Initial import

.gitignore

@@ -0,0 +1,21 @@
+.hg
+.hgignore
+.rbenv-gemsets
+vendor/bundle
+*.gem
+*.rbc
+.bundle
+.config
+.yardoc
+Gemfile.lock
+InstalledFiles
+_yardoc
+coverage
+doc/
+lib/bundler/man
+pkg
+rdoc
+spec/reports
+test/tmp
+test/version_tmp
+tmp

Gemfile

@@ -0,0 +1,3 @@
+source 'https://rubygems.org'
+
+gemspec

LICENSE

@@ -0,0 +1,22 @@
+Copyright (c) 2012 ITO Nobuaki
+
+MIT License
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

README.md

@@ -0,0 +1,65 @@
+# MSWordDoc::Extractor
+
+Extract text contents from Microsoft Word Document
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'msworddoc-extractor', :git =>
+  'git://github.com/dayflower/msworddoc-extractor.git'
+```
+
+And then execute:
+
+    $ bundle install
+
+## Usage
+
+```ruby
+require 'msworddoc-extractor'
+
+doc = MSWordDoc::Extractor.load('sample.doc')
+puts doc.contents   # doc is MSWordDoc::Essence
+# You have to close document explicitly
+doc.close()
+
+# Or call load() with block argument (recommended way)
+MSWordDoc::Extractor.load('sample.doc') do |doc|
+  puts doc.header
+end
+```
+
+### Properties of `MSWordDoc::Essence`
+
+* `document`
+* `header`
+* `footnote`
+* `macro`
+* `annotation`
+* `endnote`
+* `textbox`
+* `header_textbox`
+* `whole_contents`
+
+## Limitations
+
+Only supports Microsoft Word binary document.  
+Does not support Microsoft Word XML document (.docx).
+
+This module does not handle `PAP` (PAragraph Properties) and `CHP` (CHaracter
+Properties), that define paragraphs and characters style.
+Those styling information are required to determine functionalities of
+some of special characters (such as row mark, footnote reference, and etc),
+but are just ignored in the module, so extracted text will be inaccurate.
+
+Also this module does not handle summary information stream in Word file.
+
+## Contributing
+
+1. Fork it
+2. Create your feature branch (`git checkout -b my-new-feature`)
+3. Commit your changes (`git commit -am 'Added some feature'`)
+4. Push to the branch (`git push origin my-new-feature`)
+5. Create new Pull Request

Rakefile

@@ -0,0 +1,8 @@
+#!/usr/bin/env rake
+require 'bundler/gem_tasks'
+require 'rake/testtask'
+
+Rake::TestTask.new do |test|
+  test.libs << 'test'
+  test.test_files = Dir[ 'test/test_*.rb' ]
+end

bin/worddoc-extract

@@ -0,0 +1,48 @@
+#!/usr/bin/env ruby
+
+require 'optparse'
+require 'msworddoc-extractor'
+
+def app(*argv)
+  actions = []
+
+  options = [
+    [ '-d', '--document',   'Main contents (default)', :document       ],
+    [ '-w', '--whole',      'Whole text contents',     :whole_contents ],
+    [ '-i', '--header',     'Header parts',            :header         ],
+    [ '-f', '--footnote',   'Footnotes',               :footnote       ],
+    [ '-e', '--endnote',    'Endnotes',                :endnote        ],
+    [ '-a', '--annotation', 'Annotations',             :annotatation   ],
+    [ '-t', '--textbox',    'Text boxes',              :textbox        ],
+    [       '--header_textbox', 'Header text boxes',   :header_textbox ],
+    [ '-m', '--macro',      'Macro part',              :marco          ],
+  ]
+
+  optparse = OptionParser.new do |opt|
+    opt.banner = 'Usage: worddoc-extract [options] <files> ...'
+
+    options.each do |o|
+      action = o.pop
+      opt.on(*o) { actions << action }
+    end
+
+    opt.separator ''
+    opt.on('-h', '--help', 'Show this help') { puts opt; exit }
+  end
+
+  if actions.empty?
+    actions = [ :document ]
+  end
+
+  files = optparse.parse(argv)
+
+  files.each do |file|
+    doc = MSWordDoc::Extractor.load_file(file)
+    actions.each do |action|
+      puts doc.send(action)
+    end
+  end
+end
+
+app(*ARGV)
+

lib/msworddoc-extractor.rb

@@ -0,0 +1 @@
+require File.expand_path('../msworddoc/extractor', __FILE__)