rika 0.9.0-java

data/.gitignore

@@ -0,0 +1,19 @@
+*.gem
+*.rbc
+.bundle
+.config
+.yardoc
+Gemfile.lock
+InstalledFiles
+_yardoc
+coverage
+doc/
+lib/bundler/man
+pkg
+rdoc
+spec/reports
+test/tmp
+test/version_tmp
+tmp
+
+.DS_Store

data/.rspec

@@ -0,0 +1,2 @@
+--color
+--format progress

data/Gemfile

@@ -0,0 +1,4 @@
+source 'https://rubygems.org'
+
+# Specify your gem's dependencies in rika.gemspec
+gemspec

data/LICENSE.txt

@@ -0,0 +1,22 @@
+Copyright (c) 2012 Richard Nyström
+
+MIT License
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/README.md

@@ -0,0 +1,43 @@
+# Rika
+
+A JRuby wrapper for Apache Tika to extract text and metadata from various file formats.
+
+More information about Apache Tika can be found here: http://tika.apache.org/
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+    gem 'rika'
+
+Remember that this gem only works on JRuby.
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install rika
+
+## Usage
+
+Something like this:
+
+require 'rika'
+
+parser = Rika::Parser.new('document.pdf')
+
+parser.content # Returns the content of the document as text
+
+parser.metadata["title"] if parser.metadata_exists?("title") # Returns the metadata field title if it exists 
+
+parser.available_metadata # Returns all the available metadata keys that can be read from the document
+
+## Contributing
+
+1. Fork it
+2. Create your feature branch (`git checkout -b my-new-feature`)
+3. Commit your changes (`git commit -am 'Add some feature'`)
+4. Push to the branch (`git push origin my-new-feature`)
+5. Create new Pull Request

data/Rakefile

@@ -0,0 +1 @@
+require "bundler/gem_tasks"

data/lib/rika.rb

@@ -0,0 +1,64 @@
+raise "You need to run JRuby to use Rika" unless RUBY_PLATFORM =~ /java/
+
+require "rika/version"
+require 'java' 
+
+Dir[File.join(File.dirname(__FILE__), "*.jar")].each do |jar|
+  require jar
+end
+
+module Rika
+	import org.apache.tika.sax.BodyContentHandler
+	import org.apache.tika.parser.AutoDetectParser
+	import org.apache.tika.metadata.Metadata
+
+  class Parser
+  	
+  	def initialize(filename)
+  		if File.exists?(filename)
+  			@filename = filename
+				self.perform
+			else
+				raise IOError, "File does not exist"
+			end
+  	end
+
+  	def content
+  		@content.to_s
+  	end
+
+  	def metadata
+  		metadata_hash = {}
+  		
+  		@metadata.names.each do |name|
+  			metadata_hash[name] = @metadata.get(name) 
+  		end
+
+  		metadata_hash
+  	end
+
+  	def available_metadata
+  		@metadata.names.to_a
+  	end
+
+  	def metadata_exists?(name)
+  		if @metadata.get(name) == nil
+  			false
+  		else
+  			true
+  		end
+  	end
+
+  	protected
+		
+		def perform
+			input_stream = java.io.FileInputStream.new(java.io.File.new(@filename))
+			@metadata = Metadata.new
+			@metadata.set("filename", File.basename(@filename))
+			@parser = AutoDetectParser.new
+			@content = BodyContentHandler.new
+			@parser.parse(input_stream, @content, @metadata)
+			input_stream.close
+		end
+  end
+end

data/lib/rika/version.rb

@@ -0,0 +1,3 @@
+module Rika
+  VERSION = "0.9.0"
+end

data/rika.gemspec

@@ -0,0 +1,20 @@
+# -*- encoding: utf-8 -*-
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'rika/version'
+
+Gem::Specification.new do |gem|
+  gem.name          = "rika"
+  gem.version       = Rika::VERSION
+  gem.authors       = ["Richard Nyström"]
+  gem.email         = ["ricny046@gmail.com"]
+  gem.description   = %q{ A JRuby wrapper for Apache Tika to extract text and metadata from various file formats. }
+  gem.summary       = %q{ A JRuby wrapper for Apache Tika to extract text and metadata from various file formats. }
+  gem.homepage      = "https://github.com/ricn/rika"
+  gem.files         = `git ls-files`.split($/)
+  gem.executables   = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
+  gem.test_files    = gem.files.grep(%r{^(test|spec|features)/})
+  gem.require_paths = ["lib"]
+  gem.add_development_dependency "rspec"
+  gem.platform = "java"
+end

data/spec/fixtures/text_file.txt

@@ -0,0 +1 @@
+First they ignore you, then they ridicule you, then they fight you, then you win.

data/spec/rika_spec.rb

@@ -0,0 +1,80 @@
+# encoding: utf-8
+
+require 'spec_helper'
+
+describe Rika::Parser do 
+  before(:all) do
+    @txt_parser = Rika::Parser.new(file_path("text_file.txt"))
+    @docx_parser = Rika::Parser.new(file_path("document.docx"))
+    @pdf_parser = Rika::Parser.new(file_path("document.pdf"))
+    @image_parser = Rika::Parser.new(file_path("image.jpg"))
+  end
+
+  it "should crash if file does not exists" do
+    lambda { Rika::Parser.new(file_path("nonsense.txt")) }.should raise_error(IOError, "File does not exist")
+  end
+
+  describe '#content' do
+    it "should return the content in a text file" do
+      @txt_parser.content.strip.should == "First they ignore you, then they ridicule you, then they fight you, then you win."
+    end
+
+    it "should return the content in a docx file" do
+      @docx_parser.content.strip.should == "First they ignore you, then they ridicule you, then they fight you, then you win."
+    end
+
+    it "should return the content in a pdf file" do 
+      @pdf_parser.content.strip.should == "First they ignore you, then they ridicule you, then they fight you, then you win."
+    end
+
+    it "should return no content for an image" do
+      @image_parser.content.should be_empty
+    end
+  end
+
+  # We just test a few of the metadata fields for some common file formats 
+  # to make sure the integration with Apache Tika works. Apache Tika already 
+  # have tests for all file formats it supports so we won't retest that
+  describe '#metadata' do
+    it "should return nil if metadata field does not exists" do
+      @txt_parser.metadata["nonsense"].should be_nil
+    end
+
+    it "should return metadata from a text file" do
+      @txt_parser.metadata["filename"].should == "text_file.txt"
+    end
+
+    it "should return metadata from a docx file" do
+      @docx_parser.metadata["Page-Count"].should == "1"
+    end
+
+    it "should return metadata from a pdf file" do
+      @pdf_parser.metadata["title"].should == "A simple title"
+    end
+
+    it "should return metadata from an image" do
+      @image_parser.metadata["Image Height"].should == "72 pixels"
+      @image_parser.metadata["Image Width"].should == "72 pixels"
+    end
+  end
+
+  describe '#available_metadata' do
+    it "should return available metadata fields" do
+      @txt_parser.available_metadata.should_not be_empty
+    end
+
+    it "should be an array" do
+      @txt_parser.available_metadata.is_a?(Array).should == true
+    end
+  end
+
+  describe '#metadata_exists?' do
+    it "should return false if metadata does not exists" do
+      @txt_parser.metadata_exists?("title").should == false
+    end
+
+    it "should return true if metadata exists" do
+      @docx_parser.metadata_exists?("title").should == true
+    end
+  end
+end

data/spec/spec_helper.rb

@@ -0,0 +1,13 @@
+require "rika"
+
+def file_path( *paths )
+  File.expand_path(File.join(File.dirname(__FILE__), 'fixtures', *paths))
+end
+# See http://rubydoc.info/gems/rspec-core/RSpec/Core/Configuration
+RSpec.configure do |config|
+  config.treat_symbols_as_metadata_keys_with_true_values = true
+  config.run_all_when_everything_filtered = true
+  config.filter_run :focus
+
+  config.order = 'random'
+end

metadata

@@ -0,0 +1,119 @@
+--- !ruby/object:Gem::Specification
+name: rika
+version: !ruby/object:Gem::Version
+  prerelease:
+  version: 0.9.0
+platform: java
+authors:
+- Richard Nyström
+autorequire:
+bindir: bin
+cert_chain: []
+date: 2012-09-16 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: rspec
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: !binary |-
+          MA==
+    none: false
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: !binary |-
+          MA==
+    none: false
+  prerelease: false
+  type: :development
+description: ! ' A JRuby wrapper for Apache Tika to extract text and metadata from
+  various file formats. '
+email:
+- ricny046@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- .gitignore
+- .rspec
+- Gemfile
+- LICENSE.txt
+- README.md
+- Rakefile
+- lib/apache-mime4j-core-0.7.2.jar
+- lib/apache-mime4j-dom-0.7.2.jar
+- lib/asm-3.1.jar
+- lib/aspectjrt-1.6.11.jar
+- lib/bcmail-jdk15-1.45.jar
+- lib/bcprov-jdk15-1.45.jar
+- lib/boilerpipe-1.1.0.jar
+- lib/commons-codec-1.5.jar
+- lib/commons-compress-1.4.1.jar
+- lib/commons-logging-1.1.1.jar
+- lib/dom4j-1.6.1.jar
+- lib/fontbox-1.7.0.jar
+- lib/isoparser-1.0-RC-1.jar
+- lib/jempbox-1.7.0.jar
+- lib/juniversalchardet-1.0.3.jar
+- lib/metadata-extractor-2.4.0-beta-1.jar
+- lib/pdfbox-1.7.0.jar
+- lib/poi-3.8.jar
+- lib/poi-ooxml-3.8.jar
+- lib/poi-ooxml-schemas-3.8.jar
+- lib/poi-scratchpad-3.8.jar
+- lib/rika.rb
+- lib/rika/version.rb
+- lib/rome-0.9.jar
+- lib/tagsoup-1.2.1.jar
+- lib/tika-core-1.2.jar
+- lib/tika-parsers-1.2.jar
+- lib/vorbis-java-core-0.1-tests.jar
+- lib/vorbis-java-core-0.1.jar
+- lib/vorbis-java-tika-0.1.jar
+- lib/xmlbeans-2.3.0.jar
+- lib/xz-1.0.jar
+- rika.gemspec
+- spec/fixtures/document.doc
+- spec/fixtures/document.docx
+- spec/fixtures/document.pdf
+- spec/fixtures/image.jpg
+- spec/fixtures/text_file.txt
+- spec/rika_spec.rb
+- spec/spec_helper.rb
+homepage: https://github.com/ricn/rika
+licenses: []
+post_install_message:
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: !binary |-
+        MA==
+  none: false
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: !binary |-
+        MA==
+  none: false
+requirements: []
+rubyforge_project:
+rubygems_version: 1.8.24
+signing_key:
+specification_version: 3
+summary: A JRuby wrapper for Apache Tika to extract text and metadata from various file formats.
+test_files:
+- spec/fixtures/document.doc
+- spec/fixtures/document.docx
+- spec/fixtures/document.pdf
+- spec/fixtures/image.jpg
+- spec/fixtures/text_file.txt
+- spec/rika_spec.rb
+- spec/spec_helper.rb