Merge pull request #24 from minio-sk/feature-multiple_languages

Feature multiple languages

Author: jashkenas

lib/docsplit.rb

@@ -11,7 +11,10 @@ module Docsplit
 
   HEADLESS      = "-Djava.awt.headless=true"
 
-  OFFICE        = RUBY_PLATFORM.match(/darwin/i) ? '' : '-Doffice.home=/usr/lib/openoffice'
+  office ||= "/usr/lib/openoffice" if File.exists? '/usr/lib/openoffice'
+  office ||= "/usr/lib/libreoffice" if File.exists? '/usr/lib/libreoffice'
+
+  OFFICE        = RUBY_PLATFORM.match(/darwin/i) ? '' : "-Doffice.home=#{office}"
 
   METADATA_KEYS = [:author, :date, :creator, :keywords, :producer, :subject, :title, :length]
 

lib/docsplit/text_extractor.rb

@@ -66,15 +66,15 @@ def extract_from_ocr(pdf, pages)
           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 eng 2>&1"
+          run "tesseract #{escaped_tiff} #{ESCAPE[file]} -l #{@language} 2>&1"
           clean_text(file + '.txt') if @clean_ocr
           FileUtils.remove_entry_secure tiff
         end
       else
         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 eng 2>&1"
+        run "tesseract #{escaped_tiff} #{base_path} -l #{@language} 2>&1"
         clean_text(base_path + '.txt') if @clean_ocr
       end
     ensure
@@ -122,6 +122,7 @@ def extract_options(options)
       @force_ocr  = options[:ocr] == true
       @forbid_ocr = options[:ocr] == false
       @clean_ocr  = !(options[:clean] == false)
+      @language   = options[:language] || 'eng'
     end
 
   end

test/unit/test_extract_text.rb

@@ -38,6 +38,11 @@ def test_ocr_extraction
     end
   end
 
+  def test_ocr_extraction_in_mock_language
+    exception = assert_raise(Docsplit::ExtractionFailed) {Docsplit.extract_text('test/fixtures/corrosion.pdf', :pages => 'all', :output => OUTPUT, :language => "mock")}
+    assert exception.message.match("tessdata/mock"), "Expected problem with loading data for language 'mock'"
+  end
+
   def test_password_protected
     assert_raises(ExtractionFailed) do
       Docsplit.extract_text('test/fixtures/completely_encrypted.pdf')