def test_location_method_2():
document = build_document_from_string("""
# na nb nc ha hb
ha = 1 + 1 + 0 = 2
middle = 0
ha hb = 2 + 1 + 0 = 3
first = 1
ha hb ha = 3
last = 1
# hc hd
hb hc hd = 3 + 1 + 0 = 4
ha hb = 2 + 1 + 0 = 3
""")
summarizer = EdmundsonSummarizer()
summarizer.null_words = ("na", "nb", "nc", "nd", "ne",)
sentences = summarizer.location_method(document, 4, w_p1=0, w_p2=0)
assert list(map(to_unicode, sentences)) == [
"ha hb = 2 + 1 + 0 = 3",
"ha hb ha = 3",
"hb hc hd = 3 + 1 + 0 = 4",
"ha hb = 2 + 1 + 0 = 3",
]
def test_less_sentences_than_requested():
document = build_document_from_string("""
This is only one sentence.
""")
summarizer = RandomSummarizer()
sentences = summarizer(document, 10)
assert len(sentences) == 1
assert to_unicode(sentences[0]) == "This is only one sentence."
def test_headings():
document = build_document_from_string("""
Nějaký muž šel kolem naší zahrady
Nějaký jiný muž šel kolem vaší zahrady
# Nová myšlenka
Už už abych taky šel
""")
assert list(map(to_unicode, document.headings)) == ["Nová myšlenka"]
def test_only_instances_of_sentence_allowed():
document = build_document_from_string("""
Nějaký muž šel kolem naší zahrady
Nějaký jiný muž šel kolem vaší zahrady
# Nová myšlenka
Už už abych taky šel
""")
with pytest.raises(TypeError):
Paragraph(list(document.sentences) + ["Last sentence"])
def test_sentences_in_right_order():
document = build_document_from_string("""
# Heading one
First sentence.
Second sentence.
Third sentence.
""")
summarizer = RandomSummarizer()
sentences = summarizer(document, 4)
assert len(sentences) == 3
assert to_unicode(sentences[0]) == "First sentence."
assert to_unicode(sentences[1]) == "Second sentence."
assert to_unicode(sentences[2]) == "Third sentence."
def test_more_sentences_than_requested():
document = build_document_from_string("""
# Heading one
First sentence.
Second sentence.
Third sentence.
# Heading two
I like sentences
They are so wordy
And have many many letters
And are green in my editor
But someone doesn't like them :(
""")
summarizer = RandomSummarizer()
sentences = summarizer(document, 4)
assert len(sentences) == 4
def test_title_method_1():
document = build_document_from_string("""
# This is cool heading
Because I am sentence I like words
And because I am string I like characters
# blank and heading
This is next paragraph because of blank line above
Here is the winner because contains words like cool and heading
""")
summarizer = EdmundsonSummarizer()
summarizer.null_words = ("this", "is", "I", "am", "and",)
sentences = summarizer.title_method(document, 1)
assert list(map(to_unicode, sentences)) == [
"Here is the winner because contains words like cool and heading",
]
def test_mixed_cue_key():
document = build_document_from_string("""
# This is cool heading
Because I am sentence I like words
And because I am string I like characters
# blank and heading
This is next paragraph because of blank line above
Here is the winner because contains words like cool and heading
""")
summarizer = EdmundsonSummarizer(cue_weight=1, key_weight=1, title_weight=0, location_weight=0)
summarizer.bonus_words = ("cool", "heading", "sentence", "words", "like", "because")
summarizer.stigma_words = ("this", "is", "I", "am", "and",)
sentences = summarizer(document, 2)
assert list(map(to_unicode, sentences)) == [
"Because I am sentence I like words",
"Here is the winner because contains words like cool and heading",
]
