docsplit.rb in docsplit-0.6.1

- old
+ new

@@ -1,23 +1,26 @@
 # The Docsplit module delegates to the Java PDF extractors.
 module Docsplit
 
-  VERSION       = '0.6.0' # Keep in sync with gemspec.
+  VERSION       = '0.6.1' # Keep in sync with gemspec.
 
   ROOT          = File.expand_path(File.dirname(__FILE__) + '/..')
 
   CLASSPATH     = "#{ROOT}/build#{File::PATH_SEPARATOR}#{ROOT}/vendor/'*'"
 
   LOGGING       = "-Djava.util.logging.config.file=#{ROOT}/vendor/logging.properties"
 
   HEADLESS      = "-Djava.awt.headless=true"
 
-  OFFICE        = RUBY_PLATFORM.match(/darwin/i) ? '' : '-Doffice.home=/usr/lib/openoffice'
+  office ||= "/usr/lib/openoffice" if File.exists? '/usr/lib/openoffice'
+  office ||= "/usr/lib/libreoffice" if File.exists? '/usr/lib/libreoffice'
 
+  OFFICE        = RUBY_PLATFORM.match(/darwin/i) ? '' : "-Doffice.home=#{office}"
+
   METADATA_KEYS = [:author, :date, :creator, :keywords, :producer, :subject, :title, :length]
   
-  GM_FORMATS    = [:png, :gif, :jpg, :jpeg, :tif, :tiff, :bmp, :pnm, :ppm, :svg, :eps]
+  GM_FORMATS    = ["image/gif", "image/jpeg", "image/png", "image/x-ms-bmp", "image/svg+xml", "image/tiff", "image/x-portable-bitmap", "application/postscript", "image/x-portable-pixmap"]
 
   DEPENDENCIES  = {:java => false, :gm => false, :pdftotext => false, :pdftk => false, :tesseract => false}
 
   ESCAPE        = lambda {|x| Shellwords.shellescape(x) }
 
@@ -63,13 +66,13 @@
     [docs].flatten.each do |doc|
       ext = File.extname(doc)
       basename = File.basename(doc, ext)
       escaped_doc, escaped_out, escaped_basename = [doc, out, basename].map(&ESCAPE)
 
-      if ext.length > 0 && GM_FORMATS.include?(ext.sub(/^\./, '').downcase.to_sym)
+      if GM_FORMATS.include?(`file -b --mime #{doc}`.strip.split(/[:;]\s+/)[0])
         `gm convert #{escaped_doc} #{escaped_out}/#{escaped_basename}.pdf`
       else
-        options = "-jar #{ROOT}/vendor/jodconverter/jodconverter-core-3.0-beta-3.jar -r #{ROOT}/vendor/conf/document-formats.js"
+        options = "-jar #{ROOT}/vendor/jodconverter/jodconverter-core-3.0-beta-4.jar -r #{ROOT}/vendor/conf/document-formats.js"
         run "#{options} #{escaped_doc} #{escaped_out}/#{escaped_basename}.pdf", [], {}
       end
     end
   end
 