delta_attack 0.1.4

data/ChangeLog

@@ -0,0 +1,4 @@
+== 0.0.1 / 2008-09-12
+
+* initial release
+

data/NOTICE

@@ -0,0 +1,5 @@
+This library depends on Apache POI libraries,
+which is provided as Apache Licence version 2.
+
+http://poi.apache.org/
+

data/README

@@ -0,0 +1,50 @@
+
+= delta_attack
+
+
+== Description
+
+Extract MS Office files to plain text.
+
+== Installation
+
+
+=== Archive Installation
+
+ $ rake install
+
+=== Gem Installation
+
+ $ gem source -a http://gems.github.com
+ $ gem install moro-delta-attack
+
+== Features/Problems
+
+Extract MS Office files to plain text usin Apache POI and JRuby.
+It works with Client/Server architecture.
+
+The extract server is works on JRuby but the client is works with
+both cRuby and JRuby.
+
+This library originally aim to index Office documents to fulltext 
+serach engine.
+
+== Synopsis
+
+first you start DeltaAttackServer, which needs JRuby and Apache POI
+
+ $ export CLASSPATH=path/to/poi-3.1-FINAL/poi-3.1-FINAL-20080629.jar:\
+                    path/to/poi-3.1-FINAL/poi-scratchpad-3.1-FINAL-20080629.jar
+ $ jruby bin/delta_attack_server
+
+Then you can use DeltaAttack::Client, in both CRuby(MRI) and JRuby.
+
+ require 'delta_attack/client'
+ DeletaAttack::Client.cast("path/to/some.xls")
+
+== Copyright
+
+Author::    moro <moronatural@gmail.com>
+Copyright:: Copyright (c) 2008 moro
+License::   MIT
+

data/Rakefile

@@ -0,0 +1,139 @@
+require 'rubygems'
+require 'rake'
+require 'rake/clean'
+require 'rake/testtask'
+require 'rake/packagetask'
+require 'rake/gempackagetask'
+require 'rake/rdoctask'
+require 'rake/contrib/rubyforgepublisher'
+require 'rake/contrib/sshpublisher'
+require 'lib/delta_attack'
+require 'spec/rake/spectask'
+require 'fileutils'
+include FileUtils
+
+NAME              = "delta_attack"
+AUTHOR            = "MOROHASHI Kyosuke"
+EMAIL             = "moronatural@gmail.com"
+DESCRIPTION       = "extract text from MS Office document with Apache POI"
+# RUBYFORGE_PROJECT = "delta_attack"
+HOMEPATH          = "http://github.com/moro/delta_attack"
+BIN_FILES         = %w( delta_attack_server )
+VERS              = DeltaAttack::VERSION
+
+
+REV = File.read(".svn/entries")[/committed-rev="(d+)"/, 1] rescue nil
+CLEAN.include ['**/.*.sw?', '*.gem', '.config']
+RDOC_OPTS = [
+  '--title', "#{NAME} documentation",
+  "--charset", "utf-8",
+  "--opname", "index.html",
+  "--line-numbers",
+  "--main", "README",
+  "--inline-source",
+]
+
+task :default => [:spec]
+task :package => [:clean]
+
+Spec::Rake::SpecTask.new("spec") do |t|
+  t.libs   << "spec"
+  t.pattern = "spec/**/*_spec.rb"
+  t.verbose = true
+end
+
+spec = Gem::Specification.new do |s|
+  s.name              = NAME
+  s.version           = VERS
+  s.platform          = Gem::Platform::RUBY
+  s.has_rdoc          = true
+  s.extra_rdoc_files  = ["README", "ChangeLog"]
+  s.rdoc_options     += RDOC_OPTS + ['--exclude', '^(examples|extras)/']
+  s.summary           = DESCRIPTION
+  s.description       = DESCRIPTION
+  s.author            = AUTHOR
+  s.email             = EMAIL
+  s.homepage          = HOMEPATH
+  s.executables       = BIN_FILES
+# s.rubyforge_project = RUBYFORGE_PROJECT
+  s.bindir            = "bin"
+  s.require_path      = "lib"
+  s.test_files        = Dir["spec/*_test.rb"]
+
+  #s.add_dependency('activesupport', '>=1.3.1')
+  #s.required_ruby_version = '>= 1.8.2'
+
+  s.files = %w(README NOTICE ChangeLog Rakefile) +
+    Dir.glob("{bin,doc,spec,lib,templates,generator,extras,website,script}/**/*") +
+    Dir.glob("tools/*.rb") -
+    Dir.glob("lib/vendor/**/*") +
+    Dir.glob("lib/vendor/README")
+
+  s.extensions = FileList["ext/**/extconf.rb"].to_a
+end
+
+Rake::GemPackageTask.new(spec) do |p|
+  p.need_tar = true
+  p.gem_spec = spec
+end
+
+task :debug_gem do |p|
+  puts spec.to_ruby
+end
+
+task :install do
+  name = "#{NAME}-#{VERS}.gem"
+  sh %{rake package}
+  sh %{sudo gem install pkg/#{name}}
+end
+
+task :uninstall => [:clean] do
+  sh %{sudo gem uninstall #{NAME}}
+end
+
+
+Rake::RDocTask.new do |rdoc|
+  rdoc.rdoc_dir = 'html'
+  rdoc.options += RDOC_OPTS
+  rdoc.template = "resh"
+  #rdoc.template = "#{ENV['template']}.rb" if ENV['template']
+  if ENV['DOC_FILES']
+    rdoc.rdoc_files.include(ENV['DOC_FILES'].split(/,\s*/))
+  else
+    rdoc.rdoc_files.include('README', 'ChangeLog')
+    rdoc.rdoc_files.include('lib/**/*.rb')
+    rdoc.rdoc_files.include('ext/**/*.c')
+  end
+end
+=begin
+desc "Publish to RubyForge"
+task :rubyforge => [:rdoc, :package] do
+  require 'rubyforge'
+  Rake::RubyForgePublisher.new(RUBYFORGE_PROJECT, 'moro').upload
+end
+
+desc 'Package and upload the release to rubyforge.'
+task :release => [:clean, :package] do |t|
+  v = ENV["VERSION"] or abort "Must supply VERSION=x.y.z"
+  abort "Versions don't match #{v} vs #{VERS}" unless v == VERS
+  pkg = "pkg/#{NAME}-#{VERS}"
+
+  require 'rubyforge'
+  rf = RubyForge.new
+  puts "Logging in"
+  rf.login
+
+  c = rf.userconfig
+# c["release_notes"] = description if description
+# c["release_changes"] = changes if changes
+  c["preformatted"] = true
+
+  files = [
+    "#{pkg}.tgz",
+    "#{pkg}.gem"
+  ].compact
+
+  puts "Releasing #{NAME} v. #{VERS}"
+  rf.add_release RUBYFORGE_PROJECT, NAME, VERS, *files
+end
+=end

data/bin/delta_attack_server

@@ -0,0 +1,66 @@
+#!/usr/bin/env jruby
+# vim:set fileencoding=utf-8 filetype=ruby
+$KCODE = 'u'
+
+require "optparse"
+require "rbconfig"
+require "delta_attack"
+
+module DeltaAttack
+  class Server
+
+    DEFAULT_OPTION = {
+      :port => 3333,
+      :mount => "/extract",
+    }.freeze
+
+    def self.run(argv)
+      if RbConfig::CONFIG["arch"] =~ /java/i
+        new(argv.dup).run
+      else
+        exec(*["jruby", $0, *argv])
+      end
+    end
+
+    def initialize(argv)
+      @argv = argv
+      @options = DEFAULT_OPTION.dup
+
+      @parser = OptionParser.new do |parser|
+        parser.banner = <<-EOB.gsub(/^\t+/, "")
+          Usage: #$0 [options]
+        EOB
+
+        parser.separator "Options:"
+        parser.on("-p", "--port=PORT", Integer, "specify port default: #{DEFAULT_OPTION[:port]}") do |v|
+          @options[:port] = v
+        end
+        parser.on("-m", "--mount=PATH", String, "mount path of extract servlet #{DEFAULT_OPTION[:mount].dump}") do |v|
+          @options[:mount] = v
+        end
+
+        parser.separator ""
+
+        parser.on("--version", "Show version string `#{VERSION}'") do
+          puts VERSION
+          exit
+        end
+      end
+    end
+
+    def run
+		  @parser.order!(@argv)
+      require 'webrick/httpserver'
+      require 'delta_attack/extractor'
+      require 'delta_attack/extractor/servlet'
+
+      @server = WEBrick::HTTPServer.new(:Port=>@options[:port])
+      @server.mount(@options[:mount], DeltaAttack::Extractor::Servlet)
+      trap("INT"){ @server.shutdown }
+      @server.start
+    end
+  end
+end
+
+DeltaAttack::Server.run(ARGV)
+

data/lib/delta_attack.rb

@@ -0,0 +1,5 @@
+
+module DeltaAttack
+  VERSION = "0.1.3"
+end
+

data/lib/delta_attack/client.rb

@@ -0,0 +1,65 @@
+
+require 'net/http'
+require 'delta_attack/filetype_assumption'
+require 'securerandom'
+
+module DeltaAttack
+  class Client
+    class << self
+      def cast(filename, content_type = nil, host="localhost", port=3333)
+        cast_buf(nil, filename, content_type, host, port)
+      end
+      alias extract cast
+
+      def cast_buf(content, filename = "no-filename", content_type = nil, host="localhost", port=3333)
+        begin
+          client = new(filename, content)
+          client.content_type = content_type
+          res = Net::HTTP.start(host, port){|http| http.request(client.request) }
+          raise "Request failed #{res}" unless res.is_a? Net::HTTPOK
+          res.body
+        rescue Errno::ECONNREFUSED => e
+          raise "DeltaAttack Server is down on http://#{host}:#{port}"
+        end
+      end
+      alias extract_buf cast_buf
+    end
+
+    attr_writer :content_type
+
+    def initialize(filename, content=nil)
+      @filename = filename
+      @content = content
+    end
+
+    def boundary
+      @boundary ||= Digest::SHA1.hexdigest(File.read(__FILE__))[0,8]
+    end
+
+    def content
+      @content ||= File.open(@filename,"rb"){|f| f.read }
+    end
+
+    def content_type
+      @content_type ||= FiletypeAssumption.new(File.basename(@filename)).content_type
+    end
+
+    def body
+      data = ''
+      data << "--#{boundary}\r\n"
+      data << "Content-Disposition: form-data; name=\"file\"; filename=\"#{@filename}\"\r\n"
+      data << "Content-Type: #{content_type}\r\n\r\n"
+      data << content
+      data << "\r\n--#{boundary}--\r\n"
+    end
+
+    def request(path = "/extract" )
+      req = Net::HTTP::Post.new(path)
+      req.content_type = "multipart/form-data; boundary=#{boundary}"
+      req.body = body
+      req.content_length = req.body.size
+      req
+    end
+  end
+end
+

data/lib/delta_attack/extractor.rb

@@ -0,0 +1,21 @@
+require 'delta_attack/extractor/base'
+require 'delta_attack/extractor/word'
+require 'delta_attack/extractor/excel'
+require 'delta_attack/extractor/power_point'
+
+module DeltaAttack
+  module Extractor
+    Error = Class.new(RuntimeError)
+    def extract(content,type)
+      extractor = case type
+                  when :word then Word
+                  when :excel then Excel
+                  when :power_point then PowerPoint
+                  else raise Error.new("not supported")
+                  end
+
+      extractor.new(content.to_java_bytes).data.flatten.join("\n")
+    end
+    module_function :extract
+  end
+end

data/lib/delta_attack/extractor/base.rb

@@ -0,0 +1,23 @@
+require 'java'
+
+module DeltaAttack
+  module Extractor
+    class Base
+      attr_accessor :bytes
+      def initialize(bytes)
+        @bytes = bytes
+      end
+
+      def data(ignore_cache=false)
+        return @data if (!ignore_cache) && @data
+
+        @data = extract_data
+      end
+
+      private
+      def java_input_stream
+        Java::JavaIo::ByteArrayInputStream.new(@bytes)
+      end
+    end
+  end
+end

data/lib/delta_attack/extractor/excel.rb

@@ -0,0 +1,41 @@
+require 'delta_attack/extractor/base'
+
+include_class 'org.apache.poi.hssf.usermodel.HSSFWorkbook'
+include_class 'org.apache.poi.hssf.usermodel.HSSFCell'
+
+module DeltaAttack
+  module Extractor
+    class Excel < Base
+      private
+      def extract_data
+        input_stream = java_input_stream
+        begin
+          book = HSSFWorkbook.new(input_stream)
+          return (0...book.number_of_sheets).map do |i|
+            extract_sheet(book.sheet_at(i))
+          end
+        ensure
+          input_stream.close
+        end
+      end
+
+      def extract_sheet(sheet)
+        sheet.iterator.map do |row|
+          row.iterator.map{|cell| handle_cell(cell) }
+        end
+      end
+
+      def handle_cell(cell)
+        case cell.cell_type
+        when HSSFCell::CELL_TYPE_NUMERIC
+          cell.numeric_cell_value
+        when HSSFCell::CELL_TYPE_STRING
+          cell.rich_string_cell_value.string
+        when HSSFCell::CELL_TYPE_BOOLEAN, HSSFCell::CELL_TYPE_BLANK
+          nil
+        end
+      end
+    end
+  end
+end
+

data/lib/delta_attack/extractor/power_point.rb

@@ -0,0 +1,20 @@
+require 'delta_attack/extractor/base'
+
+include_class 'org.apache.poi.hslf.usermodel.SlideShow'
+
+module DeltaAttack
+  module Extractor
+    class PowerPoint < Base
+      private
+      def extract_data
+        input_stream = java_input_stream
+        begin
+          slide_show = SlideShow.new(input_stream)
+          slide_show.slides.map do |slide|
+            slide.text_runs.map{|tr| tr.text }
+          end
+        end
+      end
+    end
+  end
+end

data/lib/delta_attack/extractor/servlet.rb

@@ -0,0 +1,37 @@
+require 'webrick/httpservlet'
+require 'delta_attack/extractor'
+require 'delta_attack/filetype_assumption'
+
+module DeltaAttack
+  module Extractor
+    class Servlet < WEBrick::HTTPServlet::AbstractServlet
+      def do_GET(req, res)
+        res.body = <<-HTML
+<html>
+  <head></head>
+  <body>
+    <form action="/extract" enctype="multipart/form-data" method="post">
+      <input type="file" name="file" />
+      <input type="submit" name="submit" value="up" />
+    </form>
+  </body>
+</html>
+        HTML
+      end
+
+      def do_POST(req, res)
+        f = req.query["file"]
+        type = FiletypeAssumption.new(f.filename, f['content-type'])
+        begin
+          res.body = Extractor.extract(f.to_s, type.filetype)
+          res.content_type = "text/plain"
+        rescue Extractor::Error => exe
+          raise WEBrick::HTTPStatus::BadRequest, exe.message
+        rescue StandardError => stdex
+          raise WEBrick::HTTPStatus::InternalServerError, stdex.message
+        end
+      end
+    end
+  end
+end
+

data/lib/delta_attack/extractor/word.rb

@@ -0,0 +1,25 @@
+require 'delta_attack/extractor/base'
+
+include_class 'org.apache.poi.hwpf.HWPFDocument'
+
+module DeltaAttack
+  module Extractor
+    class Word < Base
+
+      private
+      def extract_data
+        input_stream = java_input_stream
+        begin
+          book = HWPFDocument.new(input_stream)
+          range = book.range
+          (0...range.num_paragraphs).map do |i|
+            range.paragraph(i).text.strip
+          end
+        ensure
+          input_stream.close
+        end
+      end
+    end
+  end
+end
+

data/lib/delta_attack/filetype_assumption.rb

@@ -0,0 +1,46 @@
+begin
+  require 'mahoro'
+rescue LoadError
+  nil
+end
+
+module DeltaAttack
+  class FiletypeAssumption
+    CONTENT_TYPES = {
+      "application/msword" => :word,
+      "application/vnd.ms-excel" => :excel,
+      "application/vnd.ms-powerpoint" => :power_point,
+    }.freeze
+
+    def self.support_magic?
+      defined? Mahoro
+    end
+
+    def initialize(filename, content_type = nil, content = nil)
+      @filename = filename
+      @content_type = content_type
+      @content = content
+    end
+
+    def filetype
+      by_content_type || by_extention || :unknown
+    end
+
+    def content_type
+      CONTENT_TYPES.index(filetype)
+    end
+
+    private
+    def by_content_type
+      CONTENT_TYPES[@content_type]
+    end
+
+    def by_extention
+      case File.extname(@filename).downcase
+      when ".doc" then :word
+      when ".xls" then :excel
+      when ".ppt" then :power_point
+      end
+    end
+  end
+end

data/lib/vendor/README

@@ -0,0 +1,8 @@
+Download POI from <http://poi.apache.org/> version =< 3.1
+
+and symlink here poi-current.jar
+
+example, 
+
+ $ ls -l lib/vendor/
+ lrwxr-xr-x  1 you  us   40 Sep 12 09:54 poi-current.jar -> poi-3.1-FINAL/poi-3.1-FINAL-20080629.jar

data/spec/extractor/excel_spec.rb

@@ -0,0 +1,23 @@
+require File.expand_path("../spec_helper", File.dirname(__FILE__))
+require 'delta_attack/extractor/excel'
+require 'java'
+require 'timeout'
+
+describe DeltaAttack::Extractor::Excel do
+  include SpecHelper
+  before do
+    content = File.read(sample_data("13TOKYO.xls"))
+    @xls = DeltaAttack::Extractor::Excel.new(content.to_java_bytes)
+  end
+
+  it { @xls.bytes.should_not be_nil }
+  it "data[0][0].should == 13101" do
+    @xls.data[0][0][0].should == 13101
+  end
+
+  it "2nd call of data() should be cached" do
+    @xls.data # 1st.
+    lambda{ timeout(0.1){ @xls.data } }.should_not raise_error(Timeout::Error)
+  end
+end
+

data/spec/extractor/power_point_spec.rb

@@ -0,0 +1,23 @@
+require File.expand_path("../spec_helper", File.dirname(__FILE__))
+require 'delta_attack/extractor/power_point'
+require 'java'
+require 'timeout'
+
+describe DeltaAttack::Extractor::PowerPoint do
+  include SpecHelper
+  before do
+    content = File.read(sample_data("named_scope06.ppt"))
+    @ppt = DeltaAttack::Extractor::PowerPoint.new(content.to_java_bytes)
+  end
+
+  it { @ppt.bytes.should_not be_nil }
+  it "data.flatten.first.should == /named_scope/" do
+    @ppt.data.flatten.first.should =~ /named_scope/
+  end
+
+  it "2nd call of data() should be cached" do
+    @ppt.data # 1st.
+    lambda{ timeout(0.1){ @ppt.data } }.should_not raise_error(Timeout::Error)
+  end
+end
+

data/spec/extractor/servlet_spec.rb

@@ -0,0 +1,54 @@
+require File.expand_path("../spec_helper", File.dirname(__FILE__))
+require 'delta_attack/extractor/servlet'
+
+describe DeltaAttack::Extractor::Servlet do
+  before do
+    @servlet = DeltaAttack::Extractor::Servlet.new("hoge", {})
+
+    file = mock("upload_file")
+    file.should_receive(:filename).and_return("foo.xls")
+    file.should_receive(:[]).with("content-type").and_return("application/vnd.ms-excel")
+    file.should_receive(:to_s).and_return("DATA-DATA")
+
+    @req = mock("request")
+    @req.should_receive(:query).and_return("file"=>file)
+
+    @res = Struct.new(:body, :content_type, :status).new
+  end
+
+  describe "pass" do
+    before do
+      DeltaAttack::Extractor.should_receive(:extract).with("DATA-DATA", :excel).and_return("RESPONSE")
+      @servlet.do_POST(@req, @res)
+    end
+
+    it "@res.body.should == 'RESPONSE'" do
+      @res.body.should == 'RESPONSE'
+    end
+
+    it "@res.content_type.should == 'text/plain'" do
+      @res.body.should == 'RESPONSE'
+    end
+  end
+
+  describe "fail with unsupported type" do
+    before do
+      DeltaAttack::Extractor.should_receive(:extract).and_raise(DeltaAttack::Extractor::Error)
+    end
+
+    it "do_POST.should raise_error(WEBrick::HTTPStatus::BadRequest)" do
+      lambda{ @servlet.do_POST(@req, @res) }.should raise_error(WEBrick::HTTPStatus::BadRequest)
+    end
+  end
+
+  describe "fail with something" do
+    before do
+      DeltaAttack::Extractor.should_receive(:extract).and_raise(StandardError)
+    end
+
+    it "do_POST.should raise_error(WEBrick::HTTPStatus::BadRequest)" do
+      lambda{ @servlet.do_POST(@req, @res) }.should raise_error(WEBrick::HTTPStatus::InternalServerError)
+    end
+  end
+end
+

data/spec/extractor/word_spec.rb

@@ -0,0 +1,24 @@
+require File.expand_path("../spec_helper", File.dirname(__FILE__))
+require 'delta_attack/extractor/word'
+require 'java'
+require 'timeout'
+$KCODE = "u"
+
+describe DeltaAttack::Extractor::Word do
+  include SpecHelper
+  before do
+    content = File.read(sample_data("myblog.doc"))
+    @doc = DeltaAttack::Extractor::Word.new(content.to_java_bytes)
+  end
+
+  it { @doc.bytes.should_not be_nil }
+  it "data.flatten.first.should =~ /WEBrick/" do
+    @doc.data.flatten.first.should =~ /WEBrick/
+  end
+
+  it "2nd call of data() should be cached" do
+    @doc.data # 1st.
+    lambda{ timeout(0.1){ @doc.data } }.should_not raise_error(Timeout::Error)
+  end
+end
+

data/spec/extractor_spec.rb

@@ -0,0 +1,26 @@
+require File.expand_path("spec_helper", File.dirname(__FILE__))
+require 'delta_attack/extractor'
+
+describe DeltaAttack::Extractor, ".extract" do
+  it "(nil, :unknown).should raise_error(DeltaAttack::Extractor::Error)" do
+    lambda{
+      DeltaAttack::Extractor.extract(nil, :unknown)
+    }.should raise_error(DeltaAttack::Extractor::Error)
+  end
+
+  describe "(mock, :word)" do
+    before do
+      @content = mock("content")
+      @content.should_receive(:to_java_bytes).and_return(%w(a b c))
+
+      extractor = mock("extractor")
+      extractor.should_receive(:data).and_return(%w(a b c))
+      DeltaAttack::Extractor::Word.should_receive(:new).with(%w(a b c)).and_return(extractor)
+    end
+
+    it 'should == "a\nb\nc"' do
+      DeltaAttack::Extractor.extract(@content, :word)
+    end
+  end
+end
+

data/spec/filetype_assumption_spec.rb

@@ -0,0 +1,51 @@
+require File.expand_path("spec_helper", File.dirname(__FILE__))
+require 'delta_attack/filetype_assumption'
+
+describe DeltaAttack::FiletypeAssumption do
+  include SpecHelper
+  it "should not support_magic" do
+    DeltaAttack::FiletypeAssumption.should_not be_support_magic
+  end
+
+  describe "new('hoge.xls')" do
+    before do
+      @asm = DeltaAttack::FiletypeAssumption.new('hoge.xls')
+    end
+
+    it "filetype.should == :excel" do
+      @asm.filetype.should == :excel
+    end
+  end
+
+  describe "new('hoge.dat', 'application/vnd.ms-excel')" do
+    before do
+      @asm = DeltaAttack::FiletypeAssumption.new('hoge.dat', 'application/vnd.ms-excel')
+    end
+
+    it "filetype.should == :excel" do
+      @asm.filetype.should == :excel
+    end
+  end
+
+  describe "new('hoge.dat', 'application/octet-stream')" do
+    before do
+      @asm = DeltaAttack::FiletypeAssumption.new('hoge.dat', 'application/octet-stream')
+    end
+
+    it "filetype.should == :unknown" do
+      @asm.filetype.should == :unknown
+    end
+  end
+
+  describe "new('hoge.dat', 'application/octet-stream', <content>)" do
+    before do
+      content = File.read(sample_data("13TOKYO.xls"))
+      @asm = DeltaAttack::FiletypeAssumption.new('hoge.dat', 'application/octet-stream', content)
+    end
+
+    it "filetype.should == :excel" do
+      pending "mahoro is not installed" unless DeltaAttack::FiletypeAssumption.support_magic?
+      @asm.filetype.should == :excel
+    end
+  end
+end

data/spec/spec_helper.rb

@@ -0,0 +1,13 @@
+#!/usr/bin/env ruby
+# vim:set fileencoding=utf-8 filetype=ruby
+$KCODE = 'u'
+
+require 'rubygems'
+$:.unshift(File.expand_path("../lib", File.dirname(__FILE__)))
+
+module SpecHelper
+  def sample_data(name)
+    File.expand_path("../samples/data/" + name, File.dirname(__FILE__))
+  end
+end
+

metadata

@@ -0,0 +1,100 @@
+--- !ruby/object:Gem::Specification 
+name: delta_attack
+version: !ruby/object:Gem::Version 
+  hash: 19
+  prerelease: false
+  segments: 
+  - 0
+  - 1
+  - 4
+  version: 0.1.4
+platform: ruby
+authors: 
+- MOROHASHI Kyosuke
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2008-09-30 00:00:00 -07:00
+default_executable: delta_attack_server
+dependencies: []
+
+description: extract text from MS Office document with Apache POI
+email: moronatural@gmail.com
+executables: 
+- delta_attack_server
+extensions: []
+
+extra_rdoc_files: 
+- README
+- ChangeLog
+files: 
+- README
+- NOTICE
+- ChangeLog
+- Rakefile
+- bin/delta_attack_server
+- spec/extractor/excel_spec.rb
+- spec/extractor/power_point_spec.rb
+- spec/extractor/servlet_spec.rb
+- spec/extractor/word_spec.rb
+- spec/extractor_spec.rb
+- spec/filetype_assumption_spec.rb
+- spec/spec_helper.rb
+- lib/delta_attack/client.rb
+- lib/delta_attack/extractor/base.rb
+- lib/delta_attack/extractor/excel.rb
+- lib/delta_attack/extractor/power_point.rb
+- lib/delta_attack/extractor/servlet.rb
+- lib/delta_attack/extractor/word.rb
+- lib/delta_attack/extractor.rb
+- lib/delta_attack/filetype_assumption.rb
+- lib/delta_attack.rb
+- lib/vendor/README
+has_rdoc: true
+homepage: http://github.com/moro/delta_attack
+licenses: []
+
+post_install_message: 
+rdoc_options: 
+- --title
+- delta_attack documentation
+- --charset
+- utf-8
+- --opname
+- index.html
+- --line-numbers
+- --main
+- README
+- --inline-source
+- --exclude
+- ^(examples|extras)/
+require_paths: 
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      hash: 3
+      segments: 
+      - 0
+      version: "0"
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      hash: 3
+      segments: 
+      - 0
+      version: "0"
+requirements: []
+
+rubyforge_project: 
+rubygems_version: 1.3.7
+signing_key: 
+specification_version: 2
+summary: extract text from MS Office document with Apache POI
+test_files: []
+