mindee 3.2.0 → 3.3.0

data/docs/invoices_v4.md

@@ -34,123 +34,84 @@ puts result.document
 ########
 Document
 ########
-:Mindee ID: 656c2ec1-0920-4556-9bc2-772162bc698a
-:Filename: invoice.pdf
+:Mindee ID: 16bd8752-8c4d-450f-8213-f33b2097504c
+:Filename: default_sample.jpg
 
 Inference
 #########
-:Product: mindee/invoices v4.1
+:Product: mindee/invoices v4.2
 :Rotation applied: Yes
 
 Prediction
 ==========
-:Locale: fr; fr; EUR;
-:Document type: INVOICE
-:Invoice number: 0042004801351
-:Reference numbers: AD29094
-:Invoice date: 2020-02-17
-:Invoice due date: 2020-02-17
-:Supplier name: TURNPIKE DESIGNS CO.
-:Supplier address: 156 University Ave, Toronto ON, Canada M5H 2H7
-:Supplier company registrations: 501124705; FR33501124705
-:Supplier payment details: FR7640254025476501124705368;
-:Customer name: JIRO DOI
-:Customer address: 1954 Bloon Street West Toronto, ON, M6P 3K9 Canada
-:Customer company registrations: FR00000000000; 111222333
+:Locale: en; en; CAD;
+:Invoice Number: 14
+:Reference Numbers: AD29094
+:Purchase Date: 2018-09-25
+:Due Date: 2018-09-25
+:Total Net:
+:Total Amount: 2608.20
 :Taxes:
   +---------------+--------+----------+---------------+
   | Base          | Code   | Rate (%) | Amount        |
   +===============+========+==========+===============+
-  |               |        | 20.00    | 97.98         |
+  |               |        | 8.00     | 193.20        |
   +---------------+--------+----------+---------------+
-:Total net: 489.97
-:Total tax: 97.98
-:Total amount: 587.95
+:Supplier Payment Details:
+:Supplier Name: TURNPIKE DESIGNS CO.
+:Supplier Company Registrations:
+:Supplier Address: 156 University Ave, Toronto ON, Canada M5H 2H7
+:Customer Name: JIRO DOI
+:Customer Company Registrations:
+:Customer Address: 1954 Bloor Street West Toronto, ON, M6P 3K9 Canada
+:Document Type: INVOICE
 :Line Items:
-  +----------------------+---------+---------+----------+------------------+--------------------------------------+
-  | Code                 | QTY     | Price   | Amount   | Tax (Rate)       | Description                          |
-  +======================+=========+=========+==========+==================+======================================+
-  |                      |         |         | 4.31     |  (2.10%)         | PQ20 ETIQ ULTRA RESIS METAXXDC       |
-  +----------------------+---------+---------+----------+------------------+--------------------------------------+
-  |                      | 1.00    | 65.00   | 75.00    | 10.00            | Platinum web hosting package Down... |
-  +----------------------+---------+---------+----------+------------------+--------------------------------------+
-  | XXX81125600010       | 1.00    | 250.01  | 275.51   | 25.50 (10.20%)   | a long string describing the item    |
-  +----------------------+---------+---------+----------+------------------+--------------------------------------+
-  | ABC456               | 200.30  | 8.101   | 1622.63  | 121.70 (7.50%)   | Liquid perfection                    |
-  +----------------------+---------+---------+----------+------------------+--------------------------------------+
-  |                      |         |         |          |                  | CARTOUCHE L NR BROTHER TN247BK       |
-  +----------------------+---------+---------+----------+------------------+--------------------------------------+
+  +--------------------------------------+--------------+----------+------------+--------------+--------------+------------+
+  | Description                          | Product code | Quantity | Tax Amount | Tax Rate (%) | Total Amount | Unit Price |
+  +======================================+==============+==========+============+==============+==============+============+
+  | Platinum web hosting package Down... |              | 1.00     |            |              | 65.00        | 65.00      |
+  +--------------------------------------+--------------+----------+------------+--------------+--------------+------------+
+  | 2 page website design Includes ba... |              | 3.00     |            |              | 2100.00      | 2100.00    |
+  +--------------------------------------+--------------+----------+------------+--------------+--------------+------------+
+  | Mobile designs Includes responsiv... |              | 1.00     |            |              | 250.00       | 250.00     |
+  +--------------------------------------+--------------+----------+------------+--------------+--------------+------------+
 
 Page Predictions
 ================
 
 Page 0
 ------
-:Locale: fr; fr; EUR;
-:Document type: INVOICE
-:Invoice number: 0042004801351
-:Reference numbers:
-:Invoice date: 2020-02-17
-:Invoice due date: 2020-02-17
-:Supplier name:
-:Supplier address:
-:Supplier company registrations: 501124705; FR33501124705
-:Supplier payment details: FR7640254025476501124705368;
-:Customer name:
-:Customer address:
-:Customer company registrations:
-:Taxes:
-  +---------------+--------+----------+---------------+
-  | Base          | Code   | Rate (%) | Amount        |
-  +===============+========+==========+===============+
-  |               |        | 20.00    | 97.98         |
-  +---------------+--------+----------+---------------+
-:Total net: 489.97
-:Total tax: 97.98
-:Total amount: 587.95
-:Line Items:
-  +----------------------+---------+---------+----------+------------------+--------------------------------------+
-  | Code                 | QTY     | Price   | Amount   | Tax (Rate)       | Description                          |
-  +======================+=========+=========+==========+==================+======================================+
-  |                      |         |         | 4.31     |  (2.10%)         | PQ20 ETIQ ULTRA RESIS METAXXDC       |
-  +----------------------+---------+---------+----------+------------------+--------------------------------------+
-  |                      | 1.00    | 65.00   | 75.00    | 10.00            | Platinum web hosting package Down... |
-  +----------------------+---------+---------+----------+------------------+--------------------------------------+
-
-Page 1
-------
-:Locale: fr; fr; EUR;
-:Document type: INVOICE
-:Invoice number:
-:Reference numbers: AD29094
-:Invoice date:
-:Invoice due date: 2020-02-17
-:Supplier name: TURNPIKE DESIGNS CO.
-:Supplier address: 156 University Ave, Toronto ON, Canada M5H 2H7
-:Supplier company registrations:
-:Supplier payment details:
-:Customer name: JIRO DOI
-:Customer address: 1954 Bloon Street West Toronto, ON, M6P 3K9 Canada
-:Customer company registrations:
+:Locale: en; en; CAD;
+:Invoice Number: 14
+:Reference Numbers: AD29094
+:Purchase Date: 2018-09-25
+:Due Date: 2018-09-25
+:Total Net:
+:Total Amount: 2608.20
 :Taxes:
   +---------------+--------+----------+---------------+
   | Base          | Code   | Rate (%) | Amount        |
   +===============+========+==========+===============+
   |               |        | 8.00     | 193.20        |
   +---------------+--------+----------+---------------+
-:Total net:
-:Total tax: 193.20
-:Total amount: 2608.20
+:Supplier Payment Details:
+:Supplier Name: TURNPIKE DESIGNS CO.
+:Supplier Company Registrations:
+:Supplier Address: 156 University Ave, Toronto ON, Canada M5H 2H7
+:Customer Name: JIRO DOI
+:Customer Company Registrations:
+:Customer Address: 1954 Bloor Street West Toronto, ON, M6P 3K9 Canada
+:Document Type: INVOICE
 :Line Items:
-  +----------------------+---------+---------+----------+------------------+--------------------------------------+
-  | Code                 | QTY     | Price   | Amount   | Tax (Rate)       | Description                          |
-  +======================+=========+=========+==========+==================+======================================+
-  | XXX81125600010       | 1.00    | 250.00  | 250.00   |  (10.00%)        | a long string describing the item    |
-  +----------------------+---------+---------+----------+------------------+--------------------------------------+
-  | ABC456               | 200.30  | 8.101   | 1622.63  | 121.70 (7.50%)   | Liquid perfection                    |
-  +----------------------+---------+---------+----------+------------------+--------------------------------------+
-  |                      |         |         |          |                  | CARTOUCHE L NR BROTHER TN247BK       |
-  +----------------------+---------+---------+----------+------------------+--------------------------------------+
+  +--------------------------------------+--------------+----------+------------+--------------+--------------+------------+
+  | Description                          | Product code | Quantity | Tax Amount | Tax Rate (%) | Total Amount | Unit Price |
+  +======================================+==============+==========+============+==============+==============+============+
+  | Platinum web hosting package Down... |              | 1.00     |            |              | 65.00        | 65.00      |
+  +--------------------------------------+--------------+----------+------------+--------------+--------------+------------+
+  | 2 page website design Includes ba... |              | 3.00     |            |              | 2100.00      | 2100.00    |
+  +--------------------------------------+--------------+----------+------------+--------------+--------------+------------+
+  | Mobile designs Includes responsiv... |              | 1.00     |            |              | 250.00       | 250.00     |
+  +--------------------------------------+--------------+----------+------------+--------------+--------------+------------+
 ```
 
 # Field Types
@@ -199,6 +160,14 @@ The locale field `LocaleField` only implements the **value**, **confidence** and
 * **country** (`String`): ISO 3166-1 alpha-2 or ISO 3166-1 alpha-3 code for countries (e.g.: `GRB` or `GB` for "Great Britain"). Can be `nil`.
 * **currency** (`String`): ISO 4217 code for currencies (e.g.: `USD` for "US Dollars"). Can be `nil`.
 
+### Payment Details Field
+Aside from the basic `Field` attributes, the payment details field `PaymentDetailsField` also implements the following:
+
+* **account_number** (`String`): number of an account, expressed as a string. Can be `nil`.
+* **iban** (`String`): International Bank Account Number. Can be `nil`.
+* **routing_number** (`String`): routing number of an account. Can be `nil`.
+* **swift** (`String`): the account holder's bank's SWIFT Business Identifier Code (BIC). Can be `nil`.
+
 ### String Field
 The text field `StringField` only has one constraint: it's **value** is a `String` (or `nil`).
 
@@ -206,7 +175,7 @@ The text field `StringField` only has one constraint: it's **value** is a `Strin
 #### Tax
 Aside from the basic `Field` attributes, the tax field `TaxField` also implements the following:
 
-* **rate** (`Float`): the tax rate applied to an item can be undefined. Expressed as a percentage. Can be `nil`.
+* **rate** (`Float`): the tax rate applied to an item can be expressed as a percentage. Can be `nil`.
 * **code** (`String`): tax code (or equivalent, depending on the origin of the document). Can be `nil`.
 * **base** (`Float`): base amount used for the tax. Can be `nil`.
 
@@ -225,7 +194,7 @@ A `InvoiceV4LineItem` implements the following attributes:
 
 * `description` (String): The item description.
 * `product_code` (String): The product code referring to the item.
-* `quantity` (Integer): The item quantity
+* `quantity` (Float): The item quantity
 * `tax_amount` (Float): The item tax amount.
 * `tax_rate` (Float): The item tax rate in percentage.
 * `total_amount` (Float): The item total amount.
@@ -235,7 +204,7 @@ A `InvoiceV4LineItem` implements the following attributes:
 The following fields are extracted for Invoice V4:
 
 ## Customer Address
-**customerAddress** ([StringField](#string-field)): The address of the customer.
+**customer_address** ([StringField](#string-field)): The address of the customer.
 
 ```rb
 puts result.document.inference.prediction.customer_address.value
@@ -245,13 +214,13 @@ puts result.document.inference.prediction.customer_address.value
 **customer_company_registrations** (Array<[CompanyRegistrationField](#company-registration-field)>): List of company registrations associated to the customer.
 
 ```rb
-for customer_company_registration_elem in result.document.inference.prediction.customer_company_registration do
-  puts customer_company_registration_elem.value
+for customer_company_registrations_elem in result.document.inference.prediction.customer_company_registrations do
+  puts customer_company_registrations_elem.value
 end
 ```
 
 ## Customer Name
-**customer_name** ([StringField](#string-field)): The name of the customer.
+**customer_name** ([StringField](#string-field)): The name of the customer or client.
 
 ```rb
 puts result.document.inference.prediction.customer_name.value
@@ -314,7 +283,7 @@ end
 **supplier_address** ([StringField](#string-field)): The address of the supplier or merchant.
 
 ```rb
-result.document.inference.prediction.supplier_address.value
+puts result.document.inference.prediction.supplier_address.value
 ```
 
 ## Supplier Company Registrations
@@ -343,7 +312,7 @@ end
 ```
 
 ## Taxes
-**taxes** (Array<[TaxField](#taxes-field)>): List of tax lines information.
+**taxes** (Array<[TaxField](#taxes-field)>): List of tax line details.
 
 ```rb
 for taxes_elem in result.document.inference.prediction.taxes do

data/docs/multi_receipts_detector_v1.md

@@ -1,5 +1,5 @@
 ---
-title: Multi Receipts Detector API Ruby
+title: Multi Receipts Detector OCR Ruby
 ---
 The Ruby OCR SDK supports the [Multi Receipts Detector API](https://platform.mindee.com/mindee/multi_receipts_detector).
 

data/docs/us_w9_v1.md

@@ -1,10 +1,10 @@
 ---
 title: US W9 OCR Ruby
 ---
-The Ruby OCR SDK supports the [US W9 API](https://platform.mindee.com/mindee/us_w9).
+The Ruby OCR SDK supports the [W9 API](https://platform.mindee.com/mindee/us_w9).
 
 Using the [sample below](https://github.com/mindee/client-lib-test-data/blob/main/products/us_w9/default_sample.jpg), we are going to illustrate how to extract the data that we want using the OCR SDK.
-![US W9 sample](https://github.com/mindee/client-lib-test-data/blob/main/products/us_w9/default_sample.jpg?raw=true)
+![W9 sample](https://github.com/mindee/client-lib-test-data/blob/main/products/us_w9/default_sample.jpg?raw=true)
 
 # Quick-Start
 ```rb
@@ -93,7 +93,7 @@ The text field `StringField` only has one constraint: it's **value** is a `Strin
 Some fields are constrained to the page level, and so will not be retrievable to through the document.
 
 # Attributes
-The following fields are extracted for US W9 V1:
+The following fields are extracted for W9 V1:
 
 ## Address
 [📄](#page-level-fields "This field is only present on individual pages.")**address** ([StringField](#string-field)): The street address (number, street, and apt. or suite no.) of the applicant.

data/lib/mindee/http/endpoint.rb

@@ -31,6 +31,8 @@ module Mindee
       attr_reader :api_key
       # @return [Integer]
       attr_reader :request_timeout
+      # @return [String]
+      attr_reader :url_root
 
       def initialize(owner, url_name, version, api_key: '')
         @owner = owner
@@ -38,7 +40,8 @@ module Mindee
         @version = version
         @request_timeout = ENV.fetch(REQUEST_TIMEOUT_ENV_NAME, TIMEOUT_DEFAULT).to_i
         @api_key = api_key.nil? || api_key.empty? ? ENV.fetch(API_KEY_ENV_NAME, API_KEY_DEFAULT) : api_key
-        @url_root = "#{BASE_URL_DEFAULT}/products/#{@owner}/#{@url_name}/v#{@version}"
+        base_url = ENV.fetch(BASE_URL_ENV_NAME, BASE_URL_DEFAULT)
+        @url_root = "#{base_url.chomp('/')}/products/#{@owner}/#{@url_name}/v#{@version}"
       end
 
       # Call the prediction API.
@@ -174,6 +177,7 @@ module Mindee
         response
       end
 
+      # Checks API key
       def check_api_key
         return unless @api_key.nil? || @api_key.empty?
 

data/lib/mindee/http/error.rb

@@ -73,7 +73,7 @@ module Mindee
       class MindeeHttpError < StandardError
         # @return [String]
         attr_reader :status_code
-        # @return [String]
+        # @return [Integer]
         attr_reader :api_code
         # @return [String]
         attr_reader :api_details

data/lib/mindee/parsing/common/api_response.rb

@@ -95,13 +95,14 @@ module Mindee
         attr_reader :job
         # @return [Mindee::Parsing::Common::ApiRequest]
         attr_reader :api_request
-        # @return [String]
+        # @return [Hash]
         attr_reader :raw_http
 
         # @param product_class [Class<Mindee::Product>]
         # @param http_response [Hash]
+        # @param raw_http [String]
         def initialize(product_class, http_response, raw_http)
-          @raw_http = raw_http
+          @raw_http = raw_http.to_s
           if http_response.key?('api_request')
             @api_request = Mindee::Parsing::Common::ApiRequest.new(http_response['api_request'])
           end

data/lib/mindee/parsing/common/document.rb

@@ -13,8 +13,10 @@ module Mindee
         attr_reader :name
         # @return [String] Mindee ID of the document
         attr_reader :id
-        # @return [Mindee::Parsing::Common::Ocr::Ocr, nil]
+        # @return [Mindee::Parsing::Common::Ocr::Ocr, nil] OCR text results (limited availability)
         attr_reader :ocr
+        # @return [Integer] Amount of pages of the document
+        attr_reader :n_pages
 
         # @param http_response [Hash]
         # @return [Mindee::Parsing::Common::Ocr::Ocr]
@@ -32,6 +34,7 @@ module Mindee
           @name = http_response['name']
           @inference = product_class.new(http_response['inference'])
           @ocr = self.class.load_ocr(http_response)
+          @n_pages = http_response['n_pages']
         end
 
         # @return [String]

data/lib/mindee/parsing/custom/list_field.rb

@@ -14,13 +14,16 @@ module Mindee
         attr_reader :polygon
         # @return [Array, Hash, String, nil]
         attr_reader :content
+        # @return [Integer, nil]
+        attr_reader :page_id
 
         # @param prediction [Hash]
-        def initialize(prediction)
+        def initialize(prediction, page_id: nil)
           @content = prediction['content']
           @confidence = prediction['confidence']
           @polygon = Geometry.polygon_from_prediction(prediction['polygon'])
           @bounding_box = Geometry.get_bounding_box(@polygon) unless @polygon.nil? || @polygon.empty?
+          @page_id = page_id
         end
 
         # @return [String]
@@ -33,8 +36,6 @@ module Mindee
       class ListField
         # @return [Array<Mindee::Parsing::Custom::ListFieldItem>]
         attr_reader :values
-        # @return [Integer, nil]
-        attr_reader :page_id
         # true if the field was reconstructed or computed using other fields.
         # @return [Boolean]
         attr_reader :reconstructed
@@ -48,11 +49,12 @@ module Mindee
         def initialize(prediction, page_id, reconstructed: false)
           @values = []
           @confidence = prediction['confidence']
-          @page_id = page_id || prediction['page_id']
+          page_id = prediction['page_id'] if page_id.nil? && prediction.include?('page_id')
           @reconstructed = reconstructed
 
           prediction['values'].each do |field|
-            @values.push(ListFieldItem.new(field))
+            page_id = field['page_id'] if field.include?('page_id')
+            @values.push(ListFieldItem.new(field, page_id: page_id))
           end
         end
 

data/lib/mindee/parsing/standard/base_field.rb

@@ -96,7 +96,7 @@ module Mindee
           return '' if in_str.nil?
           return in_str if max_col_size.nil?
 
-          in_str.length < max_col_size ? in_str : "#{in_str[0..max_col_size - 3]}..."
+          in_str.length < max_col_size ? in_str : "#{in_str[0..max_col_size - 4]}..."
         end
       end
     end

data/lib/mindee/product/financial_document/financial_document_v1_document.rb

@@ -140,11 +140,11 @@ module Mindee
           out_str << "\n:Total Amount: #{@total_amount}".rstrip
           out_str << "\n:Taxes:#{@taxes}".rstrip
           out_str << "\n:Supplier Payment Details: #{supplier_payment_details}".rstrip
-          out_str << "\n:Supplier name: #{@supplier_name}".rstrip
+          out_str << "\n:Supplier Name: #{@supplier_name}".rstrip
           out_str << "\n:Supplier Company Registrations: #{supplier_company_registrations}".rstrip
           out_str << "\n:Supplier Address: #{@supplier_address}".rstrip
           out_str << "\n:Supplier Phone Number: #{@supplier_phone_number}".rstrip
-          out_str << "\n:Customer name: #{@customer_name}".rstrip
+          out_str << "\n:Customer Name: #{@customer_name}".rstrip
           out_str << "\n:Customer Company Registrations: #{customer_company_registrations}".rstrip
           out_str << "\n:Customer Address: #{@customer_address}".rstrip
           out_str << "\n:Document Type: #{@document_type}".rstrip

data/lib/mindee/product/fr/carte_grise/carte_grise_v1.rb

@@ -0,0 +1,39 @@
+# frozen_string_literal: true
+
+require_relative '../../../parsing'
+require_relative 'carte_grise_v1_document'
+require_relative 'carte_grise_v1_page'
+
+module Mindee
+  module Product
+    module FR
+      # Carte Grise module.
+      module CarteGrise
+        # Carte Grise V1 prediction inference.
+        class CarteGriseV1 < Mindee::Parsing::Common::Inference
+          @endpoint_name = 'carte_grise'
+          @endpoint_version = '1'
+
+          # @param prediction [Hash]
+          def initialize(prediction)
+            super
+            @prediction = CarteGriseV1Document.new(prediction['prediction'], nil)
+            @pages = []
+            prediction['pages'].each do |page|
+              @pages.push(CarteGriseV1Page.new(page))
+            end
+          end
+
+          class << self
+            # Name of the endpoint for this product.
+            # @return [String]
+            attr_reader :endpoint_name
+            # Version for this product.
+            # @return [String]
+            attr_reader :endpoint_version
+          end
+        end
+      end
+    end
+  end
+end