tabula-extractor 0.6.4-java → 0.6.5-java

data/lib/tabula/line_segment_detector.rb

@@ -43,6 +43,18 @@ module Tabula
       :image_size => 2048
     }
 
+    def LSD.detect_lines_in_pdf(pdf_path, options={})
+      options = DETECT_LINES_DEFAULTS.merge(options)
+
+      pdf_file = PDDocument.loadNonSeq(java.io.File.new(pdf_path), nil)
+      lines = pdf_file.getDocumentCatalog.getAllPages.to_a.map do |page|
+        bi = Tabula::Render.pageToBufferedImage(page, options[:image_size])
+        detect_lines(bi, options[:scale_factor] || (page.findCropBox.width / options[:image_size]))
+      end
+      pdf_file.close
+      lines
+    end
+
     def LSD.detect_lines_in_pdf_page(pdf_path, page_number, options={})
       options = DETECT_LINES_DEFAULTS.merge(options)
 
@@ -67,10 +79,6 @@ module Tabula
                  raise ArgumentError, 'image must be a string or a BufferedImage'
                end
 
-      ImageIO.write(bimage,
-                    'png',
-                    java.io.File.new("/tmp/white.png"))
-
       image = LSD.image_to_image_double(bimage)
 
       lines_found_ptr = FFI::MemoryPointer.new(:int, 1)

data/lib/tabula/pdf_dump.rb

@@ -40,8 +40,6 @@ module Tabula
         self.characters = []; self.fonts = {}
       end
 
-
-
       def processTextPosition(text)
         # return if text.getCharacter == ' '
 

data/lib/tabula/table_extractor.rb

@@ -182,6 +182,10 @@ module Tabula
     default_options = {:separators => []}
     options = default_options.merge(options)
 
+    if text_elements.empty?
+      return []
+    end
+
     extractor = TableExtractor.new(text_elements, options).text_elements
     lines = group_by_lines(text_elements)
     top = lines[0].text_elements.map(&:top).min
@@ -211,11 +215,11 @@ module Tabula
       end
     end
 
-    table.lines.map do |l|
+    table.lines.map { |l|
       l.text_elements.map! { |te|
         te.nil? ? TextElement.new(nil, nil, nil, nil, nil, nil, '', nil) : te
       }
-    end
+    }.sort_by { |l| l.map { |te| te.top or 0 }.max }
 
   end
 

data/lib/tabula/version.rb

@@ -1,3 +1,3 @@
 module Tabula
-  VERSION = '0.6.4'
+  VERSION = '0.6.5'
 end

data/tabula-extractor.gemspec

@@ -11,6 +11,7 @@ Gem::Specification.new do |s|
   s.homepage    = "https://github.com/jazzido/tabula-extractor"
   s.summary     = %q{extract tables from PDF files}
   s.description = %q{extract tables from PDF files}
+  s.license     = 'MIT'
 
   s.platform = 'java'
 

metadata

@@ -2,7 +2,7 @@
 name: tabula-extractor
 version: !ruby/object:Gem::Version
   prerelease:
-  version: 0.6.4
+  version: 0.6.5
 platform: java
 authors:
 - Manuel Aristarán
@@ -11,7 +11,7 @@ authors:
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2013-07-09 00:00:00.000000000 Z
+date: 2013-07-23 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: minitest
@@ -133,7 +133,8 @@ files:
 - test/data/tabla_subsidios.pdf
 - test/tests.rb
 homepage: https://github.com/jazzido/tabula-extractor
-licenses: []
+licenses:
+- MIT
 post_install_message:
 rdoc_options: []
 require_paths: