+
+ /**
+ * A helper method that strips off any leading or trailing html and body tags.
+ * If no html tag is found, then also html-encodes angle bracket characters.
+ *
+ * @param text
+ * @return
+ */
+ public static String stripHtmlTags(String text)
+ {
+ if (text == null)
+ {
+ return null;
+ }
+ String tmp2up = text.toUpperCase();
+ int startTag = tmp2up.indexOf("<HTML>");
+ if (startTag > -1)
+ {
+ text = text.substring(startTag + 6);
+ tmp2up = tmp2up.substring(startTag + 6);
+ }
+ // is omission of "<BODY>" intentional here??
+ int endTag = tmp2up.indexOf("</BODY>");
+ if (endTag > -1)
+ {
+ text = text.substring(0, endTag);
+ tmp2up = tmp2up.substring(0, endTag);
+ }
+ endTag = tmp2up.indexOf("</HTML>");
+ if (endTag > -1)
+ {
+ text = text.substring(0, endTag);
+ }
+
+ if (startTag == -1 && (text.contains("<") || text.contains(">")))
+ {
+ text = text.replaceAll("<", "<");
+ text = text.replaceAll(">", ">");
+ }
+ return text;
+ }