diff --git a/README.md b/README.md
index c109cc8df99fda480c5ac4b666d258c53c6e46c8..d4d320b0fdc75bcfe55b8e8b18eebe1b51f986fc 100644
--- a/README.md
+++ b/README.md
@@ -8,7 +8,7 @@
# Starten des Programms:
-Um das Programm nutzen zu können muss zuerst \grqq citation\_parser\_ui.py\grqq \, ausgeführt werden und der entstandene Lik in einen Browser eingefügt werden. Danach öffnet sich die Benutzeroberfläche im Browser.
+Um das Programm nutzen zu können muss zuerst 'citation\_parser\_ui.py', ausgeführt werden und der entstandene Lik in einen Browser eingefügt werden. Danach öffnet sich die Benutzeroberfläche im Browser.
# Übersicht der Benutzeroberfläche:
@@ -43,5 +43,6 @@ Um das Programm nutzen zu können muss zuerst \grqq citation\_parser\_ui.py\grqq
- Alina Molkentin
- Donna Löding
- Malte Schokolowski
+- Judith Große
- Katja Ehlers
- Merle Stahl
diff --git a/verarbeitung/construct_new_graph/add_citations_rec.py b/verarbeitung/construct_new_graph/add_citations_rec.py
index 9467fe412b01c7f4d78d20c80296b8cb3f184373..82ae23fd9c38c4e8ee150be2418d393386ac42c1 100644
--- a/verarbeitung/construct_new_graph/add_citations_rec.py
+++ b/verarbeitung/construct_new_graph/add_citations_rec.py
@@ -6,7 +6,7 @@ Functions to add citations recursively for multiple ACS/Nature journals
__authors__ = "Donna Löding, Alina Molkentin, Judith Große, Malte Schokolowski"
__email__ = "cis-project2021@zbh.uni-hamburg.de"
-__status__ = "Production"
+__status__ = "Finished"
# __copyright__ = ""
# __credits__ = ["", "", "", ""]
@@ -28,11 +28,26 @@ 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):
'''
- :param test_nodes: list of publications from unit test
- :type test_nodes: List[Publication]
+ :param pub: publication which citations will be added
+ :type pub: Publication
+
+ :param search_depth: current depth to search for citations
+ :type search_depth_max: int
+
+ :param search_depth_max: maximum depth to search for citations
+ :type search_depth_max: int
- :param test_edges: list of links from unit test
- :type test_edges: List[List[String,String]]
+ :param cit_type: variable to differentiate citation and reference call
+ :type cit_type: String
+
+ :param test_var: variable to differentiate between test and url call
+ :type test_var: boolean
+
+ :param test_nodes: list of publications from unit test
+ :type test_nodes: List[Publication]
+
+ :param test_edges: list of links from unit test
+ :type test_edges: List[List[String,String]]
for unit test purposes only
'''
@@ -117,12 +132,16 @@ 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)
@@ -165,11 +184,10 @@ def process_citations_rec(citations_pub_obj_list, search_depth, search_depth_max
:param test_var: variable to differentiate between test and url call
:type test_var: boolean
- recursive function to implement depth-first-search on citations
+ recursive function to implement breadth-first-search on citations
'''
- # adds next level to nodes/edges
-
+ # searches citations for every publication in list and adds the one found to new list
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,
@@ -177,7 +195,7 @@ def process_citations_rec(citations_pub_obj_list, search_depth, search_depth_max
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 recursively 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)
diff --git a/verarbeitung/construct_new_graph/export_to_json.py b/verarbeitung/construct_new_graph/export_to_json.py
index 00627dfb36edc6bcadce5c74b9487f7652f68921..2c40da91b8549faf15b6a08fd8d2a09c83b3ce21 100644
--- a/verarbeitung/construct_new_graph/export_to_json.py
+++ b/verarbeitung/construct_new_graph/export_to_json.py
@@ -6,7 +6,7 @@ Functions that format the computed graph to match the interface to the output-pa
__authors__ = "Donna Löding, Alina Molkentin, Judith Große, Malte Schokolowski"
__email__ = "cis-project2021@zbh.uni-hamburg.de"
-__status__ = "Production"
+__status__ = "Finished"
# __copyright__ = ""
# __credits__ = ["", "", "", ""]
@@ -44,9 +44,7 @@ def format_nodes(nodes):
list_of_node_dicts.append(new_dict)
return list_of_node_dicts
-
-# 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):
'''
:param edges: list of links to export to json
@@ -74,7 +72,7 @@ def output_to_json(nodes, edges, search_depth, search_height, json_file='json_te
: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
+ function to export nodes and links as a dictionary to a given json file
'''
dict_of_all = dict()
list_of_node_dicts = format_nodes(nodes)
@@ -82,6 +80,8 @@ def output_to_json(nodes, edges, search_depth, search_height, json_file='json_te
dict_of_all["nodes"] = list_of_node_dicts
dict_of_all["links"] = list_of_edge_dicts
dict_of_all["depth_height"] = [search_depth, search_height]
+
+ # output to json. json name depends on test_var and if a non standard filename was given.
if (test_var):
if json_file != 'json_text.json':
with open(json_file, 'w') as outfile:
diff --git a/verarbeitung/construct_new_graph/initialize_graph.py b/verarbeitung/construct_new_graph/initialize_graph.py
index 81571dbe0e9a193a1dfcbc0a92f8240d95c50b7c..92f9e941db80f92e4a6419b19b576d040ceaabd9 100644
--- a/verarbeitung/construct_new_graph/initialize_graph.py
+++ b/verarbeitung/construct_new_graph/initialize_graph.py
@@ -6,7 +6,7 @@ Functions to generate a graph representing citations between multiple ACS/Nature
__authors__ = "Donna Löding, Alina Molkentin, Judith Große, Malte Schokolowski"
__email__ = "cis-project2021@zbh.uni-hamburg.de"
-__status__ = "Production"
+__status__ = "Finished"
# __copyright__ = ""
# __credits__ = ["", "", "", ""]
@@ -24,17 +24,29 @@ sys.path.append("../")
from input.publication import Publication
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):
'''
+ :param doi_input_list: input list of doi from UI
+ :type doi_input_list: List[String]
+
+ :param search_depth_max: maximum depth to search for references
+ :type search_depth_max: int
+
+ :param search_height_max: maximum height to search for citations
+ :type search_height_max: int
+
+ :param test_var: variable to differentiate between test and url call
+ :type test_var: boolean
+
for unit test purposes only
'''
global nodes, edges
nodes = []
edges = []
+
return (initialize_nodes_list(doi_input_list, search_depth_max, search_height_max, test_var))
@@ -52,6 +64,7 @@ def complete_inner_edges_test(test_nodes, test_edges):
global nodes, edges
nodes = test_nodes
edges = test_edges
+
complete_inner_edges()
return (nodes, edges)
@@ -132,11 +145,15 @@ def complete_inner_edges(update_var=False, input_nodes=[], input_edges=[]):
for node in nodes:
if (node.group < 0):
+
+ # searches nodes fron 'other' group to find cross references
for citation in node.citations:
for pub in nodes:
if ((pub.doi_url == citation.doi_url) and ([citation.doi_url, node.doi_url] not in edges)):
edges.append([citation.doi_url, node.doi_url])
if (node.group > 0):
+
+ # searches nodes fron 'other' group to find cross references
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)):
diff --git a/verarbeitung/dev_files/README.md b/verarbeitung/dev_files/README.md
deleted file mode 100644
index f42d3f9d67fb15ff3d219354b76967e8b3fe794e..0000000000000000000000000000000000000000
--- a/verarbeitung/dev_files/README.md
+++ /dev/null
@@ -1 +0,0 @@
-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/__init__.py b/verarbeitung/dev_files/__init__.py
deleted file mode 100644
index e69de29bb2d1d6434b8b29ae775ad8c2e48c5391..0000000000000000000000000000000000000000
diff --git a/verarbeitung/dev_files/print_graph_test.py b/verarbeitung/dev_files/print_graph_test.py
deleted file mode 100644
index 9fa8441a38fdc65514fdd52835bc558450708b05..0000000000000000000000000000000000000000
--- a/verarbeitung/dev_files/print_graph_test.py
+++ /dev/null
@@ -1,115 +0,0 @@
-# -*- coding: utf-8 -*-
-"""
-Functions to test and print the nodes and edges sets
-
-"""
-
-__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
-
-# 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")
- for node in nodes:
- print(node.title, "\n")
- print("\nKanten:\n")
- for edge in edges:
- print(edge, "\n")
- print(len(nodes))
- print(len(edges))
- print(" ")
-
-
-def print_extended_graph(nodes, edges):
- print("Knoten:\n")
- for node in nodes:
- print(node.title, "\n")
- print(node.doi_url)
- for reference in node.references:
- print(reference.doi_url)
- for citation in node.citations:
- print(citation.doi_url)
- print("\nKanten:\n")
- for edge in edges:
- print(edge, "\n")
- print(len(nodes))
- print(len(edges))
- print(" ")
-
-
-def print_simple(nodes, edges):
- # for node in nodes:
- # print(node)
- # for edge in edges:
- # print(edge)
- print(len(nodes))
- print(len(edges))
- print(" ")
-
-
-# program test with some random DOIs
-def try_known_publications():
- doi_list = []
- doi_list.append('https://pubs.acs.org/doi/10.1021/acs.jcim.9b00249')
- # doi_list.append('https://doi.org/10.1021/acs.jcim.9b00249')
- doi_list.append('https://pubs.acs.org/doi/10.1021/acs.jcim.1c00203')
- # 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/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]
-
- nodes, edges = init_graph_construction(doi_list, 2, 2)
-
- print_graph(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)
-
- # list_of_nodes_py, list_of_edges_py = input_from_json('json_text.json')
- # doi_list = []
- # doi_list.append('https://pubs.acs.org/doi/10.1021/acs.jcim.9b00249')
- # valid_nodes, valid_edges = 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)
-
-
-# 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()
diff --git a/verarbeitung/get_pub_from_input.py b/verarbeitung/get_pub_from_input.py
index f27b72d8601387e1e72fd10ff7432a4f768f001f..c1fd8e7e02b901754fc4462a340f20d512b18f7a 100644
--- a/verarbeitung/get_pub_from_input.py
+++ b/verarbeitung/get_pub_from_input.py
@@ -6,7 +6,7 @@ A function to return an object of Type Publication for a given DOI
__authors__ = "Donna Löding, Alina Molkentin, Judith Große, Malte Schokolowski"
__email__ = "cis-project2021@zbh.uni-hamburg.de"
-__status__ = "Production"
+__status__ = "Finished"
#__copyright__ = ""
#__credits__ = ["", "", "", ""]
#__license__ = ""
diff --git a/verarbeitung/json_text.json b/verarbeitung/json_text.json
deleted file mode 100644
index f77fc38c5d062f2c4eb808b2180e4256c493681b..0000000000000000000000000000000000000000
--- a/verarbeitung/json_text.json
+++ /dev/null
@@ -1 +0,0 @@
-{"nodes": [{"doi": "doi_lg_1_i", "name": "title_lg_1_i", "author": ["contributor_lg_1_i"], "year": "date_lg_1_i", "journal": "journal_lg_1_i", "abstract": null, "group": "Input", "depth": 0, "citations": 2}, {"doi": "doi_lg_1_d11", "name": "title_lg_1_d11", "author": ["contributor_lg_1_d11"], "year": "date_lg_1_d11", "journal": "journal_lg_1_d11", "abstract": null, "group": "Reference", "depth": -1, "citations": 1}, {"doi": "doi_lg_1_d12", "name": "title_lg_1_d12", "author": ["contributor_lg_1_d12"], "year": "date_lg_1_d12", "journal": "journal_lg_1_d12", "abstract": null, "group": "Reference", "depth": -1, "citations": 2}, {"doi": "doi_lg_1_h11", "name": "title_lg_1_h11", "author": ["contributor_lg_1_h11"], "year": "date_lg_1_h11", "journal": "journal_lg_1_h11", "abstract": null, "group": "Citedby", "depth": 1, "citations": 2}, {"doi": "doi_lg_1_h12", "name": "title_lg_1_h12", "author": ["contributor_lg_1_h12"], "year": "date_lg_1_h12", "journal": "journal_lg_1_h12", "abstract": null, "group": "Citedby", "depth": 1, "citations": 2}, {"doi": "doi_lg_1_h21", "name": "title_lg_1_h21", "author": ["contributor_lg_1_h21"], "year": "date_lg_1_h21", "journal": "journal_lg_1_h21", "abstract": null, "group": "Citedby", "depth": 2, "citations": 0}, {"doi": "doi_lg_1_h22", "name": "title_lg_1_h22", "author": ["contributor_lg_1_h22"], "year": "date_lg_1_h22", "journal": "journal_lg_1_h22", "abstract": null, "group": "Citedby", "depth": 2, "citations": 0}, {"doi": "doi_lg_1_h23", "name": "title_lg_1_h23", "author": ["contributor_lg_1_h23"], "year": "date_lg_1_h23", "journal": "journal_lg_1_h23", "abstract": null, "group": "Citedby", "depth": 2, "citations": 0}, {"doi": "doi_lg_1_d21", "name": "title_lg_1_d21", "author": ["contributor_lg_1_d21"], "year": "date_lg_1_d21", "journal": "journal_lg_1_d21", "abstract": null, "group": "Reference", "depth": -2, "citations": 2}, {"doi": "doi_lg_1_d22", "name": "title_lg_1_d22", "author": ["contributor_lg_1_d22"], "year": "date_lg_1_d22", "journal": "journal_lg_1_d22", "abstract": null, "group": "Reference", "depth": -2, "citations": 2}, {"doi": "doi_lg_1_d23", "name": "title_lg_1_d23", "author": ["contributor_lg_1_d23"], "year": "date_lg_1_d23", "journal": "journal_lg_1_d23", "abstract": null, "group": "Reference", "depth": -2, "citations": 2}], "links": [{"source": "doi_lg_1_i", "target": "doi_lg_1_d11"}, {"source": "doi_lg_1_i", "target": "doi_lg_1_d12"}, {"source": "doi_lg_1_h11", "target": "doi_lg_1_i"}, {"source": "doi_lg_1_h12", "target": "doi_lg_1_i"}, {"source": "doi_lg_1_h21", "target": "doi_lg_1_h11"}, {"source": "doi_lg_1_h22", "target": "doi_lg_1_h11"}, {"source": "doi_lg_1_h22", "target": "doi_lg_1_h12"}, {"source": "doi_lg_1_h23", "target": "doi_lg_1_h12"}, {"source": "doi_lg_1_d11", "target": "doi_lg_1_d21"}, {"source": "doi_lg_1_d11", "target": "doi_lg_1_d22"}, {"source": "doi_lg_1_d12", "target": "doi_lg_1_d23"}, {"source": "doi_lg_1_d21", "target": "doi_lg_1_d22"}, {"source": "doi_lg_1_d22", "target": "doi_lg_1_d21"}, {"source": "doi_lg_1_h12", "target": "doi_lg_1_d12"}], "depth_height": ["new_height.json", true]}
\ No newline at end of file
diff --git a/verarbeitung/new_height.json b/verarbeitung/new_height.json
deleted file mode 100644
index 0cc59401969ce8a984fee556a67099167f2144a6..0000000000000000000000000000000000000000
--- a/verarbeitung/new_height.json
+++ /dev/null
@@ -1 +0,0 @@
-{"nodes": [{"doi": "doi_lg_1_i", "name": "title_lg_1_i", "author": ["contributor_lg_1_i"], "year": "date_lg_1_i", "journal": "journal_lg_1_i", "abstract": null, "group": "Input", "depth": 0, "citations": 2}, {"doi": "doi_lg_1_d11", "name": "title_lg_1_d11", "author": ["contributor_lg_1_d11"], "year": "date_lg_1_d11", "journal": "journal_lg_1_d11", "abstract": null, "group": "Reference", "depth": -1, "citations": 1}, {"doi": "doi_lg_1_d12", "name": "title_lg_1_d12", "author": ["contributor_lg_1_d12"], "year": "date_lg_1_d12", "journal": "journal_lg_1_d12", "abstract": null, "group": "Reference", "depth": -1, "citations": 2}, {"doi": "doi_lg_1_h11", "name": "title_lg_1_h11", "author": ["contributor_lg_1_h11"], "year": "date_lg_1_h11", "journal": "journal_lg_1_h11", "abstract": null, "group": "Citedby", "depth": 1, "citations": 2}, {"doi": "doi_lg_1_h12", "name": "title_lg_1_h12", "author": ["contributor_lg_1_h12"], "year": "date_lg_1_h12", "journal": "journal_lg_1_h12", "abstract": null, "group": "Citedby", "depth": 1, "citations": 2}, {"doi": "doi_lg_1_h21", "name": "title_lg_1_h21", "author": ["contributor_lg_1_h21"], "year": "date_lg_1_h21", "journal": "journal_lg_1_h21", "abstract": null, "group": "Citedby", "depth": 2, "citations": 0}, {"doi": "doi_lg_1_h22", "name": "title_lg_1_h22", "author": ["contributor_lg_1_h22"], "year": "date_lg_1_h22", "journal": "journal_lg_1_h22", "abstract": null, "group": "Citedby", "depth": 2, "citations": 0}, {"doi": "doi_lg_1_h23", "name": "title_lg_1_h23", "author": ["contributor_lg_1_h23"], "year": "date_lg_1_h23", "journal": "journal_lg_1_h23", "abstract": null, "group": "Citedby", "depth": 2, "citations": 0}, {"doi": "doi_lg_1_d21", "name": "title_lg_1_d21", "author": ["contributor_lg_1_d21"], "year": "date_lg_1_d21", "journal": "journal_lg_1_d21", "abstract": null, "group": "Reference", "depth": -2, "citations": 2}, {"doi": "doi_lg_1_d22", "name": "title_lg_1_d22", "author": ["contributor_lg_1_d22"], "year": "date_lg_1_d22", "journal": "journal_lg_1_d22", "abstract": null, "group": "Reference", "depth": -2, "citations": 2}, {"doi": "doi_lg_1_d23", "name": "title_lg_1_d23", "author": ["contributor_lg_1_d23"], "year": "date_lg_1_d23", "journal": "journal_lg_1_d23", "abstract": null, "group": "Reference", "depth": -2, "citations": 2}], "links": [{"source": "doi_lg_1_i", "target": "doi_lg_1_d11"}, {"source": "doi_lg_1_i", "target": "doi_lg_1_d12"}, {"source": "doi_lg_1_h11", "target": "doi_lg_1_i"}, {"source": "doi_lg_1_h12", "target": "doi_lg_1_i"}, {"source": "doi_lg_1_h21", "target": "doi_lg_1_h11"}, {"source": "doi_lg_1_h22", "target": "doi_lg_1_h11"}, {"source": "doi_lg_1_h22", "target": "doi_lg_1_h12"}, {"source": "doi_lg_1_h23", "target": "doi_lg_1_h12"}, {"source": "doi_lg_1_d11", "target": "doi_lg_1_d21"}, {"source": "doi_lg_1_d11", "target": "doi_lg_1_d22"}, {"source": "doi_lg_1_d12", "target": "doi_lg_1_d23"}, {"source": "doi_lg_1_d21", "target": "doi_lg_1_d22"}, {"source": "doi_lg_1_d22", "target": "doi_lg_1_d21"}, {"source": "doi_lg_1_h12", "target": "doi_lg_1_d12"}], "depth_height": [2, 2]}
\ No newline at end of file
diff --git "a/verarbeitung/n\303\266tige Tests.txt" "b/verarbeitung/n\303\266tige Tests.txt"
deleted file mode 100644
index 95563280436fbf6b9b8702dffef6f32e213f5a16..0000000000000000000000000000000000000000
--- "a/verarbeitung/n\303\266tige Tests.txt"
+++ /dev/null
@@ -1,4 +0,0 @@
-Zyklus
-großer Zyklus
-Innere Kanten vervollständigen
-
diff --git a/verarbeitung/process_main.py b/verarbeitung/process_main.py
index 2567c24c9fea70dd4c62abc40dc26dd677bf99e1..05e580e3c1c91154fb1443a634814609c071bbc4 100644
--- a/verarbeitung/process_main.py
+++ b/verarbeitung/process_main.py
@@ -6,7 +6,7 @@ main function to call to generate a graph representing citations between multipl
__authors__ = "Donna Löding, Alina Molkentin, Judith Große, Malte Schokolowski"
__email__ = "cis-project2021@zbh.uni-hamburg.de"
-__status__ = "Production"
+__status__ = "Finished"
#__copyright__ = ""
#__credits__ = ["", "", "", ""]
#__license__ = ""
@@ -39,7 +39,7 @@ def Processing(url_list, search_depth, search_height, json_file = 'json_text.jso
:param json_file: file to export graph to
:type json_file: String
- main function to construct new or updated publication graphs
+ main function to construct new or update known publication graph
'''
# updates graph if json file is known in directory otherwise starts new graph construction
diff --git a/verarbeitung/start_script.py b/verarbeitung/start_script.py
index 92295eefbd363053762a3d6df99d028af44151b1..0e9ae8366c65b8b81032d114eb1f76db698eeaee 100644
--- a/verarbeitung/start_script.py
+++ b/verarbeitung/start_script.py
@@ -1,8 +1,13 @@
+"""
+ This file is for testing purposes only. We left it in the directory for ease of use.
+ To use it you need to shift it into the main directory of the project
+"""
+
import sys
import gc
from pathlib import Path
from verarbeitung.process_main import Processing
-#from verarbeitung.dev_files.print_graph_test import try_known_publications, try_delete_nodes
+
doi_list = []
diff --git a/verarbeitung/test/construct_graph_unittest.py b/verarbeitung/test/construct_graph_unittest.py
index 1cef0dd92393ecb062d6543f0c50ef32090710f8..5e0632a05ad37af7ac191253675d87058708aa9e 100644
--- a/verarbeitung/test/construct_graph_unittest.py
+++ b/verarbeitung/test/construct_graph_unittest.py
@@ -1,5 +1,21 @@
-import unittest
+# -*- coding: utf-8 -*-
+"""
+Functions to unittest functions which construct a new graph
+
+"""
+
+__authors__ = "Donna Löding, Alina Molkentin, Judith Große, Malte Schokolowski"
+__email__ = "cis-project2021@zbh.uni-hamburg.de"
+__status__ = "Finished"
+# __copyright__ = ""
+# __credits__ = ["", "", "", ""]
+# __license__ = ""
+# __version__ = ""
+# __maintainer__ = ""
+
+
+import unittest
import sys
sys.path.append("../")
@@ -98,7 +114,7 @@ class ConstructionTest(unittest.TestCase):
self.assertCountEqual(edges, [['doi1', 'doi2'], ['doi3', 'doi1']])
self.assertCountEqual(err_list, ['doi2ic'])
- ## From here the tests for the individual functions ##
+ ## from here: tests for the individual functions ##
# initialize_graph.py:
diff --git a/verarbeitung/test/input_test.py b/verarbeitung/test/input_test.py
index 7164e234dd55b65bd5804744d6535a50b7b9cb68..f9839a2e3b8b7fd4a87aaefd17018d5c9b863cb0 100644
--- a/verarbeitung/test/input_test.py
+++ b/verarbeitung/test/input_test.py
@@ -1,3 +1,21 @@
+# -*- coding: utf-8 -*-
+"""
+Functions implement an test input function analogue to the one from the input group.
+Also implements example graphs
+
+"""
+
+__authors__ = "Donna Löding, Alina Molkentin, Judith Große, Malte Schokolowski"
+__email__ = "cis-project2021@zbh.uni-hamburg.de"
+__status__ = "Finished"
+
+# __copyright__ = ""
+# __credits__ = ["", "", "", ""]
+# __license__ = ""
+# __version__ = ""
+# __maintainer__ = ""
+
+
import sys
sys.path.append("../")
@@ -23,8 +41,11 @@ def input_test_func(pub_doi):
def cit(list_doi, cit_type):
'''
- :param list_doi list of citation DOIs to get their Citation Class
- :type list_doi: List[String]
+ :param list_doi: list of citation DOIs to get their Citation Class
+ :type list_doi: List[String]
+
+ :param cit_type: variable to differentiate citation and reference call
+ :type cit_type: String
returns a list of citations objects for given DOI list
'''
@@ -37,6 +58,8 @@ def cit(list_doi, cit_type):
return cits
+# large_graph_1, large_graph_2 and crossed_graph are visualized in test_graphs_plan.pdf
+
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'], []]
diff --git a/verarbeitung/test/update_graph_unittest.py b/verarbeitung/test/update_graph_unittest.py
index 1ebb0d10d885b4f8aea45a9b59a487ed25988197..ae0e3a4dec85ae6d3f10d25206d62bb64c2049fb 100644
--- a/verarbeitung/test/update_graph_unittest.py
+++ b/verarbeitung/test/update_graph_unittest.py
@@ -1,5 +1,21 @@
-import unittest
+# -*- coding: utf-8 -*-
+"""
+Functions to unittest functions which are updating a known graph
+
+"""
+
+__authors__ = "Donna Löding, Alina Molkentin, Judith Große, Malte Schokolowski"
+__email__ = "cis-project2021@zbh.uni-hamburg.de"
+__status__ = "Finished"
+# __copyright__ = ""
+# __credits__ = ["", "", "", ""]
+# __license__ = ""
+# __version__ = ""
+# __maintainer__ = ""
+
+
+import unittest
import sys
from pathlib import Path
@@ -79,7 +95,7 @@ class UpdatingTest(unittest.TestCase):
self.assertCountEqual(new_nodes, nodes)
self.assertCountEqual(new_edges, edges)
- ## From here the tests for the individual functions ##
+ ## From here: tests for the individual functions ##
# update_graph.py:
diff --git a/verarbeitung/test_output.json b/verarbeitung/test_output.json
deleted file mode 100644
index 0cc59401969ce8a984fee556a67099167f2144a6..0000000000000000000000000000000000000000
--- a/verarbeitung/test_output.json
+++ /dev/null
@@ -1 +0,0 @@
-{"nodes": [{"doi": "doi_lg_1_i", "name": "title_lg_1_i", "author": ["contributor_lg_1_i"], "year": "date_lg_1_i", "journal": "journal_lg_1_i", "abstract": null, "group": "Input", "depth": 0, "citations": 2}, {"doi": "doi_lg_1_d11", "name": "title_lg_1_d11", "author": ["contributor_lg_1_d11"], "year": "date_lg_1_d11", "journal": "journal_lg_1_d11", "abstract": null, "group": "Reference", "depth": -1, "citations": 1}, {"doi": "doi_lg_1_d12", "name": "title_lg_1_d12", "author": ["contributor_lg_1_d12"], "year": "date_lg_1_d12", "journal": "journal_lg_1_d12", "abstract": null, "group": "Reference", "depth": -1, "citations": 2}, {"doi": "doi_lg_1_h11", "name": "title_lg_1_h11", "author": ["contributor_lg_1_h11"], "year": "date_lg_1_h11", "journal": "journal_lg_1_h11", "abstract": null, "group": "Citedby", "depth": 1, "citations": 2}, {"doi": "doi_lg_1_h12", "name": "title_lg_1_h12", "author": ["contributor_lg_1_h12"], "year": "date_lg_1_h12", "journal": "journal_lg_1_h12", "abstract": null, "group": "Citedby", "depth": 1, "citations": 2}, {"doi": "doi_lg_1_h21", "name": "title_lg_1_h21", "author": ["contributor_lg_1_h21"], "year": "date_lg_1_h21", "journal": "journal_lg_1_h21", "abstract": null, "group": "Citedby", "depth": 2, "citations": 0}, {"doi": "doi_lg_1_h22", "name": "title_lg_1_h22", "author": ["contributor_lg_1_h22"], "year": "date_lg_1_h22", "journal": "journal_lg_1_h22", "abstract": null, "group": "Citedby", "depth": 2, "citations": 0}, {"doi": "doi_lg_1_h23", "name": "title_lg_1_h23", "author": ["contributor_lg_1_h23"], "year": "date_lg_1_h23", "journal": "journal_lg_1_h23", "abstract": null, "group": "Citedby", "depth": 2, "citations": 0}, {"doi": "doi_lg_1_d21", "name": "title_lg_1_d21", "author": ["contributor_lg_1_d21"], "year": "date_lg_1_d21", "journal": "journal_lg_1_d21", "abstract": null, "group": "Reference", "depth": -2, "citations": 2}, {"doi": "doi_lg_1_d22", "name": "title_lg_1_d22", "author": ["contributor_lg_1_d22"], "year": "date_lg_1_d22", "journal": "journal_lg_1_d22", "abstract": null, "group": "Reference", "depth": -2, "citations": 2}, {"doi": "doi_lg_1_d23", "name": "title_lg_1_d23", "author": ["contributor_lg_1_d23"], "year": "date_lg_1_d23", "journal": "journal_lg_1_d23", "abstract": null, "group": "Reference", "depth": -2, "citations": 2}], "links": [{"source": "doi_lg_1_i", "target": "doi_lg_1_d11"}, {"source": "doi_lg_1_i", "target": "doi_lg_1_d12"}, {"source": "doi_lg_1_h11", "target": "doi_lg_1_i"}, {"source": "doi_lg_1_h12", "target": "doi_lg_1_i"}, {"source": "doi_lg_1_h21", "target": "doi_lg_1_h11"}, {"source": "doi_lg_1_h22", "target": "doi_lg_1_h11"}, {"source": "doi_lg_1_h22", "target": "doi_lg_1_h12"}, {"source": "doi_lg_1_h23", "target": "doi_lg_1_h12"}, {"source": "doi_lg_1_d11", "target": "doi_lg_1_d21"}, {"source": "doi_lg_1_d11", "target": "doi_lg_1_d22"}, {"source": "doi_lg_1_d12", "target": "doi_lg_1_d23"}, {"source": "doi_lg_1_d21", "target": "doi_lg_1_d22"}, {"source": "doi_lg_1_d22", "target": "doi_lg_1_d21"}, {"source": "doi_lg_1_h12", "target": "doi_lg_1_d12"}], "depth_height": [2, 2]}
\ 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 a899a8a7fd6b405af423780be599e6affde76a67..2b1102b6cdead683c9e03d85f6fb1cb0fadb5f80 100644
--- a/verarbeitung/update_graph/compare_old_and_new_node_lists.py
+++ b/verarbeitung/update_graph/compare_old_and_new_node_lists.py
@@ -1,4 +1,20 @@
-#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+ compares old and new input list to find common, deleted and inserted input dois.
+
+"""
+
+__authors__ = "Donna Löding, Alina Molkentin, Judith Große, Malte Schokolowski"
+__email__ = "cis-project2021@zbh.uni-hamburg.de"
+__status__ = "Finished"
+
+# __copyright__ = ""
+# __credits__ = ["", "", "", ""]
+# __license__ = ""
+# __version__ = ""
+# __maintainer__ = ""
+
+
from collections import Counter
@@ -29,11 +45,5 @@ def compare_old_and_new_node_lists(old_doi_node_list, new_doi_node_list):
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 6beb4a88e1a5424011d45ac1479c63268445307b..45cb55c1cf200b8902d776ab5b721d57a2b22602 100644
--- a/verarbeitung/update_graph/connect_new_input.py
+++ b/verarbeitung/update_graph/connect_new_input.py
@@ -6,7 +6,7 @@ Functions to update a graph representing citations between multiple ACS/Nature j
__authors__ = "Donna Löding, Alina Molkentin, Judith Große, Malte Schokolowski"
__email__ = "cis-project2021@zbh.uni-hamburg.de"
-__status__ = "Production"
+__status__ = "Finished"
# __copyright__ = ""
# __credits__ = ["", "", "", ""]
@@ -23,10 +23,34 @@ sys.path.append("../")
from input.publication import Publication
from verarbeitung.get_pub_from_input import get_pub
from verarbeitung.construct_new_graph.initialize_graph import init_graph_construction
-from verarbeitung.construct_new_graph.add_citations_rec import add_citations, get_cit_type_list, create_global_lists_cit
+from verarbeitung.construct_new_graph.add_citations_rec import add_citations, get_cit_type_list
def find_furthermost_citations_test(test_nodes, test_edges, changed_node, old_search_depth, new_search_depth, cit_type):
+ """
+ :param test_nodes: list of publications from unit test
+ :type test_nodes: List[Publication]
+
+ :param test_edges: list of links from unit test
+ :type test_edges: List[List[String,String]]
+
+ :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 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
+ :type node: Publication
+
+ :param old_search_depth: depth to search for references from old construction call
+ :type old_search_depth: int
+
+ :param cit_type: determines whether the function call is for a reference or citation
+ :type cit_type: String
+
+ for unit test purposes only
+ """
global nodes, edges
nodes = test_nodes
edges = test_edges
@@ -36,6 +60,30 @@ def find_furthermost_citations_test(test_nodes, test_edges, changed_node, old_se
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):
+ """
+ :param test_nodes: list of publications from unit test
+ :type test_nodes: List[Publication]
+
+ :param test_edges: list of links from unit test
+ :type test_edges: List[List[String,String]]
+
+ :param inserted_nodes: list of nodes which are inserted to new input array
+ :type inserted_nodes: List[String]
+
+ :param old_search_depth: depth to search for references from old construction call
+ :type old_search_depth: int
+
+ :param old_search_height: height to search for citations from old construction call
+ :type old_search_height: int
+
+ :param new_search_depth: depth to search for references from new construction call
+ :type new_search_depth: int
+
+ :param new_search_height: height to search for citations from new construction call
+ :type new_search_height: int
+
+ for unit test purposes only
+ """
global nodes, edges
nodes = test_nodes
edges = test_edges
diff --git a/verarbeitung/update_graph/delete_nodes_edges.py b/verarbeitung/update_graph/delete_nodes_edges.py
index b7af110fb0f554cf29471c76a029278c86116708..6836ccfa316748ff4a19fc2c954f299c060c7570 100644
--- a/verarbeitung/update_graph/delete_nodes_edges.py
+++ b/verarbeitung/update_graph/delete_nodes_edges.py
@@ -1,12 +1,12 @@
# -*- coding: utf-8 -*-
"""
-Functions to remove publications/links from nodes/edges list, if they can no longer be reached
+ Functions to remove publications/links from nodes/edges list, if they can no longer be reached
"""
__authors__ = "Donna Löding, Alina Molkentin, Judith Große, Malte Schokolowski"
__email__ = "cis-project2021@zbh.uni-hamburg.de"
-__status__ = "Production"
+__status__ = "Finished"
#__copyright__ = ""
#__credits__ = ["", "", "", ""]
#__license__ = ""
@@ -20,15 +20,31 @@ sys.path.append("../../")
from .update_edges import back_to_valid_edges
-def search_ref_cit_graph_rec_test(pubs, new_test_input, old_max_depth, cit_var):
+def search_ref_cit_graph_rec_test(pubs, new_test_input, old_max_depth, cit_type):
+ '''
+ :param pub: pub go get appended to usable_nodes
+ :type pub: Publication
+
+ :param new_test_input: current recursion depth
+ :type new_test_input: int
+
+ :param old_max_depth: old max search depth
+ :type old_max_depth: int
+
+ :param cit_type: variable to differentiate citation and reference call
+ :type cit_type: String
+
+ for unit test purposes only
+ '''
+
global usable_nodes, input_obj_list
usable_nodes = []
input_obj_list = pubs
- if cit_var == "Reference":
+ if cit_type == "Reference":
for pub in new_test_input:
search_ref_graph_rec(pub, 1, old_max_depth)
- elif cit_var == "Citation":
+ elif cit_type == "Citation":
for pub in new_test_input:
search_cit_graph_rec(pub, 1, old_max_depth)
return usable_nodes
diff --git a/verarbeitung/update_graph/import_from_json.py b/verarbeitung/update_graph/import_from_json.py
index 36b4778c5a8a27234ed341697657d05af1662c3c..62c464481a9561c79d6e10cbd9eceb2387082ec7 100644
--- a/verarbeitung/update_graph/import_from_json.py
+++ b/verarbeitung/update_graph/import_from_json.py
@@ -1,12 +1,12 @@
# -*- coding: utf-8 -*-
"""
-Functions to read old json files to recreate old graph structure
+ Functions to read old json files to recreate old graph structure
"""
__authors__ = "Donna Löding, Alina Molkentin, Judith Große, Malte Schokolowski"
__email__ = "cis-project2021@zbh.uni-hamburg.de"
-__status__ = "Production"
+__status__ = "Finished"
#__copyright__ = ""
#__credits__ = ["", "", "", ""]
#__license__ = ""
@@ -24,7 +24,7 @@ from input.publication import Publication, Citation
def create_pubs_from_json(input_dict):
'''
:param input_dict: dictionary read from old graph json file
- :type json_file: dictionary
+ :type input_dict: Dict
creates list of publication retrieved from old json file
'''
@@ -42,7 +42,7 @@ def create_pubs_from_json(input_dict):
def add_ref_and_cit_to_pubs(input_dict):
'''
:param input_dict: dictionary read from old graph json file
- :type json_file: dictionary
+ :type input_dict: Dict
adds references and citations to retrieved publication list
'''
diff --git a/verarbeitung/update_graph/update_depth.py b/verarbeitung/update_graph/update_depth.py
index 27607fcb5deb340cc5fd1fdd59034de8887b3eeb..640f919c0ad5ae26caead5b0d83e079e9afcc569 100644
--- a/verarbeitung/update_graph/update_depth.py
+++ b/verarbeitung/update_graph/update_depth.py
@@ -6,7 +6,7 @@ Functions to update the citation depth of recursive graph construction
__authors__ = "Donna Löding, Alina Molkentin, Judith Große, Malte Schokolowski"
__email__ = "cis-project2021@zbh.uni-hamburg.de"
-__status__ = "Production"
+__status__ = "Finished"
#__copyright__ = ""
#__credits__ = ["", "", "", ""]
#__license__ = ""
@@ -17,7 +17,6 @@ import sys
sys.path.append("../../")
from verarbeitung.construct_new_graph.add_citations_rec import add_citations
-from verarbeitung.construct_new_graph.initialize_graph import complete_inner_edges
from verarbeitung.get_pub_from_input import get_pub
from .update_edges import back_to_valid_edges
from input.publication import Publication
@@ -101,6 +100,9 @@ def get_old_max_references(old_depth, test_var):
:param old_depth: old maximum depth to search for citations
:type old_depth: int
+ :param test_var: variable to differentiate between test and url call
+ :type test_var: boolean
+
function to get references for new recursive levels
'''
old_max_references = []
@@ -119,6 +121,9 @@ def get_old_max_citations(old_height, test_var):
:param old_height: old maximum height to search for citations
:type old_height: int
+ :param test_var: variable to differentiate between test and url call
+ :type test_var: boolean
+
function to get citations for new recursive levels
'''
old_max_citations = []
diff --git a/verarbeitung/update_graph/update_edges.py b/verarbeitung/update_graph/update_edges.py
index 45a7bded40d8e6328e0addf524d05d9de66d2477..bb174da3a5c1f0a1fdfda0313f2e0fe1e592c6e5 100644
--- a/verarbeitung/update_graph/update_edges.py
+++ b/verarbeitung/update_graph/update_edges.py
@@ -1,4 +1,18 @@
-#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+ returns the edges list to a valid state after node deletion
+
+"""
+
+__authors__ = "Donna Löding, Alina Molkentin, Judith Große, Malte Schokolowski"
+__email__ = "cis-project2021@zbh.uni-hamburg.de"
+__status__ = "Finished"
+
+# __copyright__ = ""
+# __credits__ = ["", "", "", ""]
+# __license__ = ""
+# __version__ = ""
+# __maintainer__ = ""
def back_to_valid_edges(links_from_json, processed_input_list):
'''
diff --git a/verarbeitung/update_graph/update_graph.py b/verarbeitung/update_graph/update_graph.py
index 2bb93c3f851862398f9287173987deb6e2279e21..a92ff7dfa0e1363a28c53ed16a5e26d990c297c6 100644
--- a/verarbeitung/update_graph/update_graph.py
+++ b/verarbeitung/update_graph/update_graph.py
@@ -6,7 +6,8 @@ Functions to update a graph representing citations between multiple ACS/Nature j
__authors__ = "Donna Löding, Alina Molkentin, Judith Große, Malte Schokolowski"
__email__ = "cis-project2021@zbh.uni-hamburg.de"
-__status__ = "Production"
+__status__ = "Finished"
+
#__copyright__ = ""
#__credits__ = ["", "", "", ""]
#__license__ = ""
@@ -16,7 +17,6 @@ __status__ = "Production"
import sys
-
sys.path.append("../../")
from input.publication import Publication
@@ -59,6 +59,7 @@ def get_new_input_dois(new_input, test_var):
# new list to save doi_url for each new input url
new_input_dois = []
for new_node in new_input:
+
# retrieves information and adds to new list if successful
pub = get_pub(new_node, test_var)
if (type(pub) != Publication):
@@ -111,12 +112,14 @@ def update_graph(new_doi_input_list, json_file, search_depth, search_height, tes
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)
+ # returns new lists for nodes and edges if new input dois exist
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:
if err_node not in error_doi_list:
error_doi_list.append(err_node)
+ # compares new list to processed list and adds new nodes/replaces known nodes
for inserted_node in inserted_pub_nodes:
not_in_nodes = True
for node in processed_list:
@@ -128,10 +131,12 @@ def update_graph(new_doi_input_list, json_file, search_depth, search_height, tes
if not_in_nodes:
processed_list.append(inserted_node)
+ # adds new edges to list valid_edges
for inserted_edge in inserted_edges:
if inserted_edge not in valid_edges:
valid_edges.append(inserted_edge)
+ # calls function to find cross references between citation and reference group
complete_inner_edges(True, processed_list, valid_edges)
return(processed_list, valid_edges, error_doi_list)