pdf_extract 0.5.0

data/.document

@@ -0,0 +1,5 @@
+lib/**/*.rb
+bin/*
+- 
+features/**/*.feature
+LICENSE.txt

data/.ruby-version

@@ -0,0 +1 @@
+jruby-1.7.3

data/Gemfile

@@ -0,0 +1,21 @@
+source "http://rubygems.org"
+# Add dependencies required to use your gem here.
+# Example:
+#   gem "activesupport", ">= 2.3.5"
+
+platform :jruby do
+#	gem 'tabula-extractor',github: "jazzido/tabula-extractor", :require => "tabula"
+	gem 'tesseract-ocr'
+	gem 'docsplit'
+	gem "bundler", ">= 1.0.0"
+end
+
+# Add dependencies to develop your gem here.
+# Include everything needed to run rake, tests, features, etc.
+group :development do
+	gem "jeweler", "~> 1.8.4"
+	gem "rake", ">= 10.0.3"
+
+ # gem "shoulda", ">= 0"
+#  gem "rdoc", "~> 3.12"
+end

data/Gemfile.lock

@@ -0,0 +1,70 @@
+GEM
+  remote: http://rubygems.org/
+  specs:
+    addressable (2.3.5)
+    builder (3.2.2)
+    call-me (0.0.2.3)
+      refining
+    docsplit (0.7.2)
+    faraday (0.8.7)
+      multipart-post (~> 1.1)
+    ffi (1.9.0-java)
+    ffi-extra (0.1.0)
+      ffi
+    ffi-inline (0.0.4.3)
+      ffi (>= 0.4.0)
+    git (1.2.5)
+    github_api (0.10.1)
+      addressable
+      faraday (~> 0.8.1)
+      hashie (>= 1.2)
+      multi_json (~> 1.4)
+      nokogiri (~> 1.5.2)
+      oauth2
+    hashie (2.0.5)
+    highline (1.6.19)
+    httpauth (0.2.0)
+    iso-639 (0.1.0)
+    jeweler (1.8.6)
+      builder
+      bundler (~> 1.0)
+      git (>= 1.2.5)
+      github_api (= 0.10.1)
+      highline (>= 1.6.15)
+      nokogiri (= 1.5.10)
+      rake
+      rdoc
+    json (1.8.0-java)
+    jwt (0.1.8)
+      multi_json (>= 1.5)
+    multi_json (1.7.7)
+    multi_xml (0.5.4)
+    multipart-post (1.2.0)
+    nokogiri (1.5.10-java)
+    oauth2 (0.9.2)
+      faraday (~> 0.8)
+      httpauth (~> 0.2)
+      jwt (~> 0.1.4)
+      multi_json (~> 1.0)
+      multi_xml (~> 0.5)
+      rack (~> 1.2)
+    rack (1.5.2)
+    rake (10.1.0)
+    rdoc (4.0.1)
+      json (~> 1.4)
+    refining (0.0.5.5)
+    tesseract-ocr (0.1.5)
+      call-me
+      ffi-extra
+      ffi-inline
+      iso-639
+
+PLATFORMS
+  java
+
+DEPENDENCIES
+  bundler (>= 1.0.0)
+  docsplit
+  jeweler (~> 1.8.4)
+  rake (>= 10.0.3)
+  tesseract-ocr

data/LICENSE.txt

@@ -0,0 +1,20 @@
+Copyright (c) 2013 noah pryor
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/README.rdoc

@@ -0,0 +1,19 @@
+= pdf_extract
+
+Description goes here.
+
+== Contributing to pdf_extract
+ 
+* Check out the latest master to make sure the feature hasn't been implemented or the bug hasn't been fixed yet.
+* Check out the issue tracker to make sure someone already hasn't requested it and/or contributed it.
+* Fork the project.
+* Start a feature/bugfix branch.
+* Commit and push until you are happy with your contribution.
+* Make sure to add tests for it. This is important so I don't break it in a future version unintentionally.
+* Please try not to mess with the Rakefile, version, or history. If you want to have your own version, or is otherwise necessary, that is fine, but please isolate to its own commit so I can cherry-pick around it.
+
+== Copyright
+
+Copyright (c) 2013 noah pryor. See LICENSE.txt for
+further details.
+

data/Rakefile

@@ -0,0 +1,45 @@
+# encoding: utf-8
+
+require 'rubygems'
+require 'bundler'
+begin
+  Bundler.setup(:default, :development)
+rescue Bundler::BundlerError => e
+  $stderr.puts e.message
+  $stderr.puts "Run `bundle install` to install missing gems"
+  exit e.status_code
+end
+require 'rake'
+
+require 'jeweler'
+Jeweler::Tasks.new do |gem|
+  # gem is a Gem::Specification... see http://docs.rubygems.org/read/chapter/20 for more options
+  gem.name = "pdf_extract"
+  gem.homepage = "http://github.com/noahpryor/pdf_extract"
+  gem.license = "MIT"
+  gem.summary = "PDF extraction. Best with jRuby"
+  gem.description = "description yo "
+  gem.email = "noah@noahpryor.com"
+  gem.authors = ["noah pryor"]
+  # dependencies defined in Gemfile
+end
+Jeweler::RubygemsDotOrgTasks.new
+
+require 'rake/testtask'
+Rake::TestTask.new(:test) do |test|
+  test.libs << 'lib' << 'test'
+  test.pattern = 'test/**/test_*.rb'
+  test.verbose = true
+end
+
+task :default => :test
+
+require 'rdoc/task'
+Rake::RDocTask.new do |rdoc|
+  version = File.exist?('VERSION') ? File.read('VERSION') : ""
+
+  rdoc.rdoc_dir = 'rdoc'
+  rdoc.title = "pdf_extract #{version}"
+  rdoc.rdoc_files.include('README*')
+  rdoc.rdoc_files.include('lib/**/*.rb')
+end

data/VERSION

@@ -0,0 +1 @@
+0.5.0

data/lib/pdf_extract.rb

@@ -0,0 +1,246 @@
+require 'java'
+require 'tesseract'
+require 'docsplit'
+#require 'image_voodoo'
+require 'json'
+require 'open-uri'
+class PageExtractor
+	attr_accessor :page, :results, :items, :image_path, :pdf_path, :results
+	def initialize(page)
+		@image_path = page[:image_path]
+		@pdf_path = page[:pdf_path]
+		@items = page[:items]
+		@page_num = page[:page] ||= 1
+		@results = {}
+	end
+
+	def process
+		items.each do |item|
+			case item[:kind]
+			when 'ocr' then extract_ocr(item)
+			when 'table' then extract_table(item)
+			end
+		end
+
+	end
+
+	def extract_ocr(item)
+		dimensions = item[:dimensions]
+		@results[item[:name]] = ocr_text(crop_image(dimensions))	
+	end
+
+	def crop_image(d)
+		new_image_name = "CR.png"
+	#	ImageVoodoo.with_image(image_path) do |img|
+			x1 = d[:x1]	
+			x2 = d[:x2]
+			y1 = d[:y1]
+			y2 = d[:y2]
+	#		img.with_crop(x1,y1,x2,y2) { |img2| img2.save new_image_name }
+	#	end
+		return new_image_name
+	end
+
+	def extract_table(item)
+		table = run_tabula(item[:dimensions])
+		@results[item[:name]] = lines_to_array(table)
+	end
+
+	def run_tabula(d)
+	area = [d[:y1],d[:x1],d[:y2],d[:x2]].join(", ")
+	table = `tabula --area='#{area}' #{pdf_path} --page=#{page_num}`
+	return table
+	end
+	
+	def lines_to_array(table)
+	  table.lines.map(&:chomp).map { |l|
+	    l.split(",")
+	  }
+	end
+
+	def ocr_text(image_path,blacklist='|',language=:eng)
+		e = Tesseract::Engine.new {|e|
+		  e.language  = language
+		  e.blacklist = blacklist
+		}
+		return e.text_for(image_path).strip
+	end
+end
+
+class Hash
+	def symbolize_keys!
+	  keys.each do |key|
+	    self[(key.to_sym rescue key) || key] = delete(key)
+	  end
+	  self
+	end
+end
+
+class PDFextract
+	attr_accessor :file_path, :results
+	attr_accessor :options,:text_dir,:base_dir
+	attr_accessor :image_dir, :output_dir, :pages
+
+	def initialize(schema)
+		schema.symbolize_keys!
+
+		@base_dir = Time.now.to_i.to_s
+		setup_folders(@base_dir)
+		@text_dir = @base_dir+'/text_files'
+		@image_dir = @base_dir+'/image_files'
+		@output_dir = @base_dir+'/output'
+		if schema[:file_url]
+			@file_path = get_file_from_url(schema[:file_url])
+		else
+			@file_path = get_file_from_path(schema[:file_path])
+			puts @file_path
+		end
+		@options = schema[:options] if schema[:options]
+		@pages = schema[:pages] if schema[:options]
+		@results = {}
+
+	end
+	def setup_folders(folder_name)
+			`rm -r #{folder_name}` if Dir.exists? folder_name
+			`mkdir #{folder_name}`
+			`mkdir #{text_dir}`
+			`mkdir #{output_dir}`
+	end
+
+	def get_file_from_url(file_url)
+		file_data = open(file_url).read
+		temp_file = open(@base_dir+"/temp-file.pdf","w")
+		temp_file.write file_data
+		temp_file.close
+		return temp_file.path
+	end
+	def get_file_from_path(path)
+		new_path = @base_dir+"/temp-file.pdf"
+		`cp #{path} #{new_path}` 
+		return new_path
+	end
+
+	def process
+		remove_protection if options[:remove_protection] == true 
+		results[:images] = pdf_to_image_files("all")
+		results[:text] = convert_to_text if options[:extract_all_text] == true 
+		process_pages
+		cleanup
+	end
+	def cleanup
+		`rm -r #{base_dir}`
+	end
+	def remove_protection
+		#todo
+
+	end
+	
+	def process_pages
+		pages.each do |page|
+			if page[:match] == "page_num"
+				page_num = page[:page]
+				page[:image_path] = image_dir+"/temp-file_#{page_num}.png"
+				page[:pdf_path] = file_path
+								
+			end
+			page_extractor = PageExtractor.new(page)
+			page_extractor.process
+			results[page_num] = page_extractor.results
+		end
+
+	end
+
+
+	def convert_to_text(pages = "all")
+		pdf_to_text_files(pages)
+		text = {}
+		#take the text from the pdf pages and load em into this shit
+		Dir.glob(text_dir+"/*.txt").each do |file|  
+			page_num = file.split("_")[-1].split(".")[0]
+			text[page_num] = File.open(file).read 
+		end
+		puts text
+		return text
+	end
+	def convert_to_image(pages = "all")
+		pdf_to_image_files(pages)
+		images = []
+		Dir.glob(image_dir+"/*.png").each do |file|  
+			images << file 
+		end
+	end
+
+	def pdf_to_image_files(pages)
+		Docsplit.extract_images(file_path,:output => image_dir, :format => [:png])
+	end
+
+	def pdf_to_text_files(pages)
+	    Docsplit.extract_text(file_path, :output => text_dir,:pages => pages)
+	end
+	def extract_with_ocr(page_path,dimensions)
+		engine = Tesseract::Engine.new(language: :eng)
+		engine.image = page_path
+		engine.select 1,34,59,281
+		text = engine.text.strip
+		dimensions[:result] = text 
+		return text
+	end
+	def self.extract_ocr(image_path,coords)
+		
+		x = coords["x1"]
+		y = coords["y1"]
+		width = coords["x2"] - x
+		height = coords["y2"] - y
+		puts image_path
+		puts [x,y,width,height]
+		engine = Tesseract::Engine.new(language: :eng)
+		engine.image = image_path
+		engine.select x,y,width,height
+		text = engine.text.strip
+		return text
+	end
+
+	def self.example_schema 
+		{
+			file_path: "test_files/dream-may.pdf",
+			options: {
+				remove_protection: false,
+				password: nil,
+				extract_all_text: true,
+				extract_text: []
+			},
+			pages: [{
+				match: "page_num",
+				page: 1,
+				items: [
+					{
+						name: 'title',
+						kind: 'ocr', #alternative is kind table
+						dimensions:  {
+							x1: 10,
+							x2: 282,
+							y1: 50,
+							y2: 100
+						}
+					},
+					{
+						name: 'units_table',
+						kind: 'table',
+						dimensions: {
+							x1: 0,
+							x2: 265.73,
+							y1: 184.94,
+							y2: 233.84
+						}
+					}
+				]
+			}]
+		}
+	end
+
+end
+puts 'woo'
+#coords = '[{"x1":59,"y1":55,"x2":237,"y2":95,"width":178,"height":40,"id":0,"page":1}]'
+#parsed = JSON.parse(coords)
+#puts parsed[0]
+#puts PDFextract.extract_ocr("document_560_1.pdf",parsed[0])

data/pdf_extract.gemspec

@@ -0,0 +1,72 @@
+# Generated by jeweler
+# DO NOT EDIT THIS FILE DIRECTLY
+# Instead, edit Jeweler::Tasks in Rakefile, and run 'rake gemspec'
+# -*- encoding: utf-8 -*-
+
+Gem::Specification.new do |s|
+  s.name = "pdf_extract"
+  s.version = "0.5.0"
+
+  s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
+  s.authors = ["noah pryor"]
+  s.date = "2013-07-16"
+  s.description = "description yo "
+  s.email = "noah@noahpryor.com"
+  s.extra_rdoc_files = [
+    "LICENSE.txt",
+    "README.rdoc"
+  ]
+  s.files = [
+    ".document",
+    ".ruby-version",
+    "Gemfile",
+    "Gemfile.lock",
+    "LICENSE.txt",
+    "README.rdoc",
+    "Rakefile",
+    "VERSION",
+    "lib/document.pdf",
+    "lib/document_1.png",
+    "lib/document_560_1.png",
+    "lib/pdf_extract.rb",
+    "pdf_extract-0.1.0.gem",
+    "pdf_extract-0.2.0.gem",
+    "pdf_extract-0.2.1.gem",
+    "pdf_extract-0.2.2.gem",
+    "pdf_extract-0.3.0.gem",
+    "pdf_extract-0.3.1.gem",
+    "pdf_extract.gemspec",
+    "test/helper.rb",
+    "test/test_pdf_extract.rb"
+  ]
+  s.homepage = "http://github.com/noahpryor/pdf_extract"
+  s.licenses = ["MIT"]
+  s.require_paths = ["lib"]
+  s.rubygems_version = "1.8.24"
+  s.summary = "PDF extraction. Best with jRuby"
+
+  if s.respond_to? :specification_version then
+    s.specification_version = 3
+
+    if Gem::Version.new(Gem::VERSION) >= Gem::Version.new('1.2.0') then
+      s.add_runtime_dependency(%q<tesseract-ocr>, [">= 0"])
+      s.add_runtime_dependency(%q<docsplit>, [">= 0"])
+      s.add_runtime_dependency(%q<bundler>, [">= 1.0.0"])
+      s.add_development_dependency(%q<jeweler>, ["~> 1.8.4"])
+      s.add_development_dependency(%q<rake>, [">= 10.0.3"])
+    else
+      s.add_dependency(%q<tesseract-ocr>, [">= 0"])
+      s.add_dependency(%q<docsplit>, [">= 0"])
+      s.add_dependency(%q<bundler>, [">= 1.0.0"])
+      s.add_dependency(%q<jeweler>, ["~> 1.8.4"])
+      s.add_dependency(%q<rake>, [">= 10.0.3"])
+    end
+  else
+    s.add_dependency(%q<tesseract-ocr>, [">= 0"])
+    s.add_dependency(%q<docsplit>, [">= 0"])
+    s.add_dependency(%q<bundler>, [">= 1.0.0"])
+    s.add_dependency(%q<jeweler>, ["~> 1.8.4"])
+    s.add_dependency(%q<rake>, [">= 10.0.3"])
+  end
+end
+

data/test/helper.rb

@@ -0,0 +1,18 @@
+require 'rubygems'
+require 'bundler'
+begin
+  Bundler.setup(:default, :development)
+rescue Bundler::BundlerError => e
+  $stderr.puts e.message
+  $stderr.puts "Run `bundle install` to install missing gems"
+  exit e.status_code
+end
+require 'test/unit'
+require 'shoulda'
+
+$LOAD_PATH.unshift(File.join(File.dirname(__FILE__), '..', 'lib'))
+$LOAD_PATH.unshift(File.dirname(__FILE__))
+require 'pdf_extract'
+
+class Test::Unit::TestCase
+end

data/test/test_pdf_extract.rb

@@ -0,0 +1,7 @@
+require 'helper'
+
+class TestPdfExtract < Test::Unit::TestCase
+  should "probably rename this file and start testing for real" do
+    flunk "hey buddy, you should probably rename this file and start testing for real"
+  end
+end

metadata

@@ -0,0 +1,157 @@
+--- !ruby/object:Gem::Specification
+name: pdf_extract
+version: !ruby/object:Gem::Version
+  version: 0.5.0
+  prerelease:
+platform: ruby
+authors:
+- noah pryor
+autorequire:
+bindir: bin
+cert_chain: []
+date: 2013-07-16 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: tesseract-ocr
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: !binary |-
+          MA==
+    none: false
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: !binary |-
+          MA==
+    none: false
+  prerelease: false
+  type: :runtime
+- !ruby/object:Gem::Dependency
+  name: docsplit
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: !binary |-
+          MA==
+    none: false
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: !binary |-
+          MA==
+    none: false
+  prerelease: false
+  type: :runtime
+- !ruby/object:Gem::Dependency
+  name: bundler
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.0.0
+    none: false
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.0.0
+    none: false
+  prerelease: false
+  type: :runtime
+- !ruby/object:Gem::Dependency
+  name: jeweler
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 1.8.4
+    none: false
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 1.8.4
+    none: false
+  prerelease: false
+  type: :development
+- !ruby/object:Gem::Dependency
+  name: rake
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 10.0.3
+    none: false
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 10.0.3
+    none: false
+  prerelease: false
+  type: :development
+description: ! 'description yo '
+email: noah@noahpryor.com
+executables: []
+extensions: []
+extra_rdoc_files:
+- LICENSE.txt
+- README.rdoc
+files:
+- ".document"
+- ".ruby-version"
+- Gemfile
+- Gemfile.lock
+- LICENSE.txt
+- README.rdoc
+- Rakefile
+- VERSION
+- lib/document.pdf
+- lib/document_1.png
+- lib/document_560_1.png
+- lib/pdf_extract.rb
+- pdf_extract-0.1.0.gem
+- pdf_extract-0.2.0.gem
+- pdf_extract-0.2.1.gem
+- pdf_extract-0.2.2.gem
+- pdf_extract-0.3.0.gem
+- pdf_extract-0.3.1.gem
+- pdf_extract.gemspec
+- test/helper.rb
+- test/test_pdf_extract.rb
+homepage: http://github.com/noahpryor/pdf_extract
+licenses:
+- MIT
+post_install_message:
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      segments:
+      - 0
+      hash: 2
+      version: !binary |-
+        MA==
+  none: false
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: !binary |-
+        MA==
+  none: false
+requirements: []
+rubyforge_project:
+rubygems_version: 1.8.24
+signing_key:
+specification_version: 3
+summary: PDF extraction. Best with jRuby
+test_files: []