| 1 |
769 |
jeremybenn |
/* gnu/regexp/RETokenWordBoundary.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 |
|
|
|
| 39 |
|
|
package gnu.java.util.regex;
|
| 40 |
|
|
|
| 41 |
|
|
import gnu.java.lang.CPStringBuilder;
|
| 42 |
|
|
|
| 43 |
|
|
/**
|
| 44 |
|
|
* Represents a combination lookahead/lookbehind for POSIX [:alnum:].
|
| 45 |
|
|
*/
|
| 46 |
|
|
final class RETokenWordBoundary extends REToken
|
| 47 |
|
|
{
|
| 48 |
|
|
private boolean negated;
|
| 49 |
|
|
private int where;
|
| 50 |
|
|
static final int BEGIN = 1;
|
| 51 |
|
|
static final int END = 2;
|
| 52 |
|
|
|
| 53 |
|
|
RETokenWordBoundary (int subIndex, int where, boolean negated)
|
| 54 |
|
|
{
|
| 55 |
|
|
super (subIndex);
|
| 56 |
|
|
this.where = where;
|
| 57 |
|
|
this.negated = negated;
|
| 58 |
|
|
}
|
| 59 |
|
|
|
| 60 |
|
|
int getMaximumLength ()
|
| 61 |
|
|
{
|
| 62 |
|
|
return 0;
|
| 63 |
|
|
}
|
| 64 |
|
|
|
| 65 |
|
|
|
| 66 |
|
|
REMatch matchThis (CharIndexed input, REMatch mymatch)
|
| 67 |
|
|
{
|
| 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|
|
| 73 |
|
|
// ^ ^ ^ ^ ^ ^
|
| 74 |
|
|
boolean after = false; // is current character a letter or digit?
|
| 75 |
|
|
boolean before = false; // is previous character a letter or digit?
|
| 76 |
|
|
char ch;
|
| 77 |
|
|
|
| 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))
|
| 81 |
|
|
{
|
| 82 |
|
|
if ((ch =
|
| 83 |
|
|
input.charAt (mymatch.index - 1)) != CharIndexed.OUT_OF_BOUNDS)
|
| 84 |
|
|
{
|
| 85 |
|
|
before = Character.isLetterOrDigit (ch) || (ch == '_');
|
| 86 |
|
|
}
|
| 87 |
|
|
}
|
| 88 |
|
|
|
| 89 |
|
|
if ((ch = input.charAt (mymatch.index)) != CharIndexed.OUT_OF_BOUNDS)
|
| 90 |
|
|
{
|
| 91 |
|
|
after = Character.isLetterOrDigit (ch) || (ch == '_');
|
| 92 |
|
|
}
|
| 93 |
|
|
|
| 94 |
|
|
// if (before) and (!after), we're at end (\>)
|
| 95 |
|
|
// if (after) and (!before), we're at beginning (\<)
|
| 96 |
|
|
boolean doNext = false;
|
| 97 |
|
|
|
| 98 |
|
|
if ((where & BEGIN) == BEGIN)
|
| 99 |
|
|
{
|
| 100 |
|
|
doNext = after && !before;
|
| 101 |
|
|
}
|
| 102 |
|
|
if ((where & END) == END)
|
| 103 |
|
|
{
|
| 104 |
|
|
doNext ^= before && !after;
|
| 105 |
|
|
}
|
| 106 |
|
|
|
| 107 |
|
|
if (negated)
|
| 108 |
|
|
doNext = !doNext;
|
| 109 |
|
|
|
| 110 |
|
|
return (doNext ? mymatch : null);
|
| 111 |
|
|
}
|
| 112 |
|
|
|
| 113 |
|
|
boolean returnsFixedLengthMatches ()
|
| 114 |
|
|
{
|
| 115 |
|
|
return true;
|
| 116 |
|
|
}
|
| 117 |
|
|
|
| 118 |
|
|
int findFixedLengthMatches (CharIndexed input, REMatch mymatch, int max)
|
| 119 |
|
|
{
|
| 120 |
|
|
if (matchThis (input, mymatch) != null)
|
| 121 |
|
|
return max;
|
| 122 |
|
|
else
|
| 123 |
|
|
return 0;
|
| 124 |
|
|
}
|
| 125 |
|
|
|
| 126 |
|
|
void dump (CPStringBuilder os)
|
| 127 |
|
|
{
|
| 128 |
|
|
if (where == (BEGIN | END))
|
| 129 |
|
|
{
|
| 130 |
|
|
os.append (negated ? "\\B" : "\\b");
|
| 131 |
|
|
}
|
| 132 |
|
|
else if (where == BEGIN)
|
| 133 |
|
|
{
|
| 134 |
|
|
os.append ("\\<");
|
| 135 |
|
|
}
|
| 136 |
|
|
else
|
| 137 |
|
|
{
|
| 138 |
|
|
os.append ("\\>");
|
| 139 |
|
|
}
|
| 140 |
|
|
}
|
| 141 |
|
|
}
|