rika 0.9.3-java → 0.9.4-java

data/README.md

@@ -31,6 +31,10 @@ Something like this:
 	# Return the content of the document:
 	parser.content 
 
+	# Return the media type for the document:
+	parser.media_type 
+	=> "application/pdf"
+
 	# Return the metadata field title if it exists:
 	parser.metadata["title"] if parser.metadata_exists?("title") 
 
@@ -42,7 +46,7 @@ Something like this:
 	parser.content # 10000 first chars returned
 
 	# Return content from URL
-	parser = Rika::Parser.new('http://www.exampleurl.com/example.pdf')
+	parser = Rika::Parser.new('http://riakhandbook.com/sample.pdf', 200)
 	parser.content
 ```
 ## Contributing

data/lib/rika.rb

@@ -46,6 +46,10 @@ module Rika
       metadata_hash
     end
 
+    def media_type
+      @media_type
+    end
+
     def available_metadata
       @metadata.names.to_a
     end
@@ -59,6 +63,7 @@ module Rika
     def parse_file
       input_stream = java.io.FileInputStream.new(java.io.File.new(@uri))
       @metadata.set("filename", File.basename(@uri))
+      @media_type = @tika.detect(java.io.FileInputStream.new(java.io.File.new(@uri)))
       @content = @tika.parse_to_string(input_stream, @metadata) 
     end
 
@@ -66,6 +71,7 @@ module Rika
       raise IOError, "File does not exist or can't be reached." if not Net::HTTP.get_response(URI(@uri)).is_a?(Net::HTTPSuccess)
       url = java.net.URL.new(@uri)
       input_stream = url.open_stream
+      @media_type = @tika.detect(url.open_stream)
       @metadata.set("url", @uri)
       @content = @tika.parse_to_string(input_stream, @metadata) 
     end

data/lib/rika/version.rb

@@ -1,3 +1,3 @@
 module Rika
-  VERSION = "0.9.3"
+  VERSION = "0.9.4"
 end

data/spec/rika_spec.rb

@@ -11,10 +11,11 @@ describe Rika::Parser do
     @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"))
+    @unknown_parser = Rika::Parser.new(file_path("unknown.bin"))
     @dir = File.expand_path(File.join(File.dirname(__FILE__), 'fixtures'))  
     port = 50505
     @url = "http://#{Socket.gethostname}:#{port}"
-    
+    @qoute = "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))  
@@ -41,15 +42,15 @@ describe Rika::Parser do
 
   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."
+      @txt_parser.content.strip.should == @qoute
     end
 
     it "should return the content in a docx file" do
-      @docx_parser.content.should == "First they ignore you, then they ridicule you, then they fight you, then you win."
+      @docx_parser.content.should == @qoute
     end
 
     it "should return the content in a pdf file" do 
-      @pdf_parser.content.should == "First they ignore you, then they ridicule you, then they fight you, then you win."
+      @pdf_parser.content.should == @qoute
     end
 
     it "should return no content for an image" do
@@ -73,7 +74,11 @@ describe Rika::Parser do
 
     it "should return the content from a file over http" do
       parser = Rika::Parser.new(@url + "/document.pdf")
-      parser.content.should == "First they ignore you, then they ridicule you, then they fight you, then you win."   
+      parser.content.should == @qoute   
+    end
+
+    it "should return empty string for unknown file" do
+      @unknown_parser.content.should be_empty
     end
   end
 
@@ -127,4 +132,23 @@ describe Rika::Parser do
       @docx_parser.metadata_exists?("title").should == true
     end
   end
+
+  describe '#media_type' do
+    it "should return application/pdf for a pdf file" do
+      @pdf_parser.media_type.should == "application/pdf"
+    end
+
+    it "should return text/plain for a txt file" do
+      @txt_parser.media_type.should == "text/plain"
+    end
+
+    it "should return application/pdf for a pdf over http" do
+      parser = Rika::Parser.new(@url + "/document.pdf")
+      parser.media_type.should == "application/pdf"
+    end
+
+    it "should return application/octet-stream for unknown file" do
+      @unknown_parser.media_type.should == "application/octet-stream"
+    end
+  end
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: rika
 version: !ruby/object:Gem::Version
-  version: 0.9.3
+  version: 0.9.4
   prerelease:
 platform: java
 authors:
@@ -9,7 +9,7 @@ authors:
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2012-09-23 00:00:00.000000000 Z
+date: 2012-09-25 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rspec
@@ -54,6 +54,7 @@ files:
 - spec/fixtures/over_100k_file.txt
 - spec/fixtures/text_file.txt
 - spec/fixtures/text_file_without_extension
+- spec/fixtures/unknown.bin
 - spec/rika_spec.rb
 - spec/spec_helper.rb
 - target/dependency/apache-mime4j-core-0.7.2.jar
@@ -124,5 +125,6 @@ test_files:
 - spec/fixtures/over_100k_file.txt
 - spec/fixtures/text_file.txt
 - spec/fixtures/text_file_without_extension
+- spec/fixtures/unknown.bin
 - spec/rika_spec.rb
 - spec/spec_helper.rb