act_as_page_extractor 0.6.3 → 0.7.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 9c4528cd1633b4691d46d7cef1eac6b66c986bfd3ebdebedec786b01bab0f0e6
-  data.tar.gz: 05b6967bb2092e17fefca9923614a3b16fae9e5dc3bfd5caf91a16f4e93b6d57
+  metadata.gz: 0e2f7b9cc30bb8ba03a61ed873b43d4b1764997c65f470a751abe3a2042561e4
+  data.tar.gz: ec3e7125f2119a3666e8e9732ff2ae171df2b1c7e51a02eb9c0794e9f73a5bf5
 SHA512:
-  metadata.gz: 1ea4ba52c2cfc10c21ca3ca82791af40689140de14ce56781859e6cee6ce538d8c8ad9c9b64f2acb39f0fce4848ca548395f3442146d2e1b4e7f4711f2f0c801
-  data.tar.gz: 3cfbd8aef08741aceaf34103bdfbeb45ddbf9b34d863e9daf92f2d9a7c1636577cc265770cfd318287d0b77dacfb896c5c2d68923ed65393c250246f29053e3d
+  metadata.gz: b4ba9e08f4a11c250cb9449035d5728dbd764870c85709aa76a2f532e3f41d5e895a813ddd8a7bf98b3885ca871c25aa29867db9f2e7b099e4d99504c3a81907
+  data.tar.gz: 36e66d4bbf0300f570cf964902c0163caad97c8c6ca0c8856c7aaba8c72a1716b0a6a8218e5176edebd8dd261786a9142f9ba9cbfe62cf0193c9b677fb17088a

data/.github/workflows/coverage.yml

@@ -0,0 +1,32 @@
+# .github/workflows/coverage.yml
+name: Coverage
+
+
+on:
+  push:
+    branches: [ main, master ]
+  pull_request:
+    branches: [ main, master ]
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Set up Ruby
+        uses: ruby/setup-ruby@v1
+        with:
+          ruby-version: 3.2.3
+      - name: Install dependencies
+        run: |
+          sudo apt-get update
+          sudo apt-get install -y libreoffice unoconv poppler-utils zlib1g zlib1g-dev zip rar p7zip-full
+          bundle install --jobs 4 --retry 3
+      - name: Run tests with coverage
+        run: |
+          bundle exec rspec
+      - name: Upload coverage to Codecov
+        uses: codecov/codecov-action@v4
+        with:
+          files: ./coverage/.resultset.json,./coverage/coverage.json,./coverage/index.html
+          fail_ci_if_error: false

data/.gitignore

@@ -20,6 +20,7 @@ build/
 *.bridgesupport
 build-iPhoneOS/
 build-iPhoneSimulator/
+.byebug_history
 
 ## Specific to RubyMotion (use of CocoaPods):
 #

data/Aptfile.sh

@@ -0,0 +1,55 @@
+# https://github.com/phlowerteam/total_compressor
+sudo apt-get install zlib1g
+sudo apt-get install zlib1g-dev
+sudo apt-get install zip
+sudo apt-get install rar
+sudo apt-get install p7zip-full
+
+# PDF
+sudo apt-get install poppler-utils
+
+# OpenOffice
+sudo apt-get install jodconverter
+
+sudo apt-get install nautilus-filename-repairer
+sudo apt-get install python3-chardet
+sudo apt-get install xfonts-encodings
+sudo apt-get install libfontenc1
+sudo apt-get install console-setup
+sudo apt-get install fontconfig
+sudo apt-get install fontconfig-config
+sudo apt-get install fonts-kacst
+sudo apt-get install fonts-kacst-one
+sudo apt-get install fonts-khmeros-core
+sudo apt-get install fonts-lao
+sudo apt-get install fonts-liberation
+sudo apt-get install fonts-nanum
+sudo apt-get install fonts-opensymbol
+sudo apt-get install fonts-sil-gentium-basic
+sudo apt-get install fonts-takao-pgothic
+sudo apt-get install fonts-thai-tlwg
+sudo apt-get install fonts-tlwg-garuda
+sudo apt-get install fonts-tlwg-kinnari
+sudo apt-get install fonts-tlwg-loma
+sudo apt-get install fonts-tlwg-mono
+sudo apt-get install fonts-tlwg-norasi
+sudo apt-get install fonts-tlwg-purisa
+sudo apt-get install fonts-tlwg-sawasdee
+sudo apt-get install fonts-tlwg-typewriter
+sudo apt-get install fonts-tlwg-typist
+sudo apt-get install fonts-tlwg-typo
+sudo apt-get install fonts-tlwg-umpush
+sudo apt-get install fonts-tlwg-waree
+sudo apt-get install gnome-font-viewer
+sudo apt-get install gsfonts gucharmap
+sudo apt-get install kbd
+sudo apt-get install libfontconfig1
+sudo apt-get install libfontenc1
+sudo apt-get install libfreetype6
+sudo apt-get install libxft2
+sudo apt-get install fonts-ubuntu
+sudo apt-get install fonts-wqy-microhei
+sudo apt-get install x11-xfs-utils xfonts-base
+sudo apt-get install xfonts-encodings
+sudo apt-get install xfonts-scalable
+sudo apt-get install xfonts-utils

data/CHANGELOG.md

@@ -0,0 +1,67 @@
+# Changelog
+
+## [0.7.0] - 2025-08-21
+### Added
+- Breaking changes: added root folder as an option to access the folder between deployments, improved error processing ([883cafc], [b10a367])
+
+HINT: to upgrade an older version, you need to fix the DB scheme and data migrations like this:
+```rb
+# db/migrate/20250804182426_upgrade_act_as_page_extractor_to_version.rb
+class UpgradeActAsPageExtractorToVersion < ActiveRecord::Migration
+  def change
+    add_column :documents, :pages_extraction_errors, :string, default: ''
+  end
+end
+
+# db/data/20250804183544_upgrade_act_as_page_extractor_to_version.rb
+class UpgradeActAsPageExtractorToVersion < ActiveRecord::Migration
+  def up
+    Document
+      .where(page_extraction_state: 'error.extraction')
+      .update_all(page_extraction_state: 'error_extraction')
+  end
+
+  def down
+    raise ActiveRecord::IrreversibleMigration
+  end
+end
+```
+
+## [0.6.0] - 2024-08-31
+### Changed
+- Upgraded to Ruby 3.2 minimal version ([4b463a1], [be52d9c])
+- Upgraded to ActiveRecord >=6.x.x ([7881613], [48e6d8b], [8bd3707])
+- Improved docs & Readme ([c405044], [6e895bb])
+
+## [0.5.0] - 2024-08-30
+### Changed
+- Upgraded to ActiveRecord 6.0 ([9eea586])
+
+## [0.2.3] - 2020-06-05
+### Changed
+- Upgraded to ActiveRecord-5.2.0 ([cde1f36])
+
+## [0.2.2] - 2020-06-04
+### Changed
+- Upgraded to ActiveRecord-5.1.0 ([f6ea8d7])
+
+## [0.2.1] - 2020-05-11
+### Changed
+- Upgraded to ActiveRecord-5.0.0 ([5c595ee], [3eb4ad7])
+
+## [0.1.6] - 2020-05-10
+### Changed
+- Updated libraries ([eca4346]), ([7d3bb4f], [203c689], [171cf27])
+
+## [0.1.2] - 2018-11-29
+### Changed
+- Updated rubyzip library ([38c4156])
+
+## [0.1.1] - 2017-01-10
+### Changed
+- Removed code coverage from Rails generators ([a990357])
+
+## [0.1.0] - 2017-01-09
+### Added
+- Initial commit ([47c0950], [5225f33])
+- Fixed tests ([e68a6b7])

data/Gemfile

@@ -3,9 +3,11 @@ source 'https://rubygems.org'
 # Specify your gem's dependencies in total_compressor.gemspec
 gemspec
 
-gem 'activerecord', '~> 6'
+ruby '3.2.3'
 
-gem 'awesome_print'
+gem 'activerecord'
+
+gem 'amazing_print'
 
 gem 'docsplit'            # API for OpenOffice jodconverter (any to pdf)
 gem 'pdf_utils'           # getting text from pdf

data/Gemfile.lock

@@ -1,9 +1,9 @@
 PATH
   remote: .
   specs:
-    act_as_page_extractor (0.6.1)
-      activerecord (~> 6)
-      awesome_print (~> 1)
+    act_as_page_extractor (0.7.0)
+      activerecord (>= 6)
+      amazing_print (~> 1)
       docsplit (~> 0)
       filesize (~> 0)
       pdf-reader (~> 1, >= 1.4)
@@ -27,8 +27,9 @@ GEM
       tzinfo (~> 2.0)
       zeitwerk (~> 2.3)
     afm (0.2.2)
+    amazing_print (1.8.1)
     awesome_print (1.9.2)
-    byebug (11.1.3)
+    byebug (12.0.0)
     concurrent-ruby (1.3.4)
     diff-lcs (1.5.1)
     docile (1.4.1)
@@ -80,13 +81,13 @@ GEM
     zeitwerk (2.6.17)
 
 PLATFORMS
-  ruby
+  x86_64-linux
 
 DEPENDENCIES
   act_as_page_extractor!
-  activerecord (~> 6)
-  awesome_print
-  bundler (~> 1)
+  activerecord
+  amazing_print
+  bundler (>= 2.2.33)
   byebug
   docsplit
   filesize
@@ -98,5 +99,8 @@ DEPENDENCIES
   simplecov
   total_compressor
 
+RUBY VERSION
+   ruby 3.2.3p157
+
 BUNDLED WITH
-   1.17.3
+   2.4.1

data/README.md

@@ -1,30 +1,29 @@
+[![codecov](https://codecov.io/gh/phlowerteam/act_as_page_extractor/branch/41-Feature-Improve-error-procesing/graph/badge.svg)](https://codecov.io/gh/phlowerteam/act_as_page_extractor)
+
 act_as_page_extractor
 ================
 
-Library for extracting plain text from documents(files) for further processing (indexing and searching).
+A library that extracts plain text from documents for subsequent processing, such as indexing and search.
 
 ## Installation
 
-Install appropriate tools before using:
-
+Install all dependencies before use:
 ```sh
-sudo apt-get install zlib1g zlib1g-dev zip rar p7zip-full
+sh Aptfile.sh
 ```
-Add this line to your application's Gemfile:
 
+Add this to your Gemfile:
 ```rb
 gem 'act_as_page_extractor'
-bundle
 ```
 ## Usage
 
-For example, for model Document in the Rails framework we need run:
-
+Generate a migration, for example for a Document model:
 ```sh
 rails g act_as_page_extractor:migration Document category_id user_id
 ```
 
-As a result we get two migration files:
+This will generate two migration files:
 ```rb
 class AddPageExtractorFields < ActiveRecord::Migration
   def change
@@ -32,6 +31,7 @@ class AddPageExtractorFields < ActiveRecord::Migration
     add_column :documents, :page_extraction_pages, :integer, default: 0
     add_column :documents, :page_extraction_doctype, :string, default: ''
     add_column :documents, :page_extraction_filesize, :string, default: ''
+    add_column :documents, :pages_extraction_errors, :string, default: ''
   end
 end
 
@@ -65,20 +65,20 @@ Add to model next parameters for initializing:
 
     act_as_page_extractor options: {
       document_class:    'Document',
-      save_as_pdf:       true,
+      save_as_pdf:       true, # store converted document as PDF
       filename:          :filename,
       document_id:       :document_id,
-      additional_fields: [:category_id, :user_id],
-      #file_storage:      "/full/path/to/documents/storage",
-      #pdf_storage:       "/full/path/to/extracted/pdf/storage"
+      additional_fields: [:category_id, :user_id], # copy values of these fields from document to extracted_page
+      root_folder:       Rails.root.to_s, # or "/full/path/to/project", it needs to share folder between deployments
+      # file_storage:      "/full/path/to/project/public/uploads/documents/storage" # optional
+      # pdf_storage:       "/full/path/to/project/public/uploads/extracted/pdf/storage" # optional
     }
 
     has_many :extracted_pages, dependent: :destroy
 end
 ```
 
-Now our instance has few new methods:
-
+The instance now provides several new methods:
 ```rb
 document = Document.first
 document.page_extract!
@@ -100,29 +100,24 @@ ActAsPageExtractor.statistics
 
 Parameters of initializing **act_as_page_extractor**:
 
-* **document_class** - name of model (e.g. Document)
-* **save_as_pdf** - boolean [true, false] when we want save temporary pdf
-* **filename** - name of field which contains access to the file and it should be an object with 'url' method that returns path to file (e.g. CarrierWave object with 'filename.url')
-* **document_id** - name for saving id
-* **additional_fields** - additional fields that added to extracted page (e.g. for indexing, etc.)
-* **file_storage** - path for saving tmp files (by default it is "public")
-* **pdf_storage** - path for saving pdf (by default it is "public/uploads/extracted/pdf")
+* **document_class** — The name of the model (e.g., `Document`).
+* **save_as_pdf** — Boolean (`true`/`false`). Indicates whether to save a temporary PDF.
+* **filename** — The field containing access to the file. This should be an object with a `url` method that returns the file path (e.g., a CarrierWave object with `filename.url`).
+* **document_id** — The field name for storing the document ID.
+* **additional_fields** — Extra fields to be added to the extracted page (useful for indexing, etc.).
+* **root_folder** — The root folder to be shared across deployments (e.g., `Rails.root.to_s`).
+* **file_storage** — Path for saving temporary files (default: `"public"`).
+* **pdf_storage** — Path for saving PDFs (default: `"public/uploads/extracted/pdf"`).
 
 ## Run tests
 ```sh
+bundle
 rspec
 ```
-## Contributing
-1. Fork it
-2. Create your feature branch (`git checkout -b my-new-feature`)
-3. Commit your changes (`git commit -am 'Add some feature'`)
-4. Push to the branch (`git push origin my-new-feature`)
-5. Create new Pull Request
 
 ## Contacts
-https://github.com/phlowerteam
-phlowerteam@gmail.com
+https://github.com/phlowerteam / phlowerteam[A]gmail.com
 
 ## License
-Copyright (c) 2024 PhlowerTeam
-MIT License
+
+MIT License © 2025 PhlowerTeam

data/act_as_page_extractor.gemspec

@@ -16,15 +16,16 @@ Gem::Specification.new do |spec|
   spec.files         = `git ls-files`.split($/)
   spec.test_files    = spec.files.grep(%r{^(test|spec|features)/})
   spec.require_paths = ['lib']
+  spec.required_ruby_version = '>= 3.2'
 
-  spec.add_development_dependency 'bundler',   '~> 1'
+  spec.add_development_dependency 'bundler', '>= 2.2.33'
   spec.add_development_dependency 'rake',      '~> 12', '>= 12.3.3'
   spec.add_development_dependency 'byebug',    '~> 0'
   spec.add_development_dependency 'rspec',     '~> 0'
   spec.add_development_dependency 'simplecov', '~> 0'
 
-  spec.add_runtime_dependency 'activerecord',     '~> 6'
-  spec.add_runtime_dependency 'awesome_print',    '~> 1'
+  spec.add_runtime_dependency 'activerecord',     '>= 6'
+  spec.add_runtime_dependency 'amazing_print',    '~> 1'
   spec.add_runtime_dependency 'docsplit',         '~> 0'                  # API for OpenOffice jodconverter (any to pdf)
   spec.add_runtime_dependency 'pdf_utils',        '~> 0'                  # getting text from pdf
   spec.add_runtime_dependency 'prawn',            '~> 1'                # need for pdf_utils

data/lib/act_as_page_extractor/modules/extracting.rb

@@ -1,3 +1,10 @@
+# Fix: https://github.com/documentcloud/docsplit/pull/159
+class File
+  class << self
+    alias_method :exists?, :exist?
+  end
+end
+
 module ActAsPageExtractor
   def extract_pages
     convert_to_pdf
@@ -10,26 +17,25 @@ module ActAsPageExtractor
      else
       if timeout_wrapper{ Docsplit.extract_pdf(@document_path, output: @tmp_dir)}
         pdf_path = (@document_path.split('.')[0..-2] + ['pdf']).join('.')
-        pdf_path if File.exists?(pdf_path)
+        pdf_path if File.exist?(pdf_path)
       end
     end
+  rescue StandardError => e
+    add_error(e)
   end
 
   def convert_to_text
-    begin
-      @pdf_pages = PdfUtils.info(@pdf_path).pages
-      if @pdf_pages
-        if timeout_wrapper{ Docsplit::extract_text(@pdf_path, ocr: false, pages: 'all', output: @tmp_dir) }
-        else
-          # :nocov:
-          @pdf_pages = nil
-          raise
-          # :nocov:
-        end
+    @pdf_pages = PdfUtils.info(@pdf_path).pages
+    if @pdf_pages
+      if timeout_wrapper{ Docsplit::extract_text(@pdf_path, ocr: false, pages: 'all', output: @tmp_dir) }
+      else
+        # :nocov:
+        @pdf_pages = nil
+        raise ERRORS[:unknown_docsplit_error]
+        # :nocov:
       end
-    # :nocov:
-    rescue
     end
-    # :nocov:
+  rescue StandardError => e
+    add_error(e)
   end
 end

data/lib/act_as_page_extractor/modules/interface.rb

@@ -10,7 +10,7 @@ module ActAsPageExtractor
   end
 
   def remove_files
-    FileUtils::rm_rf(pdf_path) if File.exists?(pdf_path.to_s)
+    FileUtils::rm_rf(pdf_path) if File.exist?(pdf_path.to_s)
   end
 
   def self.start_extraction

data/lib/act_as_page_extractor/modules/tools.rb

@@ -5,8 +5,9 @@ module ActAsPageExtractor
   def timeout_wrapper
     result = nil
     begin
-      result = Timeout::timeout(60*5) { yield }
-    rescue
+      result = Timeout::timeout(EXTRACTION_TIMEOUT) { yield }
+    rescue StandardError => e
+      add_error(e)
     ensure
       result
     end
@@ -25,12 +26,13 @@ module ActAsPageExtractor
       }
     else
       {
-        page_extraction_state: EXTRACTING_STATES[:'error.extraction'],
+        page_extraction_state: @page_extraction_state || EXTRACTING_STATES[:error_extraction],
         page_extraction_pages: 0
       }
     end.merge({
         page_extraction_doctype: @document_path&.split('.')&.last,
-        page_extraction_filesize: Filesize.from("#{File.size(@document_path)} B").pretty
+        page_extraction_filesize: Filesize.from("#{File.size(@document_path)} B").pretty,
+        pages_extraction_errors: @pages_extraction_errors.chomp
       })
     self.update(updated_attributes)
   end
@@ -39,6 +41,14 @@ module ActAsPageExtractor
     self.extracted_pages.destroy_all
   end
 
+  def add_error(e)
+    if ERRORS.values.include?(e.message)
+      @pages_extraction_errors << "#{e.message}\n\n"
+    else
+      @pages_extraction_errors << "#{e.class}, #{e.message}\n#{e.backtrace[0..ERROR_BACKTRACE_LINES].join("\n")}\n"
+    end
+  end
+
   # :nocov:
   def debug_info
     # ap "@tmp_dir"

data/lib/act_as_page_extractor/modules/unzipping.rb

@@ -1,6 +1,9 @@
 module ActAsPageExtractor
  def unzip_document
     @document_path = @copy_document_path
+
+    return if VALIDATE_DOC_TYPES.include?(@document_path.split('.').last&.downcase)
+
     if validate_compress_types
       result = TotalCompressor.decompress(@copy_document_path)
       if result[:success] && result[:files].length == 1
@@ -12,4 +15,15 @@ module ActAsPageExtractor
       end
     end
   end
+
+  def validate_compress_types
+    valid = VALIDATE_COMPRESS_TYPES.include?(@copy_document_path.split('.').last&.downcase)
+
+    unless valid
+      @page_extraction_state = EXTRACTING_STATES[:error_doctype]
+      @pages_extraction_errors << "#{EXTRACTING_STATES[:error_doctype]} "
+    end
+
+    valid
+  end
 end

data/lib/act_as_page_extractor/modules/validating.rb

@@ -1,22 +1,28 @@
 module ActAsPageExtractor
-  VALIDATE_COMPRESS_TYPES = ['zip', 'rar', '7z', 'gzip'].freeze
-  VALIDATE_DOC_TYPES = ['txt', 'pdf', 'doc', 'docx',
-                        'rtf', 'odt', 'htm', 'html'].freeze
-
   def valid_document
     validate_size && validate_doc_types
   end
 
   def validate_size
     mb = 2**20
-    File.size(@copy_document_path) <= 1*mb
-  end
+    valid = File.size(@copy_document_path) <= 1*mb
+
+    unless valid
+      @page_extraction_state = EXTRACTING_STATES[:error_filesize]
+      @pages_extraction_errors << "#{EXTRACTING_STATES[:error_filesize]} "
+    end
 
-  def validate_compress_types
-    VALIDATE_COMPRESS_TYPES.include?(@copy_document_path.split('.').last&.downcase)
+    valid
   end
 
   def validate_doc_types
-    VALIDATE_DOC_TYPES.include?(@document_path.split('.').last&.downcase)
+    valid = VALIDATE_DOC_TYPES.include?(@document_path.split('.').last&.downcase)
+
+    unless valid
+      @page_extraction_state = EXTRACTING_STATES[:error_doctype]
+      @pages_extraction_errors << "#{EXTRACTING_STATES[:error_doctype]} "
+    end
+
+    valid
   end
 end

data/lib/act_as_page_extractor/version.rb

@@ -1,5 +1,5 @@
 # :nocov:
 module ActAsPageExtractor
-  VERSION = "0.6.3"
+  VERSION = "0.7.0"
 end
 # :nocov:

data/lib/act_as_page_extractor.rb

@@ -19,9 +19,26 @@ require 'act_as_page_extractor/modules/saving.rb'
 require 'act_as_page_extractor/modules/interface'
 
 module ActAsPageExtractor
-
   extend ActiveSupport::Concern
 
+  DEFAULT_ROOT_FOLDER = Dir.pwd.to_s
+  ERRORS = {
+    unknown_docsplit_error: 'Unknown Docsplit error'
+  }.freeze
+  ERROR_BACKTRACE_LINES = 15
+  EXTRACTING_STATES = {
+    new: 'new',
+    extracting: 'extracting',
+    extracted: 'extracted',
+    error_doctype: 'error_doctype',
+    error_extraction: 'error_extraction',
+    error_filesize: 'error_filesize'
+  }.freeze
+  EXTRACTION_TIMEOUT = 60*5 # 5 minutes
+  VALIDATE_COMPRESS_TYPES = ['zip', 'rar', '7z', 'gzip'].freeze
+  VALIDATE_DOC_TYPES = ['txt', 'pdf', 'doc', 'docx',
+                        'rtf', 'odt', 'htm', 'html'].freeze
+
   included do
     before_create { self.page_extraction_state = EXTRACTING_STATES[:new] }
     before_destroy :remove_files
@@ -35,23 +52,16 @@ module ActAsPageExtractor
       ActAsPageExtractor.define_singleton_method(:document_class) {|*args| Object.const_get(options[:document_class]) }
       define_method(:extracted_document_id){|*args| options[:document_id] }
       define_method(:additional_fields){|*args| options[:additional_fields] || [] }
-      define_method(:file_storage){|*args| options[:file_storage] || FILE_STORAGE }
-      define_method(:pdf_storage){|*args| options[:pdf_storage] || PDF_STORAGE }
+      define_method(:root_folder){|*args| options[:root_folder] || DEFAULT_ROOT_FOLDER }
+      define_method(:file_storage){|*args| options[:file_storage] || "#{root_folder}/public".freeze }
+      define_method(:pdf_storage){|*args| options[:pdf_storage] || "#{file_storage}/uploads/extracted/pdf".freeze }
+      define_method(:tmp_extraction_file_storage){|*args| "#{root_folder}/tmp/page_extraction" }
     end
   end
 
-  EXTRACTING_STATES = {
-    new: 'new',
-    extracting: 'extracting',
-    extracted: 'extracted',
-    'error.extraction': 'error.extraction'
-  }.freeze
-
-  TMP_EXTRACTION_FILE_STORAGE = "#{Dir.pwd}/tmp/page_extraction".freeze
-  FILE_STORAGE = "#{Dir.pwd}/public".freeze
-  PDF_STORAGE = "#{FILE_STORAGE}/uploads/extracted/pdf".freeze
-
   def initialized
+    @page_extraction_state = nil
+    @pages_extraction_errors = ''
     # add all need callbacks
       #on destroy remove pdf
 
@@ -85,13 +95,13 @@ module ActAsPageExtractor
 
   def create_pdf_dir
     if save_as_pdf
-      FileUtils::mkdir_p(pdf_storage) unless File.exists?(pdf_storage)
+      FileUtils::mkdir_p(pdf_storage) unless File.exist?(pdf_storage)
     end
   end
 
   def create_tmp_dir
-    @tmp_dir = "#{TMP_EXTRACTION_FILE_STORAGE}/#{SecureRandom.hex(6)}"
-    FileUtils::mkdir_p(@tmp_dir) unless File.exists?(@tmp_dir)
+    @tmp_dir = "#{tmp_extraction_file_storage}/#{SecureRandom.hex(6)}"
+    FileUtils::mkdir_p(@tmp_dir) unless File.exist?(@tmp_dir)
   end
 
   def copy_document

data/lib/generators/act_as_page_extractor/templates/add_page_extractor_fields_to_documents.rb.erb

@@ -4,5 +4,6 @@ class <%= migration_class_name_documents %> < ActiveRecord::Migration
     add_column :<%= documents_table_name %>, :page_extraction_pages, :integer, default: 0
     add_column :<%= documents_table_name %>, :page_extraction_doctype, :string, default: ''
     add_column :<%= documents_table_name %>, :page_extraction_filesize, :string, default: ''
+    add_column :<%= documents_table_name %>, :pages_extraction_errors, :text, default: ''
   end
 end