Last active
August 29, 2015 14:05
-
-
Save mtourne/1a343eb4c1f0cc390343 to your computer and use it in GitHub Desktop.
js cut words
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
function is_word_char(c) { | |
return (c >= 'a' && c <= 'z') || (c >= 'A' && c <= 'Z'); | |
} | |
function cut_words(content) { | |
var in_word = false; | |
var start_word = 0; | |
var word; | |
var result = []; | |
var i; | |
for (i = 0; i < content.length; i++) { | |
if (is_word_char(content[i])) { | |
// char is part of a word | |
if (!in_word) { | |
// not in a word yet | |
in_word = true; | |
start_word = i; | |
} | |
} else { | |
// char is not a word | |
if (in_word) { | |
// end of a word | |
in_word = false; | |
// now actually cut the word | |
// if it's more than one character | |
if (i - start_word > 1) { | |
word = content.substring(start_word, i).toLowerCase(); | |
result.push(word); | |
} | |
} | |
} | |
} | |
if (in_word) { | |
// we were in a word at the end of the parsing | |
if (i - start_word > 1) { | |
word = content.substring(start_word, i).toLowerCase(); | |
result.push(word); | |
} | |
} | |
return result; | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment