Created
July 20, 2016 04:37
-
-
Save oozman/8e78d465632745fd197eebe95239f176 to your computer and use it in GitHub Desktop.
[js] clean msword special characters
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
/// Replaces commonly-used Windows 1252 encoded chars that do not exist in ASCII or ISO-8859-1 with ISO-8859-1 cognates. | |
var replaceWordChars = function(text) { | |
var s = text; | |
// smart single quotes and apostrophe | |
s = s.replace(/[\u2018\u2019\u201A]/g, "\'"); | |
// smart double quotes | |
s = s.replace(/[\u201C\u201D\u201E]/g, "\""); | |
// ellipsis | |
s = s.replace(/\u2026/g, "..."); | |
// dashes | |
s = s.replace(/[\u2013\u2014]/g, "-"); | |
// circumflex | |
s = s.replace(/\u02C6/g, "^"); | |
// open angle bracket | |
s = s.replace(/\u2039/g, "<"); | |
// close angle bracket | |
s = s.replace(/\u203A/g, ">"); | |
// spaces | |
s = s.replace(/[\u02DC\u00A0]/g, " "); | |
return s; | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment