Created
November 19, 2013 09:56
-
-
Save fl00r/7542994 to your computer and use it in GitHub Desktop.
Trie-like pure fuzzy search implementation on Ruby
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
class TrieDict | |
attr_reader :dict | |
def initialize | |
@dict = {} | |
end | |
def put(str) | |
d = nil | |
str.chars.each do |c| | |
d && (d = (d[1][c] ||= [nil, {}])) || d = (@dict[c] ||= [nil, {}]) | |
end | |
d[0] = true | |
end | |
def fetch(prefix, fuzzy = 0) | |
storage = [] | |
str = "" | |
error = 0 | |
recur_fetch(prefix, fuzzy, @dict, storage, str, error) | |
storage | |
end | |
def recur_fetch(prefix, fuzzy, dict, storage, str, error) | |
dict.each do |k, vals| | |
e = error | |
if prefix[0] != k | |
e += 1 | |
next if e > fuzzy | |
end | |
s = str + k | |
storage << s if vals[0] && (prefix.size - 1) <= (fuzzy - e) | |
recur_fetch(prefix[1..-1] || "", fuzzy, vals[1], storage, s, e) | |
end | |
end | |
end | |
def bench | |
t = Time.now.to_f | |
res = nil | |
10.times{ res = yield } | |
e = Time.now.to_f - t | |
puts "Elapsed for 10 times: #{e}" | |
puts "Result: #{res}" | |
end | |
trie = TrieDict.new | |
# http://www.infochimps.com/datasets/word-list-100000-official-crossword-words-excel-readable/downloads/195488 | |
File.read("/home/petr/code/tmp/words.txt").each_line do |word| | |
trie.put(word.strip) | |
end; :ok | |
# Elapsed for 10 times: 0.0006465911865234375 | |
# Result: ["hello"] | |
bench{ trie.fetch "hello", 1 } | |
# Elapsed for 10 times: 0.013643741607666016 | |
# Result: ["cello", "hallo", "helio", "hell", "hello", "hellos", "hells", "hillo", "hollo", "hullo"] | |
bench{ trie.fetch "hello", 2 } | |
# Elapsed for 10 times: 0.08267641067504883 | |
# Result: ["bell", "belle", "bellow", "bells", "belly", "cell", "cella", "celli", "cello", "cellos", "cells", "dell", "dells", "delly", "fell", "fella", "felloe", "fellow", "fells", "felly", "hall", "hallo", "halloa", "halloo", "hallos", "hallot", "hallow", "halls", "heal", "heals", "heel", "heels", "heil", "heils", "held", "helio", "helios", "helix", "hell", "helled", "heller", "hello", "helloed", "helloes", "hellos", "hells", "helm", "helms", "helot", "help", "helps", "helve", "herl", "herls", "hill", "hillo", "hilloa", "hillos", "hills", "hilly", "holla", "hollo", "holloa", "holloo", "hollos", "hollow", "holly", "hull", "hullo", "hulloa", "hullos", "hulls", "jell", "jells", "jelly", "mell", "mellow", "mells", "sell", "selle", "sells", "tell", "tells", "telly", "well", "wells", "yell", "yellow", "yells"] | |
bench{ trie.fetch "engineer", 2 } | |
# Elapsed for 10 times: 0.04654884338378906 | |
# Result: ["engender", "engine", "engined", "engineer", "engineered", "engineers", "enginery", "engines"] | |
bench{ trie.fetch "engeneer", 1 } | |
# Elapsed for 10 times: 0.005484580993652344 | |
# Result: ["engender", "engineer"] |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment