Created
February 21, 2013 08:26
-
-
Save mumumu/5003175 to your computer and use it in GitHub Desktop.
jdom claims "....." is not legal for a JDOM character content: 0x... is not a legal XML character.
for workaround, i used the following method. From http://blog.mark-mclaren.info/2007/02/invalid-xml-characters-when-valid-utf8_5873.html
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
/** | |
* This method ensures that the output String has only | |
* valid XML unicode characters as specified by the | |
* XML 1.0 standard. For reference, please see | |
* <a href="http://www.w3.org/TR/2000/REC-xml-20001006#NT-Char">the | |
* standard</a>. This method will return an empty | |
* String if the input is null or empty. | |
* | |
* @param in The String whose non-valid characters we want to remove. | |
* @return The in String, stripped of non-valid characters. | |
*/ | |
public String skipInValidXMLChars(String in) { | |
StringBuffer out = new StringBuffer(); | |
char current; | |
if (in == null || ("".equals(in))) return ""; | |
for (int i = 0; i < in.length(); i++) { | |
current = in.charAt(i); | |
if ((current == 0x9) || | |
(current == 0xA) || | |
(current == 0xD) || | |
((current >= 0x20) && (current <= 0xD7FF)) || | |
((current >= 0xE000) && (current <= 0xFFFD)) || | |
((current >= 0x10000) && (current <= 0x10FFFF))) | |
out.append(current); | |
} | |
return out.toString(); | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment