ruby_tika_app 0.3 → 1.0.0

data/.gitignore

@@ -5,3 +5,5 @@ pkg/*
 .sublime-project
 .sublime-project.sublime-workspace
 .rbenv-version
+.idea
+coverage/*

data/.rspec

@@ -1,2 +1,3 @@
---color
+--colour --profile
 --format documentation
+--format progress

data/Gemfile

@@ -1,4 +1,4 @@
-source "http://rubygems.org"
+source 'http://rubygems.org'
 
 # Specify your gem's dependencies in ruby_tika_app.gemspec
 gemspec

data/Rakefile

@@ -1 +1 @@
-require "bundler/gem_tasks"
+require 'bundler/gem_tasks'

data/lib/ruby_tika_app.rb

@@ -10,20 +10,19 @@ class RubyTikaApp
 
   class CommandFailedError < Error
     attr_reader :status
-    def initialize status
+    def initialize(status)
       @status = status
     end
   end
 
   def initialize(document)
-
-    @document = document
+    @document = "file://#{document}"
 
     java_cmd = 'java'
     java_args = '-server -Djava.awt.headless=true'
     tika_path = "#{File.join(File.dirname(__FILE__))}/../ext/tika-app-1.2.jar"
 
-    @tika_cmd = "#{java_cmd} #{java_args} -jar #{tika_path}"
+    @tika_cmd = "#{java_cmd} #{java_args} -jar '#{tika_path}'"
   end
 
   def to_xml
@@ -53,17 +52,14 @@ class RubyTikaApp
   private
 
   def run_tika(option)
-
-    final_cmd = "#{@tika_cmd} #{option} #{@document}"
-    result = []
-
+    final_cmd = "#{@tika_cmd} #{option} '#{@document}'"
 
     pid, stdin, stdout, stderr = Open4::popen4(final_cmd)
 
     stdout_result = stdout.read.strip
     stderr_result = stderr.read.strip
 
-    unless stderr_result.strip == "" then
+    unless strip_stderr(stderr_result).empty?
       raise(CommandFailedError.new(stderr_result),
             "execution failed with status #{stderr_result}: #{final_cmd}")
     end
@@ -75,4 +71,8 @@ class RubyTikaApp
     stderr.close
   end
 
+  def strip_stderr(s)
+    s.gsub(/^(info|warn) - .*$/i, '').strip
+  end
+
 end

data/ruby_tika_app.gemspec

@@ -1,27 +1,29 @@
 # -*- encoding: utf-8 -*-
-$:.push File.expand_path("../lib", __FILE__)
+$:.push File.expand_path('../lib', __FILE__)
 
 Gem::Specification.new do |s|
-  s.name        = "ruby_tika_app"
-  s.version     = "0.3"
+  s.name        = 'ruby_tika_app'
+  s.version     = '1.0.0'
   s.platform    = Gem::Platform::RUBY
-  s.authors     = ["Chris Parker"]
-  s.email       = ["mrcsparker@gmail.com"]
-  s.homepage    = "https://github.com/mrcsparker/ruby_tika_app"
+  s.authors     = ['Chris Parker']
+  s.email       = %w(mrcsparker@gmail.com)
+  s.homepage    = 'https://github.com/mrcsparker/ruby_tika_app'
   s.summary     = %q{Wrapper around the tika-app jar}
   s.description = %q{Wrapper around the tika-app jar}
 
-  s.rubyforge_project = "ruby_tika_app"
+  s.rubyforge_project = 'ruby_tika_app'
 
   s.files         = `git ls-files`.split("\n") + 
     %w(LICENSE README.textile HISTORY)
   s.test_files    = `git ls-files -- {test,spec,features}/*`.split("\n")
   s.executables   = `git ls-files -- bin/*`.split("\n").map{ |f| File.basename(f) }
-  s.require_paths = ["lib"]
+  s.require_paths = %w(lib)
   s.test_files    = Dir.glob('spec/**/*')
 
-  s.add_runtime_dependency("open4")
+  s.add_runtime_dependency('open4')
 
-  s.add_development_dependency("rspec", "~> 2.7.0")
-  s.add_development_dependency("bundler", ">= 1.0.15")
+  s.add_development_dependency('rake')
+  s.add_development_dependency('rspec', '~> 2.13.0')
+  s.add_development_dependency('bundler', '>= 1.0.15')
+  s.add_development_dependency('simplecov')
 end

data/spec/ruby_tika_app_spec.rb

@@ -3,84 +3,92 @@ require 'spec_helper'
 describe RubyTikaApp do
 
   before(:each) do
-    @test_file = "#{File.join(File.dirname(__FILE__))}/docs/graph_sampling_simplex11.pdf"
+    @test_file = "#{File.join(File.dirname(__FILE__))}/docs/graph sampling simplex - 11.pdf"
   end
 
-  describe "#to_xml" do
-    it "header" do
+  describe 'Error' do
+    it 'has an error' do
+      expect {
+        rta = RubyTikaApp.new('No file')
+        rta.to_xml
+      }.to raise_error
+    end
+  end
+
+  describe '#to_xml' do
+    it 'header' do
       rta = RubyTikaApp.new(@test_file)
       rta.to_xml[0..37].should == "<?xml version=\"1.0\" encoding=\"UTF-8\"?>"
     end
   
-    it "middle" do
+    it 'middle' do
       rta = RubyTikaApp.new(@test_file)
       xml = rta.to_xml
 
       xml_size = xml.size / 2
 
-      xml[xml_size..(xml_size + 100)].should == "(Section IV). Besides,\nMHRW performs better in well connected graphs than in\nloosely connected graphs"
+      xml[xml_size..(xml_size + 100)].should == "S (Section IV). Besides,\nMHRW performs better in well connected graphs than in\nloosely connected grap"
     end
   end
 
-  describe "#to_html" do
-    it "header" do
+  describe '#to_html' do
+    it 'header' do
       rta = RubyTikaApp.new(@test_file)
       rta.to_html[0..42].should == "<html xmlns=\"http://www.w3.org/1999/xhtml\">"
     end
 
-    it "middle" do
+    it 'middle' do
       rta = RubyTikaApp.new(@test_file)
-      rta.to_html[1000 ... 1100].should == "rceName\" content=\"graph_sampling_simplex11.pdf\"/>\n<meta name=\"Last-Save-Date\" content=\"2011-03-29T13"
+      rta.to_html[1000 ... 1100].should == "rceName\" content=\"graph sampling simplex - 11.pdf\"/>\n<meta name=\"Last-Save-Date\" content=\"2011-03-29"
     end
   end
 
-  describe "#to_json" do
-    it "header" do
+  describe '#to_json' do
+    it 'header' do
       rta = RubyTikaApp.new(@test_file)
       rta.to_json[0..42].should == "{ \"Application\":\"\\u0027Certified by IEEE PD"
     end
 
-    it "middle" do
+    it 'middle' do
       rta = RubyTikaApp.new(@test_file)
       rta.to_json[100 ... 150].should == "h\":171510, \n\"Content-Type\":\"application/pdf\", \n\"Cr"
     end
   end
 
-  describe "#to_text" do
-    it "header" do
+  describe '#to_text' do
+    it 'header' do
       rta = RubyTikaApp.new(@test_file)
       rta.to_text[0..42].should == "Understanding Graph Sampling Algorithms\nfor"
     end
 
-    it "middle" do
+    it 'middle' do
       rta = RubyTikaApp.new(@test_file)
       rta.to_text[100 ... 150].should == "n Zhang3, Tianyin Xu2\n\nLong Jin1, Pan Hui4, Beixin"
     end
   end
 
-  describe "#to_text_main" do
-    it "header" do
+  describe '#to_text_main' do
+    it 'header' do
       rta = RubyTikaApp.new(@test_file)
-      rta.to_text_main[0..42].should == "Understanding Graph Sampling Algorithms for"
+      rta.to_text_main[0..42].should == 'Understanding Graph Sampling Algorithms for'
     end
 
-    it "middle" do
+    it 'middle' do
       rta = RubyTikaApp.new(@test_file)
       rta.to_text_main[100 ... 150].should == "n Zhang3, Tianyin Xu2\nLong Jin1, Pan Hui4, Beixing"
     end
   end
 
-  describe "#to_metadata" do
-    it "header" do
+  describe '#to_metadata' do
+    it 'header' do
       rta = RubyTikaApp.new(@test_file)
       rta.to_metadata[0..42].should == "Application: 'Certified by IEEE PDFeXpress "
     end
 
-    it "middle" do
+    it 'middle' do
       rta = RubyTikaApp.new(@test_file)
       rta.to_metadata[100 ... 150].should == "Type: application/pdf\nCreation-Date: 2011-03-29T12"
     end
-
   end
 
 end

data/spec/spec_helper.rb

@@ -1,3 +1,6 @@
+require 'simplecov'
+SimpleCov.start
+
 require 'rubygems'
 require 'bundler/setup'
 

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: ruby_tika_app
 version: !ruby/object:Gem::Version
-  version: '0.3'
+  version: 1.0.0
   prerelease: 
 platform: ruby
 authors:
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-10-29 00:00:00.000000000 Z
+date: 2013-03-24 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: open4
@@ -27,6 +27,22 @@ dependencies:
     - - ! '>='
       - !ruby/object:Gem::Version
         version: '0'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: rspec
   requirement: !ruby/object:Gem::Requirement
@@ -34,7 +50,7 @@ dependencies:
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
-        version: 2.7.0
+        version: 2.13.0
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
@@ -42,7 +58,7 @@ dependencies:
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
-        version: 2.7.0
+        version: 2.13.0
 - !ruby/object:Gem::Dependency
   name: bundler
   requirement: !ruby/object:Gem::Requirement
@@ -59,6 +75,22 @@ dependencies:
     - - ! '>='
       - !ruby/object:Gem::Version
         version: 1.0.15
+- !ruby/object:Gem::Dependency
+  name: simplecov
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
 description: Wrapper around the tika-app jar
 email:
 - mrcsparker@gmail.com
@@ -76,7 +108,7 @@ files:
 - ext/tika-app-1.2.jar
 - lib/ruby_tika_app.rb
 - ruby_tika_app.gemspec
-- spec/docs/graph_sampling_simplex11.pdf
+- spec/docs/graph sampling simplex - 11.pdf
 - spec/ruby_tika_app_spec.rb
 - spec/spec_helper.rb
 homepage: https://github.com/mrcsparker/ruby_tika_app
@@ -99,11 +131,11 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: ruby_tika_app
-rubygems_version: 1.8.24
+rubygems_version: 1.8.25
 signing_key: 
 specification_version: 3
 summary: Wrapper around the tika-app jar
 test_files:
-- spec/docs/graph_sampling_simplex11.pdf
+- spec/docs/graph sampling simplex - 11.pdf
 - spec/ruby_tika_app_spec.rb
 - spec/spec_helper.rb