act_as_page_extractor 0.1.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +7 -0
- data/.gitignore +57 -0
- data/.rmvrc +1 -0
- data/.rspec +3 -0
- data/.ruby-gemset +1 -0
- data/.ruby-version +1 -0
- data/Gemfile +22 -0
- data/Gemfile.lock +107 -0
- data/LICENSE +21 -0
- data/README.md +119 -0
- data/Rakefile +6 -0
- data/act_as_page_extractor.gemspec +34 -0
- data/lib/act_as_page_extractor.rb +126 -0
- data/lib/act_as_page_extractor/modules/extracting.rb +35 -0
- data/lib/act_as_page_extractor/modules/interface.rb +30 -0
- data/lib/act_as_page_extractor/modules/saving.rb +47 -0
- data/lib/act_as_page_extractor/modules/tools.rb +54 -0
- data/lib/act_as_page_extractor/modules/unzipping.rb +15 -0
- data/lib/act_as_page_extractor/modules/validating.rb +22 -0
- data/lib/act_as_page_extractor/version.rb +5 -0
- data/lib/generators/act_as_page_extractor/migration_generator.rb +49 -0
- data/lib/generators/act_as_page_extractor/templates/act_as_page_extractor.rb.erb +14 -0
- data/lib/generators/act_as_page_extractor/templates/add_page_extractor_fields_to_documents.rb.erb +8 -0
- data/lib/generators/act_as_page_extractor/templates/create_extracted_pages_table.rb.erb +19 -0
- data/lib/generators/act_as_page_extractor/templates/extracted_page.rb.erb +3 -0
- data/spec/act_as_page_extractor_spec.rb +46 -0
- data/spec/spec_helper.rb +8 -0
- data/spec/support/models.rb +92 -0
- data/test/test-doc-3-pages.doc +0 -0
- data/test/test-doc-3-pages.docx +0 -0
- data/test/test-doc-3-pages.docx.7z +0 -0
- data/test/test-doc-3-pages.docx.rar +0 -0
- data/test/test-doc-3-pages.docx.zip +0 -0
- data/test/test-doc-3-pages.html +279 -0
- data/test/test-doc-3-pages.odt +0 -0
- data/test/test-doc-3-pages.pdf +0 -0
- data/test/test-doc-3-pages.rtf +339 -0
- data/test/test-doc-3-pages.txt +125 -0
- data/test/test-doc-3-pages.wrong +0 -0
- metadata +279 -0
|
@@ -0,0 +1,125 @@
|
|
|
1
|
+
require 'act_as_page_extractor/version'
|
|
2
|
+
|
|
3
|
+
require 'active_record'
|
|
4
|
+
|
|
5
|
+
require 'awesome_print'
|
|
6
|
+
require 'filesize'
|
|
7
|
+
require 'total_compressor'
|
|
8
|
+
require 'docsplit'
|
|
9
|
+
require 'pdf_utils'
|
|
10
|
+
require 'prawn'
|
|
11
|
+
require 'pdf-reader'
|
|
12
|
+
|
|
13
|
+
require 'act_as_page_extractor/modules/tools.rb'
|
|
14
|
+
require 'act_as_page_extractor/modules/validating.rb'
|
|
15
|
+
require 'act_as_page_extractor/modules/unzipping.rb'
|
|
16
|
+
require 'act_as_page_extractor/modules/extracting.rb'
|
|
17
|
+
require 'act_as_page_extractor/modules/saving.rb'
|
|
18
|
+
|
|
19
|
+
require 'act_as_page_extractor/modules/interface'
|
|
20
|
+
|
|
21
|
+
module ActAsPageExtractor
|
|
22
|
+
|
|
23
|
+
extend ActiveSupport::Concern
|
|
24
|
+
|
|
25
|
+
included do
|
|
26
|
+
before_create { self.page_extraction_state = EXTRACTING_STATES[:new] }
|
|
27
|
+
before_destroy :remove_files
|
|
28
|
+
end
|
|
29
|
+
|
|
30
|
+
# attr_reader :options
|
|
31
|
+
|
|
32
|
+
module ClassMethods
|
|
33
|
+
def act_as_page_extractor(options: {})
|
|
34
|
+
define_method(:save_as_pdf){|*args| options[:save_as_pdf] }
|
|
35
|
+
define_method(:extracted_filename){|*args| self.send(options[:filename].to_sym) }
|
|
36
|
+
ActAsPageExtractor.define_singleton_method(:extracted_filename) {|*args| options[:filename] }
|
|
37
|
+
ActAsPageExtractor.define_singleton_method(:document_class) {|*args| options[:document_class].constantize }
|
|
38
|
+
define_method(:extracted_document_id){|*args| options[:document_id] }
|
|
39
|
+
define_method(:additional_fields){|*args| options[:additional_fields] }
|
|
40
|
+
end
|
|
41
|
+
end
|
|
42
|
+
|
|
43
|
+
EXTRACTING_STATES = {
|
|
44
|
+
new: 'new',
|
|
45
|
+
extracting: 'extracting',
|
|
46
|
+
extracted: 'extracted',
|
|
47
|
+
'error.extraction': 'error.extraction'
|
|
48
|
+
}.freeze
|
|
49
|
+
|
|
50
|
+
TMP_EXTRACTION_FILE_STORAGE = "#{Dir.pwd}/tmp/page_extraction".freeze
|
|
51
|
+
FILE_STORAGE = "#{Dir.pwd}/public".freeze
|
|
52
|
+
PDF_STORAGE = "#{FILE_STORAGE}/uploads/extracted/pdf".freeze
|
|
53
|
+
|
|
54
|
+
def initialized
|
|
55
|
+
# add all need callbacks
|
|
56
|
+
#on destroy remove pdf
|
|
57
|
+
|
|
58
|
+
#Add to Readme!!
|
|
59
|
+
#rails g act_as_page_extractor:migration Document category_id user_id
|
|
60
|
+
# add to [Document] model:
|
|
61
|
+
# has_many :extracted_pages, dependent: :destroy
|
|
62
|
+
create_pdf_dir
|
|
63
|
+
end
|
|
64
|
+
|
|
65
|
+
def page_extract!
|
|
66
|
+
initialized
|
|
67
|
+
cleanup_pages
|
|
68
|
+
create_tmp_dir
|
|
69
|
+
begin
|
|
70
|
+
copy_document
|
|
71
|
+
# debug_info
|
|
72
|
+
unzip_document
|
|
73
|
+
if valid_document
|
|
74
|
+
extract_pages
|
|
75
|
+
save_to_db
|
|
76
|
+
end
|
|
77
|
+
ensure
|
|
78
|
+
update_state
|
|
79
|
+
save_pdf
|
|
80
|
+
finish
|
|
81
|
+
end
|
|
82
|
+
end
|
|
83
|
+
|
|
84
|
+
def create_pdf_dir
|
|
85
|
+
if save_as_pdf
|
|
86
|
+
FileUtils::mkdir_p(PDF_STORAGE) unless File.exists?(PDF_STORAGE)
|
|
87
|
+
end
|
|
88
|
+
end
|
|
89
|
+
|
|
90
|
+
def create_tmp_dir
|
|
91
|
+
@tmp_dir = "#{TMP_EXTRACTION_FILE_STORAGE}/#{SecureRandom.hex(6)}"
|
|
92
|
+
FileUtils::mkdir_p(@tmp_dir) unless File.exists?(@tmp_dir)
|
|
93
|
+
end
|
|
94
|
+
|
|
95
|
+
def copy_document
|
|
96
|
+
@origin_document_path = "#{FILE_STORAGE}#{self.send(:extracted_filename).url.to_s}"
|
|
97
|
+
ap @origin_document_path
|
|
98
|
+
FileUtils.cp(@origin_document_path, @tmp_dir)
|
|
99
|
+
@copy_document_path = "#{@tmp_dir}/#{@origin_document_path.split("/").last}"
|
|
100
|
+
@document_filename = @origin_document_path.split("/").last
|
|
101
|
+
end
|
|
102
|
+
|
|
103
|
+
def finish
|
|
104
|
+
remove_tmp_dir
|
|
105
|
+
end
|
|
106
|
+
|
|
107
|
+
def remove_tmp_dir
|
|
108
|
+
FileUtils.rm_rf(@tmp_dir) if @tmp_dir =~ /\/tmp\//
|
|
109
|
+
end
|
|
110
|
+
end
|
|
111
|
+
|
|
112
|
+
# rails g model ExtractedPage page:text document_id:integer category_id:integer page_number:integer
|
|
113
|
+
|
|
114
|
+
# Rails 4 way
|
|
115
|
+
# 9.2.7.1 Multiple Callback Methods in One Class
|
|
116
|
+
# 258 page
|
|
117
|
+
|
|
118
|
+
# class ActiveRecord::Base
|
|
119
|
+
# def self.acts_as_page_extractor(document_field=:filename)
|
|
120
|
+
# auditor = Auditor.new(audit_log)
|
|
121
|
+
# after_create auditor
|
|
122
|
+
# after_update auditor
|
|
123
|
+
# after_destroy auditor
|
|
124
|
+
# end
|
|
125
|
+
# end
|
|
Binary file
|
metadata
ADDED
|
@@ -0,0 +1,279 @@
|
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
|
2
|
+
name: act_as_page_extractor
|
|
3
|
+
version: !ruby/object:Gem::Version
|
|
4
|
+
version: 0.1.0
|
|
5
|
+
platform: ruby
|
|
6
|
+
authors:
|
|
7
|
+
- PhlowerTeam
|
|
8
|
+
autorequire:
|
|
9
|
+
bindir: bin
|
|
10
|
+
cert_chain: []
|
|
11
|
+
date: 2017-01-09 00:00:00.000000000 Z
|
|
12
|
+
dependencies:
|
|
13
|
+
- !ruby/object:Gem::Dependency
|
|
14
|
+
name: bundler
|
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
|
16
|
+
requirements:
|
|
17
|
+
- - "~>"
|
|
18
|
+
- !ruby/object:Gem::Version
|
|
19
|
+
version: '1.3'
|
|
20
|
+
type: :development
|
|
21
|
+
prerelease: false
|
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
23
|
+
requirements:
|
|
24
|
+
- - "~>"
|
|
25
|
+
- !ruby/object:Gem::Version
|
|
26
|
+
version: '1.3'
|
|
27
|
+
- !ruby/object:Gem::Dependency
|
|
28
|
+
name: rake
|
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
|
30
|
+
requirements:
|
|
31
|
+
- - ">="
|
|
32
|
+
- !ruby/object:Gem::Version
|
|
33
|
+
version: '0'
|
|
34
|
+
type: :development
|
|
35
|
+
prerelease: false
|
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
37
|
+
requirements:
|
|
38
|
+
- - ">="
|
|
39
|
+
- !ruby/object:Gem::Version
|
|
40
|
+
version: '0'
|
|
41
|
+
- !ruby/object:Gem::Dependency
|
|
42
|
+
name: byebug
|
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
|
44
|
+
requirements:
|
|
45
|
+
- - ">="
|
|
46
|
+
- !ruby/object:Gem::Version
|
|
47
|
+
version: '0'
|
|
48
|
+
type: :development
|
|
49
|
+
prerelease: false
|
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
51
|
+
requirements:
|
|
52
|
+
- - ">="
|
|
53
|
+
- !ruby/object:Gem::Version
|
|
54
|
+
version: '0'
|
|
55
|
+
- !ruby/object:Gem::Dependency
|
|
56
|
+
name: rspec
|
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
|
58
|
+
requirements:
|
|
59
|
+
- - ">="
|
|
60
|
+
- !ruby/object:Gem::Version
|
|
61
|
+
version: '0'
|
|
62
|
+
type: :development
|
|
63
|
+
prerelease: false
|
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
65
|
+
requirements:
|
|
66
|
+
- - ">="
|
|
67
|
+
- !ruby/object:Gem::Version
|
|
68
|
+
version: '0'
|
|
69
|
+
- !ruby/object:Gem::Dependency
|
|
70
|
+
name: simplecov
|
|
71
|
+
requirement: !ruby/object:Gem::Requirement
|
|
72
|
+
requirements:
|
|
73
|
+
- - ">="
|
|
74
|
+
- !ruby/object:Gem::Version
|
|
75
|
+
version: '0'
|
|
76
|
+
type: :development
|
|
77
|
+
prerelease: false
|
|
78
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
79
|
+
requirements:
|
|
80
|
+
- - ">="
|
|
81
|
+
- !ruby/object:Gem::Version
|
|
82
|
+
version: '0'
|
|
83
|
+
- !ruby/object:Gem::Dependency
|
|
84
|
+
name: activerecord
|
|
85
|
+
requirement: !ruby/object:Gem::Requirement
|
|
86
|
+
requirements:
|
|
87
|
+
- - "~>"
|
|
88
|
+
- !ruby/object:Gem::Version
|
|
89
|
+
version: '4.1'
|
|
90
|
+
type: :runtime
|
|
91
|
+
prerelease: false
|
|
92
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
93
|
+
requirements:
|
|
94
|
+
- - "~>"
|
|
95
|
+
- !ruby/object:Gem::Version
|
|
96
|
+
version: '4.1'
|
|
97
|
+
- !ruby/object:Gem::Dependency
|
|
98
|
+
name: awesome_print
|
|
99
|
+
requirement: !ruby/object:Gem::Requirement
|
|
100
|
+
requirements:
|
|
101
|
+
- - ">="
|
|
102
|
+
- !ruby/object:Gem::Version
|
|
103
|
+
version: '0'
|
|
104
|
+
type: :runtime
|
|
105
|
+
prerelease: false
|
|
106
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
107
|
+
requirements:
|
|
108
|
+
- - ">="
|
|
109
|
+
- !ruby/object:Gem::Version
|
|
110
|
+
version: '0'
|
|
111
|
+
- !ruby/object:Gem::Dependency
|
|
112
|
+
name: docsplit
|
|
113
|
+
requirement: !ruby/object:Gem::Requirement
|
|
114
|
+
requirements:
|
|
115
|
+
- - ">="
|
|
116
|
+
- !ruby/object:Gem::Version
|
|
117
|
+
version: '0'
|
|
118
|
+
type: :runtime
|
|
119
|
+
prerelease: false
|
|
120
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
121
|
+
requirements:
|
|
122
|
+
- - ">="
|
|
123
|
+
- !ruby/object:Gem::Version
|
|
124
|
+
version: '0'
|
|
125
|
+
- !ruby/object:Gem::Dependency
|
|
126
|
+
name: pdf_utils
|
|
127
|
+
requirement: !ruby/object:Gem::Requirement
|
|
128
|
+
requirements:
|
|
129
|
+
- - ">="
|
|
130
|
+
- !ruby/object:Gem::Version
|
|
131
|
+
version: '0'
|
|
132
|
+
type: :runtime
|
|
133
|
+
prerelease: false
|
|
134
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
135
|
+
requirements:
|
|
136
|
+
- - ">="
|
|
137
|
+
- !ruby/object:Gem::Version
|
|
138
|
+
version: '0'
|
|
139
|
+
- !ruby/object:Gem::Dependency
|
|
140
|
+
name: prawn
|
|
141
|
+
requirement: !ruby/object:Gem::Requirement
|
|
142
|
+
requirements:
|
|
143
|
+
- - "~>"
|
|
144
|
+
- !ruby/object:Gem::Version
|
|
145
|
+
version: 0.7.1
|
|
146
|
+
type: :runtime
|
|
147
|
+
prerelease: false
|
|
148
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
149
|
+
requirements:
|
|
150
|
+
- - "~>"
|
|
151
|
+
- !ruby/object:Gem::Version
|
|
152
|
+
version: 0.7.1
|
|
153
|
+
- !ruby/object:Gem::Dependency
|
|
154
|
+
name: pdf-reader
|
|
155
|
+
requirement: !ruby/object:Gem::Requirement
|
|
156
|
+
requirements:
|
|
157
|
+
- - ">="
|
|
158
|
+
- !ruby/object:Gem::Version
|
|
159
|
+
version: '0'
|
|
160
|
+
type: :runtime
|
|
161
|
+
prerelease: false
|
|
162
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
163
|
+
requirements:
|
|
164
|
+
- - ">="
|
|
165
|
+
- !ruby/object:Gem::Version
|
|
166
|
+
version: '0'
|
|
167
|
+
- !ruby/object:Gem::Dependency
|
|
168
|
+
name: total_compressor
|
|
169
|
+
requirement: !ruby/object:Gem::Requirement
|
|
170
|
+
requirements:
|
|
171
|
+
- - ">="
|
|
172
|
+
- !ruby/object:Gem::Version
|
|
173
|
+
version: '0'
|
|
174
|
+
type: :runtime
|
|
175
|
+
prerelease: false
|
|
176
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
177
|
+
requirements:
|
|
178
|
+
- - ">="
|
|
179
|
+
- !ruby/object:Gem::Version
|
|
180
|
+
version: '0'
|
|
181
|
+
- !ruby/object:Gem::Dependency
|
|
182
|
+
name: filesize
|
|
183
|
+
requirement: !ruby/object:Gem::Requirement
|
|
184
|
+
requirements:
|
|
185
|
+
- - ">="
|
|
186
|
+
- !ruby/object:Gem::Version
|
|
187
|
+
version: '0'
|
|
188
|
+
type: :runtime
|
|
189
|
+
prerelease: false
|
|
190
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
191
|
+
requirements:
|
|
192
|
+
- - ">="
|
|
193
|
+
- !ruby/object:Gem::Version
|
|
194
|
+
version: '0'
|
|
195
|
+
description: Library (Docsplit wrapper) for text extraction from pdf, doc/x, txt files
|
|
196
|
+
with OpenOffice
|
|
197
|
+
email:
|
|
198
|
+
- phlowerteam@gmail.com
|
|
199
|
+
executables: []
|
|
200
|
+
extensions: []
|
|
201
|
+
extra_rdoc_files: []
|
|
202
|
+
files:
|
|
203
|
+
- ".gitignore"
|
|
204
|
+
- ".rmvrc"
|
|
205
|
+
- ".rspec"
|
|
206
|
+
- ".ruby-gemset"
|
|
207
|
+
- ".ruby-version"
|
|
208
|
+
- Gemfile
|
|
209
|
+
- Gemfile.lock
|
|
210
|
+
- LICENSE
|
|
211
|
+
- README.md
|
|
212
|
+
- Rakefile
|
|
213
|
+
- act_as_page_extractor.gemspec
|
|
214
|
+
- lib/act_as_page_extractor.rb
|
|
215
|
+
- lib/act_as_page_extractor/modules/extracting.rb
|
|
216
|
+
- lib/act_as_page_extractor/modules/interface.rb
|
|
217
|
+
- lib/act_as_page_extractor/modules/saving.rb
|
|
218
|
+
- lib/act_as_page_extractor/modules/tools.rb
|
|
219
|
+
- lib/act_as_page_extractor/modules/unzipping.rb
|
|
220
|
+
- lib/act_as_page_extractor/modules/validating.rb
|
|
221
|
+
- lib/act_as_page_extractor/version.rb
|
|
222
|
+
- lib/generators/act_as_page_extractor/migration_generator.rb
|
|
223
|
+
- lib/generators/act_as_page_extractor/templates/act_as_page_extractor.rb.erb
|
|
224
|
+
- lib/generators/act_as_page_extractor/templates/add_page_extractor_fields_to_documents.rb.erb
|
|
225
|
+
- lib/generators/act_as_page_extractor/templates/create_extracted_pages_table.rb.erb
|
|
226
|
+
- lib/generators/act_as_page_extractor/templates/extracted_page.rb.erb
|
|
227
|
+
- spec/act_as_page_extractor_spec.rb
|
|
228
|
+
- spec/spec_helper.rb
|
|
229
|
+
- spec/support/models.rb
|
|
230
|
+
- test/test-doc-3-pages.doc
|
|
231
|
+
- test/test-doc-3-pages.docx
|
|
232
|
+
- test/test-doc-3-pages.docx.7z
|
|
233
|
+
- test/test-doc-3-pages.docx.rar
|
|
234
|
+
- test/test-doc-3-pages.docx.zip
|
|
235
|
+
- test/test-doc-3-pages.html
|
|
236
|
+
- test/test-doc-3-pages.odt
|
|
237
|
+
- test/test-doc-3-pages.pdf
|
|
238
|
+
- test/test-doc-3-pages.rtf
|
|
239
|
+
- test/test-doc-3-pages.txt
|
|
240
|
+
- test/test-doc-3-pages.wrong
|
|
241
|
+
homepage: https://github.com/phlowerteam
|
|
242
|
+
licenses:
|
|
243
|
+
- MIT
|
|
244
|
+
metadata: {}
|
|
245
|
+
post_install_message:
|
|
246
|
+
rdoc_options: []
|
|
247
|
+
require_paths:
|
|
248
|
+
- lib
|
|
249
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
|
250
|
+
requirements:
|
|
251
|
+
- - ">="
|
|
252
|
+
- !ruby/object:Gem::Version
|
|
253
|
+
version: '0'
|
|
254
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
|
255
|
+
requirements:
|
|
256
|
+
- - ">="
|
|
257
|
+
- !ruby/object:Gem::Version
|
|
258
|
+
version: '0'
|
|
259
|
+
requirements: []
|
|
260
|
+
rubyforge_project:
|
|
261
|
+
rubygems_version: 2.5.1
|
|
262
|
+
signing_key:
|
|
263
|
+
specification_version: 4
|
|
264
|
+
summary: Uses system calls
|
|
265
|
+
test_files:
|
|
266
|
+
- spec/act_as_page_extractor_spec.rb
|
|
267
|
+
- spec/spec_helper.rb
|
|
268
|
+
- spec/support/models.rb
|
|
269
|
+
- test/test-doc-3-pages.doc
|
|
270
|
+
- test/test-doc-3-pages.docx
|
|
271
|
+
- test/test-doc-3-pages.docx.7z
|
|
272
|
+
- test/test-doc-3-pages.docx.rar
|
|
273
|
+
- test/test-doc-3-pages.docx.zip
|
|
274
|
+
- test/test-doc-3-pages.html
|
|
275
|
+
- test/test-doc-3-pages.odt
|
|
276
|
+
- test/test-doc-3-pages.pdf
|
|
277
|
+
- test/test-doc-3-pages.rtf
|
|
278
|
+
- test/test-doc-3-pages.txt
|
|
279
|
+
- test/test-doc-3-pages.wrong
|