|
/*
* 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, separator specified,
* preserving all tokens, including empty tokens created by adjacent
* separators. This is an alternative to using StringTokenizer.</p>
*
* <p>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.</p>
*
* <p>A <code>null</code> input String returns <code>null</code>.</p>
*
* <pre>
* StringUtils.splitPreserveAllTokens(null, *) = null
* StringUtils.splitPreserveAllTokens("", *) = []
* StringUtils.splitPreserveAllTokens("a.b.c", '.') = ["a", "b", "c"]
* StringUtils.splitPreserveAllTokens("a..b.c", '.') = ["a", "", "b", "c"]
* StringUtils.splitPreserveAllTokens("a:b:c", '.') = ["a:b:c"]
* StringUtils.splitPreserveAllTokens("a\tb\nc", null) = ["a", "b", "c"]
* StringUtils.splitPreserveAllTokens("a b c", ' ') = ["a", "b", "c"]
* StringUtils.splitPreserveAllTokens("a b c ", ' ') = ["a", "b", "c", ""]
* StringUtils.splitPreserveAllTokens("a b c ", ' ') = ["a", "b", "c", "", ""]
* StringUtils.splitPreserveAllTokens(" a b c", ' ') = ["", a", "b", "c"]
* StringUtils.splitPreserveAllTokens(" a b c", ' ') = ["", "", a", "b", "c"]
* StringUtils.splitPreserveAllTokens(" a b c ", ' ') = ["", a", "b", "c", ""]
* </pre>
*
* @param str the String to parse, may be <code>null</code>
* @param separatorChar the character used as the delimiter,
* <code>null</code> splits on whitespace
* @return an array of parsed Strings, <code>null</code> if null String input
* @since 2.1
*/
public static String[] splitPreserveAllTokens(String str, char separatorChar) {
return splitWorker(str, separatorChar, true);
}
/**
* Performs the logic for the <code>split</code> and
* <code>splitPreserveAllTokens</code> methods that do not return a
* maximum array length.
*
* @param str the String to parse, may be <code>null</code>
* @param separatorChar the separate character
* @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, char separatorChar, boolean preserveAllTokens) {
// Performance tuned for 2.0 (JDK1.4)
if (str == null) {
return null;
}
int len = str.length();
if (len == 0) {
return new String[0];
}
List list = new ArrayList();
int i = 0, start = 0;
boolean match = false;
boolean lastMatch = false;
while (i < len) {
if (str.charAt(i) == separatorChar) {
if (match || preserveAllTokens) {
list.add(str.substring(start, i));
match = false;
lastMatch = true;
}
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()]);
}
}
|