|
@@ 5103-5125 (lines=23) @@
|
| 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).""" |
| 5105 |
|
if not ALLOW_RANDOM: |
| 5106 |
|
return |
| 5107 |
|
with open(TESTDIR + '/corpora/uscensus2000.bm.csv') as uscensus_ts: |
| 5108 |
|
next(uscensus_ts) |
| 5109 |
|
for cen_line in uscensus_ts: |
| 5110 |
|
cen_line = cen_line.strip().split(',') |
| 5111 |
|
# This test set is very large (~150000 entries) |
| 5112 |
|
# so let's just randomly select about 20 for testing |
| 5113 |
|
if cen_line[0] != '#' and one_in(7500): |
| 5114 |
|
self.assertEqual(bmpm(cen_line[0], match_mode='approx', |
| 5115 |
|
name_mode='gen'), cen_line[1]) |
| 5116 |
|
self.assertEqual(bmpm(cen_line[0], match_mode='approx', |
| 5117 |
|
name_mode='ash'), cen_line[2]) |
| 5118 |
|
self.assertEqual(bmpm(cen_line[0], match_mode='approx', |
| 5119 |
|
name_mode='sep'), cen_line[3]) |
| 5120 |
|
self.assertEqual(bmpm(cen_line[0], match_mode='exact', |
| 5121 |
|
name_mode='gen'), cen_line[4]) |
| 5122 |
|
self.assertEqual(bmpm(cen_line[0], match_mode='exact', |
| 5123 |
|
name_mode='ash'), cen_line[5]) |
| 5124 |
|
self.assertEqual(bmpm(cen_line[0], match_mode='exact', |
| 5125 |
|
name_mode='sep'), cen_line[6]) |
| 5126 |
|
|
| 5127 |
|
def test_bmpm_uscensus2000_cc(self): |
| 5128 |
|
"""Test abydos.phonetic.bmpm (US Census 2000 set, corner cases).""" |
|
@@ 5127-5147 (lines=21) @@
|
| 5124 |
|
self.assertEqual(bmpm(cen_line[0], match_mode='exact', |
| 5125 |
|
name_mode='sep'), cen_line[6]) |
| 5126 |
|
|
| 5127 |
|
def test_bmpm_uscensus2000_cc(self): |
| 5128 |
|
"""Test abydos.phonetic.bmpm (US Census 2000 set, corner cases).""" |
| 5129 |
|
with open(TESTDIR + '/corpora/uscensus2000.bm.cc.csv') as uscensus_ts: |
| 5130 |
|
next(uscensus_ts) |
| 5131 |
|
for cen_line in uscensus_ts: |
| 5132 |
|
cen_line = cen_line.strip().split(',') |
| 5133 |
|
# This test set is very large (~150000 entries) |
| 5134 |
|
# so let's just randomly select about 20 for testing |
| 5135 |
|
if cen_line[0] != '#' and one_in(10): |
| 5136 |
|
self.assertEqual(bmpm(cen_line[0], match_mode='approx', |
| 5137 |
|
name_mode='gen'), cen_line[1]) |
| 5138 |
|
self.assertEqual(bmpm(cen_line[0], match_mode='approx', |
| 5139 |
|
name_mode='ash'), cen_line[2]) |
| 5140 |
|
self.assertEqual(bmpm(cen_line[0], match_mode='approx', |
| 5141 |
|
name_mode='sep'), cen_line[3]) |
| 5142 |
|
self.assertEqual(bmpm(cen_line[0], match_mode='exact', |
| 5143 |
|
name_mode='gen'), cen_line[4]) |
| 5144 |
|
self.assertEqual(bmpm(cen_line[0], match_mode='exact', |
| 5145 |
|
name_mode='ash'), cen_line[5]) |
| 5146 |
|
self.assertEqual(bmpm(cen_line[0], match_mode='exact', |
| 5147 |
|
name_mode='sep'), cen_line[6]) |
| 5148 |
|
|
| 5149 |
|
def test_bm_phonetic_number(self): |
| 5150 |
|
"""Test abydos.bm._bm_phonetic_number.""" |
chrislit /
abydos
