def test_that_roman_numbers_work(self):
pnums = mp.extract_page_numbers_from_par({
1: ["|| - Seite I -"],
7: ["|| - Seite XVI -"],
20: ["|| - Seite CCC -"],
})
self.assertEqual(len(pnums), 3)
def test_that_more_than_one_pnum_is_parsed_and_line_numbers_are_correct(self):
pars = collections.OrderedDict()
pars[1] = ['|| - Seite 80 -']
pars[3] = ['|| Some text', 'hopefully ignored']
pars[5] = ['|| - Seite 81 -']
pnums = mp.extract_page_numbers_from_par(pars)
self.assertEqual(len(pnums), 2)
lnums = [pnum.line_no for pnum in pnums]
self.assertTrue(1 in lnums and 5 in lnums)
def test_invalid_roman_numbers_trigger_exception(self):
pnums = mp.extract_page_numbers_from_par({1:['|| - Seite IIIIIVC -']})
self.assertEqual(len(pnums), 0)
def test_that_varying_spaces_are_not_an_issue(self):
pnums = mp.extract_page_numbers_from_par({1:['|| -Seite 80 -'],
7:['|| - Seite 80-']})
self.assertEqual(len(pnums), 2)
def test_that_lower_case_page_identifiers_are_recognized(self):
pnums = mp.extract_page_numbers_from_par({999:['|| - seite 80 -']})
self.assertEqual(len(pnums), 1)
def test_that_invalid_page_numbers_are_ignored(self):
pnums = mp.extract_page_numbers_from_par({1:['|| - Seite abc -']})
self.assertEqual(len(pnums), 0)
def test_that_incorrect_pnum_is_not_recognized(self):
pars = {1:['|| - alles fehlerhaft hier -']}
self.assertEqual(len(mp.extract_page_numbers_from_par(pars)), 0)
def test_that_correct_pnum_is_recognized(self):
pnums = mp.extract_page_numbers_from_par({1:['|| - Seite 80 -']})
self.assertEqual(len(pnums), 1, "exactly one page number is expected.")
self.assertEqual(pnums[0].number, 80)