tabula-extractor 0.0.1-java → 0.5.0-java

data/lib/tabula/line_segment_detector.rb

@@ -0,0 +1,99 @@
+require 'java'
+require 'rbconfig'
+
+require 'ffi'
+
+require_relative './entities'
+require_relative './pdf_render'
+require File.join(File.dirname(__FILE__), '../../target/', Tabula::PDFBOX)
+
+java_import javax.imageio.ImageIO
+java_import java.awt.image.BufferedImage
+java_import org.apache.pdfbox.pdmodel.PDDocument
+
+module Tabula
+  module LSD
+    extend FFI::Library
+    ffi_lib File.expand_path('../../ext/' + case RbConfig::CONFIG['host_os']
+                                            when /mswin|msys|mingw|cygwin|bccwin|wince|emc/
+                                              'liblsd.dll'
+                                            when /darwin|mac os/
+                                              'liblsd.dylib'
+                                            when /linux/
+                                              if RbConfig::CONFIG['target_cpu'] == 'x86_64'
+                                                'liblsd-linux64.so'
+                                              else
+                                                'liblsd-linux32.so'
+                                              end
+                                            else
+                                              raise "unknown os: #{RbConfig::CONFIG['host_os']}"
+                                            end,
+                             File.dirname(__FILE__))
+
+    attach_function :lsd, [ :pointer, :buffer_in, :int, :int ], :pointer
+    attach_function :free_values, [ :pointer ], :void
+
+    def LSD.detect_lines_in_pdf_page(pdf_path, page_number, scale_factor=1)
+      pdf_file = PDDocument.loadNonSeq(java.io.File.new(pdf_path), nil)
+      bi = Tabula::Render.pageToBufferedImage(pdf_file.getDocumentCatalog.getAllPages[page_number - 1])
+      pdf_file.close
+      detect_lines(bi,scale_factor)
+    end
+
+    # image can be either a string (path to image) or a Java::JavaAwtImage::BufferedImage
+    # image to pixels: http://stackoverflow.com/questions/6524196/java-get-pixel-array-from-image
+    def LSD.detect_lines(image, scale_factor=1)
+      bimage = if image.class == Java::JavaAwtImage::BufferedImage
+                 image
+               elsif image.class == String
+                 ImageIO.read(java.io.File.new(image))
+                 else
+                 raise ArgumentError, 'image must be a string or a BufferedImage'
+               end
+      image = LSD.image_to_image_double(bimage)
+
+      lines_found_ptr = FFI::MemoryPointer.new(:int, 1)
+
+      out = lsd(lines_found_ptr, image, bimage.getWidth, bimage.getHeight)
+
+      lines_found = lines_found_ptr.get_int
+
+      rv = []
+      lines_found.times do |i|
+        a = out[7*8*i].read_array_of_type(:double, 7)
+
+        a_round = a[0..3].map(&:round)
+        p1, p2 = [[a_round[0], a_round[1]], [a_round[2], a_round[3]]]
+
+        rv << Tabula::Ruling.new(p1[1] * scale_factor,
+                                 p1[0] * scale_factor,
+                                 (p2[0] - p1[0]) * scale_factor,
+                                 (p2[1] - p1[1]) * scale_factor)
+      end
+
+      free_values(out)
+      bimage.flush
+      bimage.getGraphics.dispose
+      image = nil
+
+      return rv
+    end
+
+    private
+    def LSD.image_to_image_double(buffered_image)
+      width = buffered_image.getWidth; height = buffered_image.getHeight
+      raster_size = width * height
+
+      image_double = FFI::MemoryPointer.new(:double, raster_size)
+      pixels = Java::int[width * height].new
+      buffered_image.getRGB(0, 0, width, height, pixels, 0, width)
+
+      image_double.put_array_of_double 0, pixels.to_a
+    end
+
+  end
+end
+
+if __FILE__ == $0
+  puts Tabula::LSD.detect_lines_in_pdf_page ARGV[0], ARGV[1].to_i
+end

data/lib/tabula/pdf_dump.rb

@@ -3,7 +3,7 @@ require 'observer'
 require_relative './entities.rb'
 
 require 'java'
-require File.join(File.dirname(__FILE__), '../../target/pdfbox-app-1.8.0.jar')
+require File.join(File.dirname(__FILE__), '../../target/', Tabula::PDFBOX)
 java_import org.apache.pdfbox.pdfparser.PDFParser
 java_import org.apache.pdfbox.pdmodel.PDDocument
 java_import org.apache.pdfbox.util.PDFTextStripper
@@ -44,13 +44,14 @@ module Tabula
         c = text.getCharacter
         # probably not the fastest way of detecting printable chars
         self.characters << text  if c =~ PRINTABLE_RE
+
       end
     end
 
     class PagesInfoExtractor
       def initialize(pdf_filename)
         raise Errno::ENOENT unless File.exists?(pdf_filename)
-        @pdf_file = PDDocument.loadNonSeq(java.io.File.new(pdf_filename), nil)
+        @pdf_file = PDDocument.load(java.io.File.new(pdf_filename))
         @all_pages = @pdf_file.getDocumentCatalog.getAllPages
       end
 
@@ -99,13 +100,14 @@ module Tabula
                                        page.getRotation.to_i,
                                        i+1,
                                        @extractor.characters.map { |char|
-                                         Tabula::TextElement.new(char.getYDirAdj,
-                                                                 char.getXDirAdj,
-                                                                 char.getWidthDirAdj,
-                                                                 char.getHeightDir,
+                                         Tabula::TextElement.new(char.getYDirAdj.round(2),
+                                                                 char.getXDirAdj.round(2),
+                                                                 char.getWidthDirAdj.round(2),
+                                                                 char.getHeightDir.round(2),
                                                                  nil,
-                                                                 char.getFontSize,
-                                                                 char.getCharacter)
+                                                                 char.getFontSize.round(2),
+                                                                 char.getCharacter,
+                                                                 char.getWidthOfSpace)
                                        })
             end
           ensure

data/lib/tabula/pdf_render.rb

@@ -0,0 +1,64 @@
+require 'java'
+
+require File.join(File.dirname(__FILE__), '../../target/', Tabula::PDFBOX)
+
+java_import org.apache.pdfbox.pdmodel.PDDocument
+java_import org.apache.pdfbox.pdfviewer.PageDrawer
+java_import java.awt.image.BufferedImage
+java_import javax.imageio.ImageIO
+java_import java.awt.Dimension
+java_import java.awt.Color
+
+module Tabula
+  module Render
+
+    # render a PDF page to a graphics context, but skip rendering the text
+    # This is done to reduce 'noise' introduced by the text, we only
+    # care about lines.
+    class PageDrawerNoText < PageDrawer
+      def processTextPosition(text)
+      end
+    end
+
+    TRANSPARENT_WHITE = Color.new(255, 255, 255, 0)
+
+    def self.pageToBufferedImage(page, width=2048, pageDrawerClass=PageDrawerNoText)
+      cropbox = page.findCropBox
+      widthPt, heightPt = cropbox.getWidth, cropbox.getHeight
+      pageDimension = Dimension.new(widthPt, heightPt)
+      rotation = java.lang.Math.toRadians(page.findRotation)
+
+      scaling = width / (rotation == 0 ? widthPt : heightPt)
+      widthPx, heightPx = java.lang.Math.round(widthPt * scaling), java.lang.Math.round(heightPt * scaling)
+      
+      retval = if rotation != 0
+                 BufferedImage.new(heightPx, widthPx, BufferedImage::TYPE_BYTE_GRAY)
+               else
+                 BufferedImage.new(widthPx, heightPx, BufferedImage::TYPE_BYTE_GRAY)
+               end
+      graphics = retval.getGraphics()
+      graphics.setBackground(TRANSPARENT_WHITE)
+      graphics.clearRect(0, 0, retval.getWidth, retval.getHeight)
+      if rotation != 0
+        graphics.translate(retval.getWidth, 0.0)
+        graphics.rotate(rotation)
+      end
+      graphics.scale(scaling, scaling)
+      drawer = pageDrawerClass.new()
+      drawer.drawPage(graphics,  page, pageDimension)
+      graphics.dispose
+
+      return retval
+    end
+  end
+end
+
+# testing
+if __FILE__ == $0
+  pdf_file = PDDocument.loadNonSeq(java.io.File.new(ARGV[0]), nil)
+  bi = Tabula::Render.pageToBufferedImage(pdf_file.getDocumentCatalog.getAllPages[ARGV[1].to_i - 1])
+  puts bi.class
+  ImageIO.write(bi, 'png',
+                java.io.File.new('notext.png'))
+end
+

data/lib/tabula/table_extractor.rb

@@ -14,7 +14,6 @@ module Tabula
     def initialize(text_elements, options = {})
       self.text_elements = text_elements
       self.options = DEFAULT_OPTIONS.merge(options)
-      @merged = false
       merge_words! if self.options[:merge_words]
     end
 
@@ -42,9 +41,9 @@ module Tabula
     end
 
     def get_columns
-      Tabula.group_by_columns(text_elements).map { |c|
+      Tabula.group_by_columns(text_elements).map do |c|
         {'left' => c.left, 'right' => c.right, 'width' => c.width}
-      }
+      end
     end
 
     def get_line_boundaries
@@ -108,6 +107,7 @@ module Tabula
           # is there a space? is this within `CHARACTER_DISTANCE_THRESHOLD` points of previous char?
           if (char1.text != " ") and (char2.text != " ") and self.text_elements[current_word_index].should_add_space?(char2)
             self.text_elements[current_word_index].text += " "
+            self.text_elements[current_word_index].width += self.text_elements[current_word_index].width_of_space
           end
           current_word_index = i+1
         end
@@ -135,11 +135,11 @@ module Tabula
   end
 
   def Tabula.lines_to_csv(lines)
-    CSV.generate { |csv|
-      lines.each { |l|
+    CSV.generate do |csv|
+      lines.each do |l|
         csv << l.map { |c| c.text.strip }
-      }
-    }
+      end
+    end
   end
 
   ONLY_SPACES_RE = Regexp.new('^\s+$')
@@ -154,45 +154,43 @@ module Tabula
 
     # find all the text elements
     # contained within each detected line (table row) boundary
-    line_boundaries.each { |lb|
+    line_boundaries.each do |lb|
       line = Line.new
 
-      line_members = text_elements.find_all { |te|
+      line_members = text_elements.find_all do |te|
         te.vertically_overlaps?(lb)
-      }
+      end
 
       text_elements -= line_members
 
-      line_members.sort_by(&:left).each { |te|
+      line_members.sort_by(&:left).each do |te|
         # skip text_elements that only contain spaces
         next if te.text =~ ONLY_SPACES_RE
         line << te
-      }
+      end
 
       lines << line if line.text_elements.size > 0
-    }
+    end
 
     lines.sort_by!(&:top)
 
     columns = Tabula.group_by_columns(lines.map(&:text_elements).flatten.compact.uniq).sort_by(&:left)
 
     # # insert empty cells if needed
-    lines.each_with_index { |l, line_index|
+    lines.each_with_index do |l, line_index|
       next if l.text_elements.nil?
       l.text_elements.compact! # TODO WHY do I have to do this?
       l.text_elements.uniq!  # TODO WHY do I have to do this?
       l.text_elements.sort_by!(&:left)
 
-      # l.text_elements = Tabula.merge_words(l.text_elements)
-
       next unless l.text_elements.size < columns.size
 
       columns.each_with_index do |c, i|
         if (i > l.text_elements.size - 1) or !l.text_elements(&:left)[i].nil? and !c.text_elements.include?(l.text_elements[i])
-          l.text_elements.insert(i, TextElement.new(l.top, c.left, c.width, l.height, nil, 0, ''))
+          l.text_elements.insert(i, TextElement.new(l.top, c.left, c.width, l.height, nil, 0, '', 0))
         end
       end
-    }
+    end
 
     # # merge elements that are in the same column
     columns = Tabula.group_by_columns(lines.map(&:text_elements).flatten.compact.uniq)
@@ -230,8 +228,9 @@ module Tabula
         lines[i+1] = nil
       end
     end
-    lines.compact.map { |line|
+
+    lines.compact.map do |line|
       line.text_elements.sort_by(&:left)
-    }
+    end
   end
 end

data/lib/tabula/version.rb

@@ -1,3 +1,3 @@
 module Tabula
-  VERSION = '0.0.1'
+  VERSION = '0.5.0'
 end

data/lib/tabula/writers.rb

@@ -16,7 +16,7 @@ module Tabula
 
     def Writers.TSV(lines, output=$stdout)
       tsv_string = lines.each { |l|
-        output.write(l.map(&:text).join("\t") + '\n')
+        output.write(l.map(&:text).join("\t") + "\n")
       }
     end
 

data/tabula-extractor.gemspec

@@ -14,13 +14,14 @@ Gem::Specification.new do |s|
 
   s.platform = 'java'
 
-  s.files         = `git ls-files`.split("\n")
+  shared_libs = ['liblsd.dylib', 'liblsd-linux64.so', 'liblsd-linux32.so', 'liblsd.dll'].map { |f| 'ext/' + f }
+  s.files         = `git ls-files`.split("\n") + shared_libs.map.reject { |f| !File.exists?(f) }
   s.test_files    = `git ls-files -- {test,features}/*`.split("\n")
   s.executables   = `git ls-files -- bin/*`.split("\n").map{ |f| File.basename(f) }
   s.require_paths = ["lib"]
 
   s.add_development_dependency 'minitest'
-  s.add_development_dependency 'bundler', '>= 1.3.5'
+  s.add_development_dependency 'bundler', '>= 1.3.4'
 
   s.add_runtime_dependency "trollop", ["~> 2.0"]
 end

data/test/tests.rb

@@ -1,4 +1,5 @@
 # -*- coding: utf-8 -*-
+require 'minitest'
 require 'minitest/autorun'
 
 require_relative '../lib/tabula'
@@ -9,7 +10,7 @@ def lines_to_array(lines)
   }
 end
 
-class TestPagesInfoExtractor < MiniTest::Unit::TestCase
+class TestPagesInfoExtractor < Minitest::Test
   def test_pages_info_extractor
     extractor = Tabula::Extraction::PagesInfoExtractor.new(File.expand_path('data/gre.pdf', File.dirname(__FILE__)))
 
@@ -23,7 +24,7 @@ class TestPagesInfoExtractor < MiniTest::Unit::TestCase
 end
 
 
-class TestDumper < MiniTest::Unit::TestCase
+class TestDumper < Minitest::Test
 
   def test_extractor
     extractor = Tabula::Extraction::CharacterExtractor.new(File.expand_path('data/gre.pdf', File.dirname(__FILE__)))
@@ -40,7 +41,7 @@ class TestDumper < MiniTest::Unit::TestCase
   end
 end
 
-class TestExtractor < MiniTest::Unit::TestCase
+class TestExtractor < Minitest::Test
 
   def test_table_extraction_1
     character_extractor = Tabula::Extraction::CharacterExtractor.new(File.expand_path('data/gre.pdf', File.dirname(__FILE__)))
@@ -54,7 +55,7 @@ class TestExtractor < MiniTest::Unit::TestCase
     character_extractor = Tabula::Extraction::CharacterExtractor.new(File.expand_path('data/argentina_diputados_voting_record.pdf', File.dirname(__FILE__)))
     characters = character_extractor.extract.next.get_text([269.875, 12.75, 790.5, 561])
 
-    expected = [["Apellido y Nombre", "Bloque político", "Provincia", ""], ["ABDALA de MATARAZZO, Norma Amanda", "Frente Cívico por Santiago", "Santiago del Estero", "AFIRMATIVO"], ["ALBRIEU, Oscar Edmundo Nicolas", "Frente para la Victoria - PJ", "Rio Negro", "AFIRMATIVO"], ["ALONSO, María Luz", "Frente para la Victoria - PJ", "La Pampa", "AFIRMATIVO"], ["ARENA, Celia Isabel", "Frente para la Victoria - PJ", "Santa Fe", "AFIRMATIVO"], ["ARREGUI, Andrés Roberto", "Frente para la Victoria - PJ", "Buenos Aires", "AFIRMATIVO"], ["AVOSCAN, Herman Horacio", "Frente para la Victoria - PJ", "Rio Negro", "AFIRMATIVO"], ["BALCEDO, María Ester", "Frente para la Victoria - PJ", "Buenos Aires", "AFIRMATIVO"], ["BARRANDEGUY, Raúl Enrique", "Frente para la Victoria - PJ", "Entre Ríos", "AFIRMATIVO"], ["BASTERRA, Luis Eugenio", "Frente para la Victoria - PJ", "Formosa", "AFIRMATIVO"], ["BEDANO, Nora Esther", "Frente para la Victoria - PJ", "Córdoba", "AFIRMATIVO"], ["BERNAL, María Eugenia", "Frente para la Victoria - PJ", "Jujuy", "AFIRMATIVO"], ["BERTONE, Rosana Andrea", "Frente para la Victoria - PJ", "Tierra del Fuego", "AFIRMATIVO"], ["BIANCHI, María del Carmen", "Frente para la Victoria - PJ", "Cdad. Aut. Bs. As.", "AFIRMATIVO"], ["BIDEGAIN, Gloria Mercedes", "Frente para la Victoria - PJ", "Buenos Aires", "AFIRMATIVO"], ["BRAWER, Mara", "Frente para la Victoria - PJ", "Cdad. Aut. Bs. As.", "AFIRMATIVO"], ["BRILLO, José Ricardo", "Movimiento Popular Neuquino", "Neuquén", "AFIRMATIVO"], ["BROMBERG, Isaac Benjamín", "Frente para la Victoria - PJ", "Tucumán", "AFIRMATIVO"], ["BRUE, Daniel Agustín", "Frente Cívico por Santiago", "Santiago del Estero", "AFIRMATIVO"], ["CALCAGNO, Eric", "Frente para la Victoria - PJ", "Buenos Aires", "AFIRMATIVO"], ["CARLOTTO, Remo Gerardo", "Frente para la Victoria - PJ", "Buenos Aires", "AFIRMATIVO"], ["CARMONA, Guillermo Ramón", "Frente para la Victoria - PJ", "Mendoza", "AFIRMATIVO"], ["CATALAN MAGNI, Julio César", "Frente para la Victoria - PJ", "Tierra del Fuego", "AFIRMATIVO"], ["CEJAS, Jorge Alberto", "Frente para la Victoria - PJ", "Rio Negro", "AFIRMATIVO"], ["CHIENO, María Elena", "Frente para la Victoria - PJ", "Corrientes", "AFIRMATIVO"], ["CIAMPINI, José Alberto", "Frente para la Victoria - PJ", "Neuquén", "AFIRMATIVO"], ["CIGOGNA, Luis Francisco Jorge", "Frente para la Victoria - PJ", "Buenos Aires", "AFIRMATIVO"], ["CLERI, Marcos", "Frente para la Victoria - PJ", "Santa Fe", "AFIRMATIVO"], ["COMELLI, Alicia Marcela", "Movimiento Popular Neuquino", "Neuquén", "AFIRMATIVO"], ["CONTI, Diana Beatriz", "Frente para la Victoria - PJ", "Buenos Aires", "AFIRMATIVO"], ["CORDOBA, Stella Maris", "Frente para la Victoria - PJ", "Tucumán", "AFIRMATIVO"], ["CURRILEN, Oscar Rubén", "Frente para la Victoria - PJ", "Chubut", "AFIRMATIVO"]]
+    expected = [["ABDALA de MATARAZZO, Norma Amanda", "Frente Cívico por Santiago", "Santiago del Estero", "AFIRMATIVO"], ["ALBRIEU, Oscar Edmundo Nicolas", "Frente para la Victoria - PJ", "Rio Negro", "AFIRMATIVO"], ["ALONSO, María Luz", "Frente para la Victoria - PJ", "La Pampa", "AFIRMATIVO"], ["ARENA, Celia Isabel", "Frente para la Victoria - PJ", "Santa Fe", "AFIRMATIVO"], ["ARREGUI, Andrés Roberto", "Frente para la Victoria - PJ", "Buenos Aires", "AFIRMATIVO"], ["AVOSCAN, Herman Horacio", "Frente para la Victoria - PJ", "Rio Negro", "AFIRMATIVO"], ["BALCEDO, María Ester", "Frente para la Victoria - PJ", "Buenos Aires", "AFIRMATIVO"], ["BARRANDEGUY, Raúl Enrique", "Frente para la Victoria - PJ", "Entre Ríos", "AFIRMATIVO"], ["BASTERRA, Luis Eugenio", "Frente para la Victoria - PJ", "Formosa", "AFIRMATIVO"], ["BEDANO, Nora Esther", "Frente para la Victoria - PJ", "Córdoba", "AFIRMATIVO"], ["BERNAL, María Eugenia", "Frente para la Victoria - PJ", "Jujuy", "AFIRMATIVO"], ["BERTONE, Rosana Andrea", "Frente para la Victoria - PJ", "Tierra del Fuego", "AFIRMATIVO"], ["BIANCHI, María del Carmen", "Frente para la Victoria - PJ", "Cdad. Aut. Bs. As.", "AFIRMATIVO"], ["BIDEGAIN, Gloria Mercedes", "Frente para la Victoria - PJ", "Buenos Aires", "AFIRMATIVO"], ["BRAWER, Mara", "Frente para la Victoria - PJ", "Cdad. Aut. Bs. As.", "AFIRMATIVO"], ["BRILLO, José Ricardo", "Movimiento Popular Neuquino", "Neuquén", "AFIRMATIVO"], ["BROMBERG, Isaac Benjamín", "Frente para la Victoria - PJ", "Tucumán", "AFIRMATIVO"], ["BRUE, Daniel Agustín", "Frente Cívico por Santiago", "Santiago del Estero", "AFIRMATIVO"], ["CALCAGNO, Eric", "Frente para la Victoria - PJ", "Buenos Aires", "AFIRMATIVO"], ["CARLOTTO, Remo Gerardo", "Frente para la Victoria - PJ", "Buenos Aires", "AFIRMATIVO"], ["CARMONA, Guillermo Ramón", "Frente para la Victoria - PJ", "Mendoza", "AFIRMATIVO"], ["CATALAN MAGNI, Julio César", "Frente para la Victoria - PJ", "Tierra del Fuego", "AFIRMATIVO"], ["CEJAS, Jorge Alberto", "Frente para la Victoria - PJ", "Rio Negro", "AFIRMATIVO"], ["CHIENO, María Elena", "Frente para la Victoria - PJ", "Corrientes", "AFIRMATIVO"], ["CIAMPINI, José Alberto", "Frente para la Victoria - PJ", "Neuquén", "AFIRMATIVO"], ["CIGOGNA, Luis Francisco Jorge", "Frente para la Victoria - PJ", "Buenos Aires", "AFIRMATIVO"], ["CLERI, Marcos", "Frente para la Victoria - PJ", "Santa Fe", "AFIRMATIVO"], ["COMELLI, Alicia Marcela", "Movimiento Popular Neuquino", "Neuquén", "AFIRMATIVO"], ["CONTI, Diana Beatriz", "Frente para la Victoria - PJ", "Buenos Aires", "AFIRMATIVO"], ["CORDOBA, Stella Maris", "Frente para la Victoria - PJ", "Tucumán", "AFIRMATIVO"], ["CURRILEN, Oscar Rubén", "Frente para la Victoria - PJ", "Chubut", "AFIRMATIVO"]]
 
     assert_equal expected, lines_to_array(Tabula.make_table(characters))
   end
@@ -62,9 +63,9 @@ class TestExtractor < MiniTest::Unit::TestCase
   # TODO Spaces inserted in words - fails
   def test_bo_page24
     character_extractor = Tabula::Extraction::CharacterExtractor.new(File.expand_path('data/bo_page24.pdf', File.dirname(__FILE__)))
-    characters = character_extractor.extract.next.get_text([435.625, 53.125, 570.7142857142857, 810.5357142857142])
+    characters = character_extractor.extract.next.get_text([435.625, 53.125, 585.7142857142857, 810.5357142857142])
 
-    expected = [["1", "UNICA", "CECILIA KANDUS", "16/12/2008", "PEDRO ALBERTO GALINDEZ", "60279/09"], ["1", "UNICA", "CECILIA KANDUS", "10/06/2009", "PASTORA FILOMENA NAVARRO", "60280/09"], ["13", "UNICA", "MIRTA S. BOTTALLO DE VILLA", "02/07/2009", "MARIO LUIS ANGELERI, DNI 4.313.138", "60198/09"], ["16", "UNICA", "LUIS PEDRO FASANELLI", "22/05/2009", "PETTER o PEDRO KAHRS", "60244/09"], ["18", "UNICA", "ALEJANDRA SALLES", "26/06/2009", "RAUL FERNANDO FORTINI", "60236/09"], ["31", "UNICA", "MARÍA CRISTINA GARCÍA", "17/06/2009", "DOMINGO TRIPODI Y PAULA LUPPINO", "60302/09"], ["34", "UNICA", "SUSANA B.MARZIONI", "11/06/2009", "JESUSA CARMEN VAZQUEZ", "60177/09"], ["51", "UNICA", "MARIA LUCRECIA SERRAT", "19/05/2009", "DANIEL DECUADRO", "60227/09"], ["51", "UNICA", "MARIA LUCRECIA SERRAT", "12/02/2009", "ELIZABETH LILIANA MANSILLA ROMERO", "60150/09"], ["75", "UNICA", "IGNACIO M. REBAUDI BASAVILBASO", "01/07/2009", "ABALSAMO ALFREDO DANIEL", "60277/09"], ["94", "UNICA", "GABRIELA PALÓPOLI", "02/07/2009", "ALVAREZ ALICIA ESTHER", "60360/09"], ["96", "UNICA", "DANIEL PAZ EYNARD", "16/06/2009", "NELIDA ALBORADA ALCARAZ SERRANO", "60176/09"]]
+    expected = [["1", "UNICA", "CECILIA KANDUS", "16/12/2008", "PEDRO ALBERTO GALINDEZ", "60279/09"], ["1", "UNICA", "CECILIA KANDUS", "10/06/2009", "PASTORA FILOMENA NAVARRO", "60280/09"], ["13", "UNICA", "MIRTA S. BOTTALLO DE VILLA", "02/07/2009", "MARIO LUIS ANGELERI, DNI 4.313.138", "60198/09"], ["16", "UNICA", "LUIS PEDRO FASANELLI", "22/05/2009", "PETTER o PEDRO KAHRS", "60244/09"], ["18", "UNICA", "ALEJANDRA SALLES", "26/06/2009", "RAUL FERNANDO FORTINI", "60236/09"], ["31", "UNICA", "MARÍA CRISTINA GARCÍA", "17/06/2009", "DOMINGO TRIPODI Y PAULA LUPPINO", "60302/09"], ["34", "UNICA", "SUSANA B. MARZIONI", "11/06/2009", "JESUSA CARMEN VAZQUEZ", "60177/09"], ["51", "UNICA", "MARIA LUCRECIA SERRAT", "19/05/2009", "DANIEL DECUADRO", "60227/09"], ["51", "UNICA", "MARIA LUCRECIA SERRAT", "12/02/2009", "ELIZABETH LILIANA MANSILLA ROMERO", "60150/09"], ["75", "UNICA", "IGNACIO M. REBAUDI BASAVILBASO", "01/07/2009", "ABALSAMO ALFREDO DANIEL", "60277/09"], ["94", "UNICA", "GABRIELA PALÓPOLI", "02/07/2009", "ALVAREZ ALICIA ESTHER", "60360/09"], ["96", "UNICA", "DANIEL PAZ EYNARD", "16/06/2009", "NELIDA ALBORADA ALCARAZ SERRANO", "60176/09"]]
     assert_equal expected, lines_to_array(Tabula.make_table(characters))
   end
 

metadata

@@ -2,14 +2,14 @@
 name: tabula-extractor
 version: !ruby/object:Gem::Version
   prerelease:
-  version: 0.0.1
+  version: 0.5.0
 platform: java
 authors:
 - Manuel Aristarán
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2013-05-09 00:00:00.000000000 Z
+date: 2013-06-12 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: minitest
@@ -35,13 +35,13 @@ dependencies:
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: 1.3.5
+        version: 1.3.4
     none: false
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: 1.3.5
+        version: 1.3.4
     none: false
   prerelease: false
   type: :development
@@ -70,6 +70,7 @@ extensions: []
 extra_rdoc_files: []
 files:
 - ".gitignore"
+- ".travis.yml"
 - AUTHORS.md
 - Gemfile
 - LICENSE.md
@@ -77,15 +78,31 @@ files:
 - README.md
 - Rakefile
 - bin/tabula
+- ext/COPYING
+- ext/Makefile.OSX
+- ext/Makefile.defaults
+- ext/Makefile.linux32
+- ext/Makefile.linux64
+- ext/Makefile.mingw
+- ext/liblsd-linux32.so
+- ext/liblsd-linux64.so
+- ext/liblsd.def
+- ext/liblsd.dll
+- ext/liblsd.dylib
+- ext/lsd.c
+- ext/lsd.h
 - lib/tabula.rb
+- lib/tabula/core_ext.rb
 - lib/tabula/entities.rb
+- lib/tabula/line_segment_detector.rb
 - lib/tabula/pdf_dump.rb
+- lib/tabula/pdf_render.rb
 - lib/tabula/table_extractor.rb
 - lib/tabula/version.rb
 - lib/tabula/whitespace.rb
 - lib/tabula/writers.rb
 - tabula-extractor.gemspec
-- target/pdfbox-app-1.8.0.jar
+- target/pdfbox-app-2.0.0-SNAPSHOT.jar
 - test/data/ClinicalResearchDisclosureReport2012Q2.pdf
 - test/data/argentina_diputados_voting_record.pdf
 - test/data/bo_page24.pdf