re.java

jakarta-regexp-1.5 正则表达式的源代码

/*
 * Licensed to the Apache Software Foundation (ASF) under one or more
 * contributor license agreements.  See the NOTICE file distributed with
 * this work for additional information regarding copyright ownership.
 * The ASF licenses this file to You under the Apache License, Version 2.0
 * (the "License"); you may not use this file except in compliance with
 * the License.  You may obtain a copy of the License at
 *
 *     http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */

package org.apache.regexp;

import java.io.Serializable;
import java.util.Vector;

/**
 * RE is an efficient, lightweight regular expression evaluator/matcher
 * class. Regular expressions are pattern descriptions which enable
 * sophisticated matching of strings.  In addition to being able to
 * match a string against a pattern, you can also extract parts of the
 * match.  This is especially useful in text parsing! Details on the
 * syntax of regular expression patterns are given below.
 *
 * <p>
 * To compile a regular expression (RE), you can simply construct an RE
 * matcher object from the string specification of the pattern, like this:
 *
 * <pre>
 *  RE r = new RE("a*b");
 * </pre>
 *
 * <p>
 * Once you have done this, you can call either of the RE.match methods to
 * perform matching on a String.  For example:
 *
 * <pre>
 *  boolean matched = r.match("aaaab");
 * </pre>
 *
 * will cause the boolean matched to be set to true because the
 * pattern "a*b" matches the string "aaaab".
 *
 * <p>
 * If you were interested in the <i>number</i> of a's which matched the
 * first part of our example expression, you could change the expression to
 * "(a*)b".  Then when you compiled the expression and matched it against
 * something like "xaaaab", you would get results like this:
 *
 * <pre>
 *  RE r = new RE("(a*)b");                  // Compile expression
 *  boolean matched = r.match("xaaaab");     // Match against "xaaaab"
 *
 *  String wholeExpr = r.getParen(0);        // wholeExpr will be 'aaaab'
 *  String insideParens = r.getParen(1);     // insideParens will be 'aaaa'
 *
 *  int startWholeExpr = r.getParenStart(0); // startWholeExpr will be index 1
 *  int endWholeExpr = r.getParenEnd(0);     // endWholeExpr will be index 6
 *  int lenWholeExpr = r.getParenLength(0);  // lenWholeExpr will be 5
 *
 *  int startInside = r.getParenStart(1);    // startInside will be index 1
 *  int endInside = r.getParenEnd(1);        // endInside will be index 5
 *  int lenInside = r.getParenLength(1);     // lenInside will be 4
 * </pre>
 *
 * You can also refer to the contents of a parenthesized expression
 * within a regular expression itself.  This is called a
 * 'backreference'.  The first backreference in a regular expression is
 * denoted by \1, the second by \2 and so on.  So the expression:
 *
 * <pre>
 *  ([0-9]+)=\1
 * </pre>
 *
 * will match any string of the form n=n (like 0=0 or 2=2).
 *
 * <p>
 * The full regular expression syntax accepted by RE is described here:
 *
 * <pre>
 *
 *  <b><font face=times roman>Characters</font></b>
 *
 *    <i>unicodeChar</i>   Matches any identical unicode character
 *    \                    Used to quote a meta-character (like '*')
 *    \\                   Matches a single '\' character
 *    \0nnn                Matches a given octal character
 *    \xhh                 Matches a given 8-bit hexadecimal character
 *    \\uhhhh              Matches a given 16-bit hexadecimal character
 *    \t                   Matches an ASCII tab character
 *    \n                   Matches an ASCII newline character
 *    \r                   Matches an ASCII return character
 *    \f                   Matches an ASCII form feed character
 *
 *
 *  <b><font face=times roman>Character Classes</font></b>
 *
 *    [abc]                Simple character class
 *    [a-zA-Z]             Character class with ranges
 *    [^abc]               Negated character class
 * </pre>
 *
 * <b>NOTE:</b> Incomplete ranges will be interpreted as &quot;starts
 * from zero&quot; or &quot;ends with last character&quot;.
 * <br>
 * I.e. [-a] is the same as [\\u0000-a], and [a-] is the same as [a-\\uFFFF],
 * [-] means &quot;all characters&quot;.
 *
 * <pre>
 *
 *  <b><font face=times roman>Standard POSIX Character Classes</font></b>
 *
 *    [:alnum:]            Alphanumeric characters.
 *    [:alpha:]            Alphabetic characters.
 *    [:blank:]            Space and tab characters.
 *    [:cntrl:]            Control characters.
 *    [:digit:]            Numeric characters.
 *    [:graph:]            Characters that are printable and are also visible.
 *                         (A space is printable, but not visible, while an
 *                         `a' is both.)
 *    [:lower:]            Lower-case alphabetic characters.
 *    [:print:]            Printable characters (characters that are not
 *                         control characters.)
 *    [:punct:]            Punctuation characters (characters that are not letter,
 *                         digits, control characters, or space characters).
 *    [:space:]            Space characters (such as space, tab, and formfeed,
 *                         to name a few).
 *    [:upper:]            Upper-case alphabetic characters.
 *    [:xdigit:]           Characters that are hexadecimal digits.
 *
 *
 *  <b><font face=times roman>Non-standard POSIX-style Character Classes</font></b>
 *
 *    [:javastart:]        Start of a Java identifier
 *    [:javapart:]         Part of a Java identifier
 *
 *
 *  <b><font face=times roman>Predefined Classes</font></b>
 *
 *    .         Matches any character other than newline
 *    \w        Matches a "word" character (alphanumeric plus "_")
 *    \W        Matches a non-word character
 *    \s        Matches a whitespace character
 *    \S        Matches a non-whitespace character
 *    \d        Matches a digit character
 *    \D        Matches a non-digit character
 *
 *
 *  <b><font face=times roman>Boundary Matchers</font></b>
 *
 *    ^         Matches only at the beginning of a line
 *    $         Matches only at the end of a line
 *    \b        Matches only at a word boundary
 *    \B        Matches only at a non-word boundary
 *
 *
 *  <b><font face=times roman>Greedy Closures</font></b>
 *
 *    A*        Matches A 0 or more times (greedy)
 *    A+        Matches A 1 or more times (greedy)
 *    A?        Matches A 1 or 0 times (greedy)
 *    A{n}      Matches A exactly n times (greedy)
 *    A{n,}     Matches A at least n times (greedy)
 *    A{n,m}    Matches A at least n but not more than m times (greedy)
 *
 *
 *  <b><font face=times roman>Reluctant Closures</font></b>
 *
 *    A*?       Matches A 0 or more times (reluctant)
 *    A+?       Matches A 1 or more times (reluctant)
 *    A??       Matches A 0 or 1 times (reluctant)
 *
 *
 *  <b><font face=times roman>Logical Operators</font></b>
 *
 *    AB        Matches A followed by B
 *    A|B       Matches either A or B
 *    (A)       Used for subexpression grouping
 *   (?:A)      Used for subexpression clustering (just like grouping but
 *              no backrefs)
 *
 *
 *  <b><font face=times roman>Backreferences</font></b>
 *
 *    \1    Backreference to 1st parenthesized subexpression
 *    \2    Backreference to 2nd parenthesized subexpression
 *    \3    Backreference to 3rd parenthesized subexpression
 *    \4    Backreference to 4th parenthesized subexpression
 *    \5    Backreference to 5th parenthesized subexpression
 *    \6    Backreference to 6th parenthesized subexpression
 *    \7    Backreference to 7th parenthesized subexpression
 *    \8    Backreference to 8th parenthesized subexpression
 *    \9    Backreference to 9th parenthesized subexpression
 * </pre>
 *
 * <p>
 * All closure operators (+, *, ?, {m,n}) are greedy by default, meaning
 * that they match as many elements of the string as possible without
 * causing the overall match to fail.  If you want a closure to be
 * reluctant (non-greedy), you can simply follow it with a '?'.  A
 * reluctant closure will match as few elements of the string as
 * possible when finding matches.  {m,n} closures don't currently
 * support reluctancy.
 *
 * <p>
 * <b><font face="times roman">Line terminators</font></b>
 * <br>
 * A line terminator 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 ('\n'),</li>
 * <li>A carriage-return character followed immediately by a newline character ("\r\n"),</li>
 * <li>A standalone carriage-return character ('\r'),</li>
 * <li>A next-line character ('\u0085'),</li>
 * <li>A line-separator character ('\u2028'), or</li>
 * <li>A paragraph-separator character ('\u2029).</li>
 * </ul>
 *
 * <p>
 * RE runs programs compiled by the RECompiler class.  But the RE
 * matcher class does not include the actual regular expression compiler
 * for reasons of efficiency.  In fact, if you want to pre-compile one
 * or more regular expressions, the 'recompile' class can be invoked
 * from the command line to produce compiled output like this:
 *
 * <pre>
 *    // Pre-compiled regular expression "a*b"
 *    char[] re1Instructions =
 *    {
 *        0x007c, 0x0000, 0x001a, 0x007c, 0x0000, 0x000d, 0x0041,
 *        0x0001, 0x0004, 0x0061, 0x007c, 0x0000, 0x0003, 0x0047,
 *        0x0000, 0xfff6, 0x007c, 0x0000, 0x0003, 0x004e, 0x0000,
 *        0x0003, 0x0041, 0x0001, 0x0004, 0x0062, 0x0045, 0x0000,
 *        0x0000,
 *    };
 *
 *
 *    REProgram re1 = new REProgram(re1Instructions);
 * </pre>
 *
 * You can then construct a regular expression matcher (RE) object from
 * the pre-compiled expression re1 and thus avoid the overhead of
 * compiling the expression at runtime. If you require more dynamic
 * regular expressions, you can construct a single RECompiler object and
 * re-use it to compile each expression. Similarly, you can change the
 * program run by a given matcher object at any time. However, RE and
 * RECompiler are not threadsafe (for efficiency reasons, and because
 * requiring thread safety in this class is deemed to be a rare
 * requirement), so you will need to construct a separate compiler or
 * matcher object for each thread (unless you do thread synchronization
 * yourself). Once expression compiled into the REProgram object, REProgram
 * can be safely shared across multiple threads and RE objects.
 *
 * <br><p><br>
 *
 * <font color="red">
 * <i>ISSUES:</i>
 *
 * <ul>
 *  <li>com.weusours.util.re is not currently compatible with all
 *      standard POSIX regcomp flags</li>
 *  <li>com.weusours.util.re does not support POSIX equivalence classes
 *      ([=foo=] syntax) (I18N/locale issue)</li>
 *  <li>com.weusours.util.re does not support nested POSIX character
 *      classes (definitely should, but not completely trivial)</li>
 *  <li>com.weusours.util.re Does not support POSIX character collation
 *      concepts ([.foo.] syntax) (I18N/locale issue)</li>
 *  <li>Should there be different matching styles (simple, POSIX, Perl etc?)</li>
 *  <li>Should RE support character iterators (for backwards RE matching!)?</li>
 *  <li>Should RE support reluctant {m,n} closures (does anyone care)?</li>
 *  <li>Not *all* possibilities are considered for greediness when backreferences
 *      are involved (as POSIX suggests should be the case).  The POSIX RE
 *      "(ac*)c*d[ac]*\1", when matched against "acdacaa" should yield a match
 *      of acdacaa where \1 is "a".  This is not the case in this RE package,
 *      and actually Perl doesn't go to this extent either!  Until someone
 *      actually complains about this, I'm not sure it's worth "fixing".
 *      If it ever is fixed, test #137 in RETest.txt should be updated.</li>
 * </ul>
 *
 * </font>
 *
 * @see recompile
 * @see RECompiler
 *
 * @author <a href="mailto:[e-mail]">Jonathan Locke</a>
 * @author <a href="mailto:[e-mail]">Tobias Sch&auml;fer</a>
 * @version $Id: RE.java 518156 2007-03-14 14:31:26Z vgritsenko $
 */
public class RE implements Serializable
{
    /**
     * Specifies normal, case-sensitive matching behaviour.
     */
    public static final int MATCH_NORMAL          = 0x0000;

    /**
     * Flag to indicate that matching should be case-independent (folded)
     */
    public static final int MATCH_CASEINDEPENDENT = 0x0001;

    /**
     * Newlines should match as BOL/EOL (^ and $)
     */
    public static final int MATCH_MULTILINE       = 0x0002;

    /**
     * Consider all input a single body of text - newlines are matched by .
     */
    public static final int MATCH_SINGLELINE      = 0x0004;

    /************************************************
     *                                              *
     * The format of a node in a program is:        *
     *                                              *
     * [ OPCODE ] [ OPDATA ] [ OPNEXT ] [ OPERAND ] *
     *                                              *
     * char OPCODE - instruction                    *
     * char OPDATA - modifying data                 *
     * char OPNEXT - next node (relative offset)    *
     *                                              *
     ************************************************/

                 //   Opcode              Char       Opdata/Operand  Meaning
                 //   ----------          ---------- --------------- --------------------------------------------------
    static final char OP_END              = 'E';  //                 end of program
    static final char OP_BOL              = '^';  //                 match only if at beginning of line
    static final char OP_EOL              = '$';  //                 match only if at end of line
    static final char OP_ANY              = '.';  //                 match any single character except newline
    static final char OP_ANYOF            = '[';  // count/ranges    match any char in the list of ranges
    static final char OP_BRANCH           = '|';  // node            match this alternative or the next one
    static final char OP_ATOM             = 'A';  // length/string   length of string followed by string itself
    static final char OP_STAR             = '*';  // node            kleene closure
    static final char OP_PLUS             = '+';  // node            positive closure
    static final char OP_MAYBE            = '?';  // node            optional closure
    static final char OP_ESCAPE           = '\\'; // escape          special escape code char class (escape is E_* code)
    static final char OP_OPEN             = '(';  // number          nth opening paren
    static final char OP_OPEN_CLUSTER     = '<';  //                 opening cluster
    static final char OP_CLOSE            = ')';  // number          nth closing paren
    static final char OP_CLOSE_CLUSTER    = '>';  //                 closing cluster
    static final char OP_BACKREF          = '#';  // number          reference nth already matched parenthesized string
    static final char OP_GOTO             = 'G';  //                 nothing but a (back-)pointer
    static final char OP_NOTHING          = 'N';  //                 match null string such as in '(a|)'
    static final char OP_CONTINUE         = 'C';  //                 continue to the following command (ignore next)