Source for java.util.StringTokenizer

   1: /* StringTokenizer -- breaks a String into tokens
   2:    Copyright (C) 1998, 1999, 2001, 2002, 2005  Free Software Foundation, Inc.
   3: 
   4: This file is part of GNU Classpath.
   5: 
   6: GNU Classpath is free software; you can redistribute it and/or modify
   7: it under the terms of the GNU General Public License as published by
   8: the Free Software Foundation; either version 2, or (at your option)
   9: any later version.
  10: 
  11: GNU Classpath is distributed in the hope that it will be useful, but
  12: WITHOUT ANY WARRANTY; without even the implied warranty of
  13: MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  14: General Public License for more details.
  15: 
  16: You should have received a copy of the GNU General Public License
  17: along with GNU Classpath; see the file COPYING.  If not, write to the
  18: Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
  19: 02110-1301 USA.
  20: 
  21: Linking this library statically or dynamically with other modules is
  22: making a combined work based on this library.  Thus, the terms and
  23: conditions of the GNU General Public License cover the whole
  24: combination.
  25: 
  26: As a special exception, the copyright holders of this library give you
  27: permission to link this library with independent modules to produce an
  28: executable, regardless of the license terms of these independent
  29: modules, and to copy and distribute the resulting executable under
  30: terms of your choice, provided that you also meet, for each linked
  31: independent module, the terms and conditions of the license of that
  32: module.  An independent module is a module which is not derived from
  33: or based on this library.  If you modify this library, you may extend
  34: this exception to your version of the library, but you are not
  35: obligated to do so.  If you do not wish to do so, delete this
  36: exception statement from your version. */
  37: 
  38: 
  39: package java.util;
  40: 
  41: /**
  42:  * This class splits a string into tokens.  The caller can set on which
  43:  * delimiters the string should be split and if the delimiters should be
  44:  * returned. This is much simpler than {@link java.io.StreamTokenizer}.
  45:  *
  46:  * <p>You may change the delimiter set on the fly by calling
  47:  * nextToken(String).  But the semantic is quite difficult; it even
  48:  * depends on calling <code>hasMoreTokens()</code>.  You should call
  49:  * <code>hasMoreTokens()</code> before, otherwise the old delimiters
  50:  * after the last token are candidates for being returned.
  51:  *
  52:  * <p>If you want to get the delimiters, you have to use the three argument
  53:  * constructor.  The delimiters are returned as token consisting of a
  54:  * single character.
  55:  *
  56:  * @author Jochen Hoenicke
  57:  * @author Warren Levy (warrenl@cygnus.com)
  58:  * @see java.io.StreamTokenizer
  59:  * @status updated to 1.4
  60:  */
  61: public class StringTokenizer implements Enumeration
  62: {
  63:   // WARNING: StringTokenizer is a CORE class in the bootstrap cycle. See the
  64:   // comments in vm/reference/java/lang/Runtime for implications of this fact.
  65: 
  66:   /**
  67:    * The position in the str, where we currently are.
  68:    */
  69:   private int pos;
  70: 
  71:   /**
  72:    * The string that should be split into tokens.
  73:    */
  74:   private final String str;
  75: 
  76:   /**
  77:    * The length of the string.
  78:    */
  79:   private final int len;
  80: 
  81:   /**
  82:    * The string containing the delimiter characters.
  83:    */
  84:   private String delim;
  85: 
  86:   /**
  87:    * Tells, if we should return the delimiters.
  88:    */
  89:   private final boolean retDelims;
  90: 
  91:   /**
  92:    * Creates a new StringTokenizer for the string <code>str</code>,
  93:    * that should split on the default delimiter set (space, tab,
  94:    * newline, return and formfeed), and which doesn't return the
  95:    * delimiters.
  96:    *
  97:    * @param str The string to split
  98:    * @throws NullPointerException if str is null
  99:    */
 100:   public StringTokenizer(String str)
 101:   {
 102:     this(str, " \t\n\r\f", false);
 103:   }
 104: 
 105:   /**
 106:    * Create a new StringTokenizer, that splits the given string on
 107:    * the given delimiter characters.  It doesn't return the delimiter
 108:    * characters.
 109:    *
 110:    * @param str the string to split
 111:    * @param delim a string containing all delimiter characters
 112:    * @throws NullPointerException if either argument is null
 113:    */
 114:   public StringTokenizer(String str, String delim)
 115:   {
 116:     this(str, delim, false);
 117:   }
 118: 
 119:   /**
 120:    * Create a new StringTokenizer, that splits the given string on
 121:    * the given delimiter characters.  If you set
 122:    * <code>returnDelims</code> to <code>true</code>, the delimiter
 123:    * characters are returned as tokens of their own.  The delimiter
 124:    * tokens always consist of a single character.
 125:    *
 126:    * @param str the string to split
 127:    * @param delim a string containing all delimiter characters
 128:    * @param returnDelims tells, if you want to get the delimiters
 129:    * @throws NullPointerException if str or delim is null
 130:    */
 131:   public StringTokenizer(String str, String delim, boolean returnDelims)
 132:   {
 133:     len = str.length();
 134:     this.str = str;
 135:     // The toString() hack causes the NullPointerException.
 136:     this.delim = delim.toString();
 137:     this.retDelims = returnDelims;
 138:     this.pos = 0;
 139:   }
 140: 
 141:   /**
 142:    * Tells if there are more tokens.
 143:    *
 144:    * @return true if the next call of nextToken() will succeed
 145:    */
 146:   public boolean hasMoreTokens()
 147:   {
 148:     if (! retDelims)
 149:       {
 150:         while (pos < len && delim.indexOf(str.charAt(pos)) >= 0)
 151:           pos++;
 152:       }
 153:     return pos < len;
 154:   }
 155: 
 156:   /**
 157:    * Returns the nextToken, changing the delimiter set to the given
 158:    * <code>delim</code>.  The change of the delimiter set is
 159:    * permanent, ie. the next call of nextToken(), uses the same
 160:    * delimiter set.
 161:    *
 162:    * @param delim a string containing the new delimiter characters
 163:    * @return the next token with respect to the new delimiter characters
 164:    * @throws NoSuchElementException if there are no more tokens
 165:    * @throws NullPointerException if delim is null
 166:    */
 167:   public String nextToken(String delim) throws NoSuchElementException
 168:   {
 169:     this.delim = delim;
 170:     return nextToken();
 171:   }
 172: 
 173:   /**
 174:    * Returns the nextToken of the string.
 175:    *
 176:    * @return the next token with respect to the current delimiter characters
 177:    * @throws NoSuchElementException if there are no more tokens
 178:    */
 179:   public String nextToken() throws NoSuchElementException
 180:   {
 181:     if (pos < len && delim.indexOf(str.charAt(pos)) >= 0)
 182:       {
 183:         if (retDelims)
 184:           return str.substring(pos, ++pos);
 185:         while (++pos < len && delim.indexOf(str.charAt(pos)) >= 0);
 186:       }
 187:     if (pos < len)
 188:       {
 189:         int start = pos;
 190:         while (++pos < len && delim.indexOf(str.charAt(pos)) < 0);
 191: 
 192:         return str.substring(start, pos);
 193:       }
 194:     throw new NoSuchElementException();
 195:   }
 196: 
 197:   /**
 198:    * This does the same as hasMoreTokens. This is the
 199:    * <code>Enumeration</code> interface method.
 200:    *
 201:    * @return true, if the next call of nextElement() will succeed
 202:    * @see #hasMoreTokens()
 203:    */
 204:   public boolean hasMoreElements()
 205:   {
 206:     return hasMoreTokens();
 207:   }
 208: 
 209:   /**
 210:    * This does the same as nextTokens. This is the
 211:    * <code>Enumeration</code> interface method.
 212:    *
 213:    * @return the next token with respect to the current delimiter characters
 214:    * @throws NoSuchElementException if there are no more tokens
 215:    * @see #nextToken()
 216:    */
 217:   public Object nextElement() throws NoSuchElementException
 218:   {
 219:     return nextToken();
 220:   }
 221: 
 222:   /**
 223:    * This counts the number of remaining tokens in the string, with
 224:    * respect to the current delimiter set.
 225:    *
 226:    * @return the number of times <code>nextTokens()</code> will succeed
 227:    * @see #nextToken()
 228:    */
 229:   public int countTokens()
 230:   {
 231:     int count = 0;
 232:     int delimiterCount = 0;
 233:     boolean tokenFound = false; // Set when a non-delimiter is found
 234:     int tmpPos = pos;
 235: 
 236:     // Note for efficiency, we count up the delimiters rather than check
 237:     // retDelims every time we encounter one.  That way, we can
 238:     // just do the conditional once at the end of the method
 239:     while (tmpPos < len)
 240:       {
 241:         if (delim.indexOf(str.charAt(tmpPos++)) >= 0)
 242:           {
 243:             if (tokenFound)
 244:               {
 245:                 // Got to the end of a token
 246:                 count++;
 247:                 tokenFound = false;
 248:               }
 249:             delimiterCount++; // Increment for this delimiter
 250:           }
 251:         else
 252:           {
 253:             tokenFound = true;
 254:             // Get to the end of the token
 255:             while (tmpPos < len
 256:                    && delim.indexOf(str.charAt(tmpPos)) < 0)
 257:               ++tmpPos;
 258:           }
 259:       }
 260: 
 261:     // Make sure to count the last token
 262:     if (tokenFound)
 263:       count++;
 264: 
 265:     // if counting delmiters add them into the token count
 266:     return retDelims ? count + delimiterCount : count;
 267:   }
 268: } // class StringTokenizer