universal_document_processor 1.0.0
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/AI_USAGE_GUIDE.md +404 -0
- data/CHANGELOG.md +67 -0
- data/GEM_RELEASE_GUIDE.md +288 -0
- data/Gemfile +27 -0
- data/LICENSE +21 -0
- data/README.md +726 -0
- data/Rakefile +36 -0
- data/lib/universal_document_processor/ai_agent.rb +491 -0
- data/lib/universal_document_processor/document.rb +225 -0
- data/lib/universal_document_processor/processors/archive_processor.rb +290 -0
- data/lib/universal_document_processor/processors/base_processor.rb +58 -0
- data/lib/universal_document_processor/processors/character_validator.rb +283 -0
- data/lib/universal_document_processor/processors/excel_processor.rb +219 -0
- data/lib/universal_document_processor/processors/image_processor.rb +172 -0
- data/lib/universal_document_processor/processors/pdf_processor.rb +105 -0
- data/lib/universal_document_processor/processors/powerpoint_processor.rb +214 -0
- data/lib/universal_document_processor/processors/text_processor.rb +360 -0
- data/lib/universal_document_processor/processors/word_processor.rb +137 -0
- data/lib/universal_document_processor/utils/file_detector.rb +83 -0
- data/lib/universal_document_processor/utils/japanese_filename_handler.rb +205 -0
- data/lib/universal_document_processor/version.rb +3 -0
- data/lib/universal_document_processor.rb +223 -0
- metadata +198 -0
metadata
ADDED
@@ -0,0 +1,198 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: universal_document_processor
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 1.0.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Vikas Patil
|
8
|
+
bindir: exe
|
9
|
+
cert_chain: []
|
10
|
+
date: 1980-01-02 00:00:00.000000000 Z
|
11
|
+
dependencies:
|
12
|
+
- !ruby/object:Gem::Dependency
|
13
|
+
name: activesupport
|
14
|
+
requirement: !ruby/object:Gem::Requirement
|
15
|
+
requirements:
|
16
|
+
- - "~>"
|
17
|
+
- !ruby/object:Gem::Version
|
18
|
+
version: '7.0'
|
19
|
+
type: :runtime
|
20
|
+
prerelease: false
|
21
|
+
version_requirements: !ruby/object:Gem::Requirement
|
22
|
+
requirements:
|
23
|
+
- - "~>"
|
24
|
+
- !ruby/object:Gem::Version
|
25
|
+
version: '7.0'
|
26
|
+
- !ruby/object:Gem::Dependency
|
27
|
+
name: marcel
|
28
|
+
requirement: !ruby/object:Gem::Requirement
|
29
|
+
requirements:
|
30
|
+
- - "~>"
|
31
|
+
- !ruby/object:Gem::Version
|
32
|
+
version: '1.0'
|
33
|
+
type: :runtime
|
34
|
+
prerelease: false
|
35
|
+
version_requirements: !ruby/object:Gem::Requirement
|
36
|
+
requirements:
|
37
|
+
- - "~>"
|
38
|
+
- !ruby/object:Gem::Version
|
39
|
+
version: '1.0'
|
40
|
+
- !ruby/object:Gem::Dependency
|
41
|
+
name: nokogiri
|
42
|
+
requirement: !ruby/object:Gem::Requirement
|
43
|
+
requirements:
|
44
|
+
- - "~>"
|
45
|
+
- !ruby/object:Gem::Version
|
46
|
+
version: '1.13'
|
47
|
+
type: :runtime
|
48
|
+
prerelease: false
|
49
|
+
version_requirements: !ruby/object:Gem::Requirement
|
50
|
+
requirements:
|
51
|
+
- - "~>"
|
52
|
+
- !ruby/object:Gem::Version
|
53
|
+
version: '1.13'
|
54
|
+
- !ruby/object:Gem::Dependency
|
55
|
+
name: rubyzip
|
56
|
+
requirement: !ruby/object:Gem::Requirement
|
57
|
+
requirements:
|
58
|
+
- - "~>"
|
59
|
+
- !ruby/object:Gem::Version
|
60
|
+
version: '2.3'
|
61
|
+
type: :runtime
|
62
|
+
prerelease: false
|
63
|
+
version_requirements: !ruby/object:Gem::Requirement
|
64
|
+
requirements:
|
65
|
+
- - "~>"
|
66
|
+
- !ruby/object:Gem::Version
|
67
|
+
version: '2.3'
|
68
|
+
- !ruby/object:Gem::Dependency
|
69
|
+
name: rspec
|
70
|
+
requirement: !ruby/object:Gem::Requirement
|
71
|
+
requirements:
|
72
|
+
- - "~>"
|
73
|
+
- !ruby/object:Gem::Version
|
74
|
+
version: '3.12'
|
75
|
+
type: :development
|
76
|
+
prerelease: false
|
77
|
+
version_requirements: !ruby/object:Gem::Requirement
|
78
|
+
requirements:
|
79
|
+
- - "~>"
|
80
|
+
- !ruby/object:Gem::Version
|
81
|
+
version: '3.12'
|
82
|
+
- !ruby/object:Gem::Dependency
|
83
|
+
name: rake
|
84
|
+
requirement: !ruby/object:Gem::Requirement
|
85
|
+
requirements:
|
86
|
+
- - "~>"
|
87
|
+
- !ruby/object:Gem::Version
|
88
|
+
version: '13.0'
|
89
|
+
type: :development
|
90
|
+
prerelease: false
|
91
|
+
version_requirements: !ruby/object:Gem::Requirement
|
92
|
+
requirements:
|
93
|
+
- - "~>"
|
94
|
+
- !ruby/object:Gem::Version
|
95
|
+
version: '13.0'
|
96
|
+
- !ruby/object:Gem::Dependency
|
97
|
+
name: rubocop
|
98
|
+
requirement: !ruby/object:Gem::Requirement
|
99
|
+
requirements:
|
100
|
+
- - "~>"
|
101
|
+
- !ruby/object:Gem::Version
|
102
|
+
version: '1.50'
|
103
|
+
type: :development
|
104
|
+
prerelease: false
|
105
|
+
version_requirements: !ruby/object:Gem::Requirement
|
106
|
+
requirements:
|
107
|
+
- - "~>"
|
108
|
+
- !ruby/object:Gem::Version
|
109
|
+
version: '1.50'
|
110
|
+
- !ruby/object:Gem::Dependency
|
111
|
+
name: yard
|
112
|
+
requirement: !ruby/object:Gem::Requirement
|
113
|
+
requirements:
|
114
|
+
- - "~>"
|
115
|
+
- !ruby/object:Gem::Version
|
116
|
+
version: '0.9'
|
117
|
+
type: :development
|
118
|
+
prerelease: false
|
119
|
+
version_requirements: !ruby/object:Gem::Requirement
|
120
|
+
requirements:
|
121
|
+
- - "~>"
|
122
|
+
- !ruby/object:Gem::Version
|
123
|
+
version: '0.9'
|
124
|
+
- !ruby/object:Gem::Dependency
|
125
|
+
name: bundler
|
126
|
+
requirement: !ruby/object:Gem::Requirement
|
127
|
+
requirements:
|
128
|
+
- - "~>"
|
129
|
+
- !ruby/object:Gem::Version
|
130
|
+
version: '2.0'
|
131
|
+
type: :development
|
132
|
+
prerelease: false
|
133
|
+
version_requirements: !ruby/object:Gem::Requirement
|
134
|
+
requirements:
|
135
|
+
- - "~>"
|
136
|
+
- !ruby/object:Gem::Version
|
137
|
+
version: '2.0'
|
138
|
+
description: A comprehensive Ruby gem that handles document processing, text extraction,
|
139
|
+
and AI-powered analysis for PDF, Word, Excel, PowerPoint, images, archives, and
|
140
|
+
more with a unified API. Includes agentic AI features for document analysis, summarization,
|
141
|
+
and intelligent extraction.
|
142
|
+
email:
|
143
|
+
- vikas.v.patil1696@gmail.com
|
144
|
+
executables: []
|
145
|
+
extensions: []
|
146
|
+
extra_rdoc_files: []
|
147
|
+
files:
|
148
|
+
- AI_USAGE_GUIDE.md
|
149
|
+
- CHANGELOG.md
|
150
|
+
- GEM_RELEASE_GUIDE.md
|
151
|
+
- Gemfile
|
152
|
+
- LICENSE
|
153
|
+
- README.md
|
154
|
+
- Rakefile
|
155
|
+
- lib/universal_document_processor.rb
|
156
|
+
- lib/universal_document_processor/ai_agent.rb
|
157
|
+
- lib/universal_document_processor/document.rb
|
158
|
+
- lib/universal_document_processor/processors/archive_processor.rb
|
159
|
+
- lib/universal_document_processor/processors/base_processor.rb
|
160
|
+
- lib/universal_document_processor/processors/character_validator.rb
|
161
|
+
- lib/universal_document_processor/processors/excel_processor.rb
|
162
|
+
- lib/universal_document_processor/processors/image_processor.rb
|
163
|
+
- lib/universal_document_processor/processors/pdf_processor.rb
|
164
|
+
- lib/universal_document_processor/processors/powerpoint_processor.rb
|
165
|
+
- lib/universal_document_processor/processors/text_processor.rb
|
166
|
+
- lib/universal_document_processor/processors/word_processor.rb
|
167
|
+
- lib/universal_document_processor/utils/file_detector.rb
|
168
|
+
- lib/universal_document_processor/utils/japanese_filename_handler.rb
|
169
|
+
- lib/universal_document_processor/version.rb
|
170
|
+
homepage: https://github.com/vikas-vpatil/universal_document_processor
|
171
|
+
licenses:
|
172
|
+
- MIT
|
173
|
+
metadata:
|
174
|
+
homepage_uri: https://github.com/vikas-vpatil/universal_document_processor
|
175
|
+
source_code_uri: https://github.com/vikas-vpatil/universal_document_processor
|
176
|
+
bug_tracker_uri: https://github.com/vikas-vpatil/universal_document_processor/issues
|
177
|
+
changelog_uri: https://github.com/vikas-vpatil/universal_document_processor/blob/main/CHANGELOG.md
|
178
|
+
documentation_uri: https://github.com/vikas-vpatil/universal_document_processor/blob/main/README.md
|
179
|
+
funding_uri: https://github.com/sponsors/vikas-vpatil
|
180
|
+
rubygems_mfa_required: 'true'
|
181
|
+
rdoc_options: []
|
182
|
+
require_paths:
|
183
|
+
- lib
|
184
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
185
|
+
requirements:
|
186
|
+
- - ">="
|
187
|
+
- !ruby/object:Gem::Version
|
188
|
+
version: 2.7.0
|
189
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
190
|
+
requirements:
|
191
|
+
- - ">="
|
192
|
+
- !ruby/object:Gem::Version
|
193
|
+
version: '0'
|
194
|
+
requirements: []
|
195
|
+
rubygems_version: 3.6.9
|
196
|
+
specification_version: 4
|
197
|
+
summary: Universal document processor with AI capabilities for all file formats
|
198
|
+
test_files: []
|