< prev index next >
src/java.base/share/classes/java/util/regex/Pattern.java
Print this page
*** 86,129 ****
* <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>
*
--- 86,129 ----
* <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">{@code \\}</td>
* <td headers="matches">The backslash character</td></tr>
! * <tr><td valign="top" headers="construct characters">{@code \0}<i>n</i></td>
! * <td headers="matches">The character with octal value {@code 0}<i>n</i>
! * (0 {@code <=} <i>n</i> {@code <=} 7)</td></tr>
! * <tr><td valign="top" headers="construct characters">{@code \0}<i>nn</i></td>
! * <td headers="matches">The character with octal value {@code 0}<i>nn</i>
! * (0 {@code <=} <i>n</i> {@code <=} 7)</td></tr>
! * <tr><td valign="top" headers="construct characters">{@code \0}<i>mnn</i></td>
! * <td headers="matches">The character with octal value {@code 0}<i>mnn</i>
! * (0 {@code <=} <i>m</i> {@code <=} 3,
! * 0 {@code <=} <i>n</i> {@code <=} 7)</td></tr>
! * <tr><td valign="top" headers="construct characters">{@code \x}<i>hh</i></td>
! * <td headers="matches">The character with hexadecimal value {@code 0x}<i>hh</i></td></tr>
! * <tr><td valign="top" headers="construct characters"><code>\u</code><i>hhhh</i></td>
! * <td headers="matches">The character with hexadecimal value {@code 0x}<i>hhhh</i></td></tr>
! * <tr><td valign="top" headers="construct characters"><code>\x</code><i>{h...h}</i></td>
! * <td headers="matches">The character with hexadecimal value {@code 0x}<i>h...h</i>
* ({@link java.lang.Character#MIN_CODE_POINT Character.MIN_CODE_POINT}
! * <= {@code 0x}<i>h...h</i> <=
* {@link java.lang.Character#MAX_CODE_POINT Character.MAX_CODE_POINT})</td></tr>
! * <tr><td valign="top" headers="matches">{@code \t}</td>
! * <td headers="matches">The tab character (<code>'\u0009'</code>)</td></tr>
! * <tr><td valign="top" headers="construct characters">{@code \n}</td>
! * <td headers="matches">The newline (line feed) character (<code>'\u000A'</code>)</td></tr>
! * <tr><td valign="top" headers="construct characters">{@code \r}</td>
! * <td headers="matches">The carriage-return character (<code>'\u000D'</code>)</td></tr>
! * <tr><td valign="top" headers="construct characters">{@code \f}</td>
! * <td headers="matches">The form-feed character (<code>'\u000C'</code>)</td></tr>
! * <tr><td valign="top" headers="construct characters">{@code \a}</td>
! * <td headers="matches">The alert (bell) character (<code>'\u0007'</code>)</td></tr>
! * <tr><td valign="top" headers="construct characters">{@code \e}</td>
! * <td headers="matches">The escape character (<code>'\u001B'</code>)</td></tr>
! * <tr><td valign="top" headers="construct characters">{@code \c}<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>
*
*** 147,180 ****
* and not {@code m} through {@code p}: {@code [a-lq-z]}(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>\h</tt></td>
* <td headers="matches">A horizontal whitespace character:
! * <tt>[ \t\xA0\u1680\u180e\u2000-\u200a\u202f\u205f\u3000]</tt></td></tr>
! * <tr><td valign="top" headers="construct predef"><tt>\H</tt></td>
! * <td headers="matches">A non-horizontal whitespace character: <tt>[^\h]</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>\v</tt></td>
! * <td headers="matches">A vertical whitespace character: <tt>[\n\x0B\f\r\x85\u2028\u2029]</tt>
* </td></tr>
! * <tr><td valign="top" headers="construct predef"><tt>\V</tt></td>
! * <td headers="matches">A non-vertical whitespace character: <tt>[^\v]</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"><b>POSIX character classes (US-ASCII only)</b></th></tr>
*
* <tr><td valign="top" headers="construct posix">{@code \p{Lower}}</td>
* <td headers="matches">A lower-case alphabetic character: {@code [a-z]}</td></tr>
--- 147,180 ----
* and not {@code m} through {@code p}: {@code [a-lq-z]}(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">{@code .}</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">{@code \d}</td>
! * <td headers="matches">A digit: {@code [0-9]}</td></tr>
! * <tr><td valign="top" headers="construct predef">{@code \D}</td>
! * <td headers="matches">A non-digit: {@code [^0-9]}</td></tr>
! * <tr><td valign="top" headers="construct predef">{@code \h}</td>
* <td headers="matches">A horizontal whitespace character:
! * <code>[ \t\xA0\u1680\u180e\u2000-\u200a\u202f\u205f\u3000]</code></td></tr>
! * <tr><td valign="top" headers="construct predef">{@code \H}</td>
! * <td headers="matches">A non-horizontal whitespace character: {@code [^\h]}</td></tr>
! * <tr><td valign="top" headers="construct predef">{@code \s}</td>
! * <td headers="matches">A whitespace character: {@code [ \t\n\x0B\f\r]}</td></tr>
! * <tr><td valign="top" headers="construct predef">{@code \S}</td>
! * <td headers="matches">A non-whitespace character: {@code [^\s]}</td></tr>
! * <tr><td valign="top" headers="construct predef">{@code \v}</td>
! * <td headers="matches">A vertical whitespace character: <code>[\n\x0B\f\r\x85\u2028\u2029]</code>
* </td></tr>
! * <tr><td valign="top" headers="construct predef">{@code \V}</td>
! * <td headers="matches">A non-vertical whitespace character: {@code [^\v]}</td></tr>
! * <tr><td valign="top" headers="construct predef">{@code \w}</td>
! * <td headers="matches">A word character: {@code [a-zA-Z_0-9]}</td></tr>
! * <tr><td valign="top" headers="construct predef">{@code \W}</td>
! * <td headers="matches">A non-word character: {@code [^\w]}</td></tr>
* <tr><th> </th></tr>
* <tr align="left"><th colspan="2" id="posix"><b>POSIX character classes (US-ASCII only)</b></th></tr>
*
* <tr><td valign="top" headers="construct posix">{@code \p{Lower}}</td>
* <td headers="matches">A lower-case alphabetic character: {@code [a-z]}</td></tr>
*** 206,222 ****
* <td headers="matches">A whitespace character: {@code [ \t\n\x0B\f\r]}</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">{@code \p{IsLatin}}</td>
--- 206,222 ----
* <td headers="matches">A whitespace character: {@code [ \t\n\x0B\f\r]}</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">{@code \p{javaLowerCase}}</td>
* <td>Equivalent to java.lang.Character.isLowerCase()</td></tr>
! * <tr><td valign="top">{@code \p{javaUpperCase}}</td>
* <td>Equivalent to java.lang.Character.isUpperCase()</td></tr>
! * <tr><td valign="top">{@code \p{javaWhitespace}}</td>
* <td>Equivalent to java.lang.Character.isWhitespace()</td></tr>
! * <tr><td valign="top">{@code \p{javaMirrored}}</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">{@code \p{IsLatin}}</td>
*** 235,388 ****
* <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="lineending">Linebreak matcher</th></tr>
! * <tr><td valign="top" headers="construct lineending"><tt>\R</tt></td>
* <td headers="matches">Any Unicode linebreak sequence, is equivalent to
! * <tt>\u000D\u000A|[\u000A\u000B\u000C\u000D\u0085\u2028\u2029]
! * </tt></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>
*
*
* <h3><a name="bs">Backslashes, escapes, and quoting</a></h3>
*
! * <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
--- 235,388 ----
* <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">{@code ^}</td>
* <td headers="matches">The beginning of a line</td></tr>
! * <tr><td valign="top" headers="construct bounds">{@code $}</td>
* <td headers="matches">The end of a line</td></tr>
! * <tr><td valign="top" headers="construct bounds">{@code \b}</td>
* <td headers="matches">A word boundary</td></tr>
! * <tr><td valign="top" headers="construct bounds">{@code \B}</td>
* <td headers="matches">A non-word boundary</td></tr>
! * <tr><td valign="top" headers="construct bounds">{@code \A}</td>
* <td headers="matches">The beginning of the input</td></tr>
! * <tr><td valign="top" headers="construct bounds">{@code \G}</td>
* <td headers="matches">The end of the previous match</td></tr>
! * <tr><td valign="top" headers="construct bounds">{@code \Z}</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">{@code \z}</td>
* <td headers="matches">The end of the input</td></tr>
*
* <tr><th> </th></tr>
* <tr align="left"><th colspan="2" id="lineending">Linebreak matcher</th></tr>
! * <tr><td valign="top" headers="construct lineending">{@code \R}</td>
* <td headers="matches">Any Unicode linebreak sequence, is equivalent to
! * <code>\u000D\u000A|[\u000A\u000B\u000C\u000D\u0085\u2028\u2029]
! * </code></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>{@code ?}</td>
* <td headers="matches"><i>X</i>, once or not at all</td></tr>
! * <tr><td valign="top" headers="construct greedy"><i>X</i>{@code *}</td>
* <td headers="matches"><i>X</i>, zero or more times</td></tr>
! * <tr><td valign="top" headers="construct greedy"><i>X</i>{@code +}</td>
* <td headers="matches"><i>X</i>, one or more times</td></tr>
! * <tr><td valign="top" headers="construct greedy"><i>X</i><code>{</code><i>n</i><code>}</code></td>
* <td headers="matches"><i>X</i>, exactly <i>n</i> times</td></tr>
! * <tr><td valign="top" headers="construct greedy"><i>X</i><code>{</code><i>n</i>{@code ,}}</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><code>{</code><i>n</i>{@code ,}<i>m</i><code>}</code></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>{@code ??}</td>
* <td headers="matches"><i>X</i>, once or not at all</td></tr>
! * <tr><td valign="top" headers="construct reluc"><i>X</i>{@code *?}</td>
* <td headers="matches"><i>X</i>, zero or more times</td></tr>
! * <tr><td valign="top" headers="construct reluc"><i>X</i>{@code +?}</td>
* <td headers="matches"><i>X</i>, one or more times</td></tr>
! * <tr><td valign="top" headers="construct reluc"><i>X</i><code>{</code><i>n</i><code>}?</code></td>
* <td headers="matches"><i>X</i>, exactly <i>n</i> times</td></tr>
! * <tr><td valign="top" headers="construct reluc"><i>X</i><code>{</code><i>n</i><code>,}?</code></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><code>{</code><i>n</i>{@code ,}<i>m</i><code>}?</code></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>{@code ?+}</td>
* <td headers="matches"><i>X</i>, once or not at all</td></tr>
! * <tr><td valign="top" headers="construct poss"><i>X</i>{@code *+}</td>
* <td headers="matches"><i>X</i>, zero or more times</td></tr>
! * <tr><td valign="top" headers="construct poss"><i>X</i>{@code ++}</td>
* <td headers="matches"><i>X</i>, one or more times</td></tr>
! * <tr><td valign="top" headers="construct poss"><i>X</i><code>{</code><i>n</i><code>}+</code></td>
* <td headers="matches"><i>X</i>, exactly <i>n</i> times</td></tr>
! * <tr><td valign="top" headers="construct poss"><i>X</i><code>{</code><i>n</i><code>,}+</code></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><code>{</code><i>n</i>{@code ,}<i>m</i><code>}+</code></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>{@code |}<i>Y</i></td>
* <td headers="matches">Either <i>X</i> or <i>Y</i></td></tr>
! * <tr><td valign="top" headers="construct logical">{@code (}<i>X</i>{@code )}</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">{@code \}<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">{@code \}<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">{@code \}</td>
* <td headers="matches">Nothing, but quotes the following character</td></tr>
! * <tr><td valign="top" headers="construct quot">{@code \Q}</td>
! * <td headers="matches">Nothing, but quotes all characters until {@code \E}</td></tr>
! * <tr><td valign="top" headers="construct quot">{@code \E}</td>
! * <td headers="matches">Nothing, but ends quoting started by {@code \Q}</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"><code>(?<<a href="#groupname">name</a>></code><i>X</i>{@code )}</td>
* <td headers="matches"><i>X</i>, as a named-capturing group</td></tr>
! * <tr><td valign="top" headers="construct special">{@code (?:}<i>X</i>{@code )}</td>
* <td headers="matches"><i>X</i>, as a non-capturing group</td></tr>
! * <tr><td valign="top" headers="construct special"><code>(?idmsuxU-idmsuxU) </code></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"><code>(?idmsux-idmsux:</code><i>X</i>{@code )} </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">{@code (?=}<i>X</i>{@code )}</td>
* <td headers="matches"><i>X</i>, via zero-width positive lookahead</td></tr>
! * <tr><td valign="top" headers="construct special">{@code (?!}<i>X</i>{@code )}</td>
* <td headers="matches"><i>X</i>, via zero-width negative lookahead</td></tr>
! * <tr><td valign="top" headers="construct special">{@code (?<=}<i>X</i>{@code )}</td>
* <td headers="matches"><i>X</i>, via zero-width positive lookbehind</td></tr>
! * <tr><td valign="top" headers="construct special">{@code (?<!}<i>X</i>{@code )}</td>
* <td headers="matches"><i>X</i>, via zero-width negative lookbehind</td></tr>
! * <tr><td valign="top" headers="construct special">{@code (?>}<i>X</i>{@code )}</td>
* <td headers="matches"><i>X</i>, as an independent, non-capturing group</td></tr>
*
* </table>
*
* <hr>
*
*
* <h3><a name="bs">Backslashes, escapes, and quoting</a></h3>
*
! * <p> The backslash character ({@code '\'}) 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 {@code \\} matches a single backslash and <code>\{</code> 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
*** 394,415 ****
* <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.
*
* <h3><a name="cc">Character Classes</a></h3>
*
* <p> Character classes may appear within other character classes, and
* may be composed by the union operator (implicit) and the intersection
! * 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.
*
--- 394,415 ----
* <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
! * <code>"\b"</code>, for example, matches a single backspace character when
! * interpreted as a regular expression, while {@code "\\b"} matches a
! * word boundary. The string literal {@code "\(hello\)"} is illegal
* and leads to a compile-time error; in order to match the string
! * {@code (hello)} the string literal {@code "\\(hello\\)"}
* must be used.
*
* <h3><a name="cc">Character Classes</a></h3>
*
* <p> Character classes may appear within other character classes, and
* may be composed by the union operator (implicit) and the intersection
! * operator ({@code &&}).
* 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.
*
*** 418,584 ****
*
* <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>{@code [a-z&&[aeiou]]}</td></tr>
* </table></blockquote>
*
* <p> Note that a different set of metacharacters are in effect inside
* a character class than outside a character class. For instance, the
! * regular expression <tt>.</tt> loses its special meaning inside a
! * character class, while the expression <tt>-</tt> becomes a range
* forming metacharacter.
*
* <h3><a name="lt">Line terminators</a></h3>
*
* <p> A <i>line terminator</i> is a one- or two-character sequence that marks
* the end of a line of the input character sequence. The following are
* recognized as line terminators:
*
* <ul>
*
! * <li> A 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.
*
* <h3><a name="cg">Groups and capturing</a></h3>
*
* <h4><a name="gnumber">Group number</a></h4>
* <p> Capturing groups are numbered by counting their opening parentheses from
! * 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.
*
* <h4><a name="groupname">Group name</a></h4>
! * <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.
*
* <h3> Unicode support </h3>
*
* <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.
*
* <p>
* <b><a name="usc">Scripts</a></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}.
*
* <p>
* <b><a name="ubc">Blocks</a></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>
*
* <b><a name="ucc">Categories</a></b> may be specified with the optional prefix {@code Is}:
--- 418,584 ----
*
* <blockquote><table border="0" cellpadding="1" cellspacing="0"
* summary="Precedence of character class operators.">
* <tr><th>1 </th>
* <td>Literal escape </td>
! * <td>{@code \x}</td></tr>
* <tr><th>2 </th>
* <td>Grouping</td>
! * <td>{@code [...]}</td></tr>
* <tr><th>3 </th>
* <td>Range</td>
! * <td>{@code a-z}</td></tr>
* <tr><th>4 </th>
* <td>Union</td>
! * <td>{@code [a-e][i-u]}</td></tr>
* <tr><th>5 </th>
* <td>Intersection</td>
* <td>{@code [a-z&&[aeiou]]}</td></tr>
* </table></blockquote>
*
* <p> Note that a different set of metacharacters are in effect inside
* a character class than outside a character class. For instance, the
! * regular expression {@code .} loses its special meaning inside a
! * character class, while the expression {@code -} becomes a range
* forming metacharacter.
*
* <h3><a name="lt">Line terminators</a></h3>
*
* <p> A <i>line terminator</i> is a one- or two-character sequence that marks
* the end of a line of the input character sequence. The following are
* recognized as line terminators:
*
* <ul>
*
! * <li> A newline (line feed) character ({@code '\n'}),
*
* <li> A carriage-return character followed immediately by a newline
! * character ({@code "\r\n"}),
*
! * <li> A standalone carriage-return character ({@code '\r'}),
*
! * <li> A next-line character (<code>'\u0085'</code>),
*
! * <li> A line-separator character (<code>'\u2028'</code>), or
*
! * <li> A paragraph-separator character (<code>'\u2029</code>).
*
* </ul>
* <p>If {@link #UNIX_LINES} mode is activated, then the only line terminators
* recognized are newline characters.
*
! * <p> The regular expression {@code .} matches any character except a line
* terminator unless the {@link #DOTALL} flag is specified.
*
! * <p> By default, the regular expressions {@code ^} and {@code $} 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
! * {@code ^} matches at the beginning of input and after any line terminator
! * except at the end of input. When in {@link #MULTILINE} mode {@code $}
* matches just before a line terminator or the end of the input sequence.
*
* <h3><a name="cg">Groups and capturing</a></h3>
*
* <h4><a name="gnumber">Group number</a></h4>
* <p> Capturing groups are numbered by counting their opening parentheses from
! * left to right. In the expression {@code ((A)(B(C)))}, for example, there
* are four such groups: </p>
*
* <blockquote><table cellpadding=1 cellspacing=0 summary="Capturing group numberings">
* <tr><th>1 </th>
! * <td>{@code ((A)(B(C)))}</td></tr>
* <tr><th>2 </th>
! * <td>{@code (A)}</td></tr>
* <tr><th>3 </th>
! * <td>{@code (B(C))}</td></tr>
* <tr><th>4 </th>
! * <td>{@code (C)}</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.
*
* <h4><a name="groupname">Group name</a></h4>
! * <p>A capturing group can also be assigned a "name", a {@code named-capturing group},
* and then be back-referenced later by the "name". Group names are composed of
! * the following characters. The first character must be a {@code letter}.
*
* <ul>
! * <li> The uppercase letters {@code 'A'} through {@code 'Z'}
! * (<code>'\u0041'</code> through <code>'\u005a'</code>),
! * <li> The lowercase letters {@code 'a'} through {@code 'z'}
! * (<code>'\u0061'</code> through <code>'\u007a'</code>),
! * <li> The digits {@code '0'} through {@code '9'}
! * (<code>'\u0030'</code> through <code>'\u0039'</code>),
* </ul>
*
! * <p> A {@code named-capturing group} 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
! * {@code "aba"} against the expression {@code (a(b)?)+}, for example, leaves
! * group two set to {@code "b"}. All captured input is discarded at the
* beginning of each match.
*
! * <p> Groups beginning with {@code (?} 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.
*
* <h3> Unicode support </h3>
*
* <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 <code>\u2014</code> 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 <code>"\u2014"</code> and
! * {@code "\\u2014"}, while not equal, compile into the same pattern, which
! * matches the character with hexadecimal value {@code 0x2014}.
* <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
! * <code>\x{...}</code>, for example a supplementary character U+2011F
! * can be specified as <code>\x{2011F}</code>, instead of two consecutive
* Unicode escape sequences of the surrogate pair
! * <code>\uD840</code><code>\uDD1F</code>.
* <p>
* Unicode scripts, blocks, categories and binary properties are written with
! * the {@code \p} and {@code \P} constructs as in Perl.
! * <code>\p{</code><i>prop</i><code>}</code> matches if
! * the input has the property <i>prop</i>, while <code>\P{</code><i>prop</i><code>}</code>
* 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.
*
* <p>
* <b><a name="usc">Scripts</a></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} are the valid script names
* accepted and defined by
* {@link java.lang.Character.UnicodeScript#forName(String) UnicodeScript.forName}.
*
* <p>
* <b><a name="ubc">Blocks</a></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} are the valid block names
* accepted and defined by
* {@link java.lang.Character.UnicodeBlock#forName(String) UnicodeBlock.forName}.
* <p>
*
* <b><a name="ucc">Categories</a></b> may be specified with the optional prefix {@code Is}:
*** 593,603 ****
* {@link java.lang.Character Character} class. The category names are those
* defined in the Standard, both normative and informative.
* <p>
*
* <b><a name="ubpc">Binary properties</a></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
--- 593,603 ----
* {@link java.lang.Character Character} class. The category names are those
* defined in the Standard, both normative and informative.
* <p>
*
* <b><a name="ubpc">Binary properties</a></b> are specified with the prefix {@code Is}, as in
! * {@code IsAlphabetic}. The supported binary properties by {@code Pattern}
* are
* <ul>
* <li> Alphabetic
* <li> Ideographic
* <li> Letter
*** 623,714 ****
* summary="predefined and posix character classes in Unicode mode">
* <tr align="left">
* <th align="left" id="predef_classes">Classes</th>
* <th align="left" id="predef_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: {@code [\p{Graph}\p{Blank}&&[^\p{Cntrl}]]}</td></tr>
! * <tr><td><tt>\p{Blank}</tt></td>
* <td>A space or a tab: {@code [\p{IsWhite_Space}&&[^\p{gc=Zl}\p{gc=Zp}\x0a\x0b\x0c\x0d\x85]]}</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}\p{IsJoin_Control}]</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></a>.
*
* <h3> Comparison to Perl 5 </h3>
*
! * <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>\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>
*
--- 623,714 ----
* summary="predefined and posix character classes in Unicode mode">
* <tr align="left">
* <th align="left" id="predef_classes">Classes</th>
* <th align="left" id="predef_matches">Matches</th>
*</tr>
! * <tr><td>{@code \p{Lower}}</td>
! * <td>A lowercase character:{@code \p{IsLowercase}}</td></tr>
! * <tr><td>{@code \p{Upper}}</td>
! * <td>An uppercase character:{@code \p{IsUppercase}}</td></tr>
! * <tr><td>{@code \p{ASCII}}</td>
! * <td>All ASCII:{@code [\x00-\x7F]}</td></tr>
! * <tr><td>{@code \p{Alpha}}</td>
! * <td>An alphabetic character:{@code \p{IsAlphabetic}}</td></tr>
! * <tr><td>{@code \p{Digit}}</td>
! * <td>A decimal digit character:{@code p{IsDigit}}</td></tr>
! * <tr><td>{@code \p{Alnum}}</td>
! * <td>An alphanumeric character:{@code [\p{IsAlphabetic}\p{IsDigit}]}</td></tr>
! * <tr><td>{@code \p{Punct}}</td>
! * <td>A punctuation character:{@code p{IsPunctuation}}</td></tr>
! * <tr><td>{@code \p{Graph}}</td>
! * <td>A visible character: {@code [^\p{IsWhite_Space}\p{gc=Cc}\p{gc=Cs}\p{gc=Cn}]}</td></tr>
! * <tr><td>{@code \p{Print}}</td>
* <td>A printable character: {@code [\p{Graph}\p{Blank}&&[^\p{Cntrl}]]}</td></tr>
! * <tr><td>{@code \p{Blank}}</td>
* <td>A space or a tab: {@code [\p{IsWhite_Space}&&[^\p{gc=Zl}\p{gc=Zp}\x0a\x0b\x0c\x0d\x85]]}</td></tr>
! * <tr><td>{@code \p{Cntrl}}</td>
! * <td>A control character: {@code \p{gc=Cc}}</td></tr>
! * <tr><td>{@code \p{XDigit}}</td>
! * <td>A hexadecimal digit: {@code [\p{gc=Nd}\p{IsHex_Digit}]}</td></tr>
! * <tr><td>{@code \p{Space}}</td>
! * <td>A whitespace character:{@code \p{IsWhite_Space}}</td></tr>
! * <tr><td>{@code \d}</td>
! * <td>A digit: {@code \p{IsDigit}}</td></tr>
! * <tr><td>{@code \D}</td>
! * <td>A non-digit: {@code [^\d]}</td></tr>
! * <tr><td>{@code \s}</td>
! * <td>A whitespace character: {@code \p{IsWhite_Space}}</td></tr>
! * <tr><td>{@code \S}</td>
! * <td>A non-whitespace character: {@code [^\s]}</td></tr>
! * <tr><td>{@code \w}</td>
! * <td>A word character: {@code [\p{Alpha}\p{gc=Mn}\p{gc=Me}\p{gc=Mc}\p{Digit}\p{gc=Pc}\p{IsJoin_Control}]}</td></tr>
! * <tr><td>{@code \W}</td>
! * <td>A non-word character: {@code [^\w]}</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 <code>\p{</code><i>prop</i><code>}</code> syntax where
! * the specified property has the name <code>java<i>methodname</i></code></a>.
*
* <h3> Comparison to Perl 5 </h3>
*
! * <p>The {@code Pattern} 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><code>\X </code>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, <code>\g{</code><i>n</i><code>}</code> for
* the <i>n</i><sup>th</sup><a href="#cg">capturing group</a> and
! * <code>\g{</code><i>name</i><code>}</code> for
* <a href="#groupname">named-capturing group</a>.
* </p></li>
*
! * <li><p> The named character construct, <code>\N{</code><i>name</i><code>}</code>
* for a Unicode character by its name.
* </p></li>
*
* <li><p> The conditional constructs
! * {@code (?(}<i>condition</i>{@code )}<i>X</i>{@code )} and
! * {@code (?(}<i>condition</i>{@code )}<i>X</i>{@code |}<i>Y</i>{@code )},
* </p></li>
*
! * <li><p> The embedded code constructs <code>(?{</code><i>code</i><code>})</code>
! * and <code>(??{</code><i>code</i><code>})</code>,</p></li>
*
! * <li><p> The embedded comment syntax {@code (?#comment)}, and </p></li>
*
! * <li><p> The preprocessing operations {@code \l} <code>\u</code>,
! * {@code \L}, and {@code \U}. </p></li>
*
* </ul>
*
* <p> Constructs supported by this class but not by Perl: </p>
*
*** 721,743 ****
*
* <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>
*
--- 721,743 ----
*
* <p> Notable differences from Perl: </p>
*
* <ul>
*
! * <li><p> In Perl, {@code \1} through {@code \9} are always interpreted
! * as back references; a backslash-escaped number greater than {@code 9} 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,
! * {@code \1} through {@code \9} 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 {@code g} 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>
*
*** 784,798 ****
*/
/**
* 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.
--- 784,798 ----
*/
/**
* Enables Unix lines mode.
*
! * <p> In this mode, only the {@code '\n'} line terminator is recognized
! * in the behavior of {@code .}, {@code ^}, and {@code $}.
*
* <p> Unix lines mode can also be enabled via the embedded flag
! * expression {@code (?d)}.
*/
public static final int UNIX_LINES = 0x01;
/**
* Enables case-insensitive matching.
*** 801,837 ****
* in the US-ASCII charset are being matched. Unicode-aware
* case-insensitive matching can be enabled by specifying the {@link
* #UNICODE_CASE} flag in conjunction with this flag.
*
* <p> Case-insensitive matching can also be enabled via the embedded flag
! * expression <tt>(?i)</tt>.
*
* <p> Specifying this flag may impose a slight performance penalty. </p>
*/
public static final int CASE_INSENSITIVE = 0x02;
/**
* Permits whitespace and comments in pattern.
*
* <p> In this mode, whitespace is ignored, and embedded comments starting
! * with <tt>#</tt> are ignored until the end of a line.
*
* <p> Comments mode can also be enabled via the embedded flag
! * expression <tt>(?x)</tt>.
*/
public static final int COMMENTS = 0x04;
/**
* Enables multiline mode.
*
! * <p> In multiline mode the expressions <tt>^</tt> and <tt>$</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.
--- 801,837 ----
* 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 {@code (?i)}.
*
* <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 {@code #} are ignored until the end of a line.
*
* <p> Comments mode can also be enabled via the embedded flag
! * expression {@code (?x)}.
*/
public static final int COMMENTS = 0x04;
/**
* Enables multiline mode.
*
! * <p> In multiline mode the expressions {@code ^} and {@code $} 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 {@code (?m)}. </p>
*/
public static final int MULTILINE = 0x08;
/**
* Enables literal parsing of the pattern.
*** 851,866 ****
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;
/**
--- 851,866 ----
public static final int LITERAL = 0x10;
/**
* Enables dotall mode.
*
! * <p> In dotall mode, the expression {@code .} 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 {@code (?s)}. (The {@code s} is a mnemonic for
* "single-line" mode, which is what this is called in Perl.) </p>
*/
public static final int DOTALL = 0x20;
/**
*** 871,893 ****
* 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.
*
--- 871,893 ----
* 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 {@code (?u)}.
*
* <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 <code>"a\u030A"</code>, for example, will match the
! * string <code>"\u00E5"</code> 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.
*
*** 905,915 ****
* <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>
--- 905,915 ----
* <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 {@code (?U)}.
* <p>
* The flag implies UNICODE_CASE, that is, it enables Unicode-aware case
* folding.
* <p>
* Specifying this flag may impose a performance penalty. </p>
*** 1050,1060 ****
* and {@link #COMMENTS}
*
* @return the given regular expression compiled into a pattern with the given flags
* @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) {
--- 1050,1060 ----
* and {@link #COMMENTS}
*
* @return the given regular expression compiled into a pattern with the given flags
* @throws IllegalArgumentException
* If bit values other than those corresponding to the defined
! * match flags are set in {@code flags}
*
* @throws PatternSyntaxException
* If the expression's syntax is invalid
*/
public static Pattern compile(String regex, int flags) {
*** 1156,1202 ****
* <p> When there is a positive-width match at the beginning of the input
* sequence then an empty leading substring is included at the beginning
* of the resulting array. A zero-width match at the beginning however
* never produces such empty leading substring.
*
! * <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 align="left"><i>Regex </i></th>
* <th align="left"><i>Limit </i></th>
* <th 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
*
--- 1156,1202 ----
* <p> When there is a positive-width match at the beginning of the input
* sequence then an empty leading substring is included at the beginning
* of the resulting array. A zero-width match at the beginning however
* never produces such empty leading substring.
*
! * <p> The {@code limit} 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 {@code "boo:and:foo"}, 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 align="left"><i>Regex </i></th>
* <th align="left"><i>Limit </i></th>
* <th align="left"><i>Result </i></th></tr>
* <tr><td align=center>:</td>
* <td align=center>2</td>
! * <td>{@code { "boo", "and:foo" }}</td></tr>
* <tr><td align=center>:</td>
* <td align=center>5</td>
! * <td>{@code { "boo", "and", "foo" }}</td></tr>
* <tr><td align=center>:</td>
* <td align=center>-2</td>
! * <td>{@code { "boo", "and", "foo" }}</td></tr>
* <tr><td align=center>o</td>
* <td align=center>5</td>
! * <td>{@code { "b", "", ":and:f", "", "" }}</td></tr>
* <tr><td align=center>o</td>
* <td align=center>-2</td>
! * <td>{@code { "b", "", ":and:f", "", "" }}</td></tr>
* <tr><td align=center>o</td>
* <td align=center>0</td>
! * <td>{@code { "b", "", ":and:f" }}</td></tr>
* </table></blockquote>
*
* @param input
* The character sequence to be split
*
*** 1254,1274 ****
* <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 align="left"><i>Regex </i></th>
* <th 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
--- 1254,1274 ----
* <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 {@code "boo:and:foo"}, for example, yields the following
* results with these expressions:
*
* <blockquote><table cellpadding=1 cellspacing=0
* summary="Split examples showing regex and result">
* <tr><th align="left"><i>Regex </i></th>
* <th align="left"><i>Result</i></th></tr>
* <tr><td align=center>:</td>
! * <td>{@code { "boo", "and", "foo" }}</td></tr>
* <tr><td align=center>o</td>
! * <td>{@code { "b", "", ":and:f" }}</td></tr>
* </table></blockquote>
*
*
* @param input
* The character sequence to be split
*** 1279,1294 ****
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
--- 1279,1294 ----
public String[] split(CharSequence input) {
return split(input, 0);
}
/**
! * Returns a literal pattern {@code String} for the specified
! * {@code String}.
*
! * <p>This method produces a {@code String} that can be used to
! * create a {@code Pattern} that would match the string
! * {@code s} 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
< prev index next >