yomu 0.1.0 → 0.1.1

data/README.md

@@ -1,5 +1,5 @@
 # Yomu 読む
-[Yomu](http://github.com/Erol/yomu) is a library for extracting text and metadata using the [Apache TIKA](http://tika.apache.org/) content analysis toolkit.
+[Yomu](http://erol.github.com/yomu) is a library for extracting text and metadata from files and documents using the [Apache TIKA](http://tika.apache.org/) content analysis toolkit.
 
 Here are some of the formats supported:
 
@@ -10,7 +10,7 @@ Here are some of the formats supported:
 - Rich Text Format (.rtf)
 - Portable Document Format (.pdf)
 
-For the complete list of supported formats, please visit the Apache Tika
+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
@@ -27,7 +27,7 @@ Or install it yourself as:
 
     $ gem install yomu
 
-Yomu packages the Apache Tika application jar and thus requires a working JRE for it to work.
+**Yomu packages the Apache TIKA application jar and requires a working JRE for it to work.**
 
 ## Usage
 
@@ -40,21 +40,21 @@ You can extract text by calling `Yomu.read` directly:
     data = File.read 'sample.pages'
     text = Yomu.read :text, data
 
-##### Filename
+### Reading text from a given filename
 
 You can also make a new instance of Yomu and pass a filename.
 
     yomu = Yomu.new 'sample.pages'
     text = yomu.text
 
-##### URL
+### Reading text from a given URL
 
 This is useful for reading remote files, like documents hosted on Amazon S3.
 
     yomu = Yomu.new 'http://svn.apache.org/repos/asf/poi/trunk/test-data/document/sample.docx'
     text = yomu.text
 
-##### Stream
+### 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:
 
@@ -66,8 +66,8 @@ Yomu can also read from a stream or any object that responds to `read`, includin
 ## Contributing
 
 1. Fork it
-2. Create your feature branch (`git checkout -b my-new-feature`)
-3. Create tests and make them pass (`rake test`)
-4. Commit your changes (`git commit -am 'Added some feature'`)
-5. Push to the branch (`git push origin my-new-feature`)
+2. Create your feature branch ( `git checkout -b my-new-feature` )
+3. Create tests and make them pass ( `rake test` )
+4. Commit your changes ( `git commit -am 'Added some feature'` )
+5. Push to the branch ( `git push origin my-new-feature` )
 6. Create a new Pull Request

data/lib/yomu.rb

@@ -1,4 +1,4 @@
-require "yomu/version"
+require 'yomu/version'
 
 require 'net/http'
 require 'yaml'
@@ -46,11 +46,12 @@ class Yomu
 
   def initialize(input)
     if input.is_a? String
-      uri = URI.parse input
-      if uri.scheme and uri.host
-        @uri = uri
-      else
+      if input =~ URI::regexp
+        @uri = URI.parse input
+      elsif File.exists? input
         @path = input
+      else
+        raise Errno::ENOENT.new "missing file or invalid URI - #{input}"
       end
     elsif input.respond_to? :read
       @stream = input
@@ -81,16 +82,28 @@ class Yomu
     @metadata = Yomu.read :metadata, data
   end
 
+  def path?
+    defined? @path
+  end
+
+  def uri?
+    defined? @uri
+  end
+
+  def stream?
+    defined? @stream
+  end
+
   protected
 
   def data
     return @data if defined? @data
 
-    if defined? @path
+    if path?
       @data = File.read @path
-    elsif defined? @uri
+    elsif uri?
       @data = Net::HTTP.get @uri
-    elsif defined? @stream
+    elsif stream?
       @data = @stream.read
     end
 

data/lib/yomu/version.rb

@@ -1,3 +1,3 @@
 class Yomu
-  VERSION = "0.1.0"
+  VERSION = "0.1.1"
 end

data/test/yomu_test.rb

@@ -23,26 +23,64 @@ class YomuTest < MiniTest::Unit::TestCase
     end
   end
 
-  def test_yomu_can_be_initialized_with_a_path
+  def test_yomu_can_be_initialized_with_a_root_path
     assert_silent do
-      Yomu.new 'test/samples/sample.pages'
+      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_url
+  def test_yomu_can_be_initialized_with_a_uri
     assert_silent do
-      Yomu.new 'http://svn.apache.org/repos/asf/poi/trunk/test-data/document/sample.docx'
+      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.new 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

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: yomu
 version: !ruby/object:Gem::Version
-  version: 0.1.0
+  version: 0.1.1
   prerelease: 
 platform: ruby
 authors:
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-03-25 00:00:00.000000000 Z
+date: 2012-04-11 00:00:00.000000000 Z
 dependencies: []
 description: Yomu is a library for extracting text and metadata using the Apache TIKA
   content analysis toolkit.
@@ -28,6 +28,7 @@ files:
 - jar/tika-app-1.1.jar
 - lib/yomu.rb
 - lib/yomu/version.rb
+- test/samples/sample filename with spaces.pages
 - test/samples/sample.pages
 - test/test_helper.rb
 - test/yomu_test.rb
@@ -58,6 +59,8 @@ specification_version: 3
 summary: Yomu is a library for extracting text and metadata using the Apache TIKA
   content analysis toolkit.
 test_files:
+- test/samples/sample filename with spaces.pages
 - test/samples/sample.pages
 - test/test_helper.rb
 - test/yomu_test.rb
+has_rdoc: