|
@@ 6775-6789 (lines=15) @@
|
| 6772 |
|
# etc. (for code coverage) |
| 6773 |
|
self.assertEqual(bmpm('van Damme', name_mode='sep'), 'dami mi dam m') |
| 6774 |
|
|
| 6775 |
|
def test_bmpm_nachnamen(self): |
| 6776 |
|
"""Test abydos.phonetic.bmpm (Nachnamen set).""" |
| 6777 |
|
if not ALLOW_RANDOM: |
| 6778 |
|
return |
| 6779 |
|
with codecs.open(TESTDIR + '/corpora/nachnamen.bm.csv', |
| 6780 |
|
encoding='utf-8') as nachnamen_testset: |
| 6781 |
|
next(nachnamen_testset) |
| 6782 |
|
for nn_line in nachnamen_testset: |
| 6783 |
|
nn_line = nn_line.strip().split(',') |
| 6784 |
|
# This test set is very large (~10000 entries) |
| 6785 |
|
# so let's just randomly select about 20 for testing |
| 6786 |
|
if nn_line[0] != '#' and one_in(500): |
| 6787 |
|
self.assertEqual(bmpm(nn_line[0], language_arg='german'), |
| 6788 |
|
nn_line[1]) |
| 6789 |
|
self.assertEqual(bmpm(nn_line[0]), nn_line[2]) |
| 6790 |
|
|
| 6791 |
|
def test_bmpm_nachnamen_cc(self): |
| 6792 |
|
"""Test abydos.phonetic.bmpm (Nachnamen set, corner cases).""" |
|
@@ 6791-6803 (lines=13) @@
|
| 6788 |
|
nn_line[1]) |
| 6789 |
|
self.assertEqual(bmpm(nn_line[0]), nn_line[2]) |
| 6790 |
|
|
| 6791 |
|
def test_bmpm_nachnamen_cc(self): |
| 6792 |
|
"""Test abydos.phonetic.bmpm (Nachnamen set, corner cases).""" |
| 6793 |
|
with codecs.open(TESTDIR + '/corpora/nachnamen.bm.cc.csv', |
| 6794 |
|
encoding='utf-8') as nachnamen_testset: |
| 6795 |
|
next(nachnamen_testset) |
| 6796 |
|
for nn_line in nachnamen_testset: |
| 6797 |
|
nn_line = nn_line.strip().split(',') |
| 6798 |
|
# This test set is very large (~10000 entries) |
| 6799 |
|
# so let's just randomly select about 20 for testing |
| 6800 |
|
if nn_line[0] != '#': |
| 6801 |
|
self.assertEqual(bmpm(nn_line[0], language_arg='german'), |
| 6802 |
|
nn_line[1]) |
| 6803 |
|
self.assertEqual(bmpm(nn_line[0]), nn_line[2]) |
| 6804 |
|
|
| 6805 |
|
def test_bmpm_uscensus2000(self): |
| 6806 |
|
"""Test abydos.phonetic.bmpm (US Census 2000 set).""" |
chrislit /
abydos
