|
@@ 5865-5879 (lines=15) @@
|
| 5862 |
|
# etc. (for code coverage) |
| 5863 |
|
self.assertEqual(bmpm('van Damme', name_mode='sep'), 'dami mi dam m') |
| 5864 |
|
|
| 5865 |
|
def test_bmpm_nachnamen(self): |
| 5866 |
|
"""Test abydos.phonetic.bmpm (Nachnamen set).""" |
| 5867 |
|
if not ALLOW_RANDOM: |
| 5868 |
|
return |
| 5869 |
|
with codecs.open(TESTDIR + '/corpora/nachnamen.bm.csv', |
| 5870 |
|
encoding='utf-8') as nachnamen_testset: |
| 5871 |
|
next(nachnamen_testset) |
| 5872 |
|
for nn_line in nachnamen_testset: |
| 5873 |
|
nn_line = nn_line.strip().split(',') |
| 5874 |
|
# This test set is very large (~10000 entries) |
| 5875 |
|
# so let's just randomly select about 20 for testing |
| 5876 |
|
if nn_line[0] != '#' and one_in(500): |
| 5877 |
|
self.assertEqual(bmpm(nn_line[0], language_arg='german'), |
| 5878 |
|
nn_line[1]) |
| 5879 |
|
self.assertEqual(bmpm(nn_line[0]), nn_line[2]) |
| 5880 |
|
|
| 5881 |
|
def test_bmpm_nachnamen_cc(self): |
| 5882 |
|
"""Test abydos.phonetic.bmpm (Nachnamen set, corner cases).""" |
|
@@ 5881-5893 (lines=13) @@
|
| 5878 |
|
nn_line[1]) |
| 5879 |
|
self.assertEqual(bmpm(nn_line[0]), nn_line[2]) |
| 5880 |
|
|
| 5881 |
|
def test_bmpm_nachnamen_cc(self): |
| 5882 |
|
"""Test abydos.phonetic.bmpm (Nachnamen set, corner cases).""" |
| 5883 |
|
with codecs.open(TESTDIR + '/corpora/nachnamen.bm.cc.csv', |
| 5884 |
|
encoding='utf-8') as nachnamen_testset: |
| 5885 |
|
next(nachnamen_testset) |
| 5886 |
|
for nn_line in nachnamen_testset: |
| 5887 |
|
nn_line = nn_line.strip().split(',') |
| 5888 |
|
# This test set is very large (~10000 entries) |
| 5889 |
|
# so let's just randomly select about 20 for testing |
| 5890 |
|
if nn_line[0] != '#': |
| 5891 |
|
self.assertEqual(bmpm(nn_line[0], language_arg='german'), |
| 5892 |
|
nn_line[1]) |
| 5893 |
|
self.assertEqual(bmpm(nn_line[0]), nn_line[2]) |
| 5894 |
|
|
| 5895 |
|
def test_bmpm_uscensus2000(self): |
| 5896 |
|
"""Test abydos.phonetic.bmpm (US Census 2000 set).""" |
chrislit /
abydos
