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
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
|
# encoding: UTF-8
module Stringex
module Localization
module ConversionExpressions
ABBREVIATION = /(\s|\(|^)([[:alpha:]](\.[[:alpha:]])+(\.?)[[:alpha:]]*(\s|\)|$))/
ACCENTED_HTML_ENTITY = /&([A-Za-z])(grave|acute|circ|tilde|uml|ring|cedil|slash);/
APOSTROPHE = /(^|[[:alpha:]])'|`([[:alpha:]]|$)/
CHARACTERS = {
and: /\s*&\s*/,
at: /\s*@\s*/,
degrees: /\s*°\s*/,
divide: /\s*÷\s*/,
dot: /(\S|^)\.(\S)/,
ellipsis: /\s*\.{3,}\s*/,
equals: /\s*=\s*/,
number: /\s*#/,
percent: /\s*%\s*/,
plus: /\s*\+\s*/,
slash: /\s*(\\|\/|／)\s*/,
star: /\s*\*\s*/,
}
# Things that just get converted to spaces
CLEANUP_CHARACTERS = /[\.,:;(){}\[\]\?!\^'ʼ"`~_\|<>]/
CLEANUP_HTML_ENTITIES = /&[^;]+;/
CURRENCIES_SUPPORTED_SIMPLE = {
generic: /¤/,
dollars: /\$/,
euros: /€/,
pounds: /£/,
yen: /¥/,
reais: /R\$/
}
CURRENCIES_SUPPORTED_COMPLEX = {
dollars: :dollars_cents,
euros: :euros_cents,
pounds: :pounds_pence,
reais: :reais_cents
}
CURRENCIES_SUPPORTED = Regexp.new(CURRENCIES_SUPPORTED_SIMPLE.values.join('|'))
CURRENCIES_SIMPLE = CURRENCIES_SUPPORTED_SIMPLE.inject({}) do |hash, content|
key, expression = content
hash[key] = /(?:\s|^)#{expression}(\d*)(?:\s|$)/
hash
end
CURRENCIES_COMPLEX = CURRENCIES_SUPPORTED_SIMPLE.inject({}) do |hash, content|
key, expression = content
# Do we really need to not worry about complex currencies if there are none for the currency?
complex_key = CURRENCIES_SUPPORTED_COMPLEX[key]
if complex_key
hash[complex_key] = /(?:\s|^)#{expression}(\d+)\.(\d+)(?:\s|$)/
end
hash
end
CURRENCIES = CURRENCIES_SIMPLE.merge(CURRENCIES_COMPLEX)
HTML_ENTITIES = Proc.new(){
base = {
amp: %w{#38 amp},
cent: %w{#162 cent},
copy: %w{#169 copy},
deg: %w{#176 deg},
divide: %w{#247 divide},
double_quote: %w{#34 #822[012] quot ldquo rdquo dbquo},
ellipsis: %w{#8230 hellip},
en_dash: %w{#8211 ndash},
em_dash: %w{#8212 mdash},
frac14: %w{#188 frac14},
frac12: %w{#189 frac12},
frac34: %w{#190 frac34},
gt: %w{#62 gt},
lt: %w{#60 lt},
nbsp: %w{#160 nbsp},
pound: %w{#163 pound},
reg: %w{#174 reg},
single_quote: %w{#39 #821[678] apos lsquo rsquo sbquo},
times: %w{#215 times},
trade: %w{#8482 trade},
yen: %w{#165 yen},
}
base.inject({}) do |hash, content|
key, expression = content
hash[key] = /&(#{expression.join('|')});/
hash
end
}.call
HTML_TAG = Proc.new(){
name = /[\w:-]+/
value = /([A-Za-z0-9]+|('[^']*?'|"[^"]*?"))/
attr = /(#{name}(\s*=\s*#{value})?)/
/<[!\/?\[]?(#{name}|--)(\s+(#{attr}(\s+#{attr})*))?\s*([!\/?\]]+|--)?>/
}.call
SMART_PUNCTUATION = {
/(“|”|\302\223|\302\224|\303\222|\303\223)/ => '"',
/(‘|’|\302\221|\302\222|\303\225)/ => "'",
/…/ => "...",
}
UNREADABLE_CONTROL_CHARACTERS = /[[:cntrl:]]/
# Ordered by denominator then numerator of the value
VULGAR_FRACTIONS = {
half: /(½|½|½)/,
one_third: /(⅓|⅓)/,
two_thirds: /(⅔|⅔)/,
one_fourth: /(¼|¼|¼)/,
three_fourths: /(¾|¾|¾)/,
one_fifth: /(⅕|⅕)/,
two_fifths: /(⅖|⅖)/,
three_fifths: /(⅗|⅗)/,
four_fifths: /(⅘|⅘)/,
one_sixth: /(⅙|⅙)/,
five_sixths: /(⅚|⅚)/,
one_eighth: /(⅛|⅛)/,
three_eighths: /(⅜|⅜)/,
five_eighths: /(⅝|⅝)/,
seven_eighths: /(⅞|⅞)/,
}
WHITESPACE = /\s+/
class << self
%w{
abbreviation
accented_html_entity
apostrophe
characters
cleanup_characters
cleanup_html_entities
currencies
currencies_simple
currencies_complex
html_entities
html_tag
smart_punctuation
unreadable_control_characters
vulgar_fractions
whitespace
}.each do |conversion_type|
define_method conversion_type do
const_get conversion_type.upcase
end
end
end
end
end
end
|
