/java-1.7.0-openjdk/openjdk/jdk/src/share/classes/java/util/regex/Pattern.java
Java | 5648 lines | 3493 code | 292 blank | 1863 comment | 904 complexity | 6489a95a7f4c9de11ec05042f9397af3 MD5 | raw file
Possible License(s): GPL-2.0, BSD-3-Clause-No-Nuclear-License-2014, LGPL-3.0, LGPL-2.0
Large files files are truncated, but you can click here to view the full file
- /*
- * Copyright (c) 1999, 2011, Oracle and/or its affiliates. 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. Oracle designates this
- * particular file as subject to the "Classpath" exception as provided
- * by Oracle 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 Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
- * or visit www.oracle.com if you need additional information or have any
- * questions.
- */
- package java.util.regex;
- import java.security.AccessController;
- import java.security.PrivilegedAction;
- import java.text.CharacterIterator;
- import java.text.Normalizer;
- import java.util.Locale;
- import java.util.Map;
- import java.util.ArrayList;
- import java.util.HashMap;
- import java.util.Arrays;
- /**
- * A compiled representation of a regular expression.
- *
- * <p> A regular expression, specified as a string, must first be compiled into
- * an instance of this class. The resulting pattern can then be used to create
- * a {@link Matcher} object that can match arbitrary {@link
- * java.lang.CharSequence </code>character sequences<code>} against the regular
- * expression. All of the state involved in performing a match resides in the
- * matcher, so many matchers can share the same pattern.
- *
- * <p> A typical invocation sequence is thus
- *
- * <blockquote><pre>
- * Pattern p = Pattern.{@link #compile compile}("a*b");
- * Matcher m = p.{@link #matcher matcher}("aaaaab");
- * boolean b = m.{@link Matcher#matches matches}();</pre></blockquote>
- *
- * <p> A {@link #matches matches} method is defined by this class as a
- * convenience for when a regular expression is used just once. This method
- * compiles an expression and matches an input sequence against it in a single
- * invocation. The statement
- *
- * <blockquote><pre>
- * boolean b = Pattern.matches("a*b", "aaaaab");</pre></blockquote>
- *
- * is equivalent to the three statements above, though for repeated matches it
- * is less efficient since it does not allow the compiled pattern to be reused.
- *
- * <p> Instances of this class are immutable and are safe for use by multiple
- * concurrent threads. Instances of the {@link Matcher} class are not safe for
- * such use.
- *
- *
- * <a name="sum">
- * <h4> Summary of regular-expression constructs </h4>
- *
- * <table border="0" cellpadding="1" cellspacing="0"
- * summary="Regular expression constructs, and what they match">
- *
- * <tr align="left">
- * <th bgcolor="#CCCCFF" align="left" id="construct">Construct</th>
- * <th bgcolor="#CCCCFF" align="left" id="matches">Matches</th>
- * </tr>
- *
- * <tr><th> </th></tr>
- * <tr align="left"><th colspan="2" id="characters">Characters</th></tr>
- *
- * <tr><td valign="top" headers="construct characters"><i>x</i></td>
- * <td headers="matches">The character <i>x</i></td></tr>
- * <tr><td valign="top" headers="construct characters"><tt>\\</tt></td>
- * <td headers="matches">The backslash character</td></tr>
- * <tr><td valign="top" headers="construct characters"><tt>\0</tt><i>n</i></td>
- * <td headers="matches">The character with octal value <tt>0</tt><i>n</i>
- * (0 <tt><=</tt> <i>n</i> <tt><=</tt> 7)</td></tr>
- * <tr><td valign="top" headers="construct characters"><tt>\0</tt><i>nn</i></td>
- * <td headers="matches">The character with octal value <tt>0</tt><i>nn</i>
- * (0 <tt><=</tt> <i>n</i> <tt><=</tt> 7)</td></tr>
- * <tr><td valign="top" headers="construct characters"><tt>\0</tt><i>mnn</i></td>
- * <td headers="matches">The character with octal value <tt>0</tt><i>mnn</i>
- * (0 <tt><=</tt> <i>m</i> <tt><=</tt> 3,
- * 0 <tt><=</tt> <i>n</i> <tt><=</tt> 7)</td></tr>
- * <tr><td valign="top" headers="construct characters"><tt>\x</tt><i>hh</i></td>
- * <td headers="matches">The character with hexadecimal value <tt>0x</tt><i>hh</i></td></tr>
- * <tr><td valign="top" headers="construct characters"><tt>\u</tt><i>hhhh</i></td>
- * <td headers="matches">The character with hexadecimal value <tt>0x</tt><i>hhhh</i></td></tr>
- * <tr><td valign="top" headers="construct characters"><tt>\x</tt><i>{h...h}</i></td>
- * <td headers="matches">The character with hexadecimal value <tt>0x</tt><i>h...h</i>
- * ({@link java.lang.Character#MIN_CODE_POINT Character.MIN_CODE_POINT}
- * <= <tt>0x</tt><i>h...h</i> <= 
- * {@link java.lang.Character#MAX_CODE_POINT Character.MAX_CODE_POINT})</td></tr>
- * <tr><td valign="top" headers="matches"><tt>\t</tt></td>
- * <td headers="matches">The tab character (<tt>'\u0009'</tt>)</td></tr>
- * <tr><td valign="top" headers="construct characters"><tt>\n</tt></td>
- * <td headers="matches">The newline (line feed) character (<tt>'\u000A'</tt>)</td></tr>
- * <tr><td valign="top" headers="construct characters"><tt>\r</tt></td>
- * <td headers="matches">The carriage-return character (<tt>'\u000D'</tt>)</td></tr>
- * <tr><td valign="top" headers="construct characters"><tt>\f</tt></td>
- * <td headers="matches">The form-feed character (<tt>'\u000C'</tt>)</td></tr>
- * <tr><td valign="top" headers="construct characters"><tt>\a</tt></td>
- * <td headers="matches">The alert (bell) character (<tt>'\u0007'</tt>)</td></tr>
- * <tr><td valign="top" headers="construct characters"><tt>\e</tt></td>
- * <td headers="matches">The escape character (<tt>'\u001B'</tt>)</td></tr>
- * <tr><td valign="top" headers="construct characters"><tt>\c</tt><i>x</i></td>
- * <td headers="matches">The control character corresponding to <i>x</i></td></tr>
- *
- * <tr><th> </th></tr>
- * <tr align="left"><th colspan="2" id="classes">Character classes</th></tr>
- *
- * <tr><td valign="top" headers="construct classes"><tt>[abc]</tt></td>
- * <td headers="matches"><tt>a</tt>, <tt>b</tt>, or <tt>c</tt> (simple class)</td></tr>
- * <tr><td valign="top" headers="construct classes"><tt>[^abc]</tt></td>
- * <td headers="matches">Any character except <tt>a</tt>, <tt>b</tt>, or <tt>c</tt> (negation)</td></tr>
- * <tr><td valign="top" headers="construct classes"><tt>[a-zA-Z]</tt></td>
- * <td headers="matches"><tt>a</tt> through <tt>z</tt>
- * or <tt>A</tt> through <tt>Z</tt>, inclusive (range)</td></tr>
- * <tr><td valign="top" headers="construct classes"><tt>[a-d[m-p]]</tt></td>
- * <td headers="matches"><tt>a</tt> through <tt>d</tt>,
- * or <tt>m</tt> through <tt>p</tt>: <tt>[a-dm-p]</tt> (union)</td></tr>
- * <tr><td valign="top" headers="construct classes"><tt>[a-z&&[def]]</tt></td>
- * <td headers="matches"><tt>d</tt>, <tt>e</tt>, or <tt>f</tt> (intersection)</tr>
- * <tr><td valign="top" headers="construct classes"><tt>[a-z&&[^bc]]</tt></td>
- * <td headers="matches"><tt>a</tt> through <tt>z</tt>,
- * except for <tt>b</tt> and <tt>c</tt>: <tt>[ad-z]</tt> (subtraction)</td></tr>
- * <tr><td valign="top" headers="construct classes"><tt>[a-z&&[^m-p]]</tt></td>
- * <td headers="matches"><tt>a</tt> through <tt>z</tt>,
- * and not <tt>m</tt> through <tt>p</tt>: <tt>[a-lq-z]</tt>(subtraction)</td></tr>
- * <tr><th> </th></tr>
- *
- * <tr align="left"><th colspan="2" id="predef">Predefined character classes</th></tr>
- *
- * <tr><td valign="top" headers="construct predef"><tt>.</tt></td>
- * <td headers="matches">Any character (may or may not match <a href="#lt">line terminators</a>)</td></tr>
- * <tr><td valign="top" headers="construct predef"><tt>\d</tt></td>
- * <td headers="matches">A digit: <tt>[0-9]</tt></td></tr>
- * <tr><td valign="top" headers="construct predef"><tt>\D</tt></td>
- * <td headers="matches">A non-digit: <tt>[^0-9]</tt></td></tr>
- * <tr><td valign="top" headers="construct predef"><tt>\s</tt></td>
- * <td headers="matches">A whitespace character: <tt>[ \t\n\x0B\f\r]</tt></td></tr>
- * <tr><td valign="top" headers="construct predef"><tt>\S</tt></td>
- * <td headers="matches">A non-whitespace character: <tt>[^\s]</tt></td></tr>
- * <tr><td valign="top" headers="construct predef"><tt>\w</tt></td>
- * <td headers="matches">A word character: <tt>[a-zA-Z_0-9]</tt></td></tr>
- * <tr><td valign="top" headers="construct predef"><tt>\W</tt></td>
- * <td headers="matches">A non-word character: <tt>[^\w]</tt></td></tr>
- *
- * <tr><th> </th></tr>
- * <tr align="left"><th colspan="2" id="posix">POSIX character classes</b> (US-ASCII only)<b></th></tr>
- *
- * <tr><td valign="top" headers="construct posix"><tt>\p{Lower}</tt></td>
- * <td headers="matches">A lower-case alphabetic character: <tt>[a-z]</tt></td></tr>
- * <tr><td valign="top" headers="construct posix"><tt>\p{Upper}</tt></td>
- * <td headers="matches">An upper-case alphabetic character:<tt>[A-Z]</tt></td></tr>
- * <tr><td valign="top" headers="construct posix"><tt>\p{ASCII}</tt></td>
- * <td headers="matches">All ASCII:<tt>[\x00-\x7F]</tt></td></tr>
- * <tr><td valign="top" headers="construct posix"><tt>\p{Alpha}</tt></td>
- * <td headers="matches">An alphabetic character:<tt>[\p{Lower}\p{Upper}]</tt></td></tr>
- * <tr><td valign="top" headers="construct posix"><tt>\p{Digit}</tt></td>
- * <td headers="matches">A decimal digit: <tt>[0-9]</tt></td></tr>
- * <tr><td valign="top" headers="construct posix"><tt>\p{Alnum}</tt></td>
- * <td headers="matches">An alphanumeric character:<tt>[\p{Alpha}\p{Digit}]</tt></td></tr>
- * <tr><td valign="top" headers="construct posix"><tt>\p{Punct}</tt></td>
- * <td headers="matches">Punctuation: One of <tt>!"#$%&'()*+,-./:;<=>?@[\]^_`{|}~</tt></td></tr>
- * <!-- <tt>[\!"#\$%&'\(\)\*\+,\-\./:;\<=\>\?@\[\\\]\^_`\{\|\}~]</tt>
- * <tt>[\X21-\X2F\X31-\X40\X5B-\X60\X7B-\X7E]</tt> -->
- * <tr><td valign="top" headers="construct posix"><tt>\p{Graph}</tt></td>
- * <td headers="matches">A visible character: <tt>[\p{Alnum}\p{Punct}]</tt></td></tr>
- * <tr><td valign="top" headers="construct posix"><tt>\p{Print}</tt></td>
- * <td headers="matches">A printable character: <tt>[\p{Graph}\x20]</tt></td></tr>
- * <tr><td valign="top" headers="construct posix"><tt>\p{Blank}</tt></td>
- * <td headers="matches">A space or a tab: <tt>[ \t]</tt></td></tr>
- * <tr><td valign="top" headers="construct posix"><tt>\p{Cntrl}</tt></td>
- * <td headers="matches">A control character: <tt>[\x00-\x1F\x7F]</tt></td></tr>
- * <tr><td valign="top" headers="construct posix"><tt>\p{XDigit}</tt></td>
- * <td headers="matches">A hexadecimal digit: <tt>[0-9a-fA-F]</tt></td></tr>
- * <tr><td valign="top" headers="construct posix"><tt>\p{Space}</tt></td>
- * <td headers="matches">A whitespace character: <tt>[ \t\n\x0B\f\r]</tt></td></tr>
- *
- * <tr><th> </th></tr>
- * <tr align="left"><th colspan="2">java.lang.Character classes (simple <a href="#jcc">java character type</a>)</th></tr>
- *
- * <tr><td valign="top"><tt>\p{javaLowerCase}</tt></td>
- * <td>Equivalent to java.lang.Character.isLowerCase()</td></tr>
- * <tr><td valign="top"><tt>\p{javaUpperCase}</tt></td>
- * <td>Equivalent to java.lang.Character.isUpperCase()</td></tr>
- * <tr><td valign="top"><tt>\p{javaWhitespace}</tt></td>
- * <td>Equivalent to java.lang.Character.isWhitespace()</td></tr>
- * <tr><td valign="top"><tt>\p{javaMirrored}</tt></td>
- * <td>Equivalent to java.lang.Character.isMirrored()</td></tr>
- *
- * <tr><th> </th></tr>
- * <tr align="left"><th colspan="2" id="unicode">Classes for Unicode scripts, blocks, categories and binary properties</th></tr>
- * * <tr><td valign="top" headers="construct unicode"><tt>\p{IsLatin}</tt></td>
- * <td headers="matches">A Latin script character (<a href="#usc">script</a>)</td></tr>
- * <tr><td valign="top" headers="construct unicode"><tt>\p{InGreek}</tt></td>
- * <td headers="matches">A character in the Greek block (<a href="#ubc">block</a>)</td></tr>
- * <tr><td valign="top" headers="construct unicode"><tt>\p{Lu}</tt></td>
- * <td headers="matches">An uppercase letter (<a href="#ucc">category</a>)</td></tr>
- * <tr><td valign="top" headers="construct unicode"><tt>\p{IsAlphabetic}</tt></td>
- * <td headers="matches">An alphabetic character (<a href="#ubpc">binary property</a>)</td></tr>
- * <tr><td valign="top" headers="construct unicode"><tt>\p{Sc}</tt></td>
- * <td headers="matches">A currency symbol</td></tr>
- * <tr><td valign="top" headers="construct unicode"><tt>\P{InGreek}</tt></td>
- * <td headers="matches">Any character except one in the Greek block (negation)</td></tr>
- * <tr><td valign="top" headers="construct unicode"><tt>[\p{L}&&[^\p{Lu}]] </tt></td>
- * <td headers="matches">Any letter except an uppercase letter (subtraction)</td></tr>
- *
- * <tr><th> </th></tr>
- * <tr align="left"><th colspan="2" id="bounds">Boundary matchers</th></tr>
- *
- * <tr><td valign="top" headers="construct bounds"><tt>^</tt></td>
- * <td headers="matches">The beginning of a line</td></tr>
- * <tr><td valign="top" headers="construct bounds"><tt>$</tt></td>
- * <td headers="matches">The end of a line</td></tr>
- * <tr><td valign="top" headers="construct bounds"><tt>\b</tt></td>
- * <td headers="matches">A word boundary</td></tr>
- * <tr><td valign="top" headers="construct bounds"><tt>\B</tt></td>
- * <td headers="matches">A non-word boundary</td></tr>
- * <tr><td valign="top" headers="construct bounds"><tt>\A</tt></td>
- * <td headers="matches">The beginning of the input</td></tr>
- * <tr><td valign="top" headers="construct bounds"><tt>\G</tt></td>
- * <td headers="matches">The end of the previous match</td></tr>
- * <tr><td valign="top" headers="construct bounds"><tt>\Z</tt></td>
- * <td headers="matches">The end of the input but for the final
- * <a href="#lt">terminator</a>, if any</td></tr>
- * <tr><td valign="top" headers="construct bounds"><tt>\z</tt></td>
- * <td headers="matches">The end of the input</td></tr>
- *
- * <tr><th> </th></tr>
- * <tr align="left"><th colspan="2" id="greedy">Greedy quantifiers</th></tr>
- *
- * <tr><td valign="top" headers="construct greedy"><i>X</i><tt>?</tt></td>
- * <td headers="matches"><i>X</i>, once or not at all</td></tr>
- * <tr><td valign="top" headers="construct greedy"><i>X</i><tt>*</tt></td>
- * <td headers="matches"><i>X</i>, zero or more times</td></tr>
- * <tr><td valign="top" headers="construct greedy"><i>X</i><tt>+</tt></td>
- * <td headers="matches"><i>X</i>, one or more times</td></tr>
- * <tr><td valign="top" headers="construct greedy"><i>X</i><tt>{</tt><i>n</i><tt>}</tt></td>
- * <td headers="matches"><i>X</i>, exactly <i>n</i> times</td></tr>
- * <tr><td valign="top" headers="construct greedy"><i>X</i><tt>{</tt><i>n</i><tt>,}</tt></td>
- * <td headers="matches"><i>X</i>, at least <i>n</i> times</td></tr>
- * <tr><td valign="top" headers="construct greedy"><i>X</i><tt>{</tt><i>n</i><tt>,</tt><i>m</i><tt>}</tt></td>
- * <td headers="matches"><i>X</i>, at least <i>n</i> but not more than <i>m</i> times</td></tr>
- *
- * <tr><th> </th></tr>
- * <tr align="left"><th colspan="2" id="reluc">Reluctant quantifiers</th></tr>
- *
- * <tr><td valign="top" headers="construct reluc"><i>X</i><tt>??</tt></td>
- * <td headers="matches"><i>X</i>, once or not at all</td></tr>
- * <tr><td valign="top" headers="construct reluc"><i>X</i><tt>*?</tt></td>
- * <td headers="matches"><i>X</i>, zero or more times</td></tr>
- * <tr><td valign="top" headers="construct reluc"><i>X</i><tt>+?</tt></td>
- * <td headers="matches"><i>X</i>, one or more times</td></tr>
- * <tr><td valign="top" headers="construct reluc"><i>X</i><tt>{</tt><i>n</i><tt>}?</tt></td>
- * <td headers="matches"><i>X</i>, exactly <i>n</i> times</td></tr>
- * <tr><td valign="top" headers="construct reluc"><i>X</i><tt>{</tt><i>n</i><tt>,}?</tt></td>
- * <td headers="matches"><i>X</i>, at least <i>n</i> times</td></tr>
- * <tr><td valign="top" headers="construct reluc"><i>X</i><tt>{</tt><i>n</i><tt>,</tt><i>m</i><tt>}?</tt></td>
- * <td headers="matches"><i>X</i>, at least <i>n</i> but not more than <i>m</i> times</td></tr>
- *
- * <tr><th> </th></tr>
- * <tr align="left"><th colspan="2" id="poss">Possessive quantifiers</th></tr>
- *
- * <tr><td valign="top" headers="construct poss"><i>X</i><tt>?+</tt></td>
- * <td headers="matches"><i>X</i>, once or not at all</td></tr>
- * <tr><td valign="top" headers="construct poss"><i>X</i><tt>*+</tt></td>
- * <td headers="matches"><i>X</i>, zero or more times</td></tr>
- * <tr><td valign="top" headers="construct poss"><i>X</i><tt>++</tt></td>
- * <td headers="matches"><i>X</i>, one or more times</td></tr>
- * <tr><td valign="top" headers="construct poss"><i>X</i><tt>{</tt><i>n</i><tt>}+</tt></td>
- * <td headers="matches"><i>X</i>, exactly <i>n</i> times</td></tr>
- * <tr><td valign="top" headers="construct poss"><i>X</i><tt>{</tt><i>n</i><tt>,}+</tt></td>
- * <td headers="matches"><i>X</i>, at least <i>n</i> times</td></tr>
- * <tr><td valign="top" headers="construct poss"><i>X</i><tt>{</tt><i>n</i><tt>,</tt><i>m</i><tt>}+</tt></td>
- * <td headers="matches"><i>X</i>, at least <i>n</i> but not more than <i>m</i> times</td></tr>
- *
- * <tr><th> </th></tr>
- * <tr align="left"><th colspan="2" id="logical">Logical operators</th></tr>
- *
- * <tr><td valign="top" headers="construct logical"><i>XY</i></td>
- * <td headers="matches"><i>X</i> followed by <i>Y</i></td></tr>
- * <tr><td valign="top" headers="construct logical"><i>X</i><tt>|</tt><i>Y</i></td>
- * <td headers="matches">Either <i>X</i> or <i>Y</i></td></tr>
- * <tr><td valign="top" headers="construct logical"><tt>(</tt><i>X</i><tt>)</tt></td>
- * <td headers="matches">X, as a <a href="#cg">capturing group</a></td></tr>
- *
- * <tr><th> </th></tr>
- * <tr align="left"><th colspan="2" id="backref">Back references</th></tr>
- *
- * <tr><td valign="bottom" headers="construct backref"><tt>\</tt><i>n</i></td>
- * <td valign="bottom" headers="matches">Whatever the <i>n</i><sup>th</sup>
- * <a href="#cg">capturing group</a> matched</td></tr>
- *
- * <tr><td valign="bottom" headers="construct backref"><tt>\</tt><i>k</i><<i>name</i>></td>
- * <td valign="bottom" headers="matches">Whatever the
- * <a href="#groupname">named-capturing group</a> "name" matched</td></tr>
- *
- * <tr><th> </th></tr>
- * <tr align="left"><th colspan="2" id="quot">Quotation</th></tr>
- *
- * <tr><td valign="top" headers="construct quot"><tt>\</tt></td>
- * <td headers="matches">Nothing, but quotes the following character</td></tr>
- * <tr><td valign="top" headers="construct quot"><tt>\Q</tt></td>
- * <td headers="matches">Nothing, but quotes all characters until <tt>\E</tt></td></tr>
- * <tr><td valign="top" headers="construct quot"><tt>\E</tt></td>
- * <td headers="matches">Nothing, but ends quoting started by <tt>\Q</tt></td></tr>
- * <!-- Metachars: !$()*+.<>?[\]^{|} -->
- *
- * <tr><th> </th></tr>
- * <tr align="left"><th colspan="2" id="special">Special constructs (named-capturing and non-capturing)</th></tr>
- *
- * <tr><td valign="top" headers="construct special"><tt>(?<<a href="#groupname">name</a>></tt><i>X</i><tt>)</tt></td>
- * <td headers="matches"><i>X</i>, as a named-capturing group</td></tr>
- * <tr><td valign="top" headers="construct special"><tt>(?:</tt><i>X</i><tt>)</tt></td>
- * <td headers="matches"><i>X</i>, as a non-capturing group</td></tr>
- * <tr><td valign="top" headers="construct special"><tt>(?idmsuxU-idmsuxU) </tt></td>
- * <td headers="matches">Nothing, but turns match flags <a href="#CASE_INSENSITIVE">i</a>
- * <a href="#UNIX_LINES">d</a> <a href="#MULTILINE">m</a> <a href="#DOTALL">s</a>
- * <a href="#UNICODE_CASE">u</a> <a href="#COMMENTS">x</a> <a href="#UNICODE_CHARACTER_CLASS">U</a>
- * on - off</td></tr>
- * <tr><td valign="top" headers="construct special"><tt>(?idmsux-idmsux:</tt><i>X</i><tt>)</tt> </td>
- * <td headers="matches"><i>X</i>, as a <a href="#cg">non-capturing group</a> with the
- * given flags <a href="#CASE_INSENSITIVE">i</a> <a href="#UNIX_LINES">d</a>
- * <a href="#MULTILINE">m</a> <a href="#DOTALL">s</a> <a href="#UNICODE_CASE">u</a >
- * <a href="#COMMENTS">x</a> on - off</td></tr>
- * <tr><td valign="top" headers="construct special"><tt>(?=</tt><i>X</i><tt>)</tt></td>
- * <td headers="matches"><i>X</i>, via zero-width positive lookahead</td></tr>
- * <tr><td valign="top" headers="construct special"><tt>(?!</tt><i>X</i><tt>)</tt></td>
- * <td headers="matches"><i>X</i>, via zero-width negative lookahead</td></tr>
- * <tr><td valign="top" headers="construct special"><tt>(?<=</tt><i>X</i><tt>)</tt></td>
- * <td headers="matches"><i>X</i>, via zero-width positive lookbehind</td></tr>
- * <tr><td valign="top" headers="construct special"><tt>(?<!</tt><i>X</i><tt>)</tt></td>
- * <td headers="matches"><i>X</i>, via zero-width negative lookbehind</td></tr>
- * <tr><td valign="top" headers="construct special"><tt>(?></tt><i>X</i><tt>)</tt></td>
- * <td headers="matches"><i>X</i>, as an independent, non-capturing group</td></tr>
- *
- * </table>
- *
- * <hr>
- *
- *
- * <a name="bs">
- * <h4> Backslashes, escapes, and quoting </h4>
- *
- * <p> The backslash character (<tt>'\'</tt>) serves to introduce escaped
- * constructs, as defined in the table above, as well as to quote characters
- * that otherwise would be interpreted as unescaped constructs. Thus the
- * expression <tt>\\</tt> matches a single backslash and <tt>\{</tt> matches a
- * left brace.
- *
- * <p> It is an error to use a backslash prior to any alphabetic character that
- * does not denote an escaped construct; these are reserved for future
- * extensions to the regular-expression language. A backslash may be used
- * prior to a non-alphabetic character regardless of whether that character is
- * part of an unescaped construct.
- *
- * <p> Backslashes within string literals in Java source code are interpreted
- * as required by
- * <cite>The Java™ Language Specification</cite>
- * as either Unicode escapes (section 3.3) or other character escapes (section 3.10.6)
- * It is therefore necessary to double backslashes in string
- * literals that represent regular expressions to protect them from
- * interpretation by the Java bytecode compiler. The string literal
- * <tt>"\b"</tt>, for example, matches a single backspace character when
- * interpreted as a regular expression, while <tt>"\\b"</tt> matches a
- * word boundary. The string literal <tt>"\(hello\)"</tt> is illegal
- * and leads to a compile-time error; in order to match the string
- * <tt>(hello)</tt> the string literal <tt>"\\(hello\\)"</tt>
- * must be used.
- *
- * <a name="cc">
- * <h4> Character Classes </h4>
- *
- * <p> Character classes may appear within other character classes, and
- * may be composed by the union operator (implicit) and the intersection
- * operator (<tt>&&</tt>).
- * The union operator denotes a class that contains every character that is
- * in at least one of its operand classes. The intersection operator
- * denotes a class that contains every character that is in both of its
- * operand classes.
- *
- * <p> The precedence of character-class operators is as follows, from
- * highest to lowest:
- *
- * <blockquote><table border="0" cellpadding="1" cellspacing="0"
- * summary="Precedence of character class operators.">
- * <tr><th>1 </th>
- * <td>Literal escape </td>
- * <td><tt>\x</tt></td></tr>
- * <tr><th>2 </th>
- * <td>Grouping</td>
- * <td><tt>[...]</tt></td></tr>
- * <tr><th>3 </th>
- * <td>Range</td>
- * <td><tt>a-z</tt></td></tr>
- * <tr><th>4 </th>
- * <td>Union</td>
- * <td><tt>[a-e][i-u]</tt></td></tr>
- * <tr><th>5 </th>
- * <td>Intersection</td>
- * <td><tt>[a-z&&[aeiou]]</tt></td></tr>
- * </table></blockquote>
- *
- * <p> Note that a different set of metacharacters are in effect inside
- * a character class than outside a character class. For instance, the
- * regular expression <tt>.</tt> loses its special meaning inside a
- * character class, while the expression <tt>-</tt> becomes a range
- * forming metacharacter.
- *
- * <a name="lt">
- * <h4> Line terminators </h4>
- *
- * <p> A <i>line terminator</i> is a one- or two-character sequence that marks
- * the end of a line of the input character sequence. The following are
- * recognized as line terminators:
- *
- * <ul>
- *
- * <li> A newline (line feed) character (<tt>'\n'</tt>),
- *
- * <li> A carriage-return character followed immediately by a newline
- * character (<tt>"\r\n"</tt>),
- *
- * <li> A standalone carriage-return character (<tt>'\r'</tt>),
- *
- * <li> A next-line character (<tt>'\u0085'</tt>),
- *
- * <li> A line-separator character (<tt>'\u2028'</tt>), or
- *
- * <li> A paragraph-separator character (<tt>'\u2029</tt>).
- *
- * </ul>
- * <p>If {@link #UNIX_LINES} mode is activated, then the only line terminators
- * recognized are newline characters.
- *
- * <p> The regular expression <tt>.</tt> matches any character except a line
- * terminator unless the {@link #DOTALL} flag is specified.
- *
- * <p> By default, the regular expressions <tt>^</tt> and <tt>$</tt> ignore
- * line terminators and only match at the beginning and the end, respectively,
- * of the entire input sequence. If {@link #MULTILINE} mode is activated then
- * <tt>^</tt> matches at the beginning of input and after any line terminator
- * except at the end of input. When in {@link #MULTILINE} mode <tt>$</tt>
- * matches just before a line terminator or the end of the input sequence.
- *
- * <a name="cg">
- * <h4> Groups and capturing </h4>
- *
- * <a name="gnumber">
- * <h5> Group number </h5>
- * <p> Capturing groups are numbered by counting their opening parentheses from
- * left to right. In the expression <tt>((A)(B(C)))</tt>, for example, there
- * are four such groups: </p>
- *
- * <blockquote><table cellpadding=1 cellspacing=0 summary="Capturing group numberings">
- * <tr><th>1 </th>
- * <td><tt>((A)(B(C)))</tt></td></tr>
- * <tr><th>2 </th>
- * <td><tt>(A)</tt></td></tr>
- * <tr><th>3 </th>
- * <td><tt>(B(C))</tt></td></tr>
- * <tr><th>4 </th>
- * <td><tt>(C)</tt></td></tr>
- * </table></blockquote>
- *
- * <p> Group zero always stands for the entire expression.
- *
- * <p> Capturing groups are so named because, during a match, each subsequence
- * of the input sequence that matches such a group is saved. The captured
- * subsequence may be used later in the expression, via a back reference, and
- * may also be retrieved from the matcher once the match operation is complete.
- *
- * <a name="groupname">
- * <h5> Group name </h5>
- * <p>A capturing group can also be assigned a "name", a <tt>named-capturing group</tt>,
- * and then be back-referenced later by the "name". Group names are composed of
- * the following characters. The first character must be a <tt>letter</tt>.
- *
- * <ul>
- * <li> The uppercase letters <tt>'A'</tt> through <tt>'Z'</tt>
- * (<tt>'\u0041'</tt> through <tt>'\u005a'</tt>),
- * <li> The lowercase letters <tt>'a'</tt> through <tt>'z'</tt>
- * (<tt>'\u0061'</tt> through <tt>'\u007a'</tt>),
- * <li> The digits <tt>'0'</tt> through <tt>'9'</tt>
- * (<tt>'\u0030'</tt> through <tt>'\u0039'</tt>),
- * </ul>
- *
- * <p> A <tt>named-capturing group</tt> is still numbered as described in
- * <a href="#gnumber">Group number</a>.
- *
- * <p> The captured input associated with a group is always the subsequence
- * that the group most recently matched. If a group is evaluated a second time
- * because of quantification then its previously-captured value, if any, will
- * be retained if the second evaluation fails. Matching the string
- * <tt>"aba"</tt> against the expression <tt>(a(b)?)+</tt>, for example, leaves
- * group two set to <tt>"b"</tt>. All captured input is discarded at the
- * beginning of each match.
- *
- * <p> Groups beginning with <tt>(?</tt> are either pure, <i>non-capturing</i> groups
- * that do not capture text and do not count towards the group total, or
- * <i>named-capturing</i> group.
- *
- * <h4> Unicode support </h4>
- *
- * <p> This class is in conformance with Level 1 of <a
- * href="http://www.unicode.org/reports/tr18/"><i>Unicode Technical
- * Standard #18: Unicode Regular Expression</i></a>, plus RL2.1
- * Canonical Equivalents.
- * <p>
- * <b>Unicode escape sequences</b> such as <tt>\u2014</tt> in Java source code
- * are processed as described in section 3.3 of
- * <cite>The Java™ Language Specification</cite>.
- * Such escape sequences are also implemented directly by the regular-expression
- * parser so that Unicode escapes can be used in expressions that are read from
- * files or from the keyboard. Thus the strings <tt>"\u2014"</tt> and
- * <tt>"\\u2014"</tt>, while not equal, compile into the same pattern, which
- * matches the character with hexadecimal value <tt>0x2014</tt>.
- * <p>
- * A Unicode character can also be represented in a regular-expression by
- * using its <b>Hex notation</b>(hexadecimal code point value) directly as described in construct
- * <tt>\x{...}</tt>, for example a supplementary character U+2011F
- * can be specified as <tt>\x{2011F}</tt>, instead of two consecutive
- * Unicode escape sequences of the surrogate pair
- * <tt>\uD840</tt><tt>\uDD1F</tt>.
- * <p>
- * Unicode scripts, blocks, categories and binary properties are written with
- * the <tt>\p</tt> and <tt>\P</tt> constructs as in Perl.
- * <tt>\p{</tt><i>prop</i><tt>}</tt> matches if
- * the input has the property <i>prop</i>, while <tt>\P{</tt><i>prop</i><tt>}</tt>
- * does not match if the input has that property.
- * <p>
- * Scripts, blocks, categories and binary properties can be used both inside
- * and outside of a character class.
- * <a name="usc">
- * <p>
- * <b>Scripts</b> are specified either with the prefix {@code Is}, as in
- * {@code IsHiragana}, or by using the {@code script} keyword (or its short
- * form {@code sc})as in {@code script=Hiragana} or {@code sc=Hiragana}.
- * <p>
- * The script names supported by <code>Pattern</code> are the valid script names
- * accepted and defined by
- * {@link java.lang.Character.UnicodeScript#forName(String) UnicodeScript.forName}.
- * <a name="ubc">
- * <p>
- * <b>Blocks</b> are specified with the prefix {@code In}, as in
- * {@code InMongolian}, or by using the keyword {@code block} (or its short
- * form {@code blk}) as in {@code block=Mongolian} or {@code blk=Mongolian}.
- * <p>
- * The block names supported by <code>Pattern</code> are the valid block names
- * accepted and defined by
- * {@link java.lang.Character.UnicodeBlock#forName(String) UnicodeBlock.forName}.
- * <p>
- * <a name="ucc">
- * <b>Categories</b> may be specified with the optional prefix {@code Is}:
- * Both {@code \p{L}} and {@code \p{IsL}} denote the category of Unicode
- * letters. Same as scripts and blocks, categories can also be specified
- * by using the keyword {@code general_category} (or its short form
- * {@code gc}) as in {@code general_category=Lu} or {@code gc=Lu}.
- * <p>
- * The supported categories are those of
- * <a href="http://www.unicode.org/unicode/standard/standard.html">
- * <i>The Unicode Standard</i></a> in the version specified by the
- * {@link java.lang.Character Character} class. The category names are those
- * defined in the Standard, both normative and informative.
- * <p>
- * <a name="ubpc">
- * <b>Binary properties</b> are specified with the prefix {@code Is}, as in
- * {@code IsAlphabetic}. The supported binary properties by <code>Pattern</code>
- * are
- * <ul>
- * <li> Alphabetic
- * <li> Ideographic
- * <li> Letter
- * <li> Lowercase
- * <li> Uppercase
- * <li> Titlecase
- * <li> Punctuation
- * <Li> Control
- * <li> White_Space
- * <li> Digit
- * <li> Hex_Digit
- * <li> Noncharacter_Code_Point
- * <li> Assigned
- * </ul>
- * <p>
- * <b>Predefined Character classes</b> and <b>POSIX character classes</b> are in
- * conformance with the recommendation of <i>Annex C: Compatibility Properties</i>
- * of <a href="http://www.unicode.org/reports/tr18/"><i>Unicode Regular Expression
- * </i></a>, when {@link #UNICODE_CHARACTER_CLASS} flag is specified.
- * <p>
- * <table border="0" cellpadding="1" cellspacing="0"
- * summary="predefined and posix character classes in Unicode mode">
- * <tr align="left">
- * <th bgcolor="#CCCCFF" align="left" id="classes">Classes</th>
- * <th bgcolor="#CCCCFF" align="left" id="matches">Matches</th>
- *</tr>
- * <tr><td><tt>\p{Lower}</tt></td>
- * <td>A lowercase character:<tt>\p{IsLowercase}</tt></td></tr>
- * <tr><td><tt>\p{Upper}</tt></td>
- * <td>An uppercase character:<tt>\p{IsUppercase}</tt></td></tr>
- * <tr><td><tt>\p{ASCII}</tt></td>
- * <td>All ASCII:<tt>[\x00-\x7F]</tt></td></tr>
- * <tr><td><tt>\p{Alpha}</tt></td>
- * <td>An alphabetic character:<tt>\p{IsAlphabetic}</tt></td></tr>
- * <tr><td><tt>\p{Digit}</tt></td>
- * <td>A decimal digit character:<tt>p{IsDigit}</tt></td></tr>
- * <tr><td><tt>\p{Alnum}</tt></td>
- * <td>An alphanumeric character:<tt>[\p{IsAlphabetic}\p{IsDigit}]</tt></td></tr>
- * <tr><td><tt>\p{Punct}</tt></td>
- * <td>A punctuation character:<tt>p{IsPunctuation}</tt></td></tr>
- * <tr><td><tt>\p{Graph}</tt></td>
- * <td>A visible character: <tt>[^\p{IsWhite_Space}\p{gc=Cc}\p{gc=Cs}\p{gc=Cn}]</tt></td></tr>
- * <tr><td><tt>\p{Print}</tt></td>
- * <td>A printable character: <tt>[\p{Graph}\p{Blank}&&[^\p{Cntrl}]]</tt></td></tr>
- * <tr><td><tt>\p{Blank}</tt></td>
- * <td>A space or a tab: <tt>[\p{IsWhite_Space}&&[^\p{gc=Zl}\p{gc=Zp}\x0a\x0b\x0c\x0d\x85]]</tt></td></tr>
- * <tr><td><tt>\p{Cntrl}</tt></td>
- * <td>A control character: <tt>\p{gc=Cc}</tt></td></tr>
- * <tr><td><tt>\p{XDigit}</tt></td>
- * <td>A hexadecimal digit: <tt>[\p{gc=Nd}\p{IsHex_Digit}]</tt></td></tr>
- * <tr><td><tt>\p{Space}</tt></td>
- * <td>A whitespace character:<tt>\p{IsWhite_Space}</tt></td></tr>
- * <tr><td><tt>\d</tt></td>
- * <td>A digit: <tt>\p{IsDigit}</tt></td></tr>
- * <tr><td><tt>\D</tt></td>
- * <td>A non-digit: <tt>[^\d]</tt></td></tr>
- * <tr><td><tt>\s</tt></td>
- * <td>A whitespace character: <tt>\p{IsWhite_Space}</tt></td></tr>
- * <tr><td><tt>\S</tt></td>
- * <td>A non-whitespace character: <tt>[^\s]</tt></td></tr>
- * <tr><td><tt>\w</tt></td>
- * <td>A word character: <tt>[\p{Alpha}\p{gc=Mn}\p{gc=Me}\p{gc=Mc}\p{Digit}\p{gc=Pc}]</tt></td></tr>
- * <tr><td><tt>\W</tt></td>
- * <td>A non-word character: <tt>[^\w]</tt></td></tr>
- * </table>
- * <p>
- * <a name="jcc">
- * Categories that behave like the java.lang.Character
- * boolean is<i>methodname</i> methods (except for the deprecated ones) are
- * available through the same <tt>\p{</tt><i>prop</i><tt>}</tt> syntax where
- * the specified property has the name <tt>java<i>methodname</i></tt>.
- *
- * <h4> Comparison to Perl 5 </h4>
- *
- * <p>The <code>Pattern</code> engine performs traditional NFA-based matching
- * with ordered alternation as occurs in Perl 5.
- *
- * <p> Perl constructs not supported by this class: </p>
- *
- * <ul>
- * <li><p> Predefined character classes (Unicode character)
- * <p><tt>\h </tt>A horizontal whitespace
- * <p><tt>\H </tt>A non horizontal whitespace
- * <p><tt>\v </tt>A vertical whitespace
- * <p><tt>\V </tt>A non vertical whitespace
- * <p><tt>\R </tt>Any Unicode linebreak sequence
- * <tt>\u005cu000D\u005cu000A|[\u005cu000A\u005cu000B\u005cu000C\u005cu000D\u005cu0085\u005cu2028\u005cu2029]</tt>
- * <p><tt>\X </tt>Match Unicode
- * <a href="http://www.unicode.org/reports/tr18/#Default_Grapheme_Clusters">
- * <i>extended grapheme cluster</i></a>
- * </p></li>
- *
- * <li><p> The backreference constructs, <tt>\g{</tt><i>n</i><tt>}</tt> for
- * the <i>n</i><sup>th</sup><a href="#cg">capturing group</a> and
- * <tt>\g{</tt><i>name</i><tt>}</tt> for
- * <a href="#groupname">named-capturing group</a>.
- * </p></li>
- *
- * <li><p> The named character construct, <tt>\N{</tt><i>name</i><tt>}</tt>
- * for a Unicode character by its name.
- * </p></li>
- *
- * <li><p> The conditional constructs
- * <tt>(?(</tt><i>condition</i><tt>)</tt><i>X</i><tt>)</tt> and
- * <tt>(?(</tt><i>condition</i><tt>)</tt><i>X</i><tt>|</tt><i>Y</i><tt>)</tt>,
- * </p></li>
- *
- * <li><p> The embedded code constructs <tt>(?{</tt><i>code</i><tt>})</tt>
- * and <tt>(??{</tt><i>code</i><tt>})</tt>,</p></li>
- *
- * <li><p> The embedded comment syntax <tt>(?#comment)</tt>, and </p></li>
- *
- * <li><p> The preprocessing operations <tt>\l</tt> <tt>\u</tt>,
- * <tt>\L</tt>, and <tt>\U</tt>. </p></li>
- *
- * </ul>
- *
- * <p> Constructs supported by this class but not by Perl: </p>
- *
- * <ul>
- *
- * <li><p> Character-class union and intersection as described
- * <a href="#cc">above</a>.</p></li>
- *
- * </ul>
- *
- * <p> Notable differences from Perl: </p>
- *
- * <ul>
- *
- * <li><p> In Perl, <tt>\1</tt> through <tt>\9</tt> are always interpreted
- * as back references; a backslash-escaped number greater than <tt>9</tt> is
- * treated as a back reference if at least that many subexpressions exist,
- * otherwise it is interpreted, if possible, as an octal escape. In this
- * class octal escapes must always begin with a zero. In this class,
- * <tt>\1</tt> through <tt>\9</tt> are always interpreted as back
- * references, and a larger number is accepted as a back reference if at
- * least that many subexpressions exist at that point in the regular
- * expression, otherwise the parser will drop digits until the number is
- * smaller or equal to the existing number of groups or it is one digit.
- * </p></li>
- *
- * <li><p> Perl uses the <tt>g</tt> flag to request a match that resumes
- * where the last match left off. This functionality is provided implicitly
- * by the {@link Matcher} class: Repeated invocations of the {@link
- * Matcher#find find} method will resume where the last match left off,
- * unless the matcher is reset. </p></li>
- *
- * <li><p> In Perl, embedded flags at the top level of an expression affect
- * the whole expression. In this class, embedded flags always take effect
- * at the point at which they appear, whether they are at the top level or
- * within a group; in the latter case, flags are restored at the end of the
- * group just as in Perl. </p></li>
- *
- * </ul>
- *
- *
- * <p> For a more precise description of the behavior of regular expression
- * constructs, please see <a href="http://www.oreilly.com/catalog/regex3/">
- * <i>Mastering Regular Expressions, 3nd Edition</i>, Jeffrey E. F. Friedl,
- * O'Reilly and Associates, 2006.</a>
- * </p>
- *
- * @see java.lang.String#split(String, int)
- * @see java.lang.String#split(String)
- *
- * @author Mike McCloskey
- * @author Mark Reinhold
- * @author JSR-51 Expert Group
- * @since 1.4
- * @spec JSR-51
- */
- public final class Pattern
- implements java.io.Serializable
- {
- /**
- * Regular expression modifier values. Instead of being passed as
- * arguments, they can also be passed as inline modifiers.
- * For example, the following statements have the same effect.
- * <pre>
- * RegExp r1 = RegExp.compile("abc", Pattern.I|Pattern.M);
- * RegExp r2 = RegExp.compile("(?im)abc", 0);
- * </pre>
- *
- * The flags are duplicated so that the familiar Perl match flag
- * names are available.
- */
- /**
- * Enables Unix lines mode.
- *
- * <p> In this mode, only the <tt>'\n'</tt> line terminator is recognized
- * in the behavior of <tt>.</tt>, <tt>^</tt>, and <tt>$</tt>.
- *
- * <p> Unix lines mode can also be enabled via the embedded flag
- * expression <tt>(?d)</tt>.
- */
- public static final int UNIX_LINES = 0x01;
- /**
- * Enables case-insensitive matching.
- *
- * <p> By default, case-insensitive matching assumes that only characters
- * in the US-ASCII charset are being matched. Unicode-aware
- * case-insensitive matching can be enabled by specifying the {@link
- * #UNICODE_CASE} flag in conjunction with this flag.
- *
- * <p> Case-insensitive matching can also be enabled via the embedded flag
- * expression <tt>(?i)</tt>.
- *
- * <p> Specifying this flag may impose a slight performance penalty. </p>
- */
- public static final int CASE_INSENSITIVE = 0x02;
- /**
- * Permits whitespace and comments in pattern.
- *
- * <p> In this mode, whitespace is ignored, and embedded comments starting
- * with <tt>#</tt> are ignored until the end of a line.
- *
- * <p> Comments mode can also be enabled via the embedded flag
- * expression <tt>(?x)</tt>.
- */
- public static final int COMMENTS = 0x04;
- /**
- * Enables multiline mode.
- *
- * <p> In multiline mode the expressions <tt>^</tt> and <tt>$</tt> match
- * just after or just before, respectively, a line terminator or the end of
- * the input sequence. By default these expressions only match at the
- * beginning and the end of the entire input sequence.
- *
- * <p> Multiline mode can also be enabled via the embedded flag
- * expression <tt>(?m)</tt>. </p>
- */
- public static final int MULTILINE = 0x08;
- /**
- * Enables literal parsing of the pattern.
- *
- * <p> When this flag is specified then the input string that specifies
- * the pattern is treated as a sequence of literal characters.
- * Metacharacters or escape sequences in the input sequence will be
- * given no special meaning.
- *
- * <p>The flags CASE_INSENSITIVE and UNICODE_CASE retain their impact on
- * matching when used in conjunction with this flag. The other flags
- * become superfluous.
- *
- * <p> There is no embedded flag character for enabling literal parsing.
- * @since 1.5
- */
- public static final int LITERAL = 0x10;
- /**
- * Enables dotall mode.
- *
- * <p> In dotall mode, the expression <tt>.</tt> matches any character,
- * including a line terminator. By default this expression does not match
- * line terminators.
- *
- * <p> Dotall mode can also be enabled via the embedded flag
- * expression <tt>(?s)</tt>. (The <tt>s</tt> is a mnemonic for
- * "single-line" mode, which is what this is called in Perl.) </p>
- */
- public static final int DOTALL = 0x20;
- /**
- * Enables Unicode-aware case folding.
- *
- * <p> When this flag is specified then case-insensitive matching, when
- * enabled by the {@link #CASE_INSENSITIVE} flag, is done in a manner
- * consistent with the Unicode Standard. By default, case-insensitive
- * matching assumes that only characters in the US-ASCII charset are being
- * matched.
- *
- * <p> Unicode-aware case folding can also be enabled via the embedded flag
- * expression <tt>(?u)</tt>.
- *
- * <p> Specifying this flag may impose a performance penalty. </p>
- */
- public static final int UNICODE_CASE = 0x40;
- /**
- * Enables canonical equivalence.
- *
- * <p> When this flag is specified then two characters will be considered
- * to match if, and only if, their full canonical decompositions match.
- * The expression <tt>"a\u030A"</tt>, for example, will match the
- * string <tt>"\u00E5"</tt> when this flag is specified. By default,
- * matching does not take canonical equivalence into account.
- *
- * <p> There is no embedded flag character for enabling canonical
- * equivalence.
- *
- * <p> Specifying this flag may impose a performance penalty. </p>
- */
- public static final int CANON_EQ = 0x80;
- /**
- * Enables the Unicode version of <i>Predefined character classes</i> and
- * <i>POSIX character classes</i>.
- *
- * <p> When this flag is specified then the (US-ASCII only)
- * <i>Predefined character classes</i> and <i>POSIX character classes</i>
- * are in conformance with
- * <a href="http://www.unicode.org/reports/tr18/"><i>Unicode Technical
- * Standard #18: Unicode Regular Expression</i></a>
- * <i>Annex C: Compatibility Properties</i>.
- * <p>
- * The UNICODE_CHARACTER_CLASS mode can also be enabled via the embedded
- * flag expression <tt>(?U)</tt>.
- * <p>
- * The flag implies UNICODE_CASE, that is, it enables Unicode-aware case
- * folding.
- * <p>
- * Specifying this flag may impose a performance penalty. </p>
- * @since 1.7
- */
- public static final int UNICODE_CHARACTER_CLASS = 0x100;
- /* Pattern has only two serialized components: The pattern string
- * and the flags, which are all that is needed to recompile the pattern
- * when it is deserialized.
- */
- /** use serialVersionUID from Merlin b59 for interoperability */
- private static final long serialVersionUID = 5073258162644648461L;
- /**
- * The original regular-expression pattern string.
- *
- * @serial
- */
- private String pattern;
- /**
- * The original pattern flags.
- *
- * @serial
- */
- private int flags;
- /**
- * Boolean indicating this Pattern is compiled; this is necessary in order
- * to lazily compile deserialized Patterns.
- */
- private transient volatile boolean compiled = false;
- /**
- * The normalized pattern string.
- */
- private transient String normalizedPattern;
- /**
- * The starting point of state machine for the find operation. This allows
- * a match to start anywhere in the input.
- */
- transient Node root;
- /**
- * The root of object tree for a match operation. The pattern is matched
- * at the beginning. This may include a find that uses BnM or a First
- * node.
- */
- transient Node matchRoot;
- /**
- * Temporary storage used by parsing pattern slice.
- */
- transient int[] buffer;
- /**
- * Map the "name" of the "named capturing group" to its group id
- * node.
- */
- transient volatile Map<String, Integer> namedGroups;
- /**
- * Temporary storage used while parsing group references.
- */
- transient GroupHead[] groupNodes;
- /**
- * Temporary null terminated code point array used by pattern compiling.
- */
- private transient int[] temp;
- /**
- * The number of capturing groups in this Pattern. Used by matchers to
- * allocate storage needed to perform a match.
- */
- transient int capturingGroupCount;
- /**
- * The local variable count used by parsing tree. Used by matchers to
- * allocate storage needed to perform a match.
- */
- transient int localCount;
- /**
- * Index into the pattern string that keeps track of how much has been
- * parsed.
- */
- private transient int cursor;
- /**
- * Holds the length of the pattern string.
- */
- private transient int patternLength;
- /**
- * If the Start node might possibly match supplementary characters.
- * It is set to true during compiling if
- * (1) There is supplementary char in pattern, or
- * (2) There is complement node of Category or Block
- */
- private transient boolean hasSupplementary;
- /**
- * Compiles the given regular expression into a pattern. </p>
- *
- * @param regex
- * The expression to be compiled
- *
- * @throws PatternSyntaxException
- * If the expression's syntax is invalid
- */
- public static Pattern compile(String regex) {
- return new Pattern(regex, 0);
- }
- /**
- * Compiles the given regular expression into a pattern with the given
- * flags. </p>
- *
- * @param regex
- * The expression to be compiled
- *
- * @param flags
- * Match flags, a bit mask that may include
- * {@link #CASE_INSENSITIVE}, {@link #MULTILINE}, {@link #DOTALL},
- * {@link #UNICODE_CASE}, {@link #CANON_EQ}, {@link #UNIX_LINES},
- * {@link #LITERAL}, {@link #UNICODE_CHARACTER_CLASS}
- * and {@link #COMMENTS}
- *
- * @throws IllegalArgumentException
- * If bit values other than those corresponding to the defined
- * match flags are set in <tt>flags</tt>
- *
- * @throws PatternSyntaxException
- * If the expression's syntax is invalid
- */
- public static Pattern compile(String regex, int flags) {
- return new Pattern(regex, flags);
- }
- /**
- * Returns the regular expression from which this pattern was compiled.
- * </p>
- *
- * @return The source of this pattern
- */
- public String pattern() {
- return pattern;
- }
- /**
- * <p>Returns the string representation of this pattern. This
- * is the reg…
Large files files are truncated, but you can click here to view the full file