def test_find_expanded_acronyms(self):
acronyms = find_expanded_acronyms('Howdy Neighbor')
self.assertEqual(len(acronyms), 0)
acronyms = find_expanded_acronyms(
'Did you work on the Alpha Beta Company (ABC) project?')
self.assertEqual(len(acronyms), 1)
self.assertTrue('ABC' in acronyms)
self.assertEqual(acronyms['ABC'], ['Alpha Beta Company'])
expansions = ['Different Expansions Fail', 'Dubious Expressions Fly']
acronyms = find_expanded_acronyms('{0} (DEF) if {1} (DEF)'.format(
expansions[0], expansions[1]))
self.assertEqual(len(acronyms), 1)
self.assertTrue('DEF' in acronyms)
self.assertEqual(len(acronyms['DEF']), 2)
self.assertListEqual(acronyms['DEF'], expansions)
# Make sure that the same expansion doesn't show up multiple times
acronyms = find_expanded_acronyms(
'{0} (DEF) if {1} (DEF) {0} (DEF)'.format(expansions[0],
expansions[1]))
self.assertEqual(len(acronyms), 1)
self.assertTrue('DEF' in acronyms)
self.assertEqual(len(acronyms['DEF']), 2)
self.assertListEqual(acronyms['DEF'], expansions)
#TODO: Consider keeping a count of expansions.
# Make sure that things like '..., Inc.' work ok
acronyms = find_expanded_acronyms(
'I think he works at My Favorite Company, Inc. (MFCI), or at least he used to.'
)
self.assertEqual(len(acronyms), 1)
self.assertTrue('MFCI' in acronyms)
self.assertEqual('My Favorite Company, Inc', acronyms['MFCI'][0])
def test_expanded_acronyms_sentence_leading_caps(self):
acronyms = find_expanded_acronyms(
'The New Old Cat Factory (NOCF) is big.')
self.assertEqual(len(acronyms), 1)
self.assertTrue('NOCF' in acronyms)
self.assertEqual(acronyms['NOCF'], ['New Old Cat Factory'])
acronyms = find_expanded_acronyms(
'Come visit The New Old Dog Factory (TNODF)')
self.assertEqual(len(acronyms), 1)
self.assertTrue('TNODF' in acronyms)
self.assertEqual(acronyms['TNODF'], ['The New Old Dog Factory'])
def test_acronyms_with_embedded_acronyms(self):
text = 'The ALPha Beta Company (ALPBC) is a company. Yes, ALPBC is for realz. ' + \
'More in Appendix Q.6 ALPha Beta Company (ALPBC).'
acronyms = find_expanded_acronyms(text)
self.assertEqual(len(acronyms), 1)
self.assertTrue('ALPBC' in acronyms)
self.assertEqual(len(acronyms['ALPBC']), 1)
self.assertEqual(acronyms['ALPBC'], ['ALPha Beta Company'])
text = 'The ALPha BeTa ComPany (ALPBC) is a company. Yes, ALPBC is for realz. ' + \
'More in Appendix Q.6 ALPha BeTa ComPany (ALPBC).'
acronyms = find_expanded_acronyms(text)
self.assertEqual(len(acronyms), 1)
self.assertTrue('ALPBC' in acronyms)
self.assertEqual(len(acronyms['ALPBC']), 1)
self.assertEqual(acronyms['ALPBC'], ['ALPha BeTa ComPany'])
def test_defined_but_not_used_acronyms(self):
acronyms = find_expanded_acronyms(
"The Alpha Beta Company (ABC) project was Really Really Good (RRG)"
)
defined_acronyms = find_acronyms("ABC RRG LOL")
self.assertEqual(len(acronyms), 2)
self.assertEqual(len(defined_acronyms), 3)
unused_acronyms = find_unused_acronyms(acronyms, defined_acronyms)
self.assertEqual(len(unused_acronyms), 1)
self.assertTrue('LOL' in unused_acronyms)
def test_pluralized_acronyms(self):
acronyms = find_acronyms('There are four CDFs due today')
self.assertEqual(len(acronyms), 1)
self.assertTrue('CDF' in acronyms)
self.assertEqual(acronyms['CDF'], [''])
acronyms = find_expanded_acronyms(
'The Corporate Data Files (CDFs) are missing.')
self.assertEqual(len(acronyms), 1)
self.assertTrue('CDF' in acronyms)
self.assertEqual(acronyms['CDF'], ['Corporate Data Files'])
def test_should_not_span_expansions_across_any_line_breaks(self):
acronyms = find_expanded_acronyms(
'Section 1.3.2 Alpha Beta Company\nThe Alpha Beta Company (ABC)')
self.assertEqual(len(acronyms), 1)
self.assertTrue('ABC' in acronyms)
self.assertEqual(acronyms['ABC'], ['Alpha Beta Company'])
acronyms = find_expanded_acronyms(
'Section 1.3.2 Alpha Beta Company\rThe Alpha Beta Company (ABC)')
self.assertEqual(len(acronyms), 1)
self.assertTrue('ABC' in acronyms)
self.assertEqual(acronyms['ABC'], ['Alpha Beta Company'])
# This one isn't strictly across line breaks, but the most common place for a dash to mess
# something up would be in a heading/line break/new paragraph starting with that acronym
# situation, including a dash or other tricksy punctuation.
acronyms = find_expanded_acronyms(
'1. New Good-Fair Company\rThe New Good-Fair Company (NGFC) always...'
)
self.assertEqual(len(acronyms), 1)
self.assertTrue('NGFC' in acronyms)
self.assertEqual(acronyms['NGFC'], ['New Good-Fair Company'])
def test_catch_divided_expansions(self):
correct_expansion = 'The Leading Article and Preposition Company, Inc'
acronym = 'TLAPCI'
divided_expansion = 'Preposition Company, Inc'
text = "When I worked for {0} ({1})".format(correct_expansion, acronym) + \
", we made sure that prepositions were never something we ended sentences with."
match = re.search(expanded_regex, text)
revised_expansion = fix_divided_expansion(divided_expansion, acronym,
match)
self.assertEqual(correct_expansion, revised_expansion)
acronyms = find_expanded_acronyms(text)
self.assertEqual(len(acronyms), 1)
self.assertTrue(acronym in acronyms)
self.assertEqual(correct_expansion, acronyms[acronym][0])
def test_sentence_leading_caps_strip(self):
extraneous_expansion = 'The Noodle Flopper'
expansion = 'Noodle Flopper'
acronym = 'NF'
self.assertEqual(strip_extraneous_words(extraneous_expansion, acronym),
expansion)
not_extraneous = 'The Leading Article Company'
acronym = 'TLAC'
self.assertEqual(strip_extraneous_words(not_extraneous, acronym),
not_extraneous)
text = 'Thus The Leading Article Company (TLAC) realized its need for following verbs.'
self.assertEqual(
strip_extraneous_words('Thus The Leading Article Company',
acronym), not_extraneous)
acronyms = find_expanded_acronyms(text)
self.assertEqual(len(acronyms), 1)
self.assertTrue('TLAC' in acronyms)
self.assertEqual(acronyms['TLAC'], [not_extraneous])
