rika 1.4.0-java → 1.5.0-java

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 03d0a3d8e955115312ddf54329e6a613bf0d58e8
+  data.tar.gz: 6de10264cd6d8791b353f1e2a574f1eaaf982dd9
+SHA512:
+  metadata.gz: 56ef6e0f28e6642dd624407335add98dededce244121996428008590bb1120908c4cb4b8b6964458bd032d2c521e985de524f578446c3c0c7102ad8a6b73d9a6
+  data.tar.gz: 67221ab8318af05b90f33cbb7520cc48fa7d474bd5c7170c76f54b268c4ab941b309bbd7c7ac704edd2aeb888634fcf5adf97a1a4d1ea1760d3fda270f6aa300

data/Rakefile

@@ -8,4 +8,4 @@ task :default => :spec
 desc 'Download jars'
 task :download_jars do
 	system "mvn dependency:copy-dependencies"
- end
+end

data/lib/rika.rb

@@ -5,13 +5,13 @@ raise "You need to run JRuby to use Rika" unless RUBY_PLATFORM =~ /java/
 require "rika/version"
 require 'uri'
 require 'net/http'
-require 'java' 
+require 'java'
 
 Dir[File.join(File.dirname(__FILE__), "../target/dependency/*.jar")].each do |jar|
   require jar
 end
 
-# Heavily based on the Apache Tika API: http://tika.apache.org/1.4/api/org/apache/tika/Tika.html
+# Heavily based on the Apache Tika API: http://tika.apache.org/1.5/api/org/apache/tika/Tika.html
 module Rika
   import org.apache.tika.metadata.Metadata
   import org.apache.tika.Tika
@@ -36,7 +36,7 @@ module Rika
   end
 
   class Parser
-    
+
     def initialize(file_location, max_content_length = -1, detector = DefaultDetector.new)
       @uri = file_location
       @tika = Tika.new(detector)
@@ -48,14 +48,14 @@ module Rika
 
     def content
       self.parse
-      @content 
+      @content
     end
 
     def metadata
       unless @metadata_ruby
         self.parse
         @metadata_ruby = {}
-      
+
         @metadata_java.names.each do |name|
           @metadata_ruby[name] = @metadata_java.get(name)
         end
@@ -85,7 +85,7 @@ module Rika
 
     def language
       @lang ||= LanguageIdentifier.new(content)
-      
+
       @lang.language
     end
 
@@ -96,7 +96,7 @@ module Rika
     end
 
     protected
-    
+
     def parse
       @content ||= @tika.parse_to_string(input_stream, @metadata_java).to_s.strip
     end

data/lib/rika/version.rb

@@ -1,3 +1,3 @@
 module Rika
-  VERSION = "1.4.0"
+  VERSION = "1.5.0"
 end

data/pom.xml

@@ -3,7 +3,7 @@
   <modelVersion>4.0.0</modelVersion>
 
   <name>Rika</name>
-  
+
   <groupId>org.rika</groupId>
   <artifactId>Rika</artifactId>
   <version>1.0-SNAPSHOT</version>
@@ -13,8 +13,8 @@
     <dependency>
       <groupId>org.apache.tika</groupId>
       <artifactId>tika-parsers</artifactId>
-      <version>1.4</version>
+      <version>1.5</version>
       <scope>test</scope>
     </dependency>
   </dependencies>
-</project>
+</project>

data/rika.gemspec

@@ -15,7 +15,7 @@ Gem::Specification.new do |gem|
   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", "2.12.0"
-  gem.add_development_dependency "rake", "10.0.3"
+  gem.add_development_dependency "rspec", "2.14.1"
+  gem.add_development_dependency "rake", "10.3.1"
   gem.platform = "java"
 end

data/spec/rika_spec.rb

@@ -4,8 +4,8 @@ require 'spec_helper'
 require 'webrick'
 
 include WEBrick
- 
-describe Rika::Parser do 
+
+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"))
@@ -13,13 +13,13 @@ describe Rika::Parser do
     @pdf_parser = Rika::Parser.new(file_path("document.pdf"))
     @image_parser = Rika::Parser.new(file_path("image.jpg"))
     @unknown_parser = Rika::Parser.new(file_path("unknown.bin"))
-    @dir = File.expand_path(File.join(File.dirname(__FILE__), 'fixtures'))  
-    port = 50505
+    @dir = File.expand_path(File.join(File.dirname(__FILE__), 'fixtures'))
+    port = 50515
     @url = "http://#{Socket.gethostname}:#{port}"
     @quote = "First they ignore you, then they ridicule you, then they fight you, then you win."
     @t1 = Thread.new do
-      @server = HTTPServer.new(:Port => port, :DocumentRoot => @dir, 
-      :AccessLog => [], :Logger => WEBrick::Log::new("/dev/null", 7))  
+      @server = HTTPServer.new(:Port => port, :DocumentRoot => @dir,
+      :AccessLog => [], :Logger => WEBrick::Log::new("/dev/null", 7))
       @server.start
     end
     @sample_pdf_filespec = file_path("document.pdf")
@@ -55,7 +55,7 @@ describe Rika::Parser do
       @docx_parser.content.should == @quote
     end
 
-    it "should return the content in a pdf file" do 
+    it "should return the content in a pdf file" do
       @pdf_parser.content.should == @quote
     end
 
@@ -70,7 +70,7 @@ describe Rika::Parser do
 
     it "should only return max content length for file over http" do
       parser = Rika::Parser.new(@url + "/document.pdf", 6)
-      parser.content.should == "First"   
+      parser.content.should == "First"
     end
 
     it "should be possible to read files over 100k by default" do
@@ -88,8 +88,8 @@ describe Rika::Parser do
     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 
+  # 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
@@ -164,7 +164,7 @@ describe Rika::Parser do
 
   describe '#language' do
     it "should return the language of the content" do
-      
+
       ["en", "de", "fr", "ru", "es"].each do |lang|
         txt = Rika::Parser.new(file_path("#{lang}.txt"))
         txt.language.should == lang

metadata

@@ -1,15 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: rika
 version: !ruby/object:Gem::Version
-  version: 1.4.0
-  prerelease:
+  version: 1.5.0
 platform: java
 authors:
 - Richard Nyström
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2013-07-04 00:00:00.000000000 Z
+date: 2014-04-23 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rspec
@@ -17,14 +16,12 @@ dependencies:
     requirements:
     - - '='
       - !ruby/object:Gem::Version
-        version: 2.12.0
-    none: false
+        version: 2.14.1
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - '='
       - !ruby/object:Gem::Version
-        version: 2.12.0
-    none: false
+        version: 2.14.1
   prerelease: false
   type: :development
 - !ruby/object:Gem::Dependency
@@ -33,14 +30,12 @@ dependencies:
     requirements:
     - - '='
       - !ruby/object:Gem::Version
-        version: 10.0.3
-    none: false
+        version: 10.3.1
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - '='
       - !ruby/object:Gem::Version
-        version: 10.0.3
-    none: false
+        version: 10.3.1
   prerelease: false
   type: :development
 description: ' A JRuby wrapper for Apache Tika to extract text and metadata from various
@@ -89,24 +84,25 @@ files:
 - target/dependency/commons-compress-1.5.jar
 - target/dependency/commons-logging-1.1.1.jar
 - target/dependency/dom4j-1.6.1.jar
-- target/dependency/fontbox-1.8.1.jar
+- target/dependency/fontbox-1.8.4.jar
 - target/dependency/geronimo-stax-api_1.0_spec-1.0.1.jar
 - target/dependency/isoparser-1.0-RC-1.jar
 - target/dependency/jdom-1.0.jar
-- target/dependency/jempbox-1.8.1.jar
+- target/dependency/jempbox-1.8.4.jar
+- target/dependency/jhighlight-1.0.jar
 - target/dependency/juniversalchardet-1.0.3.jar
 - target/dependency/metadata-extractor-2.6.2.jar
 - target/dependency/netcdf-4.2-min.jar
-- target/dependency/pdfbox-1.8.1.jar
-- target/dependency/poi-3.9.jar
-- target/dependency/poi-ooxml-3.9.jar
-- target/dependency/poi-ooxml-schemas-3.9.jar
-- target/dependency/poi-scratchpad-3.9.jar
+- target/dependency/pdfbox-1.8.4.jar
+- target/dependency/poi-3.10-beta2.jar
+- target/dependency/poi-ooxml-3.10-beta2.jar
+- target/dependency/poi-ooxml-schemas-3.10-beta2.jar
+- target/dependency/poi-scratchpad-3.10-beta2.jar
 - target/dependency/rome-0.9.jar
 - target/dependency/slf4j-api-1.5.6.jar
 - target/dependency/tagsoup-1.2.1.jar
-- target/dependency/tika-core-1.4.jar
-- target/dependency/tika-parsers-1.4.jar
+- target/dependency/tika-core-1.5.jar
+- target/dependency/tika-parsers-1.5.jar
 - target/dependency/vorbis-java-core-0.1-tests.jar
 - target/dependency/vorbis-java-core-0.1.jar
 - target/dependency/vorbis-java-tika-0.1.jar
@@ -117,6 +113,7 @@ files:
 - target/dependency/xz-1.2.jar
 homepage: https://github.com/ricn/rika
 licenses: []
+metadata: {}
 post_install_message:
 rdoc_options: []
 require_paths:
@@ -126,18 +123,16 @@ required_ruby_version: !ruby/object:Gem::Requirement
   - - '>='
     - !ruby/object:Gem::Version
       version: '0'
-  none: false
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - '>='
     - !ruby/object:Gem::Version
       version: '0'
-  none: false
 requirements: []
 rubyforge_project:
-rubygems_version: 1.8.24
+rubygems_version: 2.1.9
 signing_key:
-specification_version: 3
+specification_version: 4
 summary: A JRuby wrapper for Apache Tika to extract text and metadata from various file formats.
 test_files:
 - spec/fixtures/de.txt