sec_id 7.1.0 → 8.0.0

data/lib/sec_id/concerns/normalizable.rb

@@ -8,6 +8,10 @@ module SecID
     # Characters stripped during normalization (whitespace and hyphens); classes may override.
     SEPARATORS = /[\s-]/
 
+    # Extends the including identifier class with the concern's class methods.
+    #
+    # @param base [Class] the identifier class including this concern
+    # @return [void]
     # @api private
     def self.included(base)
       base.extend(ClassMethods)

data/lib/sec_id/concerns/suggestable.rb

@@ -7,7 +7,8 @@ module SecID
   #
   # Included by the 9 checksum types. The candidate space is the human-error net —
   # {HOMOGLYPHS} plus adjacent transpositions — never a full coincidental net. `valid?`
-  # is the oracle, so no false candidate ever escapes; the {HOMOGLYPHS} table bounds recall.
+  # is the oracle, so no checksum-invalid candidate ever escapes (a valid candidate is not
+  # necessarily the intended correction); the {HOMOGLYPHS} table bounds recall.
   #
   # @see SecID::Suggestion
   #
@@ -30,6 +31,10 @@ module SecID
     # then the checksum-recompute fallback last (R6/R7).
     RANK = { substitution: 0, transposition: 1, checksum: 2 }.freeze
 
+    # Extends the including identifier class with the concern's class methods.
+    #
+    # @param base [Class] the identifier class including this concern
+    # @return [void]
     # @api private
     def self.included(base)
       base.extend(ClassMethods)

data/lib/sec_id/concerns/validatable.rb

@@ -18,6 +18,10 @@ module SecID
       invalid_country: InvalidStructureError
     }.freeze
 
+    # Extends the including identifier class with the concern's class methods.
+    #
+    # @param base [Class] the identifier class including this concern
+    # @return [void]
     # @api private
     def self.included(base)
       base.extend(ClassMethods)

data/lib/sec_id/cusip.rb

@@ -61,7 +61,7 @@ module SecID
     # @raise [InvalidFormatError] if the CUSIP format is invalid
     def calculate_checksum
       validate_format_for_calculation!
-      mod10(luhn_sum_double_add_double(reversed_digits_single(identifier)))
+      mod10(luhn_sum_single(identifier))
     end
 
     # Generates a random CUSIP body: 8 alphanumeric characters.

data/lib/sec_id/detector.rb

@@ -19,7 +19,7 @@ module SecID
   class Detector
     # @param identifier_list [Array<Class>] registered identifier classes
     def initialize(identifier_list)
-      @classes = identifier_list.dup.freeze
+      @classes = identifier_list.sort_by(&:detection_priority).freeze
       precompute
     end
 
@@ -33,7 +33,7 @@ module SecID
 
       upcased = input.upcase
       candidates = filter_candidates(upcased)
-      validate_and_sort(input, candidates)
+      valid_types(input, candidates)
     end
 
     # Returns whether any registered type matches, short-circuiting on the first
@@ -57,8 +57,11 @@ module SecID
       return if input.empty?
 
       candidates = filter_candidates(input.upcase)
-      matches = candidates.filter_map { |klass| (i = klass.new(input)).valid? ? i : nil }
-      matches.min_by { |instance| instance.class.detection_priority }
+      candidates.each do |klass|
+        instance = klass.new(input)
+        return instance if instance.valid?
+      end
+      nil
     end
 
     private
@@ -74,14 +77,13 @@ module SecID
       stage3_charset(upcased, candidates)
     end
 
-    # Validates candidates and returns sorted symbol keys.
+    # Validates candidates in precomputed specificity order.
     #
     # @param input [String]
     # @param candidates [Array<Class>]
     # @return [Array<Symbol>]
-    def validate_and_sort(input, candidates)
+    def valid_types(input, candidates)
       matches = candidates.select { |klass| klass.valid?(input) }
-      matches.sort_by!(&:detection_priority)
       matches.map!(&:type_key)
     end
 
@@ -105,11 +107,12 @@ module SecID
     #
     # @return [void]
     def build_length_table
-      @candidates_by_length = Hash.new { |h, k| h[k] = [] }
+      @candidates_by_length = {}
       @classes.each do |klass|
-        klass.length_values.each { |len| @candidates_by_length[len] << klass }
+        klass.length_values.each { |len| (@candidates_by_length[len] ||= []) << klass }
       end
       @candidates_by_length.each_value(&:freeze)
+      @candidates_by_length.default = [].freeze
     end
 
     # Stage 1: route strings with special characters to the only types that accept them.
@@ -130,7 +133,7 @@ module SecID
     # @param length [Integer]
     # @return [Array<Class>]
     def stage2_length(length)
-      @candidates_by_length[length] || []
+      @candidates_by_length[length]
     end
 
     # Stage 3: filter candidates by character set.

data/lib/sec_id/figi.rb

@@ -69,7 +69,7 @@ module SecID
     # @raise [InvalidFormatError] if the FIGI format is invalid
     def calculate_checksum
       validate_format_for_calculation!
-      mod10(luhn_sum_indexed(reversed_digits_single(identifier)))
+      mod10(luhn_sum_single(identifier, double_first: false))
     end
 
     # Generates a random FIGI body: non-reserved 2-char prefix + 'G' + 8-char random part.

data/lib/sec_id/iban/country_rules.rb

@@ -1,7 +1,7 @@
 # frozen_string_literal: true
 
 module SecID
-  # rubocop:disable Metrics/ClassLength
+  # rubocop:disable-next Metrics/ClassLength
   class IBAN < Base
     # Country-specific BBAN rules for EU/EEA countries
     # Each entry defines:
@@ -265,5 +265,4 @@ module SecID
       'XK' => 16  # Kosovo
     }.freeze
   end
-  # rubocop:enable Metrics/ClassLength
 end

data/lib/sec_id/iban.rb

@@ -226,7 +226,7 @@ module SecID
 
     # @return [String] the numeric string representation
     def numeric_string_for_check
-      "#{bban}#{country_code}00".each_char.map { |char| CHAR_TO_DIGIT.fetch(char) }.join
+      "#{bban}#{country_code}00".gsub(/[^0-9]/) { |char| DECIMAL_VALUES.fetch(char) }
     end
   end
 end

data/lib/sec_id/isin.rb

@@ -86,7 +86,7 @@ module SecID
     # @raise [InvalidFormatError] if the ISIN format is invalid
     def calculate_checksum
       validate_format_for_calculation!
-      mod10(luhn_sum_standard(reversed_digits_multi(identifier)))
+      mod10(luhn_sum_standard(identifier))
     end
 
     # Generates a random ISIN body: 2-letter country code + 9-character NSIN.

data/lib/sec_id/lei.rb

@@ -90,7 +90,7 @@ module SecID
 
     # @return [String] the numeric string representation
     def numeric_identifier
-      identifier.each_char.map { |char| CHAR_TO_DIGIT.fetch(char) }.join
+      identifier.each_char.with_object(+'') { |char, numeric| numeric << DECIMAL_VALUES.fetch(char) }
     end
   end
 end

data/lib/sec_id/scanner.rb

@@ -73,7 +73,7 @@ module SecID
       @classes.each do |klass|
         klass.length_values.each { |len| @candidates_by_length[len] << klass }
       end
-      @candidates_by_length.each_value(&:freeze)
+      @candidates_by_length.each_value { |classes| classes.sort_by!(&:detection_priority).freeze }
     end
 
     # @param input [String]
@@ -118,18 +118,23 @@ module SecID
       return unless best
 
       end_pos = start_pos + raw.length
-      Match.new(type: best.type_key, raw: raw, range: start_pos...end_pos, identifier: best.new(cleaned))
+      Match.new(type: best.class.type_key, raw: raw, range: start_pos...end_pos, identifier: best)
     end
 
-    # @return [Class, nil]
+    # @return [Base, nil]
     def best_match(cleaned, classes)
       return if classes.empty?
 
-      candidates = (@candidates_by_length[cleaned.length] || []) & classes
-      return if candidates.empty?
+      candidates = @candidates_by_length[cleaned.length]
+      return unless candidates
 
-      validated = candidates.select { |k| cleaned.match?(k::VALID_CHARS_REGEX) && k.valid?(cleaned) }
-      validated.min_by(&:detection_priority)
+      candidates.each do |klass|
+        next unless classes.include?(klass) && cleaned.match?(klass::VALID_CHARS_REGEX)
+
+        instance = klass.new(cleaned)
+        return instance if instance.valid?
+      end
+      nil
     end
   end
 end

data/lib/sec_id/suggestion.rb

@@ -46,11 +46,15 @@ module SecID
     # The non-nil confidence tiers `confidence` can take; `:checksum` candidates carry `nil`.
     CONFIDENCE_LEVELS = %i[high medium].freeze
 
+    # Returns a JSON-compatible hash representation of the suggestion.
+    #
     # @return [Hash] the symbol-keyed field hash (JSON-compatible)
     def as_json(*)
       to_h
     end
 
+    # Returns the corrected identifier as a string.
+    #
     # @return [String] the corrected identifier string
     def to_s
       identifier.to_s

data/lib/sec_id/version.rb

@@ -2,5 +2,5 @@
 
 module SecID
   # Current gem version.
-  VERSION = '7.1.0'
+  VERSION = '8.0.0'
 end

data/lib/sec_id.rb

@@ -158,7 +158,9 @@ module SecID
       input = str.to_s.strip.upcase
       suggestable_types(input, types)
         .flat_map { |klass| klass.suggest(input) }
-        .sort_by { |suggestion| [Suggestable::RANK.fetch(suggestion.edit), self[suggestion.type].detection_priority.last] }
+        .sort_by do |suggestion|
+          [Suggestable::RANK.fetch(suggestion.edit), self[suggestion.type].detection_priority.last]
+        end
     end
 
     private

data/sec_id.gemspec

@@ -10,7 +10,7 @@ Gem::Specification.new do |spec|
   spec.authors       = ['Leonid Svyatov']
   spec.email         = ['leonid@svyatov.ru']
 
-  spec.summary       = 'A Ruby toolkit for securities identifiers — validate, parse, normalize, detect, convert, ' \
+  spec.summary       = 'A Ruby toolkit for securities identifiers: validate, parse, normalize, detect, convert, ' \
                        'generate, classify, and repair.'
   spec.description   = 'Validate, normalize, parse, convert, generate, classify, and repair securities identifiers. ' \
                        'Auto-detect identifier type from any string. Calculate and restore checksums. Suggest ' \
@@ -22,7 +22,7 @@ Gem::Specification.new do |spec|
   spec.homepage      = 'https://github.com/svyatov/sec_id'
   spec.license       = 'MIT'
 
-  spec.required_ruby_version = '>= 3.2.0'
+  spec.required_ruby_version = '>= 3.3.0'
 
   spec.require_paths = ['lib']
   spec.files = Dir['lib/**/*.rb'] + Dir['sig/**/*'] +

data/sig/sec_id/cfi/attribute_set.rbs

@@ -12,8 +12,8 @@ module SecID
               | () -> Enumerator[Field, self]
       def []: (Symbol meaning) -> Field?
       def empty?: () -> bool
-      def to_h: () -> Hash[untyped, untyped]
-      def as_json: (*untyped) -> Hash[Symbol, untyped]
+      def to_h: () -> Hash[Symbol, Hash[Symbol, untyped]]
+      def as_json: (*untyped) -> Hash[Symbol, Hash[Symbol, untyped]]
 
       # Per-meaning readers — the union of every attribute meaning. Each instance
       # only answers the meanings actually present; an absent one raises

data/sig/sec_id/concerns/checkable.rbs

@@ -1,8 +1,10 @@
 module SecID
   # Provides checksum validation and calculation for identifiers with a checksum.
   module Checkable : SecID::Base
-    CHAR_TO_DIGITS: Hash[String, Integer | Array[Integer]]
     CHAR_TO_DIGIT: Hash[String, Integer]
+    BYTE_TO_DIGIT: Hash[Integer, Integer]
+    DECIMAL_VALUES: Hash[String, String]
+    LUHN_DOUBLE: Array[Integer]
 
     def self.included: (Module base) -> void
 
@@ -33,11 +35,10 @@ module SecID
 
     private
 
-    def luhn_sum_double_add_double: (Array[Integer] digits) -> Integer
-    def luhn_sum_indexed: (Array[Integer] digits) -> Integer
-    def luhn_sum_standard: (Array[Integer] digits) -> Integer
-    def reversed_digits_single: (untyped id) -> Array[Integer]
-    def reversed_digits_multi: (untyped id) -> Array[Integer]
+    # Readers are nilable before validation. The callers validate first; local
+    # annotations keep the byte traversal typed without adding runtime guards.
+    def luhn_sum_single: (untyped id, ?double_first: bool) -> Integer
+    def luhn_sum_standard: (untyped id) -> Integer
     def error_codes: () -> Array[Symbol]
     def checksum_width: () -> Integer
     def validation_message: (Symbol code) -> String?

data/sig/sec_id/detector.rbs

@@ -11,7 +11,7 @@ module SecID
     private
 
     def filter_candidates: (String upcased) -> Array[singleton(Base)]
-    def validate_and_sort: (String input, Array[untyped] candidates) -> Array[Symbol]
+    def valid_types: (String input, Array[untyped] candidates) -> Array[Symbol]
     def precompute: () -> void
     def build_discriminator_sets: () -> void
     def build_length_table: () -> void

data/sig/sec_id/scanner.rbs

@@ -33,7 +33,7 @@ module SecID
     def scan_text: (String input, Array[singleton(Base)] target_classes) { (Match) -> void } -> void
     def identify_candidate: (untyped match_data, Array[singleton(Base)] target_classes) -> Match?
     def try_classes: (String raw, String cleaned, Integer start_pos, Array[singleton(Base)] classes) -> Match?
-    def best_match: (String cleaned, Array[singleton(Base)] classes) -> singleton(Base)?
+    def best_match: (String cleaned, Array[singleton(Base)] classes) -> Base?
 
     @classes: Array[singleton(Base)]
     @fisn_classes: Array[singleton(Base)]

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: sec_id
 version: !ruby/object:Gem::Version
-  version: 7.1.0
+  version: 8.0.0
 platform: ruby
 authors:
 - Leonid Svyatov
@@ -119,15 +119,15 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: 3.2.0
+      version: 3.3.0
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 4.0.12
+rubygems_version: 4.0.20
 specification_version: 4
-summary: A Ruby toolkit for securities identifiers — validate, parse, normalize, detect,
-  convert, generate, classify, and repair.
+summary: 'A Ruby toolkit for securities identifiers: validate, parse, normalize, detect,
+  convert, generate, classify, and repair.'
 test_files: []