|
@@ 6018-6032 (lines=15) @@
|
| 6015 |
|
# etc. (for code coverage) |
| 6016 |
|
self.assertEqual(bmpm('van Damme', name_mode='sep'), 'dami mi dam m') |
| 6017 |
|
|
| 6018 |
|
def test_bmpm_nachnamen(self): |
| 6019 |
|
"""Test abydos.phonetic.bmpm (Nachnamen set).""" |
| 6020 |
|
if not ALLOW_RANDOM: |
| 6021 |
|
return |
| 6022 |
|
with codecs.open(TESTDIR + '/corpora/nachnamen.bm.csv', |
| 6023 |
|
encoding='utf-8') as nachnamen_testset: |
| 6024 |
|
next(nachnamen_testset) |
| 6025 |
|
for nn_line in nachnamen_testset: |
| 6026 |
|
nn_line = nn_line.strip().split(',') |
| 6027 |
|
# This test set is very large (~10000 entries) |
| 6028 |
|
# so let's just randomly select about 20 for testing |
| 6029 |
|
if nn_line[0] != '#' and one_in(500): |
| 6030 |
|
self.assertEqual(bmpm(nn_line[0], language_arg='german'), |
| 6031 |
|
nn_line[1]) |
| 6032 |
|
self.assertEqual(bmpm(nn_line[0]), nn_line[2]) |
| 6033 |
|
|
| 6034 |
|
def test_bmpm_nachnamen_cc(self): |
| 6035 |
|
"""Test abydos.phonetic.bmpm (Nachnamen set, corner cases).""" |
|
@@ 6034-6046 (lines=13) @@
|
| 6031 |
|
nn_line[1]) |
| 6032 |
|
self.assertEqual(bmpm(nn_line[0]), nn_line[2]) |
| 6033 |
|
|
| 6034 |
|
def test_bmpm_nachnamen_cc(self): |
| 6035 |
|
"""Test abydos.phonetic.bmpm (Nachnamen set, corner cases).""" |
| 6036 |
|
with codecs.open(TESTDIR + '/corpora/nachnamen.bm.cc.csv', |
| 6037 |
|
encoding='utf-8') as nachnamen_testset: |
| 6038 |
|
next(nachnamen_testset) |
| 6039 |
|
for nn_line in nachnamen_testset: |
| 6040 |
|
nn_line = nn_line.strip().split(',') |
| 6041 |
|
# This test set is very large (~10000 entries) |
| 6042 |
|
# so let's just randomly select about 20 for testing |
| 6043 |
|
if nn_line[0] != '#': |
| 6044 |
|
self.assertEqual(bmpm(nn_line[0], language_arg='german'), |
| 6045 |
|
nn_line[1]) |
| 6046 |
|
self.assertEqual(bmpm(nn_line[0]), nn_line[2]) |
| 6047 |
|
|
| 6048 |
|
def test_bmpm_uscensus2000(self): |
| 6049 |
|
"""Test abydos.phonetic.bmpm (US Census 2000 set).""" |
chrislit /
abydos
