Mega Code Archive
Splits the provided text into an array with a maximum length, separators specified, preserving all tokens, including empty token
<![CDATA[
/*
* Licensed to the Apache Software Foundation (ASF) under one or more
* contributor license agreements. See the NOTICE file distributed with
* this work for additional information regarding copyright ownership.
* The ASF licenses this file to You under the Apache License, Version 2.0
* (the "License"); you may not use this file except in compliance with
* the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
import java.util.ArrayList;
import java.util.List;
public class Main {
/**
* <p>Splits the provided text into an array with a maximum length,
* separators specified, preserving all tokens, including empty tokens
* created by adjacent separators.</p>
*
* <p>The separator is not included in the returned String array.
* Adjacent separators are treated as separators for empty tokens.
* Adjacent separators are treated as one separator.</p>
*
* <p>A <code>null</code> input String returns <code>null</code>.
* A <code>null</code> separatorChars splits on whitespace.</p>
*
* <p>If more than <code>max</code> delimited substrings are found, the last
* returned string includes all characters after the first <code>max - 1</code>
* returned strings (including separator characters).</p>
*
* <pre>
* StringUtils.splitPreserveAllTokens(null, *, *) = null
* StringUtils.splitPreserveAllTokens("", *, *) = []
* StringUtils.splitPreserveAllTokens("ab de fg", null, 0) = ["ab", "cd", "ef"]
* StringUtils.splitPreserveAllTokens("ab de fg", null, 0) = ["ab", "cd", "ef"]
* StringUtils.splitPreserveAllTokens("ab:cd:ef", ":", 0) = ["ab", "cd", "ef"]
* StringUtils.splitPreserveAllTokens("ab:cd:ef", ":", 2) = ["ab", "cd:ef"]
* StringUtils.splitPreserveAllTokens("ab de fg", null, 2) = ["ab", " de fg"]
* StringUtils.splitPreserveAllTokens("ab de fg", null, 3) = ["ab", "", " de fg"]
* StringUtils.splitPreserveAllTokens("ab de fg", null, 4) = ["ab", "", "", "de fg"]
* </pre>
*
* @param str the String to parse, may be <code>null</code>
* @param separatorChars the characters used as the delimiters,
* <code>null</code> splits on whitespace
* @param max the maximum number of elements to include in the
* array. A zero or negative value implies no limit
* @return an array of parsed Strings, <code>null</code> if null String input
* @since 2.1
*/
public static String[] splitPreserveAllTokens(String str, String separatorChars, int max) {
return splitWorker(str, separatorChars, max, true);
}
/**
* 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()]);
}
}
]]>