⬆️ 💥 drop support for ruby < 3.2 and bump dependency

.github/workflows/_publish-code.yml

@@ -16,7 +16,7 @@ jobs:
     - name: Set up Ruby
       uses: ruby/setup-ruby@v1
       with:
-        ruby-version: "3.0"
+        ruby-version: "3.2"
         bundler-cache: true
 
     - name: Set credentials

.github/workflows/_publish-docs.yml

@@ -17,7 +17,7 @@ jobs:
     - name: set up Ruby
       uses: ruby/setup-ruby@v1
       with:
-        ruby-version: "3.1"
+        ruby-version: "3.2"
         bundler-cache: true
 
     - name: Analyse the code with Rubocop

.github/workflows/_static-analysis.yml

@@ -19,7 +19,7 @@ jobs:
     - name: set up Ruby
       uses: ruby/setup-ruby@v1
       with:
-        ruby-version: "3.0.0"
+        ruby-version: "3.2.0"
         bundler-cache: true
 
     - name: Set up Python

.github/workflows/_test-cli.yml

@@ -24,7 +24,7 @@ jobs:
           - os: "windows-latest"
             rid: "win-x64"
         ruby:
-          - "3.0"
+          - "3.2"
           - "4.0"
     runs-on: ${{ matrix.os_config.os }}
     steps:

.github/workflows/_test-integrations.yml

@@ -32,7 +32,7 @@ jobs:
           - "ubuntu-24.04"
           - "macos-latest"
         ruby:
-          - "3.0"
+          - "3.2"
           - "4.0"
     steps:
       - uses: actions/checkout@v5

.github/workflows/_test-smoke.yml

@@ -24,11 +24,10 @@ jobs:
     strategy:
       matrix:
         ruby:
-          - "3.0"
-          - "3.1"
           - "3.2"
           - "3.3"
           - "3.4"
+          - "4.0"
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v5

.github/workflows/_test-units.yml

@@ -18,8 +18,6 @@ jobs:
           - "ubuntu-22.04"
           - "macos-latest"
         ruby:
-          - "3.0"
-          - "3.1"
           - "3.2"
           - "3.3"
           - "3.4"

.rubocop.yml

@@ -10,7 +10,7 @@ AllCops:
     - local_test/*
     - Steepfile
 
-  TargetRubyVersion: 3.0.0
+  TargetRubyVersion: 3.2
   SuggestExtensions: false
 
 Gemspec/DevelopmentDependencies:

README.md

@@ -15,7 +15,7 @@ https://app.mindee.com
 It uses **API version 2**.
 
 Consult the
-**[V2 Documentation](https://docs.mindee.com/integrations/client-libraries-sdk)**
+**<a href="https://docs.mindee.com/integrations/client-libraries-sdk">V2 Documentation</a>**
 
 
 ### V1
@@ -26,17 +26,17 @@ https://platform.mindee.com/
 It uses **API version 1**.
 
 Consult the
-[V1 Documentation](https://docs.mindee.com/v1/libraries/ruby-sdk)
+<a href="https://docs.mindee.com/v1/libraries/ruby-sdk">V1 Documentation</a>
 
 ## Additional Information
 
-**[Source Code](https://github.com/mindee/mindee-api-ruby)**
+**<a href="https://github.com/mindee/mindee-api-ruby">Source Code</a>**
 
-**[Reference Documentation](https://mindee.github.io/mindee-api-ruby/)**
+**<a href="https://mindee.github.io/mindee-api-ruby/">Reference Documentation</a>**
 
-**[Feedback](https://feedback.mindee.com/)**
+**<a href="https://feedback.mindee.com/">Feedback</a>**
 
 ### License
 Copyright © Mindee
 
-Available as open source under the terms of the [MIT License](https://opensource.org/licenses/MIT).
+Available as open source under the terms of the <a href="https://opensource.org/licenses/MIT">MIT License</a>.

bin/v2/products.rb

@@ -25,7 +25,7 @@
   },
   'ocr' => {
     description: 'OCR Utility',
-    response_class: Mindee::V2::Product::Ocr::Ocr,
+    response_class: Mindee::V2::Product::OCR::OCR,
   },
   'split' => {
     description: 'Split Utility',

docs/code_samples/v2_ocr.txt

@@ -21,7 +21,7 @@ input_source = Mindee::Input::Source::PathInputSource.new(input_path)
 
 # Send for processing
 response = mindee_client.enqueue_and_get_result(
-    Mindee::V2::Product::Ocr::Ocr,
+    Mindee::V2::Product::OCR::OCR,
     input_source,
     ocr_params
 )

lib/mindee.rb

@@ -86,6 +86,13 @@ module Standard
       module Universal
       end
     end
+
+    # V1-specific products.
+    module Product
+      # French products.
+      module FR
+      end
+    end
   end
 
   # V2-specific module.
@@ -94,6 +101,7 @@ module V2
     module HTTP
     end
 
+    # File operations.
     module FileOperation
       # Crop operations.
       module Crop

lib/mindee/geometry/polygon.rb

@@ -7,7 +7,7 @@ module Geometry
     class Polygon < Array
       # @param server_response [Hash] Raw server response hash.
       def initialize(server_response)
-        points = []
+        points = [] # @type var points: Array[Mindee::Geometry::Point]
         server_response.map do |point|
           points << Point.new(point[0], point[1])
         end
@@ -30,7 +30,7 @@ def point_in_y?(point)
 
       # @return [String] Polygon as a string.
       def to_s
-        "(#{map(&:to_s).join(', ')})"
+        "(#{join(', ')})"
       end
     end
   end

lib/mindee/image/image_extractor.rb

@@ -47,7 +47,7 @@ def self.extract_multiple_images_from_source(input_source, page_id, polygons)
       # @param [Array<Geometry::Point, Geometry::Polygon, Geometry::Quadrilateral>] polygons
       # @return [Array<Image::ExtractedImage>] Extracted Images.
       def self.extract_images_from_polygons(input_source, pdf_stream, page_id, polygons)
-        extracted_elements = []
+        extracted_elements = [] # @type var extracted_elements: Array[Image::ExtractedImage]
 
         polygons.each_with_index do |polygon, element_id|
           polygon = ImageUtils.normalize_polygon(polygon)

lib/mindee/input/base_parameters.rb

@@ -54,6 +54,9 @@ def slug
         self.class.slug
       end
 
+      # Load from a hash
+      # @param [Hash] params Parameters to provide as a hash.
+      # @return [BaseParameters]
       def self.from_hash(params: {})
         load_from_hash(params: params)
         new(

lib/mindee/input/sources/path_input_source.rb

@@ -11,7 +11,7 @@ class PathInputSource < LocalInputSource
         # @param filepath [String]
         # @param repair_pdf [bool]
         def initialize(filepath, repair_pdf: false)
-          io_stream = File.open(filepath, 'rb')
+          io_stream = File.new(filepath, 'rb')
           super(io_stream, File.basename(filepath), repair_pdf: repair_pdf)
         end
       end

lib/mindee/page_options.rb

@@ -11,7 +11,7 @@ class PageOptions
     attr_accessor :page_indexes, :operation, :on_min_pages
 
     def initialize(params: {})
-      params ||= {}
+      params ||= {} # : Hash[Symbol, untyped]
       params = params.transform_keys(&:to_sym)
       @page_indexes = params.fetch(
         :page_indexes,

lib/mindee/pdf/extracted_pdf.rb

@@ -13,11 +13,17 @@ class ExtractedPDF
       # @return [String]
       attr_reader :filename
 
-      # @param pdf_bytes [StringIO]
+      # @param pdf_stream [StringIO, File]
       # @param filename [String]
-      def initialize(pdf_bytes, filename)
-        @pdf_bytes = pdf_bytes
+      def initialize(pdf_stream, filename)
         @filename = filename
+
+        if pdf_stream.is_a?(File)
+          pdf_stream.rewind
+          @pdf_bytes = StringIO.new(pdf_stream.read)
+        else
+          @pdf_bytes = pdf_stream
+        end
       end
 
       # Retrieves the page count for a given pdf.

lib/mindee/pdf/pdf_extractor.rb

@@ -40,7 +40,7 @@ def cut_pages(page_indexes)
       # @param page_indexes [Array<Array<Integer>>] List of page number to use for merging in the original Pdf.
       # @return [Array<Mindee::PDF::ExtractedPDF>] The buffer containing the new Pdf.
       def extract_sub_documents(page_indexes)
-        extracted_pdfs = []
+        extracted_pdfs = [] # @type var extracted_pdfs: Array[Mindee::PDF::ExtractedPDF]
         extension = File.extname(@filename)
         basename = File.basename(@filename, extension)
         page_indexes.each do |page_index_list|
@@ -54,7 +54,7 @@ def extract_sub_documents(page_indexes)
                     "Index #{page_index} is out of range."
             end
           end
-          formatted_max_index = format('%03d', page_index_list[page_index_list.length - 1] + 1).to_s
+          formatted_max_index = format('%03d', page_index_list[-1] + 1).to_s
           field_filename = "#{basename}_#{format('%03d',
                                                  page_index_list[0] + 1)}-#{formatted_max_index}#{extension}"
           extracted_pdf = Mindee::PDF::ExtractedPDF.new(cut_pages(page_index_list),
@@ -74,15 +74,15 @@ def extract_sub_documents(page_indexes)
       def extract_invoices(page_indexes, strict: false)
         raise Error::MindeePDFError, 'No indexes provided.' if page_indexes.empty?
 
-        if page_indexes[0].is_a?(Array) && page_indexes[0].all? { |i| i.is_a?(Integer) }
+        if page_indexes[0].is_a?(Array) && page_indexes[0].all?(Integer)
           page_indexes_as_array = page_indexes # @type var page_indexes : Array[Array[Integer]]
           return extract_sub_documents(page_indexes_as_array)
         end
         p_ids = page_indexes # @type var page_indexes: Product::InvoiceSplitter::InvoiceSplitterV1InvoicePageGroups
         return extract_sub_documents(p_ids.map(&:page_indexes)) unless strict
 
-        correct_page_indexes = []
-        current_list = []
+        correct_page_indexes = [] # @type var correct_page_indexes: Array[Array[Integer]]
+        current_list = [] # @type var current_list: Array[Integer]
         previous_confidence = nil
         p_ids.each_with_index do |p_i, i|
           page_index = p_i # @type var page_index: Product::InvoiceSplitter::InvoiceSplitterV1InvoicePageGroup

lib/mindee/pdf/pdf_processor.rb

@@ -1,6 +1,5 @@
 # frozen_string_literal: true
 
-require 'set'
 require 'origami'
 require_relative 'pdf_tools'
 

lib/mindee/v1/extraction/multi_receipts_extractor.rb

@@ -11,7 +11,7 @@ module Extraction
       # @param inference [Inference] Results of the inference.
       # @return [Array<ExtractedImage>] Individual extracted receipts as an array of ExtractedMultiReceiptsImage.
       def self.extract_receipts(input_source, inference)
-        images = []
+        images = [] # @type var images: Array[Image::ExtractedImage]
         unless inference.prediction.receipts
           raise Error::MindeeInputError,
                 'No possible receipts candidates found for Multi-Receipts extraction.'

lib/mindee/v1/parsing/common/extras/cropper_extra.rb

@@ -22,7 +22,7 @@ def initialize(raw_prediction, page_id = nil)
 
             # @return [String]
             def to_s
-              @croppings.map(&:to_s).join("\n           ")
+              @croppings.join("\n           ")
             end
           end
         end

lib/mindee/v1/parsing/common/inference.rb

@@ -57,7 +57,7 @@ def to_s
             out_str << "\n#{"#{@prediction}\n" if @prediction.to_s.size.positive?}"
             if @pages.any? { |page| !page.prediction.nil? }
               out_str << "\nPage Predictions\n================\n\n"
-              out_str << @pages.map(&:to_s).join("\n\n")
+              out_str << @pages.join("\n\n")
             end
             out_str.rstrip!
             out_str

lib/mindee/v1/parsing/common/ocr/ocr.rb

@@ -6,7 +6,7 @@ module Mindee
   module V1
     module Parsing
       module Common
-        # Ocr-specific parsing fields and options
+        # OCR-specific parsing fields and options
         module OCR
           # A single word.
           class OCRWord

lib/mindee/v1/parsing/standard/company_registration_field.rb

@@ -21,21 +21,21 @@ def initialize(prediction, page_id, reconstructed: false)
           # @return [String] The formatted table line, as a string.
           def to_table_line
             printable = printable_values
-            format('| %<type>-15s | %<value>-20s ', type: printable['type'], value: printable['value'])
+            format('| %<type>-15s | %<value>-20s ', type: printable[:type], value: printable[:value])
           end
 
           # @return [String]
           def to_s
             printable = printable_values
-            format('Type: %<type>s, Value: %<value>s', type: printable['type'], value: printable['value'])
+            format('Type: %<type>s, Value: %<value>s', type: printable[:type], value: printable[:value])
           end
 
           # Hashed representation of the values.
           # @return [Hash] Hash of the values.
           def printable_values
-            printable = {}
-            printable['type'] = type
-            printable['value'] = value
+            printable = {} # @type var printable: Hash[Symbol, String]
+            printable[:type] = type
+            printable[:value] = value.to_s
             printable
           end
         end

lib/mindee/v1/parsing/standard/tax_field.rb

@@ -49,7 +49,7 @@ def to_s
 
           # @return [Hash]
           def printable_values
-            out_h = {}
+            out_h = {} # @type var out_h: Hash[Symbol, String]
             out_h[:code] = @code.nil? ? '' : @code
             out_h[:base] = @base.nil? ? '' : print_float(@base)
             out_h[:rate] = @rate.nil? ? '' : print_float(@rate).to_s

lib/mindee/v1/parsing/universal/universal_list_field.rb

@@ -46,7 +46,7 @@ def contents_list
 
           # Return a string representation of all values.
           def contents_string(separator = ' ')
-            @values.map(&:to_s).join(separator)
+            @values.join(separator)
           end
 
           # String representation

lib/mindee/v1/product/barcode_reader/barcode_reader_v1_document.rb

@@ -9,6 +9,7 @@ module BarcodeReader
         # Barcode Reader API version 1.0 document data.
         class BarcodeReaderV1Document < Mindee::V1::Parsing::Common::Prediction
           include Mindee::V1::Parsing::Standard
+
           # List of decoded 1D barcodes.
           # @return [Array<Mindee::V1::Parsing::Standard::StringField>]
           attr_reader :codes_1d

lib/mindee/v1/product/financial_document/financial_document_v1_document.rb

@@ -10,6 +10,7 @@ module FinancialDocument
         # Financial Document API version 1.14 document data.
         class FinancialDocumentV1Document < Mindee::V1::Parsing::Common::Prediction
           include Mindee::V1::Parsing::Standard
+
           # The customer's address used for billing.
           # @return [Mindee::V1::Parsing::Standard::AddressField]
           attr_reader :billing_address

lib/mindee/v1/product/financial_document/financial_document_v1_line_item.rb

@@ -9,6 +9,7 @@ module FinancialDocument
         # List of line item present on the document.
         class FinancialDocumentV1LineItem < Mindee::V1::Parsing::Standard::FeatureField
           include Mindee::V1::Parsing::Standard
+
           # The item description.
           # @return [String]
           attr_reader :description
@@ -51,7 +52,7 @@ def initialize(prediction, page_id)
 
           # @return [Hash]
           def printable_values
-            printable = {}
+            printable = {} # @type var printable: Hash[Symbol, String]
             printable[:description] = format_for_display(@description)
             printable[:product_code] = format_for_display(@product_code)
             printable[:quantity] =
@@ -70,7 +71,7 @@ def printable_values
 
           # @return [Hash]
           def table_printable_values
-            printable = {}
+            printable = {} # @type var printable: Hash[Symbol, String]
             printable[:description] = format_for_display(@description, 36)
             printable[:product_code] = format_for_display(@product_code, nil)
             printable[:quantity] =

lib/mindee/v1/product/fr/bank_account_details/bank_account_details_v1_document.rb

@@ -10,6 +10,7 @@ module BankAccountDetails
           # Bank Account Details API version 1.0 document data.
           class BankAccountDetailsV1Document < Mindee::V1::Parsing::Common::Prediction
             include Mindee::V1::Parsing::Standard
+
             # The name of the account holder as seen on the document.
             # @return [Mindee::V1::Parsing::Standard::StringField]
             attr_reader :account_holder_name