Non-ASCII characters are translated into unicode hexadecimal entities. The same holds for ascii characters listed within the filter.
<..XtpipesUni.java..>
/* XtpipesUni.java (2014-05-24-12:32), generated from xtpipes.tex
Copyright (C) 2009-2010 TeX Users Group
Copyright (C) 2002-2009 Eitan M. Gurari
<.TeX4ht copyright.> */
package xtpipes;
public class XtpipesUni{
<.String toUni( char[], start, length, filter ).>
<.String toUni( String, filter ).>
}
-_-_-
<..String toUni( char[], start, length, filter )..>
private static int D800 = Integer.parseInt("D800", 16);
private static int DFFF = Integer.parseInt("DFFF", 16);
private static int DC00 = Integer.parseInt("DC00", 16);
private static int X400 = Integer.parseInt("400",16);
private static int X10000 = Integer.parseInt("10000",16);
public static String toUni( char[] ch, int start, int length,
String filter ){
StringBuffer buf = new StringBuffer(length);
for (int i = 0; i < length; i++) {
int chr = ch[ start + i ];
boolean ascii = (chr == ’\n’)
|| (chr > 31) && (chr < 127) ;
if( filter.indexOf(chr) > -1 ){ ascii = false; }
if( (chr >= D800) && (chr<= DFFF) ){
chr = ((ch[i] - D800) * X400 + (ch[++i] - DC00)) + X10000;
}
buf.append(
ascii ? Character.toString((char) chr)
: ("&#x"
+ Integer.toHexString(chr).toUpperCase()
+ ";" ) );
}
return new String(buf);
}
-_-_-
<..String toUni( String, filter )..>
public static String toUni( String s, String filter ){
char [] ch = s.toCharArray();
int length = ch.length;
return toUni(ch, 0, length, filter);
}
-_-_-