|
@@ 4852-4866 (lines=15) @@
|
| 4849 |
|
# etc. (for code coverage) |
| 4850 |
|
self.assertEqual(bmpm('van Damme', name_mode='sep'), 'dami mi dam m') |
| 4851 |
|
|
| 4852 |
|
def test_bmpm_nachnamen(self): |
| 4853 |
|
"""Test abydos.phonetic.bmpm (Nachnamen set).""" |
| 4854 |
|
if not ALLOW_RANDOM: |
| 4855 |
|
return |
| 4856 |
|
with codecs.open(TESTDIR + '/corpora/nachnamen.bm.csv', |
| 4857 |
|
encoding='utf-8') as nachnamen_testset: |
| 4858 |
|
next(nachnamen_testset) |
| 4859 |
|
for nn_line in nachnamen_testset: |
| 4860 |
|
nn_line = nn_line.strip().split(',') |
| 4861 |
|
# This test set is very large (~10000 entries) |
| 4862 |
|
# so let's just randomly select about 20 for testing |
| 4863 |
|
if nn_line[0] != '#' and one_in(500): |
| 4864 |
|
self.assertEqual(bmpm(nn_line[0], language_arg='german'), |
| 4865 |
|
nn_line[1]) |
| 4866 |
|
self.assertEqual(bmpm(nn_line[0]), nn_line[2]) |
| 4867 |
|
|
| 4868 |
|
def test_bmpm_nachnamen_cc(self): |
| 4869 |
|
"""Test abydos.phonetic.bmpm (Nachnamen set, corner cases).""" |
|
@@ 4868-4880 (lines=13) @@
|
| 4865 |
|
nn_line[1]) |
| 4866 |
|
self.assertEqual(bmpm(nn_line[0]), nn_line[2]) |
| 4867 |
|
|
| 4868 |
|
def test_bmpm_nachnamen_cc(self): |
| 4869 |
|
"""Test abydos.phonetic.bmpm (Nachnamen set, corner cases).""" |
| 4870 |
|
with codecs.open(TESTDIR + '/corpora/nachnamen.bm.cc.csv', |
| 4871 |
|
encoding='utf-8') as nachnamen_testset: |
| 4872 |
|
next(nachnamen_testset) |
| 4873 |
|
for nn_line in nachnamen_testset: |
| 4874 |
|
nn_line = nn_line.strip().split(',') |
| 4875 |
|
# This test set is very large (~10000 entries) |
| 4876 |
|
# so let's just randomly select about 20 for testing |
| 4877 |
|
if nn_line[0] != '#': |
| 4878 |
|
self.assertEqual(bmpm(nn_line[0], language_arg='german'), |
| 4879 |
|
nn_line[1]) |
| 4880 |
|
self.assertEqual(bmpm(nn_line[0]), nn_line[2]) |
| 4881 |
|
|
| 4882 |
|
def test_bmpm_uscensus2000(self): |
| 4883 |
|
"""Test abydos.phonetic.bmpm (US Census 2000 set).""" |
chrislit /
abydos
