+
+ /**
+ * 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;
+ }
+
+ /**
+ * Answers the input string with any occurrences of the 'encodeable' characters
+ * replaced by their URL encoding
+ *
+ * @param s
+ * @param encodable
+ * @return
+ */
+ public static String urlEncode(String s, String encodable)
+ {
+ if (s == null || s.isEmpty())
+ {
+ return s;
+ }
+
+ /*
+ * do % encoding first, as otherwise it may double-encode!
+ */
+ if (encodable.indexOf(PERCENT) != -1)
+ {
+ s = urlEncode(s, PERCENT);
+ }
+
+ for (char c : encodable.toCharArray())
+ {
+ if (c != PERCENT)
+ {
+ s = urlEncode(s, c);
+ }
+ }
+ return s;
+ }
+
+ /**
+ * Answers the input string with any occurrences of {@code c} replaced with
+ * their url encoding. Answers the input string if it is unchanged.
+ *
+ * @param s
+ * @param c
+ * @return
+ */
+ static String urlEncode(String s, char c)
+ {
+ String decoded = String.valueOf(c);
+ if (s.indexOf(decoded) != -1)
+ {
+ String encoded = getUrlEncoding(c);
+ if (!encoded.equals(decoded))
+ {
+ s = s.replace(decoded, encoded);
+ }
+ }
+ return s;
+ }
+
+ /**
+ * Answers the input string with any occurrences of the specified (unencoded)
+ * characters replaced by their URL decoding.
+ * <p>
+ * Example: {@code urlDecode("a%3Db%3Bc", "-;=,")} should answer
+ * {@code "a=b;c"}.
+ *
+ * @param s
+ * @param encodable
+ * @return
+ */
+ public static String urlDecode(String s, String encodable)
+ {
+ if (s == null || s.isEmpty())
+ {
+ return s;
+ }
+
+ for (char c : encodable.toCharArray())
+ {
+ String encoded = getUrlEncoding(c);
+ if (s.indexOf(encoded) != -1)
+ {
+ String decoded = String.valueOf(c);
+ s = s.replace(encoded, decoded);
+ }
+ }
+ return s;
+ }
+
+ /**
+ * Does a lazy lookup of the url encoding of the given character, saving the
+ * value for repeat lookups
+ *
+ * @param c
+ * @return
+ */
+ private static String getUrlEncoding(char c)
+ {
+ if (c < 0 || c >= urlEncodings.length)
+ {
+ return String.valueOf(c);
+ }
+
+ String enc = urlEncodings[c];
+ if (enc == null)
+ {
+ try
+ {
+ enc = urlEncodings[c] = URLEncoder.encode(String.valueOf(c),
+ "UTF-8");
+ } catch (UnsupportedEncodingException e)
+ {
+ enc = urlEncodings[c] = String.valueOf(c);
+ }
+ }
+ return enc;
+ }