docsplit.rb in docsplit-0.5.0

- old
+ new

@@ -1,9 +1,9 @@
 # The Docsplit module delegates to the Java PDF extractors.
 module Docsplit
 
-  VERSION       = '0.4.1' # Keep in sync with gemspec.
+  VERSION       = '0.5.0' # Keep in sync with gemspec.
 
   ROOT          = File.expand_path(File.dirname(__FILE__) + '/..')
 
   CLASSPATH     = "#{ROOT}/build#{File::PATH_SEPARATOR}#{ROOT}/vendor/'*'"
 
@@ -70,11 +70,16 @@
         InfoExtractor.new.extract(:#{key}, pdfs, opts)
       end
     EOS
   end
 
+  # Utility method to clean OCR'd text with garbage characters.
+  def self.clean_text(text)
+    TextCleaner.new.clean(text)
+  end
 
+
   private
 
   # Runs a Java command, with quieted logging, and the classpath set properly.
   def self.run(command, pdfs, opts, return_output=false)
     pdfs    = [pdfs].flatten.map{|pdf| "\"#{pdf}\""}.join(' ')
@@ -101,5 +106,6 @@
 require "#{Docsplit::ROOT}/lib/docsplit/image_extractor"
 require "#{Docsplit::ROOT}/lib/docsplit/transparent_pdfs"
 require "#{Docsplit::ROOT}/lib/docsplit/text_extractor"
 require "#{Docsplit::ROOT}/lib/docsplit/page_extractor"
 require "#{Docsplit::ROOT}/lib/docsplit/info_extractor"
+require "#{Docsplit::ROOT}/lib/docsplit/text_cleaner"