Last active
February 7, 2016 17:03
-
-
Save qwtel/428d8dcced808de18464 to your computer and use it in GitHub Desktop.
find words in an input, lower-case only, brute force
This file contains hidden or 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
(ns goog | |
(:require [clojure.string :as str])) | |
(def words-by-count (->> (slurp "/usr/share/dict/words" :encoding "ASCII") | |
str/split-lines | |
(map str/lower-case) | |
distinct | |
(map seq) | |
(group-by count))) | |
(def shortest-word 3) | |
(def longest-word (apply max (keys words-by-count))) | |
(defn find-words [input] | |
(for [i (range shortest-word (inc longest-word)) | |
[pos part] (map-indexed vector (partition i 1 input)) | |
word (get words-by-count i) | |
:when (= part word) | |
:let [str-word (apply str word)]] | |
[pos str-word])) | |
(def example-input | |
"ectintidaticavivestrianobsconthericarverantiontedistressinessupitousnesterworticshnomorolditicatomba") | |
(find-words example-input) | |
; => ([2 "tin"] | |
; [5 "tid"] | |
; [6 "ida"] | |
; [8 "ati"] | |
; [9 "tic"] | |
; [18 "tri"] | |
; [19 "ria"] | |
; [20 "ian"] | |
; [22 "nob"] | |
; [26 "con"] | |
; [28 "nth"] | |
; [29 "the"] | |
; [30 "her"] | |
; [32 "ric"] | |
; [34 "car"] | |
; [38 "era"] | |
; [39 "ran"] | |
; [40 "ant"] | |
; [43 "ion"] | |
; [46 "ted"] | |
; [48 "dis"] | |
; [49 "ist"] | |
; [53 "ess"] | |
; [54 "ssi"] | |
; [55 "sin"] | |
; [58 "ess"] | |
; [59 "ssu"] | |
; [60 "sup"] | |
; [62 "pit"] | |
; [63 "ito"] | |
; [64 "tou"] | |
; [75 "ort"] | |
; [77 "tic"] | |
; [84 "mor"] | |
; [87 "old"] | |
; [89 "dit"] | |
; [91 "tic"] | |
; [93 "cat"] | |
; [95 "tom"] | |
; [2 "tint"] | |
; [13 "vive"] | |
; [15 "vest"] | |
; [22 "nobs"] | |
; [31 "eric"] | |
; [37 "vera"] | |
; [39 "rant"] | |
; [40 "anti"] | |
; [50 "stre"] | |
; [55 "sine"] | |
; [57 "ness"] | |
; [68 "nest"] | |
; [74 "wort"] | |
; [84 "moro"] | |
; [94 "atom"] | |
; [95 "tomb"] | |
; [13 "vives"] | |
; [17 "stria"] | |
; [31 "erica"] | |
; [34 "carve"] | |
; [51 "tress"] | |
; [69 "ester"] | |
; [12 "avives"] | |
; [34 "carver"] | |
; [50 "stress"] | |
; [68 "nester"] | |
; [48 "distress"]) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment