pattern.java

一个简单好用的java语言实现的个人日志管理系统

    /**
     * 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&nbsp;<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&#92;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;

    /* 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;

    /**
     * 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 char[] buffer;

    /**
     * Temporary storage used while parsing group references.
     */
    transient GroupHead[] groupNodes;

    /**
     * Temporary null terminating char array used by pattern compiling.
     */
    private transient char[] temp;

    /**
     * The group count of this Pattern. Used by matchers to allocate storage
     * needed to perform a match.
     */
    transient int groupCount;

    /**
     * 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;

    /**
     * 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}, and {@link #CANON_EQ}
     *
     * @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;
    }

    /**
     * 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) {
        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>&nbsp;-&nbsp;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&nbsp;&nbsp;&nbsp;&nbsp;</i></th>
     *     <th><P align="left"><i>Limit&nbsp;&nbsp;&nbsp;&nbsp;</i></th>
     *     <th><P align="left"><i>Result&nbsp;&nbsp;&nbsp;&nbsp;</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 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 (String[])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&nbsp;&nbsp;&nbsp;&nbsp;</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>
     *