_lg_1_h_11.group = 1
+ pub_lg_1_h_12 = input_test_func('doi_lg_1_h12')
+ pub_lg_1_h_12.group = 1
+ pub_lg_1_d_11 = input_test_func('doi_lg_1_d11')
+ pub_lg_1_d_11.group = -1
+ pub_lg_1_d_12 = input_test_func('doi_lg_1_d12')
+ pub_lg_1_d_12.group = -1
+
+ # checks if citations/references are found and added
+ return_nodes, return_edges, cit_list = create_graph_structure_citations_test(pub_lg_1_i, 1, 2, "Citation", True,
+ [pub_lg_1_i, pub_lg_1_d_11,
+ pub_lg_1_d_12],
+ [['doi_lg_1_i', 'doi_lg_1_d11'],
+ ['doi_lg_1_i', 'doi_lg_1_d12']])
+ self.assertCountEqual(return_nodes, [pub_lg_1_i, pub_lg_1_h_11, pub_lg_1_h_12, pub_lg_1_d_11, pub_lg_1_d_12])
+ self.assertCountEqual(return_edges, [['doi_lg_1_i', 'doi_lg_1_d11'], ['doi_lg_1_i', 'doi_lg_1_d12'],
+ ['doi_lg_1_h11', 'doi_lg_1_i'], ['doi_lg_1_h12', 'doi_lg_1_i']])
+ self.assertCountEqual(cit_list, [pub_lg_1_h_11, pub_lg_1_h_12])
+
+ return_nodes, return_edges, cit_list = create_graph_structure_citations_test(pub_lg_1_i, 1, 2, "Reference",
+ True, [pub_lg_1_i, pub_lg_1_h_11,
+ pub_lg_1_h_12],
+ [['doi_lg_1_h11', 'doi_lg_1_i'],
+ ['doi_lg_1_h12', 'doi_lg_1_i']])
+ self.assertCountEqual(return_nodes, [pub_lg_1_i, pub_lg_1_h_11, pub_lg_1_h_12, pub_lg_1_d_11, pub_lg_1_d_12])
+ self.assertCountEqual(return_edges, [['doi_lg_1_i', 'doi_lg_1_d11'], ['doi_lg_1_i', 'doi_lg_1_d12'],
+ ['doi_lg_1_h11', 'doi_lg_1_i'], ['doi_lg_1_h12', 'doi_lg_1_i']])
+ self.assertCountEqual(cit_list, [pub_lg_1_d_11, pub_lg_1_d_12])
+
+ # checks if max depth/height is checked before added
+ return_nodes, return_edges, cit_list = create_graph_structure_citations_test(pub_lg_1_i, 1, 1, "Citation", True,
+ [pub_lg_1_i, pub_lg_1_d_11,
+ pub_lg_1_d_12],
+ [['doi_lg_1_i', 'doi_lg_1_d11'],
+ ['doi_lg_1_i', 'doi_lg_1_d12']])
+ self.assertCountEqual(return_nodes, [pub_lg_1_i, pub_lg_1_d_11, pub_lg_1_d_12])
+ self.assertCountEqual(return_edges, [['doi_lg_1_i', 'doi_lg_1_d11'], ['doi_lg_1_i', 'doi_lg_1_d12']])
+ self.assertCountEqual(cit_list, [])
+
+ return_nodes, return_edges, cit_list = create_graph_structure_citations_test(pub_lg_1_i, 1, 1, "Reference",
+ True, [pub_lg_1_i, pub_lg_1_h_11,
+ pub_lg_1_h_12],
+ [['doi_lg_1_h11', 'doi_lg_1_i'],
+ ['doi_lg_1_h12', 'doi_lg_1_i']])
+ self.assertCountEqual(return_nodes, [pub_lg_1_i, pub_lg_1_h_11, pub_lg_1_h_12])
+ self.assertCountEqual(return_edges, [['doi_lg_1_h11', 'doi_lg_1_i'], ['doi_lg_1_h12', 'doi_lg_1_i']])
+ self.assertCountEqual(cit_list, [])
+
+ # checks if max depth/height is checked before added but citation/reference from max depth/height found and added
+ return_nodes, return_edges, cit_list = create_graph_structure_citations_test(pub_lg_1_i, 1, 1, "Citation", True,
+ [pub_lg_1_i, pub_lg_1_d_11,
+ pub_lg_1_d_12, pub_lg_1_h_11],
+ [['doi_lg_1_i', 'doi_lg_1_d11'],
+ ['doi_lg_1_i', 'doi_lg_1_d12']])
+ self.assertCountEqual(return_nodes, [pub_lg_1_i, pub_lg_1_d_11, pub_lg_1_d_12, pub_lg_1_h_11])
+ self.assertCountEqual(return_edges, [['doi_lg_1_i', 'doi_lg_1_d11'], ['doi_lg_1_i', 'doi_lg_1_d12'],
+ ['doi_lg_1_h11', 'doi_lg_1_i']])
+ self.assertCountEqual(cit_list, [])
+
+ return_nodes, return_edges, cit_list = create_graph_structure_citations_test(pub_lg_1_i, 1, 1, "Reference",
+ True, [pub_lg_1_i, pub_lg_1_h_11,
+ pub_lg_1_h_12,
+ pub_lg_1_d_11],
+ [['doi_lg_1_h11', 'doi_lg_1_i'],
+ ['doi_lg_1_h12', 'doi_lg_1_i']])
+ self.assertCountEqual(return_nodes, [pub_lg_1_i, pub_lg_1_h_11, pub_lg_1_h_12, pub_lg_1_d_11])
+ self.assertCountEqual(return_edges, [['doi_lg_1_h11', 'doi_lg_1_i'], ['doi_lg_1_h12', 'doi_lg_1_i'],
+ ['doi_lg_1_i', 'doi_lg_1_d11']])
+ self.assertCountEqual(cit_list, [])
+
+ # export_to_json.py:
+
+ def test_format_nodes(self):
+ pub_lg_1_i = input_test_func('doi_lg_1_i')
+ pub_lg_1_i.group = 0
+ pub_lg_1_h_11 = input_test_func('doi_lg_1_h11')
+ pub_lg_1_h_11.group = 1
+ pub_lg_1_d_11 = input_test_func('doi_lg_1_d11')
+ pub_lg_1_d_11.group = -1
+
+ return_list_of_node_dicts = format_nodes([pub_lg_1_i, pub_lg_1_h_11, pub_lg_1_d_11])
+ check_list_of_node_dicts = [
+ {"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', "abstract": None, "group": 'Input', "depth": 0, "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', "abstract": None, "group": 'Citedby', "depth": 1,
+ "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', "abstract": None, "group": 'Reference',
+ "depth": -1, "citations": 1}]
+
+ self.assertCountEqual(return_list_of_node_dicts, check_list_of_node_dicts)
+
+ def test_format_edges(self):
+ return_list_of_edges = format_edges(
+ [['doi_lg_1_i', 'doi_lg_1_d11'], ['doi_lg_1_i', 'doi_lg_1_d12'], ['doi_lg_1_h11', 'doi_lg_1_i'],
+ ['doi_lg_1_h12', 'doi_lg_1_i']])
+ check_list_of_edges = [{"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'}]
+
+ self.assertCountEqual(return_list_of_edges, check_list_of_edges)
+
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
+ 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
+ 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
+ unittest.main()
diff --git a/verarbeitung/test/input_test.py b/verarbeitung/test/input_test.py
index 352f983..7164e23 100644
--- a/verarbeitung/test/input_test.py
+++ b/verarbeitung/test/input_test.py
@@ -1,4 +1,5 @@
import sys
+
sys.path.append("../")
from input.publication import Publication, Citation
@@ -6,10 +7,10 @@ from input.publication import Publication, Citation
def input_test_func(pub_doi):
'''
- :param pub_doi: pub doi to find publication in list_of_arrays
+ :param pub_doi: pub DOI to find publication in list_of_arrays
:type pub_doi: String
- returns the publication class for given doi
+ returns the publication class for given DOI
'''
for array in list_of_arrays:
@@ -22,10 +23,10 @@ def input_test_func(pub_doi):
def cit(list_doi, cit_type):
'''
- :param list_doi list of citation dois to get their Citation Class
+ :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
+ returns a list of citations objects for given DOI list
'''
cits = []
@@ -36,69 +37,112 @@ def cit(list_doi, 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']]
+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'], []]
+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_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_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, large_graph_2_d24, crossed_graph_h21, crossed_graph_h22, crossed_graph_h11,
- crossed_graph_i, crossed_graph_d11, crossed_graph_d12, crossed_graph_d21, crossed_graph_d22]
+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, large_graph_2_d24, crossed_graph_h21, crossed_graph_h22, crossed_graph_h11,
+ crossed_graph_i, crossed_graph_d11, crossed_graph_d12, crossed_graph_d21, crossed_graph_d22]
diff --git a/verarbeitung/test/update_graph_unittest.py b/verarbeitung/test/update_graph_unittest.py
index 62504e5..1ebb0d1 100644
--- a/verarbeitung/test/update_graph_unittest.py
+++ b/verarbeitung/test/update_graph_unittest.py
@@ -1,9 +1,8 @@
import unittest
-import sys
+import sys
from pathlib import Path
-
sys.path.append("../")
from verarbeitung.construct_new_graph.initialize_graph import init_graph_construction
@@ -14,382 +13,405 @@ from verarbeitung.update_graph.update_depth import reduce_max_height_depth_test,
from verarbeitung.update_graph.update_edges import back_to_valid_edges
from verarbeitung.update_graph.delete_nodes_edges import search_ref_cit_graph_rec_test
from verarbeitung.update_graph.compare_old_and_new_node_lists import compare_old_and_new_node_lists
-from verarbeitung.update_graph.connect_new_input import find_furthermost_citations_test, complete_changed_group_nodes_test
+from verarbeitung.update_graph.connect_new_input import find_furthermost_citations_test, \
+ complete_changed_group_nodes_test
from verarbeitung.get_pub_from_input import input_test_func
+
class UpdatingTest(unittest.TestCase):
- maxDiff = None
-
- def test_deleted_input_dois(self):
- nodes_old_single, edges_old_single, err_list = init_graph_construction(['doi_lg_1_i'],2,2,True)
- nodes_old_both, edges_old_both, err_list = init_graph_construction(['doi_lg_1_i','doi_lg_2_i'],2,2,True)
- output_to_json(nodes_old_both, edges_old_both, 2, 2, test_var=True)
- nodes_new_single, edges_new_single, err_list = 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, err_list = init_graph_construction(['doi_cg_i'],3,3,True)
- nodes_old_two, edges_old_two, err_list = init_graph_construction(['doi_lg_1_i','doi_cg_i'],3,3,True)
- nodes_old_three, edges_old_three, err_list = 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, err_list = init_graph_construction(['doi_lg_1_i'],2,0,True)
- nodes_height_1, edges_height_1, err_list = init_graph_construction(['doi_lg_1_i'],2,1,True)
- nodes_height_2, edges_height_2, err_list = init_graph_construction(['doi_lg_1_i'],2,2,True)
-
- output_to_json(nodes_height_2, edges_height_2, 2, 2, 'new_height.json', True)
- nodes_new_height_1, edges_new_height_1, err_list = 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, err_list = init_graph_construction(['doi_lg_1_i'],2,2,True)
- output_to_json(nodes_height_2, edges_height_2, 2, 2, 'new_height.json', True)
- nodes_new_height_0, edges_new_height_0, err_list = 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 test_ref_to_input(self):
- nodes, edges, err_list = init_graph_construction(['doi_cg_i'], 2, 2, True)
- nodes_2, edges_2, err_list_2 = init_graph_construction(['doi_cg_d11'], 2, 2, True)
- output_to_json(nodes, edges, 2, 2, 'ref_to_input.json')
- new_nodes, new_edges, new_err_list = update_graph(['doi_cg_d11'], 'ref_to_input.json', 2, 2, True)
- self.assertCountEqual(new_nodes, nodes_2)
- self.assertCountEqual(new_edges, edges_2)
-
- nodes, edges, err_list = init_graph_construction(['doi_cg_i','doi_lg_2_i'], 2, 2, True)
- nodes_2, edges_2, err_list_2 = init_graph_construction(['doi_cg_d11','doi_lg_2_i'], 2, 2, True)
-
- output_to_json(nodes, edges, 2, 2, 'ref_to_input.json')
- new_nodes, new_edges, new_err_list = update_graph(['doi_cg_d11','doi_lg_2_i'], 'ref_to_input.json', 2, 2, True)
- self.assertCountEqual(new_nodes, nodes_2)
- self.assertCountEqual(new_edges, edges_2)
-
- output_to_json(nodes_2, edges_2, 2, 2, 'ref_to_input.json')
- new_nodes, new_edges, new_err_list = update_graph(['doi_cg_d11','doi_lg_2_i'], 'ref_to_input.json', 2, 2, True)
- self.assertCountEqual(new_nodes, nodes_2)
- self.assertCountEqual(new_edges, edges_2)
-
- nodes, edges, err_list = init_graph_construction(['doi_cg_i','doi_lg_2_i'], 2, 2, True)
- nodes_2, edges_2, err_list_2 = init_graph_construction(['doi_cg_i','doi_lg_2_h11','doi_lg_1_i'], 3, 3, True)
-
- output_to_json(nodes_2, edges_2, 2, 2, 'ref_to_input.json')
- new_nodes, new_edges, new_err_list = update_graph(['doi_cg_i','doi_lg_2_i'], 'ref_to_input.json', 2, 2, True)
- self.assertCountEqual(new_nodes, nodes)
- self.assertCountEqual(new_edges, edges)
-
-
-
-
-
-
- ## Ab hier die Tests für die einzelnen Funktionen ##
-
- # update_graph.py:
-
- def test_get_old_input_dois(self):
- pub_lg_1_i = input_test_func('doi_lg_1_i')
- pub_lg_1_i.group = 0
- pub_lg_1_h_11 = input_test_func('doi_lg_1_h11')
- pub_lg_1_h_11.group = 1
- pub_lg_1_d_11 = input_test_func('doi_lg_1_d11')
- pub_lg_1_d_11.group = -1
- old_pubs = [pub_lg_1_i, pub_lg_1_h_11, pub_lg_1_d_11]
- self.assertCountEqual(get_old_input_dois(old_pubs),['doi_lg_1_i'])
-
- # hard to test because we only have dois as test objects and no urls variant
- def test_get_new_input_dois(self):
- new_dois = ['doi_lg_2_i', 'doi_lg_1_i', 'doi_cg_i']
- self.assertCountEqual(get_new_input_dois(new_dois, True), ['doi_lg_2_i', 'doi_lg_1_i', 'doi_cg_i'])
-
-
- # update_depth.py:
-
- def test_reduce_max_height(self):
- pub_lg_2_i = input_test_func('doi_lg_2_i')
- pub_lg_2_i.group = 0
- pub_lg_2_h_11 = input_test_func('doi_lg_2_h11')
- pub_lg_2_h_11.group = 1
- pub_lg_2_d_11 = input_test_func('doi_lg_2_d11')
- pub_lg_2_d_11.group = -1
- pub_lg_2_h_21 = input_test_func('doi_lg_2_h21')
- pub_lg_2_h_21.group = 2
- pub_lg_2_d_21 = input_test_func('doi_lg_2_d21')
- pub_lg_2_d_21.group = -2
- pubs = [pub_lg_2_i, pub_lg_2_h_11, pub_lg_2_h_21, pub_lg_2_d_11, pub_lg_2_d_21]
- self.assertCountEqual(reduce_max_height_depth_test(pubs, 2, "Height"), [pub_lg_2_i, pub_lg_2_h_11, pub_lg_2_h_21, pub_lg_2_d_11, pub_lg_2_d_21])
- self.assertCountEqual(reduce_max_height_depth_test(pubs, 1, "Height"), [pub_lg_2_i, pub_lg_2_h_11, pub_lg_2_d_11, pub_lg_2_d_21])
- self.assertCountEqual(reduce_max_height_depth_test(pubs, 0, "Height"), [pub_lg_2_i, pub_lg_2_d_11, pub_lg_2_d_21])
-
- def test_reduce_max_depth(self):
- pub_lg_2_i = input_test_func('doi_lg_2_i')
- pub_lg_2_i.group = 0
- pub_lg_2_h_11 = input_test_func('doi_lg_2_h11')
- pub_lg_2_h_11.group = 1
- pub_lg_2_d_11 = input_test_func('doi_lg_2_d11')
- pub_lg_2_d_11.group = -1
- pub_lg_2_h_21 = input_test_func('doi_lg_2_h21')
- pub_lg_2_h_21.group = 2
- pub_lg_2_d_21 = input_test_func('doi_lg_2_d21')
- pub_lg_2_d_21.group = -2
- pubs = [pub_lg_2_i, pub_lg_2_h_11, pub_lg_2_h_21, pub_lg_2_d_11, pub_lg_2_d_21]
- self.assertCountEqual(reduce_max_height_depth_test(pubs, 2, "Depth"), [pub_lg_2_i, pub_lg_2_h_11, pub_lg_2_h_21, pub_lg_2_d_11, pub_lg_2_d_21])
- self.assertCountEqual(reduce_max_height_depth_test(pubs, 1, "Depth"), [pub_lg_2_i, pub_lg_2_d_11, pub_lg_2_h_11, pub_lg_2_h_21])
- self.assertCountEqual(reduce_max_height_depth_test(pubs, 0, "Depth"), [pub_lg_2_i, pub_lg_2_h_11, pub_lg_2_h_21])
-
- def test_get_old_max_references(self):
- pub_lg_2_i = input_test_func('doi_lg_2_i')
- pub_lg_2_i.group = 0
- pub_lg_2_h_11 = input_test_func('doi_lg_2_h11')
- pub_lg_2_h_11.group = 1
- pub_lg_2_d_11 = input_test_func('doi_lg_2_d11')
- pub_lg_2_d_11.group = -1
- pub_lg_2_h_21 = input_test_func('doi_lg_2_h21')
- pub_lg_2_h_21.group = 2
- pub_lg_2_d_21 = input_test_func('doi_lg_2_d21')
- pub_lg_2_d_21.group = -2
- pub_lg_2_d_22 = input_test_func('doi_lg_2_d22')
- pub_lg_2_d_22.group = -2
- pubs = [pub_lg_2_i, pub_lg_2_h_11, pub_lg_2_h_21, pub_lg_2_d_11, pub_lg_2_d_21, pub_lg_2_d_22]
- self.assertCountEqual(get_old_max_references_citations_test(pubs, 2, "Depth"), [pub_lg_2_d_21,pub_lg_2_d_22])
-
- def test_get_old_max_citations(self):
- pub_lg_2_i = input_test_func('doi_lg_2_i')
- pub_lg_2_i.group = 0
- pub_lg_2_h_11 = input_test_func('doi_lg_2_h11')
- pub_lg_2_h_11.group = 1
- pub_lg_2_d_11 = input_test_func('doi_lg_2_d11')
- pub_lg_2_d_11.group = -1
- pub_lg_2_h_21 = input_test_func('doi_lg_2_h21')
- pub_lg_2_h_21.group = 2
- pub_lg_2_h_22 = input_test_func('doi_lg_2_h22')
- pub_lg_2_h_22.group = 2
- pub_lg_2_d_21 = input_test_func('doi_lg_2_d21')
- pub_lg_2_d_21.group = -2
- pubs = [pub_lg_2_i, pub_lg_2_h_11, pub_lg_2_h_21, pub_lg_2_h_22,pub_lg_2_d_11, pub_lg_2_d_21]
- self.assertCountEqual(get_old_max_references_citations_test(pubs, 2, "Height"), [pub_lg_2_h_21,pub_lg_2_h_22])
-
- # import_from_json.py:
-
- def test_input_from_json(self):
- nodes_old, edges_old, err_list = init_graph_construction(['doi_lg_1_i'],2,2,True)
- output_to_json(nodes_old, edges_old, 2, 2, test_var = True)
- nodes_new, edges_new, old_depth, old_height = input_from_json('test_output.json')
- self.assertCountEqual(nodes_old,nodes_new)
- self.assertCountEqual(edges_old, edges_new)
-
- # update_edges.py:
-
- def test_back_to_valid_edges(self):
- pub_lg_2_i = input_test_func('doi_lg_2_i')
- pub_lg_2_i.group = 0
- pub_lg_2_h_11 = input_test_func('doi_lg_2_h11')
- pub_lg_2_h_11.group = 1
- pub_lg_2_d_11 = input_test_func('doi_lg_2_d11')
- pub_lg_2_d_11.group = -1
- pubs = [pub_lg_2_i, pub_lg_2_h_11, pub_lg_2_d_11]
- edges = [['doi_lg_2_h11','doi_lg_2_i'],['doi_lg_2_i','doi_lg_2_d11'],['doi_lg_2_h21','doi_lg_2_h11'],['doi_lg_2_i','doi_lg_2_d21']]
- back_to_valid_edges(edges, pubs)
- self.assertCountEqual([['doi_lg_2_h11','doi_lg_2_i'],['doi_lg_2_i','doi_lg_2_d11']],edges)
-
- # delete_nodes_edges.py:
-
- def test_search_ref_graph_rec(self):
- pub_lg_2_i = input_test_func('doi_lg_2_i')
- pub_lg_2_i.group = 0
- pub_lg_2_h11 = input_test_func('doi_lg_2_h11')
- pub_lg_2_h11.group = 1
- pub_lg_2_h12 = input_test_func('doi_lg_2_h12')
- pub_lg_2_h12.group = 1
- pub_lg_2_d11 = input_test_func('doi_lg_2_d11')
- pub_lg_2_d11.group = -1
- pub_lg_2_d12 = input_test_func('doi_lg_2_d12')
- pub_lg_2_d12.group = -1
- pub_lg_2_h21 = input_test_func('doi_lg_2_h21')
- pub_lg_2_h21.group = 2
- pub_lg_2_h22 = input_test_func('doi_lg_2_h22')
- pub_lg_2_h22.group = 2
- pub_lg_2_d21 = input_test_func('doi_lg_2_d21')
- pub_lg_2_d21.group = -2
-
- pub_cg_i = input_test_func('doi_cg_i')
- pub_cg_i.group = 0
- pub_cg_h11 = input_test_func('doi_cg_h11')
- pub_cg_h11.group = 1
- pub_cg_d12 = input_test_func('doi_cg_d11')
- pub_cg_d12.group = -1
- pub_cg_d11 = input_test_func('doi_cg_d12')
- pub_cg_d11.group = -1
- pubs = [pub_lg_2_i, pub_lg_2_h11, pub_lg_2_h12, pub_lg_2_d11, pub_lg_2_d12, pub_lg_2_h21, pub_lg_2_h22, pub_lg_2_d21, pub_cg_i, pub_cg_d11, pub_cg_d12, pub_cg_h11]
- usable_nodes = search_ref_cit_graph_rec_test(pubs, [pub_cg_i], 2, "Citation")
- self.assertCountEqual(usable_nodes, [pub_cg_h11, pub_lg_2_h11, pub_lg_2_h21, pub_lg_2_h22])
-
- # compare_old_and_new_node_lists.py:
-
- def test_compare_old_and_new_nodes(self):
- old_input = ['doi_lg_1_i', 'doi_lg_2_i']
- new_input = ['doi_lg_1_i', 'doi_cg_i']
- common_nodes, inserted_nodes, deleted_nodes = compare_old_and_new_node_lists(old_input, new_input)
- self.assertCountEqual(common_nodes, ['doi_lg_1_i'])
- self.assertCountEqual(inserted_nodes, ['doi_cg_i'])
- self.assertCountEqual(deleted_nodes, ['doi_lg_2_i'])
-
-
- # connect_new_input.py:
-
- def test_find_furthermost_citations(self):
- pub_lg_2_i = input_test_func('doi_lg_2_i')
- pub_lg_2_i.group = 0
- pub_lg_2_h11 = input_test_func('doi_lg_2_h11')
- pub_lg_2_h11.group = 1
- pub_lg_2_h12 = input_test_func('doi_lg_2_h12')
- pub_lg_2_h12.group = 1
- pub_lg_2_d11 = input_test_func('doi_lg_2_d11')
- pub_lg_2_d11.group = -1
- pub_lg_2_d12 = input_test_func('doi_lg_2_d12')
- pub_lg_2_d12.group = -1
- pub_lg_2_h21 = input_test_func('doi_lg_2_h21')
- pub_lg_2_h21.group = 2
- pub_lg_2_h22 = input_test_func('doi_lg_2_h22')
- pub_lg_2_h22.group = 2
- pub_lg_2_d21 = input_test_func('doi_lg_2_d21')
- pub_lg_2_d21.group = -2
- pub_lg_2_d22 = input_test_func('doi_lg_2_d22')
- pub_lg_2_d22.group = -2
- pubs = [pub_lg_2_i, pub_lg_2_h11, pub_lg_2_h12, pub_lg_2_d11, pub_lg_2_d12, pub_lg_2_h21, pub_lg_2_h22, pub_lg_2_d21, pub_lg_2_d22]
-
- self.assertCountEqual(find_furthermost_citations_test(pubs, [], pub_lg_2_h11, 2, 2, "Citation"),[pub_lg_2_h21, pub_lg_2_h22])
- self.assertCountEqual(find_furthermost_citations_test(pubs, [], pub_lg_2_h11, 2, 1, "Citation"),[pub_lg_2_h21, pub_lg_2_h22])
-
- self.assertCountEqual(find_furthermost_citations_test(pubs, [], pub_lg_2_d11, 2, 2, "Reference"),[pub_lg_2_d21, pub_lg_2_i])
- self.assertCountEqual(find_furthermost_citations_test(pubs, [], pub_lg_2_d11, 2, 1, "Reference"),[pub_lg_2_d21, pub_lg_2_i])
-
-
- def test_complete_changed_group_nodes(self):
- pub_cg_i = input_test_func('doi_cg_i')
- pub_cg_i.group = 0
- pub_cg_h11 = input_test_func('doi_cg_h11')
- pub_cg_h11.group = 1
- pub_cg_h21 = input_test_func('doi_cg_h21')
- pub_cg_h21.group = 2
- pub_cg_h22 = input_test_func('doi_cg_h22')
- pub_cg_h22.group = 2
- pub_cg_d11 = input_test_func('doi_cg_d11')
- pub_cg_d11.group = -1
- pub_cg_d12 = input_test_func('doi_cg_d12')
- pub_cg_d12.group = -1
- pub_cg_d21 = input_test_func('doi_cg_d21')
- pub_cg_d21.group = -2
- pub_cg_d22 = input_test_func('doi_cg_d22')
- pub_cg_d22.group = -2
-
- pub_lg_1_h23 = input_test_func('doi_lg_1_h23')
- pub_lg_1_h23.group = 2
- pub_lg_1_d23 = input_test_func('doi_lg_1_d23')
- pub_lg_1_d23.group = -2
-
- pub_lg_2_i = input_test_func('doi_lg_2_i')
- pub_lg_2_i.group = 0
- pub_lg_2_h11 = input_test_func('doi_lg_2_h11')
- pub_lg_2_h11.group = 1
- pub_lg_2_h21 = input_test_func('doi_lg_2_h21')
- pub_lg_2_h21.group = 2
- pub_lg_2_h22 = input_test_func('doi_lg_2_h22')
- pub_lg_2_h22.group = 2
- pub_lg_2_d11 = input_test_func('doi_lg_2_d11')
- pub_lg_2_d11.group = -1
- pub_lg_2_d12 = input_test_func('doi_lg_2_d12')
- pub_lg_2_d12.group = -1
- pub_lg_2_d21 = input_test_func('doi_lg_2_d21')
- pub_lg_2_d21.group = -2
- pub_lg_2_d22 = input_test_func('doi_lg_2_d22')
- pub_lg_2_d22.group = -2
- pub_lg_2_d23 = input_test_func('doi_lg_2_d23')
- pub_lg_2_d23.group = -2
- pub_lg_2_d24 = input_test_func('doi_lg_2_d24')
- pub_lg_2_d24.group = -2
-
-
- moved_1_pub_cg_i = input_test_func('doi_cg_i')
- moved_1_pub_cg_i.group = 1
- moved_1_pub_cg_h11 = input_test_func('doi_cg_h11')
- moved_1_pub_cg_h11.group = 2
- moved_1_pub_cg_h21 = input_test_func('doi_cg_h21')
- moved_1_pub_cg_h21.group = 3
- moved_1_pub_cg_h22 = input_test_func('doi_cg_h22')
- moved_1_pub_cg_h22.group = 3
- moved_1_pub_cg_d11 = input_test_func('doi_cg_d11')
- moved_1_pub_cg_d11.group = 0
-
- moved_1_pub_cg_d21 = input_test_func('doi_cg_d21')
- moved_1_pub_cg_d21.group = -1
-
- moved_1_pub_lg_1_h23 = input_test_func('doi_lg_1_h23')
- moved_1_pub_lg_1_h23.group = 2
- moved_1_pub_lg_1_d23 = input_test_func('doi_lg_1_d23')
- moved_1_pub_lg_1_d23.group = -1
-
- moved_1_pub_lg_2_h11 = input_test_func('doi_lg_2_h11')
- moved_1_pub_lg_2_h11.group = 1
-
-
- moved_2_pub_cg_i = input_test_func('doi_cg_i')
- moved_2_pub_cg_i.group = -1
- moved_2_pub_cg_d11 = input_test_func('doi_cg_d11')
- moved_2_pub_cg_d11.group = -2
- moved_2_pub_cg_d12 = input_test_func('doi_cg_d12')
- moved_2_pub_cg_d12.group = -2
- moved_2_pub_cg_d21 = input_test_func('doi_cg_d21')
- moved_2_pub_cg_d21.group = -3
- moved_2_pub_cg_d22 = input_test_func('doi_cg_d22')
- moved_2_pub_cg_d22.group = -3
-
- moved_2_pub_lg_1_d23 = input_test_func('doi_lg_1_d23')
- moved_2_pub_lg_1_d23.group = -3
-
- moved_2_pub_lg_2_h21 = input_test_func('doi_lg_2_h21')
- moved_2_pub_lg_2_h21.group = 1
- moved_2_pub_lg_2_h22 = input_test_func('doi_lg_2_h22')
- moved_2_pub_lg_2_h22.group = 1
- moved_2_pub_lg_2_h11 = input_test_func('doi_lg_2_h11')
- moved_2_pub_lg_2_h11.group = 0
- moved_2_pub_lg_2_i = input_test_func('doi_lg_2_i')
- moved_2_pub_lg_2_i.group = -2
- moved_2_pub_lg_2_d11 = input_test_func('doi_lg_2_d11')
- moved_2_pub_lg_2_d11.group = -2
- moved_2_pub_lg_2_d12 = input_test_func('doi_lg_2_d12')
- moved_2_pub_lg_2_d12.group = -2
- moved_2_pub_lg_2_d21 = input_test_func('doi_lg_2_d21')
- moved_2_pub_lg_2_d21.group = -3
- moved_2_pub_lg_2_d22 = input_test_func('doi_lg_2_d22')
- moved_2_pub_lg_2_d22.group = -3
- moved_2_pub_lg_2_d23 = input_test_func('doi_lg_2_d23')
- moved_2_pub_lg_2_d23.group = -3
- moved_2_pub_lg_2_d24 = input_test_func('doi_lg_2_d24')
- moved_2_pub_lg_2_d24.group = -3
-
- pubs = [pub_cg_i, pub_cg_h11, pub_cg_h21, pub_cg_h22, pub_cg_d11, pub_cg_d12, pub_cg_d21, pub_cg_d22, pub_lg_1_h23, pub_lg_1_d23, pub_lg_2_h21, pub_lg_2_h22, pub_lg_2_h11, pub_lg_2_i, pub_lg_2_d11, pub_lg_2_d12, pub_lg_2_d21, pub_lg_2_d22, pub_lg_2_d23, pub_lg_2_d24]
- edges = []
- nodes, edges, handled_nodes = complete_changed_group_nodes_test(pubs, edges, 'doi_cg_d11', 2, 2, 2, 2)
- self.assertCountEqual(nodes, [moved_1_pub_cg_d11, moved_1_pub_cg_d21, moved_1_pub_lg_1_d23, moved_1_pub_cg_i, moved_1_pub_lg_1_h23, moved_1_pub_cg_h11, moved_1_pub_lg_2_h11])
- self.assertCountEqual(edges, [['doi_cg_d11','doi_lg_1_d23'],['doi_cg_d11','doi_cg_d21'],['doi_cg_i','doi_cg_d11'],['doi_lg_1_h23','doi_cg_i'],['doi_cg_h11','doi_cg_i'],['doi_lg_2_h11','doi_cg_i']])
-
- nodes, edges, handled_nodes = complete_changed_group_nodes_test(pubs, edges, 'doi_lg_2_h11', 2, 2, 3, 3)
- self.assertCountEqual(nodes, [moved_2_pub_cg_i, moved_2_pub_cg_d11, moved_2_pub_lg_1_d23, moved_2_pub_cg_d21, moved_2_pub_cg_d12, moved_2_pub_cg_d22, moved_2_pub_lg_2_h21, moved_2_pub_lg_2_h22, moved_2_pub_lg_2_h11, moved_2_pub_lg_2_i, moved_2_pub_lg_2_d11, moved_2_pub_lg_2_d21, moved_2_pub_lg_2_d12, moved_2_pub_lg_2_d22, moved_2_pub_lg_2_d23, moved_2_pub_lg_2_d24])
- self.assertCountEqual(edges, [['doi_cg_d11','doi_lg_1_d23'],['doi_cg_d11','doi_cg_d21'],['doi_cg_i','doi_cg_d11'],['doi_cg_i','doi_cg_d12'],['doi_cg_d12','doi_cg_d22'],['doi_lg_2_h11','doi_cg_i'],['doi_cg_i','doi_lg_2_i'],['doi_lg_2_h21','doi_lg_2_h11'],['doi_lg_2_h22','doi_lg_2_h11'],['doi_lg_2_h11','doi_lg_2_i'],['doi_lg_2_i','doi_lg_2_d11'],['doi_lg_2_d11','doi_lg_2_i'],['doi_lg_2_d11','doi_lg_2_d21'],['doi_lg_2_i','doi_lg_2_d12'],['doi_lg_2_d12','doi_lg_2_d22'],['doi_lg_2_d12','doi_lg_2_d23'],['doi_lg_2_d12','doi_lg_2_d24']])
+ maxDiff = None
+
+ def test_deleted_input_dois(self):
+ nodes_old_single, edges_old_single, err_list = init_graph_construction(['doi_lg_1_i'], 2, 2, True)
+ nodes_old_both, edges_old_both, err_list = init_graph_construction(['doi_lg_1_i', 'doi_lg_2_i'], 2, 2, True)
+ output_to_json(nodes_old_both, edges_old_both, 2, 2, test_var=True)
+ nodes_new_single, edges_new_single, err_list = 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, err_list = init_graph_construction(['doi_cg_i'], 3, 3, True)
+ nodes_old_two, edges_old_two, err_list = init_graph_construction(['doi_lg_1_i', 'doi_cg_i'], 3, 3, True)
+ nodes_old_three, edges_old_three, err_list = 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, err_list = init_graph_construction(['doi_lg_1_i'], 2, 0, True)
+ nodes_height_1, edges_height_1, err_list = init_graph_construction(['doi_lg_1_i'], 2, 1, True)
+ nodes_height_2, edges_height_2, err_list = init_graph_construction(['doi_lg_1_i'], 2, 2, True)
+
+ output_to_json(nodes_height_2, edges_height_2, 2, 2, 'new_height.json', True)
+ nodes_new_height_1, edges_new_height_1, err_list = 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, err_list = init_graph_construction(['doi_lg_1_i'], 2, 2, True)
+ output_to_json(nodes_height_2, edges_height_2, 2, 2, 'new_height.json', True)
+ nodes_new_height_0, edges_new_height_0, err_list = 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 test_ref_to_input(self):
+ nodes, edges, err_list = init_graph_construction(['doi_cg_i'], 2, 2, True)
+ nodes_2, edges_2, err_list_2 = init_graph_construction(['doi_cg_d11'], 2, 2, True)
+ output_to_json(nodes, edges, 2, 2, 'ref_to_input.json')
+ new_nodes, new_edges, new_err_list = update_graph(['doi_cg_d11'], 'ref_to_input.json', 2, 2, True)
+ self.assertCountEqual(new_nodes, nodes_2)
+ self.assertCountEqual(new_edges, edges_2)
+
+ nodes, edges, err_list = init_graph_construction(['doi_cg_i', 'doi_lg_2_i'], 2, 2, True)
+ nodes_2, edges_2, err_list_2 = init_graph_construction(['doi_cg_d11', 'doi_lg_2_i'], 2, 2, True)
+
+ output_to_json(nodes, edges, 2, 2, 'ref_to_input.json')
+ new_nodes, new_edges, new_err_list = update_graph(['doi_cg_d11', 'doi_lg_2_i'], 'ref_to_input.json', 2, 2, True)
+ self.assertCountEqual(new_nodes, nodes_2)
+ self.assertCountEqual(new_edges, edges_2)
+
+ output_to_json(nodes_2, edges_2, 2, 2, 'ref_to_input.json')
+ new_nodes, new_edges, new_err_list = update_graph(['doi_cg_d11', 'doi_lg_2_i'], 'ref_to_input.json', 2, 2, True)
+ self.assertCountEqual(new_nodes, nodes_2)
+ self.assertCountEqual(new_edges, edges_2)
+
+ nodes, edges, err_list = init_graph_construction(['doi_cg_i', 'doi_lg_2_i'], 2, 2, True)
+ nodes_2, edges_2, err_list_2 = init_graph_construction(['doi_cg_i', 'doi_lg_2_h11', 'doi_lg_1_i'], 3, 3, True)
+
+ output_to_json(nodes_2, edges_2, 2, 2, 'ref_to_input.json')
+ new_nodes, new_edges, new_err_list = update_graph(['doi_cg_i', 'doi_lg_2_i'], 'ref_to_input.json', 2, 2, True)
+ self.assertCountEqual(new_nodes, nodes)
+ self.assertCountEqual(new_edges, edges)
+
+ ## From here the tests for the individual functions ##
+
+ # update_graph.py:
+
+ def test_get_old_input_dois(self):
+ pub_lg_1_i = input_test_func('doi_lg_1_i')
+ pub_lg_1_i.group = 0
+ pub_lg_1_h_11 = input_test_func('doi_lg_1_h11')
+ pub_lg_1_h_11.group = 1
+ pub_lg_1_d_11 = input_test_func('doi_lg_1_d11')
+ pub_lg_1_d_11.group = -1
+ old_pubs = [pub_lg_1_i, pub_lg_1_h_11, pub_lg_1_d_11]
+ self.assertCountEqual(get_old_input_dois(old_pubs), ['doi_lg_1_i'])
+
+ # hard to test because we only have DOIs as test objects and no urls variant
+ def test_get_new_input_dois(self):
+ new_dois = ['doi_lg_2_i', 'doi_lg_1_i', 'doi_cg_i']
+ self.assertCountEqual(get_new_input_dois(new_dois, True), ['doi_lg_2_i', 'doi_lg_1_i', 'doi_cg_i'])
+
+ # update_depth.py:
+
+ def test_reduce_max_height(self):
+ pub_lg_2_i = input_test_func('doi_lg_2_i')
+ pub_lg_2_i.group = 0
+ pub_lg_2_h_11 = input_test_func('doi_lg_2_h11')
+ pub_lg_2_h_11.group = 1
+ pub_lg_2_d_11 = input_test_func('doi_lg_2_d11')
+ pub_lg_2_d_11.group = -1
+ pub_lg_2_h_21 = input_test_func('doi_lg_2_h21')
+ pub_lg_2_h_21.group = 2
+ pub_lg_2_d_21 = input_test_func('doi_lg_2_d21')
+ pub_lg_2_d_21.group = -2
+ pubs = [pub_lg_2_i, pub_lg_2_h_11, pub_lg_2_h_21, pub_lg_2_d_11, pub_lg_2_d_21]
+ self.assertCountEqual(reduce_max_height_depth_test(pubs, 2, "Height"),
+ [pub_lg_2_i, pub_lg_2_h_11, pub_lg_2_h_21, pub_lg_2_d_11, pub_lg_2_d_21])
+ self.assertCountEqual(reduce_max_height_depth_test(pubs, 1, "Height"),
+ [pub_lg_2_i, pub_lg_2_h_11, pub_lg_2_d_11, pub_lg_2_d_21])
+ self.assertCountEqual(reduce_max_height_depth_test(pubs, 0, "Height"),
+ [pub_lg_2_i, pub_lg_2_d_11, pub_lg_2_d_21])
+
+ def test_reduce_max_depth(self):
+ pub_lg_2_i = input_test_func('doi_lg_2_i')
+ pub_lg_2_i.group = 0
+ pub_lg_2_h_11 = input_test_func('doi_lg_2_h11')
+ pub_lg_2_h_11.group = 1
+ pub_lg_2_d_11 = input_test_func('doi_lg_2_d11')
+ pub_lg_2_d_11.group = -1
+ pub_lg_2_h_21 = input_test_func('doi_lg_2_h21')
+ pub_lg_2_h_21.group = 2
+ pub_lg_2_d_21 = input_test_func('doi_lg_2_d21')
+ pub_lg_2_d_21.group = -2
+ pubs = [pub_lg_2_i, pub_lg_2_h_11, pub_lg_2_h_21, pub_lg_2_d_11, pub_lg_2_d_21]
+ self.assertCountEqual(reduce_max_height_depth_test(pubs, 2, "Depth"),
+ [pub_lg_2_i, pub_lg_2_h_11, pub_lg_2_h_21, pub_lg_2_d_11, pub_lg_2_d_21])
+ self.assertCountEqual(reduce_max_height_depth_test(pubs, 1, "Depth"),
+ [pub_lg_2_i, pub_lg_2_d_11, pub_lg_2_h_11, pub_lg_2_h_21])
+ self.assertCountEqual(reduce_max_height_depth_test(pubs, 0, "Depth"),
+ [pub_lg_2_i, pub_lg_2_h_11, pub_lg_2_h_21])
+
+ def test_get_old_max_references(self):
+ pub_lg_2_i = input_test_func('doi_lg_2_i')
+ pub_lg_2_i.group = 0
+ pub_lg_2_h_11 = input_test_func('doi_lg_2_h11')
+ pub_lg_2_h_11.group = 1
+ pub_lg_2_d_11 = input_test_func('doi_lg_2_d11')
+ pub_lg_2_d_11.group = -1
+ pub_lg_2_h_21 = input_test_func('doi_lg_2_h21')
+ pub_lg_2_h_21.group = 2
+ pub_lg_2_d_21 = input_test_func('doi_lg_2_d21')
+ pub_lg_2_d_21.group = -2
+ pub_lg_2_d_22 = input_test_func('doi_lg_2_d22')
+ pub_lg_2_d_22.group = -2
+ pubs = [pub_lg_2_i, pub_lg_2_h_11, pub_lg_2_h_21, pub_lg_2_d_11, pub_lg_2_d_21, pub_lg_2_d_22]
+ self.assertCountEqual(get_old_max_references_citations_test(pubs, 2, "Depth"), [pub_lg_2_d_21, pub_lg_2_d_22])
+
+ def test_get_old_max_citations(self):
+ pub_lg_2_i = input_test_func('doi_lg_2_i')
+ pub_lg_2_i.group = 0
+ pub_lg_2_h_11 = input_test_func('doi_lg_2_h11')
+ pub_lg_2_h_11.group = 1
+ pub_lg_2_d_11 = input_test_func('doi_lg_2_d11')
+ pub_lg_2_d_11.group = -1
+ pub_lg_2_h_21 = input_test_func('doi_lg_2_h21')
+ pub_lg_2_h_21.group = 2
+ pub_lg_2_h_22 = input_test_func('doi_lg_2_h22')
+ pub_lg_2_h_22.group = 2
+ pub_lg_2_d_21 = input_test_func('doi_lg_2_d21')
+ pub_lg_2_d_21.group = -2
+ pubs = [pub_lg_2_i, pub_lg_2_h_11, pub_lg_2_h_21, pub_lg_2_h_22, pub_lg_2_d_11, pub_lg_2_d_21]
+ self.assertCountEqual(get_old_max_references_citations_test(pubs, 2, "Height"), [pub_lg_2_h_21, pub_lg_2_h_22])
+
+ # import_from_json.py:
+
+ def test_input_from_json(self):
+ nodes_old, edges_old, err_list = init_graph_construction(['doi_lg_1_i'], 2, 2, True)
+ output_to_json(nodes_old, edges_old, 2, 2, test_var=True)
+ nodes_new, edges_new, old_depth, old_height = input_from_json('test_output.json')
+ self.assertCountEqual(nodes_old, nodes_new)
+ self.assertCountEqual(edges_old, edges_new)
+
+ # update_edges.py:
+
+ def test_back_to_valid_edges(self):
+ pub_lg_2_i = input_test_func('doi_lg_2_i')
+ pub_lg_2_i.group = 0
+ pub_lg_2_h_11 = input_test_func('doi_lg_2_h11')
+ pub_lg_2_h_11.group = 1
+ pub_lg_2_d_11 = input_test_func('doi_lg_2_d11')
+ pub_lg_2_d_11.group = -1
+ pubs = [pub_lg_2_i, pub_lg_2_h_11, pub_lg_2_d_11]
+ edges = [['doi_lg_2_h11', 'doi_lg_2_i'], ['doi_lg_2_i', 'doi_lg_2_d11'], ['doi_lg_2_h21', 'doi_lg_2_h11'],
+ ['doi_lg_2_i', 'doi_lg_2_d21']]
+ back_to_valid_edges(edges, pubs)
+ self.assertCountEqual([['doi_lg_2_h11', 'doi_lg_2_i'], ['doi_lg_2_i', 'doi_lg_2_d11']], edges)
+
+ # delete_nodes_edges.py:
+
+ def test_search_ref_graph_rec(self):
+ pub_lg_2_i = input_test_func('doi_lg_2_i')
+ pub_lg_2_i.group = 0
+ pub_lg_2_h11 = input_test_func('doi_lg_2_h11')
+ pub_lg_2_h11.group = 1
+ pub_lg_2_h12 = input_test_func('doi_lg_2_h12')
+ pub_lg_2_h12.group = 1
+ pub_lg_2_d11 = input_test_func('doi_lg_2_d11')
+ pub_lg_2_d11.group = -1
+ pub_lg_2_d12 = input_test_func('doi_lg_2_d12')
+ pub_lg_2_d12.group = -1
+ pub_lg_2_h21 = input_test_func('doi_lg_2_h21')
+ pub_lg_2_h21.group = 2
+ pub_lg_2_h22 = input_test_func('doi_lg_2_h22')
+ pub_lg_2_h22.group = 2
+ pub_lg_2_d21 = input_test_func('doi_lg_2_d21')
+ pub_lg_2_d21.group = -2
+
+ pub_cg_i = input_test_func('doi_cg_i')
+ pub_cg_i.group = 0
+ pub_cg_h11 = input_test_func('doi_cg_h11')
+ pub_cg_h11.group = 1
+ pub_cg_d12 = input_test_func('doi_cg_d11')
+ pub_cg_d12.group = -1
+ pub_cg_d11 = input_test_func('doi_cg_d12')
+ pub_cg_d11.group = -1
+ pubs = [pub_lg_2_i, pub_lg_2_h11, pub_lg_2_h12, pub_lg_2_d11, pub_lg_2_d12, pub_lg_2_h21, pub_lg_2_h22,
+ pub_lg_2_d21, pub_cg_i, pub_cg_d11, pub_cg_d12, pub_cg_h11]
+ usable_nodes = search_ref_cit_graph_rec_test(pubs, [pub_cg_i], 2, "Citation")
+ self.assertCountEqual(usable_nodes, [pub_cg_h11, pub_lg_2_h11, pub_lg_2_h21, pub_lg_2_h22])
+
+ # compare_old_and_new_node_lists.py:
+
+ def test_compare_old_and_new_nodes(self):
+ old_input = ['doi_lg_1_i', 'doi_lg_2_i']
+ new_input = ['doi_lg_1_i', 'doi_cg_i']
+ common_nodes, inserted_nodes, deleted_nodes = compare_old_and_new_node_lists(old_input, new_input)
+ self.assertCountEqual(common_nodes, ['doi_lg_1_i'])
+ self.assertCountEqual(inserted_nodes, ['doi_cg_i'])
+ self.assertCountEqual(deleted_nodes, ['doi_lg_2_i'])
+
+ # connect_new_input.py:
+
+ def test_find_furthermost_citations(self):
+ pub_lg_2_i = input_test_func('doi_lg_2_i')
+ pub_lg_2_i.group = 0
+ pub_lg_2_h11 = input_test_func('doi_lg_2_h11')
+ pub_lg_2_h11.group = 1
+ pub_lg_2_h12 = input_test_func('doi_lg_2_h12')
+ pub_lg_2_h12.group = 1
+ pub_lg_2_d11 = input_test_func('doi_lg_2_d11')
+ pub_lg_2_d11.group = -1
+ pub_lg_2_d12 = input_test_func('doi_lg_2_d12')
+ pub_lg_2_d12.group = -1
+ pub_lg_2_h21 = input_test_func('doi_lg_2_h21')
+ pub_lg_2_h21.group = 2
+ pub_lg_2_h22 = input_test_func('doi_lg_2_h22')
+ pub_lg_2_h22.group = 2
+ pub_lg_2_d21 = input_test_func('doi_lg_2_d21')
+ pub_lg_2_d21.group = -2
+ pub_lg_2_d22 = input_test_func('doi_lg_2_d22')
+ pub_lg_2_d22.group = -2
+ pubs = [pub_lg_2_i, pub_lg_2_h11, pub_lg_2_h12, pub_lg_2_d11, pub_lg_2_d12, pub_lg_2_h21, pub_lg_2_h22,
+ pub_lg_2_d21, pub_lg_2_d22]
+
+ self.assertCountEqual(find_furthermost_citations_test(pubs, [], pub_lg_2_h11, 2, 2, "Citation"),
+ [pub_lg_2_h21, pub_lg_2_h22])
+ self.assertCountEqual(find_furthermost_citations_test(pubs, [], pub_lg_2_h11, 2, 1, "Citation"),
+ [pub_lg_2_h21, pub_lg_2_h22])
+
+ self.assertCountEqual(find_furthermost_citations_test(pubs, [], pub_lg_2_d11, 2, 2, "Reference"),
+ [pub_lg_2_d21, pub_lg_2_i])
+ self.assertCountEqual(find_furthermost_citations_test(pubs, [], pub_lg_2_d11, 2, 1, "Reference"),
+ [pub_lg_2_d21, pub_lg_2_i])
+
+ def test_complete_changed_group_nodes(self):
+ pub_cg_i = input_test_func('doi_cg_i')
+ pub_cg_i.group = 0
+ pub_cg_h11 = input_test_func('doi_cg_h11')
+ pub_cg_h11.group = 1
+ pub_cg_h21 = input_test_func('doi_cg_h21')
+ pub_cg_h21.group = 2
+ pub_cg_h22 = input_test_func('doi_cg_h22')
+ pub_cg_h22.group = 2
+ pub_cg_d11 = input_test_func('doi_cg_d11')
+ pub_cg_d11.group = -1
+ pub_cg_d12 = input_test_func('doi_cg_d12')
+ pub_cg_d12.group = -1
+ pub_cg_d21 = input_test_func('doi_cg_d21')
+ pub_cg_d21.group = -2
+ pub_cg_d22 = input_test_func('doi_cg_d22')
+ pub_cg_d22.group = -2
+
+ pub_lg_1_h23 = input_test_func('doi_lg_1_h23')
+ pub_lg_1_h23.group = 2
+ pub_lg_1_d23 = input_test_func('doi_lg_1_d23')
+ pub_lg_1_d23.group = -2
+
+ pub_lg_2_i = input_test_func('doi_lg_2_i')
+ pub_lg_2_i.group = 0
+ pub_lg_2_h11 = input_test_func('doi_lg_2_h11')
+ pub_lg_2_h11.group = 1
+ pub_lg_2_h21 = input_test_func('doi_lg_2_h21')
+ pub_lg_2_h21.group = 2
+ pub_lg_2_h22 = input_test_func('doi_lg_2_h22')
+ pub_lg_2_h22.group = 2
+ pub_lg_2_d11 = input_test_func('doi_lg_2_d11')
+ pub_lg_2_d11.group = -1
+ pub_lg_2_d12 = input_test_func('doi_lg_2_d12')
+ pub_lg_2_d12.group = -1
+ pub_lg_2_d21 = input_test_func('doi_lg_2_d21')
+ pub_lg_2_d21.group = -2
+ pub_lg_2_d22 = input_test_func('doi_lg_2_d22')
+ pub_lg_2_d22.group = -2
+ pub_lg_2_d23 = input_test_func('doi_lg_2_d23')
+ pub_lg_2_d23.group = -2
+ pub_lg_2_d24 = input_test_func('doi_lg_2_d24')
+ pub_lg_2_d24.group = -2
+
+ moved_1_pub_cg_i = input_test_func('doi_cg_i')
+ moved_1_pub_cg_i.group = 1
+ moved_1_pub_cg_h11 = input_test_func('doi_cg_h11')
+ moved_1_pub_cg_h11.group = 2
+ moved_1_pub_cg_h21 = input_test_func('doi_cg_h21')
+ moved_1_pub_cg_h21.group = 3
+ moved_1_pub_cg_h22 = input_test_func('doi_cg_h22')
+ moved_1_pub_cg_h22.group = 3
+ moved_1_pub_cg_d11 = input_test_func('doi_cg_d11')
+ moved_1_pub_cg_d11.group = 0
+
+ moved_1_pub_cg_d21 = input_test_func('doi_cg_d21')
+ moved_1_pub_cg_d21.group = -1
+
+ moved_1_pub_lg_1_h23 = input_test_func('doi_lg_1_h23')
+ moved_1_pub_lg_1_h23.group = 2
+ moved_1_pub_lg_1_d23 = input_test_func('doi_lg_1_d23')
+ moved_1_pub_lg_1_d23.group = -1
+
+ moved_1_pub_lg_2_h11 = input_test_func('doi_lg_2_h11')
+ moved_1_pub_lg_2_h11.group = 1
+
+ moved_2_pub_cg_i = input_test_func('doi_cg_i')
+ moved_2_pub_cg_i.group = -1
+ moved_2_pub_cg_d11 = input_test_func('doi_cg_d11')
+ moved_2_pub_cg_d11.group = -2
+ moved_2_pub_cg_d12 = input_test_func('doi_cg_d12')
+ moved_2_pub_cg_d12.group = -2
+ moved_2_pub_cg_d21 = input_test_func('doi_cg_d21')
+ moved_2_pub_cg_d21.group = -3
+ moved_2_pub_cg_d22 = input_test_func('doi_cg_d22')
+ moved_2_pub_cg_d22.group = -3
+
+ moved_2_pub_lg_1_d23 = input_test_func('doi_lg_1_d23')
+ moved_2_pub_lg_1_d23.group = -3
+
+ moved_2_pub_lg_2_h21 = input_test_func('doi_lg_2_h21')
+ moved_2_pub_lg_2_h21.group = 1
+ moved_2_pub_lg_2_h22 = input_test_func('doi_lg_2_h22')
+ moved_2_pub_lg_2_h22.group = 1
+ moved_2_pub_lg_2_h11 = input_test_func('doi_lg_2_h11')
+ moved_2_pub_lg_2_h11.group = 0
+ moved_2_pub_lg_2_i = input_test_func('doi_lg_2_i')
+ moved_2_pub_lg_2_i.group = -2
+ moved_2_pub_lg_2_d11 = input_test_func('doi_lg_2_d11')
+ moved_2_pub_lg_2_d11.group = -2
+ moved_2_pub_lg_2_d12 = input_test_func('doi_lg_2_d12')
+ moved_2_pub_lg_2_d12.group = -2
+ moved_2_pub_lg_2_d21 = input_test_func('doi_lg_2_d21')
+ moved_2_pub_lg_2_d21.group = -3
+ moved_2_pub_lg_2_d22 = input_test_func('doi_lg_2_d22')
+ moved_2_pub_lg_2_d22.group = -3
+ moved_2_pub_lg_2_d23 = input_test_func('doi_lg_2_d23')
+ moved_2_pub_lg_2_d23.group = -3
+ moved_2_pub_lg_2_d24 = input_test_func('doi_lg_2_d24')
+ moved_2_pub_lg_2_d24.group = -3
+
+ pubs = [pub_cg_i, pub_cg_h11, pub_cg_h21, pub_cg_h22, pub_cg_d11, pub_cg_d12, pub_cg_d21, pub_cg_d22,
+ pub_lg_1_h23, pub_lg_1_d23, pub_lg_2_h21, pub_lg_2_h22, pub_lg_2_h11, pub_lg_2_i, pub_lg_2_d11,
+ pub_lg_2_d12, pub_lg_2_d21, pub_lg_2_d22, pub_lg_2_d23, pub_lg_2_d24]
+ edges = []
+ nodes, edges, handled_nodes = complete_changed_group_nodes_test(pubs, edges, 'doi_cg_d11', 2, 2, 2, 2)
+ self.assertCountEqual(nodes, [moved_1_pub_cg_d11, moved_1_pub_cg_d21, moved_1_pub_lg_1_d23, moved_1_pub_cg_i,
+ moved_1_pub_lg_1_h23, moved_1_pub_cg_h11, moved_1_pub_lg_2_h11])
+ self.assertCountEqual(edges,
+ [['doi_cg_d11', 'doi_lg_1_d23'], ['doi_cg_d11', 'doi_cg_d21'], ['doi_cg_i', 'doi_cg_d11'],
+ ['doi_lg_1_h23', 'doi_cg_i'], ['doi_cg_h11', 'doi_cg_i'], ['doi_lg_2_h11', 'doi_cg_i']])
+
+ nodes, edges, handled_nodes = complete_changed_group_nodes_test(pubs, edges, 'doi_lg_2_h11', 2, 2, 3, 3)
+ self.assertCountEqual(nodes, [moved_2_pub_cg_i, moved_2_pub_cg_d11, moved_2_pub_lg_1_d23, moved_2_pub_cg_d21,
+ moved_2_pub_cg_d12, moved_2_pub_cg_d22, moved_2_pub_lg_2_h21,
+ moved_2_pub_lg_2_h22, moved_2_pub_lg_2_h11, moved_2_pub_lg_2_i,
+ moved_2_pub_lg_2_d11, moved_2_pub_lg_2_d21, moved_2_pub_lg_2_d12,
+ moved_2_pub_lg_2_d22, moved_2_pub_lg_2_d23, moved_2_pub_lg_2_d24])
+ self.assertCountEqual(edges,
+ [['doi_cg_d11', 'doi_lg_1_d23'], ['doi_cg_d11', 'doi_cg_d21'], ['doi_cg_i', 'doi_cg_d11'],
+ ['doi_cg_i', 'doi_cg_d12'], ['doi_cg_d12', 'doi_cg_d22'], ['doi_lg_2_h11', 'doi_cg_i'],
+ ['doi_cg_i', 'doi_lg_2_i'], ['doi_lg_2_h21', 'doi_lg_2_h11'],
+ ['doi_lg_2_h22', 'doi_lg_2_h11'], ['doi_lg_2_h11', 'doi_lg_2_i'],
+ ['doi_lg_2_i', 'doi_lg_2_d11'], ['doi_lg_2_d11', 'doi_lg_2_i'],
+ ['doi_lg_2_d11', 'doi_lg_2_d21'], ['doi_lg_2_i', 'doi_lg_2_d12'],
+ ['doi_lg_2_d12', 'doi_lg_2_d22'], ['doi_lg_2_d12', 'doi_lg_2_d23'],
+ ['doi_lg_2_d12', 'doi_lg_2_d24']])
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
+ 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
+ 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
+ unittest.main()
diff --git a/verarbeitung/update_graph/README.md b/verarbeitung/update_graph/README.md
index 0193c1e..05dfbc9 100644
--- a/verarbeitung/update_graph/README.md
+++ b/verarbeitung/update_graph/README.md
@@ -36,6 +36,5 @@ update_depth.py
## Authors
- Donna Löding
- Alina Molkentin
-- Xinyi Tang
- Judith Große
- Malte Schokolowski
\ No newline at end of file
diff --git a/verarbeitung/update_graph/compare_old_and_new_node_lists.py b/verarbeitung/update_graph/compare_old_and_new_node_lists.py
index f816fea..a899a8a 100644
--- a/verarbeitung/update_graph/compare_old_and_new_node_lists.py
+++ b/verarbeitung/update_graph/compare_old_and_new_node_lists.py
@@ -1,37 +1,39 @@
#!/usr/bin/env python3
from collections import Counter
-def compare_old_and_new_node_lists(old_doi_node_list,new_doi_node_list):
+
+def compare_old_and_new_node_lists(old_doi_node_list, new_doi_node_list):
'''
- :param old_doi_node_list: list of dois from old graph
+ :param old_doi_node_list: list of DOIs from old graph
:type old_doi_node_list: List[String]
- :param new_doi_node_list: list of dois from new graph
+ :param new_doi_node_list: list of DOIs from new graph
:type new_doi_node_list: List[String]
function to calculate, which nodes from the old graph are deleted and which are added
'''
- dois_from_old_graph = old_doi_node_list #WICHTIG: Keine doppelten DOIs
+ dois_from_old_graph = old_doi_node_list # important: no duplicate DOIs
dois_from_new_graph = new_doi_node_list
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])
+ 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 already 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])
diff --git a/verarbeitung/update_graph/connect_new_input.py b/verarbeitung/update_graph/connect_new_input.py
index 7dcad9b..6beb4a8 100644
--- a/verarbeitung/update_graph/connect_new_input.py
+++ b/verarbeitung/update_graph/connect_new_input.py
@@ -4,16 +4,17 @@ Functions to update a graph representing citations between multiple ACS/Nature j
"""
-__authors__ = "Donna Löding, Alina Molkentin, Xinyi Tang, Judith Große, Malte Schokolowski"
+__authors__ = "Donna Löding, Alina Molkentin, Judith Große, Malte Schokolowski"
__email__ = "cis-project2021@zbh.uni-hamburg.de"
__status__ = "Production"
-#__copyright__ = ""
-#__credits__ = ["", "", "", ""]
-#__license__ = ""
-#__version__ = ""
-#__maintainer__ = ""
-import sys
+# __copyright__ = ""
+# __credits__ = ["", "", "", ""]
+# __license__ = ""
+# __version__ = ""
+# __maintainer__ = ""
+
+import sys
from pathlib import Path
from os import error
@@ -25,30 +26,32 @@ from verarbeitung.construct_new_graph.initialize_graph import init_graph_constru
from verarbeitung.construct_new_graph.add_citations_rec import add_citations, get_cit_type_list, create_global_lists_cit
-
def find_furthermost_citations_test(test_nodes, test_edges, changed_node, old_search_depth, new_search_depth, cit_type):
global nodes, edges
nodes = test_nodes
edges = test_edges
- return(find_furthermost_citations(nodes, edges, changed_node, old_search_depth, new_search_depth, cit_type))
+ return (find_furthermost_citations(nodes, edges, changed_node, old_search_depth, new_search_depth, cit_type))
-def complete_changed_group_nodes_test(test_nodes, test_edges, inserted_test_nodes, old_search_depth, old_search_height, new_search_depth, new_search_height):
+
+def complete_changed_group_nodes_test(test_nodes, test_edges, inserted_test_nodes, old_search_depth, old_search_height,
+ new_search_depth, new_search_height):
global nodes, edges
nodes = test_nodes
edges = test_edges
- handled_nodes, new_nodes, new_edges = complete_changed_group_nodes(inserted_test_nodes, old_search_depth, old_search_height, new_search_depth, new_search_height, True)
- return(new_nodes, new_edges, handled_nodes)
-
+ handled_nodes, new_nodes, new_edges = complete_changed_group_nodes(inserted_test_nodes, old_search_depth,
+ old_search_height, new_search_depth,
+ new_search_height, True)
+ return (new_nodes, new_edges, handled_nodes)
def find_furthermost_citations(new_nodes, new_edges, node, old_search_depth, new_search_depth, cit_type):
'''
- :param new_nodes: list of nodes which are generated seperately from main node list to avoid recursive problems
+ :param new_nodes: list of nodes which are generated separately from main node list to avoid recursive problems
:type new_nodes List[Publication]
- :param new_edges: list of edges which are generated seperately from main edge list to avoid recursive problems
+ :param new_edges: list of edges which are generated separately from main edge list to avoid recursive problems
:type new_edges: List[List[String,String]]
:param node: node which is known but not from input group
@@ -78,46 +81,47 @@ def find_furthermost_citations(new_nodes, new_edges, node, old_search_depth, new
if cit_type == "Citation":
- # to find a cyclus and not change height
+ # to find a cycle and not change height
not_in_citations = True
for new_cit_node_citation in new_cit_node.citations:
if (cit_node.doi_url == new_cit_node_citation.doi_url):
not_in_citations = False
break
- if (not_in_citations):
+ if (not_in_citations):
new_citations.append(new_cit_node)
# change height accordingly and add link to edge
new_cit_node.group = node.group + depth
- if [cit_node.doi_url,cit_node.doi_url] not in new_edges:
- new_edges.append([new_cit_node.doi_url,cit_node.doi_url])
-
+ if [cit_node.doi_url, cit_node.doi_url] not in new_edges:
+ new_edges.append([new_cit_node.doi_url, cit_node.doi_url])
+
elif cit_type == "Reference":
- # to find a cyclus and not change depth
+ # to find a cycle and not change depth
not_in_citations = True
for new_cit_node_reference in new_cit_node.references:
if (new_cit_node.doi_url == new_cit_node_reference.doi_url):
not_in_citations = False
break
- if (not_in_citations):
+ if (not_in_citations):
new_citations.append(new_cit_node)
# change height accordingly and add link to edge
new_cit_node.group = node.group + depth
if [cit_node.doi_url, new_cit_node.doi_url] not in new_edges:
new_edges.append([cit_node.doi_url, new_cit_node.doi_url])
-
+
citations_saved = new_citations
for new_citation in new_citations:
if new_citation not in new_nodes:
new_nodes.append(new_citation)
- # returns the references/citations which needs to be processed to complete contruction
- return(citations_saved)
+ # returns the references/citations which needs to be processed to complete construction
+ return (citations_saved)
-def complete_changed_group_nodes(inserted_nodes, old_search_depth, old_search_height, new_search_depth, new_search_height, test_var):
+def complete_changed_group_nodes(inserted_nodes, old_search_depth, old_search_height, new_search_depth,
+ new_search_height, test_var):
'''
:param inserted_nodes: list of nodes which are inserted to new input array
:type inserted_nodes: List[String]
@@ -134,60 +138,64 @@ def complete_changed_group_nodes(inserted_nodes, old_search_depth, old_search_he
:param new_search_height: height to search for citations from new construction call
:type new_search_height: int
- :param test_var: variable to differenciate between test and url call
+ :param test_var: variable to differentiate between test and url call
:type test_var: boolean
completes the references and citations for nodes which were known in non input group
'''
- #changed_group_node_citations = []
- #changed_group_node_references = []
+ # changed_group_node_citations = []
+ # changed_group_node_references = []
# saves which nodes were handled because they were known before
handled_inserted_nodes = []
new_nodes = []
new_edges = []
for node in nodes:
-
+
# moves known reference node to input and completes citations and references for this node
if (node.group < 0) and (node.doi_url in inserted_nodes):
# get pub from input
pub = get_pub(node.doi_url, test_var)
if (type(pub) != Publication):
-
error_doi_list.append(node.doi_url)
continue
# find old maximum publications and complete tree to new max depth
pub.group = node.group
- old_max_references = find_furthermost_citations(new_nodes, new_edges, pub, old_search_depth, new_search_depth, "Reference")
- add_citations(new_nodes, new_edges, old_max_references, min(old_search_depth - abs(node.group), new_search_depth), new_search_depth, "Reference", test_var)
+ old_max_references = find_furthermost_citations(new_nodes, new_edges, pub, old_search_depth,
+ new_search_depth, "Reference")
+ add_citations(new_nodes, new_edges, old_max_references,
+ min(old_search_depth - abs(node.group), new_search_depth), new_search_depth, "Reference",
+ test_var)
# add tree for citations
add_citations(new_nodes, new_edges, [pub], 0, new_search_height, "Citation", test_var)
-
+
pub.group = 0
- new_nodes.append(pub)
+ new_nodes.append(pub)
handled_inserted_nodes.append(node)
-
+
# moves known citation node to input and completes citations and references for this node
elif (node.group > 0) and (node.doi_url in inserted_nodes):
# get pub from input
pub = get_pub(node.doi_url, test_var)
if (type(pub) != Publication):
-
error_doi_list.append(node.doi_url)
continue
# find old maximum publications and complete tree to new max depth
pub.group = node.group
- old_max_citations = find_furthermost_citations(new_nodes, new_edges, pub, old_search_height, new_search_height, "Citation")
- add_citations(new_nodes, new_edges, old_max_citations, min(old_search_height - abs(node.group), new_search_height), new_search_height, "Citation", test_var)
+ old_max_citations = find_furthermost_citations(new_nodes, new_edges, pub, old_search_height,
+ new_search_height, "Citation")
+ add_citations(new_nodes, new_edges, old_max_citations,
+ min(old_search_height - abs(node.group), new_search_height), new_search_height, "Citation",
+ test_var)
# add tree for citations
- add_citations(new_nodes, new_edges, [pub], 0, new_search_depth, "Reference", test_var)
-
+ add_citations(new_nodes, new_edges, [pub], 0, new_search_depth, "Reference", test_var)
+
pub.group = 0
new_nodes.append(pub)
handled_inserted_nodes.append(node)
@@ -198,10 +206,11 @@ def complete_changed_group_nodes(inserted_nodes, old_search_depth, old_search_he
if new_node.doi_url == inserted_node:
new_node.group = 0
- return(handled_inserted_nodes, new_nodes, new_edges)
+ return (handled_inserted_nodes, new_nodes, new_edges)
-def connect_old_and_new_input(input_nodes_list, input_edges_list, inserted_nodes, old_search_depth, old_search_height, new_search_depth, new_search_height, test_var = False):
+def connect_old_and_new_input(input_nodes_list, input_edges_list, inserted_nodes, old_search_depth, old_search_height,
+ new_search_depth, new_search_height, test_var=False):
'''
:param input_nodes_list: list of nodes which are processed for new construction call
:type input_nodes_list: List[Publication]
@@ -224,7 +233,7 @@ def connect_old_and_new_input(input_nodes_list, input_edges_list, inserted_nodes
:param new_search_height: height to search for citations from new construction call
:type new_search_height: int
- :param test_var: variable to differenciate between test and url call
+ :param test_var: variable to differentiate between test and url call
:type test_var: boolean
completes the references and citations for nodes which were known in non input group
@@ -234,17 +243,21 @@ def connect_old_and_new_input(input_nodes_list, input_edges_list, inserted_nodes
edges = input_edges_list.copy()
error_doi_list = []
- handled_inserted_nodes, new_nodes, new_edges = complete_changed_group_nodes(inserted_nodes, old_search_depth, old_search_height, new_search_depth, new_search_height, test_var)
+ handled_inserted_nodes, new_nodes, new_edges = complete_changed_group_nodes(inserted_nodes, old_search_depth,
+ old_search_height, new_search_depth,
+ new_search_height, test_var)
# copy all nodes from inserted_nodes to new node, if node is not in handled_inserted_nodes
not_handled_inserted_nodes = [node for node in inserted_nodes if node not in handled_inserted_nodes]
-
# function call to begin recursive processing up to max depth/height for unhandled nodes
if len(not_handled_inserted_nodes) > 0:
- new_nodes, new_edges, error_doi_list_new = init_graph_construction(not_handled_inserted_nodes, new_search_depth, new_search_height, test_var = test_var, update_var = True, input_nodes = new_nodes, input_edges = new_edges)
+ new_nodes, new_edges, error_doi_list_new = init_graph_construction(not_handled_inserted_nodes, new_search_depth,
+ new_search_height, test_var=test_var,
+ update_var=True, input_nodes=new_nodes,
+ input_edges=new_edges)
for err_node in error_doi_list_new:
if err_node not in error_doi_list:
error_doi_list.append(err_node)
- return(new_nodes, new_edges, error_doi_list)
\ No newline at end of file
+ return (new_nodes, new_edges, error_doi_list)
diff --git a/verarbeitung/update_graph/delete_nodes_edges.py b/verarbeitung/update_graph/delete_nodes_edges.py
index 08d0dbb..b7af110 100644
--- a/verarbeitung/update_graph/delete_nodes_edges.py
+++ b/verarbeitung/update_graph/delete_nodes_edges.py
@@ -4,7 +4,7 @@ Functions to remove publications/links from nodes/edges list, if they can no lon
"""
-__authors__ = "Donna Löding, Alina Molkentin, Xinyi Tang, Judith Große, Malte Schokolowski"
+__authors__ = "Donna Löding, Alina Molkentin, Judith Große, Malte Schokolowski"
__email__ = "cis-project2021@zbh.uni-hamburg.de"
__status__ = "Production"
#__copyright__ = ""
@@ -13,7 +13,7 @@ __status__ = "Production"
#__version__ = ""
#__maintainer__ = ""
-import sys
+import sys
from pathlib import Path
sys.path.append("../../")
@@ -34,7 +34,6 @@ def search_ref_cit_graph_rec_test(pubs, new_test_input, old_max_depth, cit_var):
return usable_nodes
-
def search_ref_graph_rec(pub, curr_depth, old_max_depth):
'''
:param pub: pub go get appended to usable_nodes
@@ -61,11 +60,11 @@ def search_ref_graph_rec(pub, curr_depth, old_max_depth):
if (reference.doi_url == citation.doi_url and citation.doi_url not in usable_doi_nodes):
not_in_citations = False
break
- if not_in_citations and curr_depth < old_max_depth:
+ if not_in_citations and curr_depth < old_max_depth:
search_ref_graph_rec(ref_pub, curr_depth + 1, old_max_depth)
-def search_cit_graph_rec(pub, curr_height, old_max_height):
+def search_cit_graph_rec(pub, curr_height, old_max_height):
'''
:param pub: pub go get appended to usable_nodes
:type pub: Publication
@@ -77,7 +76,7 @@ def search_cit_graph_rec(pub, curr_height, old_max_height):
:type old_max_height: int
function that appends nodes of group "citation" to list usable_nodes, if they are reachable from input nodes
- '''
+ '''
usable_doi_nodes = []
for citation in pub.citations:
@@ -87,13 +86,13 @@ def search_cit_graph_rec(pub, curr_height, old_max_height):
usable_nodes.append(cit_pub)
usable_doi_nodes.append(cit_pub.doi_url)
- # to find a cyclus and avoid recursion error
+ # to find a cycle and avoid recursion error
not_in_references = True
for reference in pub.references:
if (citation.doi_url == reference.doi_url and reference.doi_url not in usable_doi_nodes):
not_in_references = False
break
- if not_in_references and curr_height < old_max_height:
+ if not_in_references and curr_height < old_max_height:
search_cit_graph_rec(cit_pub,curr_height + 1, old_max_height)
@@ -103,7 +102,7 @@ def delete_nodes_and_edges(input_list, common_nodes, old_edges_list, old_depth,
: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
+ :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
diff --git a/verarbeitung/update_graph/import_from_json.py b/verarbeitung/update_graph/import_from_json.py
index 72217d5..36b4778 100644
--- a/verarbeitung/update_graph/import_from_json.py
+++ b/verarbeitung/update_graph/import_from_json.py
@@ -4,7 +4,7 @@ Functions to read old json files to recreate old graph structure
"""
-__authors__ = "Donna Löding, Alina Molkentin, Xinyi Tang, Judith Große, Malte Schokolowski"
+__authors__ = "Donna Löding, Alina Molkentin, Judith Große, Malte Schokolowski"
__email__ = "cis-project2021@zbh.uni-hamburg.de"
__status__ = "Production"
#__copyright__ = ""
@@ -13,7 +13,7 @@ __status__ = "Production"
#__version__ = ""
#__maintainer__ = ""
-
+
import json
import sys
sys.path.append("../")
@@ -21,27 +21,27 @@ sys.path.append("../")
from input.publication import Publication, Citation
-
def create_pubs_from_json(input_dict):
'''
- :param input_dict: dictionary read from old graph Json File
+ :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
- for node in input_dict["nodes"]:
- #creates for the nodes the objects class Publication
-
+
+ # iterates over the list of nodes
+ for node in input_dict["nodes"]:
+ # creates for the nodes the objects class Publication
+
pub = Publication(node["doi"], node["name"], node["author"], node["journal"], node["year"], [])
pub.group = node["depth"]
- #appends the objects to a list
- list_of_nodes_py.append(pub)
+ # appends the objects to a list
+ list_of_nodes_py.append(pub)
+
def add_ref_and_cit_to_pubs(input_dict):
'''
- :param input_dict: dictionary read from old graph Json File
+ :param input_dict: dictionary read from old graph json file
:type json_file: dictionary
adds references and citations to retrieved publication list
@@ -52,21 +52,21 @@ def add_ref_and_cit_to_pubs(input_dict):
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
+ # when correct dois found, adds then as references/citations to publication list
if ((source.doi_url == edge["source"]) and (target.doi_url == edge["target"])):
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.journal, source.contributors, "Citation")
target.citations.append(new_citation)
-
+
# adds edge to list
list_of_edges_py.append([edge["source"],edge["target"]])
def input_from_json(json_file):
'''
- :param json_file: Json-Datei for the old graph
+ :param json_file: Json file for the old graph
:type json_file: String
retrieves information from old json file to be reused for new graph construction
@@ -77,8 +77,8 @@ def input_from_json(json_file):
list_of_nodes_py = []
list_of_edges_py = []
- #opens the json file and saves content in dictionary
- with open(json_file,'r') as file:
+ # opens the json file and saves content in dictionary
+ with open(json_file,'r') as file:
input_dict = json.load(file)
# creates nodes of Class Publication from input Json file
@@ -89,6 +89,5 @@ def input_from_json(json_file):
old_depth_height = input_dict["depth_height"]
old_depth = old_depth_height[0]
old_height = old_depth_height[1]
-
return(list_of_nodes_py, list_of_edges_py, old_depth, old_height)
\ No newline at end of file
diff --git a/verarbeitung/update_graph/update_depth.py b/verarbeitung/update_graph/update_depth.py
index f843bb5..27607fc 100644
--- a/verarbeitung/update_graph/update_depth.py
+++ b/verarbeitung/update_graph/update_depth.py
@@ -4,7 +4,7 @@ Functions to update the citation depth of recursive graph construction
"""
-__authors__ = "Donna Löding, Alina Molkentin, Xinyi Tang, Judith Große, Malte Schokolowski"
+__authors__ = "Donna Löding, Alina Molkentin, Judith Große, Malte Schokolowski"
__email__ = "cis-project2021@zbh.uni-hamburg.de"
__status__ = "Production"
#__copyright__ = ""
@@ -45,6 +45,7 @@ def reduce_max_height_depth_test(pubs, max_dh, dh_var):
reduce_max_depth(max_dh)
return processed_input_list
+
def get_old_max_references_citations_test(pubs, old_dh, dh_var):
'''
:param pubs: list of publication to reduce height/depth in
@@ -66,6 +67,7 @@ def get_old_max_references_citations_test(pubs, old_dh, dh_var):
else:
return(get_old_max_references(old_dh, True))
+
def reduce_max_height(max_height):
'''
:param max_height: new maximum height to reduce publications in publication list to
@@ -79,6 +81,7 @@ def reduce_max_height(max_height):
if (pub.group > max_height):
processed_input_list.remove(pub)
+
def reduce_max_depth(max_depth):
'''
:param max_depth: new maximum depth to reduce publications in publication list to
@@ -110,6 +113,7 @@ def get_old_max_references(old_depth, test_var):
old_max_references.append(pub)
return(old_max_references)
+
def get_old_max_citations(old_height, test_var):
'''
:param old_height: old maximum height to search for citations
@@ -122,11 +126,11 @@ def get_old_max_citations(old_height, test_var):
if (pub.group == old_height):
pub = get_pub(pub.doi_url, test_var)
if (type(pub) != Publication):
- #print(pub)
continue
old_max_citations.append(pub)
return(old_max_citations)
+
def update_depth(obj_input_list, input_edges, new_depth, new_height, old_depth, old_height, test_var):
'''
:param obj_input_list: input list of publications of type Publication from update_graph
@@ -141,7 +145,7 @@ def update_depth(obj_input_list, input_edges, new_depth, new_height, old_depth,
:param new_height: new maximum height to search for citations
:type new_height: int
- :param test_var: variable to differenciate between test and url call
+ :param test_var: variable to differentiate between test and url call
:type test_var: boolean
function to adjust old publication search depth to update call
@@ -163,13 +167,9 @@ def update_depth(obj_input_list, input_edges, new_depth, new_height, old_depth,
elif (old_height < new_height):
old_max_citations = get_old_max_citations(old_height, test_var)
add_citations(processed_input_list, valid_edges, old_max_citations, old_height, new_height, "Citation", test_var)
-
-
-
-
+
back_to_valid_edges(valid_edges, processed_input_list)
- # adds edges between reference group and citation group of known publications
diff --git a/verarbeitung/update_graph/update_edges.py b/verarbeitung/update_graph/update_edges.py
index 1b046a1..45a7bde 100644
--- a/verarbeitung/update_graph/update_edges.py
+++ b/verarbeitung/update_graph/update_edges.py
@@ -12,8 +12,7 @@ def back_to_valid_edges(links_from_json, processed_input_list):
'''
list_of_valid_edges = links_from_json.copy()
-
- #iterates over all edges from old graph
+ # iterates over all edges from old graph
for edge in list_of_valid_edges:
# counter for adjacent nodes
@@ -27,6 +26,6 @@ def back_to_valid_edges(links_from_json, processed_input_list):
if (found_adj_nodes == 2):
break
- #removes the edge if less than 2 adjacent nodes found
+ # removes the edge if less than 2 adjacent nodes found
if (found_adj_nodes < 2):
links_from_json.remove(edge)
\ No newline at end of file
diff --git a/verarbeitung/update_graph/update_graph.py b/verarbeitung/update_graph/update_graph.py
index 8143ab4..2bb93c3 100644
--- a/verarbeitung/update_graph/update_graph.py
+++ b/verarbeitung/update_graph/update_graph.py
@@ -4,7 +4,7 @@ Functions to update a graph representing citations between multiple ACS/Nature j
"""
-__authors__ = "Donna Löding, Alina Molkentin, Xinyi Tang, Judith Große, Malte Schokolowski"
+__authors__ = "Donna Löding, Alina Molkentin, Judith Große, Malte Schokolowski"
__email__ = "cis-project2021@zbh.uni-hamburg.de"
__status__ = "Production"
#__copyright__ = ""
@@ -34,7 +34,7 @@ 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
+ 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
@@ -44,15 +44,16 @@ def get_old_input_dois(old_obj_input_list):
old_input_dois.append(pub.doi_url)
return old_input_dois
+
def get_new_input_dois(new_input, test_var):
'''
- :param new_input: input list of doi from UI
+ :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
+ :param test_var: variable to differentiate between test and url call
:type test_var: boolean
- function to return pub dois for input urls
+ function to return pub DOIs for input urls
'''
# new list to save doi_url for each new input url
@@ -61,7 +62,6 @@ def get_new_input_dois(new_input, test_var):
# retrieves information and adds to new list if successful
pub = get_pub(new_node, test_var)
if (type(pub) != Publication):
- #print(pub)
error_doi_list.append(new_node)
continue
@@ -80,13 +80,13 @@ def update_graph(new_doi_input_list, json_file, search_depth, search_height, tes
: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
+ :param test_var: variable to differentiate 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
'''
- # gets information from previous cunstruction call
+ # gets information from previous construction call
old_obj_input_list , old_edges_list, old_search_depth, old_search_height = input_from_json(json_file)
# one global list to save the process of removing unneeded publications and one to save valid edges
@@ -95,16 +95,13 @@ def update_graph(new_doi_input_list, json_file, search_depth, search_height, tes
valid_edges = old_edges_list
error_doi_list = []
-
- # get dois from lists to compare for differences
+ # 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 = compare_old_and_new_node_lists(old_doi_input_list, new_doi_input_list)
-
-
processed_list_copy = processed_list.copy()
valid_edges_copy = valid_edges.copy()
@@ -113,8 +110,7 @@ def update_graph(new_doi_input_list, json_file, search_depth, search_height, tes
# deletes publications and edges from node_list if publications can no longer be reached
if (len(deleted_nodes) > 0):
processed_list, valid_edges = delete_nodes_and_edges(processed_list, common_nodes, valid_edges, old_search_depth, old_search_height)
-
-
+
if (len(inserted_nodes) > 0):
inserted_pub_nodes, inserted_edges, error_doi_list_new = connect_old_and_new_input(processed_list_copy, valid_edges_copy, inserted_nodes, old_search_depth, old_search_height, search_depth, search_height, test_var)
for err_node in error_doi_list_new:
--
GitLab