mindee 3.3.1 → 3.5.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/CHANGELOG.md +26 -0
- data/README.md +4 -0
- data/bin/mindee.rb +39 -15
- data/docs/bank_statement_fr_v1.md +175 -0
- data/docs/carte_grise_v1.md +4 -4
- data/docs/code_samples/bank_statement_fr_v1_async.txt +19 -0
- data/docs/code_samples/default.txt +19 -19
- data/docs/code_samples/default_async.txt +25 -0
- data/docs/code_samples/eu_driver_license_v1.txt +19 -0
- data/docs/code_samples/international_id_v1_async.txt +19 -0
- data/docs/code_samples/international_id_v2_async.txt +19 -0
- data/docs/eu_driver_license_v1.md +223 -0
- data/docs/financial_document_v1.md +48 -40
- data/docs/generated_v1.md +90 -0
- data/docs/invoices_v4.md +13 -4
- data/docs/proof_of_address_v1.md +4 -4
- data/docs/us_driver_license_v1.md +2 -2
- data/lib/mindee/client.rb +5 -3
- data/lib/mindee/http/endpoint.rb +13 -12
- data/lib/mindee/input/sources.rb +28 -5
- data/lib/mindee/parsing/common/inference.rb +3 -1
- data/lib/mindee/parsing/generated/generated_list_field.rb +58 -0
- data/lib/mindee/parsing/generated/generated_object_field.rb +109 -0
- data/lib/mindee/parsing/generated.rb +4 -0
- data/lib/mindee/parsing/standard/string_field.rb +8 -0
- data/lib/mindee/parsing.rb +1 -0
- data/lib/mindee/product/barcode_reader/barcode_reader_v1.rb +3 -1
- data/lib/mindee/product/cropper/cropper_v1.rb +3 -1
- data/lib/mindee/product/eu/driver_license/driver_license_v1.rb +41 -0
- data/lib/mindee/product/eu/driver_license/driver_license_v1_document.rb +88 -0
- data/lib/mindee/product/eu/driver_license/driver_license_v1_page.rb +53 -0
- data/lib/mindee/product/eu/license_plate/license_plate_v1.rb +3 -1
- data/lib/mindee/product/financial_document/financial_document_v1.rb +3 -1
- data/lib/mindee/product/fr/bank_account_details/bank_account_details_v1.rb +3 -1
- data/lib/mindee/product/fr/bank_account_details/bank_account_details_v2.rb +3 -1
- data/lib/mindee/product/fr/bank_statement/bank_statement_v1.rb +41 -0
- data/lib/mindee/product/fr/bank_statement/bank_statement_v1_document.rb +130 -0
- data/lib/mindee/product/fr/bank_statement/bank_statement_v1_page.rb +34 -0
- data/lib/mindee/product/fr/bank_statement/bank_statement_v1_transaction.rb +64 -0
- data/lib/mindee/product/fr/carte_grise/carte_grise_v1.rb +3 -1
- data/lib/mindee/product/fr/carte_vitale/carte_vitale_v1.rb +3 -1
- data/lib/mindee/product/fr/id_card/id_card_v1.rb +3 -1
- data/lib/mindee/product/fr/id_card/id_card_v2.rb +3 -1
- data/lib/mindee/product/generated/generated_v1.rb +38 -0
- data/lib/mindee/product/generated/generated_v1_document.rb +35 -0
- data/lib/mindee/product/generated/generated_v1_page.rb +51 -0
- data/lib/mindee/product/generated/generated_v1_prediction.rb +114 -0
- data/lib/mindee/product/international_id/international_id_v1.rb +39 -0
- data/lib/mindee/product/international_id/international_id_v1_document.rb +109 -0
- data/lib/mindee/product/international_id/international_id_v1_page.rb +32 -0
- data/lib/mindee/product/international_id/international_id_v2.rb +39 -0
- data/lib/mindee/product/international_id/international_id_v2_document.rb +119 -0
- data/lib/mindee/product/international_id/international_id_v2_page.rb +32 -0
- data/lib/mindee/product/invoice/invoice_v4.rb +3 -1
- data/lib/mindee/product/invoice/invoice_v4_document.rb +5 -0
- data/lib/mindee/product/multi_receipts_detector/multi_receipts_detector_v1.rb +3 -1
- data/lib/mindee/product/passport/passport_v1.rb +3 -1
- data/lib/mindee/product/proof_of_address/proof_of_address_v1.rb +3 -1
- data/lib/mindee/product/receipt/receipt_v5.rb +3 -1
- data/lib/mindee/product/us/bank_check/bank_check_v1.rb +3 -1
- data/lib/mindee/product/us/driver_license/driver_license_v1.rb +3 -1
- data/lib/mindee/product/us/w9/w9_v1.rb +3 -1
- data/lib/mindee/product.rb +5 -0
- data/lib/mindee/version.rb +1 -1
- data/lib/mindee.rb +4 -0
- metadata +30 -2
@@ -0,0 +1,223 @@
|
|
1
|
+
---
|
2
|
+
title: EU EU Driver License OCR Ruby
|
3
|
+
---
|
4
|
+
The Ruby OCR SDK supports the [EU Driver License API](https://platform.mindee.com/mindee/eu_driver_license).
|
5
|
+
|
6
|
+
Using the [sample below](https://github.com/mindee/client-lib-test-data/blob/main/products/eu_driver_license/default_sample.jpg), we are going to illustrate how to extract the data that we want using the OCR SDK.
|
7
|
+
![EU Driver License sample](https://github.com/mindee/client-lib-test-data/blob/main/products/eu_driver_license/default_sample.jpg?raw=true)
|
8
|
+
|
9
|
+
# Quick-Start
|
10
|
+
```rb
|
11
|
+
require 'mindee'
|
12
|
+
|
13
|
+
# Init a new client
|
14
|
+
mindee_client = Mindee::Client.new(api_key: 'my-api-key')
|
15
|
+
|
16
|
+
# Load a file from disk
|
17
|
+
input_source = mindee_client.source_from_path('/path/to/the/file.ext')
|
18
|
+
|
19
|
+
# Parse the file
|
20
|
+
result = mindee_client.parse(
|
21
|
+
input_source,
|
22
|
+
Mindee::Product::EU::DriverLicense::DriverLicenseV1
|
23
|
+
)
|
24
|
+
|
25
|
+
# Print a full summary of the parsed data in RST format
|
26
|
+
puts result.document
|
27
|
+
|
28
|
+
# Print the document-level parsed data
|
29
|
+
# puts result.document.inference.prediction
|
30
|
+
```
|
31
|
+
|
32
|
+
**Output (RST):**
|
33
|
+
```rst
|
34
|
+
########
|
35
|
+
Document
|
36
|
+
########
|
37
|
+
:Mindee ID: b19cc32e-b3e6-4ff9-bdc7-619199355d54
|
38
|
+
:Filename: default_sample.jpg
|
39
|
+
|
40
|
+
Inference
|
41
|
+
#########
|
42
|
+
:Product: mindee/eu_driver_license v1.0
|
43
|
+
:Rotation applied: Yes
|
44
|
+
|
45
|
+
Prediction
|
46
|
+
==========
|
47
|
+
:Country Code: FR
|
48
|
+
:Document ID: 13AA00002
|
49
|
+
:Driver License Category: AM A1 B1 B D BE DE
|
50
|
+
:Last Name: MARTIN
|
51
|
+
:First Name: PAUL
|
52
|
+
:Date Of Birth: 1981-07-14
|
53
|
+
:Place Of Birth: Utopiacity
|
54
|
+
:Expiry Date: 2018-12-31
|
55
|
+
:Issue Date: 2013-01-01
|
56
|
+
:Issue Authority: 99999UpiaCity
|
57
|
+
:MRZ: D1FRA13AA000026181231MARTIN<<9
|
58
|
+
:Address:
|
59
|
+
|
60
|
+
Page Predictions
|
61
|
+
================
|
62
|
+
|
63
|
+
Page 0
|
64
|
+
------
|
65
|
+
:Photo: Polygon with 4 points.
|
66
|
+
:Signature: Polygon with 4 points.
|
67
|
+
:Country Code: FR
|
68
|
+
:Document ID: 13AA00002
|
69
|
+
:Driver License Category: AM A1 B1 B D BE DE
|
70
|
+
:Last Name: MARTIN
|
71
|
+
:First Name: PAUL
|
72
|
+
:Date Of Birth: 1981-07-14
|
73
|
+
:Place Of Birth: Utopiacity
|
74
|
+
:Expiry Date: 2018-12-31
|
75
|
+
:Issue Date: 2013-01-01
|
76
|
+
:Issue Authority: 99999UpiaCity
|
77
|
+
:MRZ: D1FRA13AA000026181231MARTIN<<9
|
78
|
+
:Address:
|
79
|
+
```
|
80
|
+
|
81
|
+
# Field Types
|
82
|
+
## Standard Fields
|
83
|
+
These fields are generic and used in several products.
|
84
|
+
|
85
|
+
### Basic Field
|
86
|
+
Each prediction object contains a set of fields that inherit from the generic `Field` class.
|
87
|
+
A typical `Field` object will have the following attributes:
|
88
|
+
|
89
|
+
* **value** (`String`, `Float`, `Integer`, `Boolean`): corresponds to the field value. Can be `nil` if no value was extracted.
|
90
|
+
* **confidence** (Float, nil): the confidence score of the field prediction.
|
91
|
+
* **bounding_box** (`Mindee::Geometry::Quadrilateral`, `nil`): contains exactly 4 relative vertices (points) coordinates of a right rectangle containing the field in the document.
|
92
|
+
* **polygon** (`Mindee::Geometry::Polygon`, `nil`): contains the relative vertices coordinates (`Point`) of a polygon containing the field in the image.
|
93
|
+
* **page_id** (`Integer`, `nil`): the ID of the page, is `nil` when at document-level.
|
94
|
+
* **reconstructed** (`Boolean`): indicates whether an object was reconstructed (not extracted as the API gave it).
|
95
|
+
|
96
|
+
|
97
|
+
Aside from the previous attributes, all basic fields have access to a `to_s` method that can be used to print their value as a string.
|
98
|
+
|
99
|
+
### Date Field
|
100
|
+
Aside from the basic `Field` attributes, the date field `DateField` also implements the following:
|
101
|
+
|
102
|
+
* **date_object** (`Date`): an accessible representation of the value as a JavaScript object.
|
103
|
+
|
104
|
+
|
105
|
+
### Position Field
|
106
|
+
The position field `PositionField` does not implement all the basic `Field` attributes, only **bounding_box**, **polygon** and **page_id**. On top of these, it has access to:
|
107
|
+
|
108
|
+
* **rectangle** (`Mindee::Geometry::Quadrilateral`): a Polygon with four points that may be oriented (even beyond canvas).
|
109
|
+
* **quadrangle** (`Mindee::Geometry::Quadrilateral`): a free polygon made up of four points.
|
110
|
+
|
111
|
+
### String Field
|
112
|
+
The text field `StringField` only has one constraint: it's **value** is a `String` (or `nil`).
|
113
|
+
|
114
|
+
## Page-Level Fields
|
115
|
+
Some fields are constrained to the page level, and so will not be retrievable to through the document.
|
116
|
+
|
117
|
+
# Attributes
|
118
|
+
The following fields are extracted for EU Driver License V1:
|
119
|
+
|
120
|
+
## Address
|
121
|
+
**address** ([StringField](#string-field)): EU driver license holders address
|
122
|
+
|
123
|
+
```rb
|
124
|
+
puts result.document.inference.prediction.address.value
|
125
|
+
```
|
126
|
+
|
127
|
+
## Driver License Category
|
128
|
+
**category** ([StringField](#string-field)): EU driver license holders categories
|
129
|
+
|
130
|
+
```rb
|
131
|
+
puts result.document.inference.prediction.category.value
|
132
|
+
```
|
133
|
+
|
134
|
+
## Country Code
|
135
|
+
**country_code** ([StringField](#string-field)): Country code extracted as a string.
|
136
|
+
|
137
|
+
```rb
|
138
|
+
puts result.document.inference.prediction.country_code.value
|
139
|
+
```
|
140
|
+
|
141
|
+
## Date Of Birth
|
142
|
+
**date_of_birth** ([DateField](#date-field)): The date of birth of the document holder
|
143
|
+
|
144
|
+
```rb
|
145
|
+
puts result.document.inference.prediction.date_of_birth.value
|
146
|
+
```
|
147
|
+
|
148
|
+
## Document ID
|
149
|
+
**document_id** ([StringField](#string-field)): ID number of the Document.
|
150
|
+
|
151
|
+
```rb
|
152
|
+
puts result.document.inference.prediction.document_id.value
|
153
|
+
```
|
154
|
+
|
155
|
+
## Expiry Date
|
156
|
+
**expiry_date** ([DateField](#date-field)): Date the document expires
|
157
|
+
|
158
|
+
```rb
|
159
|
+
puts result.document.inference.prediction.expiry_date.value
|
160
|
+
```
|
161
|
+
|
162
|
+
## First Name
|
163
|
+
**first_name** ([StringField](#string-field)): First name(s) of the driver license holder
|
164
|
+
|
165
|
+
```rb
|
166
|
+
puts result.document.inference.prediction.first_name.value
|
167
|
+
```
|
168
|
+
|
169
|
+
## Issue Authority
|
170
|
+
**issue_authority** ([StringField](#string-field)): Authority that issued the document
|
171
|
+
|
172
|
+
```rb
|
173
|
+
puts result.document.inference.prediction.issue_authority.value
|
174
|
+
```
|
175
|
+
|
176
|
+
## Issue Date
|
177
|
+
**issue_date** ([DateField](#date-field)): Date the document was issued
|
178
|
+
|
179
|
+
```rb
|
180
|
+
puts result.document.inference.prediction.issue_date.value
|
181
|
+
```
|
182
|
+
|
183
|
+
## Last Name
|
184
|
+
**last_name** ([StringField](#string-field)): Last name of the driver license holder.
|
185
|
+
|
186
|
+
```rb
|
187
|
+
puts result.document.inference.prediction.last_name.value
|
188
|
+
```
|
189
|
+
|
190
|
+
## MRZ
|
191
|
+
**mrz** ([StringField](#string-field)): Machine-readable license number
|
192
|
+
|
193
|
+
```rb
|
194
|
+
puts result.document.inference.prediction.mrz.value
|
195
|
+
```
|
196
|
+
|
197
|
+
## Photo
|
198
|
+
[📄](#page-level-fields "This field is only present on individual pages.")**photo** ([PositionField](#position-field)): Has a photo of the EU driver license holder
|
199
|
+
|
200
|
+
```rb
|
201
|
+
for photo_elem in result.document.photo do
|
202
|
+
puts photo_elem.polygon
|
203
|
+
end
|
204
|
+
```
|
205
|
+
|
206
|
+
## Place Of Birth
|
207
|
+
**place_of_birth** ([StringField](#string-field)): Place where the driver license holder was born
|
208
|
+
|
209
|
+
```rb
|
210
|
+
puts result.document.inference.prediction.place_of_birth.value
|
211
|
+
```
|
212
|
+
|
213
|
+
## Signature
|
214
|
+
[📄](#page-level-fields "This field is only present on individual pages.")**signature** ([PositionField](#position-field)): Has a signature of the EU driver license holder
|
215
|
+
|
216
|
+
```rb
|
217
|
+
for signature_elem in result.document.signature do
|
218
|
+
puts signature_elem.polygon
|
219
|
+
end
|
220
|
+
```
|
221
|
+
|
222
|
+
# Questions?
|
223
|
+
[Join our Slack](https://join.slack.com/t/mindee-community/shared_invite/zt-1jv6nawjq-FDgFcF2T5CmMmRpl9LLptw)
|
@@ -34,48 +34,52 @@ puts result.document
|
|
34
34
|
########
|
35
35
|
Document
|
36
36
|
########
|
37
|
-
:Mindee ID:
|
37
|
+
:Mindee ID: a6b54e2d-a7fa-4e08-8de6-6cd296f50f3d
|
38
38
|
:Filename: default_sample.jpg
|
39
39
|
|
40
40
|
Inference
|
41
41
|
#########
|
42
|
-
:Product: mindee/financial_document v1.
|
42
|
+
:Product: mindee/financial_document v1.2
|
43
43
|
:Rotation applied: Yes
|
44
44
|
|
45
45
|
Prediction
|
46
46
|
==========
|
47
47
|
:Locale: en; en; USD;
|
48
|
-
:Invoice Number:
|
49
|
-
:Reference Numbers:
|
50
|
-
:Purchase Date:
|
51
|
-
:Due Date:
|
52
|
-
:Total Net:
|
53
|
-
:Total Amount:
|
48
|
+
:Invoice Number: INT-001
|
49
|
+
:Reference Numbers: 2412/2019
|
50
|
+
:Purchase Date: 2019-02-11
|
51
|
+
:Due Date: 2019-02-26
|
52
|
+
:Total Net: 195.00
|
53
|
+
:Total Amount: 204.75
|
54
54
|
:Taxes:
|
55
55
|
+---------------+--------+----------+---------------+
|
56
56
|
| Base | Code | Rate (%) | Amount |
|
57
57
|
+===============+========+==========+===============+
|
58
|
-
| |
|
58
|
+
| | | 5.00 | 9.75 |
|
59
59
|
+---------------+--------+----------+---------------+
|
60
60
|
:Supplier Payment Details:
|
61
|
-
:Supplier Name:
|
61
|
+
:Supplier Name: JOHN SMITH
|
62
62
|
:Supplier Company Registrations:
|
63
|
-
:Supplier Address:
|
64
|
-
:Supplier Phone Number:
|
65
|
-
:Customer Name:
|
63
|
+
:Supplier Address: 4490 Oak Drive Albany, NY 12210
|
64
|
+
:Supplier Phone Number:
|
65
|
+
:Customer Name: JESSIE M HORNE
|
66
66
|
:Customer Company Registrations:
|
67
|
-
:Customer Address:
|
68
|
-
:Document Type:
|
69
|
-
:Purchase Subcategory:
|
70
|
-
:Purchase Category:
|
71
|
-
:Total Tax:
|
72
|
-
:Tip and Gratuity:
|
73
|
-
:Purchase Time:
|
67
|
+
:Customer Address: 2019 Redbud Drive New York, NY 10011
|
68
|
+
:Document Type: INVOICE
|
69
|
+
:Purchase Subcategory:
|
70
|
+
:Purchase Category: miscellaneous
|
71
|
+
:Total Tax: 9.75
|
72
|
+
:Tip and Gratuity:
|
73
|
+
:Purchase Time:
|
74
74
|
:Line Items:
|
75
75
|
+--------------------------------------+--------------+----------+------------+--------------+--------------+------------+
|
76
76
|
| Description | Product code | Quantity | Tax Amount | Tax Rate (%) | Total Amount | Unit Price |
|
77
77
|
+======================================+==============+==========+============+==============+==============+============+
|
78
|
-
|
|
78
|
+
| Front and rear brake cables | | 1.00 | | | 100.00 | 100.00 |
|
79
|
+
+--------------------------------------+--------------+----------+------------+--------------+--------------+------------+
|
80
|
+
| New set of pedal arms | | 2.00 | | | 50.00 | 25.00 |
|
81
|
+
+--------------------------------------+--------------+----------+------------+--------------+--------------+------------+
|
82
|
+
| Labon 3hrs | | 3.00 | | | 45.00 | 15.00 |
|
79
83
|
+--------------------------------------+--------------+----------+------------+--------------+--------------+------------+
|
80
84
|
|
81
85
|
Page Predictions
|
@@ -84,37 +88,41 @@ Page Predictions
|
|
84
88
|
Page 0
|
85
89
|
------
|
86
90
|
:Locale: en; en; USD;
|
87
|
-
:Invoice Number:
|
88
|
-
:Reference Numbers:
|
89
|
-
:Purchase Date:
|
90
|
-
:Due Date:
|
91
|
-
:Total Net:
|
92
|
-
:Total Amount:
|
91
|
+
:Invoice Number: INT-001
|
92
|
+
:Reference Numbers: 2412/2019
|
93
|
+
:Purchase Date: 2019-02-11
|
94
|
+
:Due Date: 2019-02-26
|
95
|
+
:Total Net: 195.00
|
96
|
+
:Total Amount: 204.75
|
93
97
|
:Taxes:
|
94
98
|
+---------------+--------+----------+---------------+
|
95
99
|
| Base | Code | Rate (%) | Amount |
|
96
100
|
+===============+========+==========+===============+
|
97
|
-
| |
|
101
|
+
| | | 5.00 | 9.75 |
|
98
102
|
+---------------+--------+----------+---------------+
|
99
103
|
:Supplier Payment Details:
|
100
|
-
:Supplier Name:
|
104
|
+
:Supplier Name: JOHN SMITH
|
101
105
|
:Supplier Company Registrations:
|
102
|
-
:Supplier Address:
|
103
|
-
:Supplier Phone Number:
|
104
|
-
:Customer Name:
|
106
|
+
:Supplier Address: 4490 Oak Drive Albany, NY 12210
|
107
|
+
:Supplier Phone Number:
|
108
|
+
:Customer Name: JESSIE M HORNE
|
105
109
|
:Customer Company Registrations:
|
106
|
-
:Customer Address:
|
107
|
-
:Document Type:
|
108
|
-
:Purchase Subcategory:
|
109
|
-
:Purchase Category:
|
110
|
-
:Total Tax:
|
111
|
-
:Tip and Gratuity:
|
112
|
-
:Purchase Time:
|
110
|
+
:Customer Address: 2019 Redbud Drive New York, NY 10011
|
111
|
+
:Document Type: INVOICE
|
112
|
+
:Purchase Subcategory:
|
113
|
+
:Purchase Category: miscellaneous
|
114
|
+
:Total Tax: 9.75
|
115
|
+
:Tip and Gratuity:
|
116
|
+
:Purchase Time:
|
113
117
|
:Line Items:
|
114
118
|
+--------------------------------------+--------------+----------+------------+--------------+--------------+------------+
|
115
119
|
| Description | Product code | Quantity | Tax Amount | Tax Rate (%) | Total Amount | Unit Price |
|
116
120
|
+======================================+==============+==========+============+==============+==============+============+
|
117
|
-
|
|
121
|
+
| Front and rear brake cables | | 1.00 | | | 100.00 | 100.00 |
|
122
|
+
+--------------------------------------+--------------+----------+------------+--------------+--------------+------------+
|
123
|
+
| New set of pedal arms | | 2.00 | | | 50.00 | 25.00 |
|
124
|
+
+--------------------------------------+--------------+----------+------------+--------------+--------------+------------+
|
125
|
+
| Labon 3hrs | | 3.00 | | | 45.00 | 15.00 |
|
118
126
|
+--------------------------------------+--------------+----------+------------+--------------+--------------+------------+
|
119
127
|
```
|
120
128
|
|
@@ -0,0 +1,90 @@
|
|
1
|
+
---
|
2
|
+
title: Generated API Ruby
|
3
|
+
---
|
4
|
+
The Ruby OCR SDK supports generated APIs.
|
5
|
+
Generated APIs can theoretically support all APIs in a catch-all generic format.
|
6
|
+
|
7
|
+
# Quick-Start
|
8
|
+
|
9
|
+
```ruby
|
10
|
+
require 'mindee'
|
11
|
+
|
12
|
+
# Init a new client
|
13
|
+
mindee_client = Mindee::Client.new(api_key: 'my-api-key')
|
14
|
+
|
15
|
+
# Load a file from disk
|
16
|
+
input_source = mindee_client.source_from_path('/path/to/the/file.ext')
|
17
|
+
|
18
|
+
# Initialize a custom endpoint for this product
|
19
|
+
custom_endpoint = mindee_client.create_endpoint(
|
20
|
+
account_name: 'my-account',
|
21
|
+
endpoint_name: 'my-endpoint',
|
22
|
+
version: 'my-version'
|
23
|
+
)
|
24
|
+
|
25
|
+
# Parse the file
|
26
|
+
result = mindee_client.enqueue_and_parse(
|
27
|
+
input_source,
|
28
|
+
Mindee::Product::Generated::GeneratedV1,
|
29
|
+
endpoint: custom_endpoint
|
30
|
+
)
|
31
|
+
|
32
|
+
# Print a full summary of the parsed data in RST format
|
33
|
+
puts result.document
|
34
|
+
```
|
35
|
+
|
36
|
+
# Generated Endpoints
|
37
|
+
|
38
|
+
You may have noticed in the previous step that in order to access a custom build, you will need to provide an account and an endpoint name at the very least.
|
39
|
+
|
40
|
+
Although it is optional, the version number should match the latest version of your build in most use-cases.
|
41
|
+
If it is not set, it will default to "1".
|
42
|
+
|
43
|
+
# Field Types
|
44
|
+
|
45
|
+
## Generated Fields
|
46
|
+
|
47
|
+
### Generated List Field
|
48
|
+
|
49
|
+
A `GeneratedListField` is a special type of custom list that implements the following:
|
50
|
+
|
51
|
+
- **values** (`Array<StringField`[GeneratedObjectField](#Generated-object-field)`>`): the confidence score of the field prediction.
|
52
|
+
- **page_id** (`Integer`): only available for some documents ATM.
|
53
|
+
|
54
|
+
Since the inner contents can vary, the value isn't accessed through a property, but rather through the following functions:
|
55
|
+
|
56
|
+
- **contents_list()** (`-> Array<String, Float>>`): returns a list of values for each element.
|
57
|
+
- **contents_string(separator=" ")** (`-> String`): returns a list of concatenated values, with an optional **separator** `String` between them.
|
58
|
+
> **Note:** the `to_s` method returns a string representation of all values of this object, with an empty space between each of them.
|
59
|
+
|
60
|
+
### Generated Object Field
|
61
|
+
|
62
|
+
Unrecognized structures and sometimes values of `ListField`s are stored in a `GeneratedObjectField` structure, which is implemented dynamically depending on the object's structure.
|
63
|
+
|
64
|
+
- **page_id** (`[Integer, nil]`): the ID of the page, is `nil` when at document-level.
|
65
|
+
- **raw_value** (`[String, nil]`): an optional field for when some post-processing has been done on fields (e.g. amounts). `nil` in most instances.
|
66
|
+
- **confidence** (`[Float, nil]`): the confidence score of the field prediction. Warning: support isn't guaranteed on all APIs.
|
67
|
+
|
68
|
+
|
69
|
+
> **Other fields**:No matter what, other fields will be stored in a dictionary-like structure with a `key: value` pair where `key` is a string and `value` is a nullable string. They can be accessed like any other regular value, but won't be suggested by your IDE.
|
70
|
+
|
71
|
+
|
72
|
+
### StringField
|
73
|
+
The text field `StringField` only has one constraint: its **value** is an `Optional[str]`.
|
74
|
+
|
75
|
+
|
76
|
+
# Attributes
|
77
|
+
|
78
|
+
Generated builds always have access to at least two attributes:
|
79
|
+
|
80
|
+
## Fields
|
81
|
+
|
82
|
+
**fields** (`Hash<String, Array<`[GeneratedListField](#generated-list-field),[GeneratedObjectField](#generated-object-field), `(#stringfield)[StringField]>>`):
|
83
|
+
|
84
|
+
```ruby
|
85
|
+
puts result.document.inference.prediction.fields["my-field"].to_s
|
86
|
+
```
|
87
|
+
|
88
|
+
# Questions?
|
89
|
+
|
90
|
+
[Join our Slack](https://join.slack.com/t/mindee-community/shared_invite/zt-1jv6nawjq-FDgFcF2T5CmMmRpl9LLptw)
|
data/docs/invoices_v4.md
CHANGED
@@ -34,12 +34,12 @@ puts result.document
|
|
34
34
|
########
|
35
35
|
Document
|
36
36
|
########
|
37
|
-
:Mindee ID:
|
37
|
+
:Mindee ID: 80f2328c-58a5-486a-9599-eb2d738680f0
|
38
38
|
:Filename: default_sample.jpg
|
39
39
|
|
40
40
|
Inference
|
41
41
|
#########
|
42
|
-
:Product: mindee/invoices v4.
|
42
|
+
:Product: mindee/invoices v4.4
|
43
43
|
:Rotation applied: Yes
|
44
44
|
|
45
45
|
Prediction
|
@@ -51,6 +51,7 @@ Prediction
|
|
51
51
|
:Due Date: 2018-09-25
|
52
52
|
:Total Net:
|
53
53
|
:Total Amount: 2608.20
|
54
|
+
:Total Tax: 193.20
|
54
55
|
:Taxes:
|
55
56
|
+---------------+--------+----------+---------------+
|
56
57
|
| Base | Code | Rate (%) | Amount |
|
@@ -58,7 +59,7 @@ Prediction
|
|
58
59
|
| | | 8.00 | 193.20 |
|
59
60
|
+---------------+--------+----------+---------------+
|
60
61
|
:Supplier Payment Details:
|
61
|
-
:Supplier Name: TURNPIKE DESIGNS
|
62
|
+
:Supplier Name: TURNPIKE DESIGNS
|
62
63
|
:Supplier Company Registrations:
|
63
64
|
:Supplier Address: 156 University Ave, Toronto ON, Canada M5H 2H7
|
64
65
|
:Customer Name: JIRO DOI
|
@@ -88,6 +89,7 @@ Page 0
|
|
88
89
|
:Due Date: 2018-09-25
|
89
90
|
:Total Net:
|
90
91
|
:Total Amount: 2608.20
|
92
|
+
:Total Tax: 193.20
|
91
93
|
:Taxes:
|
92
94
|
+---------------+--------+----------+---------------+
|
93
95
|
| Base | Code | Rate (%) | Amount |
|
@@ -95,7 +97,7 @@ Page 0
|
|
95
97
|
| | | 8.00 | 193.20 |
|
96
98
|
+---------------+--------+----------+---------------+
|
97
99
|
:Supplier Payment Details:
|
98
|
-
:Supplier Name: TURNPIKE DESIGNS
|
100
|
+
:Supplier Name: TURNPIKE DESIGNS
|
99
101
|
:Supplier Company Registrations:
|
100
102
|
:Supplier Address: 156 University Ave, Toronto ON, Canada M5H 2H7
|
101
103
|
:Customer Name: JIRO DOI
|
@@ -337,5 +339,12 @@ puts result.document.inference.prediction.total_amount.value
|
|
337
339
|
puts result.document.inference.prediction.total_net.value
|
338
340
|
```
|
339
341
|
|
342
|
+
## Total Tax
|
343
|
+
**total_tax** ([AmountField](#amount-field)): The total tax: includes all the taxes paid for this invoice.
|
344
|
+
|
345
|
+
```rb
|
346
|
+
puts result.document.inference.prediction.total_tax.value
|
347
|
+
```
|
348
|
+
|
340
349
|
# Questions?
|
341
350
|
[Join our Slack](https://join.slack.com/t/mindee-community/shared_invite/zt-1jv6nawjq-FDgFcF2T5CmMmRpl9LLptw)
|
data/docs/proof_of_address_v1.md
CHANGED
@@ -34,12 +34,12 @@ puts result.document
|
|
34
34
|
########
|
35
35
|
Document
|
36
36
|
########
|
37
|
-
:Mindee ID:
|
37
|
+
:Mindee ID: 5d2361e9-405e-4fc1-8531-f92a3aef0c38
|
38
38
|
:Filename: default_sample.jpg
|
39
39
|
|
40
40
|
Inference
|
41
41
|
#########
|
42
|
-
:Product: mindee/proof_of_address v1.
|
42
|
+
:Product: mindee/proof_of_address v1.1
|
43
43
|
:Rotation applied: Yes
|
44
44
|
|
45
45
|
Prediction
|
@@ -47,7 +47,7 @@ Prediction
|
|
47
47
|
:Locale: en; en; USD;
|
48
48
|
:Issuer Name: PPL ELECTRIC UTILITIES
|
49
49
|
:Issuer Company Registrations:
|
50
|
-
:Issuer Address: 2 NORTH 9TH STREET CPC-GENN1 ALLENTOWN
|
50
|
+
:Issuer Address: 2 NORTH 9TH STREET CPC-GENN1 ALLENTOWN.PA 18101-1175
|
51
51
|
:Recipient Name:
|
52
52
|
:Recipient Company Registrations:
|
53
53
|
:Recipient Address: 123 MAIN ST ANYTOWN,PA 18062
|
@@ -73,7 +73,7 @@ Page 0
|
|
73
73
|
:Locale: en; en; USD;
|
74
74
|
:Issuer Name: PPL ELECTRIC UTILITIES
|
75
75
|
:Issuer Company Registrations:
|
76
|
-
:Issuer Address: 2 NORTH 9TH STREET CPC-GENN1 ALLENTOWN
|
76
|
+
:Issuer Address: 2 NORTH 9TH STREET CPC-GENN1 ALLENTOWN.PA 18101-1175
|
77
77
|
:Recipient Name:
|
78
78
|
:Recipient Company Registrations:
|
79
79
|
:Recipient Address: 123 MAIN ST ANYTOWN,PA 18062
|
@@ -54,7 +54,7 @@ Prediction
|
|
54
54
|
:Date Of Birth: 1957-02-01
|
55
55
|
:Restrictions: NONE
|
56
56
|
:Endorsements: NONE
|
57
|
-
:Class:
|
57
|
+
:Driver License Class: D
|
58
58
|
:Sex: M
|
59
59
|
:Height: 5-08
|
60
60
|
:Weight: 185
|
@@ -79,7 +79,7 @@ Page 0
|
|
79
79
|
:Date Of Birth: 1957-02-01
|
80
80
|
:Restrictions: NONE
|
81
81
|
:Endorsements: NONE
|
82
|
-
:Class:
|
82
|
+
:Driver License Class: D
|
83
83
|
:Sex: M
|
84
84
|
:Height: 5-08
|
85
85
|
:Weight: 185
|
data/lib/mindee/client.rb
CHANGED
@@ -38,6 +38,7 @@ module Mindee
|
|
38
38
|
# @param cropper [Boolean] Whether to include cropper results for each page.
|
39
39
|
# This performs a cropping operation on the server and will increase response time.
|
40
40
|
#
|
41
|
+
#
|
41
42
|
# @return [Mindee::Parsing::Common::ApiResponse]
|
42
43
|
def parse(
|
43
44
|
input_source,
|
@@ -80,6 +81,7 @@ module Mindee
|
|
80
81
|
# @param cropper [Boolean] Whether to include cropper results for each page.
|
81
82
|
# This performs a cropping operation on the server and will increase response time.
|
82
83
|
#
|
84
|
+
#
|
83
85
|
# @return [Mindee::Parsing::Common::ApiResponse]
|
84
86
|
def enqueue(
|
85
87
|
input_source,
|
@@ -118,7 +120,6 @@ module Mindee
|
|
118
120
|
end
|
119
121
|
|
120
122
|
# rubocop:disable Metrics/ParameterLists
|
121
|
-
|
122
123
|
# Enqueue a document for async parsing and automatically try to retrieve it
|
123
124
|
#
|
124
125
|
# @param input_source [Mindee::Input::Source::LocalInputSource, Mindee::Input::Source::UrlInputSource]
|
@@ -139,7 +140,7 @@ module Mindee
|
|
139
140
|
# This performs a cropping operation on the server and will increase response time.
|
140
141
|
# @param initial_delay_sec [Integer, Float, nil] initial delay before polling. Defaults to 4.
|
141
142
|
# @param delay_sec [Integer, Float, nil] delay between polling attempts. Defaults to 2.
|
142
|
-
# @param max_retries [Integer, nil] maximum amount of retries. Defaults to
|
143
|
+
# @param max_retries [Integer, nil] maximum amount of retries. Defaults to 60.
|
143
144
|
# @return [Mindee::Parsing::Common::ApiResponse]
|
144
145
|
def enqueue_and_parse(
|
145
146
|
input_source,
|
@@ -151,7 +152,7 @@ module Mindee
|
|
151
152
|
cropper: false,
|
152
153
|
initial_delay_sec: 4,
|
153
154
|
delay_sec: 2,
|
154
|
-
max_retries:
|
155
|
+
max_retries: 60
|
155
156
|
)
|
156
157
|
enqueue_res = enqueue(
|
157
158
|
input_source,
|
@@ -178,6 +179,7 @@ module Mindee
|
|
178
179
|
|
179
180
|
queue_res
|
180
181
|
end
|
182
|
+
|
181
183
|
# rubocop:enable Metrics/ParameterLists
|
182
184
|
|
183
185
|
# Load a document from an absolute path, as a string.
|
data/lib/mindee/http/endpoint.rb
CHANGED
@@ -46,9 +46,9 @@ module Mindee
|
|
46
46
|
|
47
47
|
# Call the prediction API.
|
48
48
|
# @param input_source [Mindee::Input::Source::LocalInputSource, Mindee::Input::Source::UrlInputSource]
|
49
|
-
# @param all_words [Boolean]
|
50
|
-
# @param close_file [Boolean]
|
51
|
-
# @param cropper [Boolean]
|
49
|
+
# @param all_words [Boolean] Whether the full word extraction needs to be performed
|
50
|
+
# @param close_file [Boolean] Whether the file will be closed after reading
|
51
|
+
# @param cropper [Boolean] Whether a cropping operation will be applied
|
52
52
|
# @return [Hash]
|
53
53
|
def predict(input_source, all_words, close_file, cropper)
|
54
54
|
check_api_key
|
@@ -62,8 +62,9 @@ module Mindee
|
|
62
62
|
|
63
63
|
# Call the prediction API.
|
64
64
|
# @param input_source [Mindee::Input::Source::LocalInputSource, Mindee::Input::Source::UrlInputSource]
|
65
|
-
# @param
|
66
|
-
# @param
|
65
|
+
# @param all_words [Boolean] Whether the full word extraction needs to be performed
|
66
|
+
# @param close_file [Boolean] Whether the file will be closed after reading
|
67
|
+
# @param cropper [Boolean] Whether a cropping operation will be applied
|
67
68
|
# @return [Hash]
|
68
69
|
def predict_async(input_source, all_words, close_file, cropper)
|
69
70
|
check_api_key
|
@@ -91,10 +92,10 @@ module Mindee
|
|
91
92
|
private
|
92
93
|
|
93
94
|
# @param input_source [Mindee::Input::Source::LocalInputSource, Mindee::Input::Source::UrlInputSource]
|
94
|
-
# @param all_words [Boolean]
|
95
|
-
# @param close_file [Boolean]
|
96
|
-
# @param cropper [Boolean]
|
97
|
-
# @return [Net::
|
95
|
+
# @param all_words [Boolean] Whether the full word extraction needs to be performed
|
96
|
+
# @param close_file [Boolean] Whether the file will be closed after reading
|
97
|
+
# @param cropper [Boolean] Whether a cropping operation will be applied
|
98
|
+
# @return [Net::HTTP, nil]
|
98
99
|
def predict_req_post(input_source, all_words: false, close_file: true, cropper: false)
|
99
100
|
uri = URI("#{@url_root}/predict")
|
100
101
|
|
@@ -122,9 +123,9 @@ module Mindee
|
|
122
123
|
end
|
123
124
|
|
124
125
|
# @param input_source [Mindee::Input::Source::LocalInputSource, Mindee::Input::Source::UrlInputSource]
|
125
|
-
# @param all_words [Boolean]
|
126
|
-
# @param close_file [Boolean]
|
127
|
-
# @param cropper [Boolean]
|
126
|
+
# @param all_words [Boolean] Whether the full word extraction needs to be performed
|
127
|
+
# @param close_file [Boolean] Whether the file will be closed after reading
|
128
|
+
# @param cropper [Boolean] Whether a cropping operation will be applied
|
128
129
|
# @return [Net::HTTPResponse]
|
129
130
|
def document_queue_req_get(input_source, all_words, close_file, cropper)
|
130
131
|
uri = URI("#{@url_root}/predict_async")
|