|
@@ 5073-5087 (lines=15) @@
|
| 5070 |
|
# etc. (for code coverage) |
| 5071 |
|
self.assertEqual(bmpm('van Damme', name_mode='sep'), 'dami mi dam m') |
| 5072 |
|
|
| 5073 |
|
def test_bmpm_nachnamen(self): |
| 5074 |
|
"""Test abydos.phonetic.bmpm (Nachnamen set).""" |
| 5075 |
|
if not ALLOW_RANDOM: |
| 5076 |
|
return |
| 5077 |
|
with codecs.open(TESTDIR + '/corpora/nachnamen.bm.csv', |
| 5078 |
|
encoding='utf-8') as nachnamen_testset: |
| 5079 |
|
next(nachnamen_testset) |
| 5080 |
|
for nn_line in nachnamen_testset: |
| 5081 |
|
nn_line = nn_line.strip().split(',') |
| 5082 |
|
# This test set is very large (~10000 entries) |
| 5083 |
|
# so let's just randomly select about 20 for testing |
| 5084 |
|
if nn_line[0] != '#' and one_in(500): |
| 5085 |
|
self.assertEqual(bmpm(nn_line[0], language_arg='german'), |
| 5086 |
|
nn_line[1]) |
| 5087 |
|
self.assertEqual(bmpm(nn_line[0]), nn_line[2]) |
| 5088 |
|
|
| 5089 |
|
def test_bmpm_nachnamen_cc(self): |
| 5090 |
|
"""Test abydos.phonetic.bmpm (Nachnamen set, corner cases).""" |
|
@@ 5089-5101 (lines=13) @@
|
| 5086 |
|
nn_line[1]) |
| 5087 |
|
self.assertEqual(bmpm(nn_line[0]), nn_line[2]) |
| 5088 |
|
|
| 5089 |
|
def test_bmpm_nachnamen_cc(self): |
| 5090 |
|
"""Test abydos.phonetic.bmpm (Nachnamen set, corner cases).""" |
| 5091 |
|
with codecs.open(TESTDIR + '/corpora/nachnamen.bm.cc.csv', |
| 5092 |
|
encoding='utf-8') as nachnamen_testset: |
| 5093 |
|
next(nachnamen_testset) |
| 5094 |
|
for nn_line in nachnamen_testset: |
| 5095 |
|
nn_line = nn_line.strip().split(',') |
| 5096 |
|
# This test set is very large (~10000 entries) |
| 5097 |
|
# so let's just randomly select about 20 for testing |
| 5098 |
|
if nn_line[0] != '#': |
| 5099 |
|
self.assertEqual(bmpm(nn_line[0], language_arg='german'), |
| 5100 |
|
nn_line[1]) |
| 5101 |
|
self.assertEqual(bmpm(nn_line[0]), nn_line[2]) |
| 5102 |
|
|
| 5103 |
|
def test_bmpm_uscensus2000(self): |
| 5104 |
|
"""Test abydos.phonetic.bmpm (US Census 2000 set).""" |
chrislit /
abydos
