An utility to decode or unescape HTML characters in XML (EDI) documents
This is a procedure to use in Seeburger BIC Mapping Designer
It will extend your library for string handling
/* -----------------------------
Peter Lykkegaard, 25 apr 2023
-----------------------------
procedure unescapeHTML
Parameters:
Source / String, alphanumeric
Output
String, alphanumericString
Adapted from How to Unescape HTML in Java using Plain Java
https://howtodoinjava.com/java/string/unescape-html-to-string/
----------------------------- */
local lvOutput$;
#importJavaStart
import java.util.HashMap;
#importJavaEnd
// Save source in case changes are not needed
copy pSource$ to lvOutput$;
// Check for any ampersand / & character
if (containsSubstring(pSource$, "&") != 0)
if (containsSubstring(pSource$, "&") != 0)
// HTML decode ampersand / &
copy replaceAll(pSource$, "&", "&") to pSource$;
endif
#javastart
int i, j;
boolean continueLoop;
int skip = 0;
HashMap<String, String> htmlEntities = new HashMap<String, String>();
htmlEntities.put("<", "<");
htmlEntities.put(">", ">");
htmlEntities.put("&", "&");
htmlEntities.put(""", "\"");
htmlEntities.put(" ", " ");
htmlEntities.put("©", "\u00a9");
htmlEntities.put("®", "\u00ae");
htmlEntities.put("€", "\u20a0");
htmlEntities.put("Å", "Å");
htmlEntities.put("Æ", "Æ");
htmlEntities.put("Ø", "Ø");
htmlEntities.put("å", "å");
htmlEntities.put("æ", "æ");
htmlEntities.put("ø", "ø");
String source = _StrVar_PSOURCE.getString();
do {
continueLoop = false;
i = source.indexOf("&", skip);
if (i > -1) {
j = source.indexOf(";", i);
if (j > i) {
String entityToLookFor = source.substring(i, j + 1);
String value = (String) htmlEntities.get(entityToLookFor);
if (value != null) {
source = source.substring(0, i) + value + source.substring(j + 1);
continueLoop = true;
} else if (value == null) {
skip = i + 1;
continueLoop = true;
}
}
}
} while (continueLoop);
_StrVar_LVOUTPUT.setString(source);
#javaend
endif
exitProc(lvOutput$);