|
@@ 6351-6365 (lines=15) @@
|
| 6348 |
|
# etc. (for code coverage) |
| 6349 |
|
self.assertEqual(bmpm('van Damme', name_mode='sep'), 'dami mi dam m') |
| 6350 |
|
|
| 6351 |
|
def test_bmpm_nachnamen(self): |
| 6352 |
|
"""Test abydos.phonetic.bmpm (Nachnamen set).""" |
| 6353 |
|
if not ALLOW_RANDOM: |
| 6354 |
|
return |
| 6355 |
|
with codecs.open(TESTDIR + '/corpora/nachnamen.bm.csv', |
| 6356 |
|
encoding='utf-8') as nachnamen_testset: |
| 6357 |
|
next(nachnamen_testset) |
| 6358 |
|
for nn_line in nachnamen_testset: |
| 6359 |
|
nn_line = nn_line.strip().split(',') |
| 6360 |
|
# This test set is very large (~10000 entries) |
| 6361 |
|
# so let's just randomly select about 20 for testing |
| 6362 |
|
if nn_line[0] != '#' and one_in(500): |
| 6363 |
|
self.assertEqual(bmpm(nn_line[0], language_arg='german'), |
| 6364 |
|
nn_line[1]) |
| 6365 |
|
self.assertEqual(bmpm(nn_line[0]), nn_line[2]) |
| 6366 |
|
|
| 6367 |
|
def test_bmpm_nachnamen_cc(self): |
| 6368 |
|
"""Test abydos.phonetic.bmpm (Nachnamen set, corner cases).""" |
|
@@ 6367-6379 (lines=13) @@
|
| 6364 |
|
nn_line[1]) |
| 6365 |
|
self.assertEqual(bmpm(nn_line[0]), nn_line[2]) |
| 6366 |
|
|
| 6367 |
|
def test_bmpm_nachnamen_cc(self): |
| 6368 |
|
"""Test abydos.phonetic.bmpm (Nachnamen set, corner cases).""" |
| 6369 |
|
with codecs.open(TESTDIR + '/corpora/nachnamen.bm.cc.csv', |
| 6370 |
|
encoding='utf-8') as nachnamen_testset: |
| 6371 |
|
next(nachnamen_testset) |
| 6372 |
|
for nn_line in nachnamen_testset: |
| 6373 |
|
nn_line = nn_line.strip().split(',') |
| 6374 |
|
# This test set is very large (~10000 entries) |
| 6375 |
|
# so let's just randomly select about 20 for testing |
| 6376 |
|
if nn_line[0] != '#': |
| 6377 |
|
self.assertEqual(bmpm(nn_line[0], language_arg='german'), |
| 6378 |
|
nn_line[1]) |
| 6379 |
|
self.assertEqual(bmpm(nn_line[0]), nn_line[2]) |
| 6380 |
|
|
| 6381 |
|
def test_bmpm_uscensus2000(self): |
| 6382 |
|
"""Test abydos.phonetic.bmpm (US Census 2000 set).""" |
chrislit /
abydos
