|
@@ 6074-6096 (lines=23) @@
|
| 6071 |
|
nn_line[1]) |
| 6072 |
|
self.assertEqual(bmpm(nn_line[0]), nn_line[2]) |
| 6073 |
|
|
| 6074 |
|
def test_bmpm_uscensus2000(self): |
| 6075 |
|
"""Test abydos.phonetic.bmpm (US Census 2000 set).""" |
| 6076 |
|
if not ALLOW_RANDOM: |
| 6077 |
|
return |
| 6078 |
|
with open(TESTDIR + '/corpora/uscensus2000.bm.csv') as uscensus_ts: |
| 6079 |
|
next(uscensus_ts) |
| 6080 |
|
for cen_line in uscensus_ts: |
| 6081 |
|
cen_line = cen_line.strip().split(',') |
| 6082 |
|
# This test set is very large (~150000 entries) |
| 6083 |
|
# so let's just randomly select about 20 for testing |
| 6084 |
|
if cen_line[0] != '#' and one_in(7500): |
| 6085 |
|
self.assertEqual(bmpm(cen_line[0], match_mode='approx', |
| 6086 |
|
name_mode='gen'), cen_line[1]) |
| 6087 |
|
self.assertEqual(bmpm(cen_line[0], match_mode='approx', |
| 6088 |
|
name_mode='ash'), cen_line[2]) |
| 6089 |
|
self.assertEqual(bmpm(cen_line[0], match_mode='approx', |
| 6090 |
|
name_mode='sep'), cen_line[3]) |
| 6091 |
|
self.assertEqual(bmpm(cen_line[0], match_mode='exact', |
| 6092 |
|
name_mode='gen'), cen_line[4]) |
| 6093 |
|
self.assertEqual(bmpm(cen_line[0], match_mode='exact', |
| 6094 |
|
name_mode='ash'), cen_line[5]) |
| 6095 |
|
self.assertEqual(bmpm(cen_line[0], match_mode='exact', |
| 6096 |
|
name_mode='sep'), cen_line[6]) |
| 6097 |
|
|
| 6098 |
|
def test_bmpm_uscensus2000_cc(self): |
| 6099 |
|
"""Test abydos.phonetic.bmpm (US Census 2000 set, corner cases).""" |
|
@@ 6098-6118 (lines=21) @@
|
| 6095 |
|
self.assertEqual(bmpm(cen_line[0], match_mode='exact', |
| 6096 |
|
name_mode='sep'), cen_line[6]) |
| 6097 |
|
|
| 6098 |
|
def test_bmpm_uscensus2000_cc(self): |
| 6099 |
|
"""Test abydos.phonetic.bmpm (US Census 2000 set, corner cases).""" |
| 6100 |
|
with open(TESTDIR + '/corpora/uscensus2000.bm.cc.csv') as uscensus_ts: |
| 6101 |
|
next(uscensus_ts) |
| 6102 |
|
for cen_line in uscensus_ts: |
| 6103 |
|
cen_line = cen_line.strip().split(',') |
| 6104 |
|
# This test set is very large (~150000 entries) |
| 6105 |
|
# so let's just randomly select about 20 for testing |
| 6106 |
|
if cen_line[0] != '#' and one_in(10): |
| 6107 |
|
self.assertEqual(bmpm(cen_line[0], match_mode='approx', |
| 6108 |
|
name_mode='gen'), cen_line[1]) |
| 6109 |
|
self.assertEqual(bmpm(cen_line[0], match_mode='approx', |
| 6110 |
|
name_mode='ash'), cen_line[2]) |
| 6111 |
|
self.assertEqual(bmpm(cen_line[0], match_mode='approx', |
| 6112 |
|
name_mode='sep'), cen_line[3]) |
| 6113 |
|
self.assertEqual(bmpm(cen_line[0], match_mode='exact', |
| 6114 |
|
name_mode='gen'), cen_line[4]) |
| 6115 |
|
self.assertEqual(bmpm(cen_line[0], match_mode='exact', |
| 6116 |
|
name_mode='ash'), cen_line[5]) |
| 6117 |
|
self.assertEqual(bmpm(cen_line[0], match_mode='exact', |
| 6118 |
|
name_mode='sep'), cen_line[6]) |
| 6119 |
|
|
| 6120 |
|
def test_bm_phonetic_number(self): |
| 6121 |
|
"""Test abydos.bm._bm_phonetic_number.""" |
chrislit /
abydos
