yomu 0.1.9 → 0.1.10

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 23b6ed327cc94e45aea195294d84bb8dd669f1a6
+  data.tar.gz: c5ef3d9857242820b04f7c76f2f90834a7235a62
+SHA512:
+  metadata.gz: 195f73de69ed781c97f10fffac2971a258a2f23ede81e6ebbc1ce34400c38de4fccac93b765df37c0ca3ab105a95a682977fcc6c71a3d86f810a674e2226ed0e
+  data.tar.gz: a5f562f9de92eedf29a2cf889f1083f03d19928f10998998131c06f3457613e40e06a7fd2f116a88bb74058e1bceb7fe62402aa6204e0fe1a81adcc71cf1c422

data/README.md

@@ -1,4 +1,7 @@
+![Google Analytics](https://ga-beacon.appspot.com/UA-31066891-2/yomu/code)
+
 # Yomu 読む
+
 [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:
@@ -17,50 +20,62 @@ For the complete list of supported formats, please visit the Apache Tika
 
 Text, metadata and MIME type information can be extracted by calling `Yomu.read` directly:
 
-    require 'yomu'
+```ruby
+require 'yomu'
 
-    data = File.read 'sample.pages'
-    text = Yomu.read :text, data
-    metadata = Yomu.read :metadata, data
-    mimetype = Yomu.read :mimetype, data
+data = File.read 'sample.pages'
+text = Yomu.read :text, data
+metadata = Yomu.read :metadata, data
+mimetype = Yomu.read :mimetype, data
+```
 
 ### Reading text from a given filename
 
 Create a new instance of Yomu and pass a filename.
 
-    yomu = Yomu.new 'sample.pages'
-    text = yomu.text
+```ruby
+yomu = Yomu.new 'sample.pages'
+text = yomu.text
+```
 
 ### 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
+```ruby
+yomu = Yomu.new 'http://svn.apache.org/repos/asf/poi/trunk/test-data/document/sample.docx'
+text = yomu.text
+```
 
 ### Reading text from a stream
 
 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][:tempfile]
-      yomu.text
-    end
+```ruby
+post '/:name/:filename' do
+  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"
+```ruby
+yomu = Yomu.new 'sample.pages'
+yomu.metadata['Content-Type'] #=> "application/vnd.apple.pages"
+```
 
 ### Reading MIME types
 
 MIME type is returned as a MIME::Type object.
 
-    yomu = Yomu.new 'sample.docx'
-    yomu.mimetype.content_type #=> "application/vnd.openxmlformats-officedocument.wordprocessingml.document"
-    yomu.mimetype.extensions #=> ['docx']
+```ruby
+yomu = Yomu.new 'sample.docx'
+yomu.mimetype.content_type #=> "application/vnd.openxmlformats-officedocument.wordprocessingml.document"
+yomu.mimetype.extensions #=> ['docx']
+```
 
 ## Installation and Dependencies
 

data/lib/yomu.rb

@@ -6,7 +6,7 @@ require 'yaml'
 
 class Yomu
   GEMPATH = File.dirname(File.dirname(__FILE__))
-  JARPATH = File.join(Yomu::GEMPATH, 'jar', 'tika-app-1.*.jar')
+  JARPATH = File.join(Yomu::GEMPATH, 'jar', 'tika-app-1.5.jar')
 
   # Read text or metadata from a data buffer.
   #
@@ -18,6 +18,8 @@ class Yomu
     switch = case type
     when :text
       '-t'
+    when :html
+      '-h'
     when :metadata
       '-m'
     when :mimetype
@@ -33,6 +35,8 @@ class Yomu
     case type
     when :text
       result
+    when :html
+      result
     when :metadata
       YAML.load quote(result)
     when :mimetype
@@ -81,6 +85,17 @@ class Yomu
     @text = Yomu.read :text, data
   end
 
+  # Returns the text content of the Yomu document in HTML.
+  #
+  #   yomu = Yomu.new 'sample.pages'
+  #   yomu.html
+
+  def html
+    return @text if defined? @text
+
+    @text = Yomu.read :html, data
+  end
+
   # Returns the metadata hash of the Yomu document.
   #
   #   yomu = Yomu.new 'sample.pages'

data/lib/yomu/version.rb

@@ -1,3 +1,3 @@
 class Yomu
-  VERSION = "0.1.9"
+  VERSION = "0.1.10"
 end

metadata

@@ -1,78 +1,69 @@
 --- !ruby/object:Gem::Specification
 name: yomu
 version: !ruby/object:Gem::Version
-  version: 0.1.9
-  prerelease: 
+  version: 0.1.10
 platform: ruby
 authors:
 - Erol Fornoles
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-07-17 00:00:00.000000000 Z
+date: 2014-02-27 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: mime-types
   requirement: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
         version: '1.23'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
         version: '1.23'
 - !ruby/object:Gem::Dependency
   name: bundler
   requirement: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
         version: '1.3'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
         version: '1.3'
 - !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
-    none: false
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
         version: '2.14'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
         version: '2.14'
 description: Read text and metadata from files and documents (.doc, .docx, .pages,
@@ -83,14 +74,14 @@ executables: []
 extensions: []
 extra_rdoc_files: []
 files:
-- .gitignore
-- .rspec
+- ".gitignore"
+- ".rspec"
 - Gemfile
 - LICENSE
 - NOTICE.txt
 - README.md
 - Rakefile
-- jar/tika-app-1.4.jar
+- jar/tika-app-1.5.jar
 - lib/yomu.rb
 - lib/yomu/version.rb
 - spec/helper.rb
@@ -99,32 +90,30 @@ files:
 - spec/samples/sample.docx
 - spec/samples/sample.pages
 - spec/yomu_spec.rb
-- test/helper.rb
 - yomu.gemspec
 homepage: http://erol.github.com/yomu
 licenses:
 - MIT
+metadata: {}
 post_install_message: 
 rdoc_options: []
 require_paths:
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement
-  none: false
   requirements:
-  - - ! '>='
+  - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 required_rubygems_version: !ruby/object:Gem::Requirement
-  none: false
   requirements:
-  - - ! '>='
+  - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 1.8.23
+rubygems_version: 2.2.0
 signing_key: 
-specification_version: 3
+specification_version: 4
 summary: Read text and metadata from files and documents (.doc, .docx, .pages, .odt,
   .rtf, .pdf)
 test_files:
@@ -134,4 +123,3 @@ test_files:
 - spec/samples/sample.docx
 - spec/samples/sample.pages
 - spec/yomu_spec.rb
-- test/helper.rb

data/test/helper.rb

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