tabula-extractor 0.7.5-java → 0.7.6-java

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 4391bc1af8143d2f60ed2ad11a66cba9f96c955e
-  data.tar.gz: d0d905fbd5b2bae105a11a9fd01470921b7dd4f3
+  metadata.gz: 9ac7f1daa082acce10e82b94b01b31e07813ad4d
+  data.tar.gz: ac521bbba80d6b0571d904565cd31d9af5e7947a
 SHA512:
-  metadata.gz: 4ef1e681e511dc074381696689b8d86915f262d4538cf107be6b8844fcbf7102f20cedcdc8964f326178095e7cd9b47d912386801e57a0e4645ee27faacff4a5
-  data.tar.gz: 336c19a84cd2cf430e24ce0728a5f7753ca78e3b08e2f12251274da577dd2f0cfe2d6a5cf1b9df44dd09e85d9c4e5a80d2672e53632785bc70461f8ca10c3e17
+  metadata.gz: 0389d96e5a7a8ad20c147ed3170b922a501126211bec58b012f39662425599437f3f869002825b562cae57d44645ddb776088804f237e168b71473211a86c67a
+  data.tar.gz: 53dd7bd11684bf8b8ccd03ea9352140eb3dcc346b7018bee7d6b8049e7e70ee02f59b83e360d97ddf5b7f211a1dccbb83694aab8cb016c7a4ba656f46a37c4c4

data/README.md

@@ -1,7 +1,7 @@
 tabula-extractor
 ================
 
-[![Build Status](https://travis-ci.org/jazzido/tabula-extractor.png)](https://travis-ci.org/jazzido/tabula-extractor)
+[![Build Status](https://travis-ci.org/tabulapdf/tabula-extractor.png)](https://travis-ci.org/tabulapdf/tabula-extractor)
 
 Extract tables from PDF files. `tabula-extractor` is the table extraction engine that powers [Tabula](http://tabula.technology), now available as a library and command line program.
 
@@ -125,7 +125,7 @@ extractor.extract.each_with_index do |pdf_page, page_index|
   page_areas = [[250, 0, 325, 1700]]
 
   page_areas.each do |page_area|
-    out << pdf_page.get_area(page_area).make_table.to_csv
+    out << pdf_page.get_area(page_area).get_table.to_csv
     out << "\n\n"
   end
 
@@ -155,7 +155,7 @@ extractor.extract.each_with_index do |pdf_page, page_index|
   vertical_rulings = vertical_ruling_locations.map{|n| Tabula::Ruling.new(0, n * scale_factor, 0, 1000)}
 
   page_areas.each do |page_area|
-    out << pdf_page.get_area(page_area).make_table(:vertical_rulings => vertical_rulings).to_csv
+    out << pdf_page.get_area(page_area).get_table(:vertical_rulings => vertical_rulings).to_csv
     out << "\n\n"
   end
 end

data/lib/tabula/entities/page.rb

@@ -191,6 +191,10 @@ module Tabula
       end
     end
 
+    def has_text?
+      !self.texts.empty?
+    end
+
     # TODO no need for this, let's choose one name
     def ruling_lines
       get_ruling_lines!
@@ -258,7 +262,7 @@ module Tabula
         :height => self.height,
         :number => self.number,
         :rotation => self.rotation,
-        :texts => self.texts
+        :hasText => self.has_text?
       }.to_json(options)
     end
 

data/lib/tabula/entities/ruling.rb

@@ -239,7 +239,8 @@ module Tabula
     end
 
     def finite?
-      top != ::Float::INFINITY && left != ::Float::INFINITY && bottom != ::Float::INFINITY && right != ::Float::INFINITY
+      top != ::Float::INFINITY && left != ::Float::INFINITY && bottom != ::Float::INFINITY && right != ::Float::INFINITY &&
+      !top.nan? && !left.nan? && !bottom.nan? && !right.nan?
     end
 
     ##

data/lib/tabula/extraction.rb

@@ -371,26 +371,37 @@ module Tabula
 
 
     class PagesInfoExtractor
-      def initialize(pdf_filename, password='')
-        @pdf_filename = pdf_filename
-        @pdf_file = Extraction.openPDF(pdf_filename, password)
+      def initialize(pdf_file_path, password='')
+        @pdf_filename = pdf_file_path
+        @pdf_file = Extraction.openPDF(pdf_file_path, password)
         @all_pages = @pdf_file.getDocumentCatalog.getAllPages
+
+        @extractor = Tabula::Extraction::ObjectExtractor.new(pdf_file_path, :all )
       end
 
       def pages
+        found_page_with_texts = false
         Enumerator.new do |y|
           begin
             @all_pages.each_with_index do |page, i|
               contents = page.getContents
 
-              y.yield Tabula::Page.new(@pdf_filename,
+              if found_page_with_texts
+                page = Tabula::Page.new(@pdf_filename,
                                        page.findCropBox.width,
                                        page.findCropBox.height,
                                        page.getRotation.to_i,
                                        i+1) #remember, these are one-indexed
+              else 
+                page = @extractor.extract_page(i+1)
+                found_page_with_texts = page.has_text?
+              end
+
+              y.yield page
             end
           ensure
             @pdf_file.close
+            @extractor.close!
           end
         end
       end

data/lib/tabula/version.rb

@@ -1,3 +1,3 @@
 module Tabula
-  VERSION = '0.7.5'
+  VERSION = '0.7.6'
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: tabula-extractor
 version: !ruby/object:Gem::Version
-  version: 0.7.5
+  version: 0.7.6
 platform: java
 authors:
 - Manuel Aristarán
@@ -10,7 +10,7 @@ authors:
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2014-09-29 00:00:00.000000000 Z
+date: 2015-01-31 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -94,7 +94,6 @@ files:
 - .travis.yml
 - AUTHORS.md
 - Gemfile
-- Gemfile.lock
 - LICENSE.md
 - NOTICE.txt
 - README.md
@@ -147,7 +146,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project:
-rubygems_version: 2.4.1
+rubygems_version: 2.1.9
 signing_key:
 specification_version: 4
 summary: extract tables from PDF files

data/Gemfile.lock

@@ -1,39 +0,0 @@
-PATH
-  remote: .
-  specs:
-    tabula-extractor (0.7.5-java)
-      trollop (~> 2.0)
-
-GEM
-  remote: http://rubygems.org/
-  specs:
-    coderay (1.1.0)
-    columnize (0.8.9)
-    ffi (1.9.5-java)
-    method_source (0.8.2)
-    minitest (5.4.2)
-    pry (0.10.1-java)
-      coderay (~> 1.1.0)
-      method_source (~> 0.8.1)
-      slop (~> 3.4)
-      spoon (~> 0.0)
-    rake (10.3.2)
-    ruby-debug (0.10.4)
-      columnize (>= 0.1)
-      ruby-debug-base (~> 0.10.4.0)
-    ruby-debug-base (0.10.4-java)
-    slop (3.6.0)
-    spoon (0.0.4)
-      ffi
-    trollop (2.0)
-
-PLATFORMS
-  java
-
-DEPENDENCIES
-  bundler (>= 1.3.4)
-  minitest
-  pry
-  rake
-  ruby-debug
-  tabula-extractor!