rtesseract 2.0.1 → 2.1.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 6eae58279cf744227e79b7bbc9180f7aea852547
-  data.tar.gz: 3836aa96d24b7f1a0b957cf803553f547cc33544
+  metadata.gz: db992168bb87c6c4f3124403f9417c4cd46aca3e
+  data.tar.gz: b329a5ebc7316f28f63bcd7d84aa575cb661b3b9
 SHA512:
-  metadata.gz: 0ef57359c7c7f43094a50838b6d29d28d7808c9cadd8f2b8514c613be030161f8d640c41ba3d403c00fb59fdf85ffcbc57795f6c65b8418ad348eb1a6c07e901
-  data.tar.gz: ff5f0f94c8039bd0b38b0c9ec2618b4c38b07b9707e28ff29a3bb943abc85d5afaa543dfba1ba2b9e565d056ea558eda9b7f6d222a6adb43614cd86c6e8fdcac
+  metadata.gz: a74dc8fd03a678ecdff1425bc188173615da59b636cbe9ceb072353a1e4d3f2aa076b9787007ef9bfebb9c928e2a170d8c0149f864741c888c6d74ea04a78889
+  data.tar.gz: 97d3bfea1ae54841ce68427893e8e69fa358a3018ba80b8f06d23759abe0d89c81e481c5775699b3c0e98234fb39dfb898a42b833c48b8ac42128c7c7c292b88

data/.travis.yml

@@ -1,10 +1,11 @@
+sudo: required
+dist: trusty
 language: ruby
 addons:
   apt:
     packages:
     - tesseract-ocr
 
-sudo: false
 rvm:
   - 1.9.3
   - 2.0.0

data/CHANGELOG.md

@@ -1,3 +1,9 @@
+## v2.1.0
+
+#### Added
+
+* Support to generate searchable PDF
+
 ## v2.0.1
 
 #### Changed

data/README.rdoc

@@ -16,6 +16,8 @@ To work properly rtesseract are needed:
 
 Atention: Version 1.0.0 works fine with Ruby 2.0 and tesseract 3.0 and lower versions of rtesseract works fine with Ruby 1.8 and tesseract 2.0.4.
 
+PDF support requires a newer version of tesseract, specifically V.3.03 or above.
+
 == EXAMPLE USAGE
 
 It's very simple to use rtesseract:
@@ -23,7 +25,19 @@ It's very simple to use rtesseract:
 === CONVERT IMAGE TO STRING
 
   image = RTesseract.new("my_image.jpg")
-  image.to_s #Getting the value
+  image.to_s # Getting the value
+
+=== CONVERT IMAGE TO SEARCHABLE PDF
+
+  image = RTesseract.new("my_image.jpg")
+  image.to_pdf  # Getting the pdf path
+  image.to_s    # Still can get the value only.
+  # ...
+  # some stuff
+  # ...
+  image.clean   # to delete file once finished
+
+This will preserve the image colors, pictures and structure in the generated pdf.
 
 === CHANGE THE IMAGE
 
@@ -89,6 +103,7 @@ Language Options
      * por   - Portuguese
      * spa   - Spanish
      * vie   - Vietnamese
+     * or any other supported by tesseract.
   Note: Make sure you have installed the language to tesseract
 
 Other Options

data/VERSION

@@ -1 +1 @@
-2.0.1
+2.1.0

data/lib/rtesseract.rb

@@ -15,10 +15,9 @@ class RTesseract
   def initialize(src = '', options = {})
     self.configuration = RTesseract.local_config(options)
     @options = options || {}
-    @value = nil
     @points = {}
     @processor = RTesseract::Processor.choose_processor!(configuration.processor)
-    @source = @processor.image?(src) ? src : Pathname.new(src)
+    self.source = src
     initialize_hook
   end
 
@@ -29,6 +28,7 @@ class RTesseract
   # Define the source
   def source=(src)
     @value = nil
+    @pdf_path = nil
     @source = @processor.image?(src) ? src : Pathname.new(src)
   end
 
@@ -127,24 +127,50 @@ class RTesseract
     '.txt'
   end
 
+  # Detect version number
+  def tesseract_version
+    RTesseract::Utils.version_number
+  end
+
+
   # Rand file path
-  def text_file
-    @text_file = Pathname.new(Dir.tmpdir).join("#{Time.now.to_f}#{rand(1500)}").to_s
+  def file_dest
+    @file_dest = Pathname.new(Dir.tmpdir).join("#{Time.now.to_f}#{rand(1500)}").to_s
   end
 
-  # Full path of file with extension
-  def text_file_with_ext(ext = nil)
-    [@text_file, ext || file_ext].join('')
+  # Full path of file with txt extension
+  def file_with_ext(ext = nil)
+    [@file_dest, ext || file_ext].join('')
   end
 
   # Run command
   def convert_command
-    `#{configuration.command} "#{image}" "#{text_file}" #{lang} #{psm} #{tessdata_dir} #{user_words} #{user_patterns} #{config_file} #{clear_console_output} #{configuration.options_cmd.join(' ')}`
+    `#{configuration.command} "#{image}" "#{file_dest}" #{lang} #{psm} #{tessdata_dir} #{user_words} #{user_patterns} #{config_file} #{clear_console_output} #{options_cmd.join(' ')}`
+  end
+
+  # Is pdf output?
+  def pdf?
+    options_cmd.include? 'pdf'
   end
 
   # Read result file
   def convert_text
-    @value = File.read(text_file_with_ext).to_s
+    @value = File.read(file_with_ext).to_s
+  end
+
+  # Store pdf result path
+  def convert_pdf
+    @pdf_path = file_with_ext('.pdf')
+  end
+
+  # Convert result to proper type
+  def convert_result
+    if pdf?
+      convert_pdf
+    else
+      convert_text
+      RTesseract::Utils.remove_files([@image, file_with_ext])
+    end
   end
 
   # Hook to convert
@@ -155,15 +181,14 @@ class RTesseract
   def convert
     convert_command
     after_convert_hook
-    convert_text
-    RTesseract::Utils.remove_files([@image, text_file_with_ext])
+    convert_result
   rescue => error
     raise RTesseract::ConversionError.new(error), error, caller
   end
 
   # Output value
   def to_s
-    return @value if @value != nil
+    return @value if @value
 
     if @processor.image?(@source) || @source.file?
       convert
@@ -175,8 +200,30 @@ class RTesseract
 
   # Remove spaces and break-lines
   def to_s_without_spaces
-    to_s.delete(' ').delete("\n").delete("\r")
+    to_s.gsub(/\s/, '')
   end
+
+  # Output pdf path
+  def to_pdf
+    return @pdf_path if @pdf_path
+
+    fail TesseractVersionError.new if tesseract_version.nil? || tesseract_version < 3.03
+
+    if @processor.image?(@source) || @source.file?
+      options_cmd << 'pdf'
+      convert
+      options_cmd.delete('pdf')
+      @pdf_path
+    else
+      fail RTesseract::ImageNotSelectedError.new(@source)
+    end
+  end
+
+  # Destroy pdf file
+  def clean
+    RTesseract::Utils.remove_files([@pdf_path])
+  end
+
 end
 
 require 'rtesseract/mixed'

data/lib/rtesseract/box.rb

@@ -29,7 +29,7 @@ class RTesseract
 
     # Read the result file
     def parse_file
-      html = Nokogiri::HTML(File.read(text_file_with_ext))
+      html = Nokogiri::HTML(File.read(file_with_ext))
       html.css('span.ocrx_word, span.ocr_word')
     end
 
@@ -42,7 +42,7 @@ class RTesseract
 
     # Move file html to hocr
     def after_convert_hook
-      FileUtils.mv(text_file_with_ext('.html'), text_file_with_ext) rescue nil
+      FileUtils.mv(file_with_ext('.html'), file_with_ext) rescue nil
     end
 
     # Output value

data/lib/rtesseract/box_char.rb

@@ -16,7 +16,7 @@ class RTesseract
 
     # Read the result file
     def parse_file
-      File.read(text_file_with_ext).to_s
+      File.read(file_with_ext).to_s
     end
 
     def convert_text

data/lib/rtesseract/configuration.rb

@@ -43,6 +43,15 @@ class RTesseract
   def self.configure
     self.configuration ||= Configuration.new
     yield(configuration)
+    self.clear_pdf_option
+  end
+
+  # Clear pdf option
+  def self.clear_pdf_option
+    if self.configuration.options_cmd
+      self.configuration.options_cmd.delete('pdf')
+      self.configuration.options_cmd.delete(:pdf)
+    end
   end
 
   # Default command
@@ -59,7 +68,8 @@ class RTesseract
       config.processor = config.option(options, :processor, 'rmagick')
       config.load_options(options, [:lang, :psm, :tessdata_dir, :user_words, :user_patterns])
       config.debug = config.option(options, :debug, false)
-      config.options_cmd = [options.option(:options, nil)].flatten.compact
+      pdf_opts = lambda { |o| o == 'pdf' || o == :pdf }
+      config.options_cmd = [options.option(:options, nil)].delete_if(&pdf_opts).flatten.compact
     end
   end
-end
+end

data/lib/rtesseract/errors.rb

@@ -12,4 +12,10 @@ class RTesseract
   class ConversionError < ErrorWithMemory; end
   class ImageNotSelectedError < ErrorWithMemory; end
   class TempFilesNotRemovedError < ErrorWithMemory; end
+  
+  class TesseractVersionError < StandardError 
+    def initialize 
+      super "Tesseract version is unknown or below 3.03 which is required for pdf output."
+    end
+  end
 end

data/lib/rtesseract/utils.rb

@@ -1,3 +1,5 @@
+require 'open3'
+
 # RTesseract
 class RTesseract
   # Some utils methods
@@ -22,6 +24,14 @@ class RTesseract
       end
       true
     end
+
+    # Extract tesseract version number
+    def self.version_number
+      out, err, st = Open3.capture3(RTesseract.default_command, "--version")
+      
+      version = err.split("\n")[0].split(" ")[1].split('.')[0, 2].join('.')
+      Float(version) rescue nil
+    end
   end
 end
 
@@ -31,4 +41,4 @@ class Hash
   def option(attr_name, default)
     delete(attr_name.to_s) || delete(attr_name) || default
   end
-end
+end

data/rtesseract.gemspec

@@ -2,16 +2,16 @@
 # DO NOT EDIT THIS FILE DIRECTLY
 # Instead, edit Jeweler::Tasks in Rakefile, and run 'rake gemspec'
 # -*- encoding: utf-8 -*-
-# stub: rtesseract 2.0.1 ruby lib
+# stub: rtesseract 2.1.0 ruby lib
 
 Gem::Specification.new do |s|
   s.name = "rtesseract"
-  s.version = "2.0.1"
+  s.version = "2.1.0"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.require_paths = ["lib"]
   s.authors = ["Danilo Jeremias da Silva"]
-  s.date = "2016-05-17"
+  s.date = "2016-09-08"
   s.description = "Ruby library for working with the Tesseract OCR."
   s.email = "dannnylo@gmail.com"
   s.extra_rdoc_files = [
@@ -48,6 +48,7 @@ Gem::Specification.new do |s|
     "spec/images/mixed.tif",
     "spec/images/orientation_reverse.png",
     "spec/images/test with spaces.tif",
+    "spec/images/test-pdf.png",
     "spec/images/test.bmp",
     "spec/images/test.jpg",
     "spec/images/test.png",

data/spec/rtesseract_spec.rb

@@ -13,6 +13,7 @@ describe 'Rtesseract' do
   before do
     @path = Pathname.new(__FILE__.gsub('rtesseract_spec.rb', '')).expand_path
     @image_tif = @path.join('images', 'test.tif').to_s
+    @image_for_pdf = @path.join('images', 'test-pdf.png').to_s
   end
 
   it ' be instantiable' do
@@ -94,12 +95,43 @@ describe 'Rtesseract' do
     expect(RTesseract.new(@image_tif, options: [:digits, :quiet]).options_cmd).to eql([:digits, :quiet])
   end
 
+  it ' support pdf output mode' do
+    # Internal test. Consider 'pdf' option only when #to_pdf is called.
+    expect(RTesseract.new(@image_tif, options: 'pdf').options_cmd).to eql([])
+    expect(RTesseract.new(@image_for_pdf, options: :pdf).options_cmd).to eql([])
+
+    pdf_ocr = RTesseract.new(@image_for_pdf)
+    expect(File.exists?(pdf_ocr.to_pdf)).to eql(true)
+    expect(File.extname(pdf_ocr.to_pdf)).to eql('.pdf')
+    # Comment next line and go to tmp dir to see generated pdf.
+    expect(pdf_ocr.clean).to eq(true)
+    expect(File.exists?(pdf_ocr.to_pdf)).to eql(false)
+
+    # Still have original functionality (i.e. #to_s, #to_s_without_spaces).
+    pdf_ocr = RTesseract.new(@image_tif)
+    expect(File.exists?(pdf_ocr.to_pdf)).to eql(true)
+    expect(File.extname(pdf_ocr.to_pdf)).to eql('.pdf')
+    expect(pdf_ocr.to_s_without_spaces).to eql('43XF')
+    expect(pdf_ocr.clean).to eq(true)
+    expect(File.exists?(pdf_ocr.to_pdf)).to eql(false)
+  end
+
+  it ' warn when tesseract cannot give pdf' do
+    rtesseract = RTesseract.new(@image_for_pdf)
+
+    allow(rtesseract).to receive(:tesseract_version).and_return(3.02)
+    expect { rtesseract.to_pdf }.to raise_error(RTesseract::TesseractVersionError)
+
+    allow(rtesseract).to receive(:tesseract_version).and_return(3.03)
+    expect { rtesseract.to_pdf }.not_to raise_error
+  end
+
   it ' be configurable' do
     expect(RTesseract.new(@image_tif, chop_enable: 0, enable_assoc: 0, display_text: 0).config).to eql("chop_enable 0\nenable_assoc 0\ndisplay_text 0")
     expect(RTesseract.new(@image_tif, chop_enable: 0).config).to eql('chop_enable 0')
     expect(RTesseract.new(@image_tif, chop_enable: 0, enable_assoc: 0).config).to eql("chop_enable 0\nenable_assoc 0")
     expect(RTesseract.new(@image_tif, chop_enable: 0).to_s_without_spaces).to eql('43XF')
-    expect(RTesseract.new(@image_tif, tessedit_char_whitelist: "ABCDEF12345").to_s_without_spaces).to eql('43F')
+    expect(RTesseract.new(@image_tif, tessedit_char_whitelist: 'ABCDEF12345').to_s_without_spaces).to eql('43F')
   end
 
   it ' crop image' do
@@ -179,7 +211,11 @@ describe 'Rtesseract' do
     expect { RTesseract::Utils.remove_files(Pathname.new(Dir.tmpdir).join('test_not_exists')) }.to raise_error(RTesseract::TempFilesNotRemovedError)
   end
 
-  it ' support  default config processors' do
+  it ' get a numeric value for tesseract version' do
+    expect(RTesseract::Utils.version_number).to be_a Float
+  end
+
+  it ' support default config processors' do
     # Rmagick
     RTesseract.configure { |config| config.processor = 'rmagick' }
     expect(RTesseract.new(@image_tif).processor.a_name?('rmagick')).to eql(true)
@@ -212,6 +248,18 @@ describe 'Rtesseract' do
     expect(RTesseract.new(@image_tif).user_patterns).to eql(' --user-patterns /tmp/test ')
   end
 
+  it ' configure pdf has no effect and kept in-house' do
+    # So it does not interfere with #to_s outputting.
+    RTesseract.configure { |config| config.options_cmd =  ['pdf'] }
+    expect(RTesseract.new(@image_tif).options_cmd).to eql([])
+
+    RTesseract.configure { |config| config.options_cmd = [:pdf] }
+    expect(RTesseract.new(@image_tif).options_cmd).to eql([])
+
+    RTesseract.configure { |config| config.options_cmd = [:pdf, 'pdf'] }
+    expect(RTesseract.new(@image_tif).options_cmd).to eql([])
+  end
+
   it ' support new configs' do
     expect(RTesseract.new(@image_tif, tessdata_dir: '/tmp/test').tessdata_dir).to eql(' --tessdata-dir /tmp/test ')
     expect(RTesseract.new(@image_tif, user_words: '/tmp/test').user_words).to eql(' --user-words /tmp/test ')

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: rtesseract
 version: !ruby/object:Gem::Version
-  version: 2.0.1
+  version: 2.1.0
 platform: ruby
 authors:
 - Danilo Jeremias da Silva
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2016-05-17 00:00:00.000000000 Z
+date: 2016-09-08 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri
@@ -145,6 +145,7 @@ files:
 - spec/images/mixed.tif
 - spec/images/orientation_reverse.png
 - spec/images/test with spaces.tif
+- spec/images/test-pdf.png
 - spec/images/test.bmp
 - spec/images/test.jpg
 - spec/images/test.png