/*

 * Copyright (c) 1999, 2013, 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.text.Normalizer;

import java.util.Locale;

import java.util.Iterator;

import java.util.Map;

import java.util.ArrayList;

import java.util.HashMap;

import java.util.Arrays;

import java.util.NoSuchElementException;

import java.util.Spliterator;

import java.util.Spliterators;

import java.util.function.Predicate;

import java.util.stream.Stream;

import java.util.stream.StreamSupport;

/**

 * 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 {@linkplain

 * java.lang.CharSequence character sequences} 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.

 *

 *

 * <h3><a name="sum">Summary of regular-expression constructs</a></h3>

 *

 * <table border="0" cellpadding="1" cellspacing="0"

 *  summary="Regular expression constructs, and what they match">

 *

 * <tr align="left">

 * <th align="left" id="construct">Construct</th>

 * <th align="left" id="matches">Matches</th>

 * </tr>

 *

 * <tr><th>&nbsp;</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>

 *     <td headers="matches">The backslash character</td></tr>

 *         ({@link java.lang.Character#MIN_CODE_POINT Character.MIN_CODE_POINT}

 *          {@link java.lang.Character#MAX_CODE_POINT Character.MAX_CODE_POINT})</td></tr>

 *     <td headers="matches">The control character corresponding to <i>x</i></td></tr>

 *

 * <tr><th>&nbsp;</th></tr>

 * <tr align="left"><th colspan="2" id="classes">Character classes</th></tr>

 *

 * <tr><td valign="top" headers="construct classes">{@code [abc]}</td>

 *     <td headers="matches">{@code a}, {@code b}, or {@code c} (simple class)</td></tr>

 * <tr><td valign="top" headers="construct classes">{@code [^abc]}</td>

 *     <td headers="matches">Any character except {@code a}, {@code b}, or {@code c} (negation)</td></tr>

 * <tr><td valign="top" headers="construct classes">{@code [a-zA-Z]}</td>

 *     <td headers="matches">{@code a} through {@code z}

 *         or {@code A} through {@code Z}, inclusive (range)</td></tr>

 * <tr><td valign="top" headers="construct classes">{@code [a-d[m-p]]}</td>

 *     <td headers="matches">{@code a} through {@code d},

 *      or {@code m} through {@code p}: {@code [a-dm-p]} (union)</td></tr>

 * <tr><td valign="top" headers="construct classes">{@code [a-z&&[def]]}</td>

 *     <td headers="matches">{@code d}, {@code e}, or {@code f} (intersection)</tr>

 * <tr><td valign="top" headers="construct classes">{@code [a-z&&[^bc]]}</td>

 *     <td headers="matches">{@code a} through {@code z},

 *         except for {@code b} and {@code c}: {@code [ad-z]} (subtraction)</td></tr>

 * <tr><td valign="top" headers="construct classes">{@code [a-z&&[^m-p]]}</td>

 *     <td headers="matches">{@code a} through {@code z},

 *          and not {@code m} through {@code p}: {@code [a-lq-z]}(subtraction)</td></tr>

 * <tr><th>&nbsp;</th></tr>

 *

 * <tr align="left"><th colspan="2" id="predef">Predefined character classes</th></tr>

 *

 *     <td headers="matches">Any character (may or may not match <a href="#lt">line terminators</a>)</td></tr>

 *     <td headers="matches">A horizontal whitespace character:

 *     </td></tr>

 * <tr><th>&nbsp;</th></tr>

 * <tr align="left"><th colspan="2" id="posix"><b>POSIX character classes (US-ASCII only)</b></th></tr>

 *

 * <tr><td valign="top" headers="construct posix">{@code \p{Lower}}</td>

 *     <td headers="matches">A lower-case alphabetic character: {@code [a-z]}</td></tr>

 * <tr><td valign="top" headers="construct posix">{@code \p{Upper}}</td>

 *     <td headers="matches">An upper-case alphabetic character:{@code [A-Z]}</td></tr>

 * <tr><td valign="top" headers="construct posix">{@code \p{ASCII}}</td>

 *     <td headers="matches">All ASCII:{@code [\x00-\x7F]}</td></tr>

 * <tr><td valign="top" headers="construct posix">{@code \p{Alpha}}</td>

 *     <td headers="matches">An alphabetic character:{@code [\p{Lower}\p{Upper}]}</td></tr>

 * <tr><td valign="top" headers="construct posix">{@code \p{Digit}}</td>

 *     <td headers="matches">A decimal digit: {@code [0-9]}</td></tr>

 * <tr><td valign="top" headers="construct posix">{@code \p{Alnum}}</td>

 *     <td headers="matches">An alphanumeric character:{@code [\p{Alpha}\p{Digit}]}</td></tr>

 * <tr><td valign="top" headers="construct posix">{@code \p{Punct}}</td>

 *     <td headers="matches">Punctuation: One of {@code !"#$%&'()*+,-./:;<=>?@[\]^_`{|}~}</td></tr>

 *     <!-- {@code [\!"#\$%&'\(\)\*\+,\-\./:;\<=\>\?@\[\\\]\^_`\{\|\}~]}

 *          {@code [\X21-\X2F\X31-\X40\X5B-\X60\X7B-\X7E]} -->

 * <tr><td valign="top" headers="construct posix">{@code \p{Graph}}</td>

 *     <td headers="matches">A visible character: {@code [\p{Alnum}\p{Punct}]}</td></tr>

 * <tr><td valign="top" headers="construct posix">{@code \p{Print}}</td>

 *     <td headers="matches">A printable character: {@code [\p{Graph}\x20]}</td></tr>

 * <tr><td valign="top" headers="construct posix">{@code \p{Blank}}</td>

 *     <td headers="matches">A space or a tab: {@code [ \t]}</td></tr>

 * <tr><td valign="top" headers="construct posix">{@code \p{Cntrl}}</td>

 *     <td headers="matches">A control character: {@code [\x00-\x1F\x7F]}</td></tr>

 * <tr><td valign="top" headers="construct posix">{@code \p{XDigit}}</td>

 *     <td headers="matches">A hexadecimal digit: {@code [0-9a-fA-F]}</td></tr>

 * <tr><td valign="top" headers="construct posix">{@code \p{Space}}</td>

 *     <td headers="matches">A whitespace character: {@code [ \t\n\x0B\f\r]}</td></tr>

 *

 * <tr><th>&nbsp;</th></tr>

 * <tr align="left"><th colspan="2">java.lang.Character classes (simple <a href="#jcc">java character type</a>)</th></tr>

 *

 *     <td>Equivalent to java.lang.Character.isLowerCase()</td></tr>

 *     <td>Equivalent to java.lang.Character.isUpperCase()</td></tr>

 *     <td>Equivalent to java.lang.Character.isWhitespace()</td></tr>

 *     <td>Equivalent to java.lang.Character.isMirrored()</td></tr>

 *

 * <tr><th>&nbsp;</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">{@code \p{IsLatin}}</td>

 *     <td headers="matches">A Latin&nbsp;script character (<a href="#usc">script</a>)</td></tr>

 * <tr><td valign="top" headers="construct unicode">{@code \p{InGreek}}</td>

 *     <td headers="matches">A character in the Greek&nbsp;block (<a href="#ubc">block</a>)</td></tr>

 * <tr><td valign="top" headers="construct unicode">{@code \p{Lu}}</td>

 *     <td headers="matches">An uppercase letter (<a href="#ucc">category</a>)</td></tr>

 * <tr><td valign="top" headers="construct unicode">{@code \p{IsAlphabetic}}</td>

 *     <td headers="matches">An alphabetic character (<a href="#ubpc">binary property</a>)</td></tr>

 * <tr><td valign="top" headers="construct unicode">{@code \p{Sc}}</td>

 *     <td headers="matches">A currency symbol</td></tr>

 * <tr><td valign="top" headers="construct unicode">{@code \P{InGreek}}</td>

 *     <td headers="matches">Any character except one in the Greek block (negation)</td></tr>

 * <tr><td valign="top" headers="construct unicode">{@code [\p{L}&&[^\p{Lu}]]}</td>

 *     <td headers="matches">Any letter except an uppercase letter (subtraction)</td></tr>

 *

 * <tr><th>&nbsp;</th></tr>

 * <tr align="left"><th colspan="2" id="bounds">Boundary matchers</th></tr>

 *

 *     <td headers="matches">The beginning of a line</td></tr>

 *     <td headers="matches">The end of a line</td></tr>

 *     <td headers="matches">A word boundary</td></tr>

 *     <td headers="matches">A non-word boundary</td></tr>

 *     <td headers="matches">The beginning of the input</td></tr>

 *     <td headers="matches">The end of the previous match</td></tr>

 *     <td headers="matches">The end of the input but for the final

 *         <a href="#lt">terminator</a>, if&nbsp;any</td></tr>

 *     <td headers="matches">The end of the input</td></tr>

 *

 * <tr><th>&nbsp;</th></tr>

 * <tr align="left"><th colspan="2" id="lineending">Linebreak matcher</th></tr>

 *     <td headers="matches">Any Unicode linebreak sequence, is equivalent to

 *

 * <tr><th>&nbsp;</th></tr>

 * <tr align="left"><th colspan="2" id="greedy">Greedy quantifiers</th></tr>

 *

 *     <td headers="matches"><i>X</i>, once or not at all</td></tr>

 *     <td headers="matches"><i>X</i>, zero or more times</td></tr>

 *     <td headers="matches"><i>X</i>, one or more times</td></tr>

 *     <td headers="matches"><i>X</i>, exactly <i>n</i> times</td></tr>

 *     <td headers="matches"><i>X</i>, at least <i>n</i> times</td></tr>

 *     <td headers="matches"><i>X</i>, at least <i>n</i> but not more than <i>m</i> times</td></tr>

 *

 * <tr><th>&nbsp;</th></tr>

 * <tr align="left"><th colspan="2" id="reluc">Reluctant quantifiers</th></tr>

 *

 *     <td headers="matches"><i>X</i>, once or not at all</td></tr>

 *     <td headers="matches"><i>X</i>, zero or more times</td></tr>

 *     <td headers="matches"><i>X</i>, one or more times</td></tr>

 *     <td headers="matches"><i>X</i>, exactly <i>n</i> times</td></tr>

 *     <td headers="matches"><i>X</i>, at least <i>n</i> times</td></tr>

 *     <td headers="matches"><i>X</i>, at least <i>n</i> but not more than <i>m</i> times</td></tr>

 *

 * <tr><th>&nbsp;</th></tr>

 * <tr align="left"><th colspan="2" id="poss">Possessive quantifiers</th></tr>

 *

 *     <td headers="matches"><i>X</i>, once or not at all</td></tr>

 *     <td headers="matches"><i>X</i>, zero or more times</td></tr>

 *     <td headers="matches"><i>X</i>, one or more times</td></tr>

 *     <td headers="matches"><i>X</i>, exactly <i>n</i> times</td></tr>

 *     <td headers="matches"><i>X</i>, at least <i>n</i> times</td></tr>

 *     <td headers="matches"><i>X</i>, at least <i>n</i> but not more than <i>m</i> times</td></tr>

 *

 * <tr><th>&nbsp;</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>

 *     <td headers="matches">Either <i>X</i> or <i>Y</i></td></tr>

 *     <td headers="matches">X, as a <a href="#cg">capturing group</a></td></tr>

 *

 * <tr><th>&nbsp;</th></tr>

 * <tr align="left"><th colspan="2" id="backref">Back references</th></tr>

 *

 *     <td valign="bottom" headers="matches">Whatever the <i>n</i><sup>th</sup>

 *     <a href="#cg">capturing group</a> matched</td></tr>

 *

 *     <td valign="bottom" headers="matches">Whatever the

 *     <a href="#groupname">named-capturing group</a> "name" matched</td></tr>

 *

 * <tr><th>&nbsp;</th></tr>

 * <tr align="left"><th colspan="2" id="quot">Quotation</th></tr>

 *

 *     <td headers="matches">Nothing, but quotes the following character</td></tr>

 *     <!-- Metachars: !$()*+.<>?[\]^{|} -->

 *

 * <tr><th>&nbsp;</th></tr>

 * <tr align="left"><th colspan="2" id="special">Special constructs (named-capturing and non-capturing)</th></tr>

 *

 *     <td headers="matches"><i>X</i>, as a named-capturing group</td></tr>

 *     <td headers="matches"><i>X</i>, as a non-capturing group</td></tr>

 *     <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>

 *     <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>

 *     <td headers="matches"><i>X</i>, via zero-width positive lookahead</td></tr>

 *     <td headers="matches"><i>X</i>, via zero-width negative lookahead</td></tr>

 *     <td headers="matches"><i>X</i>, via zero-width positive lookbehind</td></tr>

 *     <td headers="matches"><i>X</i>, via zero-width negative lookbehind</td></tr>

 *     <td headers="matches"><i>X</i>, as an independent, non-capturing group</td></tr>

 *

 * </table>

 *

 * <hr>

 *

 *

 * <h3><a name="bs">Backslashes, escapes, and quoting</a></h3>

 *

 * constructs, as defined in the table above, as well as to quote characters

 * that otherwise would be interpreted as unescaped constructs.  Thus the

 * 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&trade; 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

 * and leads to a compile-time error; in order to match the string

 * must be used.

 *

 * <h3><a name="cc">Character Classes</a></h3>

 *

 *    <p> Character classes may appear within other character classes, and

 *    may be composed by the union operator (implicit) and the intersection

 *    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&nbsp;&nbsp;&nbsp;&nbsp;</th>

 *        <td>Literal escape&nbsp;&nbsp;&nbsp;&nbsp;</td>

 *     <tr><th>2&nbsp;&nbsp;&nbsp;&nbsp;</th>

 *        <td>Grouping</td>

 *     <tr><th>3&nbsp;&nbsp;&nbsp;&nbsp;</th>

 *        <td>Range</td>

 *      <tr><th>4&nbsp;&nbsp;&nbsp;&nbsp;</th>

 *        <td>Union</td>

 *      <tr><th>5&nbsp;&nbsp;&nbsp;&nbsp;</th>

 *        <td>Intersection</td>

 *        <td>{@code [a-z&&[aeiou]]}</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

 *    forming metacharacter.

 *

 * <h3><a name="lt">Line terminators</a></h3>

 *

 * <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 carriage-return character followed immediately by a newline

 *

 *

 *

 *

 *

 * </ul>

 * <p>If {@link #UNIX_LINES} mode is activated, then the only line terminators

 * recognized are newline characters.

 *

 * terminator unless the {@link #DOTALL} flag is specified.

 *

 * line terminators and only match at the beginning and the end, respectively,

 * of the entire input sequence. If {@link #MULTILINE} mode is activated then

 * matches just before a line terminator or the end of the input sequence.

 *

 * <h3><a name="cg">Groups and capturing</a></h3>

 *

 * <h4><a name="gnumber">Group number</a></h4>

 * <p> Capturing groups are numbered by counting their opening parentheses from

 * are four such groups: </p>

 *

 * <blockquote><table cellpadding=1 cellspacing=0 summary="Capturing group numberings">

 * <tr><th>1&nbsp;&nbsp;&nbsp;&nbsp;</th>

 * <tr><th>2&nbsp;&nbsp;&nbsp;&nbsp;</th>

 * <tr><th>3&nbsp;&nbsp;&nbsp;&nbsp;</th>

 * <tr><th>4&nbsp;&nbsp;&nbsp;&nbsp;</th>

 * </table></blockquote>

 *

 * <p> Group zero always stands for the entire expression.

 *