Created
May 23, 2012 18:14
-
-
Save unobliged/2776784 to your computer and use it in GitHub Desktop.
plymlet old dictionary script
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
if __FILE__ == $0 | |
# TODO Generated stub | |
end | |
$KCODE = "U" | |
filename = 'njs test.U8.TXT' | |
dictionary = 'cedict_ts.u8' | |
vocab_list = [] | |
lines = IO.readlines(filename) | |
lines.each {|line| vocab_list << line.split} | |
vocab_list.flatten! | |
vocab_list.collect! {|b| b.chomp(",")} | |
vocab_list.collect! {|b| b.chomp("?")} | |
vocab_list.uniq! | |
matches = [] | |
dict = File.readlines(dictionary) | |
better_matches = [] | |
search_match = [] | |
vocab_list.each do |word| | |
puts('-+-+-+-',word) | |
matches = dict.grep(/#{word}/) | |
matches.each {|match| better_matches << match if match.split.include?(word)} | |
better_matches.each do |better_match| | |
search_match = better_match.split | |
puts better_match if search_match[0].include?(word) or search_match[1].include?(word) | |
end | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment