def test_location_method_with_empty_document():
summarizer = EdmundsonSummarizer()
summarizer.null_words = ("na", "nb", "nc",)
sentences = summarizer.location_method(build_document(), 10)
assert list(map(to_unicode, sentences)) == []
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 build_edmundson(parser, language):
summarizer = EdmundsonSummarizer(Stemmer(language))
summarizer.null_words = get_stop_words(language)
summarizer.bonus_words = parser.significant_words
summarizer.stigma_words = parser.stigma_words
return summarizer
def test_null_words_property():
summarizer = EdmundsonSummarizer()
assert summarizer.null_words == frozenset()
words = ("word", "another", "and", "some", "next",)
summarizer.null_words = words
assert summarizer.null_words == frozenset(words)
def test_title_method_without_title():
document = build_document(
("This is sentence", "This is another one",),
("And some next sentence but no heading",)
)
summarizer = EdmundsonSummarizer()
summarizer.null_words = ("this", "is", "some", "and",)
sentences = summarizer.title_method(document, 10)
assert list(map(to_unicode, sentences)) == [
"This is sentence",
"This is another one",
"And some next sentence but no heading",
]
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_title_method_with_empty_document():
summarizer = EdmundsonSummarizer()
summarizer.null_words = ("ba", "bb", "bc",)
sentences = summarizer.title_method(build_document(), 10)
assert list(map(to_unicode, sentences)) == []