mindee 3.4.0 → 3.5.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: fe1aef5bf5c30b3b599d426140de05074840a57f29800129359d647e7ee1bbd5
-  data.tar.gz: 43c93a85a9a6d65fcba85345d1410844b07b5ca7d49a8a8f2487ccd5adcf767f
+  metadata.gz: d3711d1d33d9aeb118b9c891443d0e2ecf4973db242797f15d7628f3a157c0f8
+  data.tar.gz: b63e5dfd3a85fb3b234b0ae6d0afd8b1b2386eba3a2977788298e2cbf7ce79c9
 SHA512:
-  metadata.gz: eff5e3f90cb351664059c4d6dcf78b839dca0e463d0d09b1b4b15a963828355c372845b0806369c21d6b46ed3b2ce45fd199e0bf7aa4c874df3fc06cae569d22
-  data.tar.gz: cb724d0b07bc0a4729d288076b26221fb99fc74d146d181bdae578b95fa9a374ae7deb43e3bb8cadbf7a8d3e5d9e98ea6737c7917565e375668d1fc4e93f95e3
+  metadata.gz: 3ec2c83d25ca5e1cd72cc1045a5a6ed8f299dbdf3de2729344eac833a37351dd16a71d14b73679b441b7263e2992a577c618b3143484c8bfac262fd41697fbe5
+  data.tar.gz: 2de29dd3f708a25ef53e2c61aa86f40684d8ae2aac6cd875e931cd1e0cc0ed8e972439e75c8731e570b7fd7aa1a3884f5c341afe2a29fef40a37bc542ae60c15

data/CHANGELOG.md

@@ -1,5 +1,25 @@
 # Mindee Ruby API Library Changelog
 
+## v3.5.0 - 2024-02-16
+### Changes
+* :sparkles: add support for Generated V1 API
+* :recycle: documents now aren't automatically converted to b64 when enqueued as non-PDF files
+* :recycle: increase max async delay to 60 tries
+* :sparkles: add support for FR bank statements
+* :sparkles: add support for International ID V2
+* :sparkles: add support for EU Driver License V1
+* :recycle: update existing products
+* :arrow_up: upgrade test lib
+
+### Fixes
+* :memo: add missing default async sample code
+* :bug: fix rst display issues
+* :bug: fix display issues for single page models
+* :bug: fix miscellaneous issues related to data display (no changes expected on existing models)
+* :bug: fix CLI breaking for custom products
+* :bug: fix encoding issue that prevented UNICODE file names from being properly sent to the server
+
+
 ## v3.4.0 - 2024-01-30
 ### Changes
 * :arrow_up: update invoices to v4.4

data/README.md

@@ -135,13 +135,17 @@ customize the experience.
 
 * [Ruby Overview](https://developers.mindee.com/docs/getting-started-ocr-ruby)
 * [Custom OCR Ruby](https://developers.mindee.com/docs/api-builder-ocr-ruby)
+* [Generated API Ruby](https://developers.mindee.com/docs/generated-api-ruby)
 * [Invoice OCR Ruby](https://developers.mindee.com/docs/invoice-ocr-ruby)
+* [International Id OCR Ruby](https://developers.mindee.com/docs/international-id-ocr-ruby)
 * [Financial Document OCR Ruby](https://developers.mindee.com/docs/financial-document-ocr-ruby)
 * [Passport OCR Ruby](https://developers.mindee.com/docs/passport-ocr-ruby)
 * [Proof of Address OCR Ruby](https://developers.mindee.com/docs/proof-of-address-ocr-ruby)
 * [Receipt OCR Ruby](https://developers.mindee.com/docs/receipt-ocr-ruby)
 * [EU License Plate OCR Ruby](https://developers.mindee.com/docs/eu-license-plate-ocr-ruby)
+* [EU Driver License OCR Ruby](https://developers.mindee.com/docs/eu-driver-license-ocr-ruby)
 * [FR Bank Account Details OCR Ruby](https://developers.mindee.com/docs/fr-bank-account-details-ocr-ruby)
+* [FR Bank Statement OCR Ruby](https://developers.mindee.com/docs/fr-bank-statement-ocr-ruby)
 * [FR Carte Vitale OCR Ruby](https://developers.mindee.com/docs/fr-carte-vitale-ocr-ruby)
 * [FR ID Card OCR Ruby](https://developers.mindee.com/docs/fr-id-card-ocr-ruby)
 * [US Bank Check OCR Ruby](https://developers.mindee.com/docs/us-bank-check-ocr-ruby)

data/bin/mindee.rb

@@ -5,6 +5,7 @@ require 'bundler/setup'
 require 'optparse'
 require 'mindee'
 
+options = {}
 DOCUMENTS = {
   "custom" => {
     description: "Custom document type from API builder",
@@ -12,6 +13,12 @@ DOCUMENTS = {
     sync: true,
     async: false,
   },
+  "generated" => {
+    description: "Generated document type from API builder",
+    doc_class: Mindee::Product::Generated::GeneratedV1,
+    sync: true,
+    async: true,
+  },
   "proof-of-address" => {
     description: 'Proof of Address',
     doc_class: Mindee::Product::ProofOfAddress::ProofOfAddressV1,
@@ -36,6 +43,12 @@ DOCUMENTS = {
     sync: true,
     async: false,
   },
+  "international-id" => {
+    description: 'International Id',
+    doc_class: Mindee::Product::InternationalId::InternationalIdV2,
+    sync: false,
+    async: true,
+  },
   "receipt" => {
     description: "Expense Receipt",
     doc_class: Mindee::Product::Receipt::ReceiptV5,
@@ -54,12 +67,24 @@ DOCUMENTS = {
     sync: true,
     async: false,
   },
+  "eu-driver-license" => {
+    description: "EU Driver License",
+    doc_class: Mindee::Product::EU::DriverLicense::DriverLicenseV1,
+    sync: true,
+    async: false,
+  },
   "fr-bank-account-details" => {
     description: "FR Bank Account Details",
     doc_class: Mindee::Product::FR::BankAccountDetails::BankAccountDetailsV2,
     sync: true,
     async: false,
   },
+  "fr-bank-statement" => {
+    description: "FR Bank Statement",
+    doc_class: Mindee::Product::FR::BankStatement::BankStatementV1,
+    sync: false,
+    async: true,
+  },
   "fr-carte-vitale" => {
     description: "FR Carte Vitale",
     doc_class: Mindee::Product::FR::CarteVitale::CarteVitaleV1,
@@ -105,11 +130,11 @@ DEFAULT_CUTTING = {
   on_min_pages: 0,
 }
 
-# Initializes custom-specific options
+# Initializes custom & generated-specific options
 # @param cli_parser [OptionParser]
-def custom_subcommand(cli_parser)
+def custom_subcommand(cli_parser, options)
   cli_parser.on('-v [VERSION]', '--version [VERSION]', 'Model version for the API') do |v|
-    options[:version] = v
+    options[:endpoint_version] = v
   end
   cli_parser.on('-a ACCOUNT_NAME', '--account ACCOUNT_NAME', 'API account name for the endpoint') do |v|
     options[:account_name] = v
@@ -118,7 +143,7 @@ end
 
 product_parser = {}
 DOCUMENTS.each do |doc_key, doc_value|
-  product_parser[doc_key] = OptionParser.new do | opts |
+  product_parser[doc_key] = OptionParser.new do |opts|
     opts.on('-w', '--all-words', 'Include words in response') do |v|
       options[:all_words] = v
     end
@@ -134,11 +159,11 @@ DOCUMENTS.each do |doc_key, doc_value|
     opts.on('-F', '--fix-pdf', "Attempts to fix broken PDF files before sending them to the server.") do |v|
       options[:fix_pdf] = true
     end
-    if (doc_key != 'custom')
+    if (doc_key != 'custom' && doc_key != 'generated')
       opts.banner = "Product: #{doc_value[:description]}. \nUsage: mindee.rb #{doc_key} [options] file"
     else
-      opts.banner = "#{doc_value[:description]}. \nUsage: mindee.rb custom [options] endpoint_name file"
-      custom_subcommand(opts)
+      opts.banner = "#{doc_value[:description]}. \nUsage: \nmindee.rb custom [options] endpoint_name file\nor\nmindee.rb generated [options] endpoint_name file"
+      custom_subcommand(opts, options)
     end
     if doc_value[:async]
       if doc_value[:sync]
@@ -150,7 +175,7 @@ DOCUMENTS.each do |doc_key, doc_value|
   end
 end
 
-global_parser = OptionParser.new do | opts |
+global_parser = OptionParser.new do |opts|
   opts.banner = "Usage: mindee.rb product [options] file"
   opts.separator "Available products:"
   opts.separator "  #{DOCUMENTS.keys.join("\n  ")}"
@@ -163,9 +188,9 @@ end
 doc_class = DOCUMENTS[command][:doc_class]
 product_parser[command].parse!
 
-if command == 'custom'
+if command == 'custom' || command == 'generated'
   if ARGV.length < 2
-    $stderr.puts "The 'custom' command requires both ENDPOINT_NAME and file arguments."
+    $stderr.puts "The '#{command}' command requires both ENDPOINT_NAME and file arguments."
     abort(product_parser[command].help)
   end
   endpoint_name = ARGV[0]
@@ -186,12 +211,11 @@ else
   input_source = mindee_client.source_from_path(options[:file_path], fix_pdf: options[:fix_pdf])
 end
 
-if command == 'custom'
-  endpoint_name = 'endpoint_name'
+if command == 'custom' || command == 'generated'
   custom_endpoint = mindee_client.create_endpoint(
-    account_name: endpoint_name,
-    endpoint_name: options[:account_name],
-    endpoint_version: options[:endpoint_version].nil? ? "1" : options[:endpoint_version]
+    endpoint_name: endpoint_name,
+    account_name: options[:account_name],
+    version: options[:endpoint_version].nil? ? "1" : options[:endpoint_version]
   )
 else
   custom_endpoint = nil

data/docs/bank_statement_fr_v1.md

@@ -0,0 +1,175 @@
+---
+title: FR Bank Statement (FR) OCR Ruby
+---
+The Ruby OCR SDK supports the [Bank Statement (FR) API](https://platform.mindee.com/mindee/bank_statement_fr).
+
+Using the [sample below](https://github.com/mindee/client-lib-test-data/blob/main/products/bank_statement_fr/default_sample.jpg), we are going to illustrate how to extract the data that we want using the OCR SDK.
+![Bank Statement (FR) sample](https://github.com/mindee/client-lib-test-data/blob/main/products/bank_statement_fr/default_sample.jpg?raw=true)
+
+# Quick-Start
+```rb
+require 'mindee'
+
+# Init a new client
+mindee_client = Mindee::Client.new(api_key: 'my-api-key')
+
+# Load a file from disk
+input_source = mindee_client.source_from_path('/path/to/the/file.ext')
+
+# Parse the file
+result = mindee_client.enqueue_and_parse(
+  input_source,
+  Mindee::Product::FR::BankStatement::BankStatementV1
+)
+
+# Print a full summary of the parsed data in RST format
+puts result.document
+
+# Print the document-level parsed data
+# puts result.document.inference.prediction
+```
+
+**Output (RST):**
+```rst
+```
+
+# Field Types
+## Standard Fields
+These fields are generic and used in several products.
+
+### Basic Field
+Each prediction object contains a set of fields that inherit from the generic `Field` class.
+A typical `Field` object will have the following attributes:
+
+* **value** (`String`, `Float`, `Integer`, `Boolean`): corresponds to the field value. Can be `nil` if no value was extracted.
+* **confidence** (Float, nil): the confidence score of the field prediction.
+* **bounding_box** (`Mindee::Geometry::Quadrilateral`, `nil`): contains exactly 4 relative vertices (points) coordinates of a right rectangle containing the field in the document.
+* **polygon** (`Mindee::Geometry::Polygon`, `nil`): contains the relative vertices coordinates (`Point`) of a polygon containing the field in the image.
+* **page_id** (`Integer`, `nil`): the ID of the page, is `nil` when at document-level.
+* **reconstructed** (`Boolean`): indicates whether an object was reconstructed (not extracted as the API gave it).
+
+
+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.
+
+
+### Amount Field
+The amount field `AmountField` only has one constraint: its **value** is a `Float` (or `nil`).
+
+### Date Field
+Aside from the basic `Field` attributes, the date field `DateField` also implements the following: 
+
+* **date_object** (`Date`): an accessible representation of the value as a JavaScript object.
+
+### String Field
+The text field `StringField` only has one constraint: it's **value** is a `String` (or `nil`).
+
+## Specific Fields
+Fields which are specific to this product; they are not used in any other product.
+
+### Transactions Field
+The list of values that represent the financial transactions recorded in a bank statement.
+
+A `BankStatementV1Transaction` implements the following attributes:
+
+* `amount` (Float): The monetary amount of the transaction.
+* `date` (String): The date on which the transaction occurred.
+* `description` (String): The additional information about the transaction.
+
+# Attributes
+The following fields are extracted for Bank Statement (FR) V1:
+
+## Account Number
+**account_number** ([StringField](#string-field)): The unique identifier for a customer's account in the bank's system.
+
+```rb
+puts result.document.inference.prediction.account_number.value
+```
+
+## Bank Address
+**bank_address** ([StringField](#string-field)): The physical location of the bank where the statement was issued.
+
+```rb
+puts result.document.inference.prediction.bank_address.value
+```
+
+## Bank Name
+**bank_name** ([StringField](#string-field)): The name of the bank that issued the statement.
+
+```rb
+puts result.document.inference.prediction.bank_name.value
+```
+
+## Client Address
+**client_address** ([StringField](#string-field)): The address of the client associated with the bank statement.
+
+```rb
+puts result.document.inference.prediction.client_address.value
+```
+
+## Client Name
+**client_name** ([StringField](#string-field)): The name of the client who owns the bank statement.
+
+```rb
+puts result.document.inference.prediction.client_name.value
+```
+
+## Closing Balance
+**closing_balance** ([AmountField](#amount-field)): The final amount of money in the account at the end of the statement period.
+
+```rb
+puts result.document.inference.prediction.closing_balance.value
+```
+
+## Opening Balance
+**opening_balance** ([AmountField](#amount-field)): The initial amount of money in an account at the start of the period.
+
+```rb
+puts result.document.inference.prediction.opening_balance.value
+```
+
+## Statement Date
+**statement_date** ([DateField](#date-field)): The date on which the bank statement was generated.
+
+```rb
+puts result.document.inference.prediction.statement_date.value
+```
+
+## Statement End Date
+**statement_end_date** ([DateField](#date-field)): The date when the statement period ends.
+
+```rb
+puts result.document.inference.prediction.statement_end_date.value
+```
+
+## Statement Start Date
+**statement_start_date** ([DateField](#date-field)): The date when the bank statement period begins.
+
+```rb
+puts result.document.inference.prediction.statement_start_date.value
+```
+
+## Total Credits
+**total_credits** ([AmountField](#amount-field)): The total amount of money deposited into the account.
+
+```rb
+puts result.document.inference.prediction.total_credits.value
+```
+
+## Total Debits
+**total_debits** ([AmountField](#amount-field)): The total amount of money debited from the account.
+
+```rb
+puts result.document.inference.prediction.total_debits.value
+```
+
+## Transactions
+**transactions** (Array<[BankStatementV1Transaction](#transactions-field)>): The list of values that represent the financial transactions recorded in a bank statement.
+
+```rb
+for transactions_elem in result.document.inference.prediction.transactions do
+  puts transactions_elem.value
+end
+```
+
+# Questions?
+[Join our Slack](https://join.slack.com/t/mindee-community/shared_invite/zt-1jv6nawjq-FDgFcF2T5CmMmRpl9LLptw)

data/docs/carte_grise_v1.md

@@ -34,12 +34,12 @@ puts result.document
 ########
 Document
 ########
-:Mindee ID: f0e0f7a9-0f44-4a3d-92c7-5be262133d33
+:Mindee ID: 4443182b-57c1-4426-a288-01b94f226e84
 :Filename: default_sample.jpg
 
 Inference
 #########
-:Product: mindee/carte_grise v1.0
+:Product: mindee/carte_grise v1.1
 :Rotation applied: Yes
 
 Prediction
@@ -67,14 +67,14 @@ Prediction
 :p2: 90
 :p3: GO
 :p6: 6
-:q:
+:q: 006
 :s1: 5
 :s2:
 :u1: 77
 :u2: 3000
 :v7: 155
 :x1: 2011-07-06
-:y1:
+:y1: 17835
 :y2:
 :y3: 0
 :y4: 4

data/docs/code_samples/bank_statement_fr_v1_async.txt

@@ -0,0 +1,19 @@
+require 'mindee'
+
+# Init a new client
+mindee_client = Mindee::Client.new(api_key: 'my-api-key')
+
+# Load a file from disk
+input_source = mindee_client.source_from_path('/path/to/the/file.ext')
+
+# Parse the file
+result = mindee_client.enqueue_and_parse(
+  input_source,
+  Mindee::Product::FR::BankStatement::BankStatementV1
+)
+
+# Print a full summary of the parsed data in RST format
+puts result.document
+
+# Print the document-level parsed data
+# puts result.document.inference.prediction

data/docs/code_samples/default.txt

@@ -1,24 +1,24 @@
-require 'uri'
-require 'net/http'
-require 'net/https'
+require 'mindee'
 
-api_key = "my-api-key"
-account = "my-account"
-endpoint = "my-endpoint"
-version = "my-version"
+# Init a new client
+mindee_client = Mindee::Client.new(api_key: 'my-api-key')
 
-url = URI("https://api.mindee.net/v1/products/#{account}/#{endpoint}/v#{version}/predict")
-file = '/path/to/the/file.ext'
+# Load a file from disk
+input_source = mindee_client.source_from_path('/path/to/the/file.ext')
 
-http = Net::HTTP.new(url.host, url.port)
-http.use_ssl = true
+# Initialize a custom endpoint for this product
+custom_endpoint = mindee_client.create_endpoint(
+  account_name: 'my-account',
+  endpoint_name: 'my-endpoint',
+  version: 'my-version'
+)
 
-request = Net::HTTP::Post.new(url)
-request['Authorization'] = "Token #{api_key}"
-request.set_form([['document', File.open(file)]], 'multipart/form-data')
+# Parse the file
+result = mindee_client.parse(
+  input_source,
+  Mindee::Product::Generated::GeneratedV1,
+  endpoint: custom_endpoint
+)
 
-response = http.request(request)
-if !response.kind_of? Net::HTTPSuccess
-  raise response.msg
-end
-puts response.read_body
+# Print a full summary of the parsed data in RST format
+puts result.document

data/docs/code_samples/default_async.txt

@@ -0,0 +1,25 @@
+require 'mindee'
+
+# Init a new client
+mindee_client = Mindee::Client.new(api_key: 'my-api-key')
+
+# Load a file from disk
+input_source = mindee_client.source_from_path('/path/to/the/file.ext')
+
+# Initialize a custom endpoint for this product
+custom_endpoint = mindee_client.create_endpoint(
+  account_name: 'my-account',
+  endpoint_name: 'my-endpoint',
+  version: 'my-version'
+)
+
+# Parse the file
+result = mindee_client.enqueue_and_parse(
+  input_source,
+  Mindee::Product::Generated::GeneratedV1,
+  endpoint: custom_endpoint
+)
+
+# Print a full summary of the parsed data in RST format
+puts result.document
+

data/docs/code_samples/eu_driver_license_v1.txt

@@ -0,0 +1,19 @@
+require 'mindee'
+
+# Init a new client
+mindee_client = Mindee::Client.new(api_key: 'my-api-key')
+
+# Load a file from disk
+input_source = mindee_client.source_from_path('/path/to/the/file.ext')
+
+# Parse the file
+result = mindee_client.parse(
+  input_source,
+  Mindee::Product::EU::DriverLicense::DriverLicenseV1
+)
+
+# Print a full summary of the parsed data in RST format
+puts result.document
+
+# Print the document-level parsed data
+# puts result.document.inference.prediction

data/docs/code_samples/international_id_v1_async.txt

@@ -0,0 +1,19 @@
+require 'mindee'
+
+# Init a new client
+mindee_client = Mindee::Client.new(api_key: 'my-api-key')
+
+# Load a file from disk
+input_source = mindee_client.source_from_path('/path/to/the/file.ext')
+
+# Parse the file
+result = mindee_client.enqueue_and_parse(
+  input_source,
+  Mindee::Product::InternationalId::InternationalIdV1
+)
+
+# Print a full summary of the parsed data in RST format
+puts result.document
+
+# Print the document-level parsed data
+# puts result.document.inference.prediction

data/docs/code_samples/international_id_v2_async.txt

@@ -0,0 +1,19 @@
+require 'mindee'
+
+# Init a new client
+mindee_client = Mindee::Client.new(api_key: 'my-api-key')
+
+# Load a file from disk
+input_source = mindee_client.source_from_path('/path/to/the/file.ext')
+
+# Parse the file
+result = mindee_client.enqueue_and_parse(
+  input_source,
+  Mindee::Product::InternationalId::InternationalIdV2
+)
+
+# Print a full summary of the parsed data in RST format
+puts result.document
+
+# Print the document-level parsed data
+# puts result.document.inference.prediction