docsplit 0.5.1 → 0.5.2

data/docsplit.gemspec

@@ -1,7 +1,7 @@
 Gem::Specification.new do |s|
   s.name      = 'docsplit'
-  s.version   = '0.5.1'         # Keep version in sync with docsplit.rb
-  s.date      = '2010-04-26'
+  s.version   = '0.5.2'         # Keep version in sync with docsplit.rb
+  s.date      = '2011-05-13'
 
   s.homepage    = "http://documentcloud.github.com/docsplit/"
   s.summary     = "Break Apart Documents into Images, Text, Pages and PDFs"
@@ -15,7 +15,6 @@ Gem::Specification.new do |s|
   s.authors           = ['Jeremy Ashkenas', 'Samuel Clay']
   s.email             = 'jeremy@documentcloud.org'
   s.rubyforge_project = 'docsplit'
-  s.has_rdoc          = false
 
   s.require_paths     = ['lib']
   s.executables       = ['docsplit']

data/lib/docsplit.rb

@@ -1,7 +1,7 @@
 # The Docsplit module delegates to the Java PDF extractors.
 module Docsplit
 
-  VERSION       = '0.5.1' # Keep in sync with gemspec.
+  VERSION       = '0.5.2' # Keep in sync with gemspec.
 
   ROOT          = File.expand_path(File.dirname(__FILE__) + '/..')
 
@@ -14,6 +14,8 @@ module Docsplit
   OFFICE        = RUBY_PLATFORM.match(/darwin/i) ? '' : '-Doffice.home=/usr/lib/openoffice'
 
   METADATA_KEYS = [:author, :date, :creator, :keywords, :producer, :subject, :title, :length]
+  
+  GM_FORMATS    = [:png, :gif, :jpg, :jpeg, :tif, :tiff, :bmp, :pnm, :ppm, :svg, :eps]
 
   DEPENDENCIES  = {:java => false, :gm => false, :pdftotext => false, :pdftk => false, :tesseract => false}
 
@@ -53,11 +55,19 @@ module Docsplit
   end
 
   # Use JODCConverter to extract the documents as PDFs.
+  # If the document is in an image format, use GraphicsMagick to extract the PDF.
   def self.extract_pdf(docs, opts={})
+    out = opts[:output] || '.'
+    FileUtils.mkdir_p out unless File.exists?(out)
     [docs].flatten.each do |doc|
-      basename = File.basename(doc, File.extname(doc))
-      options = "-jar #{ROOT}/vendor/jodconverter/jodconverter-core-3.0-beta-3.jar -r #{ROOT}/vendor/conf/document-formats.js"
-      run "#{options} \"#{doc}\" \"#{opts[:output] || '.'}/#{basename}.pdf\"", [], {}
+      ext = File.extname(doc)
+      basename = File.basename(doc, ext)
+      if GM_FORMATS.include?(ext.sub(/^\./, '').downcase.to_sym)
+        `gm convert "#{doc}" "#{out}/#{basename}.pdf"`
+      else
+        options = "-jar #{ROOT}/vendor/jodconverter/jodconverter-core-3.0-beta-3.jar -r #{ROOT}/vendor/conf/document-formats.js"
+        run "#{options} \"#{doc}\" \"#{out}/#{basename}.pdf\"", [], {}
+      end
     end
   end
 

data/lib/docsplit/text_cleaner.rb

@@ -1,4 +1,3 @@
-require 'iconv'
 require 'strscan'
 
 module Docsplit
@@ -36,6 +35,7 @@ module Docsplit
     # For the time being, `clean` uses the regular StringScanner, and not the
     # multibyte-aware version, coercing to ASCII first.
     def clean(text)
+      require 'iconv' unless defined?(Iconv)
       text    = Iconv.iconv('ascii//translit//ignore', 'utf-8', text).first
       scanner = StringScanner.new(text)
       cleaned = []

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification 
 name: docsplit
 version: !ruby/object:Gem::Version 
-  hash: 9
+  hash: 15
   prerelease: 
   segments: 
   - 0
   - 5
-  - 1
-  version: 0.5.1
+  - 2
+  version: 0.5.2
 platform: ruby
 authors: 
 - Jeremy Ashkenas
@@ -16,7 +16,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2010-04-26 00:00:00 Z
+date: 2011-05-13 00:00:00 Z
 dependencies: []
 
 description: "    Docsplit is a command-line utility and Ruby library for splitting apart\n    documents into their component parts: searchable UTF-8 plain text, page\n    images or thumbnails in any format, PDFs, single pages, and document\n    metadata (title, author, number of pages...)\n"