def test_tokenization(self):
"""
The whether the elasticsearch analyzer yields the right tokens for the german analyzer.
Check the comments in mainapp.documents.index for more details
"""
tokenizations = {
"die": [],
"hunde": ["hunde", "hund"],
"wi-fi": ["wi", "fi"],
"Feuerwehr": ["feuerwehr"], # Would ideally split the words
"oktopoden": ["oktopoden", "oktopod"],
"Äpfel": ["äpfel", "apfel"],
"ging": ["ging"],
"schwierigste": ["schwierigste", "schwierig"],
"1234/89": ["1234", "89"], # Would be better if it included "1234/89"
}
text_analyzer = get_text_analyzer("german")
elastic_index = Index("mst-test-tokenization")
if not elastic_index.exists():
elastic_index.create()
elastic_index.close()
elastic_index.analyzer(text_analyzer)
elastic_index.save()
elastic_index.open()
elastic_index.flush()
for word, expected_tokens in tokenizations.items():
analysis = elastic_index.analyze(
body={"analyzer": "text_analyzer", "text": word}
)
actual_tokens = [i["token"] for i in analysis["tokens"]]
self.assertEqual(expected_tokens, actual_tokens, "Word was {}".format(word))
def analyze(self, text: str) -> Dict[str, List[Dict]]:
"""Shows what elasticsearch does with the tokens"""
elastic_index_file = Index(settings.ELASTICSEARCH_PREFIX + "-file")
elastic_index_file.analyzer(autocomplete_analyzer)
elastic_index_file.analyzer(text_analyzer)
return elastic_index_file.analyze(
body={"analyzer": "text_analyzer", "text": text}
)
