mht 0.0.0

Sign up to get free protection for your applications and to get access to all the features.
@@ -0,0 +1,5 @@
1
+ lib/**/*.rb
2
+ bin/*
3
+ -
4
+ features/**/*.feature
5
+ LICENSE.txt
data/Gemfile ADDED
@@ -0,0 +1,14 @@
1
+ source "http://rubygems.org"
2
+ # Add dependencies required to use your gem here.
3
+ # Example:
4
+ # gem "activesupport", ">= 2.3.5"
5
+
6
+ # Add dependencies to develop your gem here.
7
+ # Include everything needed to run rake, tests, features, etc.
8
+ group :development do
9
+ gem "shoulda", ">= 0"
10
+ gem "bundler", "~> 1.0.0"
11
+ gem "jeweler", "~> 1.6.0"
12
+ gem "rcov", ">= 0"
13
+ gem "nokogiri", ">= 0"
14
+ end
@@ -0,0 +1,22 @@
1
+ GEM
2
+ remote: http://rubygems.org/
3
+ specs:
4
+ git (1.2.5)
5
+ jeweler (1.6.0)
6
+ bundler (~> 1.0.0)
7
+ git (>= 1.2.5)
8
+ rake
9
+ nokogiri (1.4.4)
10
+ rake (0.8.7)
11
+ rcov (0.9.9)
12
+ shoulda (2.11.3)
13
+
14
+ PLATFORMS
15
+ ruby
16
+
17
+ DEPENDENCIES
18
+ bundler (~> 1.0.0)
19
+ jeweler (~> 1.6.0)
20
+ nokogiri
21
+ rcov
22
+ shoulda
@@ -0,0 +1,20 @@
1
+ Copyright (c) 2011 takuya
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.
@@ -0,0 +1,21 @@
1
+ = mht
2
+
3
+ mht is for building mhtml.
4
+ mht is known as mhtml that internet explorer's web page archive.
5
+ this package can make mhtml from URI
6
+
7
+ == Contributing to mht
8
+
9
+ * Check out the latest master to make sure the feature hasn't been implemented or the bug hasn't been fixed yet
10
+ * Check out the issue tracker to make sure someone already hasn't requested it and/or contributed it
11
+ * Fork the project
12
+ * Start a feature/bugfix branch
13
+ * Commit and push until you are happy with your contribution
14
+ * Make sure to add tests for it. This is important so I don't break it in a future version unintentionally.
15
+ * Please try not to mess with the Rakefile, version, or history. If you want to have your own version, or is otherwise necessary, that is fine, but please isolate to its own commit so I can cherry-pick around it.
16
+
17
+ == Copyright
18
+
19
+ Copyright (c) 2011 takuya. See LICENSE.txt for
20
+ further details.
21
+
@@ -0,0 +1,54 @@
1
+ # encoding: utf-8
2
+
3
+ require 'rubygems'
4
+ require 'bundler'
5
+ begin
6
+ Bundler.setup(:default, :development)
7
+ rescue Bundler::BundlerError => e
8
+ $stderr.puts e.message
9
+ $stderr.puts "Run `bundle install` to install missing gems"
10
+ exit e.status_code
11
+ end
12
+ require 'rake'
13
+
14
+ require 'jeweler'
15
+ Jeweler::Tasks.new do |gem|
16
+ # gem is a Gem::Specification... see http://docs.rubygems.org/read/chapter/20 for more options
17
+ gem.name = "mht"
18
+ gem.homepage = "http://github.com/takuya/mht"
19
+ gem.license = "MIT"
20
+ gem.summary = %Q{mht is builder of mhtml file}
21
+ gem.description = %Q{mht is builder of mhtml file}
22
+ gem.email = "takuya.1st@gmail"
23
+ gem.authors = ["takuya"]
24
+ # dependencies defined in Gemfile
25
+ end
26
+ Jeweler::RubygemsDotOrgTasks.new
27
+
28
+ require 'rake/testtask'
29
+ Rake::TestTask.new(:test) do |test|
30
+ test.libs << 'lib' << 'test'
31
+ test.pattern = 'test/**/test_*.rb'
32
+ test.verbose = true
33
+ end
34
+
35
+ require 'rcov/rcovtask'
36
+ Rcov::RcovTask.new do |test|
37
+ test.libs << 'test'
38
+ test.pattern = 'test/**/test_*.rb'
39
+ test.verbose = true
40
+ test.rcov_opts << '--exclude "gems/*"'
41
+ end
42
+
43
+ task :default => :test
44
+
45
+ require 'rake/rdoctask'
46
+ Rake::RDocTask.new do |rdoc|
47
+ version = File.exist?('VERSION') ? File.read('VERSION') : ""
48
+ rdoc.options << '-c UTF8'
49
+
50
+ rdoc.rdoc_dir = 'rdoc'
51
+ rdoc.title = "mht #{version}"
52
+ rdoc.rdoc_files.include('README*')
53
+ rdoc.rdoc_files.include('lib/**/*.rb')
54
+ end
data/VERSION ADDED
@@ -0,0 +1 @@
1
+ 0.0.0
@@ -0,0 +1,124 @@
1
+ # generate mhtml file
2
+ # == uri target uri
3
+ # return mhtml file
4
+ # mhtml = Mhtml.generate(uri)
5
+ # open("output.mht", "w+"){|f| f.write mhtml }
6
+ module MHT
7
+ require 'nokogiri'
8
+ require 'open-uri'
9
+ require 'digest/md5'
10
+ require 'stringio'
11
+ require 'thread'
12
+
13
+ def generate(uri)
14
+ generateror = Mhtml.new
15
+ return generateror.convert(uri)
16
+ end
17
+ class Mhtml
18
+
19
+ def initialize
20
+ @contents = {}
21
+ @mail = TMail::Mail.new
22
+ @src = StringIO.new
23
+ @boundary = "mimepart_#{Digest::MD5.hexdigest(Time.now.to_s)}"
24
+ @threads =[]
25
+ @queue = Queue.new
26
+ end
27
+ def convert(filename_or_uri)
28
+ f = open(filename_or_uri)
29
+ html = f.read
30
+ @parser = Nokogiri::HTML html
31
+ @src.puts "Subject: " + @parser.search("title").text()
32
+ @src.puts "Content-Type: multipart/related; boundary=#{@boundary}"
33
+ @src.puts "Content-Location: #{filename_or_uri}"
34
+ @src.puts "Date: #{Time.now.to_s}"
35
+ @src.puts "MIME-Version: 1.0"
36
+ @src.puts ""
37
+ @src.puts "mime mhtml content"
38
+ @src.puts ""
39
+ #imgs
40
+ @parser.search('img').each{|i|
41
+ uri = i.attr('src');
42
+ uri = URI::join( filename_or_uri, uri).to_s
43
+ uid = Digest::MD5.hexdigest(uri)
44
+ @contents[uid] = uri
45
+ i.set_attribute('src',"cid:#{uid}")
46
+ }
47
+ #styles
48
+ @parser.search('link[rel=stylesheet]').each{|i|
49
+ uri = i.attr('href');
50
+ uri = URI::join( filename_or_uri, uri).to_s
51
+ uid = Digest::MD5.hexdigest(uri)
52
+ @contents[uid] = uri
53
+ i.set_attribute('href',"cid:#{uid}")
54
+ }
55
+ #scripts
56
+ @parser.search('script').map{ |i|
57
+ next unless i.attr('src');
58
+ uri = i.attr('src');
59
+ uri = URI::join( filename_or_uri, uri).to_s
60
+ uid = Digest::MD5.hexdigest(uri)
61
+ @contents[uid] = uri
62
+ i.set_attribute('src',"cid:#{uid}")
63
+ }
64
+ @src.puts "--#{@boundary}"
65
+ @src.puts "Content-Disposition: inline; filename=default.htm"
66
+ @src.puts "Content-Type: #{f.meta['content-type']}"
67
+ @src.puts "Content-Id: #{Digest::MD5.hexdigest(filename_or_uri)}"
68
+ @src.puts "Content-Location: #{filename_or_uri}"
69
+ #@src.puts "Content-Transfer-Encoding: 8bit"
70
+ @src.puts "Content-Transfer-Encoding: Base64"
71
+ @src.puts ""
72
+ #@src.puts html
73
+ @src.puts "#{Base64.encode64(html)}"
74
+ @src.puts ""
75
+ self.attach_contents
76
+ @src.puts "--#{@boundary}--"
77
+ @src.rewind
78
+ return @src.read
79
+ end
80
+ private
81
+ def start_download_thread(num=5)
82
+ num.times{
83
+ t = Thread.start{
84
+ while(@queue.empty? == false)
85
+ k = @queue.pop
86
+ v = @contents[k]
87
+ next if v.class == Hash
88
+ f = open(v)
89
+ meta = f.meta
90
+ @contents[k] = { :body=>f.read, :uri=> v, :content_type=> f.meta["content-type"] }
91
+ end
92
+ }
93
+ @threads.push t
94
+ }
95
+ return @threads
96
+ end
97
+ def download_finished?
98
+ @contents.find{|k,v| v.class != Hash } == nil
99
+ end
100
+ def attach_contents
101
+ #prepeare_queue
102
+ @contents.each{|k,v| @queue.push k}
103
+ #start download threads
104
+ self.start_download_thread
105
+ # wait
106
+ @threads.each{|t|t.join}
107
+ @contents.each{|k,v|self.add_html_content(k)}
108
+ end
109
+ def add_html_content(cid)
110
+ filename = File.basename(URI(@contents[cid][:uri]).path)
111
+ @src.puts "--#{@boundary}"
112
+ @src.puts "Content-Disposition: inline; filename=" + filename
113
+ @src.puts "Content-Type: #{@contents[cid][:content_type]}"
114
+ @src.puts "Content-Location: #{@contents[cid][:uri]}"
115
+ @src.puts "Content-Transfer-Encoding: Base64"
116
+ @src.puts "Content-Id: #{cid}"
117
+ @src.puts ""
118
+ @src.puts "#{Base64.encode64(@contents[cid][:body])}"
119
+ @src.puts ""
120
+ return
121
+ end
122
+ end
123
+
124
+ end
@@ -0,0 +1,18 @@
1
+ require 'rubygems'
2
+ require 'bundler'
3
+ begin
4
+ Bundler.setup(:default, :development)
5
+ rescue Bundler::BundlerError => e
6
+ $stderr.puts e.message
7
+ $stderr.puts "Run `bundle install` to install missing gems"
8
+ exit e.status_code
9
+ end
10
+ require 'test/unit'
11
+ require 'shoulda'
12
+
13
+ $LOAD_PATH.unshift(File.join(File.dirname(__FILE__), '..', 'lib'))
14
+ $LOAD_PATH.unshift(File.dirname(__FILE__))
15
+ require 'mht'
16
+
17
+ class Test::Unit::TestCase
18
+ end
@@ -0,0 +1,7 @@
1
+ require 'helper'
2
+
3
+ class TestMht < Test::Unit::TestCase
4
+ should "probably rename this file and start testing for real" do
5
+ flunk "hey buddy, you should probably rename this file and start testing for real"
6
+ end
7
+ end
metadata ADDED
@@ -0,0 +1,150 @@
1
+ --- !ruby/object:Gem::Specification
2
+ name: mht
3
+ version: !ruby/object:Gem::Version
4
+ hash: 31
5
+ prerelease:
6
+ segments:
7
+ - 0
8
+ - 0
9
+ - 0
10
+ version: 0.0.0
11
+ platform: ruby
12
+ authors:
13
+ - takuya
14
+ autorequire:
15
+ bindir: bin
16
+ cert_chain: []
17
+
18
+ date: 2011-06-10 00:00:00 +09:00
19
+ default_executable:
20
+ dependencies:
21
+ - !ruby/object:Gem::Dependency
22
+ prerelease: false
23
+ type: :development
24
+ requirement: &id001 !ruby/object:Gem::Requirement
25
+ none: false
26
+ requirements:
27
+ - - ">="
28
+ - !ruby/object:Gem::Version
29
+ hash: 3
30
+ segments:
31
+ - 0
32
+ version: "0"
33
+ name: shoulda
34
+ version_requirements: *id001
35
+ - !ruby/object:Gem::Dependency
36
+ prerelease: false
37
+ type: :development
38
+ requirement: &id002 !ruby/object:Gem::Requirement
39
+ none: false
40
+ requirements:
41
+ - - ~>
42
+ - !ruby/object:Gem::Version
43
+ hash: 23
44
+ segments:
45
+ - 1
46
+ - 0
47
+ - 0
48
+ version: 1.0.0
49
+ name: bundler
50
+ version_requirements: *id002
51
+ - !ruby/object:Gem::Dependency
52
+ prerelease: false
53
+ type: :development
54
+ requirement: &id003 !ruby/object:Gem::Requirement
55
+ none: false
56
+ requirements:
57
+ - - ~>
58
+ - !ruby/object:Gem::Version
59
+ hash: 15
60
+ segments:
61
+ - 1
62
+ - 6
63
+ - 0
64
+ version: 1.6.0
65
+ name: jeweler
66
+ version_requirements: *id003
67
+ - !ruby/object:Gem::Dependency
68
+ prerelease: false
69
+ type: :development
70
+ requirement: &id004 !ruby/object:Gem::Requirement
71
+ none: false
72
+ requirements:
73
+ - - ">="
74
+ - !ruby/object:Gem::Version
75
+ hash: 3
76
+ segments:
77
+ - 0
78
+ version: "0"
79
+ name: rcov
80
+ version_requirements: *id004
81
+ - !ruby/object:Gem::Dependency
82
+ prerelease: false
83
+ type: :development
84
+ requirement: &id005 !ruby/object:Gem::Requirement
85
+ none: false
86
+ requirements:
87
+ - - ">="
88
+ - !ruby/object:Gem::Version
89
+ hash: 3
90
+ segments:
91
+ - 0
92
+ version: "0"
93
+ name: nokogiri
94
+ version_requirements: *id005
95
+ description: mht is builder of mhtml file
96
+ email: takuya.1st@gmail
97
+ executables: []
98
+
99
+ extensions: []
100
+
101
+ extra_rdoc_files:
102
+ - LICENSE.txt
103
+ - README.rdoc
104
+ files:
105
+ - .document
106
+ - Gemfile
107
+ - Gemfile.lock
108
+ - LICENSE.txt
109
+ - README.rdoc
110
+ - Rakefile
111
+ - VERSION
112
+ - lib/mht.rb
113
+ - test/helper.rb
114
+ - test/test_mht.rb
115
+ has_rdoc: true
116
+ homepage: http://github.com/takuya/mht
117
+ licenses:
118
+ - MIT
119
+ post_install_message:
120
+ rdoc_options: []
121
+
122
+ require_paths:
123
+ - lib
124
+ required_ruby_version: !ruby/object:Gem::Requirement
125
+ none: false
126
+ requirements:
127
+ - - ">="
128
+ - !ruby/object:Gem::Version
129
+ hash: 3
130
+ segments:
131
+ - 0
132
+ version: "0"
133
+ required_rubygems_version: !ruby/object:Gem::Requirement
134
+ none: false
135
+ requirements:
136
+ - - ">="
137
+ - !ruby/object:Gem::Version
138
+ hash: 3
139
+ segments:
140
+ - 0
141
+ version: "0"
142
+ requirements: []
143
+
144
+ rubyforge_project:
145
+ rubygems_version: 1.5.0
146
+ signing_key:
147
+ specification_version: 3
148
+ summary: mht is builder of mhtml file
149
+ test_files: []
150
+