diff --git a/changelog/src/main/org/apache/maven/cvslib/EnhancedStringTokenizer.java b/changelog/src/main/org/apache/maven/cvslib/EnhancedStringTokenizer.java new file mode 100644 index 00000000..3e11c846 --- /dev/null +++ b/changelog/src/main/org/apache/maven/cvslib/EnhancedStringTokenizer.java @@ -0,0 +1,144 @@ +package org.apache.maven.cvslib; + +/* ==================================================================== + * The Apache Software License, Version 1.1 + * + * Copyright (c) 2003 The Apache Software Foundation. All rights + * reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * + * 3. The end-user documentation included with the redistribution, + * if any, must include the following acknowledgment: + * "This product includes software developed by the + * Apache Software Foundation (http://www.apache.org/)." + * Alternately, this acknowledgment may appear in the software itself, + * if and wherever such third-party acknowledgments normally appear. + * + * 4. The names "Apache" and "Apache Software Foundation" and + * "Apache Maven" must not be used to endorse or promote products + * derived from this software without prior written permission. For + * written permission, please contact apache@apache.org. + * + * 5. Products derived from this software may not be called "Apache", + * "Apache Maven", nor may "Apache" appear in their name, without + * prior written permission of the Apache Software Foundation. + * + * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESSED OR IMPLIED + * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES + * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE + * DISCLAIMED. IN NO EVENT SHALL THE APACHE SOFTWARE FOUNDATION OR + * ITS CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF + * USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND + * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, + * OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT + * OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF + * SUCH DAMAGE. + * ==================================================================== + * + * This software consists of voluntary contributions made by many + * individuals on behalf of the Apache Software Foundation. For more + * information on the Apache Software Foundation, please see + * . + * + * ==================================================================== + */ + +import java.util.StringTokenizer; + +/** + * The java.util.StringTokenizer is horribly broken. + * Given the string 1,,,3,,4 (, delim) + * It will return 1,3,4 + * Which is clearly wrong - 1,EMPTY,EMPTY,3,EMPTY,4 is what it should return + */ +public final class EnhancedStringTokenizer { + private StringTokenizer cst = null; + String cdelim; + final boolean cdelimSingleChar; + final char cdelimChar; + boolean creturnDelims; + + public EnhancedStringTokenizer(String str) { + this(str, " \t\n\r\f", false); + } + + public EnhancedStringTokenizer(String str, String delim) { + this(str, delim, false); + } + + public EnhancedStringTokenizer(String str, String delim, boolean returnDelims) { + cst = new StringTokenizer(str, delim, true); + cdelim = delim; + creturnDelims = returnDelims; + cdelimSingleChar = (delim.length() == 1); + cdelimChar = delim.charAt(0); + } + + public boolean hasMoreTokens() { + return cst.hasMoreTokens(); + } + + String lastToken = null; + boolean delimLast = true; + private String internalNextToken() { + if (lastToken != null) { + String last = lastToken; + lastToken = null; + return last; + } + + String token = cst.nextToken(); + if (isDelim(token)) { + if (delimLast) { + lastToken = token; + return ""; + } else { + delimLast = true; + return token; + } + } else { + delimLast = false; + return token; + } + } + + public String nextToken() { + String token = internalNextToken(); + if (creturnDelims) + return token; + if (isDelim(token)) + return hasMoreTokens() ? internalNextToken() : ""; + else + return token; + } + + private boolean isDelim(String str) { + if (str.length() == 1) { + char ch = str.charAt(0); + if (cdelimSingleChar) { + if (cdelimChar == ch) { + return true; + } + } else { + if (cdelim.indexOf(ch) >= 0) { + return true; + } + } + } + return false; + + } +} \ No newline at end of file diff --git a/changelog/src/test/org/apache/maven/cvslib/EnhancedStringTokenizerTest.java b/changelog/src/test/org/apache/maven/cvslib/EnhancedStringTokenizerTest.java new file mode 100644 index 00000000..bd18fa86 --- /dev/null +++ b/changelog/src/test/org/apache/maven/cvslib/EnhancedStringTokenizerTest.java @@ -0,0 +1,142 @@ +package org.apache.maven.cvslib; + +/* ==================================================================== + * The Apache Software License, Version 1.1 + * + * Copyright (c) 2003 The Apache Software Foundation. All rights + * reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * + * 3. The end-user documentation included with the redistribution, + * if any, must include the following acknowledgment: + * "This product includes software developed by the + * Apache Software Foundation (http://www.apache.org/)." + * Alternately, this acknowledgment may appear in the software itself, + * if and wherever such third-party acknowledgments normally appear. + * + * 4. The names "Apache" and "Apache Software Foundation" and + * "Apache Maven" must not be used to endorse or promote products + * derived from this software without prior written permission. For + * written permission, please contact apache@apache.org. + * + * 5. Products derived from this software may not be called "Apache", + * "Apache Maven", nor may "Apache" appear in their name, without + * prior written permission of the Apache Software Foundation. + * + * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESSED OR IMPLIED + * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES + * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE + * DISCLAIMED. IN NO EVENT SHALL THE APACHE SOFTWARE FOUNDATION OR + * ITS CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF + * USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND + * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, + * OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT + * OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF + * SUCH DAMAGE. + * ==================================================================== + * + * This software consists of voluntary contributions made by many + * individuals on behalf of the Apache Software Foundation. For more + * information on the Apache Software Foundation, please see + * . + * + * ==================================================================== + */ + +import junit.framework.TestCase; + +public class EnhancedStringTokenizerTest extends TestCase { + + public void testSimple() { + EnhancedStringTokenizer tok = new EnhancedStringTokenizer("a,b,c,d,,e,,,f,,,,,g", ","); + assertEquals("Token 1", "a", tok.nextToken()); + assertEquals("Token 2", "b", tok.nextToken()); + assertEquals("Token 3", "c", tok.nextToken()); + assertEquals("Token 4", "d", tok.nextToken()); + assertEquals("Token 5", "", tok.nextToken()); + assertEquals("Token 6", "e", tok.nextToken()); + assertEquals("Token 7", "", tok.nextToken()); + assertEquals("Token 8", "", tok.nextToken()); + assertEquals("Token 9", "f", tok.nextToken()); + assertEquals("Token 10", "", tok.nextToken()); + assertEquals("Token 11", "", tok.nextToken()); + assertEquals("Token 12", "", tok.nextToken()); + assertEquals("Token 13", "", tok.nextToken()); + assertEquals("Token 14", "g", tok.nextToken()); + assertEquals("tok.hasMoreTokens()", false, tok.hasMoreTokens()); + } + + public void testSimpleTab() { + EnhancedStringTokenizer tok = new EnhancedStringTokenizer("a\tb\tc\td\t\te\t\t\tf\t\t\t\t\tg", "\t"); + assertEquals("Token 1", "a", tok.nextToken()); + assertEquals("Token 2", "b", tok.nextToken()); + assertEquals("Token 3", "c", tok.nextToken()); + assertEquals("Token 4", "d", tok.nextToken()); + assertEquals("Token 5", "", tok.nextToken()); + assertEquals("Token 6", "e", tok.nextToken()); + assertEquals("Token 7", "", tok.nextToken()); + assertEquals("Token 8", "", tok.nextToken()); + assertEquals("Token 9", "f", tok.nextToken()); + assertEquals("Token 10", "", tok.nextToken()); + assertEquals("Token 11", "", tok.nextToken()); + assertEquals("Token 12", "", tok.nextToken()); + assertEquals("Token 13", "", tok.nextToken()); + assertEquals("Token 14", "g", tok.nextToken()); + assertEquals("tok.hasMoreTokens()", false, tok.hasMoreTokens()); + } + + public void testNoDelim() { + EnhancedStringTokenizer tok = new EnhancedStringTokenizer("a,b,c,d,,e,,,f,,,,,g", "\t"); + assertEquals("Token 1", "a,b,c,d,,e,,,f,,,,,g", tok.nextToken()); + assertEquals("tok.hasMoreTokens()", false, tok.hasMoreTokens()); + } + + public void testNoText() { + EnhancedStringTokenizer tok = new EnhancedStringTokenizer("", ","); + assertEquals("tok.hasMoreTokens()", false, tok.hasMoreTokens()); + } + + public void testReturnDelim() { + EnhancedStringTokenizer tok = new EnhancedStringTokenizer("a,b,,c,d", ",", true); + assertEquals("Token 1", "a", tok.nextToken()); + assertEquals("Token 2", ",", tok.nextToken()); + assertEquals("Token 3", "b", tok.nextToken()); + assertEquals("Token 4", ",", tok.nextToken()); + assertEquals("Token 5", "", tok.nextToken()); + assertEquals("Token 6", ",", tok.nextToken()); + assertEquals("Token 7", "c", tok.nextToken()); + assertEquals("Token 2", ",", tok.nextToken()); + assertEquals("Token 8", "d", tok.nextToken()); + assertEquals("tok.hasMoreTokens()", false, tok.hasMoreTokens()); + } + + public void testMultipleDelim() { + EnhancedStringTokenizer tok = new EnhancedStringTokenizer("a.,b.,c.d", ".,", true); + assertEquals("Token 1", "a", tok.nextToken()); + assertEquals("Token 2", ".", tok.nextToken()); + assertEquals("Token 3", "", tok.nextToken()); + assertEquals("Token 4", ",", tok.nextToken()); + assertEquals("Token 5", "b", tok.nextToken()); + assertEquals("Token 6", ".", tok.nextToken()); + assertEquals("Token 7", "", tok.nextToken()); + assertEquals("Token 8", ",", tok.nextToken()); + assertEquals("Token 9", "c", tok.nextToken()); + assertEquals("Token 10", ".", tok.nextToken()); + assertEquals("Token 11", "d", tok.nextToken()); + assertEquals("tok.hasMoreTokens()", false, tok.hasMoreTokens()); + } + +} \ No newline at end of file