def test_performance():
""" Tests calculate_tf for huge texts.
"""
import random
palavras = ["zero", "one", "two", "three", "four", "five", "six",
"seven", "eight", "nine", "R$1000.00"]
contents = ""
language = 'english'
for _ in range(10000): # increase number and measure time when necessary
contents += palavras[random.randint(0, len(palavras) - 1)] + " "
text.calculate_tf(language, contents)
def test_calculate_tf_en():
""" Tests calculate_tf for English contents.
"""
language = "english"
contents = "Cooks who don't love cooking don't cook well."
results = text.calculate_tf(language, contents)
nose.tools.eq_(results['cook'], 3, "Wrong TF")
nose.tools.eq_(results['love'], 1, "Wrong TF")
nose.tools.eq_(results['well'], 1, "Wrong TF")
def test_calculate_tf_pt():
""" Tests calculate_tf for Portuguese contents.
"""
language = "portuguese"
contents = "Eu não gostava do gosto gasto do gesto de agosto."
results = text.calculate_tf(language, contents)
nose.tools.eq_(results['gost'], 2, "Wrong TF")
nose.tools.eq_(results['gast'], 1, "Wrong TF")
nose.tools.eq_(results['gest'], 1, "Wrong TF")
nose.tools.eq_(results['agost'], 1, "Wrong TF")
def main(argv):
if len(argv) < 2:
msg = "You must specify the language and the text"
log.error(msg)
return {"success": False, "message": msg}
vocabulary_language = argv[0]
text_for_tf = argv[1]
tf_by_term = text.calculate_tf(vocabulary_language, text_for_tf)
if tf_by_term is not None:
return {"success": True, "results": tf_by_term}