data_structures_rmolinari 0.2.0 → 0.2.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: ea5f3d2fed60234fefe18577985f1e8ae967ecec92ef0812ccaeff0fb81ca392
-  data.tar.gz: e3e59746e8d7e881209a2c3a0e78ea186aa0562d138d7e2b6ed261943f6cb45f
+  metadata.gz: b8d63f6987f160f00ce92f79643f904f95bc230e4a5b60679f4301ecd366622a
+  data.tar.gz: cdc660ab53a0259a79b72ecc3928f640faa7b1251a1bae3baabb1c70bac20d01
 SHA512:
-  metadata.gz: e480ccee258f97479f1768b8f94b65a1c13f3b1e8f15e843c4240adeac555574383ef7de3928a057fd0b6707823cb4eeddee2128a49175c2f671e1526f887c2e
-  data.tar.gz: 30ac4bf22fe37bdfbf4eeccdcdfc2feba23278703957eebf5f9be6c30bb3e68024ccd49ef63c892d78c1fd58b54336a762c86cb107f9f27937222e9baf252ef4
+  metadata.gz: 057d29af42606c7ecc4a78e6c752fa5f7a29b41788f21ca7ede6bab0893d1ba63b6c9dc3e5f3b5747f3912718565d6dfcb5952d189f78b40a6ef77efe95f34c9
+  data.tar.gz: '08f6921ab4b1c7cf84c9fe5624266b7060f4f1d4f1ecc56e3850106b3bb30e0c6b30c3ea808a61939966350118684f3353ccbb628d24b353b35ae865268222d2'

data/lib/data_structures_rmolinari/disjoint_union_internal.rb

@@ -0,0 +1,69 @@
+# A "disjoint set union" that represents a set of elements that belonging to _disjoint_ subsets. Alternatively, this expresses a
+# partion of a fixed set.
+#
+# The data structure provides efficient actions to merge two disjoint subsets, i.e., replace them by their union, and determine if
+# two elements are in the same subset.
+#
+# The elements of the set must be 0, 1, ..., n-1. Client code can map its data to these representatives. The code uses several ideas
+# from Tarjan and van Leeuwen for efficiency
+#
+# See https://en.wikipedia.org/wiki/Disjoint-set_data_structure for a good introduction.
+#
+# - Tarjan, Robert E., van Leeuwen, Jan (1984). "Worst-case analysis of set union algorithms". Journal of the ACM. 31 (2): 245–281.
+class DisjointUnionInternal
+  attr_reader :subset_count
+
+  # @param size the size of the universe, which must be known at the time of construction. The elements 0, 1, ..., size - 1 start
+  #   out in disjoint singleton subsets.
+  def initialize(size)
+    @size = size
+    # Initialize to
+    @d = (0...size).to_a
+    @rank = [0] * size
+
+    @subset_count = size
+  end
+
+  # Declare that e and f are equivalent, i.e., in the same subset. If they are already in the same subset this is a no-op.
+  #
+  # Each argument must be one of 0, 1, ..., size-1.
+  def unite(e, f)
+    check_value(e)
+    check_value(f)
+    raise 'Uniting an element with itself is meaningless' if e == f
+
+    e_root = find(e)
+    f_root = find(f)
+    return if e_root == f_root
+
+    @subset_count -= 1
+    link(e_root, f_root)
+  end
+
+  # The canonical representative of the subset containing e. Two elements d and e are in the same subset exactly when find(d) ==
+  # find(e).
+  # @param e must be one of 0, 1, ..., size-1.
+  # @return (Integer) one of 0, 1, ..., size-1.
+  def find(e)
+    # We implement find with "halving" to shrink the length of paths to the root. See Tarjan and van Leeuwin p 252.
+    x = e
+    x = @d[x] = @d[@d[x]] while @d[@d[x]] != @d[x]
+    @d[x]
+  end
+
+  private def check_value(v)
+    raise "Value must be given and be in (0..#{@size - 1})" unless v && v.between?(0, @size - 1)
+  end
+
+  private def link(e, f)
+    # Choose which way around to do the linking using the element "ranks". See Tarjan and van Leeuwen, p 250.
+    if @rank[e] > @rank[f]
+      @d[f] = e
+    elsif @rank[e] == @rank[f]
+      @d[f] = e
+      @rank[e] += 1
+    else
+      @d[e] = f
+    end
+  end
+end

data/lib/data_structures_rmolinari.rb

@@ -1,4 +1,5 @@
 require_relative 'data_structures_rmolinari/shared'
+require_relative 'data_structures_rmolinari/disjoint_union_internal'
 require_relative 'data_structures_rmolinari/generic_segment_tree_internal'
 require_relative 'data_structures_rmolinari/heap_internal'
 require_relative 'data_structures_rmolinari/max_priority_search_tree_internal'
@@ -11,6 +12,7 @@ module DataStructuresRMolinari
   # Priority Search Trees
   #
   # Note that MinmaxPrioritySearchTree is only a fragment of what we need
+
   MaxPrioritySearchTree = MaxPrioritySearchTreeInternal
   MinmaxPrioritySearchTree = MinmaxPrioritySearchTreeInternal
 
@@ -42,5 +44,11 @@ module DataStructuresRMolinari
 
   ########################################
   # Heap
+
   Heap = HeapInternal
+
+  ########################################
+  # Disjoint Union
+
+  DisjointUnion = DisjointUnionInternal
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: data_structures_rmolinari
 version: !ruby/object:Gem::Version
-  version: 0.2.0
+  version: 0.2.1
 platform: ruby
 authors:
 - Rory Molinari
@@ -72,12 +72,15 @@ description: |
   Sometimes it is not enough to read the description of a data structure and accompanying pseudo-code.
   Actually implementing the structure is often helpful in understanding what is going on. It is also
   usually fun.
+
+  We implement Disjoin Union, Heap, Priority Search Tree, and Segment Tree.
 email: rorymolinari+rubygems@gmail.com
 executables: []
 extensions: []
 extra_rdoc_files: []
 files:
 - lib/data_structures_rmolinari.rb
+- lib/data_structures_rmolinari/disjoint_union_internal.rb
 - lib/data_structures_rmolinari/generic_segment_tree_internal.rb
 - lib/data_structures_rmolinari/heap_internal.rb
 - lib/data_structures_rmolinari/max_priority_search_tree_internal.rb