File size: 1,331 Bytes
4304c2f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import re

_no_period_re = re.compile(r"(No[.])(?=[ ]?[0-9])")
_percent_re = re.compile(r"([ ]?[%])")
_half_re = re.compile("([0-9]½)|(½)")


# List of (regular expression, replacement) pairs for abbreviations:
_abbreviations = [
    (re.compile("\\b%s\\." % x[0], re.IGNORECASE), x[1])
    for x in [
        ("mrs", "misess"),
        ("ms", "miss"),
        ("mr", "mister"),
        ("dr", "doctor"),
        ("st", "saint"),
        ("co", "company"),
        ("jr", "junior"),
        ("maj", "major"),
        ("gen", "general"),
        ("drs", "doctors"),
        ("rev", "reverend"),
        ("lt", "lieutenant"),
        ("hon", "honorable"),
        ("sgt", "sergeant"),
        ("capt", "captain"),
        ("esq", "esquire"),
        ("ltd", "limited"),
        ("col", "colonel"),
        ("ft", "fort"),
    ]
]


def _expand_no_period(m):
    word = m.group(0)
    if word[0] == "N":
        return "Number"
    return "number"


def _expand_percent(m):
    return " percent"


def _expand_half(m):
    word = m.group(1)
    if word is None:
        return "half"
    return word[0] + " and a half"


def normalize_abbreviations(text):
    text = re.sub(_no_period_re, _expand_no_period, text)
    text = re.sub(_percent_re, _expand_percent, text)
    text = re.sub(_half_re, _expand_half, text)
    return text