def test_tag_ner_list_str_latin(self):
"""Test make_ner(), list, str."""
text_list = ["ut", "Venus", "Sirius"]
text_list_iu = [replace_jv(x) for x in text_list]
text = ner.tag_ner("lat", input_text=text_list_iu, output_type=str)
target = " ut Uenus/Entity Sirius/Entity"
self.assertEqual(text, target)
def test_tag_ner_str_str_latin(self):
"""Test make_ner(), str, str."""
text_str = """ut Venus, ut Sirius, ut Spica, ut aliae quae primae dicuntur esse mangitudinis."""
text_str_iu = replace_jv(text_str)
text = ner.tag_ner("lat", input_text=text_str_iu, output_type=str)
target = " ut Uenus/Entity, ut Sirius/Entity, ut Spica/Entity, ut aliae quae primae dicuntur esse mangitudinis."
self.assertEqual(text, target)
def test_tag_ner_str_list_latin(self):
"""Test make_ner(), str, list."""
text_str = """ut Venus, ut Sirius, ut Spica, ut aliae quae primae dicuntur esse mangitudinis."""
text_str_iu = replace_jv(text_str)
tokens = ner.tag_ner("lat", input_text=text_str_iu, output_type=list)
target = [
("ut", ),
("Uenus", "Entity"),
(",", ),
("ut", ),
("Sirius", "Entity"),
(",", ),
("ut", ),
("Spica", "Entity"),
(",", ),
("ut", ),
("aliae", ),
("quae", ),
("primae", ),
("dicuntur", ),
("esse", ),
("mangitudinis", ),
(".", ),
]
self.assertEqual(tokens, target)
def test_tag_ner_list_list_latin(self):
"""Test make_ner(), list, list."""
text_list = ["ut", "Venus", "Sirius"]
text_list_iu = [replace_jv(x) for x in text_list]
tokens = ner.tag_ner("lat", input_text=text_list_iu, output_type=list)
target = [("ut", ), ("Uenus", "Entity"), ("Sirius", "Entity")]
self.assertEqual(tokens, target)
def test_backoff_latin_lemmatizer_verbose(self):
"""Test LatinBackoffLemmatizer"""
train = [[
("ceterum", "ceterus"),
("antequam", "antequam"),
("destinata", "destino"),
("componam", "compono"),
]]
lemmatizer = LatinBackoffLemmatizer(verbose=True)
test_str = """Ceterum antequam destinata componam"""
target = [
("ceterum", "ceterum",
"<UnigramLemmatizer: CLTK Sentence Training Data>"),
(
"antequam",
"antequam",
"<UnigramLemmatizer: CLTK Sentence Training Data>",
),
(
"destinata",
"destino",
"<UnigramLemmatizer: CLTK Sentence Training Data>",
),
("componam", "compono", "<DictLemmatizer: Morpheus Lemmas>"),
]
tokenizer = LatinWordTokenizer()
test_str = test_str.lower()
test_str = replace_jv(test_str)
tokens = tokenizer.tokenize(test_str)
lemmas = lemmatizer.lemmatize(tokens)
self.assertEqual(lemmas, target)
def test_regex_lemmatizer(self):
"""Test regex_lemmatizer()"""
sub = [("(.)ab(o|is|it|imus|itis|unt)$", r"\1o")]
lemmatizer = RegexpLemmatizer(sub)
test_str = "amabimus"
target = [("amabimus", "amo")]
tokenizer = LatinWordTokenizer()
test_str = test_str.lower()
test_str = replace_jv(test_str)
tokens = tokenizer.tokenize(test_str)
lemmas = lemmatizer.lemmatize(tokens)
self.assertEqual(lemmas, target)
def test_backoff_latin_lemmatizer(self):
"""Test LatinBackoffLemmatizer"""
train = [[
("ceterum", "ceterus"),
("antequam", "antequam"),
("destinata", "destino"),
("componam", "compono"),
]]
lemmatizer = LatinBackoffLemmatizer()
test_str = """Ceterum antequam destinata componam"""
target = [
("ceterum", "ceterum"),
("antequam", "antequam"),
("destinata", "destino"),
("componam", "compono"),
]
tokenizer = LatinWordTokenizer()
test_str = test_str.lower()
test_str = replace_jv(test_str)
tokens = tokenizer.tokenize(test_str)
lemmas = lemmatizer.lemmatize(tokens)
self.assertEqual(lemmas, target)
def test_dict_lemmatizer(self):
"""Test model_lemmatizer()"""
lemmas = {
"ceterum": "ceterus",
"antequam": "antequam",
"destinata": "destino",
"componam": "compono",
}
lemmatizer = DictLemmatizer(lemmas=lemmas)
test_str = "Ceterum antequam destinata componam"
target = [
("ceterum", "ceterus"),
("antequam", "antequam"),
("destinata", "destino"),
("componam", "compono"),
] # pylint: disable=line-too-long
tokenizer = LatinWordTokenizer()
test_str = test_str.lower()
test_str = replace_jv(test_str)
tokens = tokenizer.tokenize(test_str)
lemmas = lemmatizer.lemmatize(tokens)
self.assertEqual(lemmas, target)
def test_unigram_lemmatizer(self):
"""Test unigram_lemmatizer()"""
train = [
[
("ceterum", "ceterus"),
("antequam", "antequam"),
("destinata", "destino"),
("componam", "compono"),
]
] # pylint: disable=line-too-long
lemmatizer = UnigramLemmatizer(train=train)
test_str = """Ceterum antequam destinata componam"""
target = [
("ceterum", "ceterus"),
("antequam", "antequam"),
("destinata", "destino"),
("componam", "compono"),
] # pylint: disable=line-too-long
tokenizer = LatinWordTokenizer()
test_str = test_str.lower()
test_str = replace_jv(test_str)
tokens = tokenizer.tokenize(test_str)
lemmas = lemmatizer.lemmatize(tokens)
self.assertEqual(lemmas, target)