--- old/src/share/classes/java/util/regex/MatchResult.java 2013-07-08 22:34:00.000000000 -0700 +++ new/src/share/classes/java/util/regex/MatchResult.java 2013-07-08 22:34:00.000000000 -0700 @@ -1,5 +1,5 @@ /* - * Copyright (c) 2003, 2004, Oracle and/or its affiliates. All rights reserved. + * Copyright (c) 2003, 2013, Oracle and/or its affiliates. All rights reserved. * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. * * This code is free software; you can redistribute it and/or modify it @@ -77,7 +77,7 @@ public int start(int group); /** - * Returns the offset after the last character matched.
+ * Returns the offset after the last character matched. * * @return The offset after the last character matched * --- old/src/share/classes/java/util/regex/Matcher.java 2013-07-08 22:34:01.000000000 -0700 +++ new/src/share/classes/java/util/regex/Matcher.java 2013-07-08 22:34:01.000000000 -0700 @@ -1,5 +1,5 @@ /* - * Copyright (c) 1999, 2012, Oracle and/or its affiliates. All rights reserved. + * Copyright (c) 1999, 2013, Oracle and/or its affiliates. All rights reserved. * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. * * This code is free software; you can redistribute it and/or modify it @@ -28,8 +28,8 @@ import java.util.Objects; /** - * An engine that performs match operations on a {@link java.lang.CharSequence - * character sequence} by interpreting a {@link Pattern}.
+ * An engine that performs match operations on a {@linkplain java.lang.CharSequence
+ * character sequence} by interpreting a {@link Pattern}.
*
* A matcher is created from a pattern by invoking the pattern's {@link
* Pattern#matcher matcher} method. Once created, a matcher can be used to
@@ -330,7 +330,7 @@
}
/**
- * Returns the start index of the previous match.
+ * Returns the start index of the previous match.
*
* @return The index of the first character matched
*
@@ -402,7 +402,7 @@
}
/**
- * Returns the offset after the last character matched.
+ * Returns the offset after the last character matched.
*
* @return The offset after the last character matched
*
@@ -647,6 +647,7 @@
* invocations of the {@link #find()} method will start at the first
* character not matched by this match.
*
+ * @param start the index to start searching for a match
* @throws IndexOutOfBoundsException
* If start is less than zero or if start is greater than the
* length of the input sequence.
@@ -736,8 +737,8 @@
* captured during the previous match: Each occurrence of
* ${name} or $g
* will be replaced by the result of evaluating the corresponding
- * {@link #group(String) group(name)} or {@link #group(int) group(g)}
- * respectively. For $g,
+ * {@link #group(String) group(name)} or {@link #group(int) group(g)}
+ * respectively. For $g,
* the first number after the $ is always treated as part of
* the group reference. Subsequent numbers are incorporated into g if
* they would form a legal group reference. Only the numerals '0'
--- old/src/share/classes/java/util/regex/Pattern.java 2013-07-08 22:34:01.000000000 -0700
+++ new/src/share/classes/java/util/regex/Pattern.java 2013-07-08 22:34:01.000000000 -0700
@@ -45,8 +45,8 @@
*
* 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
character sequences} 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.
*
@@ -73,15 +73,14 @@
* such use.
*
*
- *
- * Summary of regular-expression constructs
+ * Summary of regular-expression constructs
*
*
*
*
- * Construct
- * Matches
+ * Construct
+ * Matches
*
*
*
@@ -128,24 +127,24 @@
*
* Character classes
*
- * [abc]
- * a, b, or c (simple class)
- * [^abc]
- * Any character except a, b, or c (negation)
- * [a-zA-Z]
- * a through z
- * or A through Z, inclusive (range)
- * [a-d[m-p]]
- * a through d,
- * or m through p: [a-dm-p] (union)
- * [a-z&&[def]]
- * d, e, or f (intersection)
- * [a-z&&[^bc]]
- * a through z,
- * except for b and c: [ad-z] (subtraction)
- * [a-z&&[^m-p]]
- * a through z,
- * and not m through p: [a-lq-z](subtraction)
+ * {@code [abc]}
+ * {@code a}, {@code b}, or {@code c} (simple class)
+ * {@code [^abc]}
+ * Any character except {@code a}, {@code b}, or {@code c} (negation)
+ * {@code [a-zA-Z]}
+ * {@code a} through {@code z}
+ * or {@code A} through {@code Z}, inclusive (range)
+ * {@code [a-d[m-p]]}
+ * {@code a} through {@code d},
+ * or {@code m} through {@code p}: {@code [a-dm-p]} (union)
+ * {@code [a-z&&[def]]}
+ * {@code d}, {@code e}, or {@code f} (intersection)
+ * {@code [a-z&&[^bc]]}
+ * {@code a} through {@code z},
+ * except for {@code b} and {@code c}: {@code [ad-z]} (subtraction)
+ * {@code [a-z&&[^m-p]]}
+ * {@code a} through {@code z},
+ * and not {@code m} through {@code p}: {@code [a-lq-z]}(subtraction)
*
*
* Predefined character classes
@@ -175,36 +174,36 @@
* \W
* A non-word character: [^\w]
*
- * POSIX character classes (US-ASCII only)
+ * POSIX character classes (US-ASCII only)
*
- * \p{Lower}
- * A lower-case alphabetic character: [a-z]
- * \p{Upper}
- * An upper-case alphabetic character:[A-Z]
- * \p{ASCII}
- * All ASCII:[\x00-\x7F]
- * \p{Alpha}
- * An alphabetic character:[\p{Lower}\p{Upper}]
- * \p{Digit}
- * A decimal digit: [0-9]
- * \p{Alnum}
- * An alphanumeric character:[\p{Alpha}\p{Digit}]
- * \p{Punct}
- * Punctuation: One of !"#$%&'()*+,-./:;<=>?@[\]^_`{|}~
- *
- * \p{Graph}
- * A visible character: [\p{Alnum}\p{Punct}]
- * \p{Print}
- * A printable character: [\p{Graph}\x20]
- * \p{Blank}
- * A space or a tab: [ \t]
- * \p{Cntrl}
- * A control character: [\x00-\x1F\x7F]
- * \p{XDigit}
- * A hexadecimal digit: [0-9a-fA-F]
- * \p{Space}
- * A whitespace character: [ \t\n\x0B\f\r]
+ * {@code \p{Lower}}
+ * A lower-case alphabetic character: {@code [a-z]}
+ * {@code \p{Upper}}
+ * An upper-case alphabetic character:{@code [A-Z]}
+ * {@code \p{ASCII}}
+ * All ASCII:{@code [\x00-\x7F]}
+ * {@code \p{Alpha}}
+ * An alphabetic character:{@code [\p{Lower}\p{Upper}]}
+ * {@code \p{Digit}}
+ * A decimal digit: {@code [0-9]}
+ * {@code \p{Alnum}}
+ * An alphanumeric character:{@code [\p{Alpha}\p{Digit}]}
+ * {@code \p{Punct}}
+ * Punctuation: One of {@code !"#$%&'()*+,-./:;<=>?@[\]^_`{|}~}
+ *
+ * {@code \p{Graph}}
+ * A visible character: {@code [\p{Alnum}\p{Punct}]}
+ * {@code \p{Print}}
+ * A printable character: {@code [\p{Graph}\x20]}
+ * {@code \p{Blank}}
+ * A space or a tab: {@code [ \t]}
+ * {@code \p{Cntrl}}
+ * A control character: {@code [\x00-\x1F\x7F]}
+ * {@code \p{XDigit}}
+ * A hexadecimal digit: {@code [0-9a-fA-F]}
+ * {@code \p{Space}}
+ * A whitespace character: {@code [ \t\n\x0B\f\r]}
*
*
* java.lang.Character classes (simple java character type)
@@ -220,19 +219,19 @@
*
*
* Classes for Unicode scripts, blocks, categories and binary properties
- * * \p{IsLatin}
+ * * {@code \p{IsLatin}}
* A Latin script character (script)
- * \p{InGreek}
+ * {@code \p{InGreek}}
* A character in the Greek block (block)
- * \p{Lu}
+ * {@code \p{Lu}}
* An uppercase letter (category)
- * \p{IsAlphabetic}
+ * {@code \p{IsAlphabetic}}
* An alphabetic character (binary property)
- * \p{Sc}
+ * {@code \p{Sc}}
* A currency symbol
- * \P{InGreek}
+ * {@code \P{InGreek}}
* Any character except one in the Greek block (negation)
- * [\p{L}&&[^\p{Lu}]]
+ * {@code [\p{L}&&[^\p{Lu}]]}
* Any letter except an uppercase letter (subtraction)
*
*
@@ -376,8 +375,7 @@
*
*
*
- *
- * Backslashes, escapes, and quoting
+ * Backslashes, escapes, and quoting
*
* The backslash character ('\') serves to introduce escaped
* constructs, as defined in the table above, as well as to quote characters
@@ -405,8 +403,7 @@
* (hello) the string literal "\\(hello\\)"
* must be used.
*
- *
- * Character Classes
+ * Character Classes
*
* Character classes may appear within other character classes, and
* may be composed by the union operator (implicit) and the intersection
@@ -435,7 +432,7 @@
*
[a-e][i-u]
* 5
* Intersection
- * [a-z&&[aeiou]]
+ * {@code [a-z&&[aeiou]]}
*
*
* Note that a different set of metacharacters are in effect inside
@@ -444,8 +441,7 @@
* character class, while the expression - becomes a range
* forming metacharacter.
*
- *
- * Line terminators
+ * Line terminators
*
* A line terminator is a one- or two-character sequence that marks
* the end of a line of the input character sequence. The following are
@@ -480,11 +476,9 @@
* except at the end of input. When in {@link #MULTILINE} mode $
* matches just before a line terminator or the end of the input sequence.
*
- *
- * Groups and capturing
+ * Groups and capturing
*
- *
- * Group number
+ * Group number
* Capturing groups are numbered by counting their opening parentheses from
* left to right. In the expression ((A)(B(C))), for example, there
* are four such groups:
@@ -507,8 +501,7 @@
* 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.
*
- *
- * Group name
+ * Group name
* A capturing group can also be assigned a "name", a 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 letter.
@@ -537,7 +530,7 @@
* that do not capture text and do not count towards the group total, or
* named-capturing group.
*
- *
Unicode support
+ * Unicode support
*
* This class is in conformance with Level 1 of Unicode Technical
@@ -568,18 +561,18 @@
*
* Scripts, blocks, categories and binary properties can be used both inside
* and outside of a character class.
- *
+ *
*
- * Scripts are specified either with the prefix {@code Is}, as in
+ * Scripts 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}.
*
* The script names supported by Pattern
are the valid script names
* accepted and defined by
* {@link java.lang.Character.UnicodeScript#forName(String) UnicodeScript.forName}.
- *
+ *
*
- * Blocks are specified with the prefix {@code In}, as in
+ * Blocks 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}.
*
@@ -587,8 +580,8 @@
* accepted and defined by
* {@link java.lang.Character.UnicodeBlock#forName(String) UnicodeBlock.forName}.
*
- *
- * Categories may be specified with the optional prefix {@code Is}:
+ *
+ * Categories 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
@@ -600,8 +593,8 @@
* {@link java.lang.Character Character} class. The category names are those
* defined in the Standard, both normative and informative.
*
- *
- * Binary properties are specified with the prefix {@code Is}, as in
+ *
+ * Binary properties are specified with the prefix {@code Is}, as in
* {@code IsAlphabetic}. The supported binary properties by Pattern
* are
*
@@ -629,8 +622,8 @@
*
*
- * Classes
- * Matches
+ * Classes
+ * Matches
*
* \p{Lower}
* A lowercase character:\p{IsLowercase}
@@ -649,9 +642,9 @@
* \p{Graph}
* A visible character: [^\p{IsWhite_Space}\p{gc=Cc}\p{gc=Cs}\p{gc=Cn}]
* \p{Print}
- * A printable character: [\p{Graph}\p{Blank}&&[^\p{Cntrl}]]
+ * A printable character: {@code [\p{Graph}\p{Blank}&&[^\p{Cntrl}]]}
* \p{Blank}
- * A space or a tab: [\p{IsWhite_Space}&&[^\p{gc=Zl}\p{gc=Zp}\x0a\x0b\x0c\x0d\x85]]
+ * A space or a tab: {@code [\p{IsWhite_Space}&&[^\p{gc=Zl}\p{gc=Zp}\x0a\x0b\x0c\x0d\x85]]}
* \p{Cntrl}
* A control character: \p{gc=Cc}
* \p{XDigit}
@@ -676,9 +669,9 @@
* Categories that behave like the java.lang.Character
* boolean ismethodname methods (except for the deprecated ones) are
* available through the same \p{prop} syntax where
- * the specified property has the name javamethodname.
+ * the specified property has the name javamethodname.
*
- * Comparison to Perl 5
+ * Comparison to Perl 5
*
* The Pattern
engine performs traditional NFA-based matching
* with ordered alternation as occurs in Perl 5.
@@ -1023,11 +1016,11 @@
private transient boolean hasSupplementary;
/**
- * Compiles the given regular expression into a pattern.
+ * 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
*/
@@ -1037,7 +1030,7 @@
/**
* Compiles the given regular expression into a pattern with the given
- * flags.
+ * flags.
*
* @param regex
* The expression to be compiled
@@ -1049,6 +1042,7 @@
* {@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 flags
@@ -1062,7 +1056,6 @@
/**
* Returns the regular expression from which this pattern was compiled.
- *
*
* @return The source of this pattern
*/
@@ -1084,7 +1077,6 @@
/**
* Creates a matcher that will match the given input against this pattern.
- *
*
* @param input
* The character sequence to be matched
@@ -1103,7 +1095,7 @@
}
/**
- * Returns this pattern's match flags.
+ * Returns this pattern's match flags.
*
* @return The match flags specified when this pattern was compiled
*/
@@ -1133,7 +1125,7 @@
*
* @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
*/
@@ -1170,9 +1162,9 @@
*
*
- * Regex
- * Limit
- * Result
+ * Regex
+ * Limit
+ * Result
* :
* 2
* { "boo", "and:foo" }
@@ -1253,8 +1245,8 @@
*
*
- * Regex
- * Result
+ * Regex
+ * Result
* :
* { "boo", "and", "foo" }
* o