def test_es_lemmarizer(self):
keyword = "ciudades"
results = tfg_nlp.process(keyword)
print("Lemma de %s es: %s" % (keyword, tfg_nlp.es_lemmatizer(keyword)))
self.assertEqual(tfg_nlp.es_lemmatizer(keyword),
results["result"]["lemmatizer"])
def test_en_lemmatizer(self):
keyword = "city"
results = tfg_nlp.process(keyword)
print("Lemma of %s is: %s" % (keyword, tfg_nlp.en_lemmatizer(keyword)))
self.assertEqual(tfg_nlp.en_lemmatizer(keyword),
results["result"]["lemmatizer"])
def test_ca_lemmarizer(self):
keyword = "investigació"
results = tfg_nlp.process(keyword)
print("Lemma de %s es: %s" % (keyword, tfg_nlp.ca_lemmatizer(keyword)))
self.assertEqual(tfg_nlp.ca_lemmatizer(keyword),
results["result"]["lemmatizer"])
def test_case_other_language(self):
keywords = ["wilkomen"]
results = [tfg_nlp.process(keyword) for keyword in keywords]
print(
json.dumps(results, indent=1,
ensure_ascii=False).encode('utf-8').decode())
for result in results:
self.assertEqual(None, result["result"]["Wikidata"])
def test_ThinkingAloud(self):
keyword = "thinking aloud"
result = tfg_nlp.process(keyword)["result"]
print(
json.dumps(result, indent=1,
ensure_ascii=False).encode('utf-8').decode())
self.assertEqual("en", result["lang"])
self.assertEqual("http://www.wikidata.org/entity/Q391810",
result["Wikidata"])
def test_case_punctuation_mark(self):
keywords = ["long-range interactions"]
results = [tfg_nlp.process(keyword) for keyword in keywords]
print(
json.dumps(results, indent=1,
ensure_ascii=False).encode('utf-8').decode())
for result in results:
self.assertEqual("http://www.wikidata.org/entity/Q63926701",
result["result"]["Wikidata"])
def test_case_numbers(self):
keywords = ["1917"]
results = [tfg_nlp.process(keyword) for keyword in keywords]
print(
json.dumps(results, indent=1,
ensure_ascii=False).encode('utf-8').decode())
for result in results:
self.assertEqual("http://www.wikidata.org/entity/Q2092",
result["result"]["Wikidata"])
def test_case_different_description3(self):
keywords = ["navegación"]
results = [tfg_nlp.process(keyword) for keyword in keywords]
print(
json.dumps(results, indent=1,
ensure_ascii=False).encode('utf-8').decode())
for result in results:
self.assertEqual("http://www.wikidata.org/entity/Q1972518",
result["result"]["Wikidata"])
def test_Cryptography(self):
keywords = ['cryptography', 'criptografia', 'criptografía']
results = [tfg_nlp.process(keyword) for keyword in keywords]
print(
json.dumps(results, indent=1,
ensure_ascii=False).encode('utf-8').decode())
for result in results:
self.assertEqual("http://www.wikidata.org/entity/Q8789",
result["result"]["Wikidata"])
def test_case_strange_character(self):
keywords = ["β-catenin"]
results = [tfg_nlp.process(keyword) for keyword in keywords]
print(
json.dumps(results, indent=1,
ensure_ascii=False).encode('utf-8').decode())
for result in results:
self.assertEqual("http://www.wikidata.org/entity/Q10861922",
result["result"]["Wikidata"])
def test_case_name_of_person(self):
keywords = ["antonio del amo"]
results = [tfg_nlp.process(keyword) for keyword in keywords]
print(
json.dumps(results, indent=1,
ensure_ascii=False).encode('utf-8').decode())
for result in results:
self.assertEqual("http://www.wikidata.org/entity/Q607975",
result["result"]["Wikidata"])
def test_case_punctuation_mark2(self):
keywords = ["qrt-pcr"]
results = [tfg_nlp.process(keyword) for keyword in keywords]
print(
json.dumps(results, indent=1,
ensure_ascii=False).encode('utf-8').decode())
for result in results:
self.assertEqual(
"http://dbpedia.org/resource/Polymerase_chain_reaction",
result["result"]["DBpedia"])
def test_Acronym(self):
keywords = ["artificial intelligence", "AI"]
results = [tfg_nlp.process(keyword) for keyword in keywords]
print(
json.dumps(results, indent=1,
ensure_ascii=False).encode('utf-8').decode())
for result in results:
self.assertEqual(
"http://dbpedia.org/resource/Artificial_intelligence",
result["result"]["DBpedia"])