From aa86f2bb0f87326eb82654a075005b5956a9af32 Mon Sep 17 00:00:00 2001
From: Philipp Schneider <schneider.philipp@uni-muenster.de>
Date: Wed, 10 Aug 2022 17:57:38 +0200
Subject: [PATCH] Bug fixing for updated data and structure
---
.../integrate_manuscript_metadata_into_kg.py | 7 ++++++-
src/rdf-mappings/map-tblBranch.py | 10 +++++++---
2 files changed, 13 insertions(+), 4 deletions(-)
diff --git a/src/rdf-mappings/integrate_manuscript_metadata_into_kg.py b/src/rdf-mappings/integrate_manuscript_metadata_into_kg.py
index a9b3035..9158a26 100644
--- a/src/rdf-mappings/integrate_manuscript_metadata_into_kg.py
+++ b/src/rdf-mappings/integrate_manuscript_metadata_into_kg.py
@@ -92,6 +92,9 @@ if __name__ == '__main__':
if not pd.isnull(row['grid-system']):
g.add((manuscript_uri, dho_obj_n.hasGridSystem, Literal(row['grid-system'], datatype=XSD.string)))
+ # Serialize object graph
+ functions.serialize_graph(g, output_files)
+
# Integrate knowledge graph on heraldic data
print('Loading Knowledge Graph file...')
g.parse(kg_file)
@@ -109,7 +112,9 @@ if __name__ == '__main__':
g.add((subject, dho_rep_n.partOfObject, manuscript_uri))
# Serialize the prepared graph
- functions.serialize_graph(g, output_files)
+ print('Serialilzing representation graph...')
+ g.serialize(destination='data/rdf-output/research-dataset/knowledge-graph-representation-research-dataset.ttl', format='ttl')
+ g.serialize(destination='data/rdf-output/research-dataset/knowledge-graph-representation-research-dataset.jsonld', format='json-ld')
diff --git a/src/rdf-mappings/map-tblBranch.py b/src/rdf-mappings/map-tblBranch.py
index 2258a5c..aa77a9c 100644
--- a/src/rdf-mappings/map-tblBranch.py
+++ b/src/rdf-mappings/map-tblBranch.py
@@ -244,6 +244,9 @@ def add_layer(layer_number, layer_content, field_node, previous_layer_node=None,
if charge + '_Num' in df_tblBranch.columns and not pd.isnull(row[charge + '_Num']):
if row[charge + '_Num'] == 'Multiple':
g.add((charge_node, dho_n.hasNumber, dho_n.Multiple))
+ elif row[charge + '_Num'] == 'pair of':
+ number_uri = create_owl_class_from_string('pair of')
+ g.add((charge_node, dho_n.hasNumber, number_uri))
else:
g.add((charge_node, dho_n.hasNumber, Literal(int(row[charge + '_Num']))))
@@ -382,9 +385,6 @@ if mapping_config['create_research_dataset'] == False:
df_tblBranch = df_tblBranch[(df_tblBranch['checked_for_publication'] == "true") | (df_tblBranch['checked_for_publication'] == 'secondary-description')]
df_tblBranch = df_tblBranch[pd.isnull(df_tblBranch['published_as_rdf'])]
-# Filter all entries that cannot yet be used for RDF transformation and must therefore be skipped
-df_tblBranch = df_tblBranch[(df_tblBranch['checkBlasonIndividually'] == "true")]
-
print(df_tblBranch)
# Initialize rdflib graph object
@@ -408,6 +408,10 @@ if mapping_config['add_metadata'] == True:
# Iterate through CSV to build graph
for index, row in df_tblBranch.iterrows():
+ # Filter all entries that cannot yet be used for RDF transformation and must therefore be skipped
+ if row['checkBlasonIndividually'] == 'true' or row['checkBlasonIndividually'] == True:
+ continue
+
# New coa description
branch_id = str(row['BranchID'])
--
GitLab