libjava/classpath/java/util/regex/Pattern.java

   1 /* Pattern.java -- Compiled regular expression ready to be applied.
   2    Copyright (C) 2002, 2004, 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 package java.util.regex;
  39
  40 import gnu.regexp.RE;
  41 import gnu.regexp.REException;
  42 import gnu.regexp.RESyntax;
  43
  44 import java.io.Serializable;
  45 import java.util.ArrayList;
  46
  47
  48 /**
  49  * Compiled regular expression ready to be applied.
  50  *
  51  * @since 1.4
  52  */
  53 public final class Pattern implements Serializable
  54 {
  55   private static final long serialVersionUID = 5073258162644648461L;
  56
  57   public static final int CANON_EQ = 128;
  58   public static final int CASE_INSENSITIVE = 2;
  59   public static final int COMMENTS = 4;
  60   public static final int DOTALL = 32;
  61   public static final int MULTILINE = 8;
  62   public static final int UNICODE_CASE = 64;
  63   public static final int UNIX_LINES = 1;
  64
  65   private final String regex;
  66   private final int flags;
  67
  68   private final RE re;
  69
  70   private Pattern (String regex, int flags)
  71     throws PatternSyntaxException
  72   {
  73     this.regex = regex;
  74     this.flags = flags;
  75
  76     int gnuFlags = 0;
  77     if ((flags & CASE_INSENSITIVE) != 0)
  78       gnuFlags |= RE.REG_ICASE;
  79     if ((flags & MULTILINE) != 0)
  80       gnuFlags |= RE.REG_MULTILINE;
  81     if ((flags & DOTALL) != 0)
  82       gnuFlags |= RE.REG_DOT_NEWLINE;
  83     // not yet supported:
  84     // if ((flags & UNICODE_CASE) != 0) gnuFlags =
  85     // if ((flags & CANON_EQ) != 0) gnuFlags =
  86
  87     RESyntax syntax = RESyntax.RE_SYNTAX_JAVA_1_4;
  88     if ((flags & UNIX_LINES) != 0)
  89       {
  90         // Use a syntax set with \n for linefeeds?
  91         syntax = new RESyntax(syntax);
  92         syntax.setLineSeparator("\n");
  93       }
  94
  95     if ((flags & COMMENTS) != 0)
  96       {
  97         // Use a syntax with support for comments?
  98       }
  99
 100     try
 101       {
 102         this.re = new RE(regex, gnuFlags, syntax);
 103       }
 104     catch (REException e)
 105       {
 106         PatternSyntaxException pse;
 107         pse = new PatternSyntaxException(e.getMessage(),
 108                                          regex, e.getPosition());
 109         pse.initCause(e);
 110         throw pse;
 111       }
 112   }
 113
 114   // package private accessor method
 115   RE getRE()
 116   {
 117     return re;
 118   }
 119
 120   /**
 121    * @param regex The regular expression
 122    *
 123    * @exception PatternSyntaxException If the expression's syntax is invalid
 124    */
 125   public static Pattern compile (String regex)
 126     throws PatternSyntaxException
 127   {
 128     return compile(regex, 0);
 129   }
 130
 131   /**
 132    * @param regex The regular expression
 133    * @param flags The match flags, a bit mask
 134    *
 135    * @exception PatternSyntaxException If the expression's syntax is invalid
 136    * @exception IllegalArgumentException If bit values other than those
 137    * corresponding to the defined match flags are set in flags
 138    */
 139   public static Pattern compile (String regex, int flags)
 140     throws PatternSyntaxException
 141   {
 142     // FIXME: check which flags are really accepted
 143     if ((flags & ~0xEF) != 0)
 144       throw new IllegalArgumentException ();
 145
 146     return new Pattern (regex, flags);
 147   }
 148
 149   public int flags ()
 150   {
 151     return this.flags;
 152   }
 153
 154   /**
 155    * @param regex The regular expression
 156    * @param input The character sequence to be matched
 157    *
 158    * @exception PatternSyntaxException If the expression's syntax is invalid
 159    */
 160   public static boolean matches (String regex, CharSequence input)
 161   {
 162     return compile(regex).matcher(input).matches();
 163   }
 164
 165   /**
 166    * @param input The character sequence to be matched
 167    */
 168   public Matcher matcher (CharSequence input)
 169   {
 170     return new Matcher(this, input);
 171   }
 172
 173   /**
 174    * @param input The character sequence to be matched
 175    */
 176   public String[] split (CharSequence input)
 177   {
 178     return split(input, 0);
 179   }
 180
 181   /**
 182    * @param input The character sequence to be matched
 183    * @param limit The result threshold
 184    */
 185   public String[] split (CharSequence input, int limit)
 186   {
 187     Matcher matcher = new Matcher(this, input);
 188     ArrayList list = new ArrayList();
 189     int empties = 0;
 190     int count = 0;
 191     int start = 0;
 192     int end;
 193     boolean matched = matcher.find();
 194
 195     while (matched && (limit <= 0 || count < limit - 1))
 196       {
 197         ++count;
 198         end = matcher.start();
 199         if (start == end)
 200           empties++;
 201         else
 202           {
 203             while (empties > 0)
 204               {
 205                 list.add("");
 206                 empties--;
 207               }
 208
 209             String text = input.subSequence(start, end).toString();
 210             list.add(text);
 211           }
 212         start = matcher.end();
 213         matched = matcher.find();
 214       }
 215
 216     // We matched nothing.
 217     if (!matched && count == 0)
 218       return new String[] { input.toString() };
 219
 220     // Is the last token empty?
 221     boolean emptyLast = (start == input.length());
 222
 223     // Can/Must we add empties or an extra last token at the end?
 224     if (list.size() < limit || limit < 0 || (limit == 0 && !emptyLast))
 225       {
 226         if (limit > list.size())
 227           {
 228             int max = limit - list.size();
 229             empties = (empties > max) ? max : empties;
 230           }
 231         while (empties > 0)
 232           {
 233             list.add("");
 234             empties--;
 235           }
 236       }
 237
 238     // last token at end
 239     if (limit != 0 || (limit == 0 && !emptyLast))
 240       {
 241         String t = input.subSequence(start, input.length()).toString();
 242         if ("".equals(t) && limit == 0)
 243           ; // Don't add.
 244         else
 245           list.add(t);
 246       }
 247
 248     String[] output = new String [list.size()];
 249     list.toArray(output);
 250     return output;
 251   }
 252
 253   public String pattern ()
 254   {
 255     return regex;
 256   }
 257 }