rika 0.9.2-java → 0.9.3-java

data/README.md

@@ -39,7 +39,11 @@ Something like this:
 
 	# Return only the first 10000 chars of the content:
 	parser = Rika::Parser.new('document.pdf', 10000)
-	parser.content # 10000 first chars returned	
+	parser.content # 10000 first chars returned
+
+	# Return content from URL
+	parser = Rika::Parser.new('http://www.exampleurl.com/example.pdf')
+	parser.content
 ```
 ## Contributing
 

data/lib/rika.rb

@@ -1,24 +1,34 @@
 raise "You need to run JRuby to use Rika" unless RUBY_PLATFORM =~ /java/
 
 require "rika/version"
+require 'uri'
+require 'net/http'
 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/1.2/api/org/apache/tika/Tika.html
 module Rika
   import org.apache.tika.metadata.Metadata
   import org.apache.tika.Tika
+  
   class Parser
     
-    def initialize(filename, max_content_length = -1)
-      if File.exists?(filename)
-        @filename = filename
-        @max_content_length = max_content_length
-        self.perform
+    def initialize(uri, max_content_length = -1)
+      p = URI::Parser.new
+      @uri = uri
+      @tika = Tika.new
+      @tika.set_max_string_length(max_content_length)
+      @metadata = Metadata.new
+      
+      if File.exists?(@uri)
+        self.parse_file
+      elsif p.parse(@uri).scheme == 'http' || p.parse(@uri).scheme == 'https'
+        self.parse_url
       else
-        raise IOError, "File does not exist"
+        raise IOError, "File does not exist or can't be reached."
       end
     end
 
@@ -41,26 +51,23 @@ module Rika
     end
 
     def metadata_exists?(name)
-      if @metadata.get(name) == nil
-        false
-      else
-        true
-      end
+      @metadata.get(name) != nil
     end
 
     protected
     
-    def perform
-      input_stream = nil
-      begin
-        input_stream = java.io.FileInputStream.new(java.io.File.new(@filename))
-        @metadata = Metadata.new
-        @metadata.set("filename", File.basename(@filename))
-        @tika = Tika.new
-        @content = @tika.parse_to_string(input_stream, @metadata, @max_content_length) 
-      ensure
-        input_stream.close  
-      end
+    def parse_file
+      input_stream = java.io.FileInputStream.new(java.io.File.new(@uri))
+      @metadata.set("filename", File.basename(@uri))
+      @content = @tika.parse_to_string(input_stream, @metadata) 
+    end
+
+    def parse_url
+      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
+      @metadata.set("url", @uri)
+      @content = @tika.parse_to_string(input_stream, @metadata) 
     end
   end
 end

data/lib/rika/version.rb

@@ -1,3 +1,3 @@
 module Rika
-  VERSION = "0.9.2"
+  VERSION = "0.9.3"
 end

data/spec/rika_spec.rb

@@ -1,17 +1,37 @@
 # encoding: utf-8
 
 require 'spec_helper'
+require 'webrick'
 
+include WEBrick
+ 
 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"))
+    @dir = File.expand_path(File.join(File.dirname(__FILE__), 'fixtures'))  
+    port = 50505
+    @url = "http://#{Socket.gethostname}:#{port}"
+    
+    @t1 = Thread.new do
+      @server = HTTPServer.new(:Port => port, :DocumentRoot => @dir, 
+      :AccessLog => [], :Logger => WEBrick::Log::new("/dev/null", 7))  
+      @server.start
+    end
+  end
+
+  after(:all) do
+    @t1.exit
   end
 
   it "should raise error if file does not exists" do
-    lambda { Rika::Parser.new(file_path("nonsense.txt")) }.should raise_error(IOError, "File does not exist")
+    lambda { Rika::Parser.new(file_path("nonsense.txt")) }.should raise_error(IOError, "File does not exist or can't be reached.")
+  end
+
+  it "should raise error if URL does not exists" do
+    lambda { Rika::Parser.new("http://nonsense.com/whatever.pdf") }.should raise_error(IOError, "File does not exist or can't be reached.")
   end
 
   it "should detect file type without a file extension" do
@@ -41,10 +61,20 @@ describe Rika::Parser do
       parser.content.should == "First"
     end
 
+    it "should only return max content length for file over http" do
+      parser = Rika::Parser.new(@url + "/document.pdf", 6)
+      parser.content.should == "First"   
+    end
+
     it "should be possible to read files over 100k by default" do
       parser = Rika::Parser.new(file_path("over_100k_file.txt"))
       parser.content.length.should == 101_761
     end
+
+    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."   
+    end
   end
 
   # We just test a few of the metadata fields for some common file formats 
@@ -67,6 +97,11 @@ describe Rika::Parser do
       @pdf_parser.metadata["title"].should == "A simple title"
     end
 
+    it "should return metadata from a file over http" do
+      parser = Rika::Parser.new(@url + "/document.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"

data/spec/spec_helper.rb

@@ -3,6 +3,7 @@ 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

metadata

@@ -1,15 +1,15 @@
 --- !ruby/object:Gem::Specification
 name: rika
 version: !ruby/object:Gem::Version
+  version: 0.9.3
   prerelease:
-  version: 0.9.2
 platform: java
 authors:
 - Richard Nyström
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2012-09-17 00:00:00.000000000 Z
+date: 2012-09-23 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rspec