indexer101 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: f3987fe6c70a6da37dd0cbcb50bf3368601ee1b6ddc6a90da039d22dfa14f28b
+  data.tar.gz: f7a79a0f09d97948a5576c253c8f2d2e5f58079fdc0830ee4fbeee28c208c3af
+SHA512:
+  metadata.gz: fe696d43cc8c49962e3bb44a6f55497dd178b527d31cde3e395c2b2c1ef984add180fc503ac7f97fb2f4a716e37f785535972e149b3f6ec0cbeaa5698d64b1c9
+  data.tar.gz: e591fdfbec8eb9e579473075dabe554c04f163ffa23548746833d27053e5a55e7ba3514b2cd154acf43e8a4d2124f5cd753dd0bfcaa30697cd04d0e487bec318

data/lib/indexer101.rb

@@ -0,0 +1,177 @@
+#!/usr/bin/env ruby
+
+# file: indexer101.rb
+
+require 'c32'
+require 'thread'
+require 'thwait'
+
+
+class Indexer101
+  using ColouredText
+    
+  class Index
+    
+    attr_reader :h
+    attr_accessor :index    
+    
+    def initialize()          
+    end
+    
+    def build(a)
+      
+      threads = []
+      threads << Thread.new do
+        @index = Hash[a.map(&:to_sym).zip([''] * a.length)]
+      end
+      
+      threads << Thread.new { @h = group a }
+      ThreadsWait.all_waits(*threads)      
+            
+    end
+    
+    def inspect()
+      h = @h ? @h.inspect[0..30] + "..." : nil
+      "#<Indexer101::Index @h=#{h.inspect}>"
+    end
+    
+    private
+
+    def group(a, length=0)
+
+      h = a.group_by {|x| x[0..length]}
+
+      h.each do |key, value|
+
+        if length+1 < value.max.length - 1 then
+          h2 = group value, length + 1      
+          h[key] = h2 unless h2.length < 2 and value.length < 2
+        end
+
+      end
+      
+      h3 = h.inject({}) do |r,x|
+        r.merge(x[0].to_sym => x[-1])
+      end
+
+    end
+    
+  end
+
+  def initialize(filename='indexer.dat', debug: false)
+    
+    @filename, @debug = filename, debug
+    
+    puts
+    puts 'Indexer101'.highlight +  " ready to index".green 
+    puts
+
+    @indexer = Index.new()
+    
+  end
+
+  def build(a)
+    
+    t = Time.now
+    @indexer.build(a)    
+    t2 = Time.now - t
+    
+    puts "%d words indexed".info % a.length
+    puts "index built in %.2f seconds".info % t2 
+    
+    self
+  end
+  
+  def index()
+    @indexer.index
+  end  
+  
+  def read(filename=@filename)
+    
+    t = Time.now
+    
+    File.open(filename) do |f|  
+      @indexer = Marshal.load(f)  
+    end
+    
+    t2 = Time.now - t
+    
+    puts "index contains %d words".info % @indexer.index.length
+    puts "index read in %.2f seconds".info % t2 
+    
+  end
+  
+  def save(filename=@filename)
+
+    File.open(filename, 'w+') do |f|  
+      Marshal.dump(@indexer, f)  
+    end 
+    
+  end
+
+  def search(s, limit: 10)
+
+    t = Time.now
+    a = scan_path s
+    puts ('a: ' + a.inspect[0..100] + '...').debug if @debug
+    
+    i = scan_key @indexer.h, a
+    
+    r = @indexer.h.dig(*a[0..i])
+    puts ('r: ' + r.inspect[0..100] + '...').debug if @debug
+    
+    return r if r.is_a? Array
+    
+    results = scan_leaves(r).sort_by(&:length).take(limit)
+    t2 = Time.now - t
+    puts "search took %.2f seconds" % t2 if @debug
+    
+    return results
+    
+  end
+
+  private
+
+  def scan_key(h, keys, index=0)
+
+    r = h.fetch keys[index]
+
+    puts ('r: ' + r.inspect[0..100] + '...').debug if @debug
+    
+    if r.is_a?(Hash) and index+1 < keys.length and r.fetch keys[index+1] then
+      scan_key r, keys, index+1
+    else
+      index
+    end 
+
+  end
+  
+  def scan_leaves(h)
+
+    h.inject([]) do |r,x|
+      key, value = x
+
+      if value.is_a? Array then
+        r += value 
+      else
+        r += scan_leaves value
+      end
+
+      r
+    end
+  end
+
+  def scan_path(s, length=0)
+    
+    puts 'inside scan_path'.info if @debug
+    
+    r = [s[0..length].to_sym]
+    
+    if length < s.length - 1 then
+      r += scan_path(s, length+1)
+    else
+      r
+    end
+  end
+
+end

metadata

@@ -0,0 +1,91 @@
+--- !ruby/object:Gem::Specification
+name: indexer101
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- James Robertson
+autorequire: 
+bindir: bin
+cert_chain:
+- |
+  -----BEGIN CERTIFICATE-----
+  MIIEXjCCAsagAwIBAgIBATANBgkqhkiG9w0BAQsFADAsMSowKAYDVQQDDCFnZW1t
+  YXN0ZXIvREM9amFtZXNyb2JlcnRzb24vREM9ZXUwHhcNMTkxMTExMjI1NjA5WhcN
+  MjAxMTEwMjI1NjA5WjAsMSowKAYDVQQDDCFnZW1tYXN0ZXIvREM9amFtZXNyb2Jl
+  cnRzb24vREM9ZXUwggGiMA0GCSqGSIb3DQEBAQUAA4IBjwAwggGKAoIBgQDEF92R
+  JWEWjPhgU6nIiCKKXtWI9EE8DbqPtU+CnYuUN2BWN7c4dsbaYrU1tVMzxx22G+Of
+  apTIeIGFrq/oqub6nhx+UbnkMAqpmbJS8zTgnwEhFsGHGI2CD9+4OXh5rl36SqqP
+  IGxY7w45KDvuPWA/Htb2aC20cHclJebOjeaMNogpYDByVEjjxtZeiOmIJtJlQSf+
+  YpUviQVTkFJqbSK0WkKsPLQZu29P1zHETkdBvIGlGGDdo13haBW2Hdj9a2INeWcz
+  B+v6nAdnv9fTTvH0GX51XDa/EIisWNELaopHk1Hcx97pZdm92gaICQfdgUHje65s
+  oUDjyynUKE8dq+LAPEq5B1wj3e4BsIOFI5PSvPCMWI5jpbJWBXV6owex9qln22UA
+  lDUEP3COb9/+r6bGNiCBUvUwyy7l/RdmRXPSOYnP8jPcwD/qSVypJYObM+2q68qc
+  5Eg0WqCVdFgpIXzBJPVcxeDJiN6EKmFWr5vJkMwIGz9hhIcitQjjSguk4r8CAwEA
+  AaOBijCBhzAJBgNVHRMEAjAAMAsGA1UdDwQEAwIEsDAdBgNVHQ4EFgQUN0C2lCCv
+  /ATnmYSeZRQfUNpplfwwJgYDVR0RBB8wHYEbZ2VtbWFzdGVyQGphbWVzcm9iZXJ0
+  c29uLmV1MCYGA1UdEgQfMB2BG2dlbW1hc3RlckBqYW1lc3JvYmVydHNvbi5ldTAN
+  BgkqhkiG9w0BAQsFAAOCAYEAXrKEIca0q3x//SBOsv17jkonBSlzwVLIBuXKXX4R
+  f0q3kJw7vWBPJfIVpAcGn6mbx2ziWw3XvG/SMuwIfzitz0pKTapvwbKZFPscqy82
+  KcDxGtJt1cjDHzl0Bm+mgN/MgY+PAj3TcT/osuCc8iTu4+Ib6UxkmOP/uy2svBLs
+  Su2XzGoqd5SKxPpj7IwMOBSVQWrqgWN2B+gdkN0CqjUPVMmiEKuMNjz9Idu36nG/
+  QOPsTlpqBxR+yFbPEP0DlN5X8BRRAsraQZ+LPi7W/bU1fjkvIJxXuUkQD9dMF99+
+  me+6s7PoCJ1yMmc5XfMFmv4WYswC+VqI1EeG0EneAsxRo8MmhWZcokqRE/KUk+ym
+  NlDFqcKPZDaMsdO5dkYvEeguet/iG3XS1u7WKAcZgfhPdiIbue7cAhz9eQpNybe7
+  08cN0E9zjqKINgH/PsZTot+ohuVRLwn6WmHHhb18oUrxt3a0u4/3TNcWOcMeR0F2
+  GeYL+mKGct5bfjn8IZnAJVKY
+  -----END CERTIFICATE-----
+date: 2019-11-11 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: c32
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.2.0
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.2'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.2.0
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.2'
+description: 
+email: james@jamesrobertson.eu
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- lib/indexer101.rb
+homepage: https://github.com/jrobertson/indexer101
+licenses:
+- MIT
+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: []
+rubygems_version: 3.0.3
+signing_key: 
+specification_version: 4
+summary: Experimental gem to search a list of words 1 character at a time. Intended
+  for use as auto suggestion.
+test_files: []