Created
December 13, 2011 19:07
-
-
Save kalekseev/1473393 to your computer and use it in GitHub Desktop.
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
%Stanford www.ai-class.com. Optional NLP Programming | |
%For test use: | |
%ai1:decode("Esp qtcde nzyqpcpynp zy esp ezatn zq Lcetqtntlw Tyepwwtrpynp hld spwo le Olcexzfes Nzwwprp ty estd jplc."). | |
%corpus test 1: http://simple.wikipedia.org/wiki/Wikipedia:List_of_1000_basic_words | |
%corpus test 2: http://www.wordfrequency.info/files/entriesWithoutCollocates.txt | |
-module(ai1). | |
-export([decode/1]). | |
decode(List) -> | |
{Min, L} = decode(25, List), | |
io:format("~nMinimal cost: ~w String: ~p~n", [Min, L]). | |
decode(0, _) -> {9999999999, "ERROR: set bigger initial cost"}; | |
decode(C, List) -> | |
{Minlen, MinList} = decode(C-1, List), | |
L = lap(C, List), | |
Llen = length(corpus(L)), | |
io:fwrite("Delta: ~2w\tChars: ~w\tDecode: ~p~n", [C, Llen, L]), | |
if | |
Llen < Minlen -> | |
{Llen, L}; | |
true -> | |
{Minlen, MinList} | |
end. | |
lap(D, [H|T]) -> lists:append([delta(H,D)], lap(D,T)); | |
lap(_, []) -> []. | |
delta(S, true) -> S - 26; | |
delta(S, false) -> S; | |
delta(A, D) -> | |
if | |
A >= $a, A =< $z -> | |
delta(A + D, (A + D) > $z); | |
A >= $A, A =< $Z -> | |
delta(A + D, (A + D) > $Z); | |
true -> A | |
end. | |
corpus(TList) -> | |
{ok, File} = file:read_file("/tmp/corpus2"), | |
Crps = lists:append([binary_to_list(File),"\n",string:to_lower(TList)]), | |
Bin = zlib:gzip(Crps), | |
binary_to_list(Bin). |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment