# frozen_string_literal: true
# set.rb - defines the Set class
# Copyright (c) 2002-2020 Akinori MUSHA <knu@iDaemons.org>
# Documentation by Akinori MUSHA and Gavin Sinclair.
# All rights reserved. You can redistribute and/or modify it under the same
# This library provides the Set class, which deals with a collection
# of unordered values with no duplicates. It is a hybrid of Array's
# intuitive inter-operation facilities and Hash's fast lookup.
# The method `to_set` is added to Enumerable for convenience.
# Set implements a collection of unordered values with no duplicates.
# This is a hybrid of Array's intuitive inter-operation facilities and
# Set is easy to use with Enumerable objects (implementing `each`).
# Most of the initializer methods and binary operators accept generic
# Enumerable objects besides sets and arrays. An Enumerable object
# can be converted to Set using the `to_set` method.
# Set uses Hash as storage, so you must note the following points:
# * Equality of elements is determined according to Object#eql? and
# Object#hash. Use Set#compare_by_identity to make a set compare
# its elements by their identity.
# * Set assumes that the identity of each element does not change
# while it is stored. Modifying an element of a set will render the
# set to an unreliable state.
# * When a string is to be stored, a frozen copy of the string is
# stored instead unless the original string is already frozen.
# The comparison operators `<`, `>`, `<=`, and `>=` are implemented as
# shorthand for the {proper_,}{subset?,superset?} methods. The `<=>`
# operator reflects this order, or return `nil` for sets that both
# have distinct elements (`{x, y}` vs. `{x, z}` for example).
# s1 = Set[1, 2] #=> #<Set: {1, 2}>
# s2 = [1, 2].to_set #=> #<Set: {1, 2}>
# s1.add("foo") #=> #<Set: {1, 2, "foo"}>
# s1.merge([2, 6]) #=> #<Set: {1, 2, "foo", 6}>
# s1.subset?(s2) #=> false
# s2.subset?(s1) #=> true
# - Akinori MUSHA <<knu@iDaemons.org>> (current maintainer)
# Creates a new set containing the given objects.
# Set[1, 2] # => #<Set: {1, 2}>
# Set[1, 2, 1] # => #<Set: {1, 2}>
# Set[1, 'c', :s] # => #<Set: {1, "c", :s}>
# Creates a new set containing the elements of the given enumerable
# If a block is given, the elements of enum are preprocessed by the
# Set.new([1, 2]) #=> #<Set: {1, 2}>
# Set.new([1, 2, 1]) #=> #<Set: {1, 2}>
# Set.new([1, 'c', :s]) #=> #<Set: {1, "c", :s}>
# Set.new(1..5) #=> #<Set: {1, 2, 3, 4, 5}>
# Set.new([1, 2, 3]) { |x| x * x } #=> #<Set: {1, 4, 9}>
def initialize(enum = nil, &block) # :yields: o
@hash ||= Hash.new(false)
do_with_enum(enum) { |o| add(block[o]) }
# Makes the set compare its elements by their identity and returns
# self. This method may not be supported by all subclasses of Set.
if @hash.respond_to?(:compare_by_identity)
@hash.compare_by_identity
raise NotImplementedError, "#{self.class.name}\##{__method__} is not implemented"
# Returns true if the set will compare its elements by their
# identity. Also see Set#compare_by_identity.
@hash.respond_to?(:compare_by_identity?) && @hash.compare_by_identity?
def do_with_enum(enum, &block) # :nodoc:
if enum.respond_to?(:each_entry)
enum.each_entry(&block) if block
elsif enum.respond_to?(:each)
enum.each(&block) if block
raise ArgumentError, "value must be enumerable"
@hash = orig.instance_variable_get(:@hash).dup
if Kernel.instance_method(:initialize_clone).arity != 1
def initialize_clone(orig, **options)
@hash = orig.instance_variable_get(:@hash).clone(**options)
def initialize_clone(orig)
@hash = orig.instance_variable_get(:@hash).clone
# Returns the number of elements.
# Returns true if the set contains no elements.
# Removes all elements and returns self.
# set = Set[1, 'c', :s] #=> #<Set: {1, "c", :s}>
# set.clear #=> #<Set: {}>
# Replaces the contents of the set with the contents of the given
# enumerable object and returns self.
# set = Set[1, 'c', :s] #=> #<Set: {1, "c", :s}>
# set.replace([1, 2]) #=> #<Set: {1, 2}>
if enum.instance_of?(self.class)
@hash.replace(enum.instance_variable_get(:@hash))
do_with_enum(enum) # make sure enum is enumerable before calling clear
# Converts the set to an array. The order of elements is uncertain.
# Set[1, 2].to_a #=> [1, 2]
# Set[1, 'c', :s].to_a #=> [1, "c", :s]
# Returns self if no arguments are given. Otherwise, converts the
# set to another with `klass.new(self, *args, &block)`.
# In subclasses, returns `klass.new(self, *args, &block)` unless
def to_set(klass = Set, *args, &block)
return self if instance_of?(Set) && klass == Set && block.nil? && args.empty?
klass.new(self, *args, &block)
def flatten_merge(set, seen = Set.new) # :nodoc:
if seen.include?(e_id = e.object_id)
raise ArgumentError, "tried to flatten recursive Set"
# Returns a new set that is a copy of the set, flattening each
# containing set recursively.
self.class.new.flatten_merge(self)
# Equivalent to Set#flatten, but replaces the receiver with the
# result in place. Returns nil if no modifications were made.
replace(flatten()) if any? { |e| e.is_a?(Set) }
# Returns true if the set contains the given object.
# Note that <code>include?</code> and <code>member?</code> do not test member
# equality using <code>==</code> as do other Enumerables.
# See also Enumerable#include?
# Returns true if the set is a superset of the given set.
when set.instance_of?(self.class) && @hash.respond_to?(:>=)
@hash >= set.instance_variable_get(:@hash)
size >= set.size && set.all? { |o| include?(o) }
raise ArgumentError, "value must be a set"
# Returns true if the set is a proper superset of the given set.
def proper_superset?(set)
when set.instance_of?(self.class) && @hash.respond_to?(:>)
@hash > set.instance_variable_get(:@hash)
size > set.size && set.all? { |o| include?(o) }
raise ArgumentError, "value must be a set"
# Returns true if the set is a subset of the given set.
when set.instance_of?(self.class) && @hash.respond_to?(:<=)
@hash <= set.instance_variable_get(:@hash)
size <= set.size && all? { |o| set.include?(o) }
raise ArgumentError, "value must be a set"
# Returns true if the set is a proper subset of the given set.
when set.instance_of?(self.class) && @hash.respond_to?(:<)
@hash < set.instance_variable_get(:@hash)
size < set.size && all? { |o| set.include?(o) }
raise ArgumentError, "value must be a set"
# Returns 0 if the set are equal,
# -1 / +1 if the set is a proper subset / superset of the given set,
# or nil if they both have unique elements.
return unless set.is_a?(Set)
when -1 then -1 if proper_subset?(set)
when +1 then +1 if proper_superset?(set)
# Returns true if the set and the given set have at least one
# Set[1, 2, 3].intersect? Set[4, 5] #=> false
# Set[1, 2, 3].intersect? Set[3, 4] #=> true
set.is_a?(Set) or raise ArgumentError, "value must be a set"
any? { |o| set.include?(o) }
set.any? { |o| include?(o) }
# Returns true if the set and the given set have no element in
# common. This method is the opposite of `intersect?`.
# Set[1, 2, 3].disjoint? Set[3, 4] #=> false
# Set[1, 2, 3].disjoint? Set[4, 5] #=> true
# Calls the given block once for each element in the set, passing
# the element as parameter. Returns an enumerator if no block is
block or return enum_for(__method__) { size }
# Adds the given object to the set and returns self. Use `merge` to
# add many elements at once.
# Set[1, 2].add(3) #=> #<Set: {1, 2, 3}>
# Set[1, 2].add([3, 4]) #=> #<Set: {1, 2, [3, 4]}>
# Set[1, 2].add(2) #=> #<Set: {1, 2}>
# Adds the given object to the set and returns self. If the
# object is already in the set, returns nil.
# Set[1, 2].add?(3) #=> #<Set: {1, 2, 3}>
# Set[1, 2].add?([3, 4]) #=> #<Set: {1, 2, [3, 4]}>
# Set[1, 2].add?(2) #=> nil
add(o) unless include?(o)
# Deletes the given object from the set and returns self. Use
# `subtract` to delete many items at once.
# Deletes the given object from the set and returns self. If the
# object is not in the set, returns nil.
# Deletes every element of the set for which block evaluates to
# true, and returns self. Returns an enumerator if no block is
block_given? or return enum_for(__method__) { size }
# @hash.delete_if should be faster, but using it breaks the order
# of enumeration in subclasses.
select { |o| yield o }.each { |o| @hash.delete(o) }
# Deletes every element of the set for which block evaluates to
# false, and returns self. Returns an enumerator if no block is
block_given? or return enum_for(__method__) { size }
# @hash.keep_if should be faster, but using it breaks the order of
# enumeration in subclasses.
reject { |o| yield o }.each { |o| @hash.delete(o) }
# Replaces the elements with ones returned by `collect()`.
# Returns an enumerator if no block is given.
block_given? or return enum_for(__method__) { size }
each { |o| set << yield(o) }
# Equivalent to Set#delete_if, but returns nil if no changes were
# made. Returns an enumerator if no block is given.
block or return enum_for(__method__) { size }
# Equivalent to Set#keep_if, but returns nil if no changes were
# made. Returns an enumerator if no block is given.
block or return enum_for(__method__) { size }
# Equivalent to Set#select!
# Merges the elements of the given enumerable object to the set and
if enum.instance_of?(self.class)
@hash.update(enum.instance_variable_get(:@hash))
do_with_enum(enum) { |o| add(o) }
# Deletes every element that appears in the given enumerable object
do_with_enum(enum) { |o| delete(o) }
# Returns a new set built by merging the set and the elements of the
# given enumerable object.
# Set[1, 2, 3] | Set[2, 4, 5] #=> #<Set: {1, 2, 3, 4, 5}>
# Set[1, 5, 'z'] | (1..6) #=> #<Set: {1, 5, "z", 2, 3, 4, 6}>
# Returns a new set built by duplicating the set, removing every
# element that appears in the given enumerable object.
# Set[1, 3, 5] - Set[1, 5] #=> #<Set: {3}>
# Set['a', 'b', 'z'] - ['a', 'c'] #=> #<Set: {"b", "z"}>
# Returns a new set containing elements common to the set and the
# given enumerable object.
# Set[1, 3, 5] & Set[3, 2, 1] #=> #<Set: {3, 1}>
# Set['a', 'b', 'z'] & ['a', 'b', 'c'] #=> #<Set: {"a", "b"}>
each { |o| n.add(o) if enum.include?(o) }
enum.each { |o| n.add(o) if include?(o) }
do_with_enum(enum) { |o| n.add(o) if include?(o) }
# Returns a new set containing elements exclusive between the set
# and the given enumerable object. `(set ^ enum)` is equivalent to
# `((set | enum) - (set & enum))`.
# Set[1, 2] ^ Set[2, 3] #=> #<Set: {3, 1}>