mindee 5.0.0.beta1 → 5.0.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: a0f0f74c2ffa0b955e76431c51bff64e2683439045ee6059d1a582885c5dcd2f
-  data.tar.gz: 3663bcce828f5851c59a83bc71776e3c9d77ddc92aa657c8dc2573277a89186b
+  metadata.gz: c130d39c720927dbf32f427f50e3b6e64f43573a419adcae4b2c24b88825ceda
+  data.tar.gz: 11bea996953560479ccfec44fac65ed77ac83b45be0ceb64458d1e019fc3604d
 SHA512:
-  metadata.gz: f2741d09c26053c130af682a29e28ae54854ba6d9ad652559d8b6706ff6d8fd2ea7afcc90ed2ed2cecc27a3926bc3fc61a2e7a671a3f0eaea63886ab9db929e0
-  data.tar.gz: c3c72bbadb037a126c594c51610a43cb874a1d8cc15d43d3b5241bfaa69f3f1b647751faebf215f8642634ef77c72ea6cbd47af1e450a82c53075d7323cbf513
+  metadata.gz: cc9f76a7449ce3a9f9d99ff2cc03c545d5aadff3a088e817b34e2fb280ba1807b9bb8d1edfba3612e5929a7f51e9e4e007fe4f20bce4d4ba69c246aca3137ef3
+  data.tar.gz: 134e8286afd4e28a54a3523a9e691bb2ede3a631684d1640023badcdf758801b1b1a6eac4af6eddefe64d28f8659163feb05806024a5c6d33575c5bd002b8f2e

data/CHANGELOG.md

@@ -1,5 +1,55 @@
 # Mindee Ruby API Library Changelog
 
+## v5.0.0 - 2026-04-20
+### ¡Breaking Changes!
+* :boom: :recycle: update V1 & V2 syntaxes to match other SDKs
+    * :recycle: move V1 client to V1 module
+    * :recycle: move V2 client to V2 module
+    * :recycle: move legacy products to 'V1' module
+    * :recycle: add parsing and extraction to v1 module
+    * :recycle: move V1 HTTP to V1 module
+    * :recycle: move V2 HTTP module to V2 namespace
+    * :recycle: move data schema to extraction parameters namespace
+* :arrow_up: :boom: drop support for ruby < 3.2
+* :recycle: :boom: change raw_http attribute in responses to be actual json strings
+* :recycle: :boom: make logging configurable and default output to stderr
+* :recycle: :boom: remove useless `PDFExtractor` module
+* :recycle: :boom: change `Errors` module to `Error`
+* :recycle: :boom: change Ocr modules and classes to OCR to keep consistency
+* :recycle: :boom: change `FileOperation` module name to `FileOperations`
+* :recycle: :boom: change `Dependency` module name to `Dependencies`
+* :boom: remove support for the following V1 products:
+    * :coffin: US Bank Check V1
+    * :coffin: Bill of Lading V1
+    * :coffin: Business Card V1
+    * :coffin: FR Carte Grise V1
+    * :coffin: Delivery Notes V1
+    * :coffin: Driver License V1
+    * :coffin: FR Energy Bill V1
+    * :coffin: Nutrition Facts V1
+### Changes
+* :sparkles: :arrow_up: add support for mindee-lite gem
+* :sparkles: add support for crop operation
+* :sparkles: add support for split operation
+* :sparkles: add support for model search
+* :sparkles: add support for V2 CLI
+* :wrench: :arrow_up: add better tooling and pre-commit hook
+* :arrow_up: and bump all dependencies
+### Fixes
+* :wrench: fix many typing issues
+* :bug: fix webhook IDs not sending properly
+* :bug: fix miscellaneous issues leading to saved `ExtractedPDF` instances having invalid names
+* :recycle: fix miscellaneous typing issues relating to `ExtractedPDF` and `ExtractedImage` classes
+
+
+## v5.0.0.rc1 - 2026-04-15
+### ¡Breaking Changes!
+* :recycle: :boom: change `FileOperation` module name to `FileOperations`
+* :recycle: :boom: change `Dependency` module name to `Dependencies`
+### Fixes
+* :wrench: fix many typing issues
+
+
 ## v5.0.0.beta1 - 2026-04-07
 ### ¡Breaking Changes!
 * :boom: :recycle: update V1 & V2 syntaxes to match other SDKs
@@ -25,7 +75,6 @@
     * :coffin: Driver License V1
     * :coffin: FR Energy Bill V1
     * :coffin: Nutrition Facts V1
-
 ### Changes
 * :sparkles: :arrow_up: add support for mindee-lite gem
 * :sparkles: add support for crop operation
@@ -34,7 +83,6 @@
 * :sparkles: add support for V2 CLI
 * :wrench: :arrow_up: add better tooling and pre-commit hook
 * :arrow_up: and bump all dependencies
-
 ### Fixes
 * :bug: fix webhook IDs not sending properly
 * :bug: fix miscellaneous issues leading to saved `ExtractedPDF` instances having invalid names

data/lib/mindee/{dependency.rb → dependencies.rb}

@@ -2,7 +2,7 @@
 
 module Mindee
   # Centralized check for optional heavy dependencies
-  module Dependency
+  module Dependencies
     def self.check_all_dependencies
       require 'origami'
       require 'mini_magick'

data/lib/mindee/image/image_extractor.rb

@@ -1,6 +1,6 @@
 # frozen_string_literal: true
 
-Mindee::Dependency.require_all_deps!
+Mindee::Dependencies.require_all_deps!
 require 'mini_magick'
 require 'origami'
 require 'stringio'
@@ -37,35 +37,33 @@ module Mindee
         new_stream = load_input_source_pdf_page_as_stringio(input_source, page_id)
         new_stream.seek(0)
 
-        extract_images_from_polygons(input_source, new_stream, page_id, polygons)
+        extract_images_from_polygons(input_source, page_id, polygons)
       end
 
       # Extracts images from their positions on a file (as polygons).
       #
       # @param [Input::Source::LocalInputSource] input_source Local input source.
-      # @param [StringIO] pdf_stream Buffer of the PDF.
       # @param [Integer] page_id Page ID.
       # @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)
+      def self.extract_images_from_polygons(input_source, page_id, polygons)
         extracted_elements = [] # @type var extracted_elements: Array[Image::ExtractedImage]
 
+        input_source.io_stream.rewind
+        pdf_stream = StringIO.new(input_source.io_stream.read.to_s)
+        input_source.io_stream.rewind
         polygons.each_with_index do |polygon, element_id|
           polygon = ImageUtils.normalize_polygon(polygon)
           page_content = ImageUtils.read_page_content(pdf_stream)
+          points = [
+            polygon.top_left,
+            polygon.bottom_right,
+            polygon.top_right,
+            polygon.bottom_left,
+          ]
 
-          min_max_x = Geometry.get_min_max_x([
-                                               polygon.top_left,
-                                               polygon.bottom_right,
-                                               polygon.top_right,
-                                               polygon.bottom_left,
-                                             ])
-          min_max_y = Geometry.get_min_max_y([
-                                               polygon.top_left,
-                                               polygon.bottom_right,
-                                               polygon.top_right,
-                                               polygon.bottom_left,
-                                             ])
+          min_max_x = Geometry.get_min_max_x(points)
+          min_max_y = Geometry.get_min_max_y(points)
           file_extension = ImageUtils.determine_file_extension(input_source)
           cropped_image = ImageUtils.crop_image(page_content, min_max_x, min_max_y)
           if file_extension == 'pdf'

data/lib/mindee/input/sources/local_input_source.rb

@@ -4,9 +4,9 @@ require 'stringio'
 require 'marcel'
 require 'fileutils'
 
-require_relative '../../dependency'
-require_relative '../../pdf' if Mindee::Dependency.all_deps_available?
-require_relative '../../image' if Mindee::Dependency.all_deps_available?
+require_relative '../../dependencies'
+require_relative '../../pdf' if Mindee::Dependencies.all_deps_available?
+require_relative '../../image' if Mindee::Dependencies.all_deps_available?
 
 module Mindee
   module Input
@@ -143,8 +143,8 @@ module Mindee
         # Defaults to one for images.
         # @return [Integer]
         def page_count
-          unless Mindee::Dependency.all_deps_available?
-            raise NotImplementedError, Mindee::Dependency::MINDEE_DEPENDENCIES_LOAD_ERROR
+          unless Mindee::Dependencies.all_deps_available?
+            raise NotImplementedError, Mindee::Dependencies::MINDEE_DEPENDENCIES_LOAD_ERROR
           end
           return 1 unless pdf?
 
@@ -163,8 +163,8 @@ module Mindee
         # @param [bool] disable_source_text If the PDF has source text, whether to re-apply it to the original or
         #   not. Needs force_source_text to work.
         def compress!(quality: 85, max_width: nil, max_height: nil, force_source_text: false, disable_source_text: true)
-          unless Mindee::Dependency.all_deps_available?
-            raise NotImplementedError, Mindee::Dependency::MINDEE_DEPENDENCIES_LOAD_ERROR
+          unless Mindee::Dependencies.all_deps_available?
+            raise NotImplementedError, Mindee::Dependencies::MINDEE_DEPENDENCIES_LOAD_ERROR
           end
 
           buffer = if pdf?
@@ -189,8 +189,8 @@ module Mindee
         # Checks whether the file has source text if it is a pdf. `false` otherwise
         # @return [bool] `true` if the file is a PDF and has source text.
         def source_text?
-          unless Mindee::Dependency.all_deps_available?
-            raise NotImplementedError, Mindee::Dependency::MINDEE_DEPENDENCIES_LOAD_ERROR
+          unless Mindee::Dependencies.all_deps_available?
+            raise NotImplementedError, Mindee::Dependencies::MINDEE_DEPENDENCIES_LOAD_ERROR
           end
 
           Mindee::PDF::PDFTools.source_text?(@io_stream)

data/lib/mindee/pdf/pdf_compressor.rb

@@ -1,6 +1,6 @@
 # frozen_string_literal: true
 
-Mindee::Dependency.require_all_deps!
+Mindee::Dependencies.require_all_deps!
 require 'pdf-reader'
 
 # Shorthand for pdf-reader's PDF namespace, to avoid mixups with the local Origami fork.

data/lib/mindee/pdf/pdf_extractor.rb

@@ -7,8 +7,8 @@ module Mindee
     class PDFExtractor
       # @param local_input [Mindee::Input::Source::LocalInputSource]
       def initialize(local_input)
-        unless Mindee::Dependency.all_deps_available?
-          raise NotImplementedError, Mindee::Dependency::MINDEE_DEPENDENCIES_LOAD_ERROR
+        unless Mindee::Dependencies.all_deps_available?
+          raise NotImplementedError, Mindee::Dependencies::MINDEE_DEPENDENCIES_LOAD_ERROR
         end
 
         @filename = local_input.filename
@@ -82,14 +82,14 @@ module Mindee
           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
+        p_ids = page_indexes # @type var page_indexes: Mindee::V1::Product::InvoiceSplitter::InvoiceSplitterV1InvoicePageGroups
         return extract_sub_documents(p_ids.map(&:page_indexes)) unless strict
 
         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
+          page_index = p_i # @type var page_index: Mindee::V1::Product::InvoiceSplitter::InvoiceSplitterV1InvoicePageGroup
           confidence = page_index.confidence.to_f
           page_list = page_index.page_indexes
 

data/lib/mindee/pdf/pdf_processor.rb

@@ -1,6 +1,6 @@
 # frozen_string_literal: true
 
-Mindee::Dependency.require_all_deps!
+Mindee::Dependencies.require_all_deps!
 require 'origami'
 require_relative 'pdf_tools'
 

data/lib/mindee/pdf/pdf_tools.rb

@@ -1,6 +1,6 @@
 # frozen_string_literal: true
 
-Mindee::Dependency.require_all_deps!
+Mindee::Dependencies.require_all_deps!
 require 'origami'
 
 module Mindee

data/lib/mindee/v1/product/invoice_splitter/invoice_splitter_v1_document.rb

@@ -19,7 +19,7 @@ module Mindee
           # @param page_id [Integer, nil]
           def initialize(prediction, page_id)
             super
-            @invoice_page_groups = Product::InvoiceSplitter::InvoiceSplitterV1InvoicePageGroups.new(
+            @invoice_page_groups = InvoiceSplitterV1InvoicePageGroups.new(
               prediction['invoice_page_groups'], page_id
             )
           end

data/lib/mindee/v1.rb

@@ -1,7 +1,7 @@
 # frozen_string_literal: true
 
 require_relative 'v1/client'
-require_relative 'v1/extraction' if Mindee::Dependency.all_deps_available?
+require_relative 'v1/extraction' if Mindee::Dependencies.all_deps_available?
 require_relative 'v1/http'
 require_relative 'v1/parsing'
 require_relative 'v1/product'

data/lib/mindee/v2/{file_operation → file_operations}/crop.rb

@@ -17,11 +17,11 @@ module Mindee
           ).first
         end
 
-        # Extracts individual receipts from multi-receipts documents.
+        # Extracts multiple crop zones from an image.
         #
         # @param input_source [LocalInputSource] Local Input Source to extract sub-receipts from.
         # @param crops [Array<CropItem>] List of crops.
-        # @return [CropFiles] Individual extracted receipts as an array of ExtractedImage.
+        # @return [CropFiles] Individual extracted zones as an array of ExtractedImage.
         # @raise [MindeeError] if the crops array is empty.
         def self.extract_crops(input_source, crops)
           if crops.nil? || crops.empty?

data/lib/mindee/v2/file_operations.rb

@@ -0,0 +1,6 @@
+# frozen_string_literal: true
+
+require_relative 'file_operations/crop'
+require_relative 'file_operations/crop_files'
+require_relative 'file_operations/split'
+require_relative 'file_operations/split_files'

data/lib/mindee/v2/product/split/split_response.rb

@@ -26,7 +26,7 @@ module Mindee
             @inference.to_s
           end
 
-          # Extracts the crops from the input source.
+          # Splits the input PDF.
           # @param input_source [Mindee::Input::Source::LocalInputSource] Path to the file or a File object.
           # @return [FileOperation::SplitFiles]
           def extract_from_file(input_source)

data/lib/mindee/v2.rb

@@ -2,6 +2,6 @@
 
 require_relative 'v2/client'
 require_relative 'v2/http'
-require_relative 'v2/file_operation' if Mindee::Dependency.all_deps_available?
+require_relative 'v2/file_operations' if Mindee::Dependencies.all_deps_available?
 require_relative 'v2/parsing'
 require_relative 'v2/product'

data/lib/mindee/version.rb

@@ -3,7 +3,7 @@
 # Mindee
 module Mindee
   # Current version.
-  VERSION = '5.0.0.beta1'
+  VERSION = '5.0.0'
 
   # Finds and return the current platform.
   # @return [Symbol, Hash[String | Symbol, Regexp], Nil?]

data/lib/mindee.rb

@@ -7,7 +7,7 @@ require 'mindee/v2'
 
 module Mindee
   # Dependency management
-  module Dependency
+  module Dependencies
   end
 
   # Mindee internal error module.

data/sig/mindee/{dependency.rbs → dependencies.rbs}

@@ -1,5 +1,5 @@
 module Mindee
-  module Dependency
+  module Dependencies
     MINDEE_DEPENDENCIES_LOAD_ERROR: String
 
     self.@all_deps_available: bool

data/sig/mindee/image/image_extractor.rbs

@@ -5,7 +5,7 @@ module Mindee
       def self.attach_image_as_new_file: (StringIO | File, ?format: String) -> Origami::PDF
       def self.to_blob: () -> String
       def self.extract_multiple_images_from_source: (Input::Source::LocalInputSource, Integer, Array[Array[Geometry::Point] |Geometry::Polygon | Geometry::Quadrilateral]) -> Array[ExtractedImage]
-      def self.extract_images_from_polygons: (Input::Source::LocalInputSource, StringIO | File, Integer, Array[Array[Geometry::Point] | Geometry::Polygon | Geometry::Quadrilateral]) -> Array[ExtractedImage]
+      def self.extract_images_from_polygons: (Input::Source::LocalInputSource, Integer, Array[Array[Geometry::Point] | Geometry::Polygon | Geometry::Quadrilateral]) -> Array[ExtractedImage]
       def self.create_extracted_image: (StringIO | File, String, Integer, Integer) -> ExtractedImage
       def self.load_input_source_pdf_page_as_stringio: (Input::Source::LocalInputSource, Integer) -> (StringIO | File)
     end

data/sig/mindee/input/base_parameters.rbs

@@ -5,7 +5,7 @@ module Mindee
     class BaseParameters
       attr_reader self.slug: String
 
-      def self.from_hash: (params: Hash[String | Symbol, untyped]) -> instance
+      def self.from_hash: (params: Hash[String | Symbol, untyped]) -> BaseParameters
       def self.load_from_hash: (params: Hash[String | Symbol, untyped]) -> Hash[String | Symbol, untyped]
 
       def slug: -> String

data/sig/mindee/pdf/pdf_extractor.rbs

@@ -13,7 +13,7 @@ module Mindee
 
       def extract_sub_documents: (Array[Array[Integer]]) -> Array[ExtractedPDF]
 
-      def extract_invoices: (Array[V1::Product::InvoiceSplitter::InvoiceSplitterV1InvoicePageGroup] | Array[Array[Integer]], ?strict: bool) -> Array[ExtractedPDF]
+      def extract_invoices: (Array[Mindee::V1::Product::InvoiceSplitter::InvoiceSplitterV1InvoicePageGroup] | Array[Array[Integer]], ?strict: bool) -> Array[ExtractedPDF]
     end
   end
 end

data/sig/mindee/v1/product/invoice_splitter/invoice_splitter_v1_document.rbs

@@ -6,7 +6,7 @@ module Mindee
     module InvoiceSplitter
       class InvoiceSplitterV1Document < Parsing::Common::Prediction
         def initialize: (Hash[String | Symbol, untyped], Integer?) -> void
-        def invoice_page_groups: -> (Product::InvoiceSplitter::InvoiceSplitterV1InvoicePageGroups)
+        def invoice_page_groups: -> InvoiceSplitterV1InvoicePageGroups
         def invoice_page_groups_separator: (String) -> String
         def invoice_page_groups_to_s: -> String
         def to_s: -> String

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: mindee
 version: !ruby/object:Gem::Version
-  version: 5.0.0.beta1
+  version: 5.0.0
 platform: ruby
 authors:
 - Mindee, SA
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2026-04-08 00:00:00.000000000 Z
+date: 2026-04-20 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: base64
@@ -231,7 +231,7 @@ files:
 - examples/auto_invoice_splitter_extraction.rb
 - examples/auto_multi_receipts_detector_extraction.rb
 - lib/mindee.rb
-- lib/mindee/dependency.rb
+- lib/mindee/dependencies.rb
 - lib/mindee/error.rb
 - lib/mindee/error/mindee_error.rb
 - lib/mindee/error/mindee_http_error.rb
@@ -396,11 +396,11 @@ files:
 - lib/mindee/v1/product/universal/universal_prediction.rb
 - lib/mindee/v2.rb
 - lib/mindee/v2/client.rb
-- lib/mindee/v2/file_operation.rb
-- lib/mindee/v2/file_operation/crop.rb
-- lib/mindee/v2/file_operation/crop_files.rb
-- lib/mindee/v2/file_operation/split.rb
-- lib/mindee/v2/file_operation/split_files.rb
+- lib/mindee/v2/file_operations.rb
+- lib/mindee/v2/file_operations/crop.rb
+- lib/mindee/v2/file_operations/crop_files.rb
+- lib/mindee/v2/file_operations/split.rb
+- lib/mindee/v2/file_operations/split_files.rb
 - lib/mindee/v2/http.rb
 - lib/mindee/v2/http/.rubocop.yml
 - lib/mindee/v2/http/api_v2_settings.rb
@@ -477,7 +477,7 @@ files:
 - sig/custom/net_http.rbs
 - sig/custom/origami.rbs
 - sig/mindee.rbs
-- sig/mindee/dependency.rbs
+- sig/mindee/dependencies.rbs
 - sig/mindee/error/mindee_error.rbs
 - sig/mindee/error/mindee_http_error.rbs
 - sig/mindee/error/mindee_http_error_v2.rbs
@@ -706,9 +706,9 @@ required_ruby_version: !ruby/object:Gem::Requirement
       version: '3.2'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
-  - - ">"
+  - - ">="
     - !ruby/object:Gem::Version
-      version: 1.3.1
+      version: '0'
 requirements: []
 rubygems_version: 3.4.19
 signing_key:

data/lib/mindee/v2/file_operation.rb

@@ -1,6 +0,0 @@
-# frozen_string_literal: true
-
-require_relative 'file_operation/crop'
-require_relative 'file_operation/crop_files'
-require_relative 'file_operation/split'
-require_relative 'file_operation/split_files'