Splits the provided text into an array, separators specified, * preserving all tokens, including empty tokens created by adjacent * separators. This is an alternative to using StringTokenizer.
* *The separator is not included in the returned String array. * Adjacent separators are treated as separators for empty tokens. * For more control over the split use the StrTokenizer class.
* *A null
input String returns null
.
* A null
separatorChars splits on whitespace.
* StringUtils.splitPreserveAllTokens(null, *) = null * StringUtils.splitPreserveAllTokens("", *) = [] * StringUtils.splitPreserveAllTokens("abc def", null) = ["abc", "def"] * StringUtils.splitPreserveAllTokens("abc def", " ") = ["abc", "def"] * StringUtils.splitPreserveAllTokens("abc def", " ") = ["abc", "", def"] * StringUtils.splitPreserveAllTokens("ab:cd:ef", ":") = ["ab", "cd", "ef"] * StringUtils.splitPreserveAllTokens("ab:cd:ef:", ":") = ["ab", "cd", "ef", ""] * StringUtils.splitPreserveAllTokens("ab:cd:ef::", ":") = ["ab", "cd", "ef", "", ""] * StringUtils.splitPreserveAllTokens("ab::cd:ef", ":") = ["ab", "", cd", "ef"] * StringUtils.splitPreserveAllTokens(":cd:ef", ":") = ["", cd", "ef"] * StringUtils.splitPreserveAllTokens("::cd:ef", ":") = ["", "", cd", "ef"] * StringUtils.splitPreserveAllTokens(":cd:ef:", ":") = ["", cd", "ef", ""] ** * @param str the String to parse, may be
null
* @param separatorChars the characters used as the delimiters,
* null
splits on whitespace
* @return an array of parsed Strings, null
if null String input
* @since 2.1
*/
public static String[] splitPreserveAllTokens(String str, String separatorChars) {
return splitWorker(str, separatorChars, -1, true);
}
/**
* Performs the logic for the split
and
* splitPreserveAllTokens
methods that return a maximum array
* length.
*
* @param str the String to parse, may be null
* @param separatorChars the separate character
* @param max the maximum number of elements to include in the
* array. A zero or negative value implies no limit.
* @param preserveAllTokens if true
, adjacent separators are
* treated as empty token separators; if false
, adjacent
* separators are treated as one separator.
* @return an array of parsed Strings, null
if null String input
*/
private static String[] splitWorker(String str, String separatorChars, int max, boolean preserveAllTokens) {
// Performance tuned for 2.0 (JDK1.4)
// Direct code is quicker than StringTokenizer.
// Also, StringTokenizer uses isSpace() not isWhitespace()
if (str == null) {
return null;
}
int len = str.length();
if (len == 0) {
return new String[0];
}
List list = new ArrayList();
int sizePlus1 = 1;
int i = 0, start = 0;
boolean match = false;
boolean lastMatch = false;
if (separatorChars == null) {
// Null separator means use whitespace
while (i < len) {
if (Character.isWhitespace(str.charAt(i))) {
if (match || preserveAllTokens) {
lastMatch = true;
if (sizePlus1++ == max) {
i = len;
lastMatch = false;
}
list.add(str.substring(start, i));
match = false;
}
start = ++i;
continue;
}
lastMatch = false;
match = true;
i++;
}
} else if (separatorChars.length() == 1) {
// Optimise 1 character case
char sep = separatorChars.charAt(0);
while (i < len) {
if (str.charAt(i) == sep) {
if (match || preserveAllTokens) {
lastMatch = true;
if (sizePlus1++ == max) {
i = len;
lastMatch = false;
}
list.add(str.substring(start, i));
match = false;
}
start = ++i;
continue;
}
lastMatch = false;
match = true;
i++;
}
} else {
// standard case
while (i < len) {
if (separatorChars.indexOf(str.charAt(i)) >= 0) {
if (match || preserveAllTokens) {
lastMatch = true;
if (sizePlus1++ == max) {
i = len;
lastMatch = false;
}
list.add(str.substring(start, i));
match = false;
}
start = ++i;
continue;
}
lastMatch = false;
match = true;
i++;
}
}
if (match || (preserveAllTokens && lastMatch)) {
list.add(str.substring(start, i));
}
return (String[]) list.toArray(new String[list.size()]);
}
}