Menu
▾
▴
[Jnode-svn-commits] SF.net SVN: jnode: [3215] trunk/core/src/openjdk/java
|
From: <ls...@us...> - 2007-05-17 18:34:47
|
Revision: 3215
http://jnode.svn.sourceforge.net/jnode/?rev=3215&view=rev
Author: lsantha
Date: 2007-05-17 11:34:44 -0700 (Thu, 17 May 2007)
Log Message:
-----------
Fixed misplaced directory.
Added Paths:
-----------
trunk/core/src/openjdk/java/java/util/
trunk/core/src/openjdk/java/java/util/regex/
trunk/core/src/openjdk/java/java/util/regex/ASCII.java
trunk/core/src/openjdk/java/java/util/regex/MatchResult.java
trunk/core/src/openjdk/java/java/util/regex/Matcher.java
trunk/core/src/openjdk/java/java/util/regex/Pattern.java
trunk/core/src/openjdk/java/java/util/regex/PatternSyntaxException.java
trunk/core/src/openjdk/java/java/util/regex/package.html
Removed Paths:
-------------
trunk/core/src/openjdk/java/util/
Copied: trunk/core/src/openjdk/java/java/util/regex/ASCII.java (from rev 3211, trunk/core/src/openjdk/java/util/regex/ASCII.java)
===================================================================
--- trunk/core/src/openjdk/java/java/util/regex/ASCII.java (rev 0)
+++ trunk/core/src/openjdk/java/java/util/regex/ASCII.java 2007-05-17 18:34:44 UTC (rev 3215)
@@ -0,0 +1,274 @@
+/*
+ * Copyright 1999-2000 Sun Microsystems, Inc. All Rights Reserved.
+ * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
+ *
+ * This code is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 only, as
+ * published by the Free Software Foundation. Sun designates this
+ * particular file as subject to the "Classpath" exception as provided
+ * by Sun in the LICENSE file that accompanied this code.
+ *
+ * This code is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
+ * version 2 for more details (a copy is included in the LICENSE file that
+ * accompanied this code).
+ *
+ * You should have received a copy of the GNU General Public License version
+ * 2 along with this work; if not, write to the Free Software Foundation,
+ * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
+ *
+ * Please contact Sun Microsystems, Inc., 4150 Network Circle, Santa Clara,
+ * CA 95054 USA or visit www.sun.com if you need additional information or
+ * have any questions.
+ */
+
+package java.util.regex;
+
+
+/**
+ * Utility class that implements the standard C ctype functionality.
+ *
+ * @author Hong Zhang
+ */
+
+final class ASCII {
+
+ static final int UPPER = 0x00000100;
+
+ static final int LOWER = 0x00000200;
+
+ static final int DIGIT = 0x00000400;
+
+ static final int SPACE = 0x00000800;
+
+ static final int PUNCT = 0x00001000;
+
+ static final int CNTRL = 0x00002000;
+
+ static final int BLANK = 0x00004000;
+
+ static final int HEX = 0x00008000;
+
+ static final int UNDER = 0x00010000;
+
+ static final int ASCII = 0x0000FF00;
+
+ static final int ALPHA = (UPPER|LOWER);
+
+ static final int ALNUM = (UPPER|LOWER|DIGIT);
+
+ static final int GRAPH = (PUNCT|UPPER|LOWER|DIGIT);
+
+ static final int WORD = (UPPER|LOWER|UNDER|DIGIT);
+
+ static final int XDIGIT = (HEX);
+
+ private static final int[] ctype = new int[] {
+ CNTRL, /* 00 (NUL) */
+ CNTRL, /* 01 (SOH) */
+ CNTRL, /* 02 (STX) */
+ CNTRL, /* 03 (ETX) */
+ CNTRL, /* 04 (EOT) */
+ CNTRL, /* 05 (ENQ) */
+ CNTRL, /* 06 (ACK) */
+ CNTRL, /* 07 (BEL) */
+ CNTRL, /* 08 (BS) */
+ SPACE+CNTRL+BLANK, /* 09 (HT) */
+ SPACE+CNTRL, /* 0A (LF) */
+ SPACE+CNTRL, /* 0B (VT) */
+ SPACE+CNTRL, /* 0C (FF) */
+ SPACE+CNTRL, /* 0D (CR) */
+ CNTRL, /* 0E (SI) */
+ CNTRL, /* 0F (SO) */
+ CNTRL, /* 10 (DLE) */
+ CNTRL, /* 11 (DC1) */
+ CNTRL, /* 12 (DC2) */
+ CNTRL, /* 13 (DC3) */
+ CNTRL, /* 14 (DC4) */
+ CNTRL, /* 15 (NAK) */
+ CNTRL, /* 16 (SYN) */
+ CNTRL, /* 17 (ETB) */
+ CNTRL, /* 18 (CAN) */
+ CNTRL, /* 19 (EM) */
+ CNTRL, /* 1A (SUB) */
+ CNTRL, /* 1B (ESC) */
+ CNTRL, /* 1C (FS) */
+ CNTRL, /* 1D (GS) */
+ CNTRL, /* 1E (RS) */
+ CNTRL, /* 1F (US) */
+ SPACE+BLANK, /* 20 SPACE */
+ PUNCT, /* 21 ! */
+ PUNCT, /* 22 " */
+ PUNCT, /* 23 # */
+ PUNCT, /* 24 $ */
+ PUNCT, /* 25 % */
+ PUNCT, /* 26 & */
+ PUNCT, /* 27 ' */
+ PUNCT, /* 28 ( */
+ PUNCT, /* 29 ) */
+ PUNCT, /* 2A * */
+ PUNCT, /* 2B + */
+ PUNCT, /* 2C , */
+ PUNCT, /* 2D - */
+ PUNCT, /* 2E . */
+ PUNCT, /* 2F / */
+ DIGIT+HEX+0, /* 30 0 */
+ DIGIT+HEX+1, /* 31 1 */
+ DIGIT+HEX+2, /* 32 2 */
+ DIGIT+HEX+3, /* 33 3 */
+ DIGIT+HEX+4, /* 34 4 */
+ DIGIT+HEX+5, /* 35 5 */
+ DIGIT+HEX+6, /* 36 6 */
+ DIGIT+HEX+7, /* 37 7 */
+ DIGIT+HEX+8, /* 38 8 */
+ DIGIT+HEX+9, /* 39 9 */
+ PUNCT, /* 3A : */
+ PUNCT, /* 3B ; */
+ PUNCT, /* 3C < */
+ PUNCT, /* 3D = */
+ PUNCT, /* 3E > */
+ PUNCT, /* 3F ? */
+ PUNCT, /* 40 @ */
+ UPPER+HEX+10, /* 41 A */
+ UPPER+HEX+11, /* 42 B */
+ UPPER+HEX+12, /* 43 C */
+ UPPER+HEX+13, /* 44 D */
+ UPPER+HEX+14, /* 45 E */
+ UPPER+HEX+15, /* 46 F */
+ UPPER+16, /* 47 G */
+ UPPER+17, /* 48 H */
+ UPPER+18, /* 49 I */
+ UPPER+19, /* 4A J */
+ UPPER+20, /* 4B K */
+ UPPER+21, /* 4C L */
+ UPPER+22, /* 4D M */
+ UPPER+23, /* 4E N */
+ UPPER+24, /* 4F O */
+ UPPER+25, /* 50 P */
+ UPPER+26, /* 51 Q */
+ UPPER+27, /* 52 R */
+ UPPER+28, /* 53 S */
+ UPPER+29, /* 54 T */
+ UPPER+30, /* 55 U */
+ UPPER+31, /* 56 V */
+ UPPER+32, /* 57 W */
+ UPPER+33, /* 58 X */
+ UPPER+34, /* 59 Y */
+ UPPER+35, /* 5A Z */
+ PUNCT, /* 5B [ */
+ PUNCT, /* 5C \ */
+ PUNCT, /* 5D ] */
+ PUNCT, /* 5E ^ */
+ PUNCT|UNDER, /* 5F _ */
+ PUNCT, /* 60 ` */
+ LOWER+HEX+10, /* 61 a */
+ LOWER+HEX+11, /* 62 b */
+ LOWER+HEX+12, /* 63 c */
+ LOWER+HEX+13, /* 64 d */
+ LOWER+HEX+14, /* 65 e */
+ LOWER+HEX+15, /* 66 f */
+ LOWER+16, /* 67 g */
+ LOWER+17, /* 68 h */
+ LOWER+18, /* 69 i */
+ LOWER+19, /* 6A j */
+ LOWER+20, /* 6B k */
+ LOWER+21, /* 6C l */
+ LOWER+22, /* 6D m */
+ LOWER+23, /* 6E n */
+ LOWER+24, /* 6F o */
+ LOWER+25, /* 70 p */
+ LOWER+26, /* 71 q */
+ LOWER+27, /* 72 r */
+ LOWER+28, /* 73 s */
+ LOWER+29, /* 74 t */
+ LOWER+30, /* 75 u */
+ LOWER+31, /* 76 v */
+ LOWER+32, /* 77 w */
+ LOWER+33, /* 78 x */
+ LOWER+34, /* 79 y */
+ LOWER+35, /* 7A z */
+ PUNCT, /* 7B { */
+ PUNCT, /* 7C | */
+ PUNCT, /* 7D } */
+ PUNCT, /* 7E ~ */
+ CNTRL, /* 7F (DEL) */
+ };
+
+ static int getType(int ch) {
+ return ((ch & 0xFFFFFF80) == 0 ? ctype[ch] : 0);
+ }
+
+ static boolean isType(int ch, int type) {
+ return (getType(ch) & type) != 0;
+ }
+
+ static boolean isAscii(int ch) {
+ return ((ch & 0xFFFFFF80) == 0);
+ }
+
+ static boolean isAlpha(int ch) {
+ return isType(ch, ALPHA);
+ }
+
+ static boolean isDigit(int ch) {
+ return ((ch-'0')|('9'-ch)) >= 0;
+ }
+
+ static boolean isAlnum(int ch) {
+ return isType(ch, ALNUM);
+ }
+
+ static boolean isGraph(int ch) {
+ return isType(ch, GRAPH);
+ }
+
+ static boolean isPrint(int ch) {
+ return ((ch-0x20)|(0x7E-ch)) >= 0;
+ }
+
+ static boolean isPunct(int ch) {
+ return isType(ch, PUNCT);
+ }
+
+ static boolean isSpace(int ch) {
+ return isType(ch, SPACE);
+ }
+
+ static boolean isHexDigit(int ch) {
+ return isType(ch, HEX);
+ }
+
+ static boolean isOctDigit(int ch) {
+ return ((ch-'0')|('7'-ch)) >= 0;
+ }
+
+ static boolean isCntrl(int ch) {
+ return isType(ch, CNTRL);
+ }
+
+ static boolean isLower(int ch) {
+ return ((ch-'a')|('z'-ch)) >= 0;
+ }
+
+ static boolean isUpper(int ch) {
+ return ((ch-'A')|('Z'-ch)) >= 0;
+ }
+
+ static boolean isWord(int ch) {
+ return isType(ch, WORD);
+ }
+
+ static int toDigit(int ch) {
+ return (ctype[ch & 0x7F] & 0x3F);
+ }
+
+ static int toLower(int ch) {
+ return isUpper(ch) ? (ch + 0x20) : ch;
+ }
+
+ static int toUpper(int ch) {
+ return isLower(ch) ? (ch - 0x20) : ch;
+ }
+
+}
Copied: trunk/core/src/openjdk/java/java/util/regex/MatchResult.java (from rev 3211, trunk/core/src/openjdk/java/util/regex/MatchResult.java)
===================================================================
--- trunk/core/src/openjdk/java/java/util/regex/MatchResult.java (rev 0)
+++ trunk/core/src/openjdk/java/java/util/regex/MatchResult.java 2007-05-17 18:34:44 UTC (rev 3215)
@@ -0,0 +1,189 @@
+/*
+ * Copyright 2003-2004 Sun Microsystems, Inc. All Rights Reserved.
+ * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
+ *
+ * This code is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 only, as
+ * published by the Free Software Foundation. Sun designates this
+ * particular file as subject to the "Classpath" exception as provided
+ * by Sun in the LICENSE file that accompanied this code.
+ *
+ * This code is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
+ * version 2 for more details (a copy is included in the LICENSE file that
+ * accompanied this code).
+ *
+ * You should have received a copy of the GNU General Public License version
+ * 2 along with this work; if not, write to the Free Software Foundation,
+ * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
+ *
+ * Please contact Sun Microsystems, Inc., 4150 Network Circle, Santa Clara,
+ * CA 95054 USA or visit www.sun.com if you need additional information or
+ * have any questions.
+ */
+
+package java.util.regex;
+
+/**
+ * The result of a match operation.
+ *
+ * <p>This interface contains query methods used to determine the
+ * results of a match against a regular expression. The match boundaries,
+ * groups and group boundaries can be seen but not modified through
+ * a <code>MatchResult</code>.
+ *
+ * @author Michael McCloskey
+ * @version 1.12 05/05/07
+ * @see Matcher
+ * @since 1.5
+ */
+public interface MatchResult {
+
+ /**
+ * Returns the start index of the match.
+ *
+ * @return The index of the first character matched
+ *
+ * @throws IllegalStateException
+ * If no match has yet been attempted,
+ * or if the previous match operation failed
+ */
+ public int start();
+
+ /**
+ * Returns the start index of the subsequence captured by the given group
+ * during this match.
+ *
+ * <p> <a href="Pattern.html#cg">Capturing groups</a> are indexed from left
+ * to right, starting at one. Group zero denotes the entire pattern, so
+ * the expression <i>m.</i><tt>start(0)</tt> is equivalent to
+ * <i>m.</i><tt>start()</tt>. </p>
+ *
+ * @param group
+ * The index of a capturing group in this matcher's pattern
+ *
+ * @return The index of the first character captured by the group,
+ * or <tt>-1</tt> if the match was successful but the group
+ * itself did not match anything
+ *
+ * @throws IllegalStateException
+ * If no match has yet been attempted,
+ * or if the previous match operation failed
+ *
+ * @throws IndexOutOfBoundsException
+ * If there is no capturing group in the pattern
+ * with the given index
+ */
+ public int start(int group);
+
+ /**
+ * Returns the offset after the last character matched. </p>
+ *
+ * @return @return The offset after the last character matched
+ *
+ * @throws IllegalStateException
+ * If no match has yet been attempted,
+ * or if the previous match operation failed
+ */
+ public int end();
+
+ /**
+ * Returns the offset after the last character of the subsequence
+ * captured by the given group during this match.
+ *
+ * <p> <a href="Pattern.html#cg">Capturing groups</a> are indexed from left
+ * to right, starting at one. Group zero denotes the entire pattern, so
+ * the expression <i>m.</i><tt>end(0)</tt> is equivalent to
+ * <i>m.</i><tt>end()</tt>. </p>
+ *
+ * @param group
+ * The index of a capturing group in this matcher's pattern
+ *
+ * @return The offset after the last character captured by the group,
+ * or <tt>-1</tt> if the match was successful
+ * but the group itself did not match anything
+ *
+ * @throws IllegalStateException
+ * If no match has yet been attempted,
+ * or if the previous match operation failed
+ *
+ * @throws IndexOutOfBoundsException
+ * If there is no capturing group in the pattern
+ * with the given index
+ */
+ public int end(int group);
+
+ /**
+ * Returns the input subsequence matched by the previous match.
+ *
+ * <p> For a matcher <i>m</i> with input sequence <i>s</i>,
+ * the expressions <i>m.</i><tt>group()</tt> and
+ * <i>s.</i><tt>substring(</tt><i>m.</i><tt>start(),</tt> <i>m.</i><tt>end())</tt>
+ * are equivalent. </p>
+ *
+ * <p> Note that some patterns, for example <tt>a*</tt>, match the empty
+ * string. This method will return the empty string when the pattern
+ * successfully matches the empty string in the input. </p>
+ *
+ * @return The (possibly empty) subsequence matched by the previous match,
+ * in string form
+ *
+ * @throws IllegalStateException
+ * If no match has yet been attempted,
+ * or if the previous match operation failed
+ */
+ public String group();
+
+ /**
+ * Returns the input subsequence captured by the given group during the
+ * previous match operation.
+ *
+ * <p> For a matcher <i>m</i>, input sequence <i>s</i>, and group index
+ * <i>g</i>, the expressions <i>m.</i><tt>group(</tt><i>g</i><tt>)</tt> and
+ * <i>s.</i><tt>substring(</tt><i>m.</i><tt>start(</tt><i>g</i><tt>),</tt> <i>m.</i><tt>end(</tt><i>g</i><tt>))</tt>
+ * are equivalent. </p>
+ *
+ * <p> <a href="Pattern.html#cg">Capturing groups</a> are indexed from left
+ * to right, starting at one. Group zero denotes the entire pattern, so
+ * the expression <tt>m.group(0)</tt> is equivalent to <tt>m.group()</tt>.
+ * </p>
+ *
+ * <p> If the match was successful but the group specified failed to match
+ * any part of the input sequence, then <tt>null</tt> is returned. Note
+ * that some groups, for example <tt>(a*)</tt>, match the empty string.
+ * This method will return the empty string when such a group successfully
+ * matches the empty string in the input. </p>
+ *
+ * @param group
+ * The index of a capturing group in this matcher's pattern
+ *
+ * @return The (possibly empty) subsequence captured by the group
+ * during the previous match, or <tt>null</tt> if the group
+ * failed to match part of the input
+ *
+ * @throws IllegalStateException
+ * If no match has yet been attempted,
+ * or if the previous match operation failed
+ *
+ * @throws IndexOutOfBoundsException
+ * If there is no capturing group in the pattern
+ * with the given index
+ */
+ public String group(int group);
+
+ /**
+ * Returns the number of capturing groups in this match result's pattern.
+ *
+ * <p> Group zero denotes the entire pattern by convention. It is not
+ * included in this count.
+ *
+ * <p> Any non-negative integer smaller than or equal to the value
+ * returned by this method is guaranteed to be a valid group index for
+ * this matcher. </p>
+ *
+ * @return The number of capturing groups in this matcher's pattern
+ */
+ public int groupCount();
+
+}
Copied: trunk/core/src/openjdk/java/java/util/regex/Matcher.java (from rev 3211, trunk/core/src/openjdk/java/util/regex/Matcher.java)
===================================================================
--- trunk/core/src/openjdk/java/java/util/regex/Matcher.java (rev 0)
+++ trunk/core/src/openjdk/java/java/util/regex/Matcher.java 2007-05-17 18:34:44 UTC (rev 3215)
@@ -0,0 +1,1175 @@
+/*
+ * Copyright 1999-2006 Sun Microsystems, Inc. All Rights Reserved.
+ * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
+ *
+ * This code is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 only, as
+ * published by the Free Software Foundation. Sun designates this
+ * particular file as subject to the "Classpath" exception as provided
+ * by Sun in the LICENSE file that accompanied this code.
+ *
+ * This code is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
+ * version 2 for more details (a copy is included in the LICENSE file that
+ * accompanied this code).
+ *
+ * You should have received a copy of the GNU General Public License version
+ * 2 along with this work; if not, write to the Free Software Foundation,
+ * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
+ *
+ * Please contact Sun Microsystems, Inc., 4150 Network Circle, Santa Clara,
+ * CA 95054 USA or visit www.sun.com if you need additional information or
+ * have any questions.
+ */
+
+package java.util.regex;
+
+
+/**
+ * An engine that performs match operations on a {@link java.lang.CharSequence
+ * </code>character sequence<code>} by interpreting a {@link Pattern}.
+ *
+ * <p> A matcher is created from a pattern by invoking the pattern's {@link
+ * Pattern#matcher matcher} method. Once created, a matcher can be used to
+ * perform three different kinds of match operations:
+ *
+ * <ul>
+ *
+ * <li><p> The {@link #matches matches} method attempts to match the entire
+ * input sequence against the pattern. </p></li>
+ *
+ * <li><p> The {@link #lookingAt lookingAt} method attempts to match the
+ * input sequence, starting at the beginning, against the pattern. </p></li>
+ *
+ * <li><p> The {@link #find find} method scans the input sequence looking for
+ * the next subsequence that matches the pattern. </p></li>
+ *
+ * </ul>
+ *
+ * <p> Each of these methods returns a boolean indicating success or failure.
+ * More information about a successful match can be obtained by querying the
+ * state of the matcher.
+ *
+ * <p> A matcher finds matches in a subset of its input called the
+ * <i>region</i>. By default, the region contains all of the matcher's input.
+ * The region can be modified via the{@link #region region} method and queried
+ * via the {@link #regionStart regionStart} and {@link #regionEnd regionEnd}
+ * methods. The way that the region boundaries interact with some pattern
+ * constructs can be changed. See {@link #useAnchoringBounds
+ * useAnchoringBounds} and {@link #useTransparentBounds useTransparentBounds}
+ * for more details.
+ *
+ * <p> This class also defines methods for replacing matched subsequences with
+ * new strings whose contents can, if desired, be computed from the match
+ * result. The {@link #appendReplacement appendReplacement} and {@link
+ * #appendTail appendTail} methods can be used in tandem in order to collect
+ * the result into an existing string buffer, or the more convenient {@link
+ * #replaceAll replaceAll} method can be used to create a string in which every
+ * matching subsequence in the input sequence is replaced.
+ *
+ * <p> The explicit state of a matcher includes the start and end indices of
+ * the most recent successful match. It also includes the start and end
+ * indices of the input subsequence captured by each <a
+ * href="Pattern.html#cg">capturing group</a> in the pattern as well as a total
+ * count of such subsequences. As a convenience, methods are also provided for
+ * returning these captured subsequences in string form.
+ *
+ * <p> The explicit state of a matcher is initially undefined; attempting to
+ * query any part of it before a successful match will cause an {@link
+ * IllegalStateException} to be thrown. The explicit state of a matcher is
+ * recomputed by every match operation.
+ *
+ * <p> The implicit state of a matcher includes the input character sequence as
+ * well as the <i>append position</i>, which is initially zero and is updated
+ * by the {@link #appendReplacement appendReplacement} method.
+ *
+ * <p> A matcher may be reset explicitly by invoking its {@link #reset()}
+ * method or, if a new input sequence is desired, its {@link
+ * #reset(java.lang.CharSequence) reset(CharSequence)} method. Resetting a
+ * matcher discards its explicit state information and sets the append position
+ * to zero.
+ *
+ * <p> Instances of this class are not safe for use by multiple concurrent
+ * threads. </p>
+ *
+ *
+ * @author Mike McCloskey
+ * @author Mark Reinhold
+ * @author JSR-51 Expert Group
+ * @version 1.73, 07/05/05
+ * @since 1.4
+ * @spec JSR-51
+ */
+
+public final class Matcher implements MatchResult {
+
+ /**
+ * The Pattern object that created this Matcher.
+ */
+ Pattern parentPattern;
+
+ /**
+ * The storage used by groups. They may contain invalid values if
+ * a group was skipped during the matching.
+ */
+ int[] groups;
+
+ /**
+ * The range within the sequence that is to be matched. Anchors
+ * will match at these "hard" boundaries. Changing the region
+ * changes these values.
+ */
+ int from, to;
+
+ /**
+ * Lookbehind uses this value to ensure that the subexpression
+ * match ends at the point where the lookbehind was encountered.
+ */
+ int lookbehindTo;
+
+ /**
+ * The original string being matched.
+ */
+ CharSequence text;
+
+ /**
+ * Matcher state used by the last node. NOANCHOR is used when a
+ * match does not have to consume all of the input. ENDANCHOR is
+ * the mode used for matching all the input.
+ */
+ static final int ENDANCHOR = 1;
+ static final int NOANCHOR = 0;
+ int acceptMode = NOANCHOR;
+
+ /**
+ * The range of string that last matched the pattern. If the last
+ * match failed then first is -1; last initially holds 0 then it
+ * holds the index of the end of the last match (which is where the
+ * next search starts).
+ */
+ int first = -1, last = 0;
+
+ /**
+ * The end index of what matched in the last match operation.
+ */
+ int oldLast = -1;
+
+ /**
+ * The index of the last position appended in a substitution.
+ */
+ int lastAppendPosition = 0;
+
+ /**
+ * Storage used by nodes to tell what repetition they are on in
+ * a pattern, and where groups begin. The nodes themselves are stateless,
+ * so they rely on this field to hold state during a match.
+ */
+ int[] locals;
+
+ /**
+ * Boolean indicating whether or not more input could change
+ * the results of the last match.
+ *
+ * If hitEnd is true, and a match was found, then more input
+ * might cause a different match to be found.
+ * If hitEnd is true and a match was not found, then more
+ * input could cause a match to be found.
+ * If hitEnd is false and a match was found, then more input
+ * will not change the match.
+ * If hitEnd is false and a match was not found, then more
+ * input will not cause a match to be found.
+ */
+ boolean hitEnd;
+
+ /**
+ * Boolean indicating whether or not more input could change
+ * a positive match into a negative one.
+ *
+ * If requireEnd is true, and a match was found, then more
+ * input could cause the match to be lost.
+ * If requireEnd is false and a match was found, then more
+ * input might change the match but the match won't be lost.
+ * If a match was not found, then requireEnd has no meaning.
+ */
+ boolean requireEnd;
+
+ /**
+ * If transparentBounds is true then the boundaries of this
+ * matcher's region are transparent to lookahead, lookbehind,
+ * and boundary matching constructs that try to see beyond them.
+ */
+ boolean transparentBounds = false;
+
+ /**
+ * If anchoringBounds is true then the boundaries of this
+ * matcher's region match anchors such as ^ and $.
+ */
+ boolean anchoringBounds = true;
+
+ /**
+ * No default constructor.
+ */
+ Matcher() {
+ }
+
+ /**
+ * All matchers have the state used by Pattern during a match.
+ */
+ Matcher(Pattern parent, CharSequence text) {
+ this.parentPattern = parent;
+ this.text = text;
+
+ // Allocate state storage
+ int parentGroupCount = Math.max(parent.capturingGroupCount, 10);
+ groups = new int[parentGroupCount * 2];
+ locals = new int[parent.localCount];
+
+ // Put fields into initial states
+ reset();
+ }
+
+ /**
+ * Returns the pattern that is interpreted by this matcher.
+ *
+ * @return The pattern for which this matcher was created
+ */
+ public Pattern pattern() {
+ return parentPattern;
+ }
+
+ /**
+ * Returns the match state of this matcher as a {@link MatchResult}.
+ * The result is unaffected by subsequent operations performed upon this
+ * matcher.
+ *
+ * @return a <code>MatchResult</code> with the state of this matcher
+ * @since 1.5
+ */
+ public MatchResult toMatchResult() {
+ Matcher result = new Matcher(this.parentPattern, text.toString());
+ result.first = this.first;
+ result.last = this.last;
+ result.groups = (int[])(this.groups.clone());
+ return result;
+ }
+
+ /**
+ * Changes the <tt>Pattern</tt> that this <tt>Matcher</tt> uses to
+ * find matches with.
+ *
+ * <p> This method causes this matcher to lose information
+ * about the groups of the last match that occurred. The
+ * matcher's position in the input is maintained and its
+ * last append position is unaffected.</p>
+ *
+ * @param newPattern
+ * The new pattern used by this matcher
+ * @return This matcher
+ * @throws IllegalArgumentException
+ * If newPattern is <tt>null</tt>
+ * @since 1.5
+ */
+ public Matcher usePattern(Pattern newPattern) {
+ if (newPattern == null)
+ throw new IllegalArgumentException("Pattern cannot be null");
+ parentPattern = newPattern;
+
+ // Reallocate state storage
+ int parentGroupCount = Math.max(newPattern.capturingGroupCount, 10);
+ groups = new int[parentGroupCount * 2];
+ locals = new int[newPattern.localCount];
+ for (int i = 0; i < groups.length; i++)
+ groups[i] = -1;
+ for (int i = 0; i < locals.length; i++)
+ locals[i] = -1;
+ return this;
+ }
+
+ /**
+ * Resets this matcher.
+ *
+ * <p> Resetting a matcher discards all of its explicit state information
+ * and sets its append position to zero. The matcher's region is set to the
+ * default region, which is its entire character sequence. The anchoring
+ * and transparency of this matcher's region boundaries are unaffected.
+ *
+ * @return This matcher
+ */
+ public Matcher reset() {
+ first = -1;
+ last = 0;
+ oldLast = -1;
+ for(int i=0; i<groups.length; i++)
+ groups[i] = -1;
+ for(int i=0; i<locals.length; i++)
+ locals[i] = -1;
+ lastAppendPosition = 0;
+ from = 0;
+ to = getTextLength();
+ return this;
+ }
+
+ /**
+ * Resets this matcher with a new input sequence.
+ *
+ * <p> Resetting a matcher discards all of its explicit state information
+ * and sets its append position to zero. The matcher's region is set to
+ * the default region, which is its entire character sequence. The
+ * anchoring and transparency of this matcher's region boundaries are
+ * unaffected.
+ *
+ * @param input
+ * The new input character sequence
+ *
+ * @return This matcher
+ */
+ public Matcher reset(CharSequence input) {
+ text = input;
+ return reset();
+ }
+
+ /**
+ * Returns the start index of the previous match. </p>
+ *
+ * @return The index of the first character matched
+ *
+ * @throws IllegalStateException
+ * If no match has yet been attempted,
+ * or if the previous match operation failed
+ */
+ public int start() {
+ if (first < 0)
+ throw new IllegalStateException("No match available");
+ return first;
+ }
+
+ /**
+ * Returns the start index of the subsequence captured by the given group
+ * during the previous match operation.
+ *
+ * <p> <a href="Pattern.html#cg">Capturing groups</a> are indexed from left
+ * to right, starting at one. Group zero denotes the entire pattern, so
+ * the expression <i>m.</i><tt>start(0)</tt> is equivalent to
+ * <i>m.</i><tt>start()</tt>. </p>
+ *
+ * @param group
+ * The index of a capturing group in this matcher's pattern
+ *
+ * @return The index of the first character captured by the group,
+ * or <tt>-1</tt> if the match was successful but the group
+ * itself did not match anything
+ *
+ * @throws IllegalStateException
+ * If no match has yet been attempted,
+ * or if the previous match operation failed
+ *
+ * @throws IndexOutOfBoundsException
+ * If there is no capturing group in the pattern
+ * with the given index
+ */
+ public int start(int group) {
+ if (first < 0)
+ throw new IllegalStateException("No match available");
+ if (group > groupCount())
+ throw new IndexOutOfBoundsException("No group " + group);
+ return groups[group * 2];
+ }
+
+ /**
+ * Returns the offset after the last character matched. </p>
+ *
+ * @return The offset after the last character matched
+ *
+ * @throws IllegalStateException
+ * If no match has yet been attempted,
+ * or if the previous match operation failed
+ */
+ public int end() {
+ if (first < 0)
+ throw new IllegalStateException("No match available");
+ return last;
+ }
+
+ /**
+ * Returns the offset after the last character of the subsequence
+ * captured by the given group during the previous match operation.
+ *
+ * <p> <a href="Pattern.html#cg">Capturing groups</a> are indexed from left
+ * to right, starting at one. Group zero denotes the entire pattern, so
+ * the expression <i>m.</i><tt>end(0)</tt> is equivalent to
+ * <i>m.</i><tt>end()</tt>. </p>
+ *
+ * @param group
+ * The index of a capturing group in this matcher's pattern
+ *
+ * @return The offset after the last character captured by the group,
+ * or <tt>-1</tt> if the match was successful
+ * but the group itself did not match anything
+ *
+ * @throws IllegalStateException
+ * If no match has yet been attempted,
+ * or if the previous match operation failed
+ *
+ * @throws IndexOutOfBoundsException
+ * If there is no capturing group in the pattern
+ * with the given index
+ */
+ public int end(int group) {
+ if (first < 0)
+ throw new IllegalStateException("No match available");
+ if (group > groupCount())
+ throw new IndexOutOfBoundsException("No group " + group);
+ return groups[group * 2 + 1];
+ }
+
+ /**
+ * Returns the input subsequence matched by the previous match.
+ *
+ * <p> For a matcher <i>m</i> with input sequence <i>s</i>,
+ * the expressions <i>m.</i><tt>group()</tt> and
+ * <i>s.</i><tt>substring(</tt><i>m.</i><tt>start(),</tt> <i>m.</i><tt>end())</tt>
+ * are equivalent. </p>
+ *
+ * <p> Note that some patterns, for example <tt>a*</tt>, match the empty
+ * string. This method will return the empty string when the pattern
+ * successfully matches the empty string in the input. </p>
+ *
+ * @return The (possibly empty) subsequence matched by the previous match,
+ * in string form
+ *
+ * @throws IllegalStateException
+ * If no match has yet been attempted,
+ * or if the previous match operation failed
+ */
+ public String group() {
+ return group(0);
+ }
+
+ /**
+ * Returns the input subsequence captured by the given group during the
+ * previous match operation.
+ *
+ * <p> For a matcher <i>m</i>, input sequence <i>s</i>, and group index
+ * <i>g</i>, the expressions <i>m.</i><tt>group(</tt><i>g</i><tt>)</tt> and
+ * <i>s.</i><tt>substring(</tt><i>m.</i><tt>start(</tt><i>g</i><tt>),</tt> <i>m.</i><tt>end(</tt><i>g</i><tt>))</tt>
+ * are equivalent. </p>
+ *
+ * <p> <a href="Pattern.html#cg">Capturing groups</a> are indexed from left
+ * to right, starting at one. Group zero denotes the entire pattern, so
+ * the expression <tt>m.group(0)</tt> is equivalent to <tt>m.group()</tt>.
+ * </p>
+ *
+ * <p> If the match was successful but the group specified failed to match
+ * any part of the input sequence, then <tt>null</tt> is returned. Note
+ * that some groups, for example <tt>(a*)</tt>, match the empty string.
+ * This method will return the empty string when such a group successfully
+ * matches the empty string in the input. </p>
+ *
+ * @param group
+ * The index of a capturing group in this matcher's pattern
+ *
+ * @return The (possibly empty) subsequence captured by the group
+ * during the previous match, or <tt>null</tt> if the group
+ * failed to match part of the input
+ *
+ * @throws IllegalStateException
+ * If no match has yet been attempted,
+ * or if the previous match operation failed
+ *
+ * @throws IndexOutOfBoundsException
+ * If there is no capturing group in the pattern
+ * with the given index
+ */
+ public String group(int group) {
+ if (first < 0)
+ throw new IllegalStateException("No match found");
+ if (group < 0 || group > groupCount())
+ throw new IndexOutOfBoundsException("No group " + group);
+ if ((groups[group*2] == -1) || (groups[group*2+1] == -1))
+ return null;
+ return getSubSequence(groups[group * 2], groups[group * 2 + 1]).toString();
+ }
+
+ /**
+ * Returns the number of capturing groups in this matcher's pattern.
+ *
+ * <p> Group zero denotes the entire pattern by convention. It is not
+ * included in this count.
+ *
+ * <p> Any non-negative integer smaller than or equal to the value
+ * returned by this method is guaranteed to be a valid group index for
+ * this matcher. </p>
+ *
+ * @return The number of capturing groups in this matcher's pattern
+ */
+ public int groupCount() {
+ return parentPattern.capturingGroupCount - 1;
+ }
+
+ /**
+ * Attempts to match the entire region against the pattern.
+ *
+ * <p> If the match succeeds then more information can be obtained via the
+ * <tt>start</tt>, <tt>end</tt>, and <tt>group</tt> methods. </p>
+ *
+ * @return <tt>true</tt> if, and only if, the entire region sequence
+ * matches this matcher's pattern
+ */
+ public boolean matches() {
+ return match(from, ENDANCHOR);
+ }
+
+ /**
+ * Attempts to find the next subsequence of the input sequence that matches
+ * the pattern.
+ *
+ * <p> This method starts at the beginning of this matcher's region, or, if
+ * a previous invocation of the method was successful and the matcher has
+ * not since been reset, at the first character not matched by the previous
+ * match.
+ *
+ * <p> If the match succeeds then more information can be obtained via the
+ * <tt>start</tt>, <tt>end</tt>, and <tt>group</tt> methods. </p>
+ *
+ * @return <tt>true</tt> if, and only if, a subsequence of the input
+ * sequence matches this matcher's pattern
+ */
+ public boolean find() {
+ int nextSearchIndex = last;
+ if (nextSearchIndex == first)
+ nextSearchIndex++;
+
+ // If next search starts before region, start it at region
+ if (nextSearchIndex < from)
+ nextSearchIndex = from;
+
+ // If next search starts beyond region then it fails
+ if (nextSearchIndex > to) {
+ for (int i = 0; i < groups.length; i++)
+ groups[i] = -1;
+ return false;
+ }
+ return search(nextSearchIndex);
+ }
+
+ /**
+ * Resets this matcher and then attempts to find the next subsequence of
+ * the input sequence that matches the pattern, starting at the specified
+ * index.
+ *
+ * <p> If the match succeeds then more information can be obtained via the
+ * <tt>start</tt>, <tt>end</tt>, and <tt>group</tt> methods, and subsequent
+ * invocations of the {@link #find()} method will start at the first
+ * character not matched by this match. </p>
+ *
+ * @throws IndexOutOfBoundsException
+ * If start is less than zero or if start is greater than the
+ * length of the input sequence.
+ *
+ * @return <tt>true</tt> if, and only if, a subsequence of the input
+ * sequence starting at the given index matches this matcher's
+ * pattern
+ */
+ public boolean find(int start) {
+ int limit = getTextLength();
+ if ((start < 0) || (start > limit))
+ throw new IndexOutOfBoundsException("Illegal start index");
+ reset();
+ return search(start);
+ }
+
+ /**
+ * Attempts to match the input sequence, starting at the beginning of the
+ * region, against the pattern.
+ *
+ * <p> Like the {@link #matches matches} method, this method always starts
+ * at the beginning of the region; unlike that method, it does not
+ * require that the entire region be matched.
+ *
+ * <p> If the match succeeds then more information can be obtained via the
+ * <tt>start</tt>, <tt>end</tt>, and <tt>group</tt> methods. </p>
+ *
+ * @return <tt>true</tt> if, and only if, a prefix of the input
+ * sequence matches this matcher's pattern
+ */
+ public boolean lookingAt() {
+ return match(from, NOANCHOR);
+ }
+
+ /**
+ * Returns a literal replacement <code>String</code> for the specified
+ * <code>String</code>.
+ *
+ * This method produces a <code>String</code> that will work
+ * as a literal replacement <code>s</code> in the
+ * <code>appendReplacement</code> method of the {@link Matcher} class.
+ * The <code>String</code> produced will match the sequence of characters
+ * in <code>s</code> treated as a literal sequence. Slashes ('\') and
+ * dollar signs ('$') will be given no special meaning.
+ *
+ * @param s The string to be literalized
+ * @return A literal string replacement
+ * @since 1.5
+ */
+ public static String quoteReplacement(String s) {
+ if ((s.indexOf('\\') == -1) && (s.indexOf('$') == -1))
+ return s;
+ StringBuilder sb = new StringBuilder();
+ for (int i=0; i<s.length(); i++) {
+ char c = s.charAt(i);
+ if (c == '\\' || c == '$') {
+ sb.append('\\');
+ }
+ sb.append(c);
+ }
+ return sb.toString();
+ }
+
+ /**
+ * Implements a non-terminal append-and-replace step.
+ *
+ * <p> This method performs the following actions: </p>
+ *
+ * <ol>
+ *
+ * <li><p> It reads characters from the input sequence, starting at the
+ * append position, and appends them to the given string buffer. It
+ * stops after reading the last character preceding the previous match,
+ * that is, the character at index {@link
+ * #start()} <tt>-</tt> <tt>1</tt>. </p></li>
+ *
+ * <li><p> It appends the given replacement string to the string buffer.
+ * </p></li>
+ *
+ * <li><p> It sets the append position of this matcher to the index of
+ * the last character matched, plus one, that is, to {@link #end()}.
+ * </p></li>
+ *
+ * </ol>
+ *
+ * <p> The replacement string may contain references to subsequences
+ * captured during the previous match: Each occurrence of
+ * <tt>$</tt><i>g</i><tt></tt> will be replaced by the result of
+ * evaluating {@link #group(int) group}<tt>(</tt><i>g</i><tt>)</tt>.
+ * The first number after the <tt>$</tt> is always treated as part of
+ * the group reference. Subsequent numbers are incorporated into g if
+ * they would form a legal group reference. Only the numerals '0'
+ * through '9' are considered as potential components of the group
+ * reference. If the second group matched the string <tt>"foo"</tt>, for
+ * example, then passing the replacement string <tt>"$2bar"</tt> would
+ * cause <tt>"foobar"</tt> to be appended to the string buffer. A dollar
+ * sign (<tt>$</tt>) may be included as a literal in the replacement
+ * string by preceding it with a backslash (<tt>\$</tt>).
+ *
+ * <p> Note that backslashes (<tt>\</tt>) and dollar signs (<tt>$</tt>) in
+ * the replacement string may cause the results to be different than if it
+ * were being treated as a literal replacement string. Dollar signs may be
+ * treated as references to captured subsequences as described above, and
+ * backslashes are used to escape literal characters in the replacement
+ * string.
+ *
+ * <p> This method is intended to be used in a loop together with the
+ * {@link #appendTail appendTail} and {@link #find find} methods. The
+ * following code, for example, writes <tt>one dog two dogs in the
+ * yard</tt> to the standard-output stream: </p>
+ *
+ * <blockquote><pre>
+ * Pattern p = Pattern.compile("cat");
+ * Matcher m = p.matcher("one cat two cats in the yard");
+ * StringBuffer sb = new StringBuffer();
+ * while (m.find()) {
+ * m.appendReplacement(sb, "dog");
+ * }
+ * m.appendTail(sb);
+ * System.out.println(sb.toString());</pre></blockquote>
+ *
+ * @param sb
+ * The target string buffer
+ *
+ * @param replacement
+ * The replacement string
+ *
+ * @return This matcher
+ *
+ * @throws IllegalStateException
+ * If no match has yet been attempted,
+ * or if the previous match operation failed
+ *
+ * @throws IndexOutOfBoundsException
+ * If the replacement string refers to a capturing group
+ * that does not exist in the pattern
+ */
+ public Matcher appendReplacement(StringBuffer sb, String replacement) {
+
+ // If no match, return error
+ if (first < 0)
+ throw new IllegalStateException("No match available");
+
+ // Process substitution string to replace group references with groups
+ int cursor = 0;
+ StringBuilder result = new StringBuilder();
+
+ while (cursor < replacement.length()) {
+ char nextChar = replacement.charAt(cursor);
+ if (nextChar == '\\') {
+ cursor++;
+ nextChar = replacement.charAt(cursor);
+ result.append(nextChar);
+ cursor++;
+ } else if (nextChar == '$') {
+ // Skip past $
+ cursor++;
+ // The first number is always a group
+ int refNum = (int)replacement.charAt(cursor) - '0';
+ if ((refNum < 0)||(refNum > 9))
+ throw new IllegalArgumentException(
+ "Illegal group reference");
+ cursor++;
+
+ // Capture the largest legal group string
+ boolean done = false;
+ while (!done) {
+ if (cursor >= replacement.length()) {
+ break;
+ }
+ int nextDigit = replacement.charAt(cursor) - '0';
+ if ((nextDigit < 0)||(nextDigit > 9)) { // not a number
+ break;
+ }
+ int newRefNum = (refNum * 10) + nextDigit;
+ if (groupCount() < newRefNum) {
+ done = true;
+ } else {
+ refNum = newRefNum;
+ cursor++;
+ }
+ }
+ // Append group
+ if (start(refNum) != -1 && end(refNum) != -1)
+ result.append(text, start(refNum), end(refNum));
+ } else {
+ result.append(nextChar);
+ cursor++;
+ }
+ }
+ // Append the intervening text
+ sb.append(text, lastAppendPosition, first);
+ // Append the match substitution
+ sb.append(result);
+
+ lastAppendPosition = last;
+ return this;
+ }
+
+ /**
+ * Implements a terminal append-and-replace step.
+ *
+ * <p> This method reads characters from the input sequence, starting at
+ * the append position, and appends them to the given string buffer. It is
+ * intended to be invoked after one or more invocations of the {@link
+ * #appendReplacement appendReplacement} method in order to copy the
+ * remainder of the input sequence. </p>
+ *
+ * @param sb
+ * The target string buffer
+ *
+ * @return The target string buffer
+ */
+ public StringBuffer appendTail(StringBuffer sb) {
+ sb.append(text, lastAppendPosition, getTextLength());
+ return sb;
+ }
+
+ /**
+ * Replaces every subsequence of the input sequence that matches the
+ * pattern with the given replacement string.
+ *
+ * <p> This method first resets this matcher. It then scans the input
+ * sequence looking for matches of the pattern. Characters that are not
+ * part of any match are appended directly to the result string; each match
+ * is replaced in the result by the replacement string. The replacement
+ * string may contain references to captured subsequences as in the {@link
+ * #appendReplacement appendReplacement} method.
+ *
+ * <p> Note that backslashes (<tt>\</tt>) and dollar signs (<tt>$</tt>) in
+ * the replacement string may cause the results to be different than if it
+ * were being treated as a literal replacement string. Dollar signs may be
+ * treated as references to captured subsequences as described above, and
+ * backslashes are used to escape literal characters in the replacement
+ * string.
+ *
+ * <p> Given the regular expression <tt>a*b</tt>, the input
+ * <tt>"aabfooaabfooabfoob"</tt>, and the replacement string
+ * <tt>"-"</tt>, an invocation of this method on a matcher for that
+ * expression would yield the string <tt>"-foo-foo-foo-"</tt>.
+ *
+ * <p> Invoking this method changes this matcher's state. If the matcher
+ * is to be used in further matching operations then it should first be
+ * reset. </p>
+ *
+ * @param replacement
+ * The replacement string
+ *
+ * @return The string constructed by replacing each matching subsequence
+ * by the replacement string, substituting captured subsequences
+ * as needed
+ */
+ public String replaceAll(String replacement) {
+ reset();
+ boolean result = find();
+ if (result) {
+ StringBuffer sb = new StringBuffer();
+ do {
+ appendReplacement(sb, replacement);
+ result = find();
+ } while (result);
+ appendTail(sb);
+ return sb.toString();
+ }
+ return text.toString();
+ }
+
+ /**
+ * Replaces the first subsequence of the input sequence that matches the
+ * pattern with the given replacement string.
+ *
+ * <p> This method first resets this matcher. It then scans the input
+ * sequence looking for a match of the pattern. Characters that are not
+ * part of the match are appended directly to the result string; the match
+ * is replaced in the result by the replacement string. The replacement
+ * string may contain references to captured subsequences as in the {@link
+ * #appendReplacement appendReplacement} method.
+ *
+ * <p>Note that backslashes (<tt>\</tt>) and dollar signs (<tt>$</tt>) in
+ * the replacement string may cause the results to be different than if it
+ * were being treated as a literal replacement string. Dollar signs may be
+ * treated as references to captured subsequences as described above, and
+ * backslashes are used to escape literal characters in the replacement
+ * string.
+ *
+ * <p> Given the regular expression <tt>dog</tt>, the input
+ * <tt>"zzzdogzzzdogzzz"</tt>, and the replacement string
+ * <tt>"cat"</tt>, an invocation of this method on a matcher for that
+ * expression would yield the string <tt>"zzzcatzzzdogzzz"</tt>. </p>
+ *
+ * <p> Invoking this method changes this matcher's state. If the matcher
+ * is to be used in further matching operations then it should first be
+ * reset. </p>
+ *
+ * @param replacement
+ * The replacement string
+ * @return The string constructed by replacing the first matching
+ * subsequence by the replacement string, substituting captured
+ * subsequences as needed
+ */
+ public String replaceFirst(String replacement) {
+ if (replacement == null)
+ throw new NullPointerException("replacement");
+ reset();
+ if (!find())
+ return text.toString();
+ StringBuffer sb = new StringBuffer();
+ appendReplacement(sb, replacement);
+ appendTail(sb);
+ return sb.toString();
+ }
+
+ /**
+ * Sets the limits of this matcher's region. The region is the part of the
+ * input sequence that will be searched to find a match. Invoking this
+ * method resets the matcher, and then sets the region to start at the
+ * index specified by the <code>start</code> parameter and end at the
+ * index specified by the <code>end</code> parameter.
+ *
+ * <p>Depending on the transparency and anchoring being used (see
+ * {@link #useTransparentBounds useTransparentBounds} and
+ * {@link #useAnchoringBounds useAnchoringBounds}), certain constructs such
+ * as anchors may behave differently at or around the boundaries of the
+ * region.
+ *
+ * @param start
+ * The index to start searching at (inclusive)
+ * @param end
+ * The index to end searching at (exclusive)
+ * @throws IndexOutOfBoundsException
+ * If start or end is less than zero, if
+ * start is greater than the length of the input sequence, if
+ * end is greater than the length of the input sequence, or if
+ * start is greater than end.
+ * @return this matcher
+ * @since 1.5
+ */
+ public Matcher region(int start, int end) {
+ if ((start < 0) || (start > getTextLength()))
+ throw new IndexOutOfBoundsException("start");
+ if ((end < 0) || (end > getTextLength()))
+ throw new IndexOutOfBoundsException("end");
+ if (start > end)
+ throw new IndexOutOfBoundsException("start > end");
+ reset();
+ from = start;
+ to = end;
+ return this;
+ }
+
+ /**
+ * Reports the start index of this matcher's region. The
+ * searches this matcher conducts are limited to finding matches
+ * within {@link #regionStart regionStart} (inclusive) and
+ * {@link #regionEnd regionEnd} (exclusive).
+ *
+ * @return The starting point of this matcher's region
+ * @since 1.5
+ */
+ public int regionStart() {
+ return from;
+ }
+
+ /**
+ * Reports the end index (exclusive) of this matcher's region.
+ * The searches this matcher conducts are limited to finding matches
+ * within {@link #regionStart regionStart} (inclusive) and
+ * {@link #regionEnd regionEnd} (exclusive).
+ *
+ * @return the ending point of this matcher's region
+ * @since 1.5
+ */
+ public int regionEnd() {
+ return to;
+ }
+
+ /**
+ * Queries the transparency of region bounds for this matcher.
+ *
+ * <p> This method returns <tt>true</tt> if this matcher uses
+ * <i>transparent</i> bounds, <tt>false</tt> if it uses <i>opaque</i>
+ * bounds.
+ *
+ * <p> See {@link #useTransparentBounds useTransparentBounds} for a
+ * description of transparent and opaque bounds.
+ *
+ * <p> By default, a matcher uses opaque region boundaries.
+ *
+ * @return <tt>true</tt> iff this matcher is using transparent bounds,
+ * <tt>false</tt> otherwise.
+ * @see java.util.regex.Matcher#useTransparentBounds(boolean)
+ * @since 1.5
+ */
+ public boolean hasTransparentBounds() {
+ return transparentBounds;
+ }
+
+ /**
+ * Sets the transparency of region bounds for this matcher.
+ *
+ * <p> Invoking this method with an argument of <tt>true</tt> will set this
+ * matcher to use <i>transparent</i> bounds. If the boolean
+ * argument is <tt>false</tt>, then <i>opaque</i> bounds will be used.
+ *
+ * <p> Using transparent bounds, the boundaries of this
+ * matcher's region are transparent to lookahead, lookbehind,
+ * and boundary matching constructs. Those constructs can see beyond the
+ * boundaries of the region to see if a match is appropriate.
+ *
+ * <p> Using opaque bounds, the boundaries of this matcher's
+ * region are opaque to lookahead, lookbehind, and boundary matching
+ * constructs that may try to see beyond them. Those constructs cannot
+ * look past the boundaries so they will fail to match anything outside
+ * of the region.
+ *
+ * <p> By default, a matcher uses opaque bounds.
+ *
+ * @param b a boolean indicating whether to use opaque or transparent
+ * regions
+ * @return this matcher
+ * @see java.util.regex.Matcher#hasTransparentBounds
+ * @since 1.5
+ */
+ public Matcher useTransparentBounds(boolean b) {
+ transparentBounds = b;
+ return this;
+ }
+
+ /**
+ * Queries the anchoring of region bounds for this matcher.
+ *
+ * <p> This method returns <tt>true</tt> if this matcher uses
+ * <i>anchoring</i> bounds, <tt>false</tt> otherwise.
+ *
+ * <p> See {@link #useAnchoringBounds useAnchoringBounds} for a
+ * description of anchoring bounds.
+ *
+ * <p> By default, a matcher uses anchoring region boundaries.
+ *
+ * @return <tt>true</tt> iff this matcher is using anchoring bounds,
+ * <tt>false</tt> otherwise.
+ * @see java.util.regex.Matcher#useAnchoringBounds(boolean)
+ * @since 1.5
+ */
+ public boolean hasAnchoringBounds() {
+ return anchoringBounds;
+ }
+
+ /**
+ * Sets the anchoring of region bounds for this matcher.
+ *
+ * <p> Invoking this method with an argument of <tt>true</tt> will set this
+ * matcher to use <i>anchoring</i> bounds. If the boolean
+ * argument is <tt>false</tt>, then <i>non-anchoring</i> bounds will be
+ * used.
+ *
+ * <p> Using anchoring bounds, the boundaries of this
+ * matcher's region match anchors such as ^ and $.
+ *
+ * <p> Without anchoring bounds, the boundaries of this
+ * matcher's region will not match anchors such as ^ and $.
+ *
+ * <p> By default, a matcher uses anchoring region boundaries.
+ *
+ * @param b a boolean indicating whether or not to use anchoring bounds.
+ * @return this matcher
+ * @see java.util.regex.Matcher#hasAnchoringBounds
+ * @since 1.5
+ */
+ public Matcher useAnchoringBounds(boolean b) {
+ anchoringBounds = b;
+ return this;
+ }
+
+ /**
+ * <p>Returns the string representation of this matcher. The
+ * string representation of a ...
[truncated message content] |