Created
February 27, 2013 16:15
-
-
Save jamescway/5049133 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
require 'ruby-debug' | |
def multi_split(str, tokens) | |
results = [] | |
buffer = "" | |
maybe_token = false | |
temp_str = "" | |
str.each_char do |c| | |
if maybe_token | |
if is_token?(temp_str + c, tokens) | |
maybe_token, temp_str = reset_state(maybe_token, temp_str) | |
results << buffer | |
buffer = "" | |
elsif is_token_prefix?(temp_str + c, tokens) | |
temp_str << c | |
else | |
maybe_token, temp_str = reset_state(maybe_token, temp_str) | |
end | |
else | |
if(is_token_prefix?(c, tokens)) | |
maybe_token = true | |
temp_str << c | |
if is_token?(temp_str, tokens) | |
maybe_token, temp_str = reset_state(maybe_token, temp_str) | |
results << buffer | |
buffer = "" | |
end | |
else | |
buffer << c | |
end | |
end | |
end | |
results << buffer | |
results | |
end | |
def reset_state(maybe_token, temp_str) | |
temp_str="" | |
maybe_token = false | |
return maybe_token, temp_str | |
end | |
def is_token_prefix?(prefix, tokens) | |
tokens.each { |token| return true if token.start_with?(prefix) } | |
false | |
end | |
def is_token?(str, tokens) | |
tokens.each { |token| return true if token == str } | |
false | |
end | |
puts multi_split("dogxycat", ["og", "y"]).to_s | |
puts multi_split('ddxy', ['d']).to_s | |
#puts multi_split('ddxy', ['d']) == ['', '', 'xy'] | |
#puts multi_split('dogxycat', ['og', 'y']) == ['d', 'x', 'cat'] |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment