idata 0.1.4 → 0.1.5
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/bin/isanitize +63 -4
- data/lib/idata/version.rb +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: 2044f9a6b9fae36b3a529a88e9418b52d3d1442f
|
4
|
+
data.tar.gz: 1b9ed2d193de713bab6f27efcf521ba46445b3ab
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: aa68dbc6e46fda7637e093c272a0f2fed5887be04f888e7cfae7165d836a6e408ebcaebe00a8b45c6626ab5236f23c9f929f49abf1892d2139fd2d0adbd22ca4
|
7
|
+
data.tar.gz: 9ff78ee78166292cf035ed7636f9e2ad388b027c7d64f93f0265bd79f9b44ff0b0dbdc0add7060106ca3f44c5cf3a29b4e1853ba38116de9a4a32de9a5777314
|
data/bin/isanitize
CHANGED
@@ -1,4 +1,63 @@
|
|
1
|
-
|
2
|
-
|
3
|
-
|
4
|
-
|
1
|
+
# DATA SANITIZER
|
2
|
+
#
|
3
|
+
# @author Nghi Pham
|
4
|
+
# @date April 2014
|
5
|
+
#
|
6
|
+
require 'optparse'
|
7
|
+
|
8
|
+
$options = {
|
9
|
+
:remove => []
|
10
|
+
}
|
11
|
+
parser = OptionParser.new("", 24) do |opts|
|
12
|
+
opts.banner = "\nProgram: Data Sanitizer\nAuthor: Nghi Pham\n\n"
|
13
|
+
|
14
|
+
opts.on("--remove CHARCODE", "Unicode code") do |v|
|
15
|
+
$options[:remove] << v
|
16
|
+
end
|
17
|
+
|
18
|
+
opts.on_tail('--help', 'Displays this help') do
|
19
|
+
puts opts, "", help
|
20
|
+
exit
|
21
|
+
end
|
22
|
+
end
|
23
|
+
|
24
|
+
def help
|
25
|
+
return <<-eos
|
26
|
+
|
27
|
+
EXAMPLES
|
28
|
+
-------------------------------------------------------
|
29
|
+
|
30
|
+
eos
|
31
|
+
end
|
32
|
+
|
33
|
+
begin
|
34
|
+
parser.parse!
|
35
|
+
rescue SystemExit => ex
|
36
|
+
exit
|
37
|
+
end
|
38
|
+
|
39
|
+
if ARGV.empty?
|
40
|
+
puts "ERROR: Please specify input file"
|
41
|
+
exit
|
42
|
+
end
|
43
|
+
|
44
|
+
def sanitize(file)
|
45
|
+
s = IO.read(file)
|
46
|
+
|
47
|
+
# Remove invalid UTF-8 byte code
|
48
|
+
s = s.encode('UTF-8', 'binary', invalid: :replace, undef: :replace, replace: '')
|
49
|
+
|
50
|
+
# Remove wrong char
|
51
|
+
$options[:remove].each do |c|
|
52
|
+
s.gsub!([c.to_i].pack("U"), "")
|
53
|
+
end
|
54
|
+
|
55
|
+
# Write back
|
56
|
+
File.open(file, 'wb') {|f| f.write(s)}
|
57
|
+
end
|
58
|
+
|
59
|
+
ARGV.each do |file|
|
60
|
+
sanitize(file)
|
61
|
+
end
|
62
|
+
|
63
|
+
puts "\n#{ARGV.count} file(s) sanitized\n"
|
data/lib/idata/version.rb
CHANGED
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: idata
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.1.
|
4
|
+
version: 0.1.5
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Nghi Pham
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2014-04-
|
11
|
+
date: 2014-04-24 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: bundler
|