diff --git a/verarbeitung/Processing.py b/verarbeitung/Processing.py
index 89f1ef2707d456c565adca8988d1ebe27b6501e3..ac85f522ac884d5e48fedef2f42f256bba610c79 100644
--- a/verarbeitung/Processing.py
+++ b/verarbeitung/Processing.py
@@ -25,9 +25,13 @@ from json_demo import output_to_json
# doi_input_list: list of publication dois from user
# TO-DO: Listenelemente auf Korrektheit überprüfen
-def initialize_nodes_list(doi_input_list):
+def initialize_nodes_list(doi_input_list, test_var):
for pub_doi in doi_input_list:
- pub = input_test_func(pub_doi)
+ if(test_var):
+ pub = input_test_func(pub_doi)
+ else:
+ pub = input(pub_doi)
+
not_in_nodes = True
for node in nodes: # checks if a pub is already in nodes
if (pub.doi_url == node.doi_url):
@@ -35,6 +39,7 @@ def initialize_nodes_list(doi_input_list):
break
if (not_in_nodes):
nodes.append(pub)
+ #print(pub.doi_url)
pub.group = "input"
else:
doi_input_list.remove(pub_doi)
@@ -55,11 +60,11 @@ def create_graph_structure_citations(pub, search_height, search_height_max):
if (search_height <= search_height_max):
citation.group = "height"
nodes.append(citation)
- edges.append([pub.doi_url,citation.doi_url])
+ edges.append([citation.doi_url,pub.doi_url])
# adds only edge if citation already exists
else:
- edges.append([pub.doi_url,citation.doi_url])
+ edges.append([citation.doi_url,pub.doi_url])
@@ -77,11 +82,11 @@ def create_graph_structure_references(pub, search_depth, search_depth_max):
if (search_depth <= search_depth_max):
reference.group = "depth"
nodes.append(reference)
- edges.append([reference.doi_url,pub.doi_url])
+ edges.append([pub.doi_url,reference.doi_url])
# adds only edge if citation already exists
else:
- edges.append([reference.doi_url,pub.doi_url])
+ edges.append([pub.doi_url,reference.doi_url])
@@ -89,13 +94,17 @@ def create_graph_structure_references(pub, search_depth, search_depth_max):
# doi_citations: input list of citet dois
# search_height: current search_height of height-first-search
# search_height_max: maximal search_height for dfs
-def process_citations_rec(doi_citations, search_height, search_height_max):
+def process_citations_rec(doi_citations, search_height, search_height_max, test_var):
# height of search is increased by 1 with each recursive call
search_height += 1
# create class object for every citation from list
for pub_doi in doi_citations:
- pub = input_test_func(pub_doi)
+ if (test_var):
+ pub = input_test_func(pub_doi)
+ else:
+ pub = input(pub_doi)
+
create_graph_structure_citations(pub, search_height, search_height_max)
# If the maximum height has not yet been reached, all references from the publication
# are written to an array and the function is called again with this array.
@@ -109,7 +118,7 @@ def process_citations_rec(doi_citations, search_height, search_height_max):
citations_list.append(citation.doi_url)
# recursive call of function.
- process_citations_rec(citations_list, search_height, search_height_max)
+ process_citations_rec(citations_list, search_height, search_height_max, test_var)
@@ -117,13 +126,17 @@ def process_citations_rec(doi_citations, search_height, search_height_max):
# doi_references: input list of referenced dois
# search_depth: current search_depth of height-first-search
# search_depth_max: maximal search_depth for dfs
-def process_references_rec(doi_references, search_depth, search_depth_max):
+def process_references_rec(doi_references, search_depth, search_depth_max, test_var):
# The depth is increased by 1 with each recursive call
search_depth += 1
# create class object for every citation from list
for pub_doi in doi_references:
- pub = input_test_func(pub_doi)
+ if (test_var):
+ pub = input_test_func(pub_doi)
+ else:
+ pub = input(pub_doi)
+
create_graph_structure_references(pub, search_depth, search_depth_max)
# If the maximum depth has not yet been reached, all references from the publication
# are written to an array and the function is called again with this array.
@@ -133,16 +146,17 @@ def process_references_rec(doi_references, search_depth, search_depth_max):
# currently only the references with acs are stored in the URL, because we can't
# extract the info from other sources.
- if ("acs" in reference.doi_url):
+ if ("acs" in reference.doi_url or test_var == True):
references_list.append(reference.doi_url)
+
# recursive call of function.
- process_references_rec(references_list, search_depth, search_depth_max)
+ process_references_rec(references_list, search_depth, search_depth_max, test_var)
-def process_main(doi_input_list, search_height, search_depth):
+def process_main(doi_input_list, search_height, search_depth, test_var = False):
# ERROR-Handling doi_array = NULL
if (len(doi_input_list) == 0):
print("Error, no input data")
@@ -161,16 +175,33 @@ def process_main(doi_input_list, search_height, search_depth):
nodes = []
edges = []
- initialize_nodes_list(doi_input_list)
- process_citations_rec(doi_input_list, 0, search_height)
- process_references_rec(doi_input_list, 0, search_depth)
+ initialize_nodes_list(doi_input_list,test_var)
+ process_citations_rec(doi_input_list, 0, search_height, test_var)
+ process_references_rec(doi_input_list, 0, search_depth, test_var)
output_to_json(nodes,edges)
# only for internal testing
return(nodes,edges)
+def print_graph(nodes, edges):
+ print("Knoten:\n")
+ for node in nodes:
+ print(node.title, "\n")
+ print("\n Kanten:\n")
+ for edge in edges:
+ print(edge,"\n")
+
+
+# function to test cycles
+def test_cycle():
+ arr = []
+ arr.append('doiz1')
+ #arr.append('doiz2')
+ nodes,edges = process_main(arr,1,1,True)
+
+ print_graph(nodes, edges)
# program test, because there is no connection to the input yet.
def test_print():
@@ -185,19 +216,11 @@ def test_print():
#url = sys.argv[1]
#arr.append[url]
- arr.append('doi1')
- #arr.append('doi2')
- #arr.append('doi3')
-
- nodes,edges = process_main(arr,1,1)
+ nodes,edges = process_main(arr,2,2,True)
- print("Knoten:\n")
- for node in nodes:
- print(node.title, "\n")
- print("\n Kanten:\n")
- for edge in edges:
- print(edge,"\n")
+ print_graph(nodes, edges)
-test_print()
+#test_print()
+test_cycle()
\ No newline at end of file
diff --git a/verarbeitung/__pycache__/input_test.cpython-39.pyc b/verarbeitung/__pycache__/input_test.cpython-39.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..d5948ff804073098a6d097ad17e81503eb7ec86b
Binary files /dev/null and b/verarbeitung/__pycache__/input_test.cpython-39.pyc differ
diff --git a/verarbeitung/__pycache__/json_demo.cpython-39.pyc b/verarbeitung/__pycache__/json_demo.cpython-39.pyc
index 29c2c14b5229d9768c2a273f8e1adba6cfcfc63f..a4f37b5097c0c5a82e7d36cd45671fb178e749ca 100644
Binary files a/verarbeitung/__pycache__/json_demo.cpython-39.pyc and b/verarbeitung/__pycache__/json_demo.cpython-39.pyc differ
diff --git a/verarbeitung/input_test.py b/verarbeitung/input_test.py
index 79b00b1ce11e63f73e11251352745a673b8face9..c55f85219a7df0c76d37e6a34211a7c14ea3f1d7 100644
--- a/verarbeitung/input_test.py
+++ b/verarbeitung/input_test.py
@@ -60,4 +60,7 @@ beispiel1 = ['doi1', 'title1', ['contributor1'], 'journal1', 'date1', ['doi2'],
beispiel2 = ['doi2', 'title2', ['contributor2'], 'journal2', 'date2', [], ['doi1'], '']
beispiel3 = ['doi3', 'title3', ['contributor3'], 'journal3', 'date3', ['doi1'], [], '']
-list_of_arrays = [beispiel1, beispiel2, beispiel3]
+zyklus1 = ['doiz1', 'titlez1', ['contributorz1.1', 'contributorz1.2'], 'journalz1', 'datez1', ['doiz2'], ['doiz2'], '']
+zyklus2 = ['doiz2', 'titlez2', ['contributorz2.1', 'contributorz2.2'], 'journalz2', 'datez2', ['doiz1'], ['doiz1'], '']
+
+list_of_arrays = [beispiel1, beispiel2, beispiel3, zyklus1, zyklus2]
diff --git a/verarbeitung/json_text.json b/verarbeitung/json_text.json
index 683e49f3e3175e12dcbe10df1e48c51dd27a8b77..8f648bf42654aefc13dd47dcecee507306184420 100644
--- a/verarbeitung/json_text.json
+++ b/verarbeitung/json_text.json
@@ -1 +1 @@
-{"nodes": [{"name": "title1", "author": ["contributor1"], "year": "date1", "journal": "journal1", "doi": "doi1", "group": "input"}, {"name": "title3", "author": ["contributor3"], "year": "date3", "journal": "journal3", "doi": "doi3", "group": "height"}, {"name": "title2", "author": ["contributor2"], "year": "date2", "journal": "journal2", "doi": "doi2", "group": "depth"}], "links": [{"source": "doi1", "target": "doi3"}, {"source": "doi2", "target": "doi1"}]}
\ No newline at end of file
+{"nodes": [{"name": "titlez1", "author": ["contributorz1.1", "contributorz1.2"], "year": "datez1", "journal": "journalz1", "doi": "doiz1", "group": "input"}, {"name": "titlez2", "author": ["contributorz2.1", "contributorz2.2"], "year": "datez2", "journal": "journalz2", "doi": "doiz2", "group": "depth"}], "links": [{"source": "doiz1", "target": "doiz2"}]}
\ No newline at end of file
diff --git "a/verarbeitung/n\303\266tige Tests.txt" "b/verarbeitung/n\303\266tige Tests.txt"
new file mode 100644
index 0000000000000000000000000000000000000000..95563280436fbf6b9b8702dffef6f32e213f5a16
--- /dev/null
+++ "b/verarbeitung/n\303\266tige Tests.txt"
@@ -0,0 +1,4 @@
+Zyklus
+großer Zyklus
+Innere Kanten vervollständigen
+