def test_cue_2(self):
document = build_document(("ba bb bc bb unknown ľščťžýáíé sb sc sb", ),
("Pepek likes spinach", ))
summarizer = EdmundsonSummarizer()
summarizer.bonus_words = (
"ba",
"bb",
"bc",
)
summarizer.stigma_words = (
"sa",
"sb",
"sc",
)
sentences = summarizer.cue_method(document, 10)
self.assertEqual(len(sentences), 2)
self.assertEqual(to_unicode(sentences[0]),
"ba bb bc bb unknown ľščťžýáíé sb sc sb")
self.assertEqual(to_unicode(sentences[1]), "Pepek likes spinach")
sentences = summarizer.cue_method(document, 1)
self.assertEqual(len(sentences), 1)
self.assertEqual(to_unicode(sentences[0]),
"ba bb bc bb unknown ľščťžýáíé sb sc sb")
def test_cue_2():
document = build_document(("ba bb bc bb unknown ľščťžýáíé sb sc sb", ),
("Pepek likes spinach", ))
summarizer = EdmundsonSummarizer()
summarizer.bonus_words = (
"ba",
"bb",
"bc",
)
summarizer.stigma_words = (
"sa",
"sb",
"sc",
)
sentences = summarizer.cue_method(document, 10)
assert list(map(to_unicode, sentences)) == [
"ba bb bc bb unknown ľščťžýáíé sb sc sb",
"Pepek likes spinach",
]
sentences = summarizer.cue_method(document, 1)
assert list(map(to_unicode, sentences)) == [
"ba bb bc bb unknown ľščťžýáíé sb sc sb",
]
def test_cue_with_no_bonus_words():
summarizer = EdmundsonSummarizer()
summarizer.stigma_words = (
"useless",
"bad",
"spinach",
)
with pytest.raises(ValueError):
summarizer.cue_method(build_document(), 10)
def test_cue_with_no_stigma_words():
summarizer = EdmundsonSummarizer()
summarizer.bonus_words = (
"great",
"very",
"beautiful",
)
with pytest.raises(ValueError):
summarizer.cue_method(build_document(), 10)
def test_cue_3(self):
document = build_document((
"ba " * 10,
"bb " * 10,
" sa" * 8 + " bb" * 10,
"bb bc ba",
), (), (
"babbbc " * 10,
"na nb nc nd sa" + " bc" * 10,
" ba n" * 10,
))
summarizer = EdmundsonSummarizer()
summarizer.bonus_words = (
"ba",
"bb",
"bc",
)
summarizer.stigma_words = (
"sa",
"sb",
"sc",
)
sentences = summarizer.cue_method(document, 5)
self.assertEqual(len(sentences), 5)
self.assertEqual(to_unicode(sentences[0]), ("ba " * 10).strip())
self.assertEqual(to_unicode(sentences[1]), ("bb " * 10).strip())
self.assertEqual(to_unicode(sentences[2]), "bb bc ba")
self.assertEqual(to_unicode(sentences[3]),
"na nb nc nd sa bc bc bc bc bc bc bc bc bc bc")
self.assertEqual(to_unicode(sentences[4]), ("ba n " * 10).strip())
def test_cue_empty(self):
summarizer = EdmundsonSummarizer()
summarizer.bonus_words = ("ba", "bb", "bc",)
summarizer.stigma_words = ("sa", "sb", "sc",)
sentences = summarizer.cue_method(build_document(), 10)
self.assertEqual(len(sentences), 0)
def test_cue_3():
document = build_document((
"ba " * 10,
"bb " * 10,
" sa" * 8 + " bb" * 10,
"bb bc ba",
), (), (
"babbbc " * 10,
"na nb nc nd sa" + " bc" * 10,
" ba n" * 10,
))
summarizer = EdmundsonSummarizer()
summarizer.bonus_words = (
"ba",
"bb",
"bc",
)
summarizer.stigma_words = (
"sa",
"sb",
"sc",
)
sentences = summarizer.cue_method(document, 5)
assert list(map(to_unicode, sentences)) == [
("ba " * 10).strip(),
("bb " * 10).strip(),
"bb bc ba",
"na nb nc nd sa bc bc bc bc bc bc bc bc bc bc",
("ba n " * 10).strip(),
]
def test_cue_3(self):
document = build_document(
(
"ba "*10,
"bb "*10,
" sa"*8 + " bb"*10,
"bb bc ba",
),
(),
(
"babbbc "*10,
"na nb nc nd sa" + " bc"*10,
" ba n"*10,
)
)
summarizer = EdmundsonSummarizer()
summarizer.bonus_words = ("ba", "bb", "bc",)
summarizer.stigma_words = ("sa", "sb", "sc",)
sentences = summarizer.cue_method(document, 5)
self.assertEqual(len(sentences), 5)
self.assertEqual(to_unicode(sentences[0]), ("ba "*10).strip())
self.assertEqual(to_unicode(sentences[1]), ("bb "*10).strip())
self.assertEqual(to_unicode(sentences[2]), "bb bc ba")
self.assertEqual(to_unicode(sentences[3]),
"na nb nc nd sa bc bc bc bc bc bc bc bc bc bc")
self.assertEqual(to_unicode(sentences[4]), ("ba n "*10).strip())
def test_cue_empty():
summarizer = EdmundsonSummarizer()
summarizer.bonus_words = ("ba", "bb", "bc",)
summarizer.stigma_words = ("sa", "sb", "sc",)
sentences = summarizer.cue_method(build_document(), 10)
assert list(map(to_unicode, sentences)) == []
def test_cue_2(self):
document = build_document(
("ba bb bc bb unknown ľščťžýáíé sb sc sb",),
("Pepek likes spinach",)
)
summarizer = EdmundsonSummarizer()
summarizer.bonus_words = ("ba", "bb", "bc",)
summarizer.stigma_words = ("sa", "sb", "sc",)
sentences = summarizer.cue_method(document, 10)
self.assertEqual(len(sentences), 2)
self.assertEqual(to_unicode(sentences[0]),
"ba bb bc bb unknown ľščťžýáíé sb sc sb")
self.assertEqual(to_unicode(sentences[1]), "Pepek likes spinach")
sentences = summarizer.cue_method(document, 1)
self.assertEqual(len(sentences), 1)
self.assertEqual(to_unicode(sentences[0]),
"ba bb bc bb unknown ľščťžýáíé sb sc sb")
def test_cue_1(self):
document = build_document(
("ba bb bc bb unknown ľščťžýáíé sb sc sb",)
)
summarizer = EdmundsonSummarizer()
summarizer.bonus_words = ("ba", "bb", "bc",)
summarizer.stigma_words = ("sa", "sb", "sc",)
sentences = summarizer.cue_method(document, 10)
self.assertEqual(len(sentences), 1)
def test_cue_2():
document = build_document(
("ba bb bc bb unknown ľščťžýáíé sb sc sb",),
("Pepek likes spinach",)
)
summarizer = EdmundsonSummarizer()
summarizer.bonus_words = ("ba", "bb", "bc",)
summarizer.stigma_words = ("sa", "sb", "sc",)
sentences = summarizer.cue_method(document, 10)
assert list(map(to_unicode, sentences)) == [
"ba bb bc bb unknown ľščťžýáíé sb sc sb",
"Pepek likes spinach",
]
sentences = summarizer.cue_method(document, 1)
assert list(map(to_unicode, sentences)) == [
"ba bb bc bb unknown ľščťžýáíé sb sc sb",
]
def test_cue_letters_case(self):
document = build_document(
("X X X", "x x x x",),
("w w w", "W W W W",)
)
summarizer = EdmundsonSummarizer()
summarizer.bonus_words = ("X", "w",)
summarizer.stigma_words = ("stigma",)
sentences = summarizer.cue_method(document, 2)
self.assertEqual(len(sentences), 2)
self.assertEqual(to_unicode(sentences[0]), "x x x x")
self.assertEqual(to_unicode(sentences[1]), "W W W W")
def test_cue_empty(self):
summarizer = EdmundsonSummarizer()
summarizer.bonus_words = (
"ba",
"bb",
"bc",
)
summarizer.stigma_words = (
"sa",
"sb",
"sc",
)
sentences = summarizer.cue_method(build_document(), 10)
self.assertEqual(len(sentences), 0)
def test_cue_empty():
summarizer = EdmundsonSummarizer()
summarizer.bonus_words = (
"ba",
"bb",
"bc",
)
summarizer.stigma_words = (
"sa",
"sb",
"sc",
)
sentences = summarizer.cue_method(build_document(), 10)
assert list(map(to_unicode, sentences)) == []
def test_cue_letters_case():
document = build_document(
("X X X", "x x x x",),
("w w w", "W W W W",)
)
summarizer = EdmundsonSummarizer()
summarizer.bonus_words = ("X", "w",)
summarizer.stigma_words = ("stigma",)
sentences = summarizer.cue_method(document, 2)
assert list(map(to_unicode, sentences)) == [
"x x x x",
"W W W W",
]
def test_cue_1(self):
document = build_document(("ba bb bc bb unknown ľščťžýáíé sb sc sb", ))
summarizer = EdmundsonSummarizer()
summarizer.bonus_words = (
"ba",
"bb",
"bc",
)
summarizer.stigma_words = (
"sa",
"sb",
"sc",
)
sentences = summarizer.cue_method(document, 10)
self.assertEqual(len(sentences), 1)
def test_cue_letters_case(self):
document = build_document((
"X X X",
"x x x x",
), (
"w w w",
"W W W W",
))
summarizer = EdmundsonSummarizer()
summarizer.bonus_words = (
"X",
"w",
)
summarizer.stigma_words = ("stigma", )
sentences = summarizer.cue_method(document, 2)
self.assertEqual(len(sentences), 2)
self.assertEqual(to_unicode(sentences[0]), "x x x x")
self.assertEqual(to_unicode(sentences[1]), "W W W W")
def test_cue_letters_case():
document = build_document((
"X X X",
"x x x x",
), (
"w w w",
"W W W W",
))
summarizer = EdmundsonSummarizer()
summarizer.bonus_words = (
"X",
"w",
)
summarizer.stigma_words = ("stigma", )
sentences = summarizer.cue_method(document, 2)
assert list(map(to_unicode, sentences)) == [
"x x x x",
"W W W W",
]
def test_cue_with_no_bonus_words():
summarizer = EdmundsonSummarizer()
summarizer.stigma_words = ("useless", "bad", "spinach",)
with pytest.raises(ValueError):
summarizer.cue_method(build_document(), 10)
def test_cue_with_no_words():
summarizer = EdmundsonSummarizer()
with pytest.raises(ValueError):
summarizer.cue_method(build_document(), 10)
def test_cue_with_no_stigma_words():
summarizer = EdmundsonSummarizer()
summarizer.bonus_words = ("great", "very", "beautiful",)
with pytest.raises(ValueError):
summarizer.cue_method(build_document(), 10)
def test_cue_with_no_words():
summarizer = EdmundsonSummarizer()
with pytest.raises(ValueError):
summarizer.cue_method(build_document(), 10)
def test_cue_3():
document = build_document(
(
"ba "*10,
"bb "*10,
" sa"*8 + " bb"*10,
"bb bc ba",
),
(),
(
"babbbc "*10,
"na nb nc nd sa" + " bc"*10,
" ba n"*10,
)
)
summarizer = EdmundsonSummarizer()
summarizer.bonus_words = ("ba", "bb", "bc",)
summarizer.stigma_words = ("sa", "sb", "sc",)
sentences = summarizer.cue_method(document, 5)
assert list(map(to_unicode, sentences)) == [
("ba "*10).strip(),
("bb "*10).strip(),
"bb bc ba",
"na nb nc nd sa bc bc bc bc bc bc bc bc bc bc",
("ba n "*10).strip(),
]
