rika 1.0.0-java → 1.1.1-java

data/.gitignore

@@ -17,3 +17,5 @@ test/version_tmp
 tmp
 
 .DS_Store
+projectFilesBackup/
+.idea/

data/README.md

@@ -25,42 +25,60 @@ Or install it yourself as:
 
 ## Usage
 
-Something like this:
+For a quick start with the simplest use cases, the following functions
+are provided to get what you need in a single function call, for your convenience:
+
+```ruby
+require 'rika'
+
+content           = Rika.parse_content('document.pdf')    # string containing all content text
+metadata          = Rika.parse_metadata('document.pdf')   # hash containing the document metadata
+content, metadata = Rika.parse_content_and_metadata('document.pdf')   # both of the above
+```
+
+For other use cases and finer control, you can work directly with the Rika::Parser object:
+
 ```ruby
-	require 'rika'
+require 'rika'
 
-	parser = Rika::Parser.new('document.pdf')
+parser = Rika::Parser.new('document.pdf')
 
-	# Return the content of the document:
-	parser.content 
+# Return the content of the document:
+parser.content 
 
-	# Return the media type for the document:
-	parser.media_type 
-	=> "application/pdf"
+# 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") 
+# Return the metadata field title if it exists:
+parser.metadata["title"] if parser.metadata_exists?("title") 
 
-	# Return all the available metadata keys that can be read from the document
-	parser.available_metadata
+# Return all the available metadata keys that can be read from the document
+parser.available_metadata
 
-	# Return only the first 10000 chars of the content:
-	parser = Rika::Parser.new('document.pdf', 10000)
-	parser.content # 10000 first chars returned
+# Return only the first 10000 chars of the content:
+parser = Rika::Parser.new('document.pdf', 10000)
+parser.content # 10000 first chars returned
 
-	# Return content from URL
-	parser = Rika::Parser.new('http://riakhandbook.com/sample.pdf', 200)
-	parser.content
+# Return content from URL
+parser = Rika::Parser.new('http://riakhandbook.com/sample.pdf', 200)
+parser.content
 
-	# Return the language for the content
-	parser = parser = Rika::Parser.new('german document.pdf')
-	parser.language
-	=> "de"
+# Return the language for the content
+parser = parser = Rika::Parser.new('german document.pdf')
+parser.language
+=> "de"
 
-	# Check whether the langugage identification is certain enough to be trusted
-	parser.language_is_reasonably_certain?
+# Check whether the langugage identification is certain enough to be trusted
+parser.language_is_reasonably_certain?
 	
 ```
+
+## Credits
+The following people have contributed ideas, documentation, or code to Rika:
+* Keith Bennett
+* Richard Nyström
+
 ## Contributing
 
 1. Fork it

data/lib/rika.rb

@@ -18,7 +18,23 @@ module Rika
   import org.apache.tika.language.LanguageIdentifier
   import java.io.FileInputStream
   import java.net.URL
-  
+
+  def self.parse_content_and_metadata(file_location, max_content_length = -1)
+    parser = Parser.new(file_location, max_content_length)
+    [parser.content, parser.metadata]
+  end
+
+  def self.parse_content(file_location, max_content_length = -1)
+    parser = Parser.new(file_location, max_content_length)
+    parser.content
+  end
+
+  def self.parse_metadata(file_location)
+    parser = Parser.new(file_location, 0)
+    parser.metadata
+  end
+
+
   class Parser
     
     def initialize(file_location, max_content_length = -1)

data/lib/rika/version.rb

@@ -1,3 +1,3 @@
 module Rika
-  VERSION = "1.0.0"
+  VERSION = "1.1.1"
 end

data/spec/rika_spec.rb

@@ -21,6 +21,7 @@ describe Rika::Parser do
       :AccessLog => [], :Logger => WEBrick::Log::new("/dev/null", 7))  
       @server.start
     end
+    @sample_pdf_filespec = file_path("document.pdf")
   end
 
   after(:all) do
@@ -173,4 +174,20 @@ describe Rika::Parser do
       lang.language_is_reasonably_certain? == true
     end
   end
-end
+
+  it "should return valid content using Rika.parse_content" do
+    content = Rika.parse_content(@sample_pdf_filespec)
+    (content.should be_a(String)) && (content.should_not be_empty)
+  end
+
+  it "should return valid metadata using Rika.parse_metadata" do
+    metadata = Rika.parse_metadata(@sample_pdf_filespec)
+    (metadata.should be_a(Hash)) && (metadata.should_not be_empty)
+  end
+
+  it "should return valid content and metadata using Rika.parse_content_and_metadata" do
+    content, metadata = Rika.parse_content_and_metadata(@sample_pdf_filespec)
+    (content.should be_a(String)) && (content.should_not be_empty) && \
+      (metadata.should be_a(Hash)) && (metadata.should_not be_empty)
+  end
+end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: rika
 version: !ruby/object:Gem::Version
-  version: 1.0.0
+  version: 1.1.1
   prerelease:
 platform: java
 authors:
@@ -9,7 +9,7 @@ authors:
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2013-02-23 00:00:00.000000000 Z
+date: 2013-02-26 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rspec
@@ -43,17 +43,17 @@ dependencies:
     none: false
   prerelease: false
   type: :development
-description: ! ' A JRuby wrapper for Apache Tika to extract text and metadata from
-  various file formats. '
+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
-- .travis.yml
+- ".gitignore"
+- ".rspec"
+- ".travis.yml"
 - Gemfile
 - LICENSE.txt
 - README.md
@@ -123,14 +123,14 @@ 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==