Feature/ner (#103)

NER und Sentiment-Pipeline mit Services zur Datenextraktion.

---------

Co-authored-by: Philipp Horstenkamp <philipp@horstenkamp.de>
Co-authored-by: TrisNol <tristan.nolde@yahoo.de>

tests/utils/mongo/ner_service_test.py

@@ -0,0 +1,54 @@
+"""Tests for checking NER Services."""
+
+from aki_prj23_transparenzregister.utils.mongo.ner_service import NerAnalysisService
+
+
+def test_ner_spacy() -> None:
+    """Mock TestNerService."""
+    # Create instance of NerAnalysisService with use_spacy=True
+    ner_service = NerAnalysisService(
+        use_spacy=True, use_transformer=False, use_companylist=False
+    )
+    # 1st testing
+    doc = {"title": "Siemens ist ein Unternehmen."}
+    result = ner_service.ner_spacy(doc, ent_type="ORG", doc_attrib="title")
+    assert result == {"Siemens": 1}
+
+    # 2nd testing
+    doc = {"text": "BASF ist ein großes Unternehmen."}
+    result = ner_service.ner_spacy(doc, ent_type="ORG", doc_attrib="text")
+    assert result == {"BASF": 1}
+
+
+def test_ner_company_list() -> None:
+    """Mock test_ner_company."""
+    # Create instance of NerAnalysisService with use_use_companylist=True
+    ner_service = NerAnalysisService(
+        use_spacy=False, use_transformer=False, use_companylist=True
+    )
+
+    doc = {"title": "Siemens ist ein Unternehmen."}
+    result = ner_service.ner_company_list(doc, ent_type="ORG", doc_attrib="title")
+    assert result == {"siemens": 1}
+
+    # 2nd testing
+    doc = {"text": "BASF ist ein großes Unternehmen."}
+    result = ner_service.ner_company_list(doc, ent_type="ORG", doc_attrib="text")
+    assert result == {"basf": 1}
+
+
+def test_ner_transformer() -> None:
+    """Mock test_ner_company."""
+    # Create instance of NerAnalysisService with use_use_companylist=True
+    ner_service = NerAnalysisService(
+        use_spacy=False, use_transformer=True, use_companylist=False
+    )
+
+    doc = {"title": "Siemens ist ein Unternehmen."}
+    result = ner_service.ner_transformer(doc, ent_type="ORG", doc_attrib="title")
+    assert result == {"Siemens": 1}
+
+    # 2nd testing
+    doc = {"text": "BASF ist ein großes Unternehmen."}
+    result = ner_service.ner_transformer(doc, ent_type="ORG", doc_attrib="text")
+    assert result == {"BASF": 1}