mindee 3.17.0 → 3.18.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 12e0bc8339961d2e6be4c5dfdc9537d34ab63f449c435275324b95c031299764
-  data.tar.gz: 24021ef9d0175075365efc9e056d67f3d553b1ad7b95a5a2876d29fcff15031c
+  metadata.gz: 6d2f2fd3fa8b6ca9d7756f08d3f7b526b510866d0c75a33ccfab1ff20b3ba2c6
+  data.tar.gz: 7f09aa2efbe008271aa229515ce7f804680ea46d7318c6fe62d57889785762bb
 SHA512:
-  metadata.gz: df5dc07d28d67b0e1fe1c64c3123aeb3f9c8926264aed396fdd64858f8b06d6d2485745c61d15c35e0ae3f92ee6773eaacbdc86ba3256cefd7349fb0ff90533a
-  data.tar.gz: e07e7b776f21398ce3a9197fb54afef57361ffda29c198564da9ffa1fa0eea85830c7d1601177c241219bea60c61cbb9cbcec66ad0c80d55ffcc7aab0e8cfe4f
+  metadata.gz: 8bfa14969fc8938ca888b4c44a4861c969f816e5611bdf0150cec25677c3a6bb4cbd34d8e8b5a8ff48d2483fe8ed1ae462358a67bcd40176b3184122c65b5e76
+  data.tar.gz: 5afeb6406e28ea57c2a56d7f5e52f90739cb7be1b77648773d3365d52adf72f8ea6b97be16838aa428a32ce5cbc414acabe9b0d61196fc05a2027231062598f9

data/CHANGELOG.md

@@ -1,5 +1,13 @@
 # Mindee Ruby API Library Changelog
 
+## v3.18.0 - 2024-12-13
+### Changes
+* :sparkles: allow local downloading of remote sources
+* :coffin: remove support for (FR) Carte Vitale V1 in favor of French Health Card V1
+### Fixes
+* :bug: fix tax-extraction script
+
+
 ## v3.17.0 - 2024-11-28
 ### Changes
 * :sparkles: add support for workflows

data/README.md

@@ -116,7 +116,7 @@ result = mindee_client.parse(
 puts result.document
 ```
 
-### Custom Document (API Builder)
+### Custom Documents (docTI & Custom APIs)
 
 ```ruby
 require 'mindee'
@@ -131,9 +131,9 @@ endpoint = mindee_client.create_endpoint(
 # Load a file from disk
 input_source = mindee_client.source_from_path('/path/to/the/file.ext')
 
-result = mindee_client.parse(
+result = mindee_client.enqueue_and_parse(
   input_source,
-  Mindee::Product::Custom::CustomV1,
+  Mindee::Product::Generated::GeneratedV1,
   endpoint: endpoint
 )
 
@@ -181,7 +181,7 @@ customize the experience.
 * [EU Driver License OCR Ruby](https://developers.mindee.com/docs/ruby-eu-driver-license-ocr)
 * [FR Bank Account Details OCR Ruby](https://developers.mindee.com/docs/ruby-fr-bank-account-details-ocr)
 * [FR Bank Statement OCR Ruby](https://developers.mindee.com/docs/ruby-fr-bank-statement-ocr)
-* [FR Carte Vitale OCR Ruby](https://developers.mindee.com/docs/ruby-fr-carte-vitale-ocr)
+* [FR Health Card OCR Ruby](https://developers.mindee.com/docs/ruby-fr-health-card-ocr)
 * [FR ID Card OCR Ruby](https://developers.mindee.com/docs/ruby-fr-carte-nationale-didentite-ocr)
 * [US Bank Check OCR Ruby](https://developers.mindee.com/docs/ruby-us-bank-check-ocr)
 * [US Driver License OCR Ruby](https://developers.mindee.com/docs/ruby-us-driver-license-ocr)

data/bin/mindee.rb

@@ -97,12 +97,6 @@ DOCUMENTS = {
     sync: false,
     async: true,
   },
-  "fr-carte-vitale" => {
-    description: "FR Carte Vitale",
-    doc_class: Mindee::Product::FR::CarteVitale::CarteVitaleV1,
-    sync: true,
-    async: false,
-  },
   "fr-id-card" => {
     description: "FR ID Card",
     doc_class: Mindee::Product::FR::IdCard::IdCardV2,

data/docs/custom_v1.md

@@ -4,7 +4,7 @@ category: 622b805aaec68102ea7fcbc2
 slug: ruby-api-builder-ocr
 parentDoc: 6294d97ee723f1008d2ab28e
 ---
-> 🚧 This product is still supported, but is considered to be deprecated. If you are looking for the DocTI API documentation, you can find it [here](https://developers.mindee.com/docs/ruby-generated-ocr).
+> 🚧 This product is still supported, but is considered to be deprecated. If you are looking for the docTI API documentation, you can find it [here](https://developers.mindee.com/docs/ruby-generated-ocr).
 
 # Quick-Start
 

data/docs/getting_started.md

@@ -226,20 +226,20 @@ result = mindee_client.parse(
 )
 ```
 
-### Custom Documents
+### Custom Documents (docTI)
 For custom documents, the endpoint to use must also be set, and it must take in an `endpoint_name`:
 
 ```ruby
-endpoint = mindee_client.create_endpoint(endpoint_name: 'wnine')
+endpoint = mindee_client.create_endpoint(endpoint_name: 'wnine', account_name: 'my-account')
 
-result = mindee_client.parse(
+result = mindee_client.enqueue_and_parse(
   input_source,
-  Mindee::Product::Custom::CustomV1,
+  Mindee::Product::Generated::GeneratedV1,
   endpoint: endpoint
 )
 ```
 
-This is because the `CustomV1` class is enough to handle the return processing, but the actual endpoint needs to be specified.
+This is because the `GeneratedV1` class is enough to handle the return processing, but the actual endpoint needs to be specified.
 
 ## Process the Result
 The response object is common to all documents, including custom documents. The main properties are:

data/lib/mindee/extraction/tax_extractor/tax_extractor.rb

@@ -2,6 +2,8 @@
 
 require_relative 'ocr_extractor'
 
+# rubocop:disable Metrics/ClassLength
+
 module Mindee
   module Extraction
     # Tax extractor class
@@ -72,9 +74,12 @@ module Mindee
         reconstructed_hash['code'] =
           found_hash['code'].nil? ? found_hash['code'] : found_hash['code'].sub(%r{\s*\.*\s*$}, '')
 
-        if found_hash['rate'] && found_hash['rate'] < 1 && (found_hash['rate']).positive?
-          found_hash['rate'] =
-            found_hash['rate'] * 100
+        if found_hash['rate']
+          if found_hash['rate'].abs < 1
+            found_hash['rate'] *= 10
+          elsif found_hash['rate'].abs > 100
+            found_hash['rate'] /= 10
+          end
         end
         found_hash = swap_rates_if_needed(found_hash, min_rate_percentage, max_rate_percentage)
         found_hash = decimate_rates_if_needed(found_hash)
@@ -125,18 +130,28 @@ module Mindee
       # @param found_hash [Hash] Hash of currently retrieved values
       # @return [Hash]
       def self.set_base_and_value(reconstructed_hash, found_hash)
-        if found_hash['base'].nil?
-          reconstructed_hash['base'] = found_hash['base']
-          reconstructed_hash['value'] = found_hash['value']
-        elsif found_hash['value'].nil? && found_hash['base'] < found_hash['value']
-          reconstructed_hash['base'] = found_hash['value']
-          reconstructed_hash['value'] = found_hash['base']
-        else
-          reconstructed_hash['value'] = found_hash['value']
+        base = found_hash['base']
+        value = found_hash['value']
+
+        if base && value
+          reconstructed_hash['base'], reconstructed_hash['value'] = [base, value].minmax
+        elsif base
+          reconstructed_hash['base'] = base
+        elsif value
+          reconstructed_hash['value'] = value
+          calculate_base(reconstructed_hash)
         end
+
         reconstructed_hash
       end
 
+      def self.calculate_base(hash)
+        rate = hash['rate']
+        return unless rate&.positive?
+
+        hash['base'] = hash['value'] / (rate / 100.0)
+      end
+
       # Extracts a single custom type of tax.
       # For the sake of simplicity, this only extracts the first example, unless specifically instructed otherwise.
       # @param ocr_result [Mindee::Parsing::Common::Ocr::Ocr] result of the OCR.
@@ -149,7 +164,6 @@ module Mindee
 
         tax_names.sort!
         found_hash = pick_best(extract_horizontal_tax(ocr_result, tax_names), tax_names)
-        # a tax is considered found horizontally if it has a value, otherwise it is vertical
         if found_hash.nil? || found_hash['value'].nil?
           found_hash = extract_vertical_tax(ocr_result, tax_names,
                                             found_hash)
@@ -240,14 +254,14 @@ module Mindee
         linear_pattern_percent_first = %r{
           ((?:\s*-\s*)?(?:\d*[.,])*\d+[ ]?%?|%?[ ]?(?:\s*-\s*)?(?:\d*[.,])*\d+)?[ .]?
           ([a-zA-ZÀ-ÖØ-öø-ÿ .]*[a-zA-ZÀ-ÖØ-öø-ÿ]?)[ .]?
-          ((?:\s*-\s*)?(?:\d*[.,])+\d{2,})?[ .]*
-          ((?:\s*-\s*)?(\d*[.,])*\d{2,})?
+          ((?:\s*-\s*)?(?:\d*[.,])+\d+)?[ .]*
+          ((?:\s*-\s*)?(\d*[.,])*\d+)?
         }x
         linear_pattern_percent_second = %r{
           ([a-zA-ZÀ-ÖØ-öø-ÿ .]*[a-zA-ZÀ-ÖØ-öø-ÿ]?)[ .]*
           ((?:\s*-\s*)?(?:\d*[.,])*\d+[ ]?%?|%?[ ]?(?:\s*-\s*)?(?:\d*[.,])*\d+)?[ .]?
-          ((?:\s*-\s*)?(?:\d*[.,])+\d{2,})?[ .]*
-          ((?:\s*-\s*)?(\d*[.,])*\d{2,})?
+          ((?:\s*-\s*)?(?:\d*[.,])+\d+)?[ .]*
+          ((?:\s*-\s*)?(\d*[.,])*\d+)?
         }x
         ocr_result.mvision_v1.pages.each.with_index do |page, page_id|
           page.all_lines.each do |line|
@@ -304,7 +318,7 @@ module Mindee
           page.all_words.each do |word|
             next if match_index(word.text, tax_names).nil?
 
-            reconstructed_line = ocr_result.reconstruct_vertically(word.polygon, page_id)
+            reconstructed_line = ocr_result.reconstruct_vertically(word.polygon, page_id, 0.25)
             found_hash['page_id'] = page_id if found_hash['page_id'].nil?
             found_hash['code'] = word.text.strip if found_hash['code'].nil?
             found_hash = extract_vertical_tax_values(reconstructed_line, found_hash)
@@ -316,8 +330,9 @@ module Mindee
       private_class_method :extract_percentage_from_tax, :extract_basis_and_value, :extract_tax_from_horizontal_line,
                            :extract_horizontal_tax, :extract_vertical_tax_values, :extract_vertical_tax,
                            :create_tax_field, :fix_rate, :pick_best, :calculate_score, :curate_values,
-                           :decimate_rates_if_needed, :extract_basis_and_value, :set_base_and_value, :valid_candidate?,
-                           :swap_rates_if_needed
+                           :decimate_rates_if_needed, :set_base_and_value, :valid_candidate?,
+                           :swap_rates_if_needed, :calculate_base
     end
   end
 end
+# rubocop:enable Metrics/ClassLength

data/lib/mindee/input/sources/base64_input_source.rb

@@ -0,0 +1,31 @@
+# frozen_string_literal: true
+
+require 'stringio'
+
+module Mindee
+  module Input
+    module Source
+      # Load a document from a base64 string.
+      class Base64InputSource < LocalInputSource
+        # @param base64_string [String]
+        # @param filename [String]
+        # @param fix_pdf [Boolean]
+        def initialize(base64_string, filename, fix_pdf: false)
+          io_stream = StringIO.new(base64_string.unpack1('m*'))
+          io_stream.set_encoding Encoding::BINARY
+          super(io_stream, filename, fix_pdf: fix_pdf)
+        end
+
+        # Overload of the same function to prevent a base64 from being re-encoded.
+        # @param close [Boolean]
+        # @return [Array<String, [String, aBinaryString ], [Hash, nil] >]
+        def read_document(close: true)
+          @io_stream.seek(0)
+          data = @io_stream.read
+          @io_stream.close if close
+          ['document', [data].pack('m'), { filename: Source.convert_to_unicode_escape(@filename) }]
+        end
+      end
+    end
+  end
+end

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

@@ -0,0 +1,21 @@
+# frozen_string_literal: true
+
+require 'stringio'
+
+module Mindee
+  module Input
+    module Source
+      # Load a document from raw bytes.
+      class BytesInputSource < LocalInputSource
+        # @param raw_bytes [String]
+        # @param filename [String]
+        # @param fix_pdf [Boolean]
+        def initialize(raw_bytes, filename, fix_pdf: false)
+          io_stream = StringIO.new(raw_bytes)
+          io_stream.set_encoding Encoding::BINARY
+          super(io_stream, filename, fix_pdf: fix_pdf)
+        end
+      end
+    end
+  end
+end

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

@@ -0,0 +1,20 @@
+# frozen_string_literal: true
+
+require 'stringio'
+
+module Mindee
+  module Input
+    module Source
+      # Load a document from a file handle.
+      class FileInputSource < LocalInputSource
+        # @param input_file [File]
+        # @param filename [String]
+        # @param fix_pdf [Boolean]
+        def initialize(input_file, filename, fix_pdf: false)
+          io_stream = input_file
+          super(io_stream, filename, fix_pdf: fix_pdf)
+        end
+      end
+    end
+  end
+end

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

@@ -0,0 +1,183 @@
+# frozen_string_literal: true
+
+require 'stringio'
+require 'marcel'
+
+require_relative '../../pdf'
+require_relative '../../image'
+
+module Mindee
+  module Input
+    # Document source handling.
+    module Source
+      # Mime types accepted by the server.
+      ALLOWED_MIME_TYPES = [
+        'application/pdf',
+        'image/heic',
+        'image/png',
+        'image/jpeg',
+        'image/tiff',
+        'image/webp',
+      ].freeze
+
+      # Standard error for invalid mime types
+      class MimeTypeError < StandardError
+      end
+
+      # Error sent if the file's mimetype isn't allowed
+      class InvalidMimeTypeError < MimeTypeError
+        # @return [String]
+        attr_reader :invalid_mimetype
+
+        # @param mime_type [String]
+        def initialize(mime_type)
+          @invalid_mimetype = mime_type
+          super("'#{@invalid_mimetype}' mime type not allowed, must be one of #{ALLOWED_MIME_TYPES.join(', ')}")
+        end
+      end
+
+      # Error sent if a pdf file couldn't be fixed
+      class UnfixablePDFError < MimeTypeError
+        def initialize
+          super("Corrupted PDF couldn't be repaired.")
+        end
+      end
+
+      # Base class for loading documents.
+      class LocalInputSource
+        # @return [String]
+        attr_reader :filename
+        # @return [String]
+        attr_reader :file_mimetype
+        # @return [StringIO]
+        attr_reader :io_stream
+
+        # @param io_stream [StringIO]
+        # @param filename [String]
+        # @param fix_pdf [Boolean]
+        def initialize(io_stream, filename, fix_pdf: false)
+          @io_stream = io_stream
+          @filename = filename
+          @file_mimetype = if fix_pdf
+                             Marcel::MimeType.for @io_stream
+                           else
+                             Marcel::MimeType.for @io_stream, name: @filename
+                           end
+          return if ALLOWED_MIME_TYPES.include? @file_mimetype
+
+          if filename.end_with?('.pdf') && fix_pdf
+            rescue_broken_pdf(@io_stream)
+            @file_mimetype = Marcel::MimeType.for @io_stream
+
+            return if ALLOWED_MIME_TYPES.include? @file_mimetype
+          end
+
+          raise InvalidMimeTypeError, @file_mimetype.to_s
+        end
+
+        # Attempts to fix pdf files if mimetype is rejected.
+        # "Broken PDFs" are often a result of third-party injecting invalid headers.
+        # This attempts to remove them and send the file
+        # @param stream [StringIO]
+        def rescue_broken_pdf(stream)
+          stream.gets('%PDF-')
+          raise UnfixablePDFError if stream.eof? || stream.pos > 500
+
+          stream.pos = stream.pos - 5
+          data = stream.read
+          @io_stream.close
+
+          @io_stream = StringIO.new
+          @io_stream << data
+        end
+
+        # Shorthand for pdf mimetype validation.
+        def pdf?
+          @file_mimetype.to_s == 'application/pdf'
+        end
+
+        # Parses a PDF file according to provided options.
+        # @param options [Hash, nil] Page cutting/merge options:
+        #
+        #  * `:page_indexes` Zero-based list of page indexes.
+        #  * `:operation` Operation to apply on the document, given the `page_indexes specified:
+        #      * `:KEEP_ONLY` - keep only the specified pages, and remove all others.
+        #      * `:REMOVE` - remove the specified pages, and keep all others.
+        #  * `:on_min_pages` Apply the operation only if document has at least this many pages.
+        def process_pdf(options)
+          @io_stream.seek(0)
+          @io_stream = PdfProcessor.parse(@io_stream, options)
+        end
+
+        # Reads a document.
+        # @param close [Boolean]
+        # @return [Array<String, [String, aBinaryString ], [Hash, nil] >]
+        def read_document(close: true)
+          @io_stream.seek(0)
+          # Avoids needlessly re-packing some files
+          data = @io_stream.read
+          @io_stream.close if close
+          ['document', data, { filename: Mindee::Input::Source.convert_to_unicode_escape(@filename) }]
+        end
+
+        def count_pdf_pages
+          return 1 unless pdf?
+
+          @io_stream.seek(0)
+          pdf_processor = Mindee::PDF::PdfProcessor.open_pdf(@io_stream)
+          pdf_processor.pages.size
+        end
+
+        # Compresses the file, according to the provided info.
+        # @param [Integer] quality Quality of the output file.
+        # @param [Integer, nil] max_width Maximum width (Ignored for PDFs).
+        # @param [Integer, nil] max_height Maximum height (Ignored for PDFs).
+        # @param [Boolean] force_source_text Whether to force the operation on PDFs with source text.
+        #   This will attempt to re-render PDF text over the rasterized original. If disabled, ignored the operation.
+        #   WARNING: this operation is strongly discouraged.
+        # @param [Boolean] 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)
+          buffer = if pdf?
+                     Mindee::PDF::PDFCompressor.compress_pdf(
+                       @io_stream,
+                       quality: quality,
+                       force_source_text_compression: force_source_text,
+                       disable_source_text: disable_source_text
+                     )
+                   else
+                     Mindee::Image::ImageCompressor.compress_image(
+                       @io_stream,
+                       quality: quality,
+                       max_width: max_width,
+                       max_height: max_height
+                     )
+                   end
+          @io_stream = buffer
+          @io_stream.rewind
+        end
+
+        # Checks whether the file has source text if it is a pdf. False otherwise
+        # @return [Boolean] True if the file is a PDF and has source text.
+        def source_text?
+          Mindee::PDF::PDFTools.source_text?(@io_stream)
+        end
+      end
+
+      # Replaces non-ASCII characters by their UNICODE escape sequence.
+      # Keeps other characters as is.
+      # @return A clean String.
+      def self.convert_to_unicode_escape(string)
+        unicode_escape_string = ''.dup
+        string.each_char do |char|
+          unicode_escape_string << if char.bytesize > 1
+                                     "\\u#{char.unpack1('U').to_s(16).rjust(4, '0')}"
+                                   else
+                                     char
+                                   end
+        end
+        unicode_escape_string
+      end
+    end
+  end
+end

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

@@ -0,0 +1,20 @@
+# frozen_string_literal: true
+
+require 'stringio'
+
+module Mindee
+  module Input
+    # Document source handling.
+    module Source
+      # Load a document from a path.
+      class PathInputSource < LocalInputSource
+        # @param filepath [String]
+        # @param fix_pdf [Boolean]
+        def initialize(filepath, fix_pdf: false)
+          io_stream = File.open(filepath, 'rb')
+          super(io_stream, File.basename(filepath), fix_pdf: fix_pdf)
+        end
+      end
+    end
+  end
+end

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

@@ -0,0 +1,127 @@
+# frozen_string_literal: true
+
+require 'net/http'
+require 'uri'
+require 'fileutils'
+
+module Mindee
+  module Input
+    module Source
+      # Load a remote document from a file url.
+      class UrlInputSource
+        # @return [String]
+        attr_reader :url
+
+        def initialize(url)
+          raise 'URL must be HTTPS' unless url.start_with? 'https://'
+
+          @url = url
+        end
+
+        # Downloads the file from the URL and saves it to the specified path.
+        #
+        # @param path [String] Path to save the file to.
+        # @param filename [String, nil] Optional name to give to the file.
+        # @param username [String, nil] Optional username for authentication.
+        # @param password [String, nil] Optional password for authentication.
+        # @param token [String, nil] Optional token for JWT-based authentication.
+        # @param max_redirects [Integer] Maximum amount of redirects to follow.
+        # @return [String] The full path of the saved file.
+        def save_to_file(path, filename: nil, username: nil, password: nil, token: nil, max_redirects: 3)
+          response_body = fetch_file_content(username: username, password: password, token: token,
+                                             max_redirects: max_redirects)
+
+          filename = fill_filename(filename)
+
+          full_path = File.join(path.chomp('/'), filename)
+          File.write(full_path, response_body)
+
+          full_path
+        end
+
+        # Downloads the file from the url, and returns a BytesInputSource wrapper object for it.
+        #
+        # @param filename [String, nil] Optional name to give to the file.
+        # @param username [String, nil] Optional username for authentication.
+        # @param password [String, nil] Optional password for authentication.
+        # @param token [String, nil] Optional token for JWT-based authentication.
+        # @param max_redirects [Integer] Maximum amount of redirects to follow.
+        # @return [BytesInputSource] The full path of the saved file.
+        def as_local_input_source(filename: nil, username: nil, password: nil, token: nil, max_redirects: 3)
+          filename = fill_filename(filename)
+          response_body = fetch_file_content(username: username, password: password, token: token,
+                                             max_redirects: max_redirects)
+          bytes = StringIO.new(response_body)
+
+          BytesInputSource.new(bytes.read, filename)
+        end
+
+        # Fetches the file content from the URL.
+        #
+        # @param username [String, nil] Optional username for authentication.
+        # @param password [String, nil] Optional password for authentication.
+        # @param token [String, nil] Optional token for JWT-based authentication.
+        # @param max_redirects [Integer] Maximum amount of redirects to follow.
+        # @return [String] The downloaded file content.
+        def fetch_file_content(username: nil, password: nil, token: nil, max_redirects: 3)
+          uri = URI.parse(@url)
+          request = Net::HTTP::Get.new(uri)
+
+          request['Authorization'] = "Bearer #{token}" if token
+          request.basic_auth(username, password) if username && password
+
+          response = make_request(uri, request, max_redirects)
+          if response.code.to_i > 299
+            raise "Failed to download file: HTTP status code #{response.code}"
+          elsif response.code.to_i < 200
+            raise "Failed to download file: Invalid response code #{response.code}."
+          end
+
+          response.body
+        end
+
+        private
+
+        def extract_filename_from_url(uri)
+          filename = File.basename(uri.path)
+          filename.empty? ? '' : filename
+        end
+
+        def fill_filename(filename)
+          filename ||= extract_filename_from_url(URI.parse(@url))
+          if filename.empty? || File.extname(filename).empty?
+            filename = generate_file_name(extension: get_file_extension(filename))
+          end
+          filename
+        end
+
+        def make_request(uri, request, max_redirects)
+          Net::HTTP.start(uri.hostname, uri.port, use_ssl: true) do |http|
+            response = http.request(request)
+            if response.is_a?(Net::HTTPRedirection) && max_redirects.positive?
+              location = response['location']
+              raise 'No location in redirection header.' if location.nil?
+
+              new_uri = URI.parse(location)
+              request = Net::HTTP::Get.new(new_uri)
+              make_request(new_uri, request, max_redirects - 1)
+            else
+              response
+            end
+          end
+        end
+
+        def get_file_extension(filename)
+          ext = File.extname(filename)
+          ext.empty? ? nil : ext.downcase
+        end
+
+        def generate_file_name(extension: nil)
+          extension ||= '.tmp'
+          random_string = Array.new(8) { rand(36).to_s(36) }.join
+          "mindee_temp_#{Time.now.strftime('%Y-%m-%d_%H-%M-%S')}_#{random_string}#{extension}"
+        end
+      end
+    end
+  end
+end

data/lib/mindee/input/sources.rb

@@ -1,250 +1,8 @@
 # frozen_string_literal: true
 
-require 'stringio'
-require 'marcel'
-
-require_relative '../pdf'
-require_relative '../image'
-
-module Mindee
-  module Input
-    # Document source handling.
-    module Source
-      # Mime types accepted by the server.
-      ALLOWED_MIME_TYPES = [
-        'application/pdf',
-        'image/heic',
-        'image/png',
-        'image/jpeg',
-        'image/tiff',
-        'image/webp',
-      ].freeze
-
-      # Standard error for invalid mime types
-      class MimeTypeError < StandardError
-      end
-
-      # Error sent if the file's mimetype isn't allowed
-      class InvalidMimeTypeError < MimeTypeError
-        # @return [String]
-        attr_reader :invalid_mimetype
-
-        # @param mime_type [String]
-        def initialize(mime_type)
-          @invalid_mimetype = mime_type
-          super("'#{@invalid_mimetype}' mime type not allowed, must be one of #{ALLOWED_MIME_TYPES.join(', ')}")
-        end
-      end
-
-      # Error sent if a pdf file couldn't be fixed
-      class UnfixablePDFError < MimeTypeError
-        def initialize
-          super("Corrupted PDF couldn't be repaired.")
-        end
-      end
-
-      # Base class for loading documents.
-      class LocalInputSource
-        # @return [String]
-        attr_reader :filename
-        # @return [String]
-        attr_reader :file_mimetype
-        # @return [StringIO]
-        attr_reader :io_stream
-
-        # @param io_stream [StringIO]
-        # @param filename [String]
-        # @param fix_pdf [Boolean]
-        def initialize(io_stream, filename, fix_pdf: false)
-          @io_stream = io_stream
-          @filename = filename
-          @file_mimetype = if fix_pdf
-                             Marcel::MimeType.for @io_stream
-                           else
-                             Marcel::MimeType.for @io_stream, name: @filename
-                           end
-          return if ALLOWED_MIME_TYPES.include? @file_mimetype
-
-          if filename.end_with?('.pdf') && fix_pdf
-            rescue_broken_pdf(@io_stream)
-            @file_mimetype = Marcel::MimeType.for @io_stream
-
-            return if ALLOWED_MIME_TYPES.include? @file_mimetype
-          end
-
-          raise InvalidMimeTypeError, @file_mimetype.to_s
-        end
-
-        # Attempts to fix pdf files if mimetype is rejected.
-        # "Broken PDFs" are often a result of third-party injecting invalid headers.
-        # This attempts to remove them and send the file
-        # @param stream [StringIO]
-        def rescue_broken_pdf(stream)
-          stream.gets('%PDF-')
-          raise UnfixablePDFError if stream.eof? || stream.pos > 500
-
-          stream.pos = stream.pos - 5
-          data = stream.read
-          @io_stream.close
-
-          @io_stream = StringIO.new
-          @io_stream << data
-        end
-
-        # Shorthand for pdf mimetype validation.
-        def pdf?
-          @file_mimetype.to_s == 'application/pdf'
-        end
-
-        # Parses a PDF file according to provided options.
-        # @param options [Hash, nil] Page cutting/merge options:
-        #
-        #  * `:page_indexes` Zero-based list of page indexes.
-        #  * `:operation` Operation to apply on the document, given the `page_indexes specified:
-        #      * `:KEEP_ONLY` - keep only the specified pages, and remove all others.
-        #      * `:REMOVE` - remove the specified pages, and keep all others.
-        #  * `:on_min_pages` Apply the operation only if document has at least this many pages.
-        def process_pdf(options)
-          @io_stream.seek(0)
-          @io_stream = PdfProcessor.parse(@io_stream, options)
-        end
-
-        # Reads a document.
-        # @param close [Boolean]
-        # @return [Array<String, [String, aBinaryString ], [Hash, nil] >]
-        def read_document(close: true)
-          @io_stream.seek(0)
-          # Avoids needlessly re-packing some files
-          data = @io_stream.read
-          @io_stream.close if close
-          ['document', data, { filename: Mindee::Input::Source.convert_to_unicode_escape(@filename) }]
-        end
-
-        def count_pdf_pages
-          return 1 unless pdf?
-
-          @io_stream.seek(0)
-          pdf_processor = Mindee::PDF::PdfProcessor.open_pdf(@io_stream)
-          pdf_processor.pages.size
-        end
-
-        # Compresses the file, according to the provided info.
-        # @param [Integer] quality Quality of the output file.
-        # @param [Integer, nil] max_width Maximum width (Ignored for PDFs).
-        # @param [Integer, nil] max_height Maximum height (Ignored for PDFs).
-        # @param [Boolean] force_source_text Whether to force the operation on PDFs with source text.
-        #   This will attempt to re-render PDF text over the rasterized original. If disabled, ignored the operation.
-        #   WARNING: this operation is strongly discouraged.
-        # @param [Boolean] 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)
-          buffer = if pdf?
-                     Mindee::PDF::PDFCompressor.compress_pdf(
-                       @io_stream,
-                       quality: quality,
-                       force_source_text_compression: force_source_text,
-                       disable_source_text: disable_source_text
-                     )
-                   else
-                     Mindee::Image::ImageCompressor.compress_image(
-                       @io_stream,
-                       quality: quality,
-                       max_width: max_width,
-                       max_height: max_height
-                     )
-                   end
-          @io_stream = buffer
-          @io_stream.rewind
-        end
-
-        # Checks whether the file has source text if it is a pdf. False otherwise
-        # @return [Boolean] True if the file is a PDF and has source text.
-        def source_text?
-          Mindee::PDF::PDFTools.source_text?(@io_stream)
-        end
-      end
-
-      # Load a document from a path.
-      class PathInputSource < LocalInputSource
-        # @param filepath [String]
-        # @param fix_pdf [Boolean]
-        def initialize(filepath, fix_pdf: false)
-          io_stream = File.open(filepath, 'rb')
-          super(io_stream, File.basename(filepath), fix_pdf: fix_pdf)
-        end
-      end
-
-      # Load a document from a base64 string.
-      class Base64InputSource < LocalInputSource
-        # @param base64_string [String]
-        # @param filename [String]
-        # @param fix_pdf [Boolean]
-        def initialize(base64_string, filename, fix_pdf: false)
-          io_stream = StringIO.new(base64_string.unpack1('m*'))
-          io_stream.set_encoding Encoding::BINARY
-          super(io_stream, filename, fix_pdf: fix_pdf)
-        end
-
-        # Overload of the same function to prevent a base64 from being re-encoded.
-        # @param close [Boolean]
-        # @return [Array<String, [String, aBinaryString ], [Hash, nil] >]
-        def read_document(close: true)
-          @io_stream.seek(0)
-          data = @io_stream.read
-          @io_stream.close if close
-          ['document', [data].pack('m'), { filename: Source.convert_to_unicode_escape(@filename) }]
-        end
-      end
-
-      # Load a document from raw bytes.
-      class BytesInputSource < LocalInputSource
-        # @param raw_bytes [String]
-        # @param filename [String]
-        # @param fix_pdf [Boolean]
-        def initialize(raw_bytes, filename, fix_pdf: false)
-          io_stream = StringIO.new(raw_bytes)
-          io_stream.set_encoding Encoding::BINARY
-          super(io_stream, filename, fix_pdf: fix_pdf)
-        end
-      end
-
-      # Load a document from a file handle.
-      class FileInputSource < LocalInputSource
-        # @param input_file [File]
-        # @param filename [String]
-        # @param fix_pdf [Boolean]
-        def initialize(input_file, filename, fix_pdf: false)
-          io_stream = input_file
-          super(io_stream, filename, fix_pdf: fix_pdf)
-        end
-      end
-
-      # Load a remote document from a file url.
-      class UrlInputSource
-        # @return [String]
-        attr_reader :url
-
-        def initialize(url)
-          raise 'URL must be HTTPS' unless url.start_with? 'https://'
-
-          @url = url
-        end
-      end
-
-      # Replaces non-ASCII characters by their unicode escape sequence.
-      # Keeps other characters as is.
-      # @return A clean String.
-      def self.convert_to_unicode_escape(string)
-        unicode_escape_string = ''.dup
-        string.each_char do |char|
-          unicode_escape_string << if char.bytesize > 1
-                                     "\\u#{char.unpack1('U').to_s(16).rjust(4, '0')}"
-                                   else
-                                     char
-                                   end
-        end
-        unicode_escape_string
-      end
-    end
-  end
-end
+require_relative 'sources/local_input_source'
+require_relative 'sources/bytes_input_source'
+require_relative 'sources/base64_input_source'
+require_relative 'sources/file_input_source'
+require_relative 'sources/path_input_source'
+require_relative 'sources/url_input_source'

data/lib/mindee/product.rb

@@ -13,7 +13,6 @@ require_relative 'product/fr/bank_account_details/bank_account_details_v1'
 require_relative 'product/fr/bank_account_details/bank_account_details_v2'
 require_relative 'product/fr/bank_statement/bank_statement_v1'
 require_relative 'product/fr/carte_grise/carte_grise_v1'
-require_relative 'product/fr/carte_vitale/carte_vitale_v1'
 require_relative 'product/fr/id_card/id_card_v1'
 require_relative 'product/fr/id_card/id_card_v2'
 require_relative 'product/fr/energy_bill/energy_bill_v1'

data/lib/mindee/version.rb

@@ -3,7 +3,7 @@
 # Mindee
 module Mindee
   # Current version.
-  VERSION = '3.17.0'
+  VERSION = '3.18.0'
 
   # Finds and return the current platform.
   # @return [String]

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: mindee
 version: !ruby/object:Gem::Version
-  version: 3.17.0
+  version: 3.18.0
 platform: ruby
 authors:
 - Mindee, SA
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2024-11-28 00:00:00.000000000 Z
+date: 2024-12-13 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: marcel
@@ -166,7 +166,6 @@ files:
 - docs/code_samples/bill_of_lading_v1_async.txt
 - docs/code_samples/business_card_v1_async.txt
 - docs/code_samples/carte_grise_v1.txt
-- docs/code_samples/carte_vitale_v1.txt
 - docs/code_samples/cropper_v1.txt
 - docs/code_samples/custom_v1.txt
 - docs/code_samples/default.txt
@@ -260,6 +259,12 @@ files:
 - lib/mindee/input.rb
 - lib/mindee/input/local_response.rb
 - lib/mindee/input/sources.rb
+- lib/mindee/input/sources/base64_input_source.rb
+- lib/mindee/input/sources/bytes_input_source.rb
+- lib/mindee/input/sources/file_input_source.rb
+- lib/mindee/input/sources/local_input_source.rb
+- lib/mindee/input/sources/path_input_source.rb
+- lib/mindee/input/sources/url_input_source.rb
 - lib/mindee/parsing.rb
 - lib/mindee/parsing/common.rb
 - lib/mindee/parsing/common/api_response.rb
@@ -353,9 +358,6 @@ files:
 - lib/mindee/product/fr/carte_grise/carte_grise_v1.rb
 - lib/mindee/product/fr/carte_grise/carte_grise_v1_document.rb
 - lib/mindee/product/fr/carte_grise/carte_grise_v1_page.rb
-- lib/mindee/product/fr/carte_vitale/carte_vitale_v1.rb
-- lib/mindee/product/fr/carte_vitale/carte_vitale_v1_document.rb
-- lib/mindee/product/fr/carte_vitale/carte_vitale_v1_page.rb
 - lib/mindee/product/fr/energy_bill/energy_bill_v1.rb
 - lib/mindee/product/fr/energy_bill/energy_bill_v1_document.rb
 - lib/mindee/product/fr/energy_bill/energy_bill_v1_energy_consumer.rb

data/docs/code_samples/carte_vitale_v1.txt

@@ -1,19 +0,0 @@
-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::FR::CarteVitale::CarteVitaleV1
-)
-
-# 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/lib/mindee/product/fr/carte_vitale/carte_vitale_v1.rb

@@ -1,41 +0,0 @@
-# frozen_string_literal: true
-
-require_relative '../../../parsing'
-require_relative 'carte_vitale_v1_document'
-require_relative 'carte_vitale_v1_page'
-
-module Mindee
-  module Product
-    module FR
-      # Carte Vitale module.
-      module CarteVitale
-        # Carte Vitale API version 1 inference prediction.
-        class CarteVitaleV1 < Mindee::Parsing::Common::Inference
-          @endpoint_name = 'carte_vitale'
-          @endpoint_version = '1'
-
-          # @param prediction [Hash]
-          def initialize(prediction)
-            super
-            @prediction = CarteVitaleV1Document.new(prediction['prediction'], nil)
-            @pages = []
-            prediction['pages'].each do |page|
-              if page.key?('prediction') && !page['prediction'].nil? && !page['prediction'].empty?
-                @pages.push(CarteVitaleV1Page.new(page))
-              end
-            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

data/lib/mindee/product/fr/carte_vitale/carte_vitale_v1_document.rb

@@ -1,52 +0,0 @@
-# frozen_string_literal: true
-
-require_relative '../../../parsing'
-
-module Mindee
-  module Product
-    module FR
-      module CarteVitale
-        # Carte Vitale API version 1.1 document data.
-        class CarteVitaleV1Document < Mindee::Parsing::Common::Prediction
-          include Mindee::Parsing::Standard
-          # The given name(s) of the card holder.
-          # @return [Array<Mindee::Parsing::Standard::StringField>]
-          attr_reader :given_names
-          # The date the card was issued.
-          # @return [Mindee::Parsing::Standard::DateField]
-          attr_reader :issuance_date
-          # The Social Security Number (Numéro de Sécurité Sociale) of the card holder
-          # @return [Mindee::Parsing::Standard::StringField]
-          attr_reader :social_security
-          # The surname of the card holder.
-          # @return [Mindee::Parsing::Standard::StringField]
-          attr_reader :surname
-
-          # @param prediction [Hash]
-          # @param page_id [Integer, nil]
-          def initialize(prediction, page_id)
-            super()
-            @given_names = []
-            prediction['given_names'].each do |item|
-              @given_names.push(StringField.new(item, page_id))
-            end
-            @issuance_date = DateField.new(prediction['issuance_date'], page_id)
-            @social_security = StringField.new(prediction['social_security'], page_id)
-            @surname = StringField.new(prediction['surname'], page_id)
-          end
-
-          # @return [String]
-          def to_s
-            given_names = @given_names.join("\n #{' ' * 15}")
-            out_str = String.new
-            out_str << "\n:Given Name(s): #{given_names}".rstrip
-            out_str << "\n:Surname: #{@surname}".rstrip
-            out_str << "\n:Social Security Number: #{@social_security}".rstrip
-            out_str << "\n:Issuance Date: #{@issuance_date}".rstrip
-            out_str[1..].to_s
-          end
-        end
-      end
-    end
-  end
-end

data/lib/mindee/product/fr/carte_vitale/carte_vitale_v1_page.rb

@@ -1,34 +0,0 @@
-# frozen_string_literal: true
-
-require_relative '../../../parsing'
-require_relative 'carte_vitale_v1_document'
-
-module Mindee
-  module Product
-    module FR
-      module CarteVitale
-        # Carte Vitale API version 1.1 page data.
-        class CarteVitaleV1Page < Mindee::Parsing::Common::Page
-          # @param prediction [Hash]
-          def initialize(prediction)
-            super(prediction)
-            @prediction = CarteVitaleV1PagePrediction.new(
-              prediction['prediction'],
-              prediction['id']
-            )
-          end
-        end
-
-        # Carte Vitale V1 page prediction.
-        class CarteVitaleV1PagePrediction < CarteVitaleV1Document
-          # @return [String]
-          def to_s
-            out_str = String.new
-            out_str << "\n#{super}"
-            out_str
-          end
-        end
-      end
-    end
-  end
-end