tabula-extractor 0.6.1-java → 0.6.3-java

data/Rakefile

@@ -6,7 +6,7 @@ require 'rake'
 Bundler::GemHelper.install_tasks
 
 task :test do
-  ruby 'test/tests.rb'
+  ruby %{-J-Xmx512m test/tests.rb}
 end
 
 task :default => [:test]

data/bin/tabula

@@ -61,7 +61,13 @@ def main
   out = opts[:outfile] == '-' ? $stdout : File.new(opts[:outfile], 'w')
   extractor = Tabula::Extraction::CharacterExtractor.new(filename, parse_pages_arg(opts[:pages]))
   extractor.extract.each_with_index do |page, page_index|
-    page_areas = opts[:guess] ? Tabula::TableGuesser::find_rects_on_page(Tabula::TableGuesser::load_pdf(filename), page_index) : [area]
+    if opts[:guess] 
+      lines = Tabula::Ruling::clean_rulings(Tabula::LSD::detect_lines_in_pdf_page(filename, page_index))
+      page_areas = Tabula::TableGuesser::find_rects_from_lines(lines)      
+      page_areas.map!{|rect| rect.dims(:top, :left, :bottom, :right)}
+    else
+      page_areas = [area]
+    end
 
     page_areas.each do |page_area|
       text = page.get_text( page_area )

data/lib/tabula/pdf_render.rb

@@ -20,7 +20,8 @@ module Tabula
       end
     end
 
-    TRANSPARENT_WHITE = java.awt.Color.new(255, 255, 255, 0)
+    #ugh jruby; suppresses "ambiguous method" warning that arises due to Java's overloaded constructor.
+    TRANSPARENT_WHITE =  java.awt.Color.java_class.constructor(Java::int, Java::int, Java::int, Java::int).new_instance(255, 255, 255, 0)
 
     # 2048 width is important, if this is too small, thin lines won't be drawn.
     def self.pageToBufferedImage(page, width=2048, pageDrawerClass=PageDrawerNoText)
@@ -30,8 +31,10 @@ module Tabula
       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)
-      
+      #widthPx, heightPx = java.lang.Math.round(widthPt * scaling), java.lang.Math.round(heightPt * scaling)
+      widthPx, heightPx = (java.lang.Math.java_send :round, [Java::float], widthPt * scaling ), (java.lang.Math.java_send :round, [Java::float], heightPt * scaling)
+
+
       retval = if rotation != 0
                  BufferedImage.new(heightPx, widthPx, BufferedImage::TYPE_BYTE_GRAY)
                else

data/lib/tabula/version.rb

@@ -1,3 +1,3 @@
 module Tabula
-  VERSION = '0.6.1'
+  VERSION = '0.6.3'
 end

data/test/tests.rb

@@ -16,14 +16,14 @@ class TestPagesInfoExtractor < Minitest::Test
 
     i = 0
     extractor.pages.each do |page|
-      assert_instance_of Tabula::Page, page      
+      assert_instance_of Tabula::Page, page
       i += 1
     end
     assert_equal 2, i
   end
 end
 
-class TestTableGuesser < MiniTest::Unit::TestCase
+class TestTableGuesser < Minitest::Test
 end
 
 class TestDumper < Minitest::Test
@@ -63,8 +63,8 @@ class TestExtractor < Minitest::Test
   end
 
   def test_forest_disclosure_report_dont_regress
-    # this is the current state of the expected output. Ideally the output should be like 
-    # test_forest_disclosure_report, with spaces around the & in Regional Pulmonary & Sleep 
+    # this is the current state of the expected output. Ideally the output should be like
+    # test_forest_disclosure_report, with spaces around the & in Regional Pulmonary & Sleep
     # and a solution for half-x-height-offset lines.
     pdf_file_path = File.expand_path('data/frx_2012_disclosure.pdf', File.dirname(__FILE__))
     character_extractor = Tabula::Extraction::CharacterExtractor.new(pdf_file_path)
@@ -82,7 +82,7 @@ class TestExtractor < Minitest::Test
                 ['AARON, JOHN', '', 'CLARKSVILLE, TN', 'MEALS', '$20.39'],
                 ['TOTAL', '', '', '','$20.39'],
                 ['AARON, JOSHUA, N', '', 'WEST GROVE, PA', 'MEALS', '$310.33'],
-                ["", "REGIONAL PULMONARY & SLEEP", "", "", ""], ["AARON, JOSHUA, N", "", "WEST GROVE, PA", "SPEAKING FEES", "$4,700.00"], ["", "MEDICINE", "", "", ""], 
+                ["", "REGIONAL PULMONARY & SLEEP", "", "", ""], ["AARON, JOSHUA, N", "", "WEST GROVE, PA", "SPEAKING FEES", "$4,700.00"], ["", "MEDICINE", "", "", ""],
                 ['TOTAL', '', '', '', '$5,010.33'],
                 ['AARON, MAUREEN, M', '', 'MARTINSVILLE, VA', 'MEALS', '$193.67'],
                 ['TOTAL', '', '', '', '$193.67'],
@@ -101,13 +101,14 @@ class TestExtractor < Minitest::Test
     characters = character_extractor.extract.next.get_text([170, 28, 185, 833])
                                                            #top left bottom right
     expected = [
-                 ["", "REGIONAL PULMONARY & SLEEP", "", "", ""], ["AARON, JOSHUA, N", "", "WEST GROVE, PA", "SPEAKING FEES", "$4,700.00"], ["", "MEDICINE", "", "", ""], 
+                 ["", "REGIONAL PULMONARY & SLEEP", "", "", ""], ["AARON, JOSHUA, N", "", "WEST GROVE, PA", "SPEAKING FEES", "$4,700.00"], ["", "MEDICINE", "", "", ""],
                 ]
 
     assert_equal expected, lines_to_array(Tabula.make_table_with_vertical_rulings(characters, :vertical_rulings => vertical_rulings))
   end
 
   def test_forest_disclosure_report
+    skip "Skipping until we support multiline cells"
     pdf_file_path = File.expand_path('data/frx_2012_disclosure.pdf', File.dirname(__FILE__))
     character_extractor = Tabula::Extraction::CharacterExtractor.new(pdf_file_path)
     lines = Tabula::TableGuesser.find_lines_on_page(pdf_file_path, 0)

metadata

@@ -2,7 +2,7 @@
 name: tabula-extractor
 version: !ruby/object:Gem::Version
   prerelease:
-  version: 0.6.1
+  version: 0.6.3
 platform: java
 authors:
 - Manuel Aristarán
@@ -11,23 +11,21 @@ authors:
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2013-06-18 00:00:00.000000000 Z
+date: 2013-06-29 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: minitest
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - '>='
       - !ruby/object:Gem::Version
-        version: !binary |-
-          MA==
+        version: '0'
     none: false
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - '>='
       - !ruby/object:Gem::Version
-        version: !binary |-
-          MA==
+        version: '0'
     none: false
   prerelease: false
   type: :development
@@ -35,13 +33,13 @@ dependencies:
   name: bundler
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - '>='
       - !ruby/object:Gem::Version
         version: 1.3.4
     none: false
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - '>='
       - !ruby/object:Gem::Version
         version: 1.3.4
     none: false
@@ -51,13 +49,13 @@ dependencies:
   name: trollop
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ~>
       - !ruby/object:Gem::Version
         version: '2.0'
     none: false
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ~>
       - !ruby/object:Gem::Version
         version: '2.0'
     none: false
@@ -71,8 +69,8 @@ executables:
 extensions: []
 extra_rdoc_files: []
 files:
-- ".gitignore"
-- ".travis.yml"
+- .gitignore
+- .travis.yml
 - AUTHORS.md
 - Gemfile
 - LICENSE.md
@@ -126,23 +124,15 @@ require_paths:
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
-  - - ">="
+  - - '>='
     - !ruby/object:Gem::Version
-      segments:
-      - 0
-      hash: 2
-      version: !binary |-
-        MA==
+      version: '0'
   none: false
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
-  - - ">="
+  - - '>='
     - !ruby/object:Gem::Version
-      segments:
-      - 0
-      hash: 2
-      version: !binary |-
-        MA==
+      version: '0'
   none: false
 requirements: []
 rubyforge_project: