docsplit 0.3.1 → 0.3.3

data/docsplit.gemspec

@@ -1,7 +1,7 @@
 Gem::Specification.new do |s|
   s.name      = 'docsplit'
-  s.version   = '0.3.1'         # Keep version in sync with docsplit.rb
-  s.date      = '2010-8-10'
+  s.version   = '0.3.3'         # Keep version in sync with docsplit.rb
+  s.date      = '2010-8-17'
 
   s.homepage    = "http://documentcloud.github.com/docsplit/"
   s.summary     = "Break Apart Documents into Images, Text, Pages and PDFs"

data/lib/docsplit.rb

@@ -1,7 +1,7 @@
 # The Docsplit module delegates to the Java PDF extractors.
 module Docsplit
 
-  VERSION       = '0.3.1' # Keep in sync with gemspec.
+  VERSION       = '0.3.3' # Keep in sync with gemspec.
 
   ROOT          = File.expand_path(File.dirname(__FILE__) + '/..')
 

data/lib/docsplit/image_extractor.rb

@@ -24,6 +24,7 @@ module Docsplit
 
     # Convert a single PDF into page images at the specified size and format.
     def convert(pdf, size, format, previous=nil)
+      tempdir   = Dir.mktmpdir
       basename  = File.basename(pdf, File.extname(pdf))
       directory = directory_for(size)
       FileUtils.mkdir_p(directory) unless File.exists?(directory)
@@ -31,13 +32,14 @@ module Docsplit
       common    = "#{MEMORY_ARGS} #{DENSITY_ARG} #{resize_arg(size)} #{quality_arg(format)}"
       if previous
         FileUtils.cp(Dir[directory_for(previous) + '/*'], directory)
-        cmd = "OMP_NUM_THREADS=2 gm mogrify #{common} -unsharp 0x0.5+0.75 \"#{directory}/*.#{format}\" 2>&1"
+        cmd = "MAGICK_TMPDIR=#{tempdir} OMP_NUM_THREADS=2 gm mogrify #{common} -unsharp 0x0.5+0.75 \"#{directory}/*.#{format}\" 2>&1"
       else
-        cmd = "OMP_NUM_THREADS=2 gm convert +adjoin #{common} \"#{pdf}#{pages_arg}\" \"#{out_file}\" 2>&1"
+        cmd = "MAGICK_TMPDIR=#{tempdir} OMP_NUM_THREADS=2 gm convert +adjoin #{common} \"#{pdf}#{pages_arg}\" \"#{out_file}\" 2>&1"
       end
       result = `#{cmd}`.chomp
       raise ExtractionFailed, result if $? != 0
       renumber_images(out_file, format)
+      FileUtils.remove_entry_secure tempdir if File.exists?(tempdir)
     end
 
 

data/lib/docsplit/text_extractor.rb

@@ -42,7 +42,6 @@ module Docsplit
           end
         end
       end
-      FileUtils.remove_entry_secure @tempdir if @tempdir
     end
 
     # Does a PDF have any text embedded?
@@ -59,19 +58,20 @@ module Docsplit
 
     # Extract a page range worth of text from a PDF via OCR.
     def extract_from_ocr(pdf, pages)
-      @tempdir  ||= Dir.mktmpdir
+      tempdir = Dir.mktmpdir
       base_path = File.join(@output, @pdf_name)
       if pages
-        run "OMP_NUM_THREADS=2 gm convert +adjoin #{MEMORY_ARGS} #{OCR_FLAGS} #{pdf} #{@tempdir}/#{@pdf_name}_%d.tif 2>&1" unless @tiffs_generated
+        run "MAGICK_TMPDIR=#{tempdir} OMP_NUM_THREADS=2 gm convert +adjoin #{MEMORY_ARGS} #{OCR_FLAGS} #{pdf} #{tempdir}/#{@pdf_name}_%d.tif 2>&1" unless @tiffs_generated
         @tiffs_generated = true
         pages.each do |page|
-          run "tesseract #{@tempdir}/#{@pdf_name}_#{page - 1}.tif #{base_path}_#{page} 2>&1"
+          run "tesseract #{tempdir}/#{@pdf_name}_#{page - 1}.tif #{base_path}_#{page} 2>&1"
         end
       else
-        tiff = "#{@tempdir}/#{@pdf_name}.tif"
-        run "OMP_NUM_THREADS=2 gm convert #{MEMORY_ARGS} #{OCR_FLAGS} #{pdf} #{tiff} 2>&1"
+        tiff = "#{tempdir}/#{@pdf_name}.tif"
+        run "MAGICK_TMPDIR=#{tempdir} OMP_NUM_THREADS=2 gm convert #{MEMORY_ARGS} #{OCR_FLAGS} #{pdf} #{tiff} 2>&1"
         run "tesseract #{tiff} #{base_path} -l eng 2>&1"
       end
+      FileUtils.remove_entry_secure tempdir if File.exists?(tempdir)
     end
 
 

data/lib/docsplit/transparent_pdfs.rb

@@ -12,9 +12,9 @@ module Docsplit
         if ext.downcase == '.pdf'
           doc
         else
-          @tempdir ||= File.join(Dir.tmpdir, 'docsplit')
-          extract_pdf([doc], {:output => @tempdir})
-          File.join(@tempdir, File.basename(doc, ext) + '.pdf')
+          tempdir = File.join(Dir.tmpdir, 'docsplit')
+          extract_pdf([doc], {:output => tempdir})
+          File.join(tempdir, File.basename(doc, ext) + '.pdf')
         end
       end
     end

metadata

@@ -1,12 +1,13 @@
 --- !ruby/object:Gem::Specification 
 name: docsplit
 version: !ruby/object:Gem::Version 
+  hash: 21
   prerelease: false
   segments: 
   - 0
   - 3
-  - 1
-  version: 0.3.1
+  - 3
+  version: 0.3.3
 platform: ruby
 authors: 
 - Jeremy Ashkenas
@@ -15,7 +16,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2010-08-10 00:00:00 -04:00
+date: 2010-08-17 00:00:00 -04:00
 default_executable: 
 dependencies: []
 
@@ -60,23 +61,27 @@ rdoc_options: []
 require_paths: 
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement 
+  none: false
   requirements: 
   - - ">="
     - !ruby/object:Gem::Version 
+      hash: 3
       segments: 
       - 0
       version: "0"
 required_rubygems_version: !ruby/object:Gem::Requirement 
+  none: false
   requirements: 
   - - ">="
     - !ruby/object:Gem::Version 
+      hash: 3
       segments: 
       - 0
       version: "0"
 requirements: []
 
 rubyforge_project: docsplit
-rubygems_version: 1.3.6
+rubygems_version: 1.3.7
 signing_key: 
 specification_version: 3
 summary: Break Apart Documents into Images, Text, Pages and PDFs