|
@@ 6079-6093 (lines=15) @@
|
| 6076 |
|
# etc. (for code coverage) |
| 6077 |
|
self.assertEqual(bmpm('van Damme', name_mode='sep'), 'dami mi dam m') |
| 6078 |
|
|
| 6079 |
|
def test_bmpm_nachnamen(self): |
| 6080 |
|
"""Test abydos.phonetic.bmpm (Nachnamen set).""" |
| 6081 |
|
if not ALLOW_RANDOM: |
| 6082 |
|
return |
| 6083 |
|
with codecs.open(TESTDIR + '/corpora/nachnamen.bm.csv', |
| 6084 |
|
encoding='utf-8') as nachnamen_testset: |
| 6085 |
|
next(nachnamen_testset) |
| 6086 |
|
for nn_line in nachnamen_testset: |
| 6087 |
|
nn_line = nn_line.strip().split(',') |
| 6088 |
|
# This test set is very large (~10000 entries) |
| 6089 |
|
# so let's just randomly select about 20 for testing |
| 6090 |
|
if nn_line[0] != '#' and one_in(500): |
| 6091 |
|
self.assertEqual(bmpm(nn_line[0], language_arg='german'), |
| 6092 |
|
nn_line[1]) |
| 6093 |
|
self.assertEqual(bmpm(nn_line[0]), nn_line[2]) |
| 6094 |
|
|
| 6095 |
|
def test_bmpm_nachnamen_cc(self): |
| 6096 |
|
"""Test abydos.phonetic.bmpm (Nachnamen set, corner cases).""" |
|
@@ 6095-6107 (lines=13) @@
|
| 6092 |
|
nn_line[1]) |
| 6093 |
|
self.assertEqual(bmpm(nn_line[0]), nn_line[2]) |
| 6094 |
|
|
| 6095 |
|
def test_bmpm_nachnamen_cc(self): |
| 6096 |
|
"""Test abydos.phonetic.bmpm (Nachnamen set, corner cases).""" |
| 6097 |
|
with codecs.open(TESTDIR + '/corpora/nachnamen.bm.cc.csv', |
| 6098 |
|
encoding='utf-8') as nachnamen_testset: |
| 6099 |
|
next(nachnamen_testset) |
| 6100 |
|
for nn_line in nachnamen_testset: |
| 6101 |
|
nn_line = nn_line.strip().split(',') |
| 6102 |
|
# This test set is very large (~10000 entries) |
| 6103 |
|
# so let's just randomly select about 20 for testing |
| 6104 |
|
if nn_line[0] != '#': |
| 6105 |
|
self.assertEqual(bmpm(nn_line[0], language_arg='german'), |
| 6106 |
|
nn_line[1]) |
| 6107 |
|
self.assertEqual(bmpm(nn_line[0]), nn_line[2]) |
| 6108 |
|
|
| 6109 |
|
def test_bmpm_uscensus2000(self): |
| 6110 |
|
"""Test abydos.phonetic.bmpm (US Census 2000 set).""" |
chrislit /
abydos
