invoice_extractor_arca 0.2.0

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.
Files changed (48) hide show
  1. checksums.yaml +7 -0
  2. data/CHANGELOG.md +49 -0
  3. data/LICENSE.txt +21 -0
  4. data/README.md +631 -0
  5. data/exe/arca-invoice-extract +6 -0
  6. data/lib/invoice_extractor_arca/catalogs/copy_types.json +5 -0
  7. data/lib/invoice_extractor_arca/catalogs/currencies.json +65 -0
  8. data/lib/invoice_extractor_arca/catalogs/document_types.json +40 -0
  9. data/lib/invoice_extractor_arca/catalogs/iva_types.json +13 -0
  10. data/lib/invoice_extractor_arca/catalogs/payment_methods.json +10 -0
  11. data/lib/invoice_extractor_arca/catalogs/units_measure.json +47 -0
  12. data/lib/invoice_extractor_arca/catalogs/voucher_types.json +99 -0
  13. data/lib/invoice_extractor_arca/catalogs.rb +34 -0
  14. data/lib/invoice_extractor_arca/cli.rb +247 -0
  15. data/lib/invoice_extractor_arca/command_runner.rb +18 -0
  16. data/lib/invoice_extractor_arca/configuration.rb +42 -0
  17. data/lib/invoice_extractor_arca/dependencies/resolver.rb +118 -0
  18. data/lib/invoice_extractor_arca/error.rb +6 -0
  19. data/lib/invoice_extractor_arca/error_record.rb +39 -0
  20. data/lib/invoice_extractor_arca/errors.rb +34 -0
  21. data/lib/invoice_extractor_arca/extractor.rb +381 -0
  22. data/lib/invoice_extractor_arca/final_payload_builder.rb +67 -0
  23. data/lib/invoice_extractor_arca/ocr/rapidocr_extract.py +198 -0
  24. data/lib/invoice_extractor_arca/ocr/rapidocr_text_extractor.rb +117 -0
  25. data/lib/invoice_extractor_arca/pdf/ocr_text_extractor.rb +131 -0
  26. data/lib/invoice_extractor_arca/pdf/renderer.rb +97 -0
  27. data/lib/invoice_extractor_arca/pdf/text_extractor.rb +182 -0
  28. data/lib/invoice_extractor_arca/qr/payload_parser.rb +124 -0
  29. data/lib/invoice_extractor_arca/qr/reader.rb +53 -0
  30. data/lib/invoice_extractor_arca/qr/result_builder.rb +229 -0
  31. data/lib/invoice_extractor_arca/qr_extractor.rb +156 -0
  32. data/lib/invoice_extractor_arca/result.rb +94 -0
  33. data/lib/invoice_extractor_arca/scanners/factory.rb +88 -0
  34. data/lib/invoice_extractor_arca/scanners/qreader_scan.py +102 -0
  35. data/lib/invoice_extractor_arca/scanners/qreader_scanner.rb +131 -0
  36. data/lib/invoice_extractor_arca/scanners/scanner_chain.rb +73 -0
  37. data/lib/invoice_extractor_arca/scanners/zbar_scanner.rb +52 -0
  38. data/lib/invoice_extractor_arca/text/invoice_parser.rb +517 -0
  39. data/lib/invoice_extractor_arca/text/layout_table_parser.rb +218 -0
  40. data/lib/invoice_extractor_arca/text/locale_value_normalizer.rb +53 -0
  41. data/lib/invoice_extractor_arca/text/normalizer.rb +31 -0
  42. data/lib/invoice_extractor_arca/validation/reconciler.rb +53 -0
  43. data/lib/invoice_extractor_arca/version.rb +5 -0
  44. data/lib/invoice_extractor_arca/voucher_validator.rb +169 -0
  45. data/lib/invoice_extractor_arca.rb +117 -0
  46. data/requirements-ocr.txt +2 -0
  47. data/sig/invoice_extractor_arca.rbs +4 -0
  48. metadata +135 -0
metadata ADDED
@@ -0,0 +1,135 @@
1
+ --- !ruby/object:Gem::Specification
2
+ name: invoice_extractor_arca
3
+ version: !ruby/object:Gem::Version
4
+ version: 0.2.0
5
+ platform: ruby
6
+ authors:
7
+ - Juan Manuel Llaury
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: base64
14
+ requirement: !ruby/object:Gem::Requirement
15
+ requirements:
16
+ - - "~>"
17
+ - !ruby/object:Gem::Version
18
+ version: 0.3.0
19
+ type: :runtime
20
+ prerelease: false
21
+ version_requirements: !ruby/object:Gem::Requirement
22
+ requirements:
23
+ - - "~>"
24
+ - !ruby/object:Gem::Version
25
+ version: 0.3.0
26
+ - !ruby/object:Gem::Dependency
27
+ name: bigdecimal
28
+ requirement: !ruby/object:Gem::Requirement
29
+ requirements:
30
+ - - "~>"
31
+ - !ruby/object:Gem::Version
32
+ version: 4.1.2
33
+ type: :runtime
34
+ prerelease: false
35
+ version_requirements: !ruby/object:Gem::Requirement
36
+ requirements:
37
+ - - "~>"
38
+ - !ruby/object:Gem::Version
39
+ version: 4.1.2
40
+ - !ruby/object:Gem::Dependency
41
+ name: json
42
+ requirement: !ruby/object:Gem::Requirement
43
+ requirements:
44
+ - - "~>"
45
+ - !ruby/object:Gem::Version
46
+ version: 2.21.0
47
+ type: :runtime
48
+ prerelease: false
49
+ version_requirements: !ruby/object:Gem::Requirement
50
+ requirements:
51
+ - - "~>"
52
+ - !ruby/object:Gem::Version
53
+ version: 2.21.0
54
+ description: QR-first extraction of machine-readable ARCA electronic invoice data,
55
+ with optional text enrichment.
56
+ email:
57
+ - llauryjm@gmail.com
58
+ executables:
59
+ - arca-invoice-extract
60
+ extensions: []
61
+ extra_rdoc_files: []
62
+ files:
63
+ - CHANGELOG.md
64
+ - LICENSE.txt
65
+ - README.md
66
+ - exe/arca-invoice-extract
67
+ - lib/invoice_extractor_arca.rb
68
+ - lib/invoice_extractor_arca/catalogs.rb
69
+ - lib/invoice_extractor_arca/catalogs/copy_types.json
70
+ - lib/invoice_extractor_arca/catalogs/currencies.json
71
+ - lib/invoice_extractor_arca/catalogs/document_types.json
72
+ - lib/invoice_extractor_arca/catalogs/iva_types.json
73
+ - lib/invoice_extractor_arca/catalogs/payment_methods.json
74
+ - lib/invoice_extractor_arca/catalogs/units_measure.json
75
+ - lib/invoice_extractor_arca/catalogs/voucher_types.json
76
+ - lib/invoice_extractor_arca/cli.rb
77
+ - lib/invoice_extractor_arca/command_runner.rb
78
+ - lib/invoice_extractor_arca/configuration.rb
79
+ - lib/invoice_extractor_arca/dependencies/resolver.rb
80
+ - lib/invoice_extractor_arca/error.rb
81
+ - lib/invoice_extractor_arca/error_record.rb
82
+ - lib/invoice_extractor_arca/errors.rb
83
+ - lib/invoice_extractor_arca/extractor.rb
84
+ - lib/invoice_extractor_arca/final_payload_builder.rb
85
+ - lib/invoice_extractor_arca/ocr/rapidocr_extract.py
86
+ - lib/invoice_extractor_arca/ocr/rapidocr_text_extractor.rb
87
+ - lib/invoice_extractor_arca/pdf/ocr_text_extractor.rb
88
+ - lib/invoice_extractor_arca/pdf/renderer.rb
89
+ - lib/invoice_extractor_arca/pdf/text_extractor.rb
90
+ - lib/invoice_extractor_arca/qr/payload_parser.rb
91
+ - lib/invoice_extractor_arca/qr/reader.rb
92
+ - lib/invoice_extractor_arca/qr/result_builder.rb
93
+ - lib/invoice_extractor_arca/qr_extractor.rb
94
+ - lib/invoice_extractor_arca/result.rb
95
+ - lib/invoice_extractor_arca/scanners/factory.rb
96
+ - lib/invoice_extractor_arca/scanners/qreader_scan.py
97
+ - lib/invoice_extractor_arca/scanners/qreader_scanner.rb
98
+ - lib/invoice_extractor_arca/scanners/scanner_chain.rb
99
+ - lib/invoice_extractor_arca/scanners/zbar_scanner.rb
100
+ - lib/invoice_extractor_arca/text/invoice_parser.rb
101
+ - lib/invoice_extractor_arca/text/layout_table_parser.rb
102
+ - lib/invoice_extractor_arca/text/locale_value_normalizer.rb
103
+ - lib/invoice_extractor_arca/text/normalizer.rb
104
+ - lib/invoice_extractor_arca/validation/reconciler.rb
105
+ - lib/invoice_extractor_arca/version.rb
106
+ - lib/invoice_extractor_arca/voucher_validator.rb
107
+ - requirements-ocr.txt
108
+ - sig/invoice_extractor_arca.rbs
109
+ homepage: https://github.com/llauryjm/invoice_extractor_arca
110
+ licenses:
111
+ - MIT
112
+ metadata:
113
+ allowed_push_host: https://rubygems.org
114
+ homepage_uri: https://rubygems.org/gems/invoice_extractor_arca
115
+ source_code_uri: https://github.com/llauryjm/invoice_extractor_arca
116
+ changelog_uri: https://github.com/llauryjm/invoice_extractor_arca/blob/main/CHANGELOG.md
117
+ rubygems_mfa_required: 'true'
118
+ rdoc_options: []
119
+ require_paths:
120
+ - lib
121
+ required_ruby_version: !ruby/object:Gem::Requirement
122
+ requirements:
123
+ - - ">="
124
+ - !ruby/object:Gem::Version
125
+ version: 3.3.0
126
+ required_rubygems_version: !ruby/object:Gem::Requirement
127
+ requirements:
128
+ - - ">="
129
+ - !ruby/object:Gem::Version
130
+ version: '0'
131
+ requirements: []
132
+ rubygems_version: 4.0.16
133
+ specification_version: 4
134
+ summary: Extract structured data from Argentine ARCA electronic invoices
135
+ test_files: []