act_as_page_extractor 0.6.1 → 0.6.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: '0956a6daefbfb71e23d34ba59b5010fee87805166d419725c8d95e116ec54ef7'
-  data.tar.gz: '096d66ce3473ab91068d35a3b5c00de975ce186093735e59592fdf9863b36aee'
+  metadata.gz: d0bd64f8e12d0c7bb3a75893738e30af616e4bcc5b958b18853b35363823b5ef
+  data.tar.gz: d87505b025bd924a545e2f6cbd9071958d65f993a234092f65b3cb7e108b16b1
 SHA512:
-  metadata.gz: d4c48c1bbcdac244047230e7144504d38b453b4d05f72093dec848b733950522b0498c013be62796ef4cba0af005399aa2d6987cd6ff1c2e9fc249758f8b45e7
-  data.tar.gz: 136917cec986faeb2ad866bc63bad36a96cdd76e7d129b146c79589a67f9dee69a0f6521c4c958024e54ffcbc441332b2ec89b7d986376becddbefbbebd8efb2
+  metadata.gz: af0708407f3b4546424e1666926c248cdb9fe0813ede2dd642d099836282d2f608d8d47edcd5cd513cef9b3ead231c192f6b815ec7721eb141b6820f561d0f30
+  data.tar.gz: 6a5969118ff6a6141aaaec8989e38670f75a817afa230636ed84f9f2a4e7c1f160ee569664f940e1355cfc74dff56e30370ca993fbb38d2a7139c17f56858acf

data/README.md

@@ -7,102 +7,111 @@ Library for extracting plain text from documents(files) for further processing (
 
 Install appropriate tools before using:
 
-    sudo apt-get install zlib1g zlib1g-dev zip rar p7zip-full
-
+```sh
+sudo apt-get install zlib1g zlib1g-dev zip rar p7zip-full
+```
 Add this line to your application's Gemfile:
 
-    gem 'act_as_page_extractor'
-
+```rb
+gem 'act_as_page_extractor'
+bundle
+```
 ## Usage
 
-For example, for model Document we need execute:
+For example, for model Document in the Rails framework we need run:
 
-    $ bundle
-    $ rails g act_as_page_extractor:migration Document category_id user_id
+```sh
+rails g act_as_page_extractor:migration Document category_id user_id
+```
 
 As a result we get two migration files:
-
-    class AddPageExtractorFields < ActiveRecord::Migration
-      def change
-        add_column :documents, :page_extraction_state, :string, default: ''
-        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: ''
-      end
-    end
-
-    class CreateExtractedPages < ActiveRecord::Migration
-      def change
-        create_table :extracted_pages do |t|
-          t.text :page
-          t.integer :document_id
-          t.integer :category_id
-          t.integer :user_id
-          t.integer :page_number
-
-          t.timestamps null: false
-        end
-
-        add_index :extracted_pages, :document_id
-        add_index :extracted_pages, :category_id
-        add_index :extracted_pages, [:document_id, :category_id]
-        add_index :extracted_pages, [:document_id, :page_number]
-      end
+```rb
+class AddPageExtractorFields < ActiveRecord::Migration
+  def change
+    add_column :documents, :page_extraction_state, :string, default: ''
+    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: ''
+  end
+end
+
+class CreateExtractedPages < ActiveRecord::Migration
+  def change
+    create_table :extracted_pages do |t|
+      t.text :page
+      t.integer :document_id
+      t.integer :category_id
+      t.integer :user_id
+      t.integer :page_number
+
+      t.timestamps null: false
     end
 
+    add_index :extracted_pages, :document_id
+    add_index :extracted_pages, :category_id
+    add_index :extracted_pages, [:document_id, :category_id]
+    add_index :extracted_pages, [:document_id, :page_number]
+  end
+end
+```
 
-Model Document must have field which contains path to file(supports [different archive types](https://github.com/phlowerteam/total_compressor) that contains [txt, pdf, doc/x, txt, html, rtf, ...](https://www.exoplatform.com/docs/public/index.jsp?topic=%2FPLF43%2FPLFAdminGuide.Configuration.JODConverter.html))
+Model Document must have field which contains path to file(supports [different archive types](https://github.com/phlowerteam/total_compressor) that contains [txt, pdf, doc/x, txt, html, rtf, ...](https://docs-old.exoplatform.org/public/index.jsp?topic=%2FPLF41%2FPLFAdminGuide.Configuration.JODConverter.html))
 
 Add to model next parameters for initializing:
 
-        class Document < ActiveRecord::Base
-          include ActAsPageExtractor
+```rb
+  class Document < ActiveRecord::Base
+    include ActAsPageExtractor
 
-          act_as_page_extractor options: {
-            document_class:    'Document',
-            save_as_pdf:       true,
-            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"
-          }
+    act_as_page_extractor options: {
+      document_class:    'Document',
+      save_as_pdf:       true,
+      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"
+    }
 
-          has_many :extracted_pages, dependent: :destroy
-      end
+    has_many :extracted_pages, dependent: :destroy
+end
+```
 
 Now our instance has few new methods:
 
-    document = Document.first
-    document.page_extract!
-    document.extracted_pages
-    document.pdf_path # if option 'save_as_pdf' is 'true'
+```rb
+document = Document.first
+document.page_extract!
+document.extracted_pages
+document.pdf_path # if option 'save_as_pdf' is 'true'
 
-    # Access to pages
-    ExtractedPage.count
+# Access to pages
+ExtractedPage.count
 
-    # Importing whole directory of documents
-    ActAsPageExtractor.import_files('/path/to/foler/with/documents')
+# Importing whole directory of documents
+ActAsPageExtractor.import_files('/path/to/foler/with/documents')
 
-    # We can use cron for run the processing of all the new documents
-    ActAsPageExtractor.start_extraction
+# We can use cron for run the processing of all the new documents
+ActAsPageExtractor.start_extraction
 
-    # Getting statistics information of all documents
-    ActAsPageExtractor.statistics
+# Getting statistics information of all documents
+ActAsPageExtractor.statistics
+```
 
-Parameters of initializing `act_as_page_extractor options: { ... }`:
+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** - 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")
 
 ## Run tests
-    $ COVERAGE=true rspec
-
+```sh
+rspec
+```
 ## Contributing
 1. Fork it
 2. Create your feature branch (`git checkout -b my-new-feature`)
@@ -115,5 +124,5 @@ https://github.com/phlowerteam
 phlowerteam@gmail.com
 
 ## License
-Copyright (c) 2017 PhlowerTeam
+Copyright (c) 2024 PhlowerTeam
 MIT License

data/act_as_page_extractor.gemspec

@@ -10,7 +10,7 @@ Gem::Specification.new do |spec|
   spec.email         = ['phlowerteam@gmail.com']
   spec.description   = %q{Library (Docsplit wrapper) for text extraction from pdf, doc/x, txt files with OpenOffice}
   spec.summary       = %q{Uses system calls}
-  spec.homepage      = 'https://github.com/phlowerteam'
+  spec.homepage      = 'https://github.com/phlowerteam/act_as_page_extractor'
   spec.license       = 'MIT'
 
   spec.files         = `git ls-files`.split($/)

data/lib/act_as_page_extractor/modules/tools.rb

@@ -1,17 +1,17 @@
 require 'timeout'
 
 module ActAsPageExtractor
+  # :nocov:
   def timeout_wrapper
     result = nil
     begin
       result = Timeout::timeout(60*5) { yield }
     rescue
-    # :nocov:
     ensure
-    # :nocov:
       result
     end
   end
+  # :nocov:
 
   def is_extracted
     @pdf_pages.to_i > 0 && self.extracted_pages.count == @pdf_pages
@@ -46,11 +46,11 @@ module ActAsPageExtractor
     # ap "@copy_document_path"
     # ap @copy_document_path
     # ap "@document_path"
-    ap @document_path
+      # ap @document_path
     # ap "@pdf_path"
     # ap @pdf_path
     # ap "@pdf_pages"
-    ap @pdf_pages
+      # ap @pdf_pages
   end
   # :nocov:
 end

data/lib/act_as_page_extractor/version.rb

@@ -1,5 +1,5 @@
 # :nocov:
 module ActAsPageExtractor
-  VERSION = "0.6.1"
+  VERSION = "0.6.2"
 end
 # :nocov:

data/spec/spec_helper.rb

@@ -1,7 +1,11 @@
-if ENV['COVERAGE']
+unless ENV['SKIP_COVERAGE']
   require 'simplecov'
-  SimpleCov.start 'rails'
+  SimpleCov.start 'rails' do
+    add_filter 'vendor'
+  end
+  SimpleCov.minimum_coverage 100
 end
+
 require 'rspec'
 require 'support/models'
 require 'act_as_page_extractor'

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: act_as_page_extractor
 version: !ruby/object:Gem::Version
-  version: 0.6.1
+  version: 0.6.2
 platform: ruby
 authors:
 - PhlowerTeam
@@ -249,7 +249,7 @@ files:
 - test/test-doc-3-pages.rtf
 - test/test-doc-3-pages.txt
 - test/test-doc-3-pages.wrong
-homepage: https://github.com/phlowerteam
+homepage: https://github.com/phlowerteam/act_as_page_extractor
 licenses:
 - MIT
 metadata: {}