|
@@ 5885-5899 (lines=15) @@
|
| 5882 |
|
# etc. (for code coverage) |
| 5883 |
|
self.assertEqual(bmpm('van Damme', name_mode='sep'), 'dami mi dam m') |
| 5884 |
|
|
| 5885 |
|
def test_bmpm_nachnamen(self): |
| 5886 |
|
"""Test abydos.phonetic.bmpm (Nachnamen set).""" |
| 5887 |
|
if not ALLOW_RANDOM: |
| 5888 |
|
return |
| 5889 |
|
with codecs.open(TESTDIR + '/corpora/nachnamen.bm.csv', |
| 5890 |
|
encoding='utf-8') as nachnamen_testset: |
| 5891 |
|
next(nachnamen_testset) |
| 5892 |
|
for nn_line in nachnamen_testset: |
| 5893 |
|
nn_line = nn_line.strip().split(',') |
| 5894 |
|
# This test set is very large (~10000 entries) |
| 5895 |
|
# so let's just randomly select about 20 for testing |
| 5896 |
|
if nn_line[0] != '#' and one_in(500): |
| 5897 |
|
self.assertEqual(bmpm(nn_line[0], language_arg='german'), |
| 5898 |
|
nn_line[1]) |
| 5899 |
|
self.assertEqual(bmpm(nn_line[0]), nn_line[2]) |
| 5900 |
|
|
| 5901 |
|
def test_bmpm_nachnamen_cc(self): |
| 5902 |
|
"""Test abydos.phonetic.bmpm (Nachnamen set, corner cases).""" |
|
@@ 5901-5913 (lines=13) @@
|
| 5898 |
|
nn_line[1]) |
| 5899 |
|
self.assertEqual(bmpm(nn_line[0]), nn_line[2]) |
| 5900 |
|
|
| 5901 |
|
def test_bmpm_nachnamen_cc(self): |
| 5902 |
|
"""Test abydos.phonetic.bmpm (Nachnamen set, corner cases).""" |
| 5903 |
|
with codecs.open(TESTDIR + '/corpora/nachnamen.bm.cc.csv', |
| 5904 |
|
encoding='utf-8') as nachnamen_testset: |
| 5905 |
|
next(nachnamen_testset) |
| 5906 |
|
for nn_line in nachnamen_testset: |
| 5907 |
|
nn_line = nn_line.strip().split(',') |
| 5908 |
|
# This test set is very large (~10000 entries) |
| 5909 |
|
# so let's just randomly select about 20 for testing |
| 5910 |
|
if nn_line[0] != '#': |
| 5911 |
|
self.assertEqual(bmpm(nn_line[0], language_arg='german'), |
| 5912 |
|
nn_line[1]) |
| 5913 |
|
self.assertEqual(bmpm(nn_line[0]), nn_line[2]) |
| 5914 |
|
|
| 5915 |
|
def test_bmpm_uscensus2000(self): |
| 5916 |
|
"""Test abydos.phonetic.bmpm (US Census 2000 set).""" |
chrislit /
abydos
