1 /* gnu/regexp/REMatch.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. */
40 import java
.io
.Serializable
;
43 * An instance of this class represents a match
44 * completed by a gnu.regexp matching function. It can be used
45 * to obtain relevant information about the location of a match
48 * @author <A HREF="mailto:wes@cacas.org">Wes Biggs</A>
50 public final class REMatch
implements Serializable
, Cloneable
{
51 private String matchedText
;
53 // These variables are package scope for fast access within the engine
54 int eflags
; // execution flags this match was made using
56 // Offset in source text where match was tried. This is zero-based;
57 // the actual position in the source text is given by (offset + anchor).
60 // Anchor position refers to the index into the source input
61 // at which the matching operation began.
62 // This is also useful for the ANCHORINDEX option.
65 // Package scope; used by RE.
66 int index
; // used while matching to mark current match position in input
67 int[] start
; // start positions (relative to offset) for each (sub)exp.
68 int[] end
; // end positions for the same
69 REMatch next
; // other possibility (to avoid having to use arrays)
70 boolean empty
; // empty string matched. This flag is used only within
72 int matchFlags
; // flags passed to match methods
73 static final int MF_FIND_ALL
= 0x01;
75 public Object
clone() {
77 REMatch copy
= (REMatch
) super.clone();
80 copy
.start
= (int[]) start
.clone();
81 copy
.end
= (int[]) end
.clone();
84 } catch (CloneNotSupportedException e
) {
85 throw new Error(); // doesn't happen
89 void assignFrom(REMatch other
) {
93 // need to deep clone?
97 REMatch(int subs
, int anchor
, int eflags
) {
98 start
= new int[subs
+1];
99 end
= new int[subs
+1];
100 this.anchor
= anchor
;
101 this.eflags
= eflags
;
105 void finish(CharIndexed text
) {
107 StringBuffer sb
= new StringBuffer();
109 for (i
= 0; i
< end
[0]; i
++)
110 sb
.append(text
.charAt(i
));
111 matchedText
= sb
.toString();
112 for (i
= 0; i
< start
.length
; i
++) {
113 // If any subexpressions didn't terminate, they don't count
114 // TODO check if this code ever gets hit
115 if ((start
[i
] == -1) ^
(end
[i
] == -1)) {
120 next
= null; // cut off alternates
123 /** Clears the current match and moves the offset to the new index. */
124 void clear(int index
) {
127 for (int i
= 0; i
< start
.length
; i
++) {
128 start
[i
] = end
[i
] = -1;
130 next
= null; // cut off alternates
134 * Returns the string matching the pattern. This makes it convenient
135 * to write code like the following:
138 * REMatch myMatch = myExpression.getMatch(myString);<br>
139 * if (myMatch != null) System.out.println("Regexp found: "+myMatch);
142 public String
toString() {
147 * Returns the index within the input text where the match in its entirety
150 public int getStartIndex() {
151 return offset
+ start
[0];
155 * Returns the index within the input string where the match in
156 * its entirety ends. The return value is the next position after
157 * the end of the string; therefore, a match created by the
161 * <code>REMatch myMatch = myExpression.getMatch(myString);</code>
163 * can be viewed (given that myMatch is not null) by creating
165 * <code>String theMatch = myString.substring(myMatch.getStartIndex(),
166 * myMatch.getEndIndex());</code>
168 * But you can save yourself that work, since the <code>toString()</code>
169 * method (above) does exactly that for you.
171 public int getEndIndex() {
172 return offset
+ end
[0];
176 * Returns the string matching the given subexpression. The subexpressions
177 * are indexed starting with one, not zero. That is, the subexpression
178 * identified by the first set of parentheses in a regular expression
179 * could be retrieved from an REMatch by calling match.toString(1).
181 * @param sub Index of the subexpression.
183 public String
toString(int sub
) {
184 if ((sub
>= start
.length
) || sub
< 0)
185 throw new IndexOutOfBoundsException("No group " + sub
);
186 if (start
[sub
] == -1) return null;
187 return (matchedText
.substring(start
[sub
],end
[sub
]));
191 * Returns the index within the input string used to generate this match
192 * where subexpression number <i>sub</i> begins, or <code>-1</code> if
193 * the subexpression does not exist. The initial position is zero.
195 * @param sub Subexpression index
196 * @deprecated Use getStartIndex(int) instead.
198 public int getSubStartIndex(int sub
) {
199 if (sub
>= start
.length
) return -1;
201 return (x
== -1) ? x
: offset
+ x
;
205 * Returns the index within the input string used to generate this match
206 * where subexpression number <i>sub</i> begins, or <code>-1</code> if
207 * the subexpression does not exist. The initial position is zero.
209 * @param sub Subexpression index
210 * @since gnu.regexp 1.1.0
212 public int getStartIndex(int sub
) {
213 if (sub
>= start
.length
) return -1;
215 return (x
== -1) ? x
: offset
+ x
;
219 * Returns the index within the input string used to generate this match
220 * where subexpression number <i>sub</i> ends, or <code>-1</code> if
221 * the subexpression does not exist. The initial position is zero.
223 * @param sub Subexpression index
224 * @deprecated Use getEndIndex(int) instead
226 public int getSubEndIndex(int sub
) {
227 if (sub
>= start
.length
) return -1;
229 return (x
== -1) ? x
: offset
+ x
;
233 * Returns the index within the input string used to generate this match
234 * where subexpression number <i>sub</i> ends, or <code>-1</code> if
235 * the subexpression does not exist. The initial position is zero.
237 * @param sub Subexpression index
239 public int getEndIndex(int sub
) {
240 if (sub
>= start
.length
) return -1;
242 return (x
== -1) ? x
: offset
+ x
;
246 * Substitute the results of this match to create a new string.
247 * This is patterned after PERL, so the tokens to watch out for are
248 * <code>$0</code> through <code>$9</code>. <code>$0</code> matches
249 * the full substring matched; <code>$<i>n</i></code> matches
250 * subexpression number <i>n</i>.
251 * <code>$10, $11, ...</code> may match the 10th, 11th, ... subexpressions
252 * if such subexpressions exist.
254 * @param input A string consisting of literals and <code>$<i>n</i></code> tokens.
256 public String
substituteInto(String input
) {
257 // a la Perl, $0 is whole thing, $1 - $9 are subexpressions
258 StringBuffer output
= new StringBuffer();
260 for (pos
= 0; pos
< input
.length()-1; pos
++) {
261 if ((input
.charAt(pos
) == '$') && (Character
.isDigit(input
.charAt(pos
+1)))) {
262 int val
= Character
.digit(input
.charAt(++pos
),10);
264 while (pos1
< input
.length() &&
265 Character
.isDigit(input
.charAt(pos1
))) {
266 int val1
= val
*10 + Character
.digit(input
.charAt(pos1
),10);
267 if (val1
>= start
.length
) break;
273 if (val
< start
.length
) {
274 output
.append(toString(val
));
276 } else output
.append(input
.charAt(pos
));
278 if (pos
< input
.length()) output
.append(input
.charAt(pos
));
279 return output
.toString();
282 static class REMatchList
{
288 /* Not used now. But we may need this some day?
289 void addHead(REMatch newone) {
293 while (tail.next != null) {
298 REMatch tmp = newone;
299 while (tmp.next != null) tmp = tmp.next;
305 void addTail(REMatch newone
) {
313 while (tail
.next
!= null) {