libjava/classpath/gnu/java/util/regex/REToken.java

   1 /* gnu/regexp/REToken.java
   2    Copyright (C) 2006 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 package gnu.java.util.regex;
  39 import java.io.Serializable;
  40
  41 abstract class REToken implements Serializable, Cloneable {
  42
  43   protected REToken next = null;
  44   protected REToken uncle = null;
  45   protected int subIndex;
  46   protected boolean unicodeAware = true;
  47
  48   public Object clone() {
  49     try {
  50       REToken copy = (REToken) super.clone();
  51       return copy;
  52     } catch (CloneNotSupportedException e) {
  53       throw new Error(); // doesn't happen
  54     }
  55   }
  56
  57   protected REToken(int subIndex) {
  58       this.subIndex = subIndex;
  59   }
  60
  61   int getMinimumLength() {
  62     return 0;
  63   }
  64
  65   int getMaximumLength() {
  66     return Integer.MAX_VALUE;
  67   }
  68
  69   void setUncle(REToken anUncle) {
  70     uncle = anUncle;
  71   }
  72
  73     /** Returns true if the match succeeded, false if it failed. */
  74     boolean match(CharIndexed input, REMatch mymatch) {
  75         return match(input, mymatch, false);
  76     }
  77     boolean matchFake(CharIndexed input, REMatch mymatch) {
  78         return match(input, mymatch, true);
  79     }
  80
  81     private boolean match(CharIndexed input, REMatch mymatch, boolean fake) {
  82         if (!fake) {
  83             setHitEnd(input, mymatch);
  84         }
  85         REMatch m = matchThis(input, mymatch);
  86         if (m == null) return false;
  87         if (next(input, m)) {
  88             mymatch.assignFrom(m);
  89             return true;
  90         }
  91         return false;
  92     }
  93
  94     /** Sets whether the matching occurs at the end of input */
  95     void setHitEnd(CharIndexed input, REMatch mymatch) {
  96         input.setHitEnd(mymatch);
  97     }
  98
  99     /** Returns true if the match succeeded, false if it failed.
 100       * The matching is done against this REToken only. Chained
 101       * tokens are not checked.
 102       * This method is used to define the default match method.
 103       * Simple subclasses of REToken, for example, such that
 104       * matches only one character, should implement this method.
 105       * Then the default match method will work.  But complicated
 106       * subclasses of REToken, which needs a special match method,
 107       * do not have to implement this method.
 108       */
 109     REMatch matchThis(CharIndexed input, REMatch mymatch) {
 110         throw new UnsupportedOperationException(
 111             "This REToken does not have a matchThis method");
 112     }
 113
 114     /** Returns true if the rest of the tokens match, false if they fail. */
 115     protected boolean next(CharIndexed input, REMatch mymatch) {
 116         REToken nextToken = getNext();
 117         if (nextToken == null) return true;
 118         return nextToken.match(input, mymatch);
 119     }
 120
 121     /** Returns the next REToken chained to this REToken. */
 122     REToken getNext() {
 123         return (next != null ? next : uncle);
 124     }
 125
 126     /** Finds a match at the position specified by the given REMatch.
 127       * If necessary, adds a BacktrackStack.Backtrack object to backtrackStack
 128       * of the REmatch found this time so that another possible match
 129       * may be found when backtrack is called.
 130       * By default, nothing is added to the backtrackStack.
 131       * @param input Input character sequence.
 132       * @param mymatch Position at which a match should be found
 133       * @return REMatch object if a match was found, null otherwise.
 134       */
 135     REMatch findMatch(CharIndexed input, REMatch mymatch) {
 136         boolean b = match(input, mymatch);
 137         if (b) return mymatch;
 138         return null;
 139     }
 140
 141     boolean returnsFixedLengthMatches() {
 142         return false;
 143     }
 144
 145     int findFixedLengthMatches(CharIndexed input, REMatch mymatch, int max) {
 146         throw new UnsupportedOperationException(
 147             "This token does not support findFixedLengthMatches");
 148     }
 149
 150     /**
 151       * Backtrack to another possibility.
 152       * Ordinary REToken cannot do anything if this method is called.
 153       */
 154     REMatch backtrack(CharIndexed input, REMatch mymatch, Object param) {
 155         throw new IllegalStateException("This token cannot be backtracked to");
 156     }
 157
 158   boolean chain(REToken token) {
 159       next = token;
 160       return true; // Token was accepted
 161   }
 162
 163   abstract void dump(StringBuffer os);
 164
 165   void dumpAll(StringBuffer os) {
 166     dump(os);
 167     if (next != null) next.dumpAll(os);
 168   }
 169
 170   public String toString() {
 171     StringBuffer os = new StringBuffer();
 172     dump(os);
 173     return os.toString();
 174   }
 175
 176   /**
 177     * Converts the character argument to lowercase.
 178     * @param ch the character to be converted.
 179     * @param unicodeAware If true, use java.lang.Character#toLowerCase;
 180     * otherwise, only US-ASCII charactes can be converted.
 181     * @return the lowercase equivalent of the character, if any;
 182     * otherwise, the character itself.
 183     */
 184   public static char toLowerCase(char ch, boolean unicodeAware) {
 185     if (unicodeAware) return Character.toLowerCase(ch);
 186     if (ch >= 'A' && ch <= 'Z') return (char)(ch + 'a' - 'A');
 187     return ch;
 188   }
 189
 190   /**
 191     * Converts the character argument to uppercase.
 192     * @param ch the character to be converted.
 193     * @param unicodeAware If true, use java.lang.Character#toUpperCase;
 194     * otherwise, only US-ASCII charactes can be converted.
 195     * @return the uppercase equivalent of the character, if any;
 196     * otherwise, the character itself.
 197     */
 198   public static char toUpperCase(char ch, boolean unicodeAware) {
 199     if (unicodeAware) return Character.toUpperCase(ch);
 200     if (ch >= 'a' && ch <= 'z') return (char)(ch + 'A' - 'a');
 201     return ch;
 202   }
 203
 204 }