|
@@ 5187-5201 (lines=15) @@
|
| 5184 |
|
# etc. (for code coverage) |
| 5185 |
|
self.assertEqual(bmpm('van Damme', name_mode='sep'), 'dami mi dam m') |
| 5186 |
|
|
| 5187 |
|
def test_bmpm_nachnamen(self): |
| 5188 |
|
"""Test abydos.phonetic.bmpm (Nachnamen set).""" |
| 5189 |
|
if not ALLOW_RANDOM: |
| 5190 |
|
return |
| 5191 |
|
with codecs.open(TESTDIR + '/corpora/nachnamen.bm.csv', |
| 5192 |
|
encoding='utf-8') as nachnamen_testset: |
| 5193 |
|
next(nachnamen_testset) |
| 5194 |
|
for nn_line in nachnamen_testset: |
| 5195 |
|
nn_line = nn_line.strip().split(',') |
| 5196 |
|
# This test set is very large (~10000 entries) |
| 5197 |
|
# so let's just randomly select about 20 for testing |
| 5198 |
|
if nn_line[0] != '#' and one_in(500): |
| 5199 |
|
self.assertEqual(bmpm(nn_line[0], language_arg='german'), |
| 5200 |
|
nn_line[1]) |
| 5201 |
|
self.assertEqual(bmpm(nn_line[0]), nn_line[2]) |
| 5202 |
|
|
| 5203 |
|
def test_bmpm_nachnamen_cc(self): |
| 5204 |
|
"""Test abydos.phonetic.bmpm (Nachnamen set, corner cases).""" |
|
@@ 5203-5215 (lines=13) @@
|
| 5200 |
|
nn_line[1]) |
| 5201 |
|
self.assertEqual(bmpm(nn_line[0]), nn_line[2]) |
| 5202 |
|
|
| 5203 |
|
def test_bmpm_nachnamen_cc(self): |
| 5204 |
|
"""Test abydos.phonetic.bmpm (Nachnamen set, corner cases).""" |
| 5205 |
|
with codecs.open(TESTDIR + '/corpora/nachnamen.bm.cc.csv', |
| 5206 |
|
encoding='utf-8') as nachnamen_testset: |
| 5207 |
|
next(nachnamen_testset) |
| 5208 |
|
for nn_line in nachnamen_testset: |
| 5209 |
|
nn_line = nn_line.strip().split(',') |
| 5210 |
|
# This test set is very large (~10000 entries) |
| 5211 |
|
# so let's just randomly select about 20 for testing |
| 5212 |
|
if nn_line[0] != '#': |
| 5213 |
|
self.assertEqual(bmpm(nn_line[0], language_arg='german'), |
| 5214 |
|
nn_line[1]) |
| 5215 |
|
self.assertEqual(bmpm(nn_line[0]), nn_line[2]) |
| 5216 |
|
|
| 5217 |
|
def test_bmpm_uscensus2000(self): |
| 5218 |
|
"""Test abydos.phonetic.bmpm (US Census 2000 set).""" |
chrislit /
abydos
