act_as_page_extractor 0.6.2 → 0.6.4

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: d0bd64f8e12d0c7bb3a75893738e30af616e4bcc5b958b18853b35363823b5ef
-  data.tar.gz: d87505b025bd924a545e2f6cbd9071958d65f993a234092f65b3cb7e108b16b1
+  metadata.gz: f412c60bccb3fca934efecbc7922af07b41297423e6a2c4fbe04b8110a0e22e8
+  data.tar.gz: 4b281d9c93de0955e90b1a9d500213b1fa7103c449d72354caaa3d5d29702ff5
 SHA512:
-  metadata.gz: af0708407f3b4546424e1666926c248cdb9fe0813ede2dd642d099836282d2f608d8d47edcd5cd513cef9b3ead231c192f6b815ec7721eb141b6820f561d0f30
-  data.tar.gz: 6a5969118ff6a6141aaaec8989e38670f75a817afa230636ed84f9f2a4e7c1f160ee569664f940e1355cfc74dff56e30370ca993fbb38d2a7139c17f56858acf
+  metadata.gz: b545143db8d5fd51fb4c5c3d95d76b8122576e26e6587bb0b8c1ec62303e7e7bc5509554132ba9e65d47294fd2fa7c803a01634529c8e4ca8ecf9d0b3f1a392c
+  data.tar.gz: 3ff648cca05fe842e97db5e5153399bcfcd34f98141cd47ad5ca511de588de67c080778b643cba9be372178a6d6fc497552082bece168d3e10be6788382c8426

data/Gemfile

@@ -3,6 +3,8 @@ source 'https://rubygems.org'
 # Specify your gem's dependencies in total_compressor.gemspec
 gemspec
 
+ruby '>= 3.2'
+
 gem 'activerecord', '~> 6'
 
 gem 'awesome_print'

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    act_as_page_extractor (0.6.1)
+    act_as_page_extractor (0.6.4)
       activerecord (~> 6)
       awesome_print (~> 1)
       docsplit (~> 0)
@@ -80,13 +80,13 @@ GEM
     zeitwerk (2.6.17)
 
 PLATFORMS
-  ruby
+  x86_64-linux
 
 DEPENDENCIES
   act_as_page_extractor!
   activerecord (~> 6)
   awesome_print
-  bundler (~> 1)
+  bundler (~> 2)
   byebug
   docsplit
   filesize
@@ -98,5 +98,8 @@ DEPENDENCIES
   simplecov
   total_compressor
 
+RUBY VERSION
+   ruby 3.2.0p0
+
 BUNDLED WITH
-   1.17.3
+   2.4.1

data/act_as_page_extractor.gemspec

@@ -17,7 +17,7 @@ Gem::Specification.new do |spec|
   spec.test_files    = spec.files.grep(%r{^(test|spec|features)/})
   spec.require_paths = ['lib']
 
-  spec.add_development_dependency 'bundler',   '~> 1'
+  spec.add_development_dependency 'bundler',   '~> 2'
   spec.add_development_dependency 'rake',      '~> 12', '>= 12.3.3'
   spec.add_development_dependency 'byebug',    '~> 0'
   spec.add_development_dependency 'rspec',     '~> 0'

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
@@ -10,7 +17,7 @@ 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
   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/saving.rb

@@ -11,7 +11,7 @@ module ActAsPageExtractor
   end
 
   def save_to_db
-    self.update_attributes(page_extraction_state: EXTRACTING_STATES[:extracting])
+    self.update(page_extraction_state: EXTRACTING_STATES[:extracting])
     ExtractedPage.transaction do
       @pdf_pages&.times&.each do |pdf_page|
         page_filename = "#{@tmp_dir}/#{@document_filename.split('.').first}_#{(pdf_page + 1).to_s}.txt"

data/lib/act_as_page_extractor/modules/tools.rb

@@ -32,7 +32,7 @@ module ActAsPageExtractor
         page_extraction_doctype: @document_path&.split('.')&.last,
         page_extraction_filesize: Filesize.from("#{File.size(@document_path)} B").pretty
       })
-    self.update_attributes(updated_attributes)
+    self.update(updated_attributes)
   end
 
   def cleanup_pages

data/lib/act_as_page_extractor/version.rb

@@ -1,5 +1,5 @@
 # :nocov:
 module ActAsPageExtractor
-  VERSION = "0.6.2"
+  VERSION = "0.6.4"
 end
 # :nocov:

data/lib/act_as_page_extractor.rb

@@ -85,13 +85,13 @@ 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)
+    FileUtils::mkdir_p(@tmp_dir) unless File.exist?(@tmp_dir)
   end
 
   def copy_document

data/spec/act_as_page_extractor_spec.rb

@@ -4,24 +4,24 @@ require 'act_as_page_extractor'
 describe ActAsPageExtractor do
   context 'correct extraction' do
     [
-      'test-doc-3-pages.docx',
-      'test-doc-3-pages.doc',
-      'test-doc-3-pages.pdf',
-      'test-doc-3-pages.rtf',
-      'test-doc-3-pages.odt',
-      'test-doc-3-pages.html',
-      'test-doc-3-pages.txt',
-      'test-doc-3-pages.docx.zip',
-      'test-doc-3-pages.docx.rar',
-      'test-doc-3-pages.docx.7z'
+      'Oscar_Wilde_The_Happy_Prince_en.docx',
+      'Oscar_Wilde_The_Happy_Prince_en.doc',
+      'Oscar_Wilde_The_Happy_Prince_en.pdf',
+      'Oscar_Wilde_The_Happy_Prince_en.rtf',
+      'Oscar_Wilde_The_Happy_Prince_en.odt',
+      'Oscar_Wilde_The_Happy_Prince_en.html',
+      'Oscar_Wilde_The_Happy_Prince_en.txt',
+      'Oscar_Wilde_The_Happy_Prince_en.docx.zip',
+      'Oscar_Wilde_The_Happy_Prince_en.docx.rar',
+      'Oscar_Wilde_The_Happy_Prince_en.docx.7z'
     ].each do |document|
       it "extraction valid document #{document}" do
         book = Book.new({doc_path: document})
         allow(Book).to receive_message_chain('where') { [book] }
         ActAsPageExtractor.start_extraction
         expect(book.page_extraction_state).to eq ActAsPageExtractor::EXTRACTING_STATES[:extracted]
-        expect(ExtractedPage.array.count).to eq 3
-        expect(ExtractedPage.array[0][:page]).to match /require \'act_as_page_extractor\/modules\/interface\'/
+        expect(ExtractedPage.array.count).to eq 4
+        expect(ExtractedPage.array[0][:page]).to match /on a tall column, stood the statue of the Happy Prince/
         unless document.match /pdf/
           expect(book.pdf_path).to match /pdf/
           expect(book.remove_files.count).to eq 1
@@ -33,7 +33,7 @@ describe ActAsPageExtractor do
 
   context 'incorrect extraction' do
     [
-      'test-doc-3-pages.wrong',
+      'Oscar_Wilde_The_Happy_Prince_en.wrong',
     ].each do |document|
       it "extraction invalid document #{document}" do
         book = Book.new({doc_path: document})

data/spec/support/models.rb

@@ -60,7 +60,7 @@ class Book
     array
   end
 
-  def update_attributes params
+  def update params
     params.each do |key, value|
       instance_eval("self.#{key} = #{value.class == String ? '\'' + value + '\'': value }")
     end