encoda 0.1.0
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.
- data/.document +5 -0
- data/.gitignore +21 -0
- data/LICENSE +20 -0
- data/README.rdoc +62 -0
- data/Rakefile +46 -0
- data/VERSION +1 -0
- data/encoda.gemspec +66 -0
- data/lib/encoda.rb +141 -0
- data/spec/encoda_spec.rb +80 -0
- data/spec/spec.opts +1 -0
- data/spec/spec_helper.rb +9 -0
- data/spec/test_files/conv_files/nedivx-tbl.big5.srt +5569 -0
- data/spec/test_files/conv_files/nedivx-tbl.eng.srt +5895 -0
- data/spec/test_files/conv_files/nedivx-tbl.gb.srt +5569 -0
- data/spec/test_files/conv_files/utf8.gb.srt +5569 -0
- data/spec/test_files/files/nedivx-tbl.big5.srt +5569 -0
- data/spec/test_files/files/nedivx-tbl.eng.srt +5895 -0
- data/spec/test_files/files/nedivx-tbl.gb.srt +5569 -0
- data/spec/test_files/files/utf8.gb.srt +5569 -0
- metadata +94 -0
data/.document
ADDED
data/.gitignore
ADDED
data/LICENSE
ADDED
@@ -0,0 +1,20 @@
|
|
1
|
+
Copyright (c) 2009 Zipme
|
2
|
+
|
3
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
4
|
+
a copy of this software and associated documentation files (the
|
5
|
+
"Software"), to deal in the Software without restriction, including
|
6
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
7
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
8
|
+
permit persons to whom the Software is furnished to do so, subject to
|
9
|
+
the following conditions:
|
10
|
+
|
11
|
+
The above copyright notice and this permission notice shall be
|
12
|
+
included in all copies or substantial portions of the Software.
|
13
|
+
|
14
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
15
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
16
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
17
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
18
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
19
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
20
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.rdoc
ADDED
@@ -0,0 +1,62 @@
|
|
1
|
+
= Encoda
|
2
|
+
|
3
|
+
This is a simple file encoding converter
|
4
|
+
|
5
|
+
== Installation
|
6
|
+
|
7
|
+
sudo gem install Encoda
|
8
|
+
|
9
|
+
== Getting Started
|
10
|
+
|
11
|
+
==== Single file conversion
|
12
|
+
|
13
|
+
Encoda.convert do
|
14
|
+
to_path 'convert/to/path'
|
15
|
+
from_file 'path/to/your/file'
|
16
|
+
from_encoding 'GB2312'
|
17
|
+
to_encoding 'UTF8'
|
18
|
+
end
|
19
|
+
|
20
|
+
==== Multiple files conversion
|
21
|
+
|
22
|
+
You can batch convert multiple files from a specific directory by specifying from_path
|
23
|
+
|
24
|
+
Encoda.convert do
|
25
|
+
from_path /from/path
|
26
|
+
to_path /to/path
|
27
|
+
to_encoding 'UTF8'
|
28
|
+
end
|
29
|
+
|
30
|
+
If you specify from_path, it will alway do the batch conversion and ignore the from_path option.
|
31
|
+
|
32
|
+
As you can see, if you omit the from_encoding option, the Encoda will try to guess the file's original encoding.
|
33
|
+
The guessing feature is based on chardet library.
|
34
|
+
|
35
|
+
==== Retrieve the conversion result
|
36
|
+
|
37
|
+
encoda = Encoda.convert do
|
38
|
+
from_path /from/path
|
39
|
+
to_path /to/path
|
40
|
+
to_encoding 'UTF8'
|
41
|
+
end
|
42
|
+
|
43
|
+
puts encoda.failed #=> ['failed_file1.txt', 'failed_file2.txt']
|
44
|
+
puts encoda.success #=> ['success_file1.txt', 'success_file3.txt, file4.srt']
|
45
|
+
|
46
|
+
== TODOs
|
47
|
+
|
48
|
+
Refactoring!!!
|
49
|
+
|
50
|
+
== Note on Patches/Pull Requests
|
51
|
+
|
52
|
+
* Fork the project.
|
53
|
+
* Make your feature addition or bug fix.
|
54
|
+
* Add tests for it. This is important so I don't break it in a
|
55
|
+
future version unintentionally.
|
56
|
+
* Commit, do not mess with rakefile, version, or history.
|
57
|
+
(if you want to have your own version, that is fine but bump version in a commit by itself I can ignore when I pull)
|
58
|
+
* Send me a pull request. Bonus points for topic branches.
|
59
|
+
|
60
|
+
== Copyright
|
61
|
+
|
62
|
+
Copyright (c) 2010 Zipme. See LICENSE for details.
|
data/Rakefile
ADDED
@@ -0,0 +1,46 @@
|
|
1
|
+
require 'rubygems'
|
2
|
+
require 'rake'
|
3
|
+
|
4
|
+
begin
|
5
|
+
require 'jeweler'
|
6
|
+
Jeweler::Tasks.new do |gem|
|
7
|
+
gem.name = "encoda"
|
8
|
+
gem.summary = %Q{Encoding converter}
|
9
|
+
gem.description = %Q{It's a simple file encoding converter }
|
10
|
+
gem.email = "genkiwow@gmail.com"
|
11
|
+
gem.homepage = "http://github.com/zipme/encoda"
|
12
|
+
gem.authors = ["Zipme"]
|
13
|
+
gem.add_dependency "chardet", ">=0.9.0"
|
14
|
+
gem.add_development_dependency "rspec", ">= 1.2.9"
|
15
|
+
# gem is a Gem::Specification... see http://www.rubygems.org/read/chapter/20 for additional settings
|
16
|
+
end
|
17
|
+
Jeweler::GemcutterTasks.new
|
18
|
+
rescue LoadError
|
19
|
+
puts "Jeweler (or a dependency) not available. Install it with: gem install jeweler"
|
20
|
+
end
|
21
|
+
|
22
|
+
require 'spec/rake/spectask'
|
23
|
+
Spec::Rake::SpecTask.new(:spec) do |spec|
|
24
|
+
spec.libs << 'lib' << 'spec'
|
25
|
+
spec.spec_files = FileList['spec/**/*_spec.rb']
|
26
|
+
end
|
27
|
+
|
28
|
+
Spec::Rake::SpecTask.new(:rcov) do |spec|
|
29
|
+
spec.libs << 'lib' << 'spec'
|
30
|
+
spec.pattern = 'spec/**/*_spec.rb'
|
31
|
+
spec.rcov = true
|
32
|
+
end
|
33
|
+
|
34
|
+
task :spec => :check_dependencies
|
35
|
+
|
36
|
+
task :default => :spec
|
37
|
+
|
38
|
+
require 'rake/rdoctask'
|
39
|
+
Rake::RDocTask.new do |rdoc|
|
40
|
+
version = File.exist?('VERSION') ? File.read('VERSION') : ""
|
41
|
+
|
42
|
+
rdoc.rdoc_dir = 'rdoc'
|
43
|
+
rdoc.title = "encoda #{version}"
|
44
|
+
rdoc.rdoc_files.include('README*')
|
45
|
+
rdoc.rdoc_files.include('lib/**/*.rb')
|
46
|
+
end
|
data/VERSION
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
0.1.0
|
data/encoda.gemspec
ADDED
@@ -0,0 +1,66 @@
|
|
1
|
+
# Generated by jeweler
|
2
|
+
# DO NOT EDIT THIS FILE DIRECTLY
|
3
|
+
# Instead, edit Jeweler::Tasks in rakefile, and run the gemspec command
|
4
|
+
# -*- encoding: utf-8 -*-
|
5
|
+
|
6
|
+
Gem::Specification.new do |s|
|
7
|
+
s.name = %q{encoda}
|
8
|
+
s.version = "0.1.0"
|
9
|
+
|
10
|
+
s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
|
11
|
+
s.authors = ["Zipme"]
|
12
|
+
s.date = %q{2010-01-07}
|
13
|
+
s.description = %q{It's a simple file encoding converter }
|
14
|
+
s.email = %q{genkiwow@gmail.com}
|
15
|
+
s.extra_rdoc_files = [
|
16
|
+
"LICENSE",
|
17
|
+
"README.rdoc"
|
18
|
+
]
|
19
|
+
s.files = [
|
20
|
+
".document",
|
21
|
+
".gitignore",
|
22
|
+
"LICENSE",
|
23
|
+
"README.rdoc",
|
24
|
+
"Rakefile",
|
25
|
+
"VERSION",
|
26
|
+
"encoda.gemspec",
|
27
|
+
"lib/encoda.rb",
|
28
|
+
"spec/encoda_spec.rb",
|
29
|
+
"spec/spec.opts",
|
30
|
+
"spec/spec_helper.rb",
|
31
|
+
"spec/test_files/conv_files/nedivx-tbl.big5.srt",
|
32
|
+
"spec/test_files/conv_files/nedivx-tbl.eng.srt",
|
33
|
+
"spec/test_files/conv_files/nedivx-tbl.gb.srt",
|
34
|
+
"spec/test_files/conv_files/utf8.gb.srt",
|
35
|
+
"spec/test_files/files/nedivx-tbl.big5.srt",
|
36
|
+
"spec/test_files/files/nedivx-tbl.eng.srt",
|
37
|
+
"spec/test_files/files/nedivx-tbl.gb.srt",
|
38
|
+
"spec/test_files/files/utf8.gb.srt"
|
39
|
+
]
|
40
|
+
s.homepage = %q{http://github.com/zipme/encoda}
|
41
|
+
s.rdoc_options = ["--charset=UTF-8"]
|
42
|
+
s.require_paths = ["lib"]
|
43
|
+
s.rubygems_version = %q{1.3.5}
|
44
|
+
s.summary = %q{Encoding converter}
|
45
|
+
s.test_files = [
|
46
|
+
"spec/encoda_spec.rb",
|
47
|
+
"spec/spec_helper.rb"
|
48
|
+
]
|
49
|
+
|
50
|
+
if s.respond_to? :specification_version then
|
51
|
+
current_version = Gem::Specification::CURRENT_SPECIFICATION_VERSION
|
52
|
+
s.specification_version = 3
|
53
|
+
|
54
|
+
if Gem::Version.new(Gem::RubyGemsVersion) >= Gem::Version.new('1.2.0') then
|
55
|
+
s.add_runtime_dependency(%q<chardet>, [">= 0.9.0"])
|
56
|
+
s.add_development_dependency(%q<rspec>, [">= 1.2.9"])
|
57
|
+
else
|
58
|
+
s.add_dependency(%q<chardet>, [">= 0.9.0"])
|
59
|
+
s.add_dependency(%q<rspec>, [">= 1.2.9"])
|
60
|
+
end
|
61
|
+
else
|
62
|
+
s.add_dependency(%q<chardet>, [">= 0.9.0"])
|
63
|
+
s.add_dependency(%q<rspec>, [">= 1.2.9"])
|
64
|
+
end
|
65
|
+
end
|
66
|
+
|
data/lib/encoda.rb
ADDED
@@ -0,0 +1,141 @@
|
|
1
|
+
require 'rubygems'
|
2
|
+
require 'UniversalDetector'
|
3
|
+
require 'iconv'
|
4
|
+
require 'ftools'
|
5
|
+
|
6
|
+
class Encoda
|
7
|
+
|
8
|
+
attr_reader :from_path, :to_path, :from_file, :to_file,
|
9
|
+
:from_encoding, :to_encoding, :failed, :success
|
10
|
+
|
11
|
+
def initialize
|
12
|
+
@from_path = ""
|
13
|
+
@to_path = ""
|
14
|
+
@to_file = ""
|
15
|
+
@to_encoding = "UTF8"
|
16
|
+
@failed = []
|
17
|
+
@success = []
|
18
|
+
end
|
19
|
+
|
20
|
+
def from_path(from_path)
|
21
|
+
@from_path = from_path
|
22
|
+
end
|
23
|
+
|
24
|
+
def from_file(from_file)
|
25
|
+
@from_file = from_file
|
26
|
+
end
|
27
|
+
|
28
|
+
def to_file(to_file)
|
29
|
+
@to_file = to_file
|
30
|
+
end
|
31
|
+
|
32
|
+
def to_path(to_path)
|
33
|
+
@to_path = to_path
|
34
|
+
end
|
35
|
+
|
36
|
+
def to_encoding(to_enc)
|
37
|
+
@to_encoding = to_enc
|
38
|
+
end
|
39
|
+
|
40
|
+
|
41
|
+
def run!
|
42
|
+
#TODO: Add some validation against the attrs
|
43
|
+
process!
|
44
|
+
end
|
45
|
+
|
46
|
+
#DSL API
|
47
|
+
def self.convert(&block)
|
48
|
+
encoda = Encoda.new
|
49
|
+
encoda.instance_eval(&block)
|
50
|
+
encoda.run!
|
51
|
+
encoda
|
52
|
+
end
|
53
|
+
|
54
|
+
#Conventional API
|
55
|
+
def convert(from, to, from_encoding, to_encoding)
|
56
|
+
#TODO
|
57
|
+
end
|
58
|
+
|
59
|
+
private
|
60
|
+
|
61
|
+
def process!
|
62
|
+
puts "convert begins!"
|
63
|
+
check_file_or_dir @to_path
|
64
|
+
if convert_from_path?
|
65
|
+
create_directories
|
66
|
+
unfinished_files.each do |filename|
|
67
|
+
@failed << filename unless convert_file( "#{@from_path}/#{filename}", "#{@to_path}/#{filename}" )
|
68
|
+
end
|
69
|
+
else
|
70
|
+
check_file_or_dir @from_file
|
71
|
+
from_file_basename = File.basename(@from_file)
|
72
|
+
@to_file = "converted_#{from_file_basename}" if @to_file.strip.empty?
|
73
|
+
@failed << @from_file unless convert_file( @from_file, "#{@to_path}/#{File.basename(@to_file)}" )
|
74
|
+
end
|
75
|
+
@success = unfinished_files - @failed
|
76
|
+
puts "convert finished! #{@success.size} files have been converted, #{@failed.size} failed."
|
77
|
+
end
|
78
|
+
|
79
|
+
def convert_from_path?
|
80
|
+
!@from_path.empty? && !@from_path.nil?
|
81
|
+
end
|
82
|
+
|
83
|
+
def create_directories
|
84
|
+
check_file_or_dir @from_path
|
85
|
+
Dir.mkdir @to_path unless File.exist? @to_path
|
86
|
+
end
|
87
|
+
|
88
|
+
def check_file_or_dir(file_or_dir)
|
89
|
+
raise "File or directory: #{file_or_dir} cannot be found!" if ( file_or_dir.nil? || !File.exist?(file_or_dir) )
|
90
|
+
end
|
91
|
+
|
92
|
+
def unfinished_files
|
93
|
+
@unfinished_files ||= unfinished_files!
|
94
|
+
end
|
95
|
+
|
96
|
+
def unfinished_files!
|
97
|
+
orin_files = Dir.glob(File.join(@from_path, "*.srt"))
|
98
|
+
conv_files = Dir.glob(File.join(@to_path, "*.srt"))
|
99
|
+
orin_files.map! { |f| File.basename(f) }
|
100
|
+
conv_files.map! { |f| File.basename(f) }
|
101
|
+
orin_files - conv_files
|
102
|
+
end
|
103
|
+
|
104
|
+
def convert_file(from_file, to_file)
|
105
|
+
File.open(from_file,'r') do |f|
|
106
|
+
if @from_encoding.nil?
|
107
|
+
lines = f.read
|
108
|
+
result = UniversalDetector::chardet(lines[0..1000])
|
109
|
+
@from_encoding = result["encoding"] if result["confidence"] > 0.9
|
110
|
+
puts "Guessing Result: #{result.inspect} of file #{@from_file}"
|
111
|
+
end
|
112
|
+
raise "Not specifying from_encoding" if @from_encoding.strip.empty?
|
113
|
+
|
114
|
+
if @from_encoding.upcase.sub("-","") == @to_encoding.upcase.sub("-","")
|
115
|
+
File.copy(from_file, "#{@to_path}/#{File.basename(from_file)}")
|
116
|
+
return true
|
117
|
+
end
|
118
|
+
|
119
|
+
begin
|
120
|
+
File.open(to_file, 'w') do |cf|
|
121
|
+
begin
|
122
|
+
cf.write Iconv.conv(@to_encoding, @from_encoding, lines)
|
123
|
+
rescue Exception => e
|
124
|
+
cf.write Iconv.conv(@to_encoding, "BIG5", lines)
|
125
|
+
end
|
126
|
+
end
|
127
|
+
rescue Exception => e
|
128
|
+
puts "delete failed file"
|
129
|
+
File.delete(to_file)
|
130
|
+
puts "#{from_file} converted failed. Msg:#{e.message}."
|
131
|
+
return false
|
132
|
+
ensure
|
133
|
+
@from_encoding = nil
|
134
|
+
end
|
135
|
+
|
136
|
+
end
|
137
|
+
true
|
138
|
+
end
|
139
|
+
|
140
|
+
|
141
|
+
end
|
data/spec/encoda_spec.rb
ADDED
@@ -0,0 +1,80 @@
|
|
1
|
+
require File.expand_path(File.dirname(__FILE__) + '/spec_helper')
|
2
|
+
class TempFile
|
3
|
+
#These variable can be set in the before block, however, it won't work with DSL APIs
|
4
|
+
TO_PATH = File.expand_path(File.dirname(__FILE__) + '/test_files/conv_files')
|
5
|
+
FROM_PATH = File.expand_path(File.dirname(__FILE__) + '/test_files/files')
|
6
|
+
FROM_FILE = File.expand_path(File.dirname(__FILE__) + '/test_files/files/nedivx-tbl.gb.srt')
|
7
|
+
UTF8_FILE = File.expand_path(File.dirname(__FILE__) + '/test_files/files/utf8.gb.srt')
|
8
|
+
end
|
9
|
+
describe "Encoda" do
|
10
|
+
|
11
|
+
describe "Providing incorrect info" do
|
12
|
+
it "should raise error when providing from_path cannot be found" do
|
13
|
+
lambda {
|
14
|
+
Encoda.convert do
|
15
|
+
to_path TempFile::TO_PATH
|
16
|
+
from_file 'xxx_1.srt'
|
17
|
+
end
|
18
|
+
}.should raise_error(/xxx_1.srt cannot be found!/)
|
19
|
+
end
|
20
|
+
|
21
|
+
it "should raise error when providing from_path cannot be found" do
|
22
|
+
lambda {
|
23
|
+
Encoda.convert do
|
24
|
+
to_path TempFile::TO_PATH
|
25
|
+
from_path "xxx"
|
26
|
+
end
|
27
|
+
}.should raise_error(/xxx cannot be found!/)
|
28
|
+
end
|
29
|
+
|
30
|
+
it "should raise error when providing from_path cannot be found" do
|
31
|
+
lambda {
|
32
|
+
Encoda.convert do
|
33
|
+
to_path "to_path"
|
34
|
+
end
|
35
|
+
}.should raise_error(/to_path cannot be found!/)
|
36
|
+
end
|
37
|
+
end
|
38
|
+
|
39
|
+
describe "Providing correct info" do
|
40
|
+
|
41
|
+
def conv_files
|
42
|
+
Dir.glob(File.join(TempFile::TO_PATH, "*.srt"))
|
43
|
+
end
|
44
|
+
|
45
|
+
before(:each) do
|
46
|
+
conv_files.each do |f|
|
47
|
+
File.delete(f)
|
48
|
+
end
|
49
|
+
end
|
50
|
+
|
51
|
+
describe "Convert single file" do
|
52
|
+
it "should convert 1 file to default converted folder" do
|
53
|
+
Encoda.convert do
|
54
|
+
from_file TempFile::FROM_FILE
|
55
|
+
to_path TempFile::TO_PATH
|
56
|
+
end
|
57
|
+
conv_files.should have(1).item
|
58
|
+
end
|
59
|
+
it "should bypass the convert and copy the file directly if from_encoding is the same as to_encoding" do
|
60
|
+
Encoda.convert do
|
61
|
+
from_file TempFile::UTF8_FILE
|
62
|
+
to_path TempFile::TO_PATH
|
63
|
+
end
|
64
|
+
conv_files.should have(1).item
|
65
|
+
File.basename(conv_files[0]).should == File.basename(TempFile::UTF8_FILE)
|
66
|
+
end
|
67
|
+
end
|
68
|
+
describe "Convert files under a specific folder" do
|
69
|
+
it "should batch convert files when specifying from_path" do
|
70
|
+
encoda = Encoda.convert do
|
71
|
+
from_path TempFile::FROM_PATH
|
72
|
+
to_path TempFile::TO_PATH
|
73
|
+
end
|
74
|
+
puts encoda.inspect
|
75
|
+
conv_files.should have(encoda.failed.size + encoda.success.size).items
|
76
|
+
end
|
77
|
+
end
|
78
|
+
end
|
79
|
+
|
80
|
+
end
|