def test_rjg20():
link = "https://people.bath.ac.uk/rjg20/index.html"
filename = "../data/rjg20-index.html"
with open(filename) as file:
expect = file.read().splitlines()
link_str = wt.open_page(link)
link_lines = link_str.splitlines()
assert link_lines == expect
def test_count_rjg20():
'''
Test count words in page
'''
link = "https://people.bath.ac.uk/rjg20/index.html"
expect = 679
text = wt.open_page(link)
assert wt.count_words(text) == expect
def test_count_hamlet():
'''
Test count words in the Hamlet
'''
link = "http://www.gutenberg.org/cache/epub/2265/pg2265.txt"
expect = 32211
text = wt.open_page(link)
assert wt.count_words(text) == expect
def test_count_macbeth():
'''
Test count words in the Scottish play
'''
link = "http://www.gutenberg.org/cache/epub/2264/pg2264.txt"
expect = 20347
text = wt.open_page(link)
assert wt.count_words(text) == expect
def test_occs_macbeth4():
'''
Test count occs in the Scottish play
'''
link = "http://www.gutenberg.org/cache/epub/2264/pg2264.txt"
words = ["Macb.", "Macd.", "Lady."]
expect = [137, 58, 41]
text = wt.open_page(link)
assert wt.count_occs(text, words) == expect
def test_occs_macbeth3():
'''
Test count occs in the Scottish play
'''
link = "http://www.gutenberg.org/cache/epub/2264/pg2264.txt"
words = ["Macbeth", "Macduff"]
expect = [70, 28]
text = wt.open_page(link)
assert wt.count_occs(text, words) == expect
def test_strip_macbeth_stop():
'''
Test split and strip macbeth on 'Actus' using stop values
'''
link = "http://www.gutenberg.org/cache/epub/2264/pg2264.txt"
text = wt.open_page(link)
key_word = 'Actus'
for i in range(1,6):
expect = i
split = wt.split_strip_text(text, key_word, stop = i)
assert len(split) == expect
def test_split_macbeth():
'''
Test split macbeth on 'Actus'
'''
link = "http://www.gutenberg.org/cache/epub/2264/pg2264.txt"
expect = 6
text = wt.open_page(link)
key_word = 'Actus'
split = wt.split_strip_text(text, key_word)
assert len(split) == expect
def test_strip_macbeth_both():
'''
Test split and strip macbeth on 'Actus' using stop values
'''
link = "http://www.gutenberg.org/cache/epub/2264/pg2264.txt"
text = wt.open_page(link)
key_word = 'Actus'
for i in range(0,6):
for j in range(i+1,6):
expect = j - i
split = wt.split_strip_text(text, key_word, start = i, stop = j)
assert len(split) == expect, str(i)+'is i and j is '+str(j)