Mega Code Archive
Splits the provided text into an array, separator string specified Returns a maximum of max substrings
<![CDATA[
import java.util.ArrayList;
import java.util.List;
public class Main {
/**
* Splits the provided text into an array, separator string specified.
* Returns a maximum of <code>max</code> substrings.
*
* The separator(s) will not be included in the returned String array.
* Adjacent separators are treated as one separator.
*
* A <code>null</code> input String returns <code>null</code>.
* A <code>null</code> separator splits on whitespace.
*
* <pre>
* StringUtils.splitByWholeSeparator(null, *, *) = null
* StringUtils.splitByWholeSeparator("", *, *) = []
* StringUtils.splitByWholeSeparator("ab de fg", null, 0) = ["ab", "de", "fg"]
* StringUtils.splitByWholeSeparator("ab de fg", null, 0) = ["ab", "de", "fg"]
* StringUtils.splitByWholeSeparator("ab:cd:ef", ":", 2) = ["ab", "cd:ef"]
* StringUtils.splitByWholeSeparator("ab-!-cd-!-ef", "-!-", 5) = ["ab", "cd", "ef"]
* StringUtils.splitByWholeSeparator("ab-!-cd-!-ef", "-!-", 2) = ["ab", "cd-!-ef"]
* </pre>
*
* @param str the String to parse, may be null
* @param separator String containing the String to be used as a delimiter,
* <code>null</code> splits on whitespace
* @param max the maximum number of elements to include in the returned
* array. A zero or negative value implies no limit.
* @return an array of parsed Strings, <code>null</code> if null String was input
*/
public static String[] splitByWholeSeparator( String str, String separator, int max ) {
return splitByWholeSeparatorWorker(str, separator, max, false);
}
/**
* Performs the logic for the <code>splitByWholeSeparatorPreserveAllTokens</code> methods.
*
* @param str the String to parse, may be <code>null</code>
* @param separator String containing the String to be used as a delimiter,
* <code>null</code> splits on whitespace
* @param max the maximum number of elements to include in the returned
* array. A zero or negative value implies no limit.
* @param preserveAllTokens if <code>true</code>, adjacent separators are
* treated as empty token separators; if <code>false</code>, adjacent
* separators are treated as one separator.
* @return an array of parsed Strings, <code>null</code> if null String input
* @since 2.4
*/
private static String[] splitByWholeSeparatorWorker(String str, String separator, int max,
boolean preserveAllTokens)
{
if (str == null) {
return null;
}
int len = str.length();
if (len == 0) {
return new String[0];
}
if ((separator == null) || ("".equals(separator))) {
// Split on whitespace.
return splitWorker(str, null, max, preserveAllTokens);
}
int separatorLength = separator.length();
ArrayList substrings = new ArrayList();
int numberOfSubstrings = 0;
int beg = 0;
int end = 0;
while (end < len) {
end = str.indexOf(separator, beg);
if (end > -1) {
if (end > beg) {
numberOfSubstrings += 1;
if (numberOfSubstrings == max) {
end = len;
substrings.add(str.substring(beg));
} else {
// The following is OK, because String.substring( beg, end ) excludes
// the character at the position 'end'.
substrings.add(str.substring(beg, end));
// Set the starting point for the next search.
// The following is equivalent to beg = end + (separatorLength - 1) + 1,
// which is the right calculation:
beg = end + separatorLength;
}
} else {
// We found a consecutive occurrence of the separator, so skip it.
if (preserveAllTokens) {
numberOfSubstrings += 1;
if (numberOfSubstrings == max) {
end = len;
substrings.add(str.substring(beg));
} else {
substrings.add("");
}
}
beg = end + separatorLength;
}
} else {
// String.substring( beg ) goes from 'beg' to the end of the String.
substrings.add(str.substring(beg));
end = len;
}
}
return (String[]) substrings.toArray(new String[substrings.size()]);
}
/**
* Performs the logic for the <code>split</code> and
* <code>splitPreserveAllTokens</code> methods that return a maximum array
* length.
*
* @param str the String to parse, may be <code>null</code>
* @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 <code>true</code>, adjacent separators are
* treated as empty token separators; if <code>false</code>, adjacent
* separators are treated as one separator.
* @return an array of parsed Strings, <code>null</code> 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()]);
}
}
]]>