src/share/classes/java/util/regex/Pattern.java
Print this page
@@ -43,12 +43,12 @@
/**
* A compiled representation of a regular expression.
*
* <p> A regular expression, specified as a string, must first be compiled into
* an instance of this class. The resulting pattern can then be used to create
- * a {@link Matcher} object that can match arbitrary {@link
- * java.lang.CharSequence </code>character sequences<code>} against the regular
+ * a {@link Matcher} object that can match arbitrary {@linkplain
+ * java.lang.CharSequence character sequences} against the regular
* expression. All of the state involved in performing a match resides in the
* matcher, so many matchers can share the same pattern.
*
* <p> A typical invocation sequence is thus
*
@@ -71,19 +71,18 @@
* <p> Instances of this class are immutable and are safe for use by multiple
* concurrent threads. Instances of the {@link Matcher} class are not safe for
* such use.
*
*
- * <a name="sum">
- * <h4> Summary of regular-expression constructs </h4>
+ * <h3><a name="sum">Summary of regular-expression constructs</a></h3>
*
* <table border="0" cellpadding="1" cellspacing="0"
* summary="Regular expression constructs, and what they match">
*
* <tr align="left">
- * <th bgcolor="#CCCCFF" align="left" id="construct">Construct</th>
- * <th bgcolor="#CCCCFF" align="left" id="matches">Matches</th>
+ * <th align="left" id="construct">Construct</th>
+ * <th align="left" id="matches">Matches</th>
* </tr>
*
* <tr><th> </th></tr>
* <tr align="left"><th colspan="2" id="characters">Characters</th></tr>
*
@@ -126,28 +125,28 @@
* <td headers="matches">The control character corresponding to <i>x</i></td></tr>
*
* <tr><th> </th></tr>
* <tr align="left"><th colspan="2" id="classes">Character classes</th></tr>
*
- * <tr><td valign="top" headers="construct classes"><tt>[abc]</tt></td>
- * <td headers="matches"><tt>a</tt>, <tt>b</tt>, or <tt>c</tt> (simple class)</td></tr>
- * <tr><td valign="top" headers="construct classes"><tt>[^abc]</tt></td>
- * <td headers="matches">Any character except <tt>a</tt>, <tt>b</tt>, or <tt>c</tt> (negation)</td></tr>
- * <tr><td valign="top" headers="construct classes"><tt>[a-zA-Z]</tt></td>
- * <td headers="matches"><tt>a</tt> through <tt>z</tt>
- * or <tt>A</tt> through <tt>Z</tt>, inclusive (range)</td></tr>
- * <tr><td valign="top" headers="construct classes"><tt>[a-d[m-p]]</tt></td>
- * <td headers="matches"><tt>a</tt> through <tt>d</tt>,
- * or <tt>m</tt> through <tt>p</tt>: <tt>[a-dm-p]</tt> (union)</td></tr>
- * <tr><td valign="top" headers="construct classes"><tt>[a-z&&[def]]</tt></td>
- * <td headers="matches"><tt>d</tt>, <tt>e</tt>, or <tt>f</tt> (intersection)</tr>
- * <tr><td valign="top" headers="construct classes"><tt>[a-z&&[^bc]]</tt></td>
- * <td headers="matches"><tt>a</tt> through <tt>z</tt>,
- * except for <tt>b</tt> and <tt>c</tt>: <tt>[ad-z]</tt> (subtraction)</td></tr>
- * <tr><td valign="top" headers="construct classes"><tt>[a-z&&[^m-p]]</tt></td>
- * <td headers="matches"><tt>a</tt> through <tt>z</tt>,
- * and not <tt>m</tt> through <tt>p</tt>: <tt>[a-lq-z]</tt>(subtraction)</td></tr>
+ * <tr><td valign="top" headers="construct classes">{@code [abc]}</td>
+ * <td headers="matches">{@code a}, {@code b}, or {@code c} (simple class)</td></tr>
+ * <tr><td valign="top" headers="construct classes">{@code [^abc]}</td>
+ * <td headers="matches">Any character except {@code a}, {@code b}, or {@code c} (negation)</td></tr>
+ * <tr><td valign="top" headers="construct classes">{@code [a-zA-Z]}</td>
+ * <td headers="matches">{@code a} through {@code z}
+ * or {@code A} through {@code Z}, inclusive (range)</td></tr>
+ * <tr><td valign="top" headers="construct classes">{@code [a-d[m-p]]}</td>
+ * <td headers="matches">{@code a} through {@code d},
+ * or {@code m} through {@code p}: {@code [a-dm-p]} (union)</td></tr>
+ * <tr><td valign="top" headers="construct classes">{@code [a-z&&[def]]}</td>
+ * <td headers="matches">{@code d}, {@code e}, or {@code f} (intersection)</tr>
+ * <tr><td valign="top" headers="construct classes">{@code [a-z&&[^bc]]}</td>
+ * <td headers="matches">{@code a} through {@code z},
+ * except for {@code b} and {@code c}: {@code [ad-z]} (subtraction)</td></tr>
+ * <tr><td valign="top" headers="construct classes">{@code [a-z&&[^m-p]]}</td>
+ * <td headers="matches">{@code a} through {@code z},
+ * and not {@code m} through {@code p}: {@code [a-lq-z]}(subtraction)</td></tr>
* <tr><th> </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>
@@ -173,40 +172,40 @@
* <tr><td valign="top" headers="construct predef"><tt>\w</tt></td>
* <td headers="matches">A word character: <tt>[a-zA-Z_0-9]</tt></td></tr>
* <tr><td valign="top" headers="construct predef"><tt>\W</tt></td>
* <td headers="matches">A non-word character: <tt>[^\w]</tt></td></tr>
* <tr><th> </th></tr>
- * <tr align="left"><th colspan="2" id="posix">POSIX character classes</b> (US-ASCII only)<b></th></tr>
+ * <tr align="left"><th colspan="2" id="posix"><b>POSIX character classes (US-ASCII only)</b></th></tr>
*
- * <tr><td valign="top" headers="construct posix"><tt>\p{Lower}</tt></td>
- * <td headers="matches">A lower-case alphabetic character: <tt>[a-z]</tt></td></tr>
- * <tr><td valign="top" headers="construct posix"><tt>\p{Upper}</tt></td>
- * <td headers="matches">An upper-case alphabetic character:<tt>[A-Z]</tt></td></tr>
- * <tr><td valign="top" headers="construct posix"><tt>\p{ASCII}</tt></td>
- * <td headers="matches">All ASCII:<tt>[\x00-\x7F]</tt></td></tr>
- * <tr><td valign="top" headers="construct posix"><tt>\p{Alpha}</tt></td>
- * <td headers="matches">An alphabetic character:<tt>[\p{Lower}\p{Upper}]</tt></td></tr>
- * <tr><td valign="top" headers="construct posix"><tt>\p{Digit}</tt></td>
- * <td headers="matches">A decimal digit: <tt>[0-9]</tt></td></tr>
- * <tr><td valign="top" headers="construct posix"><tt>\p{Alnum}</tt></td>
- * <td headers="matches">An alphanumeric character:<tt>[\p{Alpha}\p{Digit}]</tt></td></tr>
- * <tr><td valign="top" headers="construct posix"><tt>\p{Punct}</tt></td>
- * <td headers="matches">Punctuation: One of <tt>!"#$%&'()*+,-./:;<=>?@[\]^_`{|}~</tt></td></tr>
- * <!-- <tt>[\!"#\$%&'\(\)\*\+,\-\./:;\<=\>\?@\[\\\]\^_`\{\|\}~]</tt>
- * <tt>[\X21-\X2F\X31-\X40\X5B-\X60\X7B-\X7E]</tt> -->
- * <tr><td valign="top" headers="construct posix"><tt>\p{Graph}</tt></td>
- * <td headers="matches">A visible character: <tt>[\p{Alnum}\p{Punct}]</tt></td></tr>
- * <tr><td valign="top" headers="construct posix"><tt>\p{Print}</tt></td>
- * <td headers="matches">A printable character: <tt>[\p{Graph}\x20]</tt></td></tr>
- * <tr><td valign="top" headers="construct posix"><tt>\p{Blank}</tt></td>
- * <td headers="matches">A space or a tab: <tt>[ \t]</tt></td></tr>
- * <tr><td valign="top" headers="construct posix"><tt>\p{Cntrl}</tt></td>
- * <td headers="matches">A control character: <tt>[\x00-\x1F\x7F]</tt></td></tr>
- * <tr><td valign="top" headers="construct posix"><tt>\p{XDigit}</tt></td>
- * <td headers="matches">A hexadecimal digit: <tt>[0-9a-fA-F]</tt></td></tr>
- * <tr><td valign="top" headers="construct posix"><tt>\p{Space}</tt></td>
- * <td headers="matches">A whitespace character: <tt>[ \t\n\x0B\f\r]</tt></td></tr>
+ * <tr><td valign="top" headers="construct posix">{@code \p{Lower}}</td>
+ * <td headers="matches">A lower-case alphabetic character: {@code [a-z]}</td></tr>
+ * <tr><td valign="top" headers="construct posix">{@code \p{Upper}}</td>
+ * <td headers="matches">An upper-case alphabetic character:{@code [A-Z]}</td></tr>
+ * <tr><td valign="top" headers="construct posix">{@code \p{ASCII}}</td>
+ * <td headers="matches">All ASCII:{@code [\x00-\x7F]}</td></tr>
+ * <tr><td valign="top" headers="construct posix">{@code \p{Alpha}}</td>
+ * <td headers="matches">An alphabetic character:{@code [\p{Lower}\p{Upper}]}</td></tr>
+ * <tr><td valign="top" headers="construct posix">{@code \p{Digit}}</td>
+ * <td headers="matches">A decimal digit: {@code [0-9]}</td></tr>
+ * <tr><td valign="top" headers="construct posix">{@code \p{Alnum}}</td>
+ * <td headers="matches">An alphanumeric character:{@code [\p{Alpha}\p{Digit}]}</td></tr>
+ * <tr><td valign="top" headers="construct posix">{@code \p{Punct}}</td>
+ * <td headers="matches">Punctuation: One of {@code !"#$%&'()*+,-./:;<=>?@[\]^_`{|}~}</td></tr>
+ * <!-- {@code [\!"#\$%&'\(\)\*\+,\-\./:;\<=\>\?@\[\\\]\^_`\{\|\}~]}
+ * {@code [\X21-\X2F\X31-\X40\X5B-\X60\X7B-\X7E]} -->
+ * <tr><td valign="top" headers="construct posix">{@code \p{Graph}}</td>
+ * <td headers="matches">A visible character: {@code [\p{Alnum}\p{Punct}]}</td></tr>
+ * <tr><td valign="top" headers="construct posix">{@code \p{Print}}</td>
+ * <td headers="matches">A printable character: {@code [\p{Graph}\x20]}</td></tr>
+ * <tr><td valign="top" headers="construct posix">{@code \p{Blank}}</td>
+ * <td headers="matches">A space or a tab: {@code [ \t]}</td></tr>
+ * <tr><td valign="top" headers="construct posix">{@code \p{Cntrl}}</td>
+ * <td headers="matches">A control character: {@code [\x00-\x1F\x7F]}</td></tr>
+ * <tr><td valign="top" headers="construct posix">{@code \p{XDigit}}</td>
+ * <td headers="matches">A hexadecimal digit: {@code [0-9a-fA-F]}</td></tr>
+ * <tr><td valign="top" headers="construct posix">{@code \p{Space}}</td>
+ * <td headers="matches">A whitespace character: {@code [ \t\n\x0B\f\r]}</td></tr>
*
* <tr><th> </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>
@@ -218,23 +217,23 @@
* <tr><td valign="top"><tt>\p{javaMirrored}</tt></td>
* <td>Equivalent to java.lang.Character.isMirrored()</td></tr>
*
* <tr><th> </th></tr>
* <tr align="left"><th colspan="2" id="unicode">Classes for Unicode scripts, blocks, categories and binary properties</th></tr>
- * * <tr><td valign="top" headers="construct unicode"><tt>\p{IsLatin}</tt></td>
+ * * <tr><td valign="top" headers="construct unicode">{@code \p{IsLatin}}</td>
* <td headers="matches">A Latin script character (<a href="#usc">script</a>)</td></tr>
- * <tr><td valign="top" headers="construct unicode"><tt>\p{InGreek}</tt></td>
+ * <tr><td valign="top" headers="construct unicode">{@code \p{InGreek}}</td>
* <td headers="matches">A character in the Greek block (<a href="#ubc">block</a>)</td></tr>
- * <tr><td valign="top" headers="construct unicode"><tt>\p{Lu}</tt></td>
+ * <tr><td valign="top" headers="construct unicode">{@code \p{Lu}}</td>
* <td headers="matches">An uppercase letter (<a href="#ucc">category</a>)</td></tr>
- * <tr><td valign="top" headers="construct unicode"><tt>\p{IsAlphabetic}</tt></td>
+ * <tr><td valign="top" headers="construct unicode">{@code \p{IsAlphabetic}}</td>
* <td headers="matches">An alphabetic character (<a href="#ubpc">binary property</a>)</td></tr>
- * <tr><td valign="top" headers="construct unicode"><tt>\p{Sc}</tt></td>
+ * <tr><td valign="top" headers="construct unicode">{@code \p{Sc}}</td>
* <td headers="matches">A currency symbol</td></tr>
- * <tr><td valign="top" headers="construct unicode"><tt>\P{InGreek}</tt></td>
+ * <tr><td valign="top" headers="construct unicode">{@code \P{InGreek}}</td>
* <td headers="matches">Any character except one in the Greek block (negation)</td></tr>
- * <tr><td valign="top" headers="construct unicode"><tt>[\p{L}&&[^\p{Lu}]] </tt></td>
+ * <tr><td valign="top" headers="construct unicode">{@code [\p{L}&&[^\p{Lu}]]}</td>
* <td headers="matches">Any letter except an uppercase letter (subtraction)</td></tr>
*
* <tr><th> </th></tr>
* <tr align="left"><th colspan="2" id="bounds">Boundary matchers</th></tr>
*
@@ -374,12 +373,11 @@
* </table>
*
* <hr>
*
*
- * <a name="bs">
- * <h4> Backslashes, escapes, and quoting </h4>
+ * <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
@@ -403,12 +401,11 @@
* word boundary. The string literal <tt>"\(hello\)"</tt> is illegal
* and leads to a compile-time error; in order to match the string
* <tt>(hello)</tt> the string literal <tt>"\\(hello\\)"</tt>
* must be used.
*
- * <a name="cc">
- * <h4> Character Classes </h4>
+ * <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
@@ -433,21 +430,20 @@
* <tr><th>4 </th>
* <td>Union</td>
* <td><tt>[a-e][i-u]</tt></td></tr>
* <tr><th>5 </th>
* <td>Intersection</td>
- * <td><tt>[a-z&&[aeiou]]</tt></td></tr>
+ * <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.
*
- * <a name="lt">
- * <h4> Line terminators </h4>
+ * <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:
*
@@ -478,15 +474,13 @@
* of the entire input sequence. If {@link #MULTILINE} mode is activated then
* <tt>^</tt> matches at the beginning of input and after any line terminator
* except at the end of input. When in {@link #MULTILINE} mode <tt>$</tt>
* matches just before a line terminator or the end of the input sequence.
*
- * <a name="cg">
- * <h4> Groups and capturing </h4>
+ * <h3><a name="cg">Groups and capturing</a></h3>
*
- * <a name="gnumber">
- * <h5> Group number </h5>
+ * <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">
@@ -505,12 +499,11 @@
* <p> Capturing groups are so named because, during a match, each subsequence
* of the input sequence that matches such a group is saved. The captured
* subsequence may be used later in the expression, via a back reference, and
* may also be retrieved from the matcher once the match operation is complete.
*
- * <a name="groupname">
- * <h5> Group name </h5>
+ * <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>
@@ -535,11 +528,11 @@
*
* <p> Groups beginning with <tt>(?</tt> are either pure, <i>non-capturing</i> groups
* that do not capture text and do not count towards the group total, or
* <i>named-capturing</i> group.
*
- * <h4> Unicode support </h4>
+ * <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.
@@ -566,31 +559,31 @@
* the input has the property <i>prop</i>, while <tt>\P{</tt><i>prop</i><tt>}</tt>
* does not match if the input has that property.
* <p>
* Scripts, blocks, categories and binary properties can be used both inside
* and outside of a character class.
- * <a name="usc">
+ *
* <p>
- * <b>Scripts</b> are specified either with the prefix {@code Is}, as in
+ * <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}.
- * <a name="ubc">
+ *
* <p>
- * <b>Blocks</b> are specified with the prefix {@code In}, as in
+ * <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>
- * <a name="ucc">
- * <b>Categories</b> may be specified with the optional prefix {@code Is}:
+ *
+ * <b><a name="ucc">Categories</a></b> may be specified with the optional prefix {@code Is}:
* Both {@code \p{L}} and {@code \p{IsL}} denote the category of Unicode
* letters. Same as scripts and blocks, categories can also be specified
* by using the keyword {@code general_category} (or its short form
* {@code gc}) as in {@code general_category=Lu} or {@code gc=Lu}.
* <p>
@@ -598,12 +591,12 @@
* <a href="http://www.unicode.org/unicode/standard/standard.html">
* <i>The Unicode Standard</i></a> in the version specified by the
* {@link java.lang.Character Character} class. The category names are those
* defined in the Standard, both normative and informative.
* <p>
- * <a name="ubpc">
- * <b>Binary properties</b> are specified with the prefix {@code Is}, as in
+ *
+ * <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
@@ -627,12 +620,12 @@
* </i></a>, when {@link #UNICODE_CHARACTER_CLASS} flag is specified.
* <p>
* <table border="0" cellpadding="1" cellspacing="0"
* summary="predefined and posix character classes in Unicode mode">
* <tr align="left">
- * <th bgcolor="#CCCCFF" align="left" id="classes">Classes</th>
- * <th bgcolor="#CCCCFF" align="left" id="matches">Matches</th>
+ * <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>
@@ -647,13 +640,13 @@
* <tr><td><tt>\p{Punct}</tt></td>
* <td>A punctuation character:<tt>p{IsPunctuation}</tt></td></tr>
* <tr><td><tt>\p{Graph}</tt></td>
* <td>A visible character: <tt>[^\p{IsWhite_Space}\p{gc=Cc}\p{gc=Cs}\p{gc=Cn}]</tt></td></tr>
* <tr><td><tt>\p{Print}</tt></td>
- * <td>A printable character: <tt>[\p{Graph}\p{Blank}&&[^\p{Cntrl}]]</tt></td></tr>
+ * <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: <tt>[\p{IsWhite_Space}&&[^\p{gc=Zl}\p{gc=Zp}\x0a\x0b\x0c\x0d\x85]]</tt></td></tr>
+ * <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>
@@ -674,13 +667,13 @@
* <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>.
+ * the specified property has the name <tt>java<i>methodname</i></tt></a>.
*
- * <h4> Comparison to Perl 5 </h4>
+ * <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>
@@ -1021,25 +1014,25 @@
* (2) There is complement node of Category or Block
*/
private transient boolean hasSupplementary;
/**
- * Compiles the given regular expression into a pattern. </p>
+ * Compiles the given regular expression into a pattern.
*
* @param regex
* The expression to be compiled
- *
+ * @return the given regular expression compiled into a pattern
* @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>
+ * flags.
*
* @param regex
* The expression to be compiled
*
* @param flags
@@ -1047,10 +1040,11 @@
* {@link #CASE_INSENSITIVE}, {@link #MULTILINE}, {@link #DOTALL},
* {@link #UNICODE_CASE}, {@link #CANON_EQ}, {@link #UNIX_LINES},
* {@link #LITERAL}, {@link #UNICODE_CHARACTER_CLASS}
* and {@link #COMMENTS}
*
+ * @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
@@ -1060,11 +1054,10 @@
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;
@@ -1082,11 +1075,10 @@
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
@@ -1101,11 +1093,11 @@
Matcher m = new Matcher(this, input);
return m;
}
/**
- * Returns this pattern's match flags. </p>
+ * Returns this pattern's match flags.
*
* @return The match flags specified when this pattern was compiled
*/
public int flags() {
return flags;
@@ -1131,11 +1123,11 @@
* @param regex
* The expression to be compiled
*
* @param input
* The character sequence to be matched
- *
+ * @return whether or not the regular expression matches on the input
* @throws PatternSyntaxException
* If the expression's syntax is invalid
*/
public static boolean matches(String regex, CharSequence input) {
Pattern p = Pattern.compile(regex);
@@ -1168,13 +1160,13 @@
* <p> The input <tt>"boo:and:foo"</tt>, for example, yields the following
* results with these parameters:
*
* <blockquote><table cellpadding=1 cellspacing=0
* summary="Split examples showing regex, limit, and result">
- * <tr><th><P align="left"><i>Regex </i></th>
- * <th><P align="left"><i>Limit </i></th>
- * <th><P align="left"><i>Result </i></th></tr>
+ * <tr><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>
@@ -1251,12 +1243,12 @@
* <p> The input <tt>"boo:and:foo"</tt>, for example, yields the following
* results with these expressions:
*
* <blockquote><table cellpadding=1 cellspacing=0
* summary="Split examples showing regex and result">
- * <tr><th><P align="left"><i>Regex </i></th>
- * <th><P align="left"><i>Result</i></th></tr>
+ * <tr><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>