docsplit 0.7.5 → 0.7.6

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: ebdecba4d9b5b3a19244e08a2f3bcbaff8d8fab1
-  data.tar.gz: adb719d204a184313c1d282c837a7d1c929977ff
+  metadata.gz: 6c4106dcd5d8d9f8f6a1915a99a438b293154e1e
+  data.tar.gz: 90450ce6412bbedb022f4bc68ec7171f47b5d829
 SHA512:
-  metadata.gz: 8e58b660472bbff77ce500e50007c1dcdeec9adce59d527d9e331b42bde76d4ff9f2df9aece56e3793eef9d49795aafeddc8a7dfc9bd56a4fa07ca69fa080ca2
-  data.tar.gz: 1ca0706ec0b4eca050c9a1d0a45858365f5bde18b639c3ff641278dc777a1edf17128585f264b2a128e36a5388d4b2c7b9386e8f0b1993e850bc995d625c731b
+  metadata.gz: 1f6ccf476687ce1bf3a5559f07d0f7d8ebd2a80034b102b3058f538fb962a3b537b8e3eaeb245df27f14a4dc70716b69e34599bb50edf3e99e7b8a7b3f38d98d
+  data.tar.gz: 912d974bc4ed17942d32a932232439cd2df6903d6d20e72af31e0e80a1c70fc5e58d4be63bd00f245c53be90dc93a815ffd41a25268072367a1a244a5cb59ec4

data/docsplit.gemspec

@@ -1,7 +1,7 @@
 Gem::Specification.new do |s|
   s.name      = 'docsplit'
-  s.version   = '0.7.5'         # Keep version in sync with docsplit.rb
-  s.date      = '2014-05-28'
+  s.version   = '0.7.6'         # Keep version in sync with docsplit.rb
+  s.date      = '2014-11-17'
 
   s.homepage    = "http://documentcloud.github.com/docsplit/"
   s.summary     = "Break Apart Documents into Images, Text, Pages and PDFs"

data/lib/docsplit.rb

@@ -5,7 +5,7 @@ require 'shellwords'
 # The Docsplit module delegates to the Java PDF extractors.
 module Docsplit
 
-  VERSION       = '0.7.5' # Keep in sync with gemspec.
+  VERSION       = '0.7.6' # Keep in sync with gemspec.
 
   ESCAPE        = lambda {|x| Shellwords.shellescape(x) }
 
@@ -16,7 +16,7 @@ module Docsplit
   
   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, :pdftailor => false, :tesseract => false}
+  DEPENDENCIES  = {:java => false, :gm => false, :pdftotext => false, :pdftk => false, :pdftailor => false, :tesseract => false, :osd => false}
 
   # Check for all dependencies, and note their absence.
   dirs = ENV['PATH'].split(File::PATH_SEPARATOR)
@@ -29,7 +29,14 @@ module Docsplit
     end
   end
 
-  # Raise an ExtractionFailed exception when the PDF is encrypted, or otherwise
+  # if tesseract is found check for the osd plugin so that we can do orientation independent OCR.
+  if DEPENDENCIES[:tesseract]
+    # osd will be listed in tesseract --listlangs
+    val = %x[ #{'tesseract --list-langs'} 2>&1 >/dev/null ]
+    DEPENDENCIES[:osd] = true if val =~ /\bosd\b/
+  end
+
+    # Raise an ExtractionFailed exception when the PDF is encrypted, or otherwise
   # broke.
   class ExtractionFailed < StandardError; end
 

data/lib/docsplit/command_line.rb

@@ -96,7 +96,9 @@ Options:
         end
         opts.on('-l', '--language [LANGUAGE]', 'set the language (ISO 639-2/T code) for text extraction') do |l|
           @options[:language] = l
-          @options[:clean] = false
+        end
+        opts.on('--no-orientation-detection', 'turn off automatic orientation detection in tesseract') do |n|
+          @options[:detect_orientation] = false
         end
         opts.on('-r', '--rolling', 'generate images from each previous image') do |r|
           @options[:rolling] = true

data/lib/docsplit/page_extractor.rb

@@ -9,13 +9,13 @@ module Docsplit
       extract_options opts
       [pdfs].flatten.each do |pdf|
         pdf_name = File.basename(pdf, File.extname(pdf))
-        page_path = File.join(@output, "#{pdf_name}_%d.pdf")
+        page_path = ESCAPE[File.join(@output, "#{pdf_name}")] + "_%d.pdf"
         FileUtils.mkdir_p @output unless File.exists?(@output)
         
         cmd = if DEPENDENCIES[:pdftailor] # prefer pdftailor, but keep pdftk for backwards compatability
-          "pdftailor unstitch --output #{ESCAPE[page_path]} #{ESCAPE[pdf]} 2>&1"
+          "pdftailor unstitch --output #{page_path} #{ESCAPE[pdf]} 2>&1"
         else
-          "pdftk #{ESCAPE[pdf]} burst output #{ESCAPE[page_path]} 2>&1"
+          "pdftk #{ESCAPE[pdf]} burst output #{page_path} 2>&1"
         end
         result = `#{cmd}`.chomp
         FileUtils.rm('doc_data.txt') if File.exists?('doc_data.txt')
@@ -33,4 +33,4 @@ module Docsplit
 
   end
 
-end
+end

data/lib/docsplit/pdf_extractor.rb

@@ -23,7 +23,7 @@ module Docsplit
       unless @@version_string
         null = windows? ? "NUL" : "/dev/null"
         @@version_string = `#{office_executable} -h 2>#{null}`.split("\n").first
-        if !!@@version_string.match(/[0-9]*/)
+        if !!@@version_string.to_s.match(/[0-9]*/)
           @@version_string = `#{office_executable} --version`.split("\n").first
         end
       end
@@ -61,6 +61,10 @@ module Docsplit
           /usr/lib64/openoffice
           /opt/openoffice.org3
           /app/vendor/libreoffice
+          /usr/bin/libreoffice
+          /usr/local/bin
+          /usr/lib64/libreoffice
+          /usr/lib64/openoffice.org3
         )
       end
       search_paths

data/lib/docsplit/text_extractor.rb

@@ -60,13 +60,14 @@ module Docsplit
       tempdir = Dir.mktmpdir
       base_path = File.join(@output, @pdf_name)
       escaped_pdf = ESCAPE[pdf]
+      psm = @detect_orientation ? "-psm 1" : ""
       if pages
         pages.each do |page|
           tiff = "#{tempdir}/#{@pdf_name}_#{page}.tif"
           escaped_tiff = ESCAPE[tiff]
           file = "#{base_path}_#{page}"
           run "MAGICK_TMPDIR=#{tempdir} OMP_NUM_THREADS=2 gm convert -despeckle +adjoin #{MEMORY_ARGS} #{OCR_FLAGS} #{escaped_pdf}[#{page - 1}] #{escaped_tiff} 2>&1"
-          run "tesseract #{escaped_tiff} #{ESCAPE[file]} -l #{@language} 2>&1"
+          run "tesseract #{escaped_tiff} #{ESCAPE[file]} -l #{@language} #{psm} 2>&1"
           clean_text(file + '.txt') if @clean_ocr
           FileUtils.remove_entry_secure tiff
         end
@@ -74,7 +75,8 @@ module Docsplit
         tiff = "#{tempdir}/#{@pdf_name}.tif"
         escaped_tiff = ESCAPE[tiff]
         run "MAGICK_TMPDIR=#{tempdir} OMP_NUM_THREADS=2 gm convert -despeckle #{MEMORY_ARGS} #{OCR_FLAGS} #{escaped_pdf} #{escaped_tiff} 2>&1"
-        run "tesseract #{escaped_tiff} #{base_path} -l #{@language} 2>&1"
+        #if the user says don't do orientation detection or the plugin is not installed, set psm to 0
+        run "tesseract #{escaped_tiff} #{base_path} -l #{@language} #{psm} 2>&1"
         clean_text(base_path + '.txt') if @clean_ocr
       end
     ensure
@@ -117,14 +119,15 @@ module Docsplit
     end
 
     def extract_options(options)
-      @output     = options[:output] || '.'
-      @pages      = options[:pages]
-      @force_ocr  = options[:ocr] == true
-      @forbid_ocr = options[:ocr] == false
-      @clean_ocr  = !(options[:clean] == false)
-      @language   = options[:language] || 'eng'
+      @output             = options[:output] || '.'
+      @pages              = options[:pages]
+      @force_ocr          = options[:ocr] == true
+      @forbid_ocr         = options[:ocr] == false
+      @language           = options[:language] || 'eng'
+      @clean_ocr          = (!(options[:clean] == false) and @language == 'eng')
+      @detect_orientation = ((options[:detect_orientation] != false) and DEPENDENCIES[:osd])
     end
 
   end
 
-end
+end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: docsplit
 version: !ruby/object:Gem::Version
-  version: 0.7.5
+  version: 0.7.6
 platform: ruby
 authors:
 - Jeremy Ashkenas
@@ -10,7 +10,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-05-28 00:00:00.000000000 Z
+date: 2014-11-17 00:00:00.000000000 Z
 dependencies: []
 description: |2
       Docsplit is a command-line utility and Ruby library for splitting apart