Add path to test if the dbpedia result set is enlargeable

app.py

@@ -3,11 +3,20 @@ from flask.json import jsonify
 
 from src.main import assemble_wikidata_groundtruth_english, assemble_dbpedia_groundtruth_english, \
     assemble_wikidata_triples, \
-    assemble_dbpedia_triples, collect_wikidata_results_with_title
+    assemble_dbpedia_triples, collect_wikidata_results_with_title, test_if_data_is_enlargeable_for_dbpedia
 
 app = Flask(__name__)
 
 
+# Todo: Füge eine Route ein die die englischen Werte nicht enhält
+# Todo: Füge eine Route ein die die zusätlichen Werte in die Triple-Dateien einbringt.
+# Todo: Es soll vorher immer erst der Grunddatensatz erzeugt werden und dann die zusätzlichen Informationen ergänzt werden.
+
+@app.route('/dbpedia/collect/enlargeable')
+def dbpedia_data_can_enlarge():
+    return jsonify(test_if_data_is_enlargeable_for_dbpedia())
+
+
 @app.route('/wikidata/collect/title')
 def wikidata_collect_title():
     return jsonify(collect_wikidata_results_with_title())

src/main.py

-import json
 from tokenize import String
 from typing import Dict, List
 
 from src import WIKIDATA_ENTRYPOINT, DBPEDIA_ENTRYPOINT
+from src.dbpedia.keys import ResultKeys
 from src.lib.decapper import Decapper
 from src.lib.engine import SPARQLEngine
-from src.lib.reader import FileReader
 from src.lib.ntriple import NTriple
+from src.lib.reader import FileReader
 from src.lib.writer import FileWriter
 from src.wikidata.keys import ResultKeys
-from src.dbpedia.keys import ResultKeys
+
+
+def test_if_data_is_enlargeable_for_dbpedia() -> Dict:
+    """
+    This method assembles a groundtruth an checks during 10 iterations if the collected data size increase or not.
+
+    :return: Result set with the information if it is possible for dbpedia to gain more data.
+    """
+
+    engine = SPARQLEngine(entrypoint=DBPEDIA_ENTRYPOINT, query='static/dbpedia_groundtruth.sparql')
+    data = engine.get_json()
+    size = len(data['results']['bindings'])
+    increased = False
+    for i in range(0, 10):
+        all_movies = [Decapper(movie[ResultKeys.movie.value]).unpack() for movie in data['results']['bindings']]
+        engine = SPARQLEngine(entrypoint=DBPEDIA_ENTRYPOINT, query='static/dbpedia_groundtruth.sparql')
+        appendix_res = engine.get_json()
+        for candidate in appendix_res['results']['bindings']:
+            if Decapper(candidate[ResultKeys.movie.value]).unpack() not in all_movies:
+                data['results']['bindings'] += [candidate]
+                increased = True
+        print('Gain after step ' + str(i) + ' is: ' + str(size - len(all_movies)))
+        size = len(all_movies)
+
+    return {
+        'increase': increased,
+        'current_size': size
+    }
 
 
 def assemble_wikidata_groundtruth_english() -> Dict: