burisu-docsplit 0.7.7 → 0.7.8

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 370a33126963926b13bef202fb15e05127a02db0
-  data.tar.gz: 76024f613e3ad9a339cc207ac428037c4ba6f7ef
+  metadata.gz: cc1638e9d3bdaf775ea840631c3e342a68e33059
+  data.tar.gz: 83834d054f1c95520aa375ebbd4d3f3ced1617d3
 SHA512:
-  metadata.gz: d3564ec6ea484e25fd09f8e3b135bdbfb31c02ed64e74f5f3f269c38fbd58ab9f2c0d63cf9387cedd7eb10549832d583819f2caf09e9d2c2b3316da1c31243e4
-  data.tar.gz: 6a88a1820ab2bf23a0dacab2d54d5949de9bee18d1ba2bda86ce67948dfec97f2dee8dd3195a01033199d2e0b5c28b8e530c7d493aaafa910d2781af82371ee8
+  metadata.gz: 93d0291009a6fb31e016f68862ee97a33cdd7f27f94c37a197078ccbe9c77f8ba5cbc5ccb19367991734e43065db7eb112510be9952c9fdbd16fb39fd5072f36
+  data.tar.gz: d0a3485206de1367d07b10ab800197396928b178c3516ae2796cda108ebb992cb19b2951579edaf7a6ec24e7ce7f0ad3a2f43ef20448664b84fe9285843eb709

data/docsplit.gemspec

@@ -1,6 +1,6 @@
 Gem::Specification.new do |s|
   s.name      = 'burisu-docsplit'
-  s.version   = '0.7.7'         # Keep version in sync with docsplit.rb
+  s.version   = '0.7.8'         # Keep version in sync with docsplit.rb
   s.homepage    = "http://documentcloud.github.com/docsplit/"
   s.summary     = "Break Apart Documents into Images, Text, Pages and PDFs"
   s.description = <<-EOS

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/pdf_extractor.rb

@@ -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: burisu-docsplit
 version: !ruby/object:Gem::Version
-  version: 0.7.7
+  version: 0.7.8
 platform: ruby
 authors:
 - Jeremy Ashkenas
@@ -10,7 +10,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-10-18 00:00:00.000000000 Z
+date: 2015-06-26 00:00:00.000000000 Z
 dependencies: []
 description: |2
       Docsplit is a command-line utility and Ruby library for splitting apart
@@ -66,8 +66,9 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.2.2
+rubygems_version: 2.4.5
 signing_key: 
 specification_version: 4
 summary: Break Apart Documents into Images, Text, Pages and PDFs
 test_files: []
+has_rdoc: