|
@@ 5003-5017 (lines=15) @@
|
| 5000 |
|
# etc. (for code coverage) |
| 5001 |
|
self.assertEqual(bmpm('van Damme', name_mode='sep'), 'dami mi dam m') |
| 5002 |
|
|
| 5003 |
|
def test_bmpm_nachnamen(self): |
| 5004 |
|
"""Test abydos.phonetic.bmpm (Nachnamen set).""" |
| 5005 |
|
if not ALLOW_RANDOM: |
| 5006 |
|
return |
| 5007 |
|
with codecs.open(TESTDIR + '/corpora/nachnamen.bm.csv', |
| 5008 |
|
encoding='utf-8') as nachnamen_testset: |
| 5009 |
|
next(nachnamen_testset) |
| 5010 |
|
for nn_line in nachnamen_testset: |
| 5011 |
|
nn_line = nn_line.strip().split(',') |
| 5012 |
|
# This test set is very large (~10000 entries) |
| 5013 |
|
# so let's just randomly select about 20 for testing |
| 5014 |
|
if nn_line[0] != '#' and one_in(500): |
| 5015 |
|
self.assertEqual(bmpm(nn_line[0], language_arg='german'), |
| 5016 |
|
nn_line[1]) |
| 5017 |
|
self.assertEqual(bmpm(nn_line[0]), nn_line[2]) |
| 5018 |
|
|
| 5019 |
|
def test_bmpm_nachnamen_cc(self): |
| 5020 |
|
"""Test abydos.phonetic.bmpm (Nachnamen set, corner cases).""" |
|
@@ 5019-5031 (lines=13) @@
|
| 5016 |
|
nn_line[1]) |
| 5017 |
|
self.assertEqual(bmpm(nn_line[0]), nn_line[2]) |
| 5018 |
|
|
| 5019 |
|
def test_bmpm_nachnamen_cc(self): |
| 5020 |
|
"""Test abydos.phonetic.bmpm (Nachnamen set, corner cases).""" |
| 5021 |
|
with codecs.open(TESTDIR + '/corpora/nachnamen.bm.cc.csv', |
| 5022 |
|
encoding='utf-8') as nachnamen_testset: |
| 5023 |
|
next(nachnamen_testset) |
| 5024 |
|
for nn_line in nachnamen_testset: |
| 5025 |
|
nn_line = nn_line.strip().split(',') |
| 5026 |
|
# This test set is very large (~10000 entries) |
| 5027 |
|
# so let's just randomly select about 20 for testing |
| 5028 |
|
if nn_line[0] != '#': |
| 5029 |
|
self.assertEqual(bmpm(nn_line[0], language_arg='german'), |
| 5030 |
|
nn_line[1]) |
| 5031 |
|
self.assertEqual(bmpm(nn_line[0]), nn_line[2]) |
| 5032 |
|
|
| 5033 |
|
def test_bmpm_uscensus2000(self): |
| 5034 |
|
"""Test abydos.phonetic.bmpm (US Census 2000 set).""" |
chrislit /
abydos
