/*
* Copyright (c) 1994, 2004, Oracle and/or its affiliates. All rights reserved.
* DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
*
* This code is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License version 2 only, as
* published by the Free Software Foundation. Oracle designates this
* particular file as subject to the "Classpath" exception as provided
* by Oracle in the LICENSE file that accompanied this code.
*
* This code is distributed in the hope that it will be useful, but WITHOUT
* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
* version 2 for more details (a copy is included in the LICENSE file that
* accompanied this code).
*
* You should have received a copy of the GNU General Public License version
* 2 along with this work; if not, write to the Free Software Foundation,
* Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
*
* Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
* or visit www.oracle.com if you need additional information or have any
* questions.
*/
package java.util;
import java.lang.*;
/**
* The string tokenizer class allows an application to break a
* string into tokens. The tokenization method is much simpler than
* the one used by the {@code StreamTokenizer} class. The
* {@code StringTokenizer} methods do not distinguish among
* identifiers, numbers, and quoted strings, nor do they recognize
* and skip comments.
* <p>
* The set of delimiters (the characters that separate tokens) may
* be specified either at creation time or on a per-token basis.
* <p>
* An instance of {@code StringTokenizer} behaves in one of two
* ways, depending on whether it was created with the
* {@code returnDelims} flag having the value {@code true}
* or {@code false}:
* <ul>
* <li>If the flag is {@code false}, delimiter characters serve to
* separate tokens. A token is a maximal sequence of consecutive
* characters that are not delimiters.
* <li>If the flag is {@code true}, delimiter characters are themselves
* considered to be tokens. A token is thus either one delimiter
* character, or a maximal sequence of consecutive characters that are
* not delimiters.
* </ul><p>
* A {@code StringTokenizer} object internally maintains a current
* position within the string to be tokenized. Some operations advance this
* current position past the characters processed.<p>
* A token is returned by taking a substring of the string that was used to
* create the {@code StringTokenizer} object.
* <p>
* The following is one example of the use of the tokenizer. The code:
* <blockquote><pre>
* StringTokenizer st = new StringTokenizer("this is a test");
* while (st.hasMoreTokens()) {
* System.out.println(st.nextToken());
* }
* </pre></blockquote>
* <p>
* prints the following output:
* <blockquote><pre>
* this
* is
* a
* test
* </pre></blockquote>
*
* <p>
* {@code StringTokenizer} is a legacy class that is retained for
* compatibility reasons although its use is discouraged in new code. It is
* recommended that anyone seeking this functionality use the {@code split}
* method of {@code String} or the java.util.regex package instead.
* <p>
* The following example illustrates how the {@code String.split}
* method can be used to break up a string into its basic tokens:
* <blockquote><pre>
* String[] result = "this is a test".split("\\s");
* for (int x=0; x<result.length; x++)
* System.out.println(result[x]);
* </pre></blockquote>
* <p>
* prints the following output:
* <blockquote><pre>
* this
* is
* a
* test
* </pre></blockquote>
*
* @author unascribed
* @see java.io.StreamTokenizer
* @since 1.0
*/
public
class StringTokenizer implements Enumeration<Object> {
private int currentPosition;
private int newPosition;
private int maxPosition;
private String str;
private String delimiters;
private boolean retDelims;
private boolean delimsChanged;
/**
* maxDelimCodePoint stores the value of the delimiter character with the
* highest value. It is used to optimize the detection of delimiter
* characters.
*
* It is unlikely to provide any optimization benefit in the
* hasSurrogates case because most string characters will be
* smaller than the limit, but we keep it so that the two code
* paths remain similar.
*/
private int maxDelimCodePoint;
/**
* If delimiters include any surrogates (including surrogate
* pairs), hasSurrogates is true and the tokenizer uses the
* different code path. This is because String.indexOf(int)
* doesn't handle unpaired surrogates as a single character.
*/
private boolean hasSurrogates = false;
/**
* When hasSurrogates is true, delimiters are converted to code
* points and isDelimiter(int) is used to determine if the given
* codepoint is a delimiter.
*/
private int[] delimiterCodePoints;
/**
* Set maxDelimCodePoint to the highest char in the delimiter set.
*/
private void setMaxDelimCodePoint() {
if (delimiters == null) {
maxDelimCodePoint = 0;
return;
}
int m = 0;
int c;
int count = 0;
for (int i = 0; i < delimiters.length(); i += Character.charCount(c)) {
c = delimiters.charAt(i);
if (c >= Character.MIN_HIGH_SURROGATE && c <= Character.MAX_LOW_SURROGATE) {
c = delimiters.codePointAt(i);
hasSurrogates = true;
}
if (m < c)
m = c;
count++;
}
maxDelimCodePoint = m;
if (hasSurrogates) {
delimiterCodePoints = new int[count];
for (int i = 0, j = 0; i < count; i++, j += Character.charCount(c)) {
c = delimiters.codePointAt(j);
delimiterCodePoints[i] = c;
}
}
}
/**
* Constructs a string tokenizer for the specified string. All
* characters in the {@code delim} argument are the delimiters
* for separating tokens.
* <p>
* If the {@code returnDelims} flag is {@code true}, then
* the delimiter characters are also returned as tokens. Each
* delimiter is returned as a string of length one. If the flag is
* {@code false}, the delimiter characters are skipped and only
* serve as separators between tokens.
* <p>
* Note that if {@code delim} is {@code null}, this constructor does
* not throw an exception. However, trying to invoke other methods on the
* resulting {@code StringTokenizer} may result in a
* {@code NullPointerException}.
*
* @param str a string to be parsed.
* @param delim the delimiters.
* @param returnDelims flag indicating whether to return the delimiters
* as tokens.
* @exception NullPointerException if str is {@code null}
*/
public StringTokenizer(String str, String delim, boolean returnDelims) {
currentPosition = 0;
newPosition = -1;
delimsChanged = false;
this.str = str;
maxPosition = str.length();
delimiters = delim;
retDelims = returnDelims;
setMaxDelimCodePoint();
}
/**
* Constructs a string tokenizer for the specified string. The
* characters in the {@code delim} argument are the delimiters
* for separating tokens. Delimiter characters themselves will not
* be treated as tokens.
* <p>
* Note that if {@code delim} is {@code null}, this constructor does
* not throw an exception. However, trying to invoke other methods on the
* resulting {@code StringTokenizer} may result in a
* {@code NullPointerException}.
*
* @param str a string to be parsed.
* @param delim the delimiters.
* @exception NullPointerException if str is {@code null}
*/
public StringTokenizer(String str, String delim) {
this(str, delim, false);
}
/**
* Constructs a string tokenizer for the specified string. The
* tokenizer uses the default delimiter set, which is
* <code>" \t\n\r\f"</code>: the space character,
* the tab character, the newline character, the carriage-return character,
* and the form-feed character. Delimiter characters themselves will
* not be treated as tokens.
*
* @param str a string to be parsed.
* @exception NullPointerException if str is {@code null}
*/
public StringTokenizer(String str) {
this(str, " \t\n\r\f", false);
}
/**
* Skips delimiters starting from the specified position. If retDelims
* is false, returns the index of the first non-delimiter character at or
* after startPos. If retDelims is true, startPos is returned.
*/
private int skipDelimiters(int startPos) {
if (delimiters == null)
throw new NullPointerException();
int position = startPos;
while (!retDelims && position < maxPosition) {
if (!hasSurrogates) {
char c = str.charAt(position);
if ((c > maxDelimCodePoint) || (delimiters.indexOf(c) < 0))
break;
position++;
} else {
int c = str.codePointAt(position);
if ((c > maxDelimCodePoint) || !isDelimiter(c)) {
break;
}
position += Character.charCount(c);
}
}
return position;
}
/**
* Skips ahead from startPos and returns the index of the next delimiter
* character encountered, or maxPosition if no such delimiter is found.
*/
private int scanToken(int startPos) {
int position = startPos;
while (position < maxPosition) {
if (!hasSurrogates) {
char c = str.charAt(position);
if ((c <= maxDelimCodePoint) && (delimiters.indexOf(c) >= 0))
break;
position++;
} else {
int c = str.codePointAt(position);
if ((c <= maxDelimCodePoint) && isDelimiter(c))
break;
position += Character.charCount(c);
}
}
if (retDelims && (startPos == position)) {
if (!hasSurrogates) {
char c = str.charAt(position);
if ((c <= maxDelimCodePoint) && (delimiters.indexOf(c) >= 0))
position++;
} else {
int c = str.codePointAt(position);
if ((c <= maxDelimCodePoint) && isDelimiter(c))
position += Character.charCount(c);
}
}
return position;
}
private boolean isDelimiter(int codePoint) {
for (int delimiterCodePoint : delimiterCodePoints) {
if (delimiterCodePoint == codePoint) {
return true;
}
}
return false;
}
/**
* Tests if there are more tokens available from this tokenizer's string.
* If this method returns {@code true}, then a subsequent call to
* {@code nextToken} with no argument will successfully return a token.
*
* @return {@code true} if and only if there is at least one token
* in the string after the current position; {@code false}
* otherwise.
*/
public boolean hasMoreTokens() {
/*
* Temporarily store this position and use it in the following
* nextToken() method only if the delimiters haven't been changed in
* that nextToken() invocation.
*/
newPosition = skipDelimiters(currentPosition);
return (newPosition < maxPosition);
}
/**
* Returns the next token from this string tokenizer.
*
* @return the next token from this string tokenizer.
* @exception NoSuchElementException if there are no more tokens in this
* tokenizer's string.
*/
public String nextToken() {
/*
* If next position already computed in hasMoreElements() and
* delimiters have changed between the computation and this invocation,
* then use the computed value.
*/
currentPosition = (newPosition >= 0 && !delimsChanged) ?
newPosition : skipDelimiters(currentPosition);
/* Reset these anyway */
delimsChanged = false;
newPosition = -1;
if (currentPosition >= maxPosition)
throw new NoSuchElementException();
int start = currentPosition;
currentPosition = scanToken(currentPosition);
return str.substring(start, currentPosition);
}
/**
* Returns the next token in this string tokenizer's string. First,
* the set of characters considered to be delimiters by this
* {@code StringTokenizer} object is changed to be the characters in
* the string {@code delim}. Then the next token in the string
* after the current position is returned. The current position is
* advanced beyond the recognized token. The new delimiter set
* remains the default after this call.
*
* @param delim the new delimiters.
* @return the next token, after switching to the new delimiter set.
* @exception NoSuchElementException if there are no more tokens in this
* tokenizer's string.
* @exception NullPointerException if delim is {@code null}
*/
public String nextToken(String delim) {
delimiters = delim;
/* delimiter string specified, so set the appropriate flag. */
delimsChanged = true;
setMaxDelimCodePoint();
return nextToken();
}
/**
* Returns the same value as the {@code hasMoreTokens}
* method. It exists so that this class can implement the
* {@code Enumeration} interface.
*
* @return {@code true} if there are more tokens;
* {@code false} otherwise.
* @see java.util.Enumeration
* @see java.util.StringTokenizer#hasMoreTokens()
*/
public boolean hasMoreElements() {
return hasMoreTokens();
}
/**
* Returns the same value as the {@code nextToken} method,
* except that its declared return value is {@code Object} rather than
* {@code String}. It exists so that this class can implement the
* {@code Enumeration} interface.
*
* @return the next token in the string.
* @exception NoSuchElementException if there are no more tokens in this
* tokenizer's string.
* @see java.util.Enumeration
* @see java.util.StringTokenizer#nextToken()
*/
public Object nextElement() {
return nextToken();
}
/**
* Calculates the number of times that this tokenizer's
* {@code nextToken} method can be called before it generates an
* exception. The current position is not advanced.
*
* @return the number of tokens remaining in the string using the current
* delimiter set.
* @see java.util.StringTokenizer#nextToken()
*/
public int countTokens() {
int count = 0;
int currpos = currentPosition;
while (currpos < maxPosition) {
currpos = skipDelimiters(currpos);
if (currpos >= maxPosition)
break;
currpos = scanToken(currpos);
count++;
}
return count;
}
}