lib/docsplit.rb in docsplit-0.6.3 vs lib/docsplit.rb in docsplit-0.6.4

- old
+ new

@@ -1,15 +1,22 @@ +require 'tmpdir' +require 'fileutils' +require 'shellwords' + # The Docsplit module delegates to the Java PDF extractors. module Docsplit - VERSION = '0.6.3' # Keep in sync with gemspec. + VERSION = '0.6.4' # Keep in sync with gemspec. + ESCAPE = lambda {|x| Shellwords.shellescape(x) } + ROOT = File.expand_path(File.dirname(__FILE__) + '/..') + ESCAPED_ROOT = ESCAPE[ROOT] - CLASSPATH = "#{ROOT}/build#{File::PATH_SEPARATOR}#{ROOT}/vendor/'*'" + CLASSPATH = "#{ESCAPED_ROOT}/build#{File::PATH_SEPARATOR}#{ESCAPED_ROOT}/vendor/'*'" - LOGGING = "-Djava.util.logging.config.file=#{ROOT}/vendor/logging.properties" + LOGGING = "-Djava.util.logging.config.file=#{ESCAPED_ROOT}/vendor/logging.properties" HEADLESS = "-Djava.awt.headless=true" office ||= "/usr/lib/openoffice" if File.exists? '/usr/lib/openoffice' office ||= "/usr/lib/libreoffice" if File.exists? '/usr/lib/libreoffice' @@ -18,14 +25,12 @@ METADATA_KEYS = [:author, :date, :creator, :keywords, :producer, :subject, :title, :length] 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} + DEPENDENCIES = {:java => false, :gm => false, :pdftotext => false, :pdftk => false, :pdftailor => false, :tesseract => false} - ESCAPE = lambda {|x| Shellwords.shellescape(x) } - # Check for all dependencies, and note their absence. dirs = ENV['PATH'].split(File::PATH_SEPARATOR) DEPENDENCIES.each_key do |dep| dirs.each do |dir| if File.executable?(File.join(dir, dep.to_s)) @@ -69,11 +74,11 @@ escaped_doc, escaped_out, escaped_basename = [doc, out, basename].map(&ESCAPE) if GM_FORMATS.include?(`file -b --mime #{ESCAPE[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-4.jar -r #{ROOT}/vendor/conf/document-formats.js" + options = "-jar #{ESCAPED_ROOT}/vendor/jodconverter/jodconverter-core-3.0-beta-4.jar -r #{ESCAPED_ROOT}/vendor/conf/document-formats.js" run "#{options} #{escaped_doc} #{escaped_out}/#{escaped_basename}.pdf", [], {} end end end @@ -115,12 +120,9 @@ end end end -require 'tmpdir' -require 'fileutils' -require 'shellwords' 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"