docsplit 0.4.0 → 0.4.1

data/docsplit.gemspec

@@ -1,6 +1,6 @@
 Gem::Specification.new do |s|
   s.name      = 'docsplit'
-  s.version   = '0.4.0'         # Keep version in sync with docsplit.rb
+  s.version   = '0.4.1'         # Keep version in sync with docsplit.rb
   s.date      = '2010-8-23'
 
   s.homepage    = "http://documentcloud.github.com/docsplit/"

data/lib/docsplit.rb

@@ -1,7 +1,7 @@
 # The Docsplit module delegates to the Java PDF extractors.
 module Docsplit
 
-  VERSION       = '0.4.0' # Keep in sync with gemspec.
+  VERSION       = '0.4.1' # Keep in sync with gemspec.
 
   ROOT          = File.expand_path(File.dirname(__FILE__) + '/..')
 
@@ -11,6 +11,8 @@ module Docsplit
 
   HEADLESS      = "-Djava.awt.headless=true"
 
+  OFFICE        = RUBY_PLATFORM.match(/darwin/i) ? '' : '-Doffice.home=/usr/lib/openoffice'
+
   METADATA_KEYS = [:author, :date, :creator, :keywords, :producer, :subject, :title, :length]
 
   DEPENDENCIES  = {:java => false, :gm => false, :pdftotext => false, :pdftk => false, :tesseract => false}
@@ -76,7 +78,7 @@ module Docsplit
   # 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(' ')
-    cmd     = "java #{HEADLESS} #{LOGGING} -cp #{CLASSPATH} #{command} #{pdfs} 2>&1"
+    cmd     = "java #{HEADLESS} #{LOGGING} #{OFFICE} -cp #{CLASSPATH} #{command} #{pdfs} 2>&1"
     result  = `#{cmd}`.chomp
     raise ExtractionFailed, result if $? != 0
     return return_output ? (result.empty? ? nil : result) : true

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification 
 name: docsplit
 version: !ruby/object:Gem::Version 
-  hash: 15
+  hash: 13
   prerelease: false
   segments: 
   - 0
   - 4
-  - 0
-  version: 0.4.0
+  - 1
+  version: 0.4.1
 platform: ruby
 authors: 
 - Jeremy Ashkenas