Docsplit 0.4.1 -- add office.home system property for Ubuntu.

Author: jashkenas

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/"

index.html

@@ -98,7 +98,7 @@ <h1>Doc<sub style="font-size:150%;">&#9889;</sub>split</h1>
       (title, author, number of pages...)
     </p>
 
-    <p>Docsplit is currently at <a href="http://rubygems.org/gems/docsplit">version 0.4.0</a>.</p>
+    <p>Docsplit is currently at <a href="http://rubygems.org/gems/docsplit">version 0.4.1</a>.</p>
 
     <p>
       <i>Docsplit is an open-source component of <a href="http://documentcloud.org/">DocumentCloud</a>.</i>
@@ -280,7 +280,7 @@ <h2 id="internals">Internals</h2>
     <h2 id="changes">Change Log</h2>
 
     <p>
-      <b class="header">0.4.0</b><br />
+      <b class="header">0.4.1</b><br />
       Upgraded the JODConverter dependency for PDF conversion via OpenOffice to
       3.0 beta. Added PNG, GIF, TIF, JPG, and BMP to the list of supported 
       formats.

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 @@ def self.extract_#{key}(pdfs, opts={})
   # 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