|
@@ 4820-4834 (lines=15) @@
|
| 4817 |
|
# etc. (for code coverage) |
| 4818 |
|
self.assertEqual(bmpm('van Damme', name_mode='sep'), 'dami mi dam m') |
| 4819 |
|
|
| 4820 |
|
def test_bmpm_nachnamen(self): |
| 4821 |
|
"""Test abydos.phonetic.bmpm (Nachnamen set).""" |
| 4822 |
|
if not ALLOW_RANDOM: |
| 4823 |
|
return |
| 4824 |
|
with codecs.open(TESTDIR + '/corpora/nachnamen.bm.csv', |
| 4825 |
|
encoding='utf-8') as nachnamen_testset: |
| 4826 |
|
next(nachnamen_testset) |
| 4827 |
|
for nn_line in nachnamen_testset: |
| 4828 |
|
nn_line = nn_line.strip().split(',') |
| 4829 |
|
# This test set is very large (~10000 entries) |
| 4830 |
|
# so let's just randomly select about 20 for testing |
| 4831 |
|
if nn_line[0] != '#' and one_in(500): |
| 4832 |
|
self.assertEqual(bmpm(nn_line[0], language_arg='german'), |
| 4833 |
|
nn_line[1]) |
| 4834 |
|
self.assertEqual(bmpm(nn_line[0]), nn_line[2]) |
| 4835 |
|
|
| 4836 |
|
def test_bmpm_nachnamen_cc(self): |
| 4837 |
|
"""Test abydos.phonetic.bmpm (Nachnamen set, corner cases).""" |
|
@@ 4836-4848 (lines=13) @@
|
| 4833 |
|
nn_line[1]) |
| 4834 |
|
self.assertEqual(bmpm(nn_line[0]), nn_line[2]) |
| 4835 |
|
|
| 4836 |
|
def test_bmpm_nachnamen_cc(self): |
| 4837 |
|
"""Test abydos.phonetic.bmpm (Nachnamen set, corner cases).""" |
| 4838 |
|
with codecs.open(TESTDIR + '/corpora/nachnamen.bm.cc.csv', |
| 4839 |
|
encoding='utf-8') as nachnamen_testset: |
| 4840 |
|
next(nachnamen_testset) |
| 4841 |
|
for nn_line in nachnamen_testset: |
| 4842 |
|
nn_line = nn_line.strip().split(',') |
| 4843 |
|
# This test set is very large (~10000 entries) |
| 4844 |
|
# so let's just randomly select about 20 for testing |
| 4845 |
|
if nn_line[0] != '#': |
| 4846 |
|
self.assertEqual(bmpm(nn_line[0], language_arg='german'), |
| 4847 |
|
nn_line[1]) |
| 4848 |
|
self.assertEqual(bmpm(nn_line[0]), nn_line[2]) |
| 4849 |
|
|
| 4850 |
|
def test_bmpm_uscensus2000(self): |
| 4851 |
|
"""Test abydos.phonetic.bmpm (US Census 2000 set).""" |
chrislit /
abydos
