Created
December 19, 2014 01:55
-
-
Save strubell/dad6fb945ef6ab0be2f7 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
/** Return a string that captures the generic "shape" of the original word, | |
mapping lowercase alphabetics to 'a', uppercase to 'A', digits to '1', whitespace to ' '. | |
Skip more than 'maxRepetitions' of the same character class. */ | |
def stringShape(word:String, maxRepetitions:Int): String = { | |
val sb = new StringBuffer | |
var i = 0; var c = 'x'; var prevc = 'x'; var repetitions = 0 | |
while (i < word.length) { | |
val char = word(i) | |
if (Character.isUpperCase(char)) c = 'A' | |
else if (Character.isLowerCase(char)) c = 'a' | |
else if (Character.isDigit(char)) c = '1' | |
else if (Character.isWhitespace(char)) c = ' ' | |
else c = char | |
if (c == prevc) repetitions += 1 | |
else { prevc = c; repetitions = 0 } | |
if (repetitions < maxRepetitions) sb.append(c) | |
i += 1 | |
} | |
sb.toString | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment