JAVA Regex Expression

String regex = "(?<=//()//d+(?=//))";
String str = "abc(123)def(234)";
Pattern pattern = Pattern.compile(regex);
Matcher matcher = pattern.matcher(str);
while(matcher.find())
{
    System.out.println(matcher.group());
}

import java.util.regex.Matcher;
import java.util.regex.Pattern;
/**
 * @author        Der    
 * @date          2006-10-23
 * @packeage_name regex
 * 
 */
public class RegexChk
{
	public  boolean startCheck(String reg,String string)
	{
		boolean tem=false;
		
		Pattern pattern = Pattern.compile(reg);
		Matcher matcher=pattern.matcher(string);
		
		tem=matcher.matches();
		return tem;
	}
	
         /**
	 * 检验整数,适用于正整数、负整数、0，负整数不能以-0开头, 
          * 正整数不能以0开头
	 * 
	 * */
	public boolean checkNr(String nr)
	{
		String reg="^(-?)[1-9]+//d*|0";
		return startCheck(reg,nr);
	}
	/**
	 * 手机号码验证,11位，不知道详细的手机号码段，只是验证开头必须是1和位数
	 * */
	public boolean checkCellPhone(String cellPhoneNr)
	{
		String reg="^[1][//d]{10}";
		return startCheck(reg,cellPhoneNr);
	}
	
	/**
	 * 检验空白符
	 * */
	public boolean checkWhiteLine(String line)
	{
		String regex="(//s|//t|//r)+";
		
		return startCheck(regex,line);
	}
	
	
	/**
	 * 检查EMAIL地址
	 * 用户名和网站名称必须>=1位字符
	 * 地址结尾必须是以com|cn|com|cn|net|org|gov|gov.cn|edu|edu.cn结尾
	 * */
	public boolean checkEmailWithSuffix(String email)
	{
		String regex="//w+//@//w+//.(com|cn|com.cn|net|org|gov|gov.cn|edu|edu.cn)";
		
		return startCheck(regex,email);
	}
	
	
	/**
	 * 检查EMAIL地址
	 * 用户名和网站名称必须>=1位字符
	 * 地址结尾必须是2位以上，如：cn,test,com,info
	 * */
	public boolean checkEmail(String email)
	{
		String regex="//w+//@//w+//.//w{2,}";
		
		return startCheck(regex,email);
	}
	
	/**
	 * 检查邮政编码(中国),6位，第一位必须是非0开头，其他5位数字为0-9
	 * */
	public boolean checkPostcode(String postCode)
	{
		String regex="^[1-9]//d{5}";
		return startCheck(regex,postCode);
	}
	
	/**
	 * 检验用户名
	 * 取值范围为a-z,A-Z,0-9,"_",汉字，不能以"_"结尾
	 * 用户名有最小长度和最大长度限制，比如用户名必须是4-20位
	 * */
	public boolean checkUsername(String username,int min,int max)
	{
		String regex="[//w/u4e00-/u9fa5]{"+min+","+max+"}(?<!_)";
		return startCheck(regex,username);
	}
	/**
	 * 检验用户名
	 * 取值范围为a-z,A-Z,0-9,"_",汉字，不能以"_"结尾
	 * 有最小位数限制的用户名，比如：用户名最少为4位字符
	 * */
	public boolean checkUsername(String username,int min)
	{
		//[//w/u4e00-/u9fa5]{2,}?
		String regex="[//w/u4e00-/u9fa5]{"+min+",}(?<!_)";
		
		return startCheck(regex,username);
	}
	
	/**
	 * 检验用户名
	 * 取值范围为a-z,A-Z,0-9,"_",汉字
	 * 最少一位字符，最大字符位数无限制，不能以"_"结尾
	 * */
	public boolean checkUsername(String username)
	{
		String regex="[//w/u4e00-/u9fa5]+(?<!_)";
		return startCheck(regex,username);
	}
	
	/**
	 *  查看IP地址是否合法
	 * */
	public boolean checkIP(String ipAddress)
	{
		String regex="(//d{1,2}|1//d//d|2[0-4]//d|25[0-5])//." +
				     "(//d{1,2}|1//d//d|2[0-4]//d|25[0-5])//." +
				     "(//d{1,2}|1//d//d|2[0-4]//d|25[0-5])//." +
				     "(//d{1,2}|1//d//d|2[0-4]//d|25[0-5])";
		
		return startCheck(regex,ipAddress);
	}
	
	/**
	 * 验证国内电话号码
	 * 格式：010-67676767，区号长度3-4位，必须以"0"开头，号码是7-8位
	 * */
	public boolean checkPhoneNr(String phoneNr)
	{
		String regex="^[0]//d{2,3}//-//d{7,8}";
		
		return startCheck(regex,phoneNr);
	}
	
	/**
	 * 验证国内电话号码
	 * 格式：6767676, 号码位数必须是7-8位,头一位不能是"0"
	 * */
	public boolean checkPhoneNrWithoutCode(String phoneNr)
	{
		String reg="^[1-9]//d{6,7}";
		
		return startCheck(reg,phoneNr);
	}
	
	/**
	 * 验证国内电话号码
	 * 格式：0106767676，共11位或者12位，必须是0开头
	 * */
	public boolean checkPhoneNrWithoutLine(String phoneNr)
	{
		String reg="^[0]//d{10,11}";
		
		return startCheck(reg,phoneNr);
	}
	
	/**
	 * 验证国内身份证号码：15或18位，由数字组成，不能以0开头
	 * */
	public boolean checkIdCard(String idNr)
	{
		String reg="^[1-9](//d{14}|//d{17})";
		
		return startCheck(reg,idNr);
	}
	
	/**
	 * 网址验证<br>
	 * 符合类型：<br>
	 *         http://www.test.com<br>
	 *         http://163.com
	 * */
	public boolean checkWebSite(String url)
	{
		//http://www.163.com
		String reg="^(http)//://(//w+//.//w+//.//w+|//w+//.//w+)";
		
		return startCheck(reg,url);
	}

贪婪,勉强,侵占: greedy, reluctant, possesive

在贪婪、勉强和侵占三个量词间有着细微的不同。
贪婪(*, ?, +)：读入整个串，从后往前匹配
勉强(*?, ??, +?)：从前往后匹配
侵占(*+, ?+, ++)：读入整个串，从前往后匹配，匹配的是整个串
贪婪量词之所以称之为“贪婪的”，这是由于它们强迫匹配器读入（或者称之为吃掉）整个输入的字符串，来优先尝试第一次匹配，如果第一次尝试匹配（对于整个输入的字符串）失败，匹配器会通过回退整个字符串的一个字符再一次进行尝试，不断地进行处理直到找到一个匹配，或者左边没有更多的字符来用于回退了。赖于在表达式中使用的量词，最终它将尝试地靠着 1 或 0 个字符的匹配。
但是，勉强量词采用相反的途径：从输入字符串的开始处开始，因此每次勉强地吞噬一个字符来寻找匹配，最终它们会尝试整个输入的字符串。
最后，侵占量词始终是吞掉整个输入的字符串，尝试着一次（仅有一次）匹配。不像贪婪量词那样，侵占量词绝不会回退，即使这样做是允许全部的匹配成功。

link: http://download.oracle.com/javase/tutorial/essential/regex/matcher.html

============================================================

JAVA中也有个类java.util.regex.Pattern实现正则表达式, 下面是引用jdk5的api说明：

Summary of regular-expression constructs
Construct Matches

Characters
x The character x
// The backslash character
/0n The character with octal value 0n (0 <= n <= 7)
/0nn The character with octal value 0nn (0 <= n <= 7)
/0mnn The character with octal value 0mnn (0 <= m <= 3, 0 <= n <= 7)
/xhh The character with hexadecimal value 0xhh
/uhhhh The character with hexadecimal value 0xhhhh
/t The tab character ('/u0009')
/n The newline (line feed) character ('/u000A')
/r The carriage-return character ('/u000D')
/f The form-feed character ('/u000C')
/a The alert (bell) character ('/u0007')
/e The escape character ('/u001B')
/cx The control character corresponding to x

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)

Predefined character classes
. Any character (may or may not match line terminators)
/d A digit: [0-9]
/D A non-digit: [^0-9]
/s A whitespace character: [ /t/n/x0B/f/r]
/S A non-whitespace character: [^/s]
/w A word character: [a-zA-Z_0-9]
/W A non-word character: [^/w]

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]

java.lang.Character classes (simple java character type)
/p{javaLowerCase} Equivalent to java.lang.Character.isLowerCase()
/p{javaUpperCase} Equivalent to java.lang.Character.isUpperCase()
/p{javaWhitespace} Equivalent to java.lang.Character.isWhitespace()
/p{javaMirrored} Equivalent to java.lang.Character.isMirrored()

Classes for Unicode blocks and categories
/p{InGreek} A character in the Greek block (simple block)
/p{Lu} An uppercase letter (simple category)
/p{Sc} A currency symbol
/P{InGreek} Any character except one in the Greek block (negation)
[/p{L}&&[^/p{Lu}]]Any letter except an uppercase letter (subtraction)

Boundary matchers
^ The beginning of a line
$ The end of a line
/b A word boundary
/B A non-word boundary
/A The beginning of the input
/G The end of the previous match
/Z The end of the input but for the final terminator, if any
/z The end of the input

Greedy quantifiers
X? X, once or not at all
X* X, zero or more times
X+ X, one or more times
X{n} X, exactly n times
X{n,} X, at least n times
X{n,m} X, at least n but not more than m times

Reluctant quantifiers
X?? X, once or not at all
X*? X, zero or more times
X+? X, one or more times
X{n}? X, exactly n times
X{n,}? X, at least n times
X{n,m}? X, at least n but not more than m times

Possessive quantifiers
X?+ X, once or not at all
X*+ X, zero or more times
X++ X, one or more times
X{n}+ X, exactly n times
X{n,}+ X, at least n times
X{n,m}+ X, at least n but not more than m times

Logical operators
XY X followed by Y
X|Y Either X or Y
(X) X, as a capturing group

Back references
/n Whatever the nth capturing group matched

Quotation
/ Nothing, but quotes the following character
/Q Nothing, but quotes all characters until /E
/E Nothing, but ends quoting started by /Q

Special constructs (non-capturing)
(?:X) X, as a non-capturing group
(?idmsux-idmsux)Nothing, but turns match flags on - off
(?idmsux-idmsux:X) X, as a non-capturing group with the given flags on - off
(?=X) X, via zero-width positive lookahead
(?!X) X, via zero-width negative lookahead
(?<=X) X, via zero-width positive lookbehind
(?<!X) X, via zero-width negative lookbehind
(?>X) X, as an independent, non-capturing group

--------------------------------------------------------------------------------

Backslashes, escapes, and quoting
The backslash character ('/') 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 // matches a single backslash and /{ matches a left brace.

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 prior to a non-alphabetic character regardless of whether that character is part of an unescaped construct.

Backslashes within string literals in Java source code are interpreted as required by the Java Language Specification as either Unicode escapes or other character escapes. 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 "/b", for example, matches a single backspace character when interpreted as a regular expression, while "//b" matches a word boundary. The string literal "/(hello/)" is illegal and leads to a compile-time error; in order to match the string (hello) the string literal "//(hello//)" must be used.

Character Classes
Character classes may appear within other character classes, and may be composed by the union operator (implicit) and the intersection operator (&&). 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.

The precedence of character-class operators is as follows, from highest to lowest:

1 Literal escape /x
2 Grouping [...]
3 Range a-z
4 Union [a-e][i-u]
5 Intersection [a-z&&[aeiou]]

Note that a different set of metacharacters are in effect inside a character class than outside a character class. For instance, the regular expression . loses its special meaning inside a character class, while the expression - becomes a range forming metacharacter.

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 recognized as line terminators:

A newline (line feed) character ('/n'),
A carriage-return character followed immediately by a newline character ("/r/n"),
A standalone carriage-return character ('/r'),
A next-line character ('/u0085'),
A line-separator character ('/u2028'), or
A paragraph-separator character ('/u2029).
If UNIX_LINES mode is activated, then the only line terminators recognized are newline characters.

The regular expression . matches any character except a line terminator unless the DOTALL flag is specified.

By default, the regular expressions ^ and $ ignore line terminators and only match at the beginning and the end, respectively, of the entire input sequence. If MULTILINE mode is activated then ^ matches at the beginning of input and after any line terminator except at the end of input. When in MULTILINE mode $ matches just before a line terminator or the end of the input sequence.

Groups and capturing
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:

1 ((A)(B(C)))
2 (A)
3 (B(C))
4 (C)

Group zero always stands for the entire expression.

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.

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 "aba" against the expression (a(b)?)+, for example, leaves group two set to "b". All captured input is discarded at the beginning of each match.

Groups beginning with (? are pure, non-capturing groups that do not capture text and do not count towards the group total.

Unicode support
This class is in conformance with Level 1 of Unicode Technical Standard #18: Unicode Regular Expression Guidelines, plus RL2.1 Canonical Equivalents.

Unicode escape sequences such as /u2014 in Java source code are processed as described in ?.3 of the Java Language Specification. 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 "/u2014" and "//u2014", while not equal, compile into the same pattern, which matches the character with hexadecimal value 0x2014.

Unicode blocks and categories are written with the /p and /P constructs as in Perl. /p{prop} matches if the input has the property prop, while /P{prop} does not match if the input has that property. Blocks are specified with the prefix In, as in InMongolian. Categories may be specified with the optional prefix Is: Both /p{L} and /p{IsL} denote the category of Unicode letters. Blocks and categories can be used both inside and outside of a character class.

The supported categories are those of The Unicode Standard in the version specified by the Character class. The category names are those defined in the Standard, both normative and informative. The block names supported by Pattern are the valid block names accepted and defined by UnicodeBlock.forName.

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.

Comparison to Perl 5
The Pattern engine performs traditional NFA-based matching with ordered alternation as occurs in Perl 5.

Perl constructs not supported by this class:

The conditional constructs (?{X}) and (?(condition)X|Y),

The embedded code constructs (?{code}) and (??{code}),

The embedded comment syntax (?#comment), and

The preprocessing operations /l /u, /L, and /U.

Constructs supported by this class but not by Perl:

Possessive quantifiers, which greedily match as much as they can and do not back off, even when doing so would allow the overall match to succeed.

Character-class union and intersection as described above.

Notable differences from Perl:

In Perl, /1 through /9 are always interpreted as back references; a backslash-escaped number greater than 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, /1 through /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.

Perl uses the g flag to request a match that resumes where the last match left off. This functionality is provided implicitly by the Matcher class: Repeated invocations of the find method will resume where the last match left off, unless the matcher is reset.

In Perl, embedded flags at the top level of an expression affect the whole expression. In this class, embedded flags always take effect at the point at which they appear, whether they are at the top level or within a group; in the latter case, flags are restored at the end of the group just as in Perl.

Perl is forgiving about malformed matching constructs, as in the expression *a, as well as dangling brackets, as in the expression abc], and treats them as literals. This class also accepts dangling brackets but is strict about dangling metacharacters like +, ? and *, and will throw a PatternSyntaxException if it encounters them.