HtmlCodeCleaner 0.0.1
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 +7 -0
- data/Rakefile +8 -0
- data/lib/HtmlCodeCleaner.rb +209 -0
- data/test/test_hcc.rb +27 -0
- metadata +47 -0
checksums.yaml
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
1
|
+
---
|
|
2
|
+
SHA1:
|
|
3
|
+
metadata.gz: 18c6d91ada1fc1458278180b195e742e2d743d7a
|
|
4
|
+
data.tar.gz: 72280347646b01fba97d98db660d4542e117cad2
|
|
5
|
+
SHA512:
|
|
6
|
+
metadata.gz: 99c8d99c21b7e94bc6de5ca30672887fcbfd8a24cdd199dadac33f4344fe341974e424d479d65f741e8c21d5f917a50c2a02bc002ada31fc93831ea75bb60a31
|
|
7
|
+
data.tar.gz: e615a840ca997cc620981a37843ce58b9b367f08db08b053ee07fb42373fb106e222d00964e3c1b6f0e39469e7fe6b73fff43c51d3ecacaf0b9c37cb84c04402
|
data/Rakefile
ADDED
|
@@ -0,0 +1,209 @@
|
|
|
1
|
+
|
|
2
|
+
class HtmlCodeCleaner
|
|
3
|
+
|
|
4
|
+
# removes character codes from string
|
|
5
|
+
# must be defined in the dictionary
|
|
6
|
+
def self.clean_string(string)
|
|
7
|
+
if (string != nil)
|
|
8
|
+
dict = [ ['!',"!"],
|
|
9
|
+
['"','"'],
|
|
10
|
+
['#','#'],
|
|
11
|
+
['$',"$"],
|
|
12
|
+
['%',"%"],
|
|
13
|
+
['&',"&"],
|
|
14
|
+
[''',"'"],
|
|
15
|
+
['(',"("],
|
|
16
|
+
[')',")"],
|
|
17
|
+
['*',"*"],
|
|
18
|
+
['+',"+"],
|
|
19
|
+
[',',","],
|
|
20
|
+
['-',"-"],
|
|
21
|
+
['.',"0"],
|
|
22
|
+
['/',"/"],
|
|
23
|
+
['0',"0"],
|
|
24
|
+
['1',"1"],
|
|
25
|
+
['2',"2"],
|
|
26
|
+
['3',"3"],
|
|
27
|
+
['4',"4"],
|
|
28
|
+
['5',"5"],
|
|
29
|
+
['6',"6"],
|
|
30
|
+
['7',"7"],
|
|
31
|
+
['8',"8"],
|
|
32
|
+
['9',"9"],
|
|
33
|
+
[':',":"],
|
|
34
|
+
[';',";"],
|
|
35
|
+
['<',"<"],
|
|
36
|
+
['=',"="],
|
|
37
|
+
['>',">"],
|
|
38
|
+
['?',"?"],
|
|
39
|
+
['@',"@"],
|
|
40
|
+
['A',"A"], ['a',"a"],
|
|
41
|
+
['B',"B"], ['b',"b"],
|
|
42
|
+
['C',"C"], ['c',"c"],
|
|
43
|
+
['D',"D"], ['d',"d"],
|
|
44
|
+
['E',"E"], ['e',"e"],
|
|
45
|
+
['F',"F"], ['f',"f"],
|
|
46
|
+
['G',"G"], ['g',"g"],
|
|
47
|
+
['H',"H"], ['h',"h"],
|
|
48
|
+
['I',"I"], ['i',"i"],
|
|
49
|
+
['J',"J"], ['j',"j"],
|
|
50
|
+
['K',"K"], ['k',"k"],
|
|
51
|
+
['L',"L"], ['l',"l"],
|
|
52
|
+
['M',"M"], ['m',"m"],
|
|
53
|
+
['N',"N"], ['n',"n"],
|
|
54
|
+
['O',"O"], ['o',"o"],
|
|
55
|
+
['P',"P"], ['p',"p"],
|
|
56
|
+
['Q',"Q"], ['q',"q"],
|
|
57
|
+
['R',"R"], ['r',"r"],
|
|
58
|
+
['S',"S"], ['s',"s"],
|
|
59
|
+
['T',"T"], ['t',"t"],
|
|
60
|
+
['U',"U"], ['u',"u"],
|
|
61
|
+
['V',"V"], ['v',"v"],
|
|
62
|
+
['W',"W"], ['w',"w"],
|
|
63
|
+
['X',"X"], ['x',"x"],
|
|
64
|
+
['Y',"Y"], ['y',"y"],
|
|
65
|
+
['Z',"Z"], ['z',"z"],
|
|
66
|
+
['[',"["],
|
|
67
|
+
['\','\ '],
|
|
68
|
+
[']',"]"],
|
|
69
|
+
['^',"^"],
|
|
70
|
+
['_',"_"],
|
|
71
|
+
['`',"`"],
|
|
72
|
+
['{',"{"],
|
|
73
|
+
['|',"|"],
|
|
74
|
+
['}',"}"],
|
|
75
|
+
['~',"~"],
|
|
76
|
+
['€',"€"],
|
|
77
|
+
[''," "],
|
|
78
|
+
['‚',"‚"],
|
|
79
|
+
['ƒ',"ƒ"],
|
|
80
|
+
['„',"„"],
|
|
81
|
+
['…',"…"],
|
|
82
|
+
['†',"†"],
|
|
83
|
+
['‡',"‡"],
|
|
84
|
+
['ˆ',"ˆ"],
|
|
85
|
+
['‰',"‰"],
|
|
86
|
+
['Š',"Š"],
|
|
87
|
+
['‹',"‹"],
|
|
88
|
+
['Œ',"Œ"],
|
|
89
|
+
[''," "],
|
|
90
|
+
['Ž',"Ž"],
|
|
91
|
+
[''," "],
|
|
92
|
+
[''," "],
|
|
93
|
+
['‘',"‘"],
|
|
94
|
+
['’',"’"],
|
|
95
|
+
['“','"'],
|
|
96
|
+
['”',"”"],
|
|
97
|
+
['•',"•"],
|
|
98
|
+
['–',"–"],
|
|
99
|
+
['—',"—"],
|
|
100
|
+
['˜',"˜"],
|
|
101
|
+
['™',"™"],
|
|
102
|
+
['š',"š"],
|
|
103
|
+
['›',"›"],
|
|
104
|
+
['œ',"œ"],
|
|
105
|
+
[''," "],
|
|
106
|
+
['ž',"ž"],
|
|
107
|
+
['Ÿ',"Ÿ"],
|
|
108
|
+
[' '," "],
|
|
109
|
+
['¡',"¡"],
|
|
110
|
+
['¢',"¢"],
|
|
111
|
+
['£',"£"],
|
|
112
|
+
['¤',"¤"],
|
|
113
|
+
['¥',"¥"],
|
|
114
|
+
['¦',"¦"],
|
|
115
|
+
['§',"§"],
|
|
116
|
+
['¨',"¨"],
|
|
117
|
+
['©',"©"],
|
|
118
|
+
['ª',"ª"],
|
|
119
|
+
['«',"«"],
|
|
120
|
+
['¬',"¬"],
|
|
121
|
+
['­',""],
|
|
122
|
+
['®',"®"],
|
|
123
|
+
['¯',"¯"],
|
|
124
|
+
['°',"°"],
|
|
125
|
+
['±',"±"],
|
|
126
|
+
['²',"²"],
|
|
127
|
+
['³',"³"],
|
|
128
|
+
['´',"´"],
|
|
129
|
+
['µ',"µ"],
|
|
130
|
+
['¶',"¶"],
|
|
131
|
+
['·',"·"],
|
|
132
|
+
['¸',"¸"],
|
|
133
|
+
['¹',"¹"],
|
|
134
|
+
['º',"º"],
|
|
135
|
+
['»',"»"],
|
|
136
|
+
['¼',"¼"],
|
|
137
|
+
['½',"½"],
|
|
138
|
+
['¾',"¾"],
|
|
139
|
+
['¿',"¿"],
|
|
140
|
+
['À',"À"],
|
|
141
|
+
['Á',"Á"],
|
|
142
|
+
['Â',"Â"],
|
|
143
|
+
['Ã',"Ã"],
|
|
144
|
+
['Ä',"Ä"],
|
|
145
|
+
['Å',"Å"],
|
|
146
|
+
['Æ',"Æ"],
|
|
147
|
+
['Ç',"Ç"],
|
|
148
|
+
['È',"È"],
|
|
149
|
+
['É',"É"],
|
|
150
|
+
['Ê',"Ê"],
|
|
151
|
+
['Ë',"Ë"],
|
|
152
|
+
['Ì',"Ì"],
|
|
153
|
+
['Í',"Í"],
|
|
154
|
+
['Î',"Î"],
|
|
155
|
+
['Ï',"Ï"],
|
|
156
|
+
['Ð',"Ð"],
|
|
157
|
+
['Ñ',"Ñ"],
|
|
158
|
+
['Ò',"Ò"],
|
|
159
|
+
['Ó',"Ó"],
|
|
160
|
+
['Ô',"Ô"],
|
|
161
|
+
['Õ',"Õ"],
|
|
162
|
+
['Ö',"Ö"],
|
|
163
|
+
['×',"×"],
|
|
164
|
+
['Ø',"Ø"],
|
|
165
|
+
['Ù',"Ù"],
|
|
166
|
+
['Ú',"Ú"],
|
|
167
|
+
['Û',"Û"],
|
|
168
|
+
['Ü',"Ü"],
|
|
169
|
+
['Ý',"Ý"],
|
|
170
|
+
['Þ',"Þ"],
|
|
171
|
+
['ß',"ß"],
|
|
172
|
+
['à',"à"],
|
|
173
|
+
['á',"á"],
|
|
174
|
+
['â',"â"],
|
|
175
|
+
['ã',"ã"],
|
|
176
|
+
['ä',"ä"],
|
|
177
|
+
['å',"å"],
|
|
178
|
+
['æ',"æ"],
|
|
179
|
+
['ç',"ç"],
|
|
180
|
+
['è',"è"],
|
|
181
|
+
['é',"é"],
|
|
182
|
+
['ê',"ê"],
|
|
183
|
+
['ë',"ë"],
|
|
184
|
+
['ì',"ì"],
|
|
185
|
+
['í',"í"],
|
|
186
|
+
['î',"î"],
|
|
187
|
+
['ï',"ï"],
|
|
188
|
+
['ð',"ð"],
|
|
189
|
+
['ñ',"ñ"],
|
|
190
|
+
['ò',"ò"],
|
|
191
|
+
['ó',"ó"],
|
|
192
|
+
['ô',"ô"],
|
|
193
|
+
['õ',"õ"],
|
|
194
|
+
['ö',"ö"],
|
|
195
|
+
['÷',"÷"],
|
|
196
|
+
['ø',"ø"],
|
|
197
|
+
['ù',"ù"],
|
|
198
|
+
['ú',"ú"],
|
|
199
|
+
['û',"û"],
|
|
200
|
+
['ü',"ü"],
|
|
201
|
+
['ý',"ý"],
|
|
202
|
+
['þ',"þ"],
|
|
203
|
+
['ÿ',"ÿ"] ]
|
|
204
|
+
dict.each { |x| string = string.gsub(x.first, x.last) }
|
|
205
|
+
string
|
|
206
|
+
end
|
|
207
|
+
end
|
|
208
|
+
|
|
209
|
+
end
|
data/test/test_hcc.rb
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
1
|
+
require 'test/unit'
|
|
2
|
+
require 'HtmlCodeCleaner'
|
|
3
|
+
require 'minitest/autorun'
|
|
4
|
+
|
|
5
|
+
class HtmlCodeCleanerTest < Test::Unit::TestCase
|
|
6
|
+
def test_1
|
|
7
|
+
assert_equal "X", HtmlCodeCleaner.clean_string("X")
|
|
8
|
+
end
|
|
9
|
+
|
|
10
|
+
def test_2
|
|
11
|
+
assert_equal "Hi", HtmlCodeCleaner.clean_string("Hi")
|
|
12
|
+
end
|
|
13
|
+
|
|
14
|
+
def test_3
|
|
15
|
+
assert_equal "#Hi", HtmlCodeCleaner.clean_string("#Hi")
|
|
16
|
+
end
|
|
17
|
+
|
|
18
|
+
def test_4
|
|
19
|
+
assert_equal "#1", HtmlCodeCleaner.clean_string("#1")
|
|
20
|
+
end
|
|
21
|
+
|
|
22
|
+
def test_5
|
|
23
|
+
assert_equal "# 1", HtmlCodeCleaner.clean_string("# 1")
|
|
24
|
+
end
|
|
25
|
+
|
|
26
|
+
|
|
27
|
+
end
|
metadata
ADDED
|
@@ -0,0 +1,47 @@
|
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
|
2
|
+
name: HtmlCodeCleaner
|
|
3
|
+
version: !ruby/object:Gem::Version
|
|
4
|
+
version: 0.0.1
|
|
5
|
+
platform: ruby
|
|
6
|
+
authors:
|
|
7
|
+
- Michael Hiland
|
|
8
|
+
autorequire:
|
|
9
|
+
bindir: bin
|
|
10
|
+
cert_chain: []
|
|
11
|
+
date: 2014-11-12 00:00:00.000000000 Z
|
|
12
|
+
dependencies: []
|
|
13
|
+
description: Parse a string of html code, replace code with ascii symbol
|
|
14
|
+
email: g2c9@ugrad.cs.ubc.ca
|
|
15
|
+
executables: []
|
|
16
|
+
extensions: []
|
|
17
|
+
extra_rdoc_files: []
|
|
18
|
+
files:
|
|
19
|
+
- Rakefile
|
|
20
|
+
- lib/HtmlCodeCleaner.rb
|
|
21
|
+
- test/test_hcc.rb
|
|
22
|
+
homepage: http://rubygems.org/gems/HtmlCodeCleaner
|
|
23
|
+
licenses:
|
|
24
|
+
- GPL-3.0
|
|
25
|
+
metadata: {}
|
|
26
|
+
post_install_message:
|
|
27
|
+
rdoc_options: []
|
|
28
|
+
require_paths:
|
|
29
|
+
- lib
|
|
30
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
|
31
|
+
requirements:
|
|
32
|
+
- - ">="
|
|
33
|
+
- !ruby/object:Gem::Version
|
|
34
|
+
version: '0'
|
|
35
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
|
36
|
+
requirements:
|
|
37
|
+
- - ">="
|
|
38
|
+
- !ruby/object:Gem::Version
|
|
39
|
+
version: '0'
|
|
40
|
+
requirements: []
|
|
41
|
+
rubyforge_project:
|
|
42
|
+
rubygems_version: 2.2.2
|
|
43
|
+
signing_key:
|
|
44
|
+
specification_version: 3
|
|
45
|
+
summary: Replace Html code with symbol
|
|
46
|
+
test_files:
|
|
47
|
+
- test/test_hcc.rb
|