/*
* 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 org.checkerframework.checker.index.qual.*;
import org.checkerframework.common.value.qual.*;
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 regular expression from which this pattern was
* compiled.</p>
*
* @return The string representation of this pattern
* @since 1.5
*/
public String toString() {
return pattern;
}
/**
* Creates a matcher that will match the given input against this pattern.
* </p>
*
* @param input
* The character sequence to be matched
*
* @return A new matcher for this pattern
*/
public Matcher matcher(CharSequence input) {
if (!compiled) {
synchronized(this) {
if (!compiled)
compile();
}
}
Matcher m = new Matcher(this, input);
return m;
}
/**
* Returns this pattern's match flags. </p>
*
* @return The match flags specified when this pattern was compiled
*/
public int flags() {
return flags;
}
/**
* Compiles the given regular expression and attempts to match the given
* input against it.
*
* <p> An invocation of this convenience method of the form
*
* <blockquote><pre>
* Pattern.matches(regex, input);</pre></blockquote>
*
* behaves in exactly the same way as the expression
*
* <blockquote><pre>
* Pattern.compile(regex).matcher(input).matches()</pre></blockquote>
*
* <p> If a pattern is to be used multiple times, compiling it once and reusing
* it will be more efficient than invoking this method each time. </p>
*
* @param regex
* The expression to be compiled
*
* @param input
* The character sequence to be matched
*
* @throws PatternSyntaxException
* If the expression's syntax is invalid
*/
public static boolean matches(String regex, CharSequence input) {
Pattern p = Pattern.compile(regex);
Matcher m = p.matcher(input);
return m.matches();
}
/**
* Splits the given input sequence around matches of this pattern.
*
* <p> The array returned by this method contains each substring of the
* input sequence that is terminated by another subsequence that matches
* this pattern or is terminated by the end of the input sequence. The
* substrings in the array are in the order in which they occur in the
* input. If this pattern does not match any subsequence of the input then
* the resulting array has just one element, namely the input sequence in
* string form.
*
* <p> The <tt>limit</tt> parameter controls the number of times the
* pattern is applied and therefore affects the length of the resulting
* array. If the limit <i>n</i> is greater than zero then the pattern
* will be applied at most <i>n</i> - 1 times, the array's
* length will be no greater than <i>n</i>, and the array's last entry
* will contain all input beyond the last matched delimiter. If <i>n</i>
* is non-positive then the pattern will be applied as many times as
* possible and the array can have any length. If <i>n</i> is zero then
* the pattern will be applied as many times as possible, the array can
* have any length, and trailing empty strings will be discarded.
*
* <p> The input <tt>"boo:and:foo"</tt>, for example, yields the following
* results with these parameters:
*
* <blockquote><table cellpadding=1 cellspacing=0
* summary="Split examples showing regex, limit, and result">
* <tr><th><P align="left"><i>Regex </i></th>
* <th><P align="left"><i>Limit </i></th>
* <th><P align="left"><i>Result </i></th></tr>
* <tr><td align=center>:</td>
* <td align=center>2</td>
* <td><tt>{ "boo", "and:foo" }</tt></td></tr>
* <tr><td align=center>:</td>
* <td align=center>5</td>
* <td><tt>{ "boo", "and", "foo" }</tt></td></tr>
* <tr><td align=center>:</td>
* <td align=center>-2</td>
* <td><tt>{ "boo", "and", "foo" }</tt></td></tr>
* <tr><td align=center>o</td>
* <td align=center>5</td>
* <td><tt>{ "b", "", ":and:f", "", "" }</tt></td></tr>
* <tr><td align=center>o</td>
* <td align=center>-2</td>
* <td><tt>{ "b", "", ":and:f", "", "" }</tt></td></tr>
* <tr><td align=center>o</td>
* <td align=center>0</td>
* <td><tt>{ "b", "", ":and:f" }</tt></td></tr>
* </table></blockquote>
*
*
* @param input
* The character sequence to be split
*
* @param limit
* The result threshold, as described above
*
* @return The array of strings computed by splitting the input
* around matches of this pattern
*/
public String [] split(CharSequence input, int limit) {
int index = 0;
boolean matchLimited = limit > 0;
ArrayList<String> matchList = new ArrayList<>();
Matcher m = matcher(input);
// Add segments before each match found
while(m.find()) {
if (!matchLimited || matchList.size() < limit - 1) {
String match = input.subSequence(index, m.start()).toString();
matchList.add(match);
index = m.end();
} else if (matchList.size() == limit - 1) { // last one
String match = input.subSequence(index,
input.length()).toString();
matchList.add(match);
index = m.end();
}
}
// If no match was found, return this
if (index == 0)
return new String[] {input.toString()};
// Add remaining segment
if (!matchLimited || matchList.size() < limit)
matchList.add(input.subSequence(index, input.length()).toString());
// Construct result
int resultSize = matchList.size();
if (limit == 0)
while (resultSize > 0 && matchList.get(resultSize-1).equals(""))
resultSize--;
String[] result = new String[resultSize];
return matchList.subList(0, resultSize).toArray(result);
}
/**
* Splits the given input sequence around matches of this pattern.
*
* <p> This method works as if by invoking the two-argument {@link
* #split(java.lang.CharSequence, int) split} method with the given input
* sequence and a limit argument of zero. Trailing empty strings are
* therefore not included in the resulting array. </p>
*
* <p> The input <tt>"boo:and:foo"</tt>, for example, yields the following
* results with these expressions:
*
* <blockquote><table cellpadding=1 cellspacing=0
* summary="Split examples showing regex and result">
* <tr><th><P align="left"><i>Regex </i></th>
* <th><P align="left"><i>Result</i></th></tr>
* <tr><td align=center>:</td>
* <td><tt>{ "boo", "and", "foo" }</tt></td></tr>
* <tr><td align=center>o</td>
* <td><tt>{ "b", "", ":and:f" }</tt></td></tr>
* </table></blockquote>
*
*
* @param input
* The character sequence to be split
*
* @return The array of strings computed by splitting the input
* around matches of this pattern
*/
public String [] split(CharSequence input) {
return split(input, 0);
}
/**
* Returns a literal pattern <code>String</code> for the specified
* <code>String</code>.
*
* <p>This method produces a <code>String</code> that can be used to
* create a <code>Pattern</code> that would match the string
* <code>s</code> as if it were a literal pattern.</p> Metacharacters
* or escape sequences in the input sequence will be given no special
* meaning.
*
* @param s The string to be literalized
* @return A literal string replacement
* @since 1.5
*/
public static String quote(String s) {
int slashEIndex = s.indexOf("\\E");
if (slashEIndex == -1)
return "\\Q" + s + "\\E";
StringBuilder sb = new StringBuilder(s.length() * 2);
sb.append("\\Q");
slashEIndex = 0;
int current = 0;
while ((slashEIndex = s.indexOf("\\E", current)) != -1) {
sb.append(s.substring(current, slashEIndex));
current = slashEIndex + 2;
sb.append("\\E\\\\E\\Q");
}
sb.append(s.substring(current, s.length()));
sb.append("\\E");
return sb.toString();
}
/**
* Recompile the Pattern instance from a stream. The original pattern
* string is read in and the object tree is recompiled from it.
*/
private void readObject(java.io.ObjectInputStream s)
throws java.io.IOException, ClassNotFoundException {
// Read in all fields
s.defaultReadObject();
// Initialize counts
capturingGroupCount = 1;
localCount = 0;
// if length > 0, the Pattern is lazily compiled
compiled = false;
if (pattern.length() == 0) {
root = new Start(lastAccept);
matchRoot = lastAccept;
compiled = true;
}
}
/**
* This private constructor is used to create all Patterns. The pattern
* string and match flags are all that is needed to completely describe
* a Pattern. An empty pattern string results in an object tree with
* only a Start node and a LastNode node.
*/
private Pattern(String p, int f) {
pattern = p;
flags = f;
// to use UNICODE_CASE if UNICODE_CHARACTER_CLASS present
if ((flags & UNICODE_CHARACTER_CLASS) != 0)
flags |= UNICODE_CASE;
// Reset group index count
capturingGroupCount = 1;
localCount = 0;
if (pattern.length() > 0) {
compile();
} else {
root = new Start(lastAccept);
matchRoot = lastAccept;
}
}
/**
* The pattern is converted to normalizedD form and then a pure group
* is constructed to match canonical equivalences of the characters.
*/
private void normalize() {
boolean inCharClass = false;
int lastCodePoint = -1;
// Convert pattern into normalizedD form
normalizedPattern = Normalizer.normalize(pattern, Normalizer.Form.NFD);
patternLength = normalizedPattern.length();
// Modify pattern to match canonical equivalences
StringBuilder newPattern = new StringBuilder(patternLength);
for(int i=0; i<patternLength; ) {
int c = normalizedPattern.codePointAt(i);
StringBuilder sequenceBuffer;
if ((Character.getType(c) == Character.NON_SPACING_MARK)
&& (lastCodePoint != -1)) {
sequenceBuffer = new StringBuilder();
sequenceBuffer.appendCodePoint(lastCodePoint);
sequenceBuffer.appendCodePoint(c);
while(Character.getType(c) == Character.NON_SPACING_MARK) {
i += Character.charCount(c);
if (i >= patternLength)
break;
c = normalizedPattern.codePointAt(i);
sequenceBuffer.appendCodePoint(c);
}
String ea = produceEquivalentAlternation(
sequenceBuffer.toString());
newPattern.setLength(newPattern.length()-Character.charCount(lastCodePoint));
newPattern.append("(?:").append(ea).append(")");
} else if (c == '[' && lastCodePoint != '\\') {
i = normalizeCharClass(newPattern, i);
} else {
newPattern.appendCodePoint(c);
}
lastCodePoint = c;
i += Character.charCount(c);
}
normalizedPattern = newPattern.toString();
}
/**
* Complete the character class being parsed and add a set
* of alternations to it that will match the canonical equivalences
* of the characters within the class.
*/
private int normalizeCharClass(StringBuilder newPattern, int i) {
StringBuilder charClass = new StringBuilder();
StringBuilder eq = null;
int lastCodePoint = -1;
String result;
i++;
charClass.append("[");
while(true) {
int c = normalizedPattern.codePointAt(i);
StringBuilder sequenceBuffer;
if (c == ']' && lastCodePoint != '\\') {
charClass.append((char)c);
break;
} else if (Character.getType(c) == Character.NON_SPACING_MARK) {
sequenceBuffer = new StringBuilder();
sequenceBuffer.appendCodePoint(lastCodePoint);
while(Character.getType(c) == Character.NON_SPACING_MARK) {
sequenceBuffer.appendCodePoint(c);
i += Character.charCount(c);
if (i >= normalizedPattern.length())
break;
c = normalizedPattern.codePointAt(i);
}
String ea = produceEquivalentAlternation(
sequenceBuffer.toString());
charClass.setLength(charClass.length()-Character.charCount(lastCodePoint));
if (eq == null)
eq = new StringBuilder();
eq.append('|');
eq.append(ea);
} else {
charClass.appendCodePoint(c);
i++;
}
if (i == normalizedPattern.length())
throw error("Unclosed character class");
lastCodePoint = c;
}
if (eq != null) {
result = "(?:"+charClass.toString()+eq.toString()+")";
} else {
result = charClass.toString();
}
newPattern.append(result);
return i;
}
/**
* Given a specific sequence composed of a regular character and
* combining marks that follow it, produce the alternation that will
* match all canonical equivalences of that sequence.
*/
private String produceEquivalentAlternation(String source) {
int len = countChars(source, 0, 1);
if (source.length() == len)
// source has one character.
return source;
String base = source.substring(0,len);
String combiningMarks = source.substring(len);
String[] perms = producePermutations(combiningMarks);
StringBuilder result = new StringBuilder(source);
// Add combined permutations
for(int x=0; x<perms.length; x++) {
String next = base + perms[x];
if (x>0)
result.append("|"+next);
next = composeOneStep(next);
if (next != null)
result.append("|"+produceEquivalentAlternation(next));
}
return result.toString();
}
/**
* Returns an array of strings that have all the possible
* permutations of the characters in the input string.
* This is used to get a list of all possible orderings
* of a set of combining marks. Note that some of the permutations
* are invalid because of combining class collisions, and these
* possibilities must be removed because they are not canonically
* equivalent.
*/
private String[] producePermutations(String input) {
if (input.length() == countChars(input, 0, 1))
return new String[] {input};
if (input.length() == countChars(input, 0, 2)) {
int c0 = Character.codePointAt(input, 0);
int c1 = Character.codePointAt(input, Character.charCount(c0));
if (getClass(c1) == getClass(c0)) {
return new String[] {input};
}
String[] result = new String[2];
result[0] = input;
StringBuilder sb = new StringBuilder(2);
sb.appendCodePoint(c1);
sb.appendCodePoint(c0);
result[1] = sb.toString();
return result;
}
int length = 1;
int nCodePoints = countCodePoints(input);
for(int x=1; x<nCodePoints; x++)
length = length * (x+1);
String[] temp = new String[length];
int combClass[] = new int[nCodePoints];
for(int x=0, i=0; x<nCodePoints; x++) {
int c = Character.codePointAt(input, i);
combClass[x] = getClass(c);
i += Character.charCount(c);
}
// For each char, take it out and add the permutations
// of the remaining chars
int index = 0;
int len;
// offset maintains the index in code units.
loop: for(int x=0, offset=0; x<nCodePoints; x++, offset+=len) {
len = countChars(input, offset, 1);
boolean skip = false;
for(int y=x-1; y>=0; y--) {
if (combClass[y] == combClass[x]) {
continue loop;
}
}
StringBuilder sb = new StringBuilder(input);
String otherChars = sb.delete(offset, offset+len).toString();
String[] subResult = producePermutations(otherChars);
String prefix = input.substring(offset, offset+len);
for(int y=0; y<subResult.length; y++)
temp[index++] = prefix + subResult[y];
}
String[] result = new String[index];
for (int x=0; x<index; x++)
result[x] = temp[x];
return result;
}
private int getClass(int c) {
return sun.text.Normalizer.getCombiningClass(c);
}
/**
* Attempts to compose input by combining the first character
* with the first combining mark following it. Returns a String
* that is the composition of the leading character with its first
* combining mark followed by the remaining combining marks. Returns
* null if the first two characters cannot be further composed.
*/
private String composeOneStep(String input) {
int len = countChars(input, 0, 2);
String firstTwoCharacters = input.substring(0, len);
String result = Normalizer.normalize(firstTwoCharacters, Normalizer.Form.NFC);
if (result.equals(firstTwoCharacters))
return null;
else {
String remainder = input.substring(len);
return result + remainder;
}
}
/**
* Preprocess any \Q...\E sequences in `temp', meta-quoting them.
* See the description of `quotemeta' in perlfunc(1).
*/
private void RemoveQEQuoting() {
final int pLen = patternLength;
int i = 0;
while (i < pLen-1) {
if (temp[i] != '\\')
i += 1;
else if (temp[i + 1] != 'Q')
i += 2;
else
break;
}
if (i >= pLen - 1) // No \Q sequence found
return;
int j = i;
i += 2;
int[] newtemp = new int[j + 2*(pLen-i) + 2];
System.arraycopy(temp, 0, newtemp, 0, j);
boolean inQuote = true;
while (i < pLen) {
int c = temp[i++];
if (! ASCII.isAscii(c) || ASCII.isAlnum(c)) {
newtemp[j++] = c;
} else if (c != '\\') {
if (inQuote) newtemp[j++] = '\\';
newtemp[j++] = c;
} else if (inQuote) {
if (temp[i] == 'E') {
i++;
inQuote = false;
} else {
newtemp[j++] = '\\';
newtemp[j++] = '\\';
}
} else {
if (temp[i] == 'Q') {
i++;
inQuote = true;
} else {
newtemp[j++] = c;
if (i != pLen)
newtemp[j++] = temp[i++];
}
}
}
patternLength = j;
temp = Arrays.copyOf(newtemp, j + 2); // double zero termination
}
/**
* Copies regular expression to an int array and invokes the parsing
* of the expression which will create the object tree.
*/
private void compile() {
// Handle canonical equivalences
if (has(CANON_EQ) && !has(LITERAL)) {
normalize();
} else {
normalizedPattern = pattern;
}
patternLength = normalizedPattern.length();
// Copy pattern to int array for convenience
// Use double zero to terminate pattern
temp = new int[patternLength + 2];
hasSupplementary = false;
int c, count = 0;
// Convert all chars into code points
for (int x = 0; x < patternLength; x += Character.charCount(c)) {
c = normalizedPattern.codePointAt(x);
if (isSupplementary(c)) {
hasSupplementary = true;
}
temp[count++] = c;
}
patternLength = count; // patternLength now in code points
if (! has(LITERAL))
RemoveQEQuoting();
// Allocate all temporary objects here.
buffer = new int[32];
groupNodes = new GroupHead[10];
namedGroups = null;
if (has(LITERAL)) {
// Literal pattern handling
matchRoot = newSlice(temp, patternLength, hasSupplementary);
matchRoot.next = lastAccept;
} else {
// Start recursive descent parsing
matchRoot = expr(lastAccept);
// Check extra pattern characters
if (patternLength != cursor) {
if (peek() == ')') {
throw error("Unmatched closing ')'");
} else {
throw error("Unexpected internal error");
}
}
}
// Peephole optimization
if (matchRoot instanceof Slice) {
root = BnM.optimize(matchRoot);
if (root == matchRoot) {
root = hasSupplementary ? new StartS(matchRoot) : new Start(matchRoot);
}
} else if (matchRoot instanceof Begin || matchRoot instanceof First) {
root = matchRoot;
} else {
root = hasSupplementary ? new StartS(matchRoot) : new Start(matchRoot);
}
// Release temporary storage
temp = null;
buffer = null;
groupNodes = null;
patternLength = 0;
compiled = true;
}
Map<String, Integer> namedGroups() {
if (namedGroups == null)
namedGroups = new HashMap<>(2);
return namedGroups;
}
/**
* Used to print out a subtree of the Pattern to help with debugging.
*/
private static void printObjectTree(Node node) {
while(node != null) {
if (node instanceof Prolog) {
System.out.println(node);
printObjectTree(((Prolog)node).loop);
System.out.println("**** end contents prolog loop");
} else if (node instanceof Loop) {
System.out.println(node);
printObjectTree(((Loop)node).body);
System.out.println("**** end contents Loop body");
} else if (node instanceof Curly) {
System.out.println(node);
printObjectTree(((Curly)node).atom);
System.out.println("**** end contents Curly body");
} else if (node instanceof GroupCurly) {
System.out.println(node);
printObjectTree(((GroupCurly)node).atom);
System.out.println("**** end contents GroupCurly body");
} else if (node instanceof GroupTail) {
System.out.println(node);
System.out.println("Tail next is "+node.next);
return;
} else {
System.out.println(node);
}
node = node.next;
if (node != null)
System.out.println("->next:");
if (node == Pattern.accept) {
System.out.println("Accept Node");
node = null;
}
}
}
/**
* Used to accumulate information about a subtree of the object graph
* so that optimizations can be applied to the subtree.
*/
static final class TreeInfo {
int minLength;
int maxLength;
boolean maxValid;
boolean deterministic;
TreeInfo() {
reset();
}
void reset() {
minLength = 0;
maxLength = 0;
maxValid = true;
deterministic = true;
}
}
/*
* The following private methods are mainly used to improve the
* readability of the code. In order to let the Java compiler easily
* inline them, we should not put many assertions or error checks in them.
*/
/**
* Indicates whether a particular flag is set or not.
*/
private boolean has(int f) {
return (flags & f) != 0;
}
/**
* Match next character, signal error if failed.
*/
private void accept(int ch, String s) {
int testChar = temp[cursor++];
if (has(COMMENTS))
testChar = parsePastWhitespace(testChar);
if (ch != testChar) {
throw error(s);
}
}
/**
* Mark the end of pattern with a specific character.
*/
private void mark(int c) {
temp[patternLength] = c;
}
/**
* Peek the next character, and do not advance the cursor.
*/
private int peek() {
int ch = temp[cursor];
if (has(COMMENTS))
ch = peekPastWhitespace(ch);
return ch;
}
/**
* Read the next character, and advance the cursor by one.
*/
private int read() {
int ch = temp[cursor++];
if (has(COMMENTS))
ch = parsePastWhitespace(ch);
return ch;
}
/**
* Read the next character, and advance the cursor by one,
* ignoring the COMMENTS setting
*/
private int readEscaped() {
int ch = temp[cursor++];
return ch;
}
/**
* Advance the cursor by one, and peek the next character.
*/
private int next() {
int ch = temp[++cursor];
if (has(COMMENTS))
ch = peekPastWhitespace(ch);
return ch;
}
/**
* Advance the cursor by one, and peek the next character,
* ignoring the COMMENTS setting
*/
private int nextEscaped() {
int ch = temp[++cursor];
return ch;
}
/**
* If in xmode peek past whitespace and comments.
*/
private int peekPastWhitespace(int ch) {
while (ASCII.isSpace(ch) || ch == '#') {
while (ASCII.isSpace(ch))
ch = temp[++cursor];
if (ch == '#') {
ch = peekPastLine();
}
}
return ch;
}
/**
* If in xmode parse past whitespace and comments.
*/
private int parsePastWhitespace(int ch) {
while (ASCII.isSpace(ch) || ch == '#') {
while (ASCII.isSpace(ch))
ch = temp[cursor++];
if (ch == '#')
ch = parsePastLine();
}
return ch;
}
/**
* xmode parse past comment to end of line.
*/
private int parsePastLine() {
int ch = temp[cursor++];
while (ch != 0 && !isLineSeparator(ch))
ch = temp[cursor++];
return ch;
}
/**
* xmode peek past comment to end of line.
*/
private int peekPastLine() {
int ch = temp[++cursor];
while (ch != 0 && !isLineSeparator(ch))
ch = temp[++cursor];
return ch;
}
/**
* Determines if character is a line separator in the current mode
*/
private boolean isLineSeparator(int ch) {
if (has(UNIX_LINES)) {
return ch == '\n';
} else {
return (ch == '\n' ||
ch == '\r' ||
(ch|1) == '\u2029' ||
ch == '\u0085');
}
}
/**
* Read the character after the next one, and advance the cursor by two.
*/
private int skip() {
int i = cursor;
int ch = temp[i+1];
cursor = i + 2;
return ch;
}
/**
* Unread one next character, and retreat cursor by one.
*/
private void unread() {
cursor--;
}
/**
* Internal method used for handling all syntax errors. The pattern is
* displayed with a pointer to aid in locating the syntax error.
*/
private PatternSyntaxException error(String s) {
return new PatternSyntaxException(s, normalizedPattern, cursor - 1);
}
/**
* Determines if there is any supplementary character or unpaired
* surrogate in the specified range.
*/
private boolean findSupplementary(int start, int end) {
for (int i = start; i < end; i++) {
if (isSupplementary(temp[i]))
return true;
}
return false;
}
/**
* Determines if the specified code point is a supplementary
* character or unpaired surrogate.
*/
private static final boolean isSupplementary(int ch) {
return ch >= Character.MIN_SUPPLEMENTARY_CODE_POINT ||
Character.isSurrogate((char)ch);
}
/**
* The following methods handle the main parsing. They are sorted
* according to their precedence order, the lowest one first.
*/
/**
* The expression is parsed with branch nodes added for alternations.
* This may be called recursively to parse sub expressions that may
* contain alternations.
*/
private Node expr(Node end) {
Node prev = null;
Node firstTail = null;
Node branchConn = null;
for (;;) {
Node node = sequence(end);
Node nodeTail = root; //double return
if (prev == null) {
prev = node;
firstTail = nodeTail;
} else {
// Branch
if (branchConn == null) {
branchConn = new BranchConn();
branchConn.next = end;
}
if (node == end) {
// if the node returned from sequence() is "end"
// we have an empty expr, set a null atom into
// the branch to indicate to go "next" directly.
node = null;
} else {
// the "tail.next" of each atom goes to branchConn
nodeTail.next = branchConn;
}
if (prev instanceof Branch) {
((Branch)prev).add(node);
} else {
if (prev == end) {
prev = null;
} else {
// replace the "end" with "branchConn" at its tail.next
// when put the "prev" into the branch as the first atom.
firstTail.next = branchConn;
}
prev = new Branch(prev, node, branchConn);
}
}
if (peek() != '|') {
return prev;
}
next();
}
}
/**
* Parsing of sequences between alternations.
*/
private Node sequence(Node end) {
Node head = null;
Node tail = null;
Node node = null;
LOOP:
for (;;) {
int ch = peek();
switch (ch) {
case '(':
// Because group handles its own closure,
// we need to treat it differently
node = group0();
// Check for comment or flag group
if (node == null)
continue;
if (head == null)
head = node;
else
tail.next = node;
// Double return: Tail was returned in root
tail = root;
continue;
case '[':
node = clazz(true);
break;
case '\\':
ch = nextEscaped();
if (ch == 'p' || ch == 'P') {
boolean oneLetter = true;
boolean comp = (ch == 'P');
ch = next(); // Consume { if present
if (ch != '{') {
unread();
} else {
oneLetter = false;
}
node = family(oneLetter, comp);
} else {
unread();
node = atom();
}
break;
case '^':
next();
if (has(MULTILINE)) {
if (has(UNIX_LINES))
node = new UnixCaret();
else
node = new Caret();
} else {
node = new Begin();
}
break;
case '$':
next();
if (has(UNIX_LINES))
node = new UnixDollar(has(MULTILINE));
else
node = new Dollar(has(MULTILINE));
break;
case '.':
next();
if (has(DOTALL)) {
node = new All();
} else {
if (has(UNIX_LINES))
node = new UnixDot();
else {
node = new Dot();
}
}
break;
case '|':
case ')':
break LOOP;
case ']': // Now interpreting dangling ] and } as literals
case '}':
node = atom();
break;
case '?':
case '*':
case '+':
next();
throw error("Dangling meta character '" + ((char)ch) + "'");
case 0:
if (cursor >= patternLength) {
break LOOP;
}
// Fall through
default:
node = atom();
break;
}
node = closure(node);
if (head == null) {
head = tail = node;
} else {
tail.next = node;
tail = node;
}
}
if (head == null) {
return end;
}
tail.next = end;
root = tail; //double return
return head;
}
/**
* Parse and add a new Single or Slice.
*/
private Node atom() {
int first = 0;
int prev = -1;
boolean hasSupplementary = false;
int ch = peek();
for (;;) {
switch (ch) {
case '*':
case '+':
case '?':
case '{':
if (first > 1) {
cursor = prev; // Unwind one character
first--;
}
break;
case '$':
case '.':
case '^':
case '(':
case '[':
case '|':
case ')':
break;
case '\\':
ch = nextEscaped();
if (ch == 'p' || ch == 'P') { // Property
if (first > 0) { // Slice is waiting; handle it first
unread();
break;
} else { // No slice; just return the family node
boolean comp = (ch == 'P');
boolean oneLetter = true;
ch = next(); // Consume { if present
if (ch != '{')
unread();
else
oneLetter = false;
return family(oneLetter, comp);
}
}
unread();
prev = cursor;
ch = escape(false, first == 0);
if (ch >= 0) {
append(ch, first);
first++;
if (isSupplementary(ch)) {
hasSupplementary = true;
}
ch = peek();
continue;
} else if (first == 0) {
return root;
}
// Unwind meta escape sequence
cursor = prev;
break;
case 0:
if (cursor >= patternLength) {
break;
}
// Fall through
default:
prev = cursor;
append(ch, first);
first++;
if (isSupplementary(ch)) {
hasSupplementary = true;
}
ch = next();
continue;
}
break;
}
if (first == 1) {
return newSingle(buffer[0]);
} else {
return newSlice(buffer, first, hasSupplementary);
}
}
private void append(int ch, int len) {
if (len >= buffer.length) {
int[] tmp = new int[len+len];
System.arraycopy(buffer, 0, tmp, 0, len);
buffer = tmp;
}
buffer[len] = ch;
}
/**
* Parses a backref greedily, taking as many numbers as it
* can. The first digit is always treated as a backref, but
* multi digit numbers are only treated as a backref if at
* least that many backrefs exist at this point in the regex.
*/
private Node ref(int refNum) {
boolean done = false;
while(!done) {
int ch = peek();
switch(ch) {
case '0':
case '1':
case '2':
case '3':
case '4':
case '5':
case '6':
case '7':
case '8':
case '9':
int newRefNum = (refNum * 10) + (ch - '0');
// Add another number if it doesn't make a group
// that doesn't exist
if (capturingGroupCount - 1 < newRefNum) {
done = true;
break;
}
refNum = newRefNum;
read();
break;
default:
done = true;
break;
}
}
if (has(CASE_INSENSITIVE))
return new CIBackRef(refNum, has(UNICODE_CASE));
else
return new BackRef(refNum);
}
/**
* Parses an escape sequence to determine the actual value that needs
* to be matched.
* If -1 is returned and create was true a new object was added to the tree
* to handle the escape sequence.
* If the returned value is greater than zero, it is the value that
* matches the escape sequence.
*/
private int escape(boolean inclass, boolean create) {
int ch = skip();
switch (ch) {
case '0':
return o();
case '1':
case '2':
case '3':
case '4':
case '5':
case '6':
case '7':
case '8':
case '9':
if (inclass) break;
if (create) {
root = ref((ch - '0'));
}
return -1;
case 'A':
if (inclass) break;
if (create) root = new Begin();
return -1;
case 'B':
if (inclass) break;
if (create) root = new Bound(Bound.NONE, has(UNICODE_CHARACTER_CLASS));
return -1;
case 'C':
break;
case 'D':
if (create) root = has(UNICODE_CHARACTER_CLASS)
? new Utype(UnicodeProp.DIGIT).complement()
: new Ctype(ASCII.DIGIT).complement();
return -1;
case 'E':
case 'F':
break;
case 'G':
if (inclass) break;
if (create) root = new LastMatch();
return -1;
case 'H':
case 'I':
case 'J':
case 'K':
case 'L':
case 'M':
case 'N':
case 'O':
case 'P':
case 'Q':
case 'R':
break;
case 'S':
if (create) root = has(UNICODE_CHARACTER_CLASS)
? new Utype(UnicodeProp.WHITE_SPACE).complement()
: new Ctype(ASCII.SPACE).complement();
return -1;
case 'T':
case 'U':
case 'V':
break;
case 'W':
if (create) root = has(UNICODE_CHARACTER_CLASS)
? new Utype(UnicodeProp.WORD).complement()
: new Ctype(ASCII.WORD).complement();
return -1;
case 'X':
case 'Y':
break;
case 'Z':
if (inclass) break;
if (create) {
if (has(UNIX_LINES))
root = new UnixDollar(false);
else
root = new Dollar(false);
}
return -1;
case 'a':
return '\007';
case 'b':
if (inclass) break;
if (create) root = new Bound(Bound.BOTH, has(UNICODE_CHARACTER_CLASS));
return -1;
case 'c':
return c();
case 'd':
if (create) root = has(UNICODE_CHARACTER_CLASS)
? new Utype(UnicodeProp.DIGIT)
: new Ctype(ASCII.DIGIT);
return -1;
case 'e':
return '\033';
case 'f':
return '\f';
case 'g':
case 'h':
case 'i':
case 'j':
break;
case 'k':
if (inclass)
break;
if (read() != '<')
throw error("\\k is not followed by '<' for named capturing group");
String name = groupname(read());
if (!namedGroups().containsKey(name))
throw error("(named capturing group <"+ name+"> does not exit");
if (create) {
if (has(CASE_INSENSITIVE))
root = new CIBackRef(namedGroups().get(name), has(UNICODE_CASE));
else
root = new BackRef(namedGroups().get(name));
}
return -1;
case 'l':
case 'm':
break;
case 'n':
return '\n';
case 'o':
case 'p':
case 'q':
break;
case 'r':
return '\r';
case 's':
if (create) root = has(UNICODE_CHARACTER_CLASS)
? new Utype(UnicodeProp.WHITE_SPACE)
: new Ctype(ASCII.SPACE);
return -1;
case 't':
return '\t';
case 'u':
return u();
case 'v':
return '\013';
case 'w':
if (create) root = has(UNICODE_CHARACTER_CLASS)
? new Utype(UnicodeProp.WORD)
: new Ctype(ASCII.WORD);
return -1;
case 'x':
return x();
case 'y':
break;
case 'z':
if (inclass) break;
if (create) root = new End();
return -1;
default:
return ch;
}
throw error("Illegal/unsupported escape sequence");
}
/**
* Parse a character class, and return the node that matches it.
*
* Consumes a ] on the way out if consume is true. Usually consume
* is true except for the case of [abc&&def] where def is a separate
* right hand node with "understood" brackets.
*/
private CharProperty clazz(boolean consume) {
CharProperty prev = null;
CharProperty node = null;
BitClass bits = new BitClass();
boolean include = true;
boolean firstInClass = true;
int ch = next();
for (;;) {
switch (ch) {
case '^':
// Negates if first char in a class, otherwise literal
if (firstInClass) {
if (temp[cursor-1] != '[')
break;
ch = next();
include = !include;
continue;
} else {
// ^ not first in class, treat as literal
break;
}
case '[':
firstInClass = false;
node = clazz(true);
if (prev == null)
prev = node;
else
prev = union(prev, node);
ch = peek();
continue;
case '&':
firstInClass = false;
ch = next();
if (ch == '&') {
ch = next();
CharProperty rightNode = null;
while (ch != ']' && ch != '&') {
if (ch == '[') {
if (rightNode == null)
rightNode = clazz(true);
else
rightNode = union(rightNode, clazz(true));
} else { // abc&&def
unread();
rightNode = clazz(false);
}
ch = peek();
}
if (rightNode != null)
node = rightNode;
if (prev == null) {
if (rightNode == null)
throw error("Bad class syntax");
else
prev = rightNode;
} else {
prev = intersection(prev, node);
}
} else {
// treat as a literal &
unread();
break;
}
continue;
case 0:
firstInClass = false;
if (cursor >= patternLength)
throw error("Unclosed character class");
break;
case ']':
firstInClass = false;
if (prev != null) {
if (consume)
next();
return prev;
}
break;
default:
firstInClass = false;
break;
}
node = range(bits);
if (include) {
if (prev == null) {
prev = node;
} else {
if (prev != node)
prev = union(prev, node);
}
} else {
if (prev == null) {
prev = node.complement();
} else {
if (prev != node)
prev = setDifference(prev, node);
}
}
ch = peek();
}
}
private CharProperty bitsOrSingle(BitClass bits, int ch) {
/* Bits can only handle codepoints in [u+0000-u+00ff] range.
Use "single" node instead of bits when dealing with unicode
case folding for codepoints listed below.
(1)Uppercase out of range: u+00ff, u+00b5
toUpperCase(u+00ff) -> u+0178
toUpperCase(u+00b5) -> u+039c
(2)LatinSmallLetterLongS u+17f
toUpperCase(u+017f) -> u+0053
(3)LatinSmallLetterDotlessI u+131
toUpperCase(u+0131) -> u+0049
(4)LatinCapitalLetterIWithDotAbove u+0130
toLowerCase(u+0130) -> u+0069
(5)KelvinSign u+212a
toLowerCase(u+212a) ==> u+006B
(6)AngstromSign u+212b
toLowerCase(u+212b) ==> u+00e5
*/
int d;
if (ch < 256 &&
!(has(CASE_INSENSITIVE) && has(UNICODE_CASE) &&
(ch == 0xff || ch == 0xb5 ||
ch == 0x49 || ch == 0x69 || //I and i
ch == 0x53 || ch == 0x73 || //S and s
ch == 0x4b || ch == 0x6b || //K and k
ch == 0xc5 || ch == 0xe5))) //A+ring
return bits.add(ch, flags());
return newSingle(ch);
}
/**
* Parse a single character or a character range in a character class
* and return its representative node.
*/
private CharProperty range(BitClass bits) {
int ch = peek();
if (ch == '\\') {
ch = nextEscaped();
if (ch == 'p' || ch == 'P') { // A property
boolean comp = (ch == 'P');
boolean oneLetter = true;
// Consume { if present
ch = next();
if (ch != '{')
unread();
else
oneLetter = false;
return family(oneLetter, comp);
} else { // ordinary escape
unread();
ch = escape(true, true);
if (ch == -1)
return (CharProperty) root;
}
} else {
ch = single();
}
if (ch >= 0) {
if (peek() == '-') {
int endRange = temp[cursor+1];
if (endRange == '[') {
return bitsOrSingle(bits, ch);
}
if (endRange != ']') {
next();
int m = single();
if (m < ch)
throw error("Illegal character range");
if (has(CASE_INSENSITIVE))
return caseInsensitiveRangeFor(ch, m);
else
return rangeFor(ch, m);
}
}
return bitsOrSingle(bits, ch);
}
throw error("Unexpected character '"+((char)ch)+"'");
}
private int single() {
int ch = peek();
switch (ch) {
case '\\':
return escape(true, false);
default:
next();
return ch;
}
}
/**
* Parses a Unicode character family and returns its representative node.
*/
private CharProperty family(boolean singleLetter,
boolean maybeComplement)
{
next();
String name;
CharProperty node = null;
if (singleLetter) {
int c = temp[cursor];
if (!Character.isSupplementaryCodePoint(c)) {
name = String.valueOf((char)c);
} else {
name = new String(temp, cursor, 1);
}
read();
} else {
int i = cursor;
mark('}');
while(read() != '}') {
}
mark('\000');
int j = cursor;
if (j > patternLength)
throw error("Unclosed character family");
if (i + 1 >= j)
throw error("Empty character family");
name = new String(temp, i, j-i-1);
}
int i = name.indexOf('=');
if (i != -1) {
// property construct \p{name=value}
String value = name.substring(i + 1);
name = name.substring(0, i).toLowerCase(Locale.ENGLISH);
if ("sc".equals(name) || "script".equals(name)) {
node = unicodeScriptPropertyFor(value);
} else if ("blk".equals(name) || "block".equals(name)) {
node = unicodeBlockPropertyFor(value);
} else if ("gc".equals(name) || "general_category".equals(name)) {
node = charPropertyNodeFor(value);
} else {
throw error("Unknown Unicode property {name=<" + name + ">, "
+ "value=<" + value + ">}");
}
} else {
if (name.startsWith("In")) {
// \p{inBlockName}
node = unicodeBlockPropertyFor(name.substring(2));
} else if (name.startsWith("Is")) {
// \p{isGeneralCategory} and \p{isScriptName}
name = name.substring(2);
UnicodeProp uprop = UnicodeProp.forName(name);
if (uprop != null)
node = new Utype(uprop);
if (node == null)
node = CharPropertyNames.charPropertyFor(name);
if (node == null)
node = unicodeScriptPropertyFor(name);
} else {
if (has(UNICODE_CHARACTER_CLASS)) {
UnicodeProp uprop = UnicodeProp.forPOSIXName(name);
if (uprop != null)
node = new Utype(uprop);
}
if (node == null)
node = charPropertyNodeFor(name);
}
}
if (maybeComplement) {
if (node instanceof Category || node instanceof Block)
hasSupplementary = true;
node = node.complement();
}
return node;
}
/**
* Returns a CharProperty matching all characters belong to
* a UnicodeScript.
*/
private CharProperty unicodeScriptPropertyFor(String name) {
final Character.UnicodeScript script;
try {
script = Character.UnicodeScript.forName(name);
} catch (IllegalArgumentException iae) {
throw error("Unknown character script name {" + name + "}");
}
return new Script(script);
}
/**
* Returns a CharProperty matching all characters in a UnicodeBlock.
*/
private CharProperty unicodeBlockPropertyFor(String name) {
final Character.UnicodeBlock block;
try {
block = Character.UnicodeBlock.forName(name);
} catch (IllegalArgumentException iae) {
throw error("Unknown character block name {" + name + "}");
}
return new Block(block);
}
/**
* Returns a CharProperty matching all characters in a named property.
*/
private CharProperty charPropertyNodeFor(String name) {
CharProperty p = CharPropertyNames.charPropertyFor(name);
if (p == null)
throw error("Unknown character property name {" + name + "}");
return p;
}
/**
* Parses and returns the name of a "named capturing group", the trailing
* ">" is consumed after parsing.
*/
private String groupname(int ch) {
StringBuilder sb = new StringBuilder();
sb.append(Character.toChars(ch));
while (ASCII.isLower(ch=read()) || ASCII.isUpper(ch) ||
ASCII.isDigit(ch)) {
sb.append(Character.toChars(ch));
}
if (sb.length() == 0)
throw error("named capturing group has 0 length name");
if (ch != '>')
throw error("named capturing group is missing trailing '>'");
return sb.toString();
}
/**
* Parses a group and returns the head node of a set of nodes that process
* the group. Sometimes a double return system is used where the tail is
* returned in root.
*/
private Node group0() {
boolean capturingGroup = false;
Node head = null;
Node tail = null;
int save = flags;
root = null;
int ch = next();
if (ch == '?') {
ch = skip();
switch (ch) {
case ':': // (?:xxx) pure group
head = createGroup(true);
tail = root;
head.next = expr(tail);
break;
case '=': // (?=xxx) and (?!xxx) lookahead
case '!':
head = createGroup(true);
tail = root;
head.next = expr(tail);
if (ch == '=') {
head = tail = new Pos(head);
} else {
head = tail = new Neg(head);
}
break;
case '>': // (?>xxx) independent group
head = createGroup(true);
tail = root;
head.next = expr(tail);
head = tail = new Ques(head, INDEPENDENT);
break;
case '<': // (?<xxx) look behind
ch = read();
if (ASCII.isLower(ch) || ASCII.isUpper(ch)) {
// named captured group
String name = groupname(ch);
if (namedGroups().containsKey(name))
throw error("Named capturing group <" + name
+ "> is already defined");
capturingGroup = true;
head = createGroup(false);
tail = root;
namedGroups().put(name, capturingGroupCount-1);
head.next = expr(tail);
break;
}
int start = cursor;
head = createGroup(true);
tail = root;
head.next = expr(tail);
tail.next = lookbehindEnd;
TreeInfo info = new TreeInfo();
head.study(info);
if (info.maxValid == false) {
throw error("Look-behind group does not have "
+ "an obvious maximum length");
}
boolean hasSupplementary = findSupplementary(start, patternLength);
if (ch == '=') {
head = tail = (hasSupplementary ?
new BehindS(head, info.maxLength,
info.minLength) :
new Behind(head, info.maxLength,
info.minLength));
} else if (ch == '!') {
head = tail = (hasSupplementary ?
new NotBehindS(head, info.maxLength,
info.minLength) :
new NotBehind(head, info.maxLength,
info.minLength));
} else {
throw error("Unknown look-behind group");
}
break;
case '$':
case '@':
throw error("Unknown group type");
default: // (?xxx:) inlined match flags
unread();
addFlag();
ch = read();
if (ch == ')') {
return null; // Inline modifier only
}
if (ch != ':') {
throw error("Unknown inline modifier");
}
head = createGroup(true);
tail = root;
head.next = expr(tail);
break;
}
} else { // (xxx) a regular group
capturingGroup = true;
head = createGroup(false);
tail = root;
head.next = expr(tail);
}
accept(')', "Unclosed group");
flags = save;
// Check for quantifiers
Node node = closure(head);
if (node == head) { // No closure
root = tail;
return node; // Dual return
}
if (head == tail) { // Zero length assertion
root = node;
return node; // Dual return
}
if (node instanceof Ques) {
Ques ques = (Ques) node;
if (ques.type == POSSESSIVE) {
root = node;
return node;
}
tail.next = new BranchConn();
tail = tail.next;
if (ques.type == GREEDY) {
head = new Branch(head, null, tail);
} else { // Reluctant quantifier
head = new Branch(null, head, tail);
}
root = tail;
return head;
} else if (node instanceof Curly) {
Curly curly = (Curly) node;
if (curly.type == POSSESSIVE) {
root = node;
return node;
}
// Discover if the group is deterministic
TreeInfo info = new TreeInfo();
if (head.study(info)) { // Deterministic
GroupTail temp = (GroupTail) tail;
head = root = new GroupCurly(head.next, curly.cmin,
curly.cmax, curly.type,
((GroupTail)tail).localIndex,
((GroupTail)tail).groupIndex,
capturingGroup);
return head;
} else { // Non-deterministic
int temp = ((GroupHead) head).localIndex;
Loop loop;
if (curly.type == GREEDY)
loop = new Loop(this.localCount, temp);
else // Reluctant Curly
loop = new LazyLoop(this.localCount, temp);
Prolog prolog = new Prolog(loop);
this.localCount += 1;
loop.cmin = curly.cmin;
loop.cmax = curly.cmax;
loop.body = head;
tail.next = loop;
root = loop;
return prolog; // Dual return
}
}
throw error("Internal logic error");
}
/**
* Create group head and tail nodes using double return. If the group is
* created with anonymous true then it is a pure group and should not
* affect group counting.
*/
private Node createGroup(boolean anonymous) {
int localIndex = localCount++;
int groupIndex = 0;
if (!anonymous)
groupIndex = capturingGroupCount++;
GroupHead head = new GroupHead(localIndex);
root = new GroupTail(localIndex, groupIndex);
if (!anonymous && groupIndex < 10)
groupNodes[groupIndex] = head;
return head;
}
/**
* Parses inlined match flags and set them appropriately.
*/
private void addFlag() {
int ch = peek();
for (;;) {
switch (ch) {
case 'i':
flags |= CASE_INSENSITIVE;
break;
case 'm':
flags |= MULTILINE;
break;
case 's':
flags |= DOTALL;
break;
case 'd':
flags |= UNIX_LINES;
break;
case 'u':
flags |= UNICODE_CASE;
break;
case 'c':
flags |= CANON_EQ;
break;
case 'x':
flags |= COMMENTS;
break;
case 'U':
flags |= (UNICODE_CHARACTER_CLASS | UNICODE_CASE);
break;
case '-': // subFlag then fall through
ch = next();
subFlag();
default:
return;
}
ch = next();
}
}
/**
* Parses the second part of inlined match flags and turns off
* flags appropriately.
*/
private void subFlag() {
int ch = peek();
for (;;) {
switch (ch) {
case 'i':
flags &= ~CASE_INSENSITIVE;
break;
case 'm':
flags &= ~MULTILINE;
break;
case 's':
flags &= ~DOTALL;
break;
case 'd':
flags &= ~UNIX_LINES;
break;
case 'u':
flags &= ~UNICODE_CASE;
break;
case 'c':
flags &= ~CANON_EQ;
break;
case 'x':
flags &= ~COMMENTS;
break;
case 'U':
flags &= ~(UNICODE_CHARACTER_CLASS | UNICODE_CASE);
default:
return;
}
ch = next();
}
}
static final int MAX_REPS = 0x7FFFFFFF;
static final int GREEDY = 0;
static final int LAZY = 1;
static final int POSSESSIVE = 2;
static final int INDEPENDENT = 3;
/**
* Processes repetition. If the next character peeked is a quantifier
* then new nodes must be appended to handle the repetition.
* Prev could be a single or a group, so it could be a chain of nodes.
*/
private Node closure(Node prev) {
Node atom;
int ch = peek();
switch (ch) {
case '?':
ch = next();
if (ch == '?') {
next();
return new Ques(prev, LAZY);
} else if (ch == '+') {
next();
return new Ques(prev, POSSESSIVE);
}
return new Ques(prev, GREEDY);
case '*':
ch = next();
if (ch == '?') {
next();
return new Curly(prev, 0, MAX_REPS, LAZY);
} else if (ch == '+') {
next();
return new Curly(prev, 0, MAX_REPS, POSSESSIVE);
}
return new Curly(prev, 0, MAX_REPS, GREEDY);
case '+':
ch = next();
if (ch == '?') {
next();
return new Curly(prev, 1, MAX_REPS, LAZY);
} else if (ch == '+') {
next();
return new Curly(prev, 1, MAX_REPS, POSSESSIVE);
}
return new Curly(prev, 1, MAX_REPS, GREEDY);
case '{':
ch = temp[cursor+1];
if (ASCII.isDigit(ch)) {
skip();
int cmin = 0;
do {
cmin = cmin * 10 + (ch - '0');
} while (ASCII.isDigit(ch = read()));
int cmax = cmin;
if (ch == ',') {
ch = read();
cmax = MAX_REPS;
if (ch != '}') {
cmax = 0;
while (ASCII.isDigit(ch)) {
cmax = cmax * 10 + (ch - '0');
ch = read();
}
}
}
if (ch != '}')
throw error("Unclosed counted closure");
if (((cmin) | (cmax) | (cmax - cmin)) < 0)
throw error("Illegal repetition range");
Curly curly;
ch = peek();
if (ch == '?') {
next();
curly = new Curly(prev, cmin, cmax, LAZY);
} else if (ch == '+') {
next();
curly = new Curly(prev, cmin, cmax, POSSESSIVE);
} else {
curly = new Curly(prev, cmin, cmax, GREEDY);
}
return curly;
} else {
throw error("Illegal repetition");
}
default:
return prev;
}
}
/**
* Utility method for parsing control escape sequences.
*/
private int c() {
if (cursor < patternLength) {
return read() ^ 64;
}
throw error("Illegal control escape sequence");
}
/**
* Utility method for parsing octal escape sequences.
*/
private int o() {
int n = read();
if (((n-'0')|('7'-n)) >= 0) {
int m = read();
if (((m-'0')|('7'-m)) >= 0) {
int o = read();
if ((((o-'0')|('7'-o)) >= 0) && (((n-'0')|('3'-n)) >= 0)) {
return (n - '0') * 64 + (m - '0') * 8 + (o - '0');
}
unread();
return (n - '0') * 8 + (m - '0');
}
unread();
return (n - '0');
}
throw error("Illegal octal escape sequence");
}
/**
* Utility method for parsing hexadecimal escape sequences.
*/
private int x() {
int n = read();
if (ASCII.isHexDigit(n)) {
int m = read();
if (ASCII.isHexDigit(m)) {
return ASCII.toDigit(n) * 16 + ASCII.toDigit(m);
}
} else if (n == '{' && ASCII.isHexDigit(peek())) {
int ch = 0;
while (ASCII.isHexDigit(n = read())) {
ch = (ch << 4) + ASCII.toDigit(n);
if (ch > Character.MAX_CODE_POINT)
throw error("Hexadecimal codepoint is too big");
}
if (n != '}')
throw error("Unclosed hexadecimal escape sequence");
return ch;
}
throw error("Illegal hexadecimal escape sequence");
}
/**
* Utility method for parsing unicode escape sequences.
*/
private int cursor() {
return cursor;
}
private void setcursor(int pos) {
cursor = pos;
}
private int uxxxx() {
int n = 0;
for (int i = 0; i < 4; i++) {
int ch = read();
if (!ASCII.isHexDigit(ch)) {
throw error("Illegal Unicode escape sequence");
}
n = n * 16 + ASCII.toDigit(ch);
}
return n;
}
private int u() {
int n = uxxxx();
if (Character.isHighSurrogate((char)n)) {
int cur = cursor();
if (read() == '\\' && read() == 'u') {
int n2 = uxxxx();
if (Character.isLowSurrogate((char)n2))
return Character.toCodePoint((char)n, (char)n2);
}
setcursor(cur);
}
return n;
}
//
// Utility methods for code point support
//
private static final int countChars(CharSequence seq, int index,
int lengthInCodePoints) {
// optimization
if (lengthInCodePoints == 1 && !Character.isHighSurrogate(seq.charAt(index))) {
assert (index >= 0 && index < seq.length());
return 1;
}
int length = seq.length();
int x = index;
if (lengthInCodePoints >= 0) {
assert (index >= 0 && index < length);
for (int i = 0; x < length && i < lengthInCodePoints; i++) {
if (Character.isHighSurrogate(seq.charAt(x++))) {
if (x < length && Character.isLowSurrogate(seq.charAt(x))) {
x++;
}
}
}
return x - index;
}
assert (index >= 0 && index <= length);
if (index == 0) {
return 0;
}
int len = -lengthInCodePoints;
for (int i = 0; x > 0 && i < len; i++) {
if (Character.isLowSurrogate(seq.charAt(--x))) {
if (x > 0 && Character.isHighSurrogate(seq.charAt(x-1))) {
x--;
}
}
}
return index - x;
}
private static final int countCodePoints(CharSequence seq) {
int length = seq.length();
int n = 0;
for (int i = 0; i < length; ) {
n++;
if (Character.isHighSurrogate(seq.charAt(i++))) {
if (i < length && Character.isLowSurrogate(seq.charAt(i))) {
i++;
}
}
}
return n;
}
/**
* Creates a bit vector for matching Latin-1 values. A normal BitClass
* never matches values above Latin-1, and a complemented BitClass always
* matches values above Latin-1.
*/
private static final class BitClass extends BmpCharProperty {
final boolean[] bits;
BitClass() { bits = new boolean[256]; }
private BitClass(boolean[] bits) { this.bits = bits; }
BitClass add(int c, int flags) {
assert c >= 0 && c <= 255;
if ((flags & CASE_INSENSITIVE) != 0) {
if (ASCII.isAscii(c)) {
bits[ASCII.toUpper(c)] = true;
bits[ASCII.toLower(c)] = true;
} else if ((flags & UNICODE_CASE) != 0) {
bits[Character.toLowerCase(c)] = true;
bits[Character.toUpperCase(c)] = true;
}
}
bits[c] = true;
return this;
}
boolean isSatisfiedBy(int ch) {
return ch < 256 && bits[ch];
}
}
/**
* Returns a suitably optimized, single character matcher.
*/
private CharProperty newSingle(final int ch) {
if (has(CASE_INSENSITIVE)) {
int lower, upper;
if (has(UNICODE_CASE)) {
upper = Character.toUpperCase(ch);
lower = Character.toLowerCase(upper);
if (upper != lower)
return new SingleU(lower);
} else if (ASCII.isAscii(ch)) {
lower = ASCII.toLower(ch);
upper = ASCII.toUpper(ch);
if (lower != upper)
return new SingleI(lower, upper);
}
}
if (isSupplementary(ch))
return new SingleS(ch); // Match a given Unicode character
return new Single(ch); // Match a given BMP character
}
/**
* Utility method for creating a string slice matcher.
*/
private Node newSlice(int[] buf, int count, boolean hasSupplementary) {
int[] tmp = new int[count];
if (has(CASE_INSENSITIVE)) {
if (has(UNICODE_CASE)) {
for (int i = 0; i < count; i++) {
tmp[i] = Character.toLowerCase(
Character.toUpperCase(buf[i]));
}
return hasSupplementary? new SliceUS(tmp) : new SliceU(tmp);
}
for (int i = 0; i < count; i++) {
tmp[i] = ASCII.toLower(buf[i]);
}
return hasSupplementary? new SliceIS(tmp) : new SliceI(tmp);
}
for (int i = 0; i < count; i++) {
tmp[i] = buf[i];
}
return hasSupplementary ? new SliceS(tmp) : new Slice(tmp);
}
/**
* The following classes are the building components of the object
* tree that represents a compiled regular expression. The object tree
* is made of individual elements that handle constructs in the Pattern.
* Each type of object knows how to match its equivalent construct with
* the match() method.
*/
/**
* Base class for all node classes. Subclasses should override the match()
* method as appropriate. This class is an accepting node, so its match()
* always returns true.
*/
static class Node extends Object {
Node next;
Node() {
next = Pattern.accept;
}
/**
* This method implements the classic accept node.
*/
boolean match(Matcher matcher, int i, CharSequence seq) {
matcher.last = i;
matcher.groups[0] = matcher.first;
matcher.groups[1] = matcher.last;
return true;
}
/**
* This method is good for all zero length assertions.
*/
boolean study(TreeInfo info) {
if (next != null) {
return next.study(info);
} else {
return info.deterministic;
}
}
}
static class LastNode extends Node {
/**
* This method implements the classic accept node with
* the addition of a check to see if the match occurred
* using all of the input.
*/
boolean match(Matcher matcher, int i, CharSequence seq) {
if (matcher.acceptMode == Matcher.ENDANCHOR && i != matcher.to)
return false;
matcher.last = i;
matcher.groups[0] = matcher.first;
matcher.groups[1] = matcher.last;
return true;
}
}
/**
* Used for REs that can start anywhere within the input string.
* This basically tries to match repeatedly at each spot in the
* input string, moving forward after each try. An anchored search
* or a BnM will bypass this node completely.
*/
static class Start extends Node {
int minLength;
Start(Node node) {
this.next = node;
TreeInfo info = new TreeInfo();
next.study(info);
minLength = info.minLength;
}
boolean match(Matcher matcher, int i, CharSequence seq) {
if (i > matcher.to - minLength) {
matcher.hitEnd = true;
return false;
}
int guard = matcher.to - minLength;
for (; i <= guard; i++) {
if (next.match(matcher, i, seq)) {
matcher.first = i;
matcher.groups[0] = matcher.first;
matcher.groups[1] = matcher.last;
return true;
}
}
matcher.hitEnd = true;
return false;
}
boolean study(TreeInfo info) {
next.study(info);
info.maxValid = false;
info.deterministic = false;
return false;
}
}
/*
* StartS supports supplementary characters, including unpaired surrogates.
*/
static final class StartS extends Start {
StartS(Node node) {
super(node);
}
boolean match(Matcher matcher, int i, CharSequence seq) {
if (i > matcher.to - minLength) {
matcher.hitEnd = true;
return false;
}
int guard = matcher.to - minLength;
while (i <= guard) {
//if ((ret = next.match(matcher, i, seq)) || i == guard)
if (next.match(matcher, i, seq)) {
matcher.first = i;
matcher.groups[0] = matcher.first;
matcher.groups[1] = matcher.last;
return true;
}
if (i == guard)
break;
// Optimization to move to the next character. This is
// faster than countChars(seq, i, 1).
if (Character.isHighSurrogate(seq.charAt(i++))) {
if (i < seq.length() &&
Character.isLowSurrogate(seq.charAt(i))) {
i++;
}
}
}
matcher.hitEnd = true;
return false;
}
}
/**
* Node to anchor at the beginning of input. This object implements the
* match for a \A sequence, and the caret anchor will use this if not in
* multiline mode.
*/
static final class Begin extends Node {
boolean match(Matcher matcher, int i, CharSequence seq) {
int fromIndex = (matcher.anchoringBounds) ?
matcher.from : 0;
if (i == fromIndex && next.match(matcher, i, seq)) {
matcher.first = i;
matcher.groups[0] = i;
matcher.groups[1] = matcher.last;
return true;
} else {
return false;
}
}
}
/**
* Node to anchor at the end of input. This is the absolute end, so this
* should not match at the last newline before the end as $ will.
*/
static final class End extends Node {
boolean match(Matcher matcher, int i, CharSequence seq) {
int endIndex = (matcher.anchoringBounds) ?
matcher.to : matcher.getTextLength();
if (i == endIndex) {
matcher.hitEnd = true;
return next.match(matcher, i, seq);
}
return false;
}
}
/**
* Node to anchor at the beginning of a line. This is essentially the
* object to match for the multiline ^.
*/
static final class Caret extends Node {
boolean match(Matcher matcher, int i, CharSequence seq) {
int startIndex = matcher.from;
int endIndex = matcher.to;
if (!matcher.anchoringBounds) {
startIndex = 0;
endIndex = matcher.getTextLength();
}
// Perl does not match ^ at end of input even after newline
if (i == endIndex) {
matcher.hitEnd = true;
return false;
}
if (i > startIndex) {
char ch = seq.charAt(i-1);
if (ch != '\n' && ch != '\r'
&& (ch|1) != '\u2029'
&& ch != '\u0085' ) {
return false;
}
// Should treat /r/n as one newline
if (ch == '\r' && seq.charAt(i) == '\n')
return false;
}
return next.match(matcher, i, seq);
}
}
/**
* Node to anchor at the beginning of a line when in unixdot mode.
*/
static final class UnixCaret extends Node {
boolean match(Matcher matcher, int i, CharSequence seq) {
int startIndex = matcher.from;
int endIndex = matcher.to;
if (!matcher.anchoringBounds) {
startIndex = 0;
endIndex = matcher.getTextLength();
}
// Perl does not match ^ at end of input even after newline
if (i == endIndex) {
matcher.hitEnd = true;
return false;
}
if (i > startIndex) {
char ch = seq.charAt(i-1);
if (ch != '\n') {
return false;
}
}
return next.match(matcher, i, seq);
}
}
/**
* Node to match the location where the last match ended.
* This is used for the \G construct.
*/
static final class LastMatch extends Node {
boolean match(Matcher matcher, int i, CharSequence seq) {
if (i != matcher.oldLast)
return false;
return next.match(matcher, i, seq);
}
}
/**
* Node to anchor at the end of a line or the end of input based on the
* multiline mode.
*
* When not in multiline mode, the $ can only match at the very end
* of the input, unless the input ends in a line terminator in which
* it matches right before the last line terminator.
*
* Note that \r\n is considered an atomic line terminator.
*
* Like ^ the $ operator matches at a position, it does not match the
* line terminators themselves.
*/
static final class Dollar extends Node {
boolean multiline;
Dollar(boolean mul) {
multiline = mul;
}
boolean match(Matcher matcher, int i, CharSequence seq) {
int endIndex = (matcher.anchoringBounds) ?
matcher.to : matcher.getTextLength();
if (!multiline) {
if (i < endIndex - 2)
return false;
if (i == endIndex - 2) {
char ch = seq.charAt(i);
if (ch != '\r')
return false;
ch = seq.charAt(i + 1);
if (ch != '\n')
return false;
}
}
// Matches before any line terminator; also matches at the
// end of input
// Before line terminator:
// If multiline, we match here no matter what
// If not multiline, fall through so that the end
// is marked as hit; this must be a /r/n or a /n
// at the very end so the end was hit; more input
// could make this not match here
if (i < endIndex) {
char ch = seq.charAt(i);
if (ch == '\n') {
// No match between \r\n
if (i > 0 && seq.charAt(i-1) == '\r')
return false;
if (multiline)
return next.match(matcher, i, seq);
} else if (ch == '\r' || ch == '\u0085' ||
(ch|1) == '\u2029') {
if (multiline)
return next.match(matcher, i, seq);
} else { // No line terminator, no match
return false;
}
}
// Matched at current end so hit end
matcher.hitEnd = true;
// If a $ matches because of end of input, then more input
// could cause it to fail!
matcher.requireEnd = true;
return next.match(matcher, i, seq);
}
boolean study(TreeInfo info) {
next.study(info);
return info.deterministic;
}
}
/**
* Node to anchor at the end of a line or the end of input based on the
* multiline mode when in unix lines mode.
*/
static final class UnixDollar extends Node {
boolean multiline;
UnixDollar(boolean mul) {
multiline = mul;
}
boolean match(Matcher matcher, int i, CharSequence seq) {
int endIndex = (matcher.anchoringBounds) ?
matcher.to : matcher.getTextLength();
if (i < endIndex) {
char ch = seq.charAt(i);
if (ch == '\n') {
// If not multiline, then only possible to
// match at very end or one before end
if (multiline == false && i != endIndex - 1)
return false;
// If multiline return next.match without setting
// matcher.hitEnd
if (multiline)
return next.match(matcher, i, seq);
} else {
return false;
}
}
// Matching because at the end or 1 before the end;
// more input could change this so set hitEnd
matcher.hitEnd = true;
// If a $ matches because of end of input, then more input
// could cause it to fail!
matcher.requireEnd = true;
return next.match(matcher, i, seq);
}
boolean study(TreeInfo info) {
next.study(info);
return info.deterministic;
}
}
/**
* Abstract node class to match one character satisfying some
* boolean property.
*/
private static abstract class CharProperty extends Node {
abstract boolean isSatisfiedBy(int ch);
CharProperty complement() {
return new CharProperty() {
boolean isSatisfiedBy(int ch) {
return ! CharProperty.this.isSatisfiedBy(ch);}};
}
boolean match(Matcher matcher, int i, CharSequence seq) {
if (i < matcher.to) {
int ch = Character.codePointAt(seq, i);
return isSatisfiedBy(ch)
&& next.match(matcher, i+Character.charCount(ch), seq);
} else {
matcher.hitEnd = true;
return false;
}
}
boolean study(TreeInfo info) {
info.minLength++;
info.maxLength++;
return next.study(info);
}
}
/**
* Optimized version of CharProperty that works only for
* properties never satisfied by Supplementary characters.
*/
private static abstract class BmpCharProperty extends CharProperty {
boolean match(Matcher matcher, int i, CharSequence seq) {
if (i < matcher.to) {
return isSatisfiedBy(seq.charAt(i))
&& next.match(matcher, i+1, seq);
} else {
matcher.hitEnd = true;
return false;
}
}
}
/**
* Node class that matches a Supplementary Unicode character
*/
static final class SingleS extends CharProperty {
final int c;
SingleS(int c) { this.c = c; }
boolean isSatisfiedBy(int ch) {
return ch == c;
}
}
/**
* Optimization -- matches a given BMP character
*/
static final class Single extends BmpCharProperty {
final int c;
Single(int c) { this.c = c; }
boolean isSatisfiedBy(int ch) {
return ch == c;
}
}
/**
* Case insensitive matches a given BMP character
*/
static final class SingleI extends BmpCharProperty {
final int lower;
final int upper;
SingleI(int lower, int upper) {
this.lower = lower;
this.upper = upper;
}
boolean isSatisfiedBy(int ch) {
return ch == lower || ch == upper;
}
}
/**
* Unicode case insensitive matches a given Unicode character
*/
static final class SingleU extends CharProperty {
final int lower;
SingleU(int lower) {
this.lower = lower;
}
boolean isSatisfiedBy(int ch) {
return lower == ch ||
lower == Character.toLowerCase(Character.toUpperCase(ch));
}
}
/**
* Node class that matches a Unicode block.
*/
static final class Block extends CharProperty {
final Character.UnicodeBlock block;
Block(Character.UnicodeBlock block) {
this.block = block;
}
boolean isSatisfiedBy(int ch) {
return block == Character.UnicodeBlock.of(ch);
}
}
/**
* Node class that matches a Unicode script
*/
static final class Script extends CharProperty {
final Character.UnicodeScript script;
Script(Character.UnicodeScript script) {
this.script = script;
}
boolean isSatisfiedBy(int ch) {
return script == Character.UnicodeScript.of(ch);
}
}
/**
* Node class that matches a Unicode category.
*/
static final class Category extends CharProperty {
final int typeMask;
Category(int typeMask) { this.typeMask = typeMask; }
boolean isSatisfiedBy(int ch) {
return (typeMask & (1 << Character.getType(ch))) != 0;
}
}
/**
* Node class that matches a Unicode "type"
*/
static final class Utype extends CharProperty {
final UnicodeProp uprop;
Utype(UnicodeProp uprop) { this.uprop = uprop; }
boolean isSatisfiedBy(int ch) {
return uprop.is(ch);
}
}
/**
* Node class that matches a POSIX type.
*/
static final class Ctype extends BmpCharProperty {
final int ctype;
Ctype(int ctype) { this.ctype = ctype; }
boolean isSatisfiedBy(int ch) {
return ch < 128 && ASCII.isType(ch, ctype);
}
}
/**
* Base class for all Slice nodes
*/
static class SliceNode extends Node {
int[] buffer;
SliceNode(int[] buf) {
buffer = buf;
}
boolean study(TreeInfo info) {
info.minLength += buffer.length;
info.maxLength += buffer.length;
return next.study(info);
}
}
/**
* Node class for a case sensitive/BMP-only sequence of literal
* characters.
*/
static final class Slice extends SliceNode {
Slice(int[] buf) {
super(buf);
}
boolean match(Matcher matcher, int i, CharSequence seq) {
int[] buf = buffer;
int len = buf.length;
for (int j=0; j<len; j++) {
if ((i+j) >= matcher.to) {
matcher.hitEnd = true;
return false;
}
if (buf[j] != seq.charAt(i+j))
return false;
}
return next.match(matcher, i+len, seq);
}
}
/**
* Node class for a case_insensitive/BMP-only sequence of literal
* characters.
*/
static class SliceI extends SliceNode {
SliceI(int[] buf) {
super(buf);
}
boolean match(Matcher matcher, int i, CharSequence seq) {
int[] buf = buffer;
int len = buf.length;
for (int j=0; j<len; j++) {
if ((i+j) >= matcher.to) {
matcher.hitEnd = true;
return false;
}
int c = seq.charAt(i+j);
if (buf[j] != c &&
buf[j] != ASCII.toLower(c))
return false;
}
return next.match(matcher, i+len, seq);
}
}
/**
* Node class for a unicode_case_insensitive/BMP-only sequence of
* literal characters. Uses unicode case folding.
*/
static final class SliceU extends SliceNode {
SliceU(int[] buf) {
super(buf);
}
boolean match(Matcher matcher, int i, CharSequence seq) {
int[] buf = buffer;
int len = buf.length;
for (int j=0; j<len; j++) {
if ((i+j) >= matcher.to) {
matcher.hitEnd = true;
return false;
}
int c = seq.charAt(i+j);
if (buf[j] != c &&
buf[j] != Character.toLowerCase(Character.toUpperCase(c)))
return false;
}
return next.match(matcher, i+len, seq);
}
}
/**
* Node class for a case sensitive sequence of literal characters
* including supplementary characters.
*/
static final class SliceS extends SliceNode {
SliceS(int[] buf) {
super(buf);
}
boolean match(Matcher matcher, int i, CharSequence seq) {
int[] buf = buffer;
int x = i;
for (int j = 0; j < buf.length; j++) {
if (x >= matcher.to) {
matcher.hitEnd = true;
return false;
}
int c = Character.codePointAt(seq, x);
if (buf[j] != c)
return false;
x += Character.charCount(c);
if (x > matcher.to) {
matcher.hitEnd = true;
return false;
}
}
return next.match(matcher, x, seq);
}
}
/**
* Node class for a case insensitive sequence of literal characters
* including supplementary characters.
*/
static class SliceIS extends SliceNode {
SliceIS(int[] buf) {
super(buf);
}
int toLower(int c) {
return ASCII.toLower(c);
}
boolean match(Matcher matcher, int i, CharSequence seq) {
int[] buf = buffer;
int x = i;
for (int j = 0; j < buf.length; j++) {
if (x >= matcher.to) {
matcher.hitEnd = true;
return false;
}
int c = Character.codePointAt(seq, x);
if (buf[j] != c && buf[j] != toLower(c))
return false;
x += Character.charCount(c);
if (x > matcher.to) {
matcher.hitEnd = true;
return false;
}
}
return next.match(matcher, x, seq);
}
}
/**
* Node class for a case insensitive sequence of literal characters.
* Uses unicode case folding.
*/
static final class SliceUS extends SliceIS {
SliceUS(int[] buf) {
super(buf);
}
int toLower(int c) {
return Character.toLowerCase(Character.toUpperCase(c));
}
}
private static boolean inRange(int lower, int ch, int upper) {
return lower <= ch && ch <= upper;
}
/**
* Returns node for matching characters within an explicit value range.
*/
private static CharProperty rangeFor(final int lower,
final int upper) {
return new CharProperty() {
boolean isSatisfiedBy(int ch) {
return inRange(lower, ch, upper);}};
}
/**
* Returns node for matching characters within an explicit value
* range in a case insensitive manner.
*/
private CharProperty caseInsensitiveRangeFor(final int lower,
final int upper) {
if (has(UNICODE_CASE))
return new CharProperty() {
boolean isSatisfiedBy(int ch) {
if (inRange(lower, ch, upper))
return true;
int up = Character.toUpperCase(ch);
return inRange(lower, up, upper) ||
inRange(lower, Character.toLowerCase(up), upper);}};
return new CharProperty() {
boolean isSatisfiedBy(int ch) {
return inRange(lower, ch, upper) ||
ASCII.isAscii(ch) &&
(inRange(lower, ASCII.toUpper(ch), upper) ||
inRange(lower, ASCII.toLower(ch), upper));
}};
}
/**
* Implements the Unicode category ALL and the dot metacharacter when
* in dotall mode.
*/
static final class All extends CharProperty {
boolean isSatisfiedBy(int ch) {
return true;
}
}
/**
* Node class for the dot metacharacter when dotall is not enabled.
*/
static final class Dot extends CharProperty {
boolean isSatisfiedBy(int ch) {
return (ch != '\n' && ch != '\r'
&& (ch|1) != '\u2029'
&& ch != '\u0085');
}
}
/**
* Node class for the dot metacharacter when dotall is not enabled
* but UNIX_LINES is enabled.
*/
static final class UnixDot extends CharProperty {
boolean isSatisfiedBy(int ch) {
return ch != '\n';
}
}
/**
* The 0 or 1 quantifier. This one class implements all three types.
*/
static final class Ques extends Node {
Node atom;
int type;
Ques(Node node, int type) {
this.atom = node;
this.type = type;
}
boolean match(Matcher matcher, int i, CharSequence seq) {
switch (type) {
case GREEDY:
return (atom.match(matcher, i, seq) && next.match(matcher, matcher.last, seq))
|| next.match(matcher, i, seq);
case LAZY:
return next.match(matcher, i, seq)
|| (atom.match(matcher, i, seq) && next.match(matcher, matcher.last, seq));
case POSSESSIVE:
if (atom.match(matcher, i, seq)) i = matcher.last;
return next.match(matcher, i, seq);
default:
return atom.match(matcher, i, seq) && next.match(matcher, matcher.last, seq);
}
}
boolean study(TreeInfo info) {
if (type != INDEPENDENT) {
int minL = info.minLength;
atom.study(info);
info.minLength = minL;
info.deterministic = false;
return next.study(info);
} else {
atom.study(info);
return next.study(info);
}
}
}
/**
* Handles the curly-brace style repetition with a specified minimum and
* maximum occurrences. The * quantifier is handled as a special case.
* This class handles the three types.
*/
static final class Curly extends Node {
Node atom;
int type;
int cmin;
int cmax;
Curly(Node node, int cmin, int cmax, int type) {
this.atom = node;
this.type = type;
this.cmin = cmin;
this.cmax = cmax;
}
boolean match(Matcher matcher, int i, CharSequence seq) {
int j;
for (j = 0; j < cmin; j++) {
if (atom.match(matcher, i, seq)) {
i = matcher.last;
continue;
}
return false;
}
if (type == GREEDY)
return match0(matcher, i, j, seq);
else if (type == LAZY)
return match1(matcher, i, j, seq);
else
return match2(matcher, i, j, seq);
}
// Greedy match.
// i is the index to start matching at
// j is the number of atoms that have matched
boolean match0(Matcher matcher, int i, int j, CharSequence seq) {
if (j >= cmax) {
// We have matched the maximum... continue with the rest of
// the regular expression
return next.match(matcher, i, seq);
}
int backLimit = j;
while (atom.match(matcher, i, seq)) {
// k is the length of this match
int k = matcher.last - i;
if (k == 0) // Zero length match
break;
// Move up index and number matched
i = matcher.last;
j++;
// We are greedy so match as many as we can
while (j < cmax) {
if (!atom.match(matcher, i, seq))
break;
if (i + k != matcher.last) {
if (match0(matcher, matcher.last, j+1, seq))
return true;
break;
}
i += k;
j++;
}
// Handle backing off if match fails
while (j >= backLimit) {
if (next.match(matcher, i, seq))
return true;
i -= k;
j--;
}
return false;
}
return next.match(matcher, i, seq);
}
// Reluctant match. At this point, the minimum has been satisfied.
// i is the index to start matching at
// j is the number of atoms that have matched
boolean match1(Matcher matcher, int i, int j, CharSequence seq) {
for (;;) {
// Try finishing match without consuming any more
if (next.match(matcher, i, seq))
return true;
// At the maximum, no match found
if (j >= cmax)
return false;
// Okay, must try one more atom
if (!atom.match(matcher, i, seq))
return false;
// If we haven't moved forward then must break out
if (i == matcher.last)
return false;
// Move up index and number matched
i = matcher.last;
j++;
}
}
boolean match2(Matcher matcher, int i, int j, CharSequence seq) {
for (; j < cmax; j++) {
if (!atom.match(matcher, i, seq))
break;
if (i == matcher.last)
break;
i = matcher.last;
}
return next.match(matcher, i, seq);
}
boolean study(TreeInfo info) {
// Save original info
int minL = info.minLength;
int maxL = info.maxLength;
boolean maxV = info.maxValid;
boolean detm = info.deterministic;
info.reset();
atom.study(info);
int temp = info.minLength * cmin + minL;
if (temp < minL) {
temp = 0xFFFFFFF; // arbitrary large number
}
info.minLength = temp;
if (maxV & info.maxValid) {
temp = info.maxLength * cmax + maxL;
info.maxLength = temp;
if (temp < maxL) {
info.maxValid = false;
}
} else {
info.maxValid = false;
}
if (info.deterministic && cmin == cmax)
info.deterministic = detm;
else
info.deterministic = false;
return next.study(info);
}
}
/**
* Handles the curly-brace style repetition with a specified minimum and
* maximum occurrences in deterministic cases. This is an iterative
* optimization over the Prolog and Loop system which would handle this
* in a recursive way. The * quantifier is handled as a special case.
* If capture is true then this class saves group settings and ensures
* that groups are unset when backing off of a group match.
*/
static final class GroupCurly extends Node {
Node atom;
int type;
int cmin;
int cmax;
int localIndex;
int groupIndex;
boolean capture;
GroupCurly(Node node, int cmin, int cmax, int type, int local,
int group, boolean capture) {
this.atom = node;
this.type = type;
this.cmin = cmin;
this.cmax = cmax;
this.localIndex = local;
this.groupIndex = group;
this.capture = capture;
}
boolean match(Matcher matcher, int i, CharSequence seq) {
int[] groups = matcher.groups;
int[] locals = matcher.locals;
int save0 = locals[localIndex];
int save1 = 0;
int save2 = 0;
if (capture) {
save1 = groups[groupIndex];
save2 = groups[groupIndex+1];
}
// Notify GroupTail there is no need to setup group info
// because it will be set here
locals[localIndex] = -1;
boolean ret = true;
for (int j = 0; j < cmin; j++) {
if (atom.match(matcher, i, seq)) {
if (capture) {
groups[groupIndex] = i;
groups[groupIndex+1] = matcher.last;
}
i = matcher.last;
} else {
ret = false;
break;
}
}
if (ret) {
if (type == GREEDY) {
ret = match0(matcher, i, cmin, seq);
} else if (type == LAZY) {
ret = match1(matcher, i, cmin, seq);
} else {
ret = match2(matcher, i, cmin, seq);
}
}
if (!ret) {
locals[localIndex] = save0;
if (capture) {
groups[groupIndex] = save1;
groups[groupIndex+1] = save2;
}
}
return ret;
}
// Aggressive group match
boolean match0(Matcher matcher, int i, int j, CharSequence seq) {
int[] groups = matcher.groups;
int save0 = 0;
int save1 = 0;
if (capture) {
save0 = groups[groupIndex];
save1 = groups[groupIndex+1];
}
for (;;) {
if (j >= cmax)
break;
if (!atom.match(matcher, i, seq))
break;
int k = matcher.last - i;
if (k <= 0) {
if (capture) {
groups[groupIndex] = i;
groups[groupIndex+1] = i + k;
}
i = i + k;
break;
}
for (;;) {
if (capture) {
groups[groupIndex] = i;
groups[groupIndex+1] = i + k;
}
i = i + k;
if (++j >= cmax)
break;
if (!atom.match(matcher, i, seq))
break;
if (i + k != matcher.last) {
if (match0(matcher, i, j, seq))
return true;
break;
}
}
while (j > cmin) {
if (next.match(matcher, i, seq)) {
if (capture) {
groups[groupIndex+1] = i;
groups[groupIndex] = i - k;
}
i = i - k;
return true;
}
// backing off
if (capture) {
groups[groupIndex+1] = i;
groups[groupIndex] = i - k;
}
i = i - k;
j--;
}
break;
}
if (capture) {
groups[groupIndex] = save0;
groups[groupIndex+1] = save1;
}
return next.match(matcher, i, seq);
}
// Reluctant matching
boolean match1(Matcher matcher, int i, int j, CharSequence seq) {
for (;;) {
if (next.match(matcher, i, seq))
return true;
if (j >= cmax)
return false;
if (!atom.match(matcher, i, seq))
return false;
if (i == matcher.last)
return false;
if (capture) {
matcher.groups[groupIndex] = i;
matcher.groups[groupIndex+1] = matcher.last;
}
i = matcher.last;
j++;
}
}
// Possessive matching
boolean match2(Matcher matcher, int i, int j, CharSequence seq) {
for (; j < cmax; j++) {
if (!atom.match(matcher, i, seq)) {
break;
}
if (capture) {
matcher.groups[groupIndex] = i;
matcher.groups[groupIndex+1] = matcher.last;
}
if (i == matcher.last) {
break;
}
i = matcher.last;
}
return next.match(matcher, i, seq);
}
boolean study(TreeInfo info) {
// Save original info
int minL = info.minLength;
int maxL = info.maxLength;
boolean maxV = info.maxValid;
boolean detm = info.deterministic;
info.reset();
atom.study(info);
int temp = info.minLength * cmin + minL;
if (temp < minL) {
temp = 0xFFFFFFF; // Arbitrary large number
}
info.minLength = temp;
if (maxV & info.maxValid) {
temp = info.maxLength * cmax + maxL;
info.maxLength = temp;
if (temp < maxL) {
info.maxValid = false;
}
} else {
info.maxValid = false;
}
if (info.deterministic && cmin == cmax) {
info.deterministic = detm;
} else {
info.deterministic = false;
}
return next.study(info);
}
}
/**
* A Guard node at the end of each atom node in a Branch. It
* serves the purpose of chaining the "match" operation to
* "next" but not the "study", so we can collect the TreeInfo
* of each atom node without including the TreeInfo of the
* "next".
*/
static final class BranchConn extends Node {
BranchConn() {};
boolean match(Matcher matcher, int i, CharSequence seq) {
return next.match(matcher, i, seq);
}
boolean study(TreeInfo info) {
return info.deterministic;
}
}
/**
* Handles the branching of alternations. Note this is also used for
* the ? quantifier to branch between the case where it matches once
* and where it does not occur.
*/
static final class Branch extends Node {
Node[] atoms = new Node[2];
int size = 2;
Node conn;
Branch(Node first, Node second, Node branchConn) {
conn = branchConn;
atoms[0] = first;
atoms[1] = second;
}
void add(Node node) {
if (size >= atoms.length) {
Node[] tmp = new Node[atoms.length*2];
System.arraycopy(atoms, 0, tmp, 0, atoms.length);
atoms = tmp;
}
atoms[size++] = node;
}
boolean match(Matcher matcher, int i, CharSequence seq) {
for (int n = 0; n < size; n++) {
if (atoms[n] == null) {
if (conn.next.match(matcher, i, seq))
return true;
} else if (atoms[n].match(matcher, i, seq)) {
return true;
}
}
return false;
}
boolean study(TreeInfo info) {
int minL = info.minLength;
int maxL = info.maxLength;
boolean maxV = info.maxValid;
int minL2 = Integer.MAX_VALUE; //arbitrary large enough num
int maxL2 = -1;
for (int n = 0; n < size; n++) {
info.reset();
if (atoms[n] != null)
atoms[n].study(info);
minL2 = Math.min(minL2, info.minLength);
maxL2 = Math.max(maxL2, info.maxLength);
maxV = (maxV & info.maxValid);
}
minL += minL2;
maxL += maxL2;
info.reset();
conn.next.study(info);
info.minLength += minL;
info.maxLength += maxL;
info.maxValid &= maxV;
info.deterministic = false;
return false;
}
}
/**
* The GroupHead saves the location where the group begins in the locals
* and restores them when the match is done.
*
* The matchRef is used when a reference to this group is accessed later
* in the expression. The locals will have a negative value in them to
* indicate that we do not want to unset the group if the reference
* doesn't match.
*/
static final class GroupHead extends Node {
int localIndex;
GroupHead(int localCount) {
localIndex = localCount;
}
boolean match(Matcher matcher, int i, CharSequence seq) {
int save = matcher.locals[localIndex];
matcher.locals[localIndex] = i;
boolean ret = next.match(matcher, i, seq);
matcher.locals[localIndex] = save;
return ret;
}
boolean matchRef(Matcher matcher, int i, CharSequence seq) {
int save = matcher.locals[localIndex];
matcher.locals[localIndex] = ~i; // HACK
boolean ret = next.match(matcher, i, seq);
matcher.locals[localIndex] = save;
return ret;
}
}
/**
* Recursive reference to a group in the regular expression. It calls
* matchRef because if the reference fails to match we would not unset
* the group.
*/
static final class GroupRef extends Node {
GroupHead head;
GroupRef(GroupHead head) {
this.head = head;
}
boolean match(Matcher matcher, int i, CharSequence seq) {
return head.matchRef(matcher, i, seq)
&& next.match(matcher, matcher.last, seq);
}
boolean study(TreeInfo info) {
info.maxValid = false;
info.deterministic = false;
return next.study(info);
}
}
/**
* The GroupTail handles the setting of group beginning and ending
* locations when groups are successfully matched. It must also be able to
* unset groups that have to be backed off of.
*
* The GroupTail node is also used when a previous group is referenced,
* and in that case no group information needs to be set.
*/
static final class GroupTail extends Node {
int localIndex;
int groupIndex;
GroupTail(int localCount, int groupCount) {
localIndex = localCount;
groupIndex = groupCount + groupCount;
}
boolean match(Matcher matcher, int i, CharSequence seq) {
int tmp = matcher.locals[localIndex];
if (tmp >= 0) { // This is the normal group case.
// Save the group so we can unset it if it
// backs off of a match.
int groupStart = matcher.groups[groupIndex];
int groupEnd = matcher.groups[groupIndex+1];
matcher.groups[groupIndex] = tmp;
matcher.groups[groupIndex+1] = i;
if (next.match(matcher, i, seq)) {
return true;
}
matcher.groups[groupIndex] = groupStart;
matcher.groups[groupIndex+1] = groupEnd;
return false;
} else {
// This is a group reference case. We don't need to save any
// group info because it isn't really a group.
matcher.last = i;
return true;
}
}
}
/**
* This sets up a loop to handle a recursive quantifier structure.
*/
static final class Prolog extends Node {
Loop loop;
Prolog(Loop loop) {
this.loop = loop;
}
boolean match(Matcher matcher, int i, CharSequence seq) {
return loop.matchInit(matcher, i, seq);
}
boolean study(TreeInfo info) {
return loop.study(info);
}
}
/**
* Handles the repetition count for a greedy Curly. The matchInit
* is called from the Prolog to save the index of where the group
* beginning is stored. A zero length group check occurs in the
* normal match but is skipped in the matchInit.
*/
static class Loop extends Node {
Node body;
int countIndex; // local count index in matcher locals
int beginIndex; // group beginning index
int cmin, cmax;
Loop(int countIndex, int beginIndex) {
this.countIndex = countIndex;
this.beginIndex = beginIndex;
}
boolean match(Matcher matcher, int i, CharSequence seq) {
// Avoid infinite loop in zero-length case.
if (i > matcher.locals[beginIndex]) {
int count = matcher.locals[countIndex];
// This block is for before we reach the minimum
// iterations required for the loop to match
if (count < cmin) {
matcher.locals[countIndex] = count + 1;
boolean b = body.match(matcher, i, seq);
// If match failed we must backtrack, so
// the loop count should NOT be incremented
if (!b)
matcher.locals[countIndex] = count;
// Return success or failure since we are under
// minimum
return b;
}
// This block is for after we have the minimum
// iterations required for the loop to match
if (count < cmax) {
matcher.locals[countIndex] = count + 1;
boolean b = body.match(matcher, i, seq);
// If match failed we must backtrack, so
// the loop count should NOT be incremented
if (!b)
matcher.locals[countIndex] = count;
else
return true;
}
}
return next.match(matcher, i, seq);
}
boolean matchInit(Matcher matcher, int i, CharSequence seq) {
int save = matcher.locals[countIndex];
boolean ret = false;
if (0 < cmin) {
matcher.locals[countIndex] = 1;
ret = body.match(matcher, i, seq);
} else if (0 < cmax) {
matcher.locals[countIndex] = 1;
ret = body.match(matcher, i, seq);
if (ret == false)
ret = next.match(matcher, i, seq);
} else {
ret = next.match(matcher, i, seq);
}
matcher.locals[countIndex] = save;
return ret;
}
boolean study(TreeInfo info) {
info.maxValid = false;
info.deterministic = false;
return false;
}
}
/**
* Handles the repetition count for a reluctant Curly. The matchInit
* is called from the Prolog to save the index of where the group
* beginning is stored. A zero length group check occurs in the
* normal match but is skipped in the matchInit.
*/
static final class LazyLoop extends Loop {
LazyLoop(int countIndex, int beginIndex) {
super(countIndex, beginIndex);
}
boolean match(Matcher matcher, int i, CharSequence seq) {
// Check for zero length group
if (i > matcher.locals[beginIndex]) {
int count = matcher.locals[countIndex];
if (count < cmin) {
matcher.locals[countIndex] = count + 1;
boolean result = body.match(matcher, i, seq);
// If match failed we must backtrack, so
// the loop count should NOT be incremented
if (!result)
matcher.locals[countIndex] = count;
return result;
}
if (next.match(matcher, i, seq))
return true;
if (count < cmax) {
matcher.locals[countIndex] = count + 1;
boolean result = body.match(matcher, i, seq);
// If match failed we must backtrack, so
// the loop count should NOT be incremented
if (!result)
matcher.locals[countIndex] = count;
return result;
}
return false;
}
return next.match(matcher, i, seq);
}
boolean matchInit(Matcher matcher, int i, CharSequence seq) {
int save = matcher.locals[countIndex];
boolean ret = false;
if (0 < cmin) {
matcher.locals[countIndex] = 1;
ret = body.match(matcher, i, seq);
} else if (next.match(matcher, i, seq)) {
ret = true;
} else if (0 < cmax) {
matcher.locals[countIndex] = 1;
ret = body.match(matcher, i, seq);
}
matcher.locals[countIndex] = save;
return ret;
}
boolean study(TreeInfo info) {
info.maxValid = false;
info.deterministic = false;
return false;
}
}
/**
* Refers to a group in the regular expression. Attempts to match
* whatever the group referred to last matched.
*/
static class BackRef extends Node {
int groupIndex;
BackRef(int groupCount) {
super();
groupIndex = groupCount + groupCount;
}
boolean match(Matcher matcher, int i, CharSequence seq) {
int j = matcher.groups[groupIndex];
int k = matcher.groups[groupIndex+1];
int groupSize = k - j;
// If the referenced group didn't match, neither can this
if (j < 0)
return false;
// If there isn't enough input left no match
if (i + groupSize > matcher.to) {
matcher.hitEnd = true;
return false;
}
// Check each new char to make sure it matches what the group
// referenced matched last time around
for (int index=0; index<groupSize; index++)
if (seq.charAt(i+index) != seq.charAt(j+index))
return false;
return next.match(matcher, i+groupSize, seq);
}
boolean study(TreeInfo info) {
info.maxValid = false;
return next.study(info);
}
}
static class CIBackRef extends Node {
int groupIndex;
boolean doUnicodeCase;
CIBackRef(int groupCount, boolean doUnicodeCase) {
super();
groupIndex = groupCount + groupCount;
this.doUnicodeCase = doUnicodeCase;
}
boolean match(Matcher matcher, int i, CharSequence seq) {
int j = matcher.groups[groupIndex];
int k = matcher.groups[groupIndex+1];
int groupSize = k - j;
// If the referenced group didn't match, neither can this
if (j < 0)
return false;
// If there isn't enough input left no match
if (i + groupSize > matcher.to) {
matcher.hitEnd = true;
return false;
}
// Check each new char to make sure it matches what the group
// referenced matched last time around
int x = i;
for (int index=0; index<groupSize; index++) {
int c1 = Character.codePointAt(seq, x);
int c2 = Character.codePointAt(seq, j);
if (c1 != c2) {
if (doUnicodeCase) {
int cc1 = Character.toUpperCase(c1);
int cc2 = Character.toUpperCase(c2);
if (cc1 != cc2 &&
Character.toLowerCase(cc1) !=
Character.toLowerCase(cc2))
return false;
} else {
if (ASCII.toLower(c1) != ASCII.toLower(c2))
return false;
}
}
x += Character.charCount(c1);
j += Character.charCount(c2);
}
return next.match(matcher, i+groupSize, seq);
}
boolean study(TreeInfo info) {
info.maxValid = false;
return next.study(info);
}
}
/**
* Searches until the next instance of its atom. This is useful for
* finding the atom efficiently without passing an instance of it
* (greedy problem) and without a lot of wasted search time (reluctant
* problem).
*/
static final class First extends Node {
Node atom;
First(Node node) {
this.atom = BnM.optimize(node);
}
boolean match(Matcher matcher, int i, CharSequence seq) {
if (atom instanceof BnM) {
return atom.match(matcher, i, seq)
&& next.match(matcher, matcher.last, seq);
}
for (;;) {
if (i > matcher.to) {
matcher.hitEnd = true;
return false;
}
if (atom.match(matcher, i, seq)) {
return next.match(matcher, matcher.last, seq);
}
i += countChars(seq, i, 1);
matcher.first++;
}
}
boolean study(TreeInfo info) {
atom.study(info);
info.maxValid = false;
info.deterministic = false;
return next.study(info);
}
}
static final class Conditional extends Node {
Node cond, yes, not;
Conditional(Node cond, Node yes, Node not) {
this.cond = cond;
this.yes = yes;
this.not = not;
}
boolean match(Matcher matcher, int i, CharSequence seq) {
if (cond.match(matcher, i, seq)) {
return yes.match(matcher, i, seq);
} else {
return not.match(matcher, i, seq);
}
}
boolean study(TreeInfo info) {
int minL = info.minLength;
int maxL = info.maxLength;
boolean maxV = info.maxValid;
info.reset();
yes.study(info);
int minL2 = info.minLength;
int maxL2 = info.maxLength;
boolean maxV2 = info.maxValid;
info.reset();
not.study(info);
info.minLength = minL + Math.min(minL2, info.minLength);
info.maxLength = maxL + Math.max(maxL2, info.maxLength);
info.maxValid = (maxV & maxV2 & info.maxValid);
info.deterministic = false;
return next.study(info);
}
}
/**
* Zero width positive lookahead.
*/
static final class Pos extends Node {
Node cond;
Pos(Node cond) {
this.cond = cond;
}
boolean match(Matcher matcher, int i, CharSequence seq) {
int savedTo = matcher.to;
boolean conditionMatched = false;
// Relax transparent region boundaries for lookahead
if (matcher.transparentBounds)
matcher.to = matcher.getTextLength();
try {
conditionMatched = cond.match(matcher, i, seq);
} finally {
// Reinstate region boundaries
matcher.to = savedTo;
}
return conditionMatched && next.match(matcher, i, seq);
}
}
/**
* Zero width negative lookahead.
*/
static final class Neg extends Node {
Node cond;
Neg(Node cond) {
this.cond = cond;
}
boolean match(Matcher matcher, int i, CharSequence seq) {
int savedTo = matcher.to;
boolean conditionMatched = false;
// Relax transparent region boundaries for lookahead
if (matcher.transparentBounds)
matcher.to = matcher.getTextLength();
try {
if (i < matcher.to) {
conditionMatched = !cond.match(matcher, i, seq);
} else {
// If a negative lookahead succeeds then more input
// could cause it to fail!
matcher.requireEnd = true;
conditionMatched = !cond.match(matcher, i, seq);
}
} finally {
// Reinstate region boundaries
matcher.to = savedTo;
}
return conditionMatched && next.match(matcher, i, seq);
}
}
/**
* For use with lookbehinds; matches the position where the lookbehind
* was encountered.
*/
static Node lookbehindEnd = new Node() {
boolean match(Matcher matcher, int i, CharSequence seq) {
return i == matcher.lookbehindTo;
}
};
/**
* Zero width positive lookbehind.
*/
static class Behind extends Node {
Node cond;
int rmax, rmin;
Behind(Node cond, int rmax, int rmin) {
this.cond = cond;
this.rmax = rmax;
this.rmin = rmin;
}
boolean match(Matcher matcher, int i, CharSequence seq) {
int savedFrom = matcher.from;
boolean conditionMatched = false;
int startIndex = (!matcher.transparentBounds) ?
matcher.from : 0;
int from = Math.max(i - rmax, startIndex);
// Set end boundary
int savedLBT = matcher.lookbehindTo;
matcher.lookbehindTo = i;
// Relax transparent region boundaries for lookbehind
if (matcher.transparentBounds)
matcher.from = 0;
for (int j = i - rmin; !conditionMatched && j >= from; j--) {
conditionMatched = cond.match(matcher, j, seq);
}
matcher.from = savedFrom;
matcher.lookbehindTo = savedLBT;
return conditionMatched && next.match(matcher, i, seq);
}
}
/**
* Zero width positive lookbehind, including supplementary
* characters or unpaired surrogates.
*/
static final class BehindS extends Behind {
BehindS(Node cond, int rmax, int rmin) {
super(cond, rmax, rmin);
}
boolean match(Matcher matcher, int i, CharSequence seq) {
int rmaxChars = countChars(seq, i, -rmax);
int rminChars = countChars(seq, i, -rmin);
int savedFrom = matcher.from;
int startIndex = (!matcher.transparentBounds) ?
matcher.from : 0;
boolean conditionMatched = false;
int from = Math.max(i - rmaxChars, startIndex);
// Set end boundary
int savedLBT = matcher.lookbehindTo;
matcher.lookbehindTo = i;
// Relax transparent region boundaries for lookbehind
if (matcher.transparentBounds)
matcher.from = 0;
for (int j = i - rminChars;
!conditionMatched && j >= from;
j -= j>from ? countChars(seq, j, -1) : 1) {
conditionMatched = cond.match(matcher, j, seq);
}
matcher.from = savedFrom;
matcher.lookbehindTo = savedLBT;
return conditionMatched && next.match(matcher, i, seq);
}
}
/**
* Zero width negative lookbehind.
*/
static class NotBehind extends Node {
Node cond;
int rmax, rmin;
NotBehind(Node cond, int rmax, int rmin) {
this.cond = cond;
this.rmax = rmax;
this.rmin = rmin;
}
boolean match(Matcher matcher, int i, CharSequence seq) {
int savedLBT = matcher.lookbehindTo;
int savedFrom = matcher.from;
boolean conditionMatched = false;
int startIndex = (!matcher.transparentBounds) ?
matcher.from : 0;
int from = Math.max(i - rmax, startIndex);
matcher.lookbehindTo = i;
// Relax transparent region boundaries for lookbehind
if (matcher.transparentBounds)
matcher.from = 0;
for (int j = i - rmin; !conditionMatched && j >= from; j--) {
conditionMatched = cond.match(matcher, j, seq);
}
// Reinstate region boundaries
matcher.from = savedFrom;
matcher.lookbehindTo = savedLBT;
return !conditionMatched && next.match(matcher, i, seq);
}
}
/**
* Zero width negative lookbehind, including supplementary
* characters or unpaired surrogates.
*/
static final class NotBehindS extends NotBehind {
NotBehindS(Node cond, int rmax, int rmin) {
super(cond, rmax, rmin);
}
boolean match(Matcher matcher, int i, CharSequence seq) {
int rmaxChars = countChars(seq, i, -rmax);
int rminChars = countChars(seq, i, -rmin);
int savedFrom = matcher.from;
int savedLBT = matcher.lookbehindTo;
boolean conditionMatched = false;
int startIndex = (!matcher.transparentBounds) ?
matcher.from : 0;
int from = Math.max(i - rmaxChars, startIndex);
matcher.lookbehindTo = i;
// Relax transparent region boundaries for lookbehind
if (matcher.transparentBounds)
matcher.from = 0;
for (int j = i - rminChars;
!conditionMatched && j >= from;
j -= j>from ? countChars(seq, j, -1) : 1) {
conditionMatched = cond.match(matcher, j, seq);
}
//Reinstate region boundaries
matcher.from = savedFrom;
matcher.lookbehindTo = savedLBT;
return !conditionMatched && next.match(matcher, i, seq);
}
}
/**
* Returns the set union of two CharProperty nodes.
*/
private static CharProperty union(final CharProperty lhs,
final CharProperty rhs) {
return new CharProperty() {
boolean isSatisfiedBy(int ch) {
return lhs.isSatisfiedBy(ch) || rhs.isSatisfiedBy(ch);}};
}
/**
* Returns the set intersection of two CharProperty nodes.
*/
private static CharProperty intersection(final CharProperty lhs,
final CharProperty rhs) {
return new CharProperty() {
boolean isSatisfiedBy(int ch) {
return lhs.isSatisfiedBy(ch) && rhs.isSatisfiedBy(ch);}};
}
/**
* Returns the set difference of two CharProperty nodes.
*/
private static CharProperty setDifference(final CharProperty lhs,
final CharProperty rhs) {
return new CharProperty() {
boolean isSatisfiedBy(int ch) {
return ! rhs.isSatisfiedBy(ch) && lhs.isSatisfiedBy(ch);}};
}
/**
* Handles word boundaries. Includes a field to allow this one class to
* deal with the different types of word boundaries we can match. The word
* characters include underscores, letters, and digits. Non spacing marks
* can are also part of a word if they have a base character, otherwise
* they are ignored for purposes of finding word boundaries.
*/
static final class Bound extends Node {
static int LEFT = 0x1;
static int RIGHT= 0x2;
static int BOTH = 0x3;
static int NONE = 0x4;
int type;
boolean useUWORD;
Bound(int n, boolean useUWORD) {
type = n;
this.useUWORD = useUWORD;
}
boolean isWord(int ch) {
return useUWORD ? UnicodeProp.WORD.is(ch)
: (ch == '_' || Character.isLetterOrDigit(ch));
}
int check(Matcher matcher, int i, CharSequence seq) {
int ch;
boolean left = false;
int startIndex = matcher.from;
int endIndex = matcher.to;
if (matcher.transparentBounds) {
startIndex = 0;
endIndex = matcher.getTextLength();
}
if (i > startIndex) {
ch = Character.codePointBefore(seq, i);
left = (isWord(ch) ||
((Character.getType(ch) == Character.NON_SPACING_MARK)
&& hasBaseCharacter(matcher, i-1, seq)));
}
boolean right = false;
if (i < endIndex) {
ch = Character.codePointAt(seq, i);
right = (isWord(ch) ||
((Character.getType(ch) == Character.NON_SPACING_MARK)
&& hasBaseCharacter(matcher, i, seq)));
} else {
// Tried to access char past the end
matcher.hitEnd = true;
// The addition of another char could wreck a boundary
matcher.requireEnd = true;
}
return ((left ^ right) ? (right ? LEFT : RIGHT) : NONE);
}
boolean match(Matcher matcher, int i, CharSequence seq) {
return (check(matcher, i, seq) & type) > 0
&& next.match(matcher, i, seq);
}
}
/**
* Non spacing marks only count as word characters in bounds calculations
* if they have a base character.
*/
private static boolean hasBaseCharacter(Matcher matcher, int i,
CharSequence seq)
{
int start = (!matcher.transparentBounds) ?
matcher.from : 0;
for (int x=i; x >= start; x--) {
int ch = Character.codePointAt(seq, x);
if (Character.isLetterOrDigit(ch))
return true;
if (Character.getType(ch) == Character.NON_SPACING_MARK)
continue;
return false;
}
return false;
}
/**
* Attempts to match a slice in the input using the Boyer-Moore string
* matching algorithm. The algorithm is based on the idea that the
* pattern can be shifted farther ahead in the search text if it is
* matched right to left.
* <p>
* The pattern is compared to the input one character at a time, from
* the rightmost character in the pattern to the left. If the characters
* all match the pattern has been found. If a character does not match,
* the pattern is shifted right a distance that is the maximum of two
* functions, the bad character shift and the good suffix shift. This
* shift moves the attempted match position through the input more
* quickly than a naive one position at a time check.
* <p>
* The bad character shift is based on the character from the text that
* did not match. If the character does not appear in the pattern, the
* pattern can be shifted completely beyond the bad character. If the
* character does occur in the pattern, the pattern can be shifted to
* line the pattern up with the next occurrence of that character.
* <p>
* The good suffix shift is based on the idea that some subset on the right
* side of the pattern has matched. When a bad character is found, the
* pattern can be shifted right by the pattern length if the subset does
* not occur again in pattern, or by the amount of distance to the
* next occurrence of the subset in the pattern.
*
* Boyer-Moore search methods adapted from code by Amy Yu.
*/
static class BnM extends Node {
int[] buffer;
int[] lastOcc;
int[] optoSft;
/**
* Pre calculates arrays needed to generate the bad character
* shift and the good suffix shift. Only the last seven bits
* are used to see if chars match; This keeps the tables small
* and covers the heavily used ASCII range, but occasionally
* results in an aliased match for the bad character shift.
*/
static Node optimize(Node node) {
if (!(node instanceof Slice)) {
return node;
}
int[] src = ((Slice) node).buffer;
int patternLength = src.length;
// The BM algorithm requires a bit of overhead;
// If the pattern is short don't use it, since
// a shift larger than the pattern length cannot
// be used anyway.
if (patternLength < 4) {
return node;
}
int i, j, k;
int[] lastOcc = new int[128];
int[] optoSft = new int[patternLength];
// Precalculate part of the bad character shift
// It is a table for where in the pattern each
// lower 7-bit value occurs
for (i = 0; i < patternLength; i++) {
lastOcc[src[i]&0x7F] = i + 1;
}
// Precalculate the good suffix shift
// i is the shift amount being considered
NEXT: for (i = patternLength; i > 0; i--) {
// j is the beginning index of suffix being considered
for (j = patternLength - 1; j >= i; j--) {
// Testing for good suffix
if (src[j] == src[j-i]) {
// src[j..len] is a good suffix
optoSft[j-1] = i;
} else {
// No match. The array has already been
// filled up with correct values before.
continue NEXT;
}
}
// This fills up the remaining of optoSft
// any suffix can not have larger shift amount
// then its sub-suffix. Why???
while (j > 0) {
optoSft[--j] = i;
}
}
// Set the guard value because of unicode compression
optoSft[patternLength-1] = 1;
if (node instanceof SliceS)
return new BnMS(src, lastOcc, optoSft, node.next);
return new BnM(src, lastOcc, optoSft, node.next);
}
BnM(int[] src, int[] lastOcc, int[] optoSft, Node next) {
this.buffer = src;
this.lastOcc = lastOcc;
this.optoSft = optoSft;
this.next = next;
}
boolean match(Matcher matcher, int i, CharSequence seq) {
int[] src = buffer;
int patternLength = src.length;
int last = matcher.to - patternLength;
// Loop over all possible match positions in text
NEXT: while (i <= last) {
// Loop over pattern from right to left
for (int j = patternLength - 1; j >= 0; j--) {
int ch = seq.charAt(i+j);
if (ch != src[j]) {
// Shift search to the right by the maximum of the
// bad character shift and the good suffix shift
i += Math.max(j + 1 - lastOcc[ch&0x7F], optoSft[j]);
continue NEXT;
}
}
// Entire pattern matched starting at i
matcher.first = i;
boolean ret = next.match(matcher, i + patternLength, seq);
if (ret) {
matcher.first = i;
matcher.groups[0] = matcher.first;
matcher.groups[1] = matcher.last;
return true;
}
i++;
}
// BnM is only used as the leading node in the unanchored case,
// and it replaced its Start() which always searches to the end
// if it doesn't find what it's looking for, so hitEnd is true.
matcher.hitEnd = true;
return false;
}
boolean study(TreeInfo info) {
info.minLength += buffer.length;
info.maxValid = false;
return next.study(info);
}
}
/**
* Supplementary support version of BnM(). Unpaired surrogates are
* also handled by this class.
*/
static final class BnMS extends BnM {
int lengthInChars;
BnMS(int[] src, int[] lastOcc, int[] optoSft, Node next) {
super(src, lastOcc, optoSft, next);
for (int x = 0; x < buffer.length; x++) {
lengthInChars += Character.charCount(buffer[x]);
}
}
boolean match(Matcher matcher, int i, CharSequence seq) {
int[] src = buffer;
int patternLength = src.length;
int last = matcher.to - lengthInChars;
// Loop over all possible match positions in text
NEXT: while (i <= last) {
// Loop over pattern from right to left
int ch;
for (int j = countChars(seq, i, patternLength), x = patternLength - 1;
j > 0; j -= Character.charCount(ch), x--) {
ch = Character.codePointBefore(seq, i+j);
if (ch != src[x]) {
// Shift search to the right by the maximum of the
// bad character shift and the good suffix shift
int n = Math.max(x + 1 - lastOcc[ch&0x7F], optoSft[x]);
i += countChars(seq, i, n);
continue NEXT;
}
}
// Entire pattern matched starting at i
matcher.first = i;
boolean ret = next.match(matcher, i + lengthInChars, seq);
if (ret) {
matcher.first = i;
matcher.groups[0] = matcher.first;
matcher.groups[1] = matcher.last;
return true;
}
i += countChars(seq, i, 1);
}
matcher.hitEnd = true;
return false;
}
}
///////////////////////////////////////////////////////////////////////////////
///////////////////////////////////////////////////////////////////////////////
/**
* This must be the very first initializer.
*/
static Node accept = new Node();
static Node lastAccept = new LastNode();
private static class CharPropertyNames {
static CharProperty charPropertyFor(String name) {
CharPropertyFactory m = map.get(name);
return m == null ? null : m.make();
}
private static abstract class CharPropertyFactory {
abstract CharProperty make();
}
private static void defCategory(String name,
final int typeMask) {
map.put(name, new CharPropertyFactory() {
CharProperty make() { return new Category(typeMask);}});
}
private static void defRange(String name,
final int lower, final int upper) {
map.put(name, new CharPropertyFactory() {
CharProperty make() { return rangeFor(lower, upper);}});
}
private static void defCtype(String name,
final int ctype) {
map.put(name, new CharPropertyFactory() {
CharProperty make() { return new Ctype(ctype);}});
}
private static abstract class CloneableProperty
extends CharProperty implements Cloneable
{
public CloneableProperty clone() {
try {
return (CloneableProperty) super.clone();
} catch (CloneNotSupportedException e) {
throw new AssertionError(e);
}
}
}
private static void defClone(String name,
final CloneableProperty p) {
map.put(name, new CharPropertyFactory() {
CharProperty make() { return p.clone();}});
}
private static final HashMap<String, CharPropertyFactory> map
= new HashMap<>();
static {
// Unicode character property aliases, defined in
// http://www.unicode.org/Public/UNIDATA/PropertyValueAliases.txt
defCategory("Cn", 1<<Character.UNASSIGNED);
defCategory("Lu", 1<<Character.UPPERCASE_LETTER);
defCategory("Ll", 1<<Character.LOWERCASE_LETTER);
defCategory("Lt", 1<<Character.TITLECASE_LETTER);
defCategory("Lm", 1<<Character.MODIFIER_LETTER);
defCategory("Lo", 1<<Character.OTHER_LETTER);
defCategory("Mn", 1<<Character.NON_SPACING_MARK);
defCategory("Me", 1<<Character.ENCLOSING_MARK);
defCategory("Mc", 1<<Character.COMBINING_SPACING_MARK);
defCategory("Nd", 1<<Character.DECIMAL_DIGIT_NUMBER);
defCategory("Nl", 1<<Character.LETTER_NUMBER);
defCategory("No", 1<<Character.OTHER_NUMBER);
defCategory("Zs", 1<<Character.SPACE_SEPARATOR);
defCategory("Zl", 1<<Character.LINE_SEPARATOR);
defCategory("Zp", 1<<Character.PARAGRAPH_SEPARATOR);
defCategory("Cc", 1<<Character.CONTROL);
defCategory("Cf", 1<<Character.FORMAT);
defCategory("Co", 1<<Character.PRIVATE_USE);
defCategory("Cs", 1<<Character.SURROGATE);
defCategory("Pd", 1<<Character.DASH_PUNCTUATION);
defCategory("Ps", 1<<Character.START_PUNCTUATION);
defCategory("Pe", 1<<Character.END_PUNCTUATION);
defCategory("Pc", 1<<Character.CONNECTOR_PUNCTUATION);
defCategory("Po", 1<<Character.OTHER_PUNCTUATION);
defCategory("Sm", 1<<Character.MATH_SYMBOL);
defCategory("Sc", 1<<Character.CURRENCY_SYMBOL);
defCategory("Sk", 1<<Character.MODIFIER_SYMBOL);
defCategory("So", 1<<Character.OTHER_SYMBOL);
defCategory("Pi", 1<<Character.INITIAL_QUOTE_PUNCTUATION);
defCategory("Pf", 1<<Character.FINAL_QUOTE_PUNCTUATION);
defCategory("L", ((1<<Character.UPPERCASE_LETTER) |
(1<<Character.LOWERCASE_LETTER) |
(1<<Character.TITLECASE_LETTER) |
(1<<Character.MODIFIER_LETTER) |
(1<<Character.OTHER_LETTER)));
defCategory("M", ((1<<Character.NON_SPACING_MARK) |
(1<<Character.ENCLOSING_MARK) |
(1<<Character.COMBINING_SPACING_MARK)));
defCategory("N", ((1<<Character.DECIMAL_DIGIT_NUMBER) |
(1<<Character.LETTER_NUMBER) |
(1<<Character.OTHER_NUMBER)));
defCategory("Z", ((1<<Character.SPACE_SEPARATOR) |
(1<<Character.LINE_SEPARATOR) |
(1<<Character.PARAGRAPH_SEPARATOR)));
defCategory("C", ((1<<Character.CONTROL) |
(1<<Character.FORMAT) |
(1<<Character.PRIVATE_USE) |
(1<<Character.SURROGATE))); // Other
defCategory("P", ((1<<Character.DASH_PUNCTUATION) |
(1<<Character.START_PUNCTUATION) |
(1<<Character.END_PUNCTUATION) |
(1<<Character.CONNECTOR_PUNCTUATION) |
(1<<Character.OTHER_PUNCTUATION) |
(1<<Character.INITIAL_QUOTE_PUNCTUATION) |
(1<<Character.FINAL_QUOTE_PUNCTUATION)));
defCategory("S", ((1<<Character.MATH_SYMBOL) |
(1<<Character.CURRENCY_SYMBOL) |
(1<<Character.MODIFIER_SYMBOL) |
(1<<Character.OTHER_SYMBOL)));
defCategory("LC", ((1<<Character.UPPERCASE_LETTER) |
(1<<Character.LOWERCASE_LETTER) |
(1<<Character.TITLECASE_LETTER)));
defCategory("LD", ((1<<Character.UPPERCASE_LETTER) |
(1<<Character.LOWERCASE_LETTER) |
(1<<Character.TITLECASE_LETTER) |
(1<<Character.MODIFIER_LETTER) |
(1<<Character.OTHER_LETTER) |
(1<<Character.DECIMAL_DIGIT_NUMBER)));
defRange("L1", 0x00, 0xFF); // Latin-1
map.put("all", new CharPropertyFactory() {
CharProperty make() { return new All(); }});
// Posix regular expression character classes, defined in
// http://www.unix.org/onlinepubs/009695399/basedefs/xbd_chap09.html
defRange("ASCII", 0x00, 0x7F); // ASCII
defCtype("Alnum", ASCII.ALNUM); // Alphanumeric characters
defCtype("Alpha", ASCII.ALPHA); // Alphabetic characters
defCtype("Blank", ASCII.BLANK); // Space and tab characters
defCtype("Cntrl", ASCII.CNTRL); // Control characters
defRange("Digit", '0', '9'); // Numeric characters
defCtype("Graph", ASCII.GRAPH); // printable and visible
defRange("Lower", 'a', 'z'); // Lower-case alphabetic
defRange("Print", 0x20, 0x7E); // Printable characters
defCtype("Punct", ASCII.PUNCT); // Punctuation characters
defCtype("Space", ASCII.SPACE); // Space characters
defRange("Upper", 'A', 'Z'); // Upper-case alphabetic
defCtype("XDigit",ASCII.XDIGIT); // hexadecimal digits
// Java character properties, defined by methods in Character.java
defClone("javaLowerCase", new CloneableProperty() {
boolean isSatisfiedBy(int ch) {
return Character.isLowerCase(ch);}});
defClone("javaUpperCase", new CloneableProperty() {
boolean isSatisfiedBy(int ch) {
return Character.isUpperCase(ch);}});
defClone("javaAlphabetic", new CloneableProperty() {
boolean isSatisfiedBy(int ch) {
return Character.isAlphabetic(ch);}});
defClone("javaIdeographic", new CloneableProperty() {
boolean isSatisfiedBy(int ch) {
return Character.isIdeographic(ch);}});
defClone("javaTitleCase", new CloneableProperty() {
boolean isSatisfiedBy(int ch) {
return Character.isTitleCase(ch);}});
defClone("javaDigit", new CloneableProperty() {
boolean isSatisfiedBy(int ch) {
return Character.isDigit(ch);}});
defClone("javaDefined", new CloneableProperty() {
boolean isSatisfiedBy(int ch) {
return Character.isDefined(ch);}});
defClone("javaLetter", new CloneableProperty() {
boolean isSatisfiedBy(int ch) {
return Character.isLetter(ch);}});
defClone("javaLetterOrDigit", new CloneableProperty() {
boolean isSatisfiedBy(int ch) {
return Character.isLetterOrDigit(ch);}});
defClone("javaJavaIdentifierStart", new CloneableProperty() {
boolean isSatisfiedBy(int ch) {
return Character.isJavaIdentifierStart(ch);}});
defClone("javaJavaIdentifierPart", new CloneableProperty() {
boolean isSatisfiedBy(int ch) {
return Character.isJavaIdentifierPart(ch);}});
defClone("javaUnicodeIdentifierStart", new CloneableProperty() {
boolean isSatisfiedBy(int ch) {
return Character.isUnicodeIdentifierStart(ch);}});
defClone("javaUnicodeIdentifierPart", new CloneableProperty() {
boolean isSatisfiedBy(int ch) {
return Character.isUnicodeIdentifierPart(ch);}});
defClone("javaIdentifierIgnorable", new CloneableProperty() {
boolean isSatisfiedBy(int ch) {
return Character.isIdentifierIgnorable(ch);}});
defClone("javaSpaceChar", new CloneableProperty() {
boolean isSatisfiedBy(int ch) {
return Character.isSpaceChar(ch);}});
defClone("javaWhitespace", new CloneableProperty() {
boolean isSatisfiedBy(int ch) {
return Character.isWhitespace(ch);}});
defClone("javaISOControl", new CloneableProperty() {
boolean isSatisfiedBy(int ch) {
return Character.isISOControl(ch);}});
defClone("javaMirrored", new CloneableProperty() {
boolean isSatisfiedBy(int ch) {
return Character.isMirrored(ch);}});
}
}
}