1 /* gnu/regexp/RETokenWordBoundary.java
2 Copyright (C) 2006 Free Software Foundation, Inc.
4 This file is part of GNU Classpath.
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)
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.
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
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
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. */
39 package gnu.java.util.regex;
41 import gnu.java.lang.CPStringBuilder;
44 * Represents a combination lookahead/lookbehind for POSIX [:alnum:].
46 final class RETokenWordBoundary extends REToken
48 private boolean negated;
50 static final int BEGIN = 1;
51 static final int END = 2;
53 RETokenWordBoundary (int subIndex, int where, boolean negated)
57 this.negated = negated;
60 int getMaximumLength ()
66 REMatch matchThis (CharIndexed input, REMatch mymatch)
68 // Word boundary means input[index-1] was a word character
69 // and input[index] is not, or input[index] is a word character
70 // and input[index-1] was not
71 // In the string "one two three", these positions match:
72 // |o|n|e| |t|w|o| |t|h|r|e|e|
74 boolean after = false; // is current character a letter or digit?
75 boolean before = false; // is previous character a letter or digit?
78 // TODO: Also check REG_ANCHORINDEX vs. anchor
79 if (((mymatch.eflags & RE.REG_ANCHORINDEX) != RE.REG_ANCHORINDEX)
80 || (mymatch.offset + mymatch.index > mymatch.anchor))
83 input.charAt (mymatch.index - 1)) != CharIndexed.OUT_OF_BOUNDS)
85 before = Character.isLetterOrDigit (ch) || (ch == '_');
89 if ((ch = input.charAt (mymatch.index)) != CharIndexed.OUT_OF_BOUNDS)
91 after = Character.isLetterOrDigit (ch) || (ch == '_');
94 // if (before) and (!after), we're at end (\>)
95 // if (after) and (!before), we're at beginning (\<)
96 boolean doNext = false;
98 if ((where & BEGIN) == BEGIN)
100 doNext = after && !before;
102 if ((where & END) == END)
104 doNext ^= before && !after;
110 return (doNext ? mymatch : null);
113 boolean returnsFixedLengthMatches ()
118 int findFixedLengthMatches (CharIndexed input, REMatch mymatch, int max)
120 if (matchThis (input, mymatch) != null)
126 void dump (CPStringBuilder os)
128 if (where == (BEGIN | END))
130 os.append (negated ? "\\B" : "\\b");
132 else if (where == BEGIN)