yomu 0.1.2 → 0.1.3

data/README.md

@@ -13,36 +13,19 @@ Here are some of the formats supported:
 For the complete list of supported formats, please visit the Apache Tika
 [Supported Document Formats](http://tika.apache.org/0.9/formats.html) page.
 
-## Installation and Dependencies
-
-Add this line to your application's Gemfile:
-
-    gem 'yomu'
-
-And then execute:
-
-    $ bundle
-
-Or install it yourself as:
-
-    $ gem install yomu
-
-**Yomu packages the Apache Tika application jar and requires a working JRE for it to work.**
-
 ## Usage
 
-If you're not using Bundler, you will need to require Yomu in your application:
+Text and metadata can be extracted by calling `Yomu.read` directly:
 
     require 'yomu'
 
-You can extract text by calling `Yomu.read` directly:
-
     data = File.read 'sample.pages'
     text = Yomu.read :text, data
+    metadata = Yomu.read :metadata, data
 
 ### Reading text from a given filename
 
-You can also make a new instance of Yomu and pass a filename.
+Create a new instance of Yomu and pass a filename.
 
     yomu = Yomu.new 'sample.pages'
     text = yomu.text
@@ -56,13 +39,36 @@ This is useful for reading remote files, like documents hosted on Amazon S3.
 
 ### Reading text from a stream
 
-Yomu can also read from a stream or any object that responds to `read`, including Ruby on Rails' and Sinatra's file uploads:
+Yomu can also read from a stream or any object that responds to `read`, including file uploads from Ruby on Rails or Sinatra.
 
     post '/:name/:filename' do
-      yomu = Yomu.new params[:data]
+      yomu = Yomu.new params[:data][:tempfile]
       yomu.text
     end
 
+### Reading metadata
+
+Metadata is returned as a hash.
+
+    yomu = Yomu.new 'sample.pages'
+    yomu.metadata['Content-Type'] #=> "application/vnd.apple.pages"
+
+## Installation and Dependencies
+
+Add this line to your application's Gemfile:
+
+    gem 'yomu'
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install yomu
+
+**Yomu packages the Apache Tika application jar and requires a working JRE for it to work.**
+
 ## Contributing
 
 1. Fork it

data/Rakefile

@@ -5,6 +5,6 @@ require 'rake/testtask'
 
 Rake::TestTask.new do |t|
   t.libs << 'test'
-  t.test_files = FileList['test/*test.rb']
+  t.test_files = FileList['test/specs/*.rb']
   t.verbose = true
-end
+end

data/lib/yomu.rb

@@ -12,7 +12,7 @@ class Yomu
   #   data = File.read 'sample.pages'
   #   text = Yomu.read :text, data
   #   metadata = Yomu.read :metadata, data
-
+  #
   def self.read(type, data)
     switch = case type
     when :text
@@ -43,7 +43,7 @@ class Yomu
   # From a stream or an object which responds to +read+
   #
   #   Yomu.new File.open('sample.pages')
-
+  #
   def initialize(input)
     if input.is_a? String
       if input =~ URI::regexp
@@ -64,7 +64,7 @@ class Yomu
   #
   #   yomu = Yomu.new 'sample.pages'
   #   yomu.text
-
+  #
   def text
     return @text if defined? @text
 
@@ -75,7 +75,7 @@ class Yomu
   #
   #   yomu = Yomu.new 'sample.pages'
   #   yomu.metadata['Content-Type']
-
+  #
   def metadata
     return @metadata if defined? @metadata
 
@@ -86,7 +86,7 @@ class Yomu
   #
   #   yomu = Yomu.new 'sample.pages'
   #   yomu.path? #=> true
-
+  #
   def path?
     defined? @path
   end
@@ -95,7 +95,7 @@ class Yomu
   #
   #   yomu = Yomu.new 'http://svn.apache.org/repos/asf/poi/trunk/test-data/document/sample.docx'
   #   yomu.uri? #=> true
-
+  #
   def uri?
     defined? @uri
   end
@@ -105,7 +105,7 @@ class Yomu
   #   file = File.open('sample.pages')
   #   yomu = Yomu.new file
   #   yomu.stream? #=> true
-
+  #
   def stream?
     defined? @stream
   end
@@ -114,7 +114,7 @@ class Yomu
   #
   #   yomu = Yomu.new 'sample.pages'
   #   yomu.data
-
+  #
   def data
     return @data if defined? @data
 

data/lib/yomu/version.rb

@@ -1,3 +1,3 @@
 class Yomu
-  VERSION = "0.1.2"
+  VERSION = "0.1.3"
 end

data/test/helper.rb

@@ -0,0 +1,3 @@
+require 'bundler/setup'
+require 'yomu'
+require 'minitest/autorun'

data/test/specs/yomu.rb

@@ -0,0 +1,141 @@
+require_relative '../helper.rb'
+
+describe Yomu do
+  let(:data) { File.read 'test/samples/sample.pages' }
+
+  describe '.read' do
+    it 'reads text' do
+      text = Yomu.read :text, data
+
+      assert_includes text, 'The quick brown fox jumped over the lazy cat.'
+    end
+
+    it 'reads metadata' do
+      metadata = Yomu.read :metadata, data
+
+      assert_equal 'application/vnd.apple.pages', metadata['Content-Type']
+    end
+  end
+
+  describe '.new' do
+    it 'requires parameters' do
+      assert_raises ArgumentError do
+        Yomu.new
+      end
+    end
+
+    it 'accepts a root path' do
+      assert_silent do
+        yomu = Yomu.new 'test/samples/sample.pages'
+
+        assert_block { yomu.path? }
+        assert_block { !yomu.uri? }
+        assert_block { !yomu.stream? }
+      end
+    end
+
+    it 'accepts a relative path' do
+      assert_silent do
+        yomu = Yomu.new 'test/samples/sample.pages'
+
+        assert_block { yomu.path? }
+        assert_block { !yomu.uri? }
+        assert_block { !yomu.stream? }
+      end
+    end
+
+    it 'accepts a path with spaces' do
+      assert_silent do
+        yomu = Yomu.new 'test/samples/sample filename with spaces.pages'
+
+        assert_block { yomu.path? }
+        assert_block { !yomu.uri? }
+        assert_block { !yomu.stream? }
+      end
+    end
+
+    it 'accepts a URI' do
+      assert_silent do
+        yomu = Yomu.new 'http://svn.apache.org/repos/asf/poi/trunk/test-data/document/sample.docx'
+
+        assert_block { yomu.uri? }
+        assert_block { !yomu.path? }
+        assert_block { !yomu.stream? }
+      end
+    end
+
+    it 'accepts a stream or object that can be read' do
+      assert_silent do
+        File.open 'test/samples/sample.pages', 'r' do |file|
+          yomu = Yomu.new file
+
+        assert_block { yomu.stream? }
+        assert_block { !yomu.path? }
+        assert_block { !yomu.uri? }
+        end
+      end
+    end
+
+    it 'does not accept a path to a missing file' do
+      assert_raises Errno::ENOENT do
+        Yomu.new 'test/sample/missing.pages'
+      end
+    end
+
+    it 'does not accept other objects' do
+      [nil, 1, 1.1].each do |object|
+        assert_raises TypeError do
+          Yomu.new object
+        end
+      end
+    end
+  end
+
+  describe 'initialized with a given path' do
+    let(:yomu) { Yomu.new 'test/samples/sample.pages' }
+
+    describe '#text' do
+      it 'reads text' do
+        assert_includes yomu.text, 'The quick brown fox jumped over the lazy cat.'
+      end
+    end
+
+    describe '#metadata' do
+      it 'reads metadata' do
+        assert_equal 'application/vnd.apple.pages', yomu.metadata['Content-Type']
+      end
+    end
+  end
+
+  describe 'initialized with a given URI' do
+    let(:yomu) { Yomu.new 'http://svn.apache.org/repos/asf/poi/trunk/test-data/document/sample.docx' }
+
+    describe '#text' do
+      it 'reads text' do
+        assert_includes yomu.text, 'Lorem ipsum dolor sit amet, consectetuer adipiscing elit.'
+      end
+    end
+
+    describe '#metadata' do
+      it 'reads metadata' do
+        assert_equal 'application/vnd.openxmlformats-officedocument.wordprocessingml.document', yomu.metadata['Content-Type']
+      end
+    end
+  end
+
+  describe 'initialized with a given stream' do
+    let(:yomu) { Yomu.new File.open('test/samples/sample.pages', 'rb') }
+
+    describe '#text' do
+      it 'reads text' do
+        assert_includes yomu.text, 'The quick brown fox jumped over the lazy cat.'
+      end
+    end
+
+    describe '#metadata' do
+      it 'reads metadata' do
+        assert_equal 'application/vnd.apple.pages', yomu.metadata['Content-Type']
+      end
+    end
+  end
+end

data/yomu.gemspec

@@ -4,9 +4,9 @@ require File.expand_path('../lib/yomu/version', __FILE__)
 Gem::Specification.new do |gem|
   gem.authors       = ["Erol Fornoles"]
   gem.email         = ["erol.fornoles@gmail.com"]
-  gem.description   = %q{Yomu is a library for extracting text and metadata using the Apache TIKA content analysis toolkit.}
-  gem.summary       = %q{Yomu is a library for extracting text and metadata using the Apache TIKA content analysis toolkit.}
-  gem.homepage      = "http://github.com/Erol/yomu"
+  gem.description   = %q{Read text and metadata from files and documents (.doc, .docx, .pages, .odt, .rtf, .pdf)}
+  gem.summary       = %q{Read text and metadata from files and documents (.doc, .docx, .pages, .odt, .rtf, .pdf)}
+  gem.homepage      = "http://erol.github.com/yomu"
 
   gem.executables   = `git ls-files -- bin/*`.split("\n").map{ |f| File.basename(f) }
   gem.files         = `git ls-files`.split("\n")
@@ -14,4 +14,4 @@ Gem::Specification.new do |gem|
   gem.name          = "yomu"
   gem.require_paths = ["lib"]
   gem.version       = Yomu::VERSION
-end
+end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: yomu
 version: !ruby/object:Gem::Version
-  version: 0.1.2
+  version: 0.1.3
   prerelease: 
 platform: ruby
 authors:
@@ -9,10 +9,10 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-09-09 00:00:00.000000000 Z
+date: 2012-10-22 00:00:00.000000000 Z
 dependencies: []
-description: Yomu is a library for extracting text and metadata using the Apache TIKA
-  content analysis toolkit.
+description: Read text and metadata from files and documents (.doc, .docx, .pages,
+  .odt, .rtf, .pdf)
 email:
 - erol.fornoles@gmail.com
 executables: []
@@ -28,12 +28,12 @@ files:
 - jar/tika-app-1.2.jar
 - lib/yomu.rb
 - lib/yomu/version.rb
+- test/helper.rb
 - test/samples/sample filename with spaces.pages
 - test/samples/sample.pages
-- test/test_helper.rb
-- test/yomu_test.rb
+- test/specs/yomu.rb
 - yomu.gemspec
-homepage: http://github.com/Erol/yomu
+homepage: http://erol.github.com/yomu
 licenses: []
 post_install_message: 
 rdoc_options: []
@@ -56,10 +56,10 @@ rubyforge_project:
 rubygems_version: 1.8.24
 signing_key: 
 specification_version: 3
-summary: Yomu is a library for extracting text and metadata using the Apache TIKA
-  content analysis toolkit.
+summary: Read text and metadata from files and documents (.doc, .docx, .pages, .odt,
+  .rtf, .pdf)
 test_files:
+- test/helper.rb
 - test/samples/sample filename with spaces.pages
 - test/samples/sample.pages
-- test/test_helper.rb
-- test/yomu_test.rb
+- test/specs/yomu.rb

data/test/test_helper.rb

@@ -1,2 +0,0 @@
-require 'bundler/setup'
-require 'minitest/autorun'

data/test/yomu_test.rb

@@ -1,131 +0,0 @@
-require_relative 'test_helper.rb'
-
-require 'yomu.rb'
-
-class YomuTest < MiniTest::Unit::TestCase
-  def test_yomu_can_read_text
-    data = File.read 'test/samples/sample.pages'
-    text = Yomu.read :text, data
-
-    assert_includes text, 'The quick brown fox jumped over the lazy cat.'
-  end
-
-  def test_yomu_can_read_metadata
-    data = File.read 'test/samples/sample.pages'
-    metadata = Yomu.read :metadata, data
-
-    assert_equal 'application/vnd.apple.pages', metadata['Content-Type']
-  end
-
-  def test_yomu_cannot_be_initialized_without_parameters
-    assert_raises ArgumentError do
-      Yomu.new
-    end
-  end
-
-  def test_yomu_can_be_initialized_with_a_root_path
-    assert_silent do
-      yomu = Yomu.new File.join(File.dirname(__FILE__), 'samples/sample.pages')
-
-      assert_block { yomu.path? }
-      assert_block { !yomu.uri? }
-      assert_block { !yomu.stream? }
-    end
-  end
-
-  def test_yomu_can_be_initialized_with_a_relative_path
-    assert_silent do
-      yomu = Yomu.new 'test/samples/sample.pages'
-
-      assert_block { yomu.path? }
-      assert_block { !yomu.uri? }
-      assert_block { !yomu.stream? }
-    end
-  end
-
-  def test_yomu_can_be_initialized_with_a_path_with_spaces
-    assert_silent do
-      yomu = Yomu.new 'test/samples/sample filename with spaces.pages'
-
-      assert_block { yomu.path? }
-      assert_block { !yomu.uri? }
-      assert_block { !yomu.stream? }
-    end
-  end
-
-  def test_yomu_can_be_initialized_with_a_uri
-    assert_silent do
-      yomu = Yomu.new 'http://svn.apache.org/repos/asf/poi/trunk/test-data/document/sample.docx'
-
-      assert_block { yomu.uri? }
-      assert_block { !yomu.path? }
-      assert_block { !yomu.stream? }
-    end
-  end
-
-  def test_yomu_can_be_initialized_with_a_stream_or_object_that_can_be_read
-    assert_silent do
-      File.open 'test/samples/sample.pages', 'r' do |file|
-        yomu = Yomu.new file
-
-      assert_block { yomu.stream? }
-      assert_block { !yomu.path? }
-      assert_block { !yomu.uri? }
-      end
-    end
-  end
-
-  def test_yomu_cannot_be_initialized_with_a_path_to_a_missing_file
-    assert_raises Errno::ENOENT do
-      Yomu.new 'test/sample/missing.pages'
-    end
-  end
-
-  def test_yomu_cannot_be_initialized_with_other_objects
-    [nil, 1, 1.1].each do |object|
-      assert_raises TypeError do
-        Yomu.new object
-      end
-    end
-  end
-
-  def test_yomu_initialized_with_a_path_can_read_text
-    yomu = Yomu.new 'test/samples/sample.pages'
-
-    assert_includes yomu.text, 'The quick brown fox jumped over the lazy cat.'
-  end
-
-  def test_yomu_initialized_with_a_path_can_read_metadata
-    yomu = Yomu.new 'test/samples/sample.pages'
-
-    assert_equal 'application/vnd.apple.pages', yomu.metadata['Content-Type']
-  end
-
-  def test_yomu_initialized_with_a_url_can_read_text
-    yomu = Yomu.new 'http://svn.apache.org/repos/asf/poi/trunk/test-data/document/sample.docx'
-
-    assert_includes yomu.text, 'Lorem ipsum dolor sit amet, consectetuer adipiscing elit.'
-  end
-
-  def test_yomu_initialized_with_a_url_can_read_metadata
-    yomu = Yomu.new 'http://svn.apache.org/repos/asf/poi/trunk/test-data/document/sample.docx'
-
-    assert_equal 'application/vnd.openxmlformats-officedocument.wordprocessingml.document', yomu.metadata['Content-Type']
-  end
-
-  def test_yomu_initialized_with_a_stream_can_read_text
-    File.open 'test/samples/sample.pages', 'rb' do |file|
-      yomu = Yomu.new file
-
-      assert_includes yomu.text, 'The quick brown fox jumped over the lazy cat.'
-    end
-  end
-
-  def test_yomu_initialized_with_a_stream_can_read_metadata
-    File.open 'test/samples/sample.pages', 'rb' do |file|
-      yomu = Yomu.new file
-
-      assert_equal 'application/vnd.apple.pages', yomu.metadata['Content-Type']
-    end
-  end
-end