luccasmaso-docsplit 0.7.4.1 → 0.7.4.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 5c348a5547895d1dadbbd0330346bf1e295677a4
-  data.tar.gz: 5f90fad7ad4849b9b85854a4a50e8450b13b1b9e
+  metadata.gz: 503116ea38655488e9a9f29ca17b2be29a3585c0
+  data.tar.gz: 26b0bc22c27bda0ef2e711a7cb0ecd46852ee5f7
 SHA512:
-  metadata.gz: 90186b801914fe20ab18f1ab2c8bc5669a9933745e312f0a326d185c0060f4d7cc2d2b65194a8b9f1fe4db39495041a63222d6b2ead650ae991fd50124ea503c
-  data.tar.gz: eacf34acea2bfc17da2c0d84bdc2a696d9a32e22ca29326727a07cad422f82de6e11f98646d9b362d6cfb8f2dd248d96c091a965b048fd5e4f886ba5e3c7da4f
+  metadata.gz: 490f30ec2b1410e026c30a8fafc6676d5e117e33f4c326b11875a209d98df62964fca4ae1bf28397319408df425184c3b0d6b0fc9f8f98586545ae83df040cfa
+  data.tar.gz: 0dbac40654167ff244b0dea9552219537f4a0a8947d5587bd2fdb206d0d85916f0421ab19fc50d81ccaaeeb9c5b241dda3bee4bd7d74b52e8d15e0528a0222a6

data/docsplit.gemspec

@@ -1,8 +1,7 @@
 Gem::Specification.new do |s|
-  s.name      = 'luccasmaso-docsplit'
-  s.version   = '0.7.4.1'         # Keep version in sync with docsplit.rb
-  s.date      = '2014-02-16'
-
+  s.name        = 'luccasmaso-docsplit'
+  s.version     = '0.7.4.2'         # 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"
   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       = '0.7.4' # 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

@@ -99,7 +99,9 @@ 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

data/lib/docsplit/transparent_pdfs.rb

@@ -8,17 +8,20 @@ module Docsplit
     # through further extraction.
     def ensure_pdfs(docs)
       [docs].flatten.map do |doc|
-        ext = File.extname(doc)
-        if ext.downcase == '.pdf' || File.open(doc, &:readline).force_encoding("BINARY") =~ /\A\%PDF-\d+(\.\d+)?$/
+        if is_pdf?(doc)
           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
 
+    def is_pdf?(doc)
+      File.extname(doc).downcase == '.pdf' || File.open(doc, 'rb', &:readline).force_encoding("BINARY") =~ /\A\%PDF-\d+(\.\d+)?/
+    end
+
   end
 
   extend TransparentPDFs

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: luccasmaso-docsplit
 version: !ruby/object:Gem::Version
-  version: 0.7.4.1
+  version: 0.7.4.2
 platform: ruby
 authors:
 - Jeremy Ashkenas
@@ -10,7 +10,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-02-16 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
@@ -66,7 +66,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: docsplit
-rubygems_version: 2.1.11
+rubygems_version: 2.0.14
 signing_key: 
 specification_version: 4
 summary: Break Apart Documents into Images, Text, Pages and PDFs