python-nameparser/nameparser/config/suffixes.py at 5838f1aa1b577a2310f086d6cb66708901db6499 · derek73/python-nameparser · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
# -*- coding: utf-8 -*-
from __future__ import unicode_literals

SUFFIX_NOT_ACRONYMS = set([
    'dr',
    'esq',
    'esquire',
    'jr',
    'jnr',
    'junior',
    'sr',
    'snr',
    '2',
    'i',
    'ii',
    'iii',
    'iv',
    'v',
])
"""

Post-nominal pieces that are not acronyms. The parser does not remove periods
when matching against these pieces.

"""
SUFFIX_ACRONYMS = set([
    'ae',
    'afc',
    'afm',
    'arrc',
    'bart',
    'bem',
    'bn',
    'bt',
    'cb',
    'cbe',
    'cfp',
    'cgc',
    'cgm',
    'ch',
    'chfc',
    'cie',
    'clu',
    'cmg',
    'cpa',
    'cpm',
    'csi',
    'csm',
    'cvo',
    'dbe',
    'dcb',
    'dcm',
    'dcmg',
    'dcvo',
    'dds',
    'dfc',
    'dfm',
    'dmd',
    'do',
    'dpm',
    'dsc',
    'dsm',
    'dso',
    'dvm',
    'ed',
    'erd',
    'gbe',
    'gc',
    'gcb',
    'gcie',
    'gcmg',
    'gcsi',
    'gcvo',
    'gm',
    'idsm',
    'iom',
    'iso',
    'jd',
    'kbe',
    'kcb',
    'kcie',
    'kcmg',
    'kcsi',
    'kcvo',
    'kg',
    'kp',
    'kt',
    'lg',
    'lt',
    'lvo',
    'ma',
    'mba',
    'mbe',
    'mc',
    'md',
    'mm',
    'mp',
    'msc'
    'msm',
    'mvo',
    'np',
    'obe',
    'obi',
    'om',
    'phd',
    'phr',
    'pmp',
    'qam',
    'qc',
    'qfsm',
    'qgm',
    'qpm',
    'rd',
    'rn',
    'rrc',
    'rvm',
    'sgm',
    'td',
    'ud',
    'vc',
    'vd',
    'vrd',
])
"""

Post-nominal acronyms. Titles, degrees and other things people stick after their name
that may or may not have periods between the letters. The parser removes periods
when matching against these pieces.

"""