array_trie 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: c5ee196913bc37a7c274bc7d36689a40d19838a6
+  data.tar.gz: b4a0dc46652a9964f29db20def6b0d648407c933
+SHA512:
+  metadata.gz: 4694fea10a3c317b20e026deb9ff1dd57fe6640b038b6d79622dc8ee8cc9713f87a6b79555627a01cd8c3df104a357826428f01ff45a2b534fee63ec96cd2b8e
+  data.tar.gz: 0258d42deceb72fc9c0df2c97c4b3212b0573291359554040be3775aa48a170a61513d04a62b2f6c42d868c3d75dded782fbe2a35d02e47a51a87aa5c22c6da4

data/.gitignore

@@ -0,0 +1,9 @@
+/.bundle/
+/.yardoc
+/Gemfile.lock
+/_yardoc/
+/coverage/
+/doc/
+/pkg/
+/spec/reports/
+/tmp/

data/.rspec

@@ -0,0 +1 @@
+--require spec_helper

data/Gemfile

@@ -0,0 +1,6 @@
+source "https://rubygems.org"
+
+git_source(:github) {|repo_name| "https://github.com/#{repo_name}" }
+
+# Specify your gem's dependencies in array_trie.gemspec
+gemspec

data/README.md

@@ -0,0 +1,35 @@
+# ArrayTrie
+
+Welcome to your new gem! In this directory, you'll find the files you need to be able to package up your Ruby library into a gem. Put your Ruby code in the file `lib/array_trie`. To experiment with that code, run `bin/console` for an interactive prompt.
+
+TODO: Delete this and the text above, and describe your gem
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'array_trie'
+```
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install array_trie
+
+## Usage
+
+TODO: Write usage instructions here
+
+## Development
+
+After checking out the repo, run `bin/setup` to install dependencies. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
+
+To install this gem onto your local machine, run `bundle exec rake install`. To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release`, which will create a git tag for the version, push git commits and tags, and push the `.gem` file to [rubygems.org](https://rubygems.org).
+
+## Contributing
+
+Bug reports and pull requests are welcome on GitHub at https://github.com/justjake/array_trie.

data/Rakefile

@@ -0,0 +1,2 @@
+require "bundler/gem_tasks"
+task :default => :spec

data/array_trie.gemspec

@@ -0,0 +1,32 @@
+# coding: utf-8
+lib = File.expand_path("../lib", __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require "array_trie/version"
+
+Gem::Specification.new do |spec|
+  spec.name          = "array_trie"
+  spec.version       = ArrayTrie::VERSION
+  spec.authors       = ["Jake Teton-Landis"]
+  spec.email         = ["jake.tl@airbnb.com"]
+
+  spec.summary       = <<-EOS
+Trie-like, prefix-tree data structures that maps from ordered keys to values.
+  EOS
+  spec.description   = <<-EOS
+Trie-like, prefix-tree data structures. First, a prefix-tree based on Arrays, which differs from a traditional trie, which maps strings to values. Second, a more general prefix-tree data structure that works for any type of keys, provided those keys can be transformed to and from an array.
+
+Both of these data structures are implemented in terms of hashes.
+  EOS
+  spec.homepage      = "https://github.com/justjake/array-trie"
+
+  spec.files         = `git ls-files -z`.split("\x0").reject do |f|
+    f.match(%r{^(test|spec|features)/})
+  end
+  spec.bindir        = "exe"
+  spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
+  spec.require_paths = ["lib"]
+
+  spec.add_development_dependency "bundler", "~> 1.15"
+  spec.add_development_dependency "rake", "~> 10.0"
+  spec.add_development_dependency "rspec", "~> 3.7"
+end

data/bin/console

@@ -0,0 +1,14 @@
+#!/usr/bin/env ruby
+
+require "bundler/setup"
+require "array_trie"
+
+# You can add fixtures and/or initialization code here to make experimenting
+# with your gem easier. You can also use a different console, if you like.
+
+# (If you use this, don't forget to add pry to your Gemfile!)
+# require "pry"
+# Pry.start
+
+require "irb"
+IRB.start(__FILE__)

data/bin/setup

@@ -0,0 +1,8 @@
+#!/usr/bin/env bash
+set -euo pipefail
+IFS=$'\n\t'
+set -vx
+
+bundle install
+
+# Do any other automated setup that you need to do here

data/bin/test

@@ -0,0 +1,6 @@
+#!/usr/bin/env bash
+set -euo pipefail
+IFS=$'\n\t'
+set -vx
+
+bundle exec rspec "$@"

data/lib/array_trie.rb

@@ -0,0 +1,198 @@
+# ArrayTrie is a trie-like, prefix-tree data structure that maps from arrays to
+# values. This differs from a traditional trie, which maps strings to values.
+#
+# ArrayTrie is implemented in terms of Ruby hashes, so members of your array
+# keys must behave by Ruby's hash contracts:
+# https://ruby-doc.org/core-2.3.1/Hash.html#class-Hash-label-Hash+Keys
+#
+# If you wish to construct a prefix tree with non-Array keys, please see
+# {ArrayTrie::PrefixTrie}, which can map arbitrary keys to values, so long as
+# your keys can be converted to and from arrays.
+class ArrayTrie
+  # Just a unique marker value.
+  # Using Class.new is better than using Object.new, because it makes sense
+  # when inspected.
+  #
+  # @api private
+  STOP = Class.new
+
+  def initialize(root = {})
+    @root = root
+  end
+
+  # Retrieve a value for the given key
+  #
+  # @param parts [Array]
+  # @return [Any] the previously stored value
+  # @return [nil] if the given key was not found
+  def [](parts)
+    last_node, remaining = traverse(@root, parts)
+    return nil unless remaining.empty?
+    last_node[STOP]
+  end
+
+  # Set a key to a value
+  #
+  # @param parts [Array] the key
+  # @param value [Any] the value
+  def []=(parts, value)
+    last_node, * = traverse(@root, parts, true)
+    last_node[STOP] = value
+  end
+
+  # insert a subtrie into this trie.
+  #
+  # @param parts [Array]
+  # @param trie [ArrayTrie]
+  # @return self
+  def insert_subtrie(parts, trie)
+    raise ArgumentError.new("trie must be a trie") unless trie.is_a? self.class
+    raise ArgumentError.new("cannot insert a subtrie at the root") if parts.empty?
+    parent, * = traverse(@root, parts[0...-1], true)
+    parent[parts.last] = trie.root
+    self
+  end
+
+  # Retrieve a view into this trie at the given key. Underlying data storage is
+  # shared with the subtrie.
+  #
+  # @param parts [Array]
+  # @return [ArrayTrie]
+  def subtrie(parts)
+    last_node, remaining = traverse(@root, parts)
+    return nil unless remaining.empty?
+    self.class.new(last_node)
+  end
+
+  # Returns true if this array is a key in this trie.
+  #
+  # @param parts [Array]
+  # @return [Boolean]
+  def include?(parts)
+    last_node, remaining = traverse(@root, parts)
+    return false unless remaining.empty?
+    last_node.key?(STOP)
+  end
+
+  # Returns true if this array is a prefix of an array in this trie
+  #
+  # @param parts [Array]
+  # @return [Boolean]
+  def include_prefix?(parts)
+    _, remaining = traverse(@root, parts)
+    remaining.empty?
+  end
+
+  # @return [Integer] Number of keys under the given prefix
+  def count_prefix(parts)
+    trie = subtrie(parts)
+    trie ? trie.count : 0
+  end
+
+  # @return [Enumerator] a depth-first enumerator
+  def depth_first
+    enum = depth_first_enumerator(@root)
+    return enum unless block_given?
+    enum.each { |path, value| yield(path, value) }
+  end
+
+  # @return [Enumerator] a breadth-first enumerator
+  def breadth_first
+    enum = breadth_first_enumerator(@root)
+    return enum unless block_given?
+    enum.each { |path, value| yield(path, value) }
+  end
+
+  # Count the number of key-value pairs in this trie.
+  #
+  # @return [Integer]
+  def count
+    breadth_first.count
+  end
+
+  protected
+
+  attr_reader :root
+
+  private
+
+  def depth_first_enumerator(node, current_path = [])
+    ::Enumerator.new do |y|
+      depth_first_scan(node, current_path) { |path, value| y.yield(path, value) }
+    end
+  end
+
+  def breadth_first_enumerator(node, start_path = [])
+    ::Enumerator.new do |y|
+      breadth_first_scan(node, start_path) { |path, value| y.yield(path, value) }
+    end
+  end
+
+  # recursive version was just too much easier
+  def depth_first_scan(current_node, current_path = [], &block)
+    if current_node.key?(STOP)
+      yield(current_path, current_node[STOP])
+    end
+
+    current_node.each do |key, value|
+      # already handled
+      next if key == STOP
+
+      # recurse
+      depth_first_scan(value, current_path + [key], &block)
+    end
+  end
+
+  def breadth_first_scan(node, start_path = [])
+    raise ::ArgumentError.new('block required') unless block_given?
+
+    queue = [ [node, start_path] ]
+    loop do
+      break if queue.empty?
+      current_node, current_path = queue.shift
+
+      if current_node.key?(STOP)
+        yield(current_path, current_node[STOP])
+      end
+
+      current_node.each do |key, value|
+        next if key == STOP
+        queue << [value, current_path + [key]]
+      end
+    end
+  end
+
+  # traverse from node `start`, to the node at path `parts`
+  #
+  # traversals are best-effort, and return the furthest node they can
+  # reach, and the remaining parts of the traversal path.
+  def traverse(start, parts, inserting = false)
+    assert_is_array!(parts)
+
+    if parts.empty?
+      return [start, []]
+    end
+
+    current_node = start
+    parts.each_with_index do |part, index|
+      if inserting
+        next_node = current_node[part] ||= {}
+      else
+        next_node = current_node[part]
+        return [current_node, parts[index..-1]] unless next_node
+      end
+
+      if index == parts.length - 1
+        return [next_node, []]
+      end
+
+      current_node = next_node
+    end
+  end
+
+  def assert_is_array!(parts)
+    unless parts.is_a?(::Array)
+      raise ::ArgumentError.new("key must be an array, instead is #{parts.inspect}")
+    end
+  end
+end

data/lib/array_trie/prefix_trie.rb

@@ -0,0 +1,130 @@
+class ArrayTrie
+  # A trie-like, prefix-tree data structure that maps arbitrary keys to values,
+  # provided that the keys may be transformed to and from arrays, as each
+  # instance uses an underlying {ArrayTrie} instance for storage.
+  #
+  # If you only care about trie membership, just map your values to `true`. If
+  # your trie keys are already arrays, you can use {ArrayTrie}
+  # directly for improved performance.
+  class PrefixTrie
+    # Create a new Trie for mapping paths to values. This could be useful for
+    # storing a large amount of paths-to-data mappings, and querying the trie
+    # based on path prefix.
+    #
+    # @return [PrefixTrie]
+    def self.of_paths
+      of_strings_split_by('/')
+    end
+
+    # Create a new trie for mapping strings to values. This could be useful
+    #
+    # @return [PrefixTrie]
+    def self.of_strings
+      of_strings_split_by('')
+    end
+
+    # Create a trie for mapping delimited strings to values.
+    # String keys will be split by the delimiter for storage.
+    #
+    # @return [PrefixTrie]
+    def self.of_strings_split_by(delim)
+      new(
+        proc { |str| str.split(delim) },
+        proc { |parts| parts.join(delim) }
+      )
+    end
+
+    # Create a new trie for mapping arrays to values.
+    #
+    # @return [PrefixTrie]
+    def self.of_arrays
+      new(
+        proc { |x| x },
+        proc { |x| x }
+      )
+    end
+
+    # Create a new Trie
+    #
+    # @param to_a [#call] A callable that given a key, returns that key as an
+    #   array.
+    # @param from_a [#call] Inverse of to_a. A callable that given an array,
+    #   returns the key form of that array.
+    # @param trie [ArrayTrie] (ArrayTrie.new) Underlying trie to use for storage.
+    def initialize(to_a, from_a, trie = ArrayTrie.new)
+      @to_a = to_a
+      @from_a = from_a
+      @trie = trie
+    end
+
+    def [](key)
+      @trie[to_a(key)]
+    end
+
+    def []=(key, value)
+      @trie[to_a(key)] = value
+    end
+
+    def insert_subtrie(key, subtrie)
+      @trie.insert_subtrie(to_a(key), subtrie.trie)
+    end
+
+    def subtrie(key)
+      lower_subtrie = @trie.subtrie(to_a(key))
+      return nil unless lower_subtrie
+      self.class.new(@to_a, @from_a, lower_subtrie)
+    end
+
+    def include?(key)
+      @trie.include?(to_a key)
+    end
+
+    def include_prefix?(key)
+      @trie.include_prefix?(to_a key)
+    end
+
+    def count_prefix(key)
+      @trie.count_prefix(to_a key)
+    end
+
+    def depth_first
+      enum = transform_enumerator(@trie.depth_first)
+      return enum unless block_given?
+      enum.each { |path, value| yield(path, value) }
+    end
+
+    def breadth_first
+      enum = transform_enumerator(@trie.breadth_first)
+      return enum unless block_given?
+      enum.each { |path, value| yield(path, value) }
+    end
+
+    def count
+      @trie.count
+    end
+
+    protected
+
+    attr_reader :trie
+
+    private
+
+    def transform_enumerator(enum)
+      ::Enumerator.new do |y|
+        loop do
+          parts, value = enum.next
+          y.yield(from_a(parts), value)
+        end
+      end
+    end
+
+    def to_a(key)
+      @to_a.call(key)
+    end
+
+    def from_a(parts)
+      @from_a.call(parts)
+    end
+  end
+end
+

data/lib/array_trie/version.rb

@@ -0,0 +1,3 @@
+class ArrayTrie
+  VERSION = "0.1.0"
+end

metadata

@@ -0,0 +1,100 @@
+--- !ruby/object:Gem::Specification
+name: array_trie
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Jake Teton-Landis
+autorequire: 
+bindir: exe
+cert_chain: []
+date: 2017-11-16 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.15'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.15'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '10.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '10.0'
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '3.7'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '3.7'
+description: |
+  Trie-like, prefix-tree data structures. First, a prefix-tree based on Arrays, which differs from a traditional trie, which maps strings to values. Second, a more general prefix-tree data structure that works for any type of keys, provided those keys can be transformed to and from an array.
+
+  Both of these data structures are implemented in terms of hashes.
+email:
+- jake.tl@airbnb.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- .gitignore
+- .rspec
+- Gemfile
+- README.md
+- Rakefile
+- array_trie.gemspec
+- bin/console
+- bin/setup
+- bin/test
+- lib/array_trie.rb
+- lib/array_trie/prefix_trie.rb
+- lib/array_trie/version.rb
+homepage: https://github.com/justjake/array-trie
+licenses: []
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.6.10
+signing_key: 
+specification_version: 4
+summary: Trie-like, prefix-tree data structures that maps from ordered keys to values.
+test_files: []