word_filter 0.0.8 → 0.0.9
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/lib/word_filter/version.rb +1 -1
- data/lib/word_filter.rb +179 -0
- data/word_filter.gemspec +1 -1
- metadata +2 -2
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 06e6a40537fb1cfad2ee83e8a598c8826bd40fda
|
4
|
+
data.tar.gz: 14efc8f39dc0a84df54e2195799ea65214134d32
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 921118f7c180ba70f95b4df31297b14351f1777a0dcfca5edaa4d2b7e77be84045880f0edc5b303c3db3059a32e07f098f6eba1d79ee607bbeb5a0fe7224ac62
|
7
|
+
data.tar.gz: 6d79bc70cb2d79ea499faa05533dfeccabbecafde561db16b4045085b0828d54b2ab902164a0bff8678bb519acc5e0b1921ea90b7d9dabea28fec60d4eb28df7
|
data/lib/word_filter/version.rb
CHANGED
data/lib/word_filter.rb
CHANGED
@@ -1,4 +1,183 @@
|
|
1
1
|
require "word_filter/version"
|
2
2
|
|
3
3
|
module WordFilter
|
4
|
+
class Filter
|
5
|
+
|
6
|
+
@@emailRegex = /[a-zA-Z0-9._%+-]+@[a-z0-9.-]+\\.[a-zA-Z]{2,4}/
|
7
|
+
@@alphaNumericDigit = /(zero|one|two|three|four|five|six|seven|eight|nine|ten|eleven|twelve|thirteen|fourteen|fifteen|sixteen|seventeen|eighteen|nineteen|twenty|\d)/;
|
8
|
+
@@digitsRegex = Regexp.new("\b(\s*" + @@alphaNumericDigit.source + ")+\b")
|
9
|
+
@@streetNameRegex = Regexp.new("\b(\s*" + @@alphaNumericDigit.source + ")+\s([a-z\d]+\.?\s*){1,5}\b(avenue|ave|street|st|court|ct|circle|boulevard|blvd|lane|ln|trail|tr|loop|lp|route|rt|drive|dr|road|rd|terrace|tr|way|wy|highway|hiway|hw)\b")
|
10
|
+
@@phoneNumber = Regexp.new("((" + @@alphaNumericDigit.source + ")\W*?){3}((" + @@alphaNumericDigit.source + ")\W*?){4}\b")
|
11
|
+
@@urlRegex = /(?:http|https):\/\/[a-z0-9]+(?:[\-\.]{1}[a-z0-9]+)*\.[a-z]{2,5}(?:(?::[0-9]{1,5})?\/[^\s]*)?/
|
12
|
+
|
13
|
+
NONE = 0;
|
14
|
+
REPEATED_VOWELS = 1;
|
15
|
+
SWAPPABLE_VOWELS = 2;
|
16
|
+
SWAPPABLE_AND_REPEATED_VOWELS = 3;
|
17
|
+
SWAPPABLE_AND_REPEATED_VOWELS_INCLUDING_NONE = 4;
|
18
|
+
|
19
|
+
|
20
|
+
|
21
|
+
def initialize()
|
22
|
+
@filterLevel = NONE
|
23
|
+
end
|
24
|
+
|
25
|
+
attr_accessor :filterLevel
|
26
|
+
|
27
|
+
def filterInit(dictionaryFile, badwordslist)
|
28
|
+
@goodWords = loadDictionary(dictionaryFile)
|
29
|
+
#The original java class requiere other three word's list
|
30
|
+
@datingWordsRegex = /dating/
|
31
|
+
@deviantWordsRegex = /deviant/
|
32
|
+
@badWordsRegex = loadBadwords(badwordslist)
|
33
|
+
|
34
|
+
vowels = /([aeiou])/
|
35
|
+
@vowelSwappedAndRepeatedRegex = Regexp.new(@badWordsRegex.source.gsub(vowels, "[aeiou]+"))
|
36
|
+
@vowelSwappedAndRepeatedRegexIncludingEmpty = Regexp.new(@badWordsRegex.source.gsub(vowels, "[aeiou]*"))
|
37
|
+
@vowelRepeatedRegex = Regexp.new(@badWordsRegex.source.gsub(vowels, "\\1+"))
|
38
|
+
@vowelSwappedRegex = Regexp.new(@badWordsRegex.source.gsub(vowels, "[aeiou]"))
|
39
|
+
|
40
|
+
end
|
41
|
+
|
42
|
+
|
43
|
+
def loadDictionary(path)
|
44
|
+
words = []
|
45
|
+
File.open(path, "r").each_line do |line|
|
46
|
+
splitted = line.split(" ")
|
47
|
+
splitted.each do |w|
|
48
|
+
words << w
|
49
|
+
end
|
50
|
+
end
|
51
|
+
return words
|
52
|
+
end
|
53
|
+
|
54
|
+
def loadBadwords(path)
|
55
|
+
words = File.read(path).gsub("\r", '').split("\n")
|
56
|
+
regex = words.join('|')
|
57
|
+
regex = '(' + regex + ')'
|
58
|
+
regex = Regexp.new(regex)
|
59
|
+
return regex
|
60
|
+
end
|
61
|
+
|
62
|
+
def filterString(input)
|
63
|
+
|
64
|
+
# Output:
|
65
|
+
# -1: An exception occured while trying to check the string, do not post
|
66
|
+
# 0: string is safe to post
|
67
|
+
# 1: string contains an email address
|
68
|
+
# 2: string contains a URL
|
69
|
+
# 3: string contains a street address
|
70
|
+
# 4: string contains a phone number
|
71
|
+
# 5: string contains a dating word
|
72
|
+
# 6: string contains a deviant word
|
73
|
+
# 9: string contains any other bad word
|
74
|
+
|
75
|
+
input = input.strip.downcase
|
76
|
+
workingCopy = input
|
77
|
+
|
78
|
+
if input == ""
|
79
|
+
return 0
|
80
|
+
end
|
81
|
+
|
82
|
+
if @@emailRegex.match(input)
|
83
|
+
return 1
|
84
|
+
end
|
85
|
+
|
86
|
+
if @@urlRegex.match(input)
|
87
|
+
return 2
|
88
|
+
end
|
89
|
+
|
90
|
+
if @@streetNameRegex.match(input)
|
91
|
+
return 3
|
92
|
+
end
|
93
|
+
|
94
|
+
if @@phoneNumber.match(input)
|
95
|
+
return 4
|
96
|
+
end
|
97
|
+
|
98
|
+
workingCopy.gsub("\s+", " ")
|
99
|
+
workingCopy.gsub!(/["',.;:?-]/, " ")
|
100
|
+
workingCopy.gsub!(/!+\s/, " ")
|
101
|
+
workingCopy.gsub!(/!+\z/, " ")
|
102
|
+
workingCopy.gsub!(/\br\su/, " ")
|
103
|
+
|
104
|
+
cleanVersion = stripGoodWords(workingCopy)
|
105
|
+
|
106
|
+
if cleanVersion == nil or cleanVersion.length == 0
|
107
|
+
return 0
|
108
|
+
end
|
109
|
+
|
110
|
+
if @datingWordsRegex.match(cleanVersion)
|
111
|
+
return 5
|
112
|
+
end
|
113
|
+
|
114
|
+
if @deviantWordsRegex.match(cleanVersion)
|
115
|
+
return 6
|
116
|
+
end
|
117
|
+
|
118
|
+
if @badWordsRegex.match(cleanVersion)
|
119
|
+
return 7
|
120
|
+
end
|
121
|
+
|
122
|
+
#let's try various combinations of bad word tricks
|
123
|
+
currentVersion = cleanVersion
|
124
|
+
|
125
|
+
#compress the string then check it again
|
126
|
+
if @badWordsRegex.match(currentVersion.gsub("[ \t\n\f\r]", ""))
|
127
|
+
return 9
|
128
|
+
end
|
129
|
+
|
130
|
+
#zap special characters and check it again
|
131
|
+
if @badWordsRegex.match(currentVersion.gsub("[^a-z]", ""))
|
132
|
+
return 9
|
133
|
+
end
|
134
|
+
|
135
|
+
#replace certain special characters with their letter equivalents
|
136
|
+
#NOTE: This one maps vertical non-letter chars (!1|) to i
|
137
|
+
specialCharsReplaced_i = currentVersion.tr("@683!1|0$+","abbeiiiost")
|
138
|
+
if @badWordsRegex.match(specialCharsReplaced_i)
|
139
|
+
return 9
|
140
|
+
end
|
141
|
+
|
142
|
+
#replace certain special characters with their letter equivalents
|
143
|
+
#NOTE: This one maps vertical non-letter chars (!1|) to l
|
144
|
+
specialCharsReplaced_l = currentVersion.tr("@683!1|0$+","abbelllost")
|
145
|
+
if @badWordsRegex.match(specialCharsReplaced_l)
|
146
|
+
return 9
|
147
|
+
end
|
148
|
+
|
149
|
+
case @filterLevel
|
150
|
+
when NONE
|
151
|
+
return 0
|
152
|
+
when REPEATED_VOWELS
|
153
|
+
if @vowelRepeatedRegex.match(specialCharsReplaced_i) or @vowelRepeatedRegex.match(specialCharsReplaced_l)
|
154
|
+
return 9
|
155
|
+
end
|
156
|
+
when SWAPPABLE_VOWELS
|
157
|
+
if @vowelSwappedRegex.match(specialCharsReplaced_i) or @vowelSwappedRegex.match(specialCharsReplaced_l)
|
158
|
+
return 9
|
159
|
+
end
|
160
|
+
when SWAPPABLE_AND_REPEATED_VOWELS
|
161
|
+
if @vowelSwappedAndRepeatedRegex.match(specialCharsReplaced_i) or @vowelSwappedAndRepeatedRegex.match(specialCharsReplaced_l)
|
162
|
+
return 9
|
163
|
+
end
|
164
|
+
when SWAPPABLE_AND_REPEATED_VOWELS_INCLUDING_NONE
|
165
|
+
if @vowelSwappedAndRepeatedRegexIncludingEmpty.match(specialCharsReplaced_i) or @vowelSwappedAndRepeatedRegexIncludingEmpty.match(specialCharsReplaced_l)
|
166
|
+
return 9
|
167
|
+
end
|
168
|
+
end
|
169
|
+
|
170
|
+
end
|
171
|
+
|
172
|
+
def stripGoodWords(input)
|
173
|
+
result = []
|
174
|
+
input = input.split(" ")
|
175
|
+
input.each do |w|
|
176
|
+
if not @goodWords.include? w
|
177
|
+
result << w
|
178
|
+
end
|
179
|
+
end
|
180
|
+
return result.join(" ")
|
181
|
+
end
|
182
|
+
end
|
4
183
|
end
|
data/word_filter.gemspec
CHANGED
@@ -6,7 +6,7 @@ require 'word_filter/version'
|
|
6
6
|
Gem::Specification.new do |spec|
|
7
7
|
spec.name = "word_filter"
|
8
8
|
spec.version = WordFilter::VERSION
|
9
|
-
spec.authors = ["Huascar
|
9
|
+
spec.authors = ["Huascar Ona"]
|
10
10
|
spec.email = ["huascarking@hotmail.com"]
|
11
11
|
spec.description = %q{A bad word filter for the input text.}
|
12
12
|
spec.summary = %q{A word filter gem}
|