talentbox-docsplit 0.5.2 → 0.5.3

data/docsplit.gemspec

@@ -1,6 +1,6 @@
 Gem::Specification.new do |s|
   s.name      = 'talentbox-docsplit'
-  s.version   = '0.5.2'         # Keep version in sync with docsplit.rb
+  s.version   = '0.5.3'         # Keep version in sync with docsplit.rb
   s.date      = '2011-05-13'
 
   s.homepage    = "http://documentcloud.github.com/docsplit/"
@@ -21,4 +21,6 @@ Gem::Specification.new do |s|
 
   s.files = Dir['build/**/*', 'lib/**/*', 'bin/*', 'vendor/**/*',
                 'docsplit.gemspec', 'LICENSE', 'README']
+
+  s.add_runtime_dependency("file_wrapper", ["~> 0.4.1"])
 end

data/lib/docsplit.rb

@@ -14,8 +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]
+
+  GM_MIME_TYPES = ["image/png", "image/gif", "image/jpeg", "image/tiff", "image/x-ms-bmp", "image/x-portable-anymap", "image/x-portable-pixmap", "mage/svg+xml", "application/postscript"]
 
   DEPENDENCIES  = {:java => false, :gm => false, :pdftotext => false, :pdftk => false, :tesseract => false}
 
@@ -60,9 +60,9 @@ module Docsplit
     out = opts[:output] || '.'
     FileUtils.mkdir_p out unless File.exists?(out)
     [docs].flatten.each do |doc|
-      ext = File.extname(doc)
-      basename = File.basename(doc, ext)
-      if ext.length > 0 && GM_FORMATS.include?(ext.sub(/^\./, '').downcase.to_sym)
+      mime = FileWrapper.get_mime(doc)
+      basename = File.basename(doc, File.extname(doc))
+      if GM_MIME_TYPES.include?(mime)
         `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"
@@ -108,11 +108,11 @@ module Docsplit
     else            value.to_s
     end
   end
-
 end
 
 require 'tmpdir'
 require 'fileutils'
+require 'file_wrapper'
 require "#{Docsplit::ROOT}/lib/docsplit/image_extractor"
 require "#{Docsplit::ROOT}/lib/docsplit/transparent_pdfs"
 require "#{Docsplit::ROOT}/lib/docsplit/text_extractor"

data/lib/docsplit/transparent_pdfs.rb

@@ -8,13 +8,13 @@ module Docsplit
     # through further extraction.
     def ensure_pdfs(docs)
       [docs].flatten.map do |doc|
-        ext = File.extname(doc)
-        if ext.downcase == '.pdf'
+        mime = FileWrapper.get_mime(doc)
+        if mime == "application/pdf"
           doc
         else
           tempdir = File.join(Dir.tmpdir, 'docsplit')
           extract_pdf([doc], {:output => tempdir})
-          File.join(tempdir, File.basename(doc, ext) + '.pdf')
+          File.join(tempdir, File.basename(doc, File.extname(doc)) + '.pdf')
         end
       end
     end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: talentbox-docsplit
 version: !ruby/object:Gem::Version
-  version: 0.5.2
+  version: 0.5.3
   prerelease: 
 platform: ruby
 authors:
@@ -12,7 +12,18 @@ bindir: bin
 cert_chain: []
 date: 2011-05-13 00:00:00.000000000 +02:00
 default_executable: 
-dependencies: []
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: file_wrapper
+  requirement: &2152606320 !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: 0.4.1
+  type: :runtime
+  prerelease: false
+  version_requirements: *2152606320
 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