javascript正则表达式简介

 

 

javascript正则表达式

javascript正则表达式

regular expression是一个描述字符模式的对象；
ECMAScript中的RegExp类表示正则表达式；
String和RegExp都定义了使用正则表达式进行强大的模式匹配、文本检索和替换的函数；
正则表达式主要用来验证客户端的输入数据；

 

Ⅰ.创建正则表达式

类似于创建字符串，可以使用new运算符也可以采用字面值；

参数	含义
g	全局匹配
i	忽略大小写
m	多行匹配

下文中的javascript代码是通过 EclipseKepler 的 rhino 解释的
代码如下：

 　 

/**
* new运算符创建正则表达式
*/
var box1 =newRegExp('box');//第一个参数是模式字符串
print('box1 = '+ box1);
var box2 =newRegExp('box','gim');//第二个参数是模式修饰符
print('box2 = '+ box2);


/**
* 字面值创建正则表达式
*/
var box3 =/Box/;//字面值方式的正则表达式
print('box3 = '+ box3);
var box4 =/Box/ig;//在第二个斜杠后加上模式修饰符
print('box4 = '+ box4);

 

运行结果如下：

box1 = /box/
box2 = /box/gim
box3 = /Box/
box4 = /Box/gi

 

Ⅱ.测试正则表达式

RegExp对象包含两个方法，test()和exec()

方法	功能
test	在字符串中测试模式匹配，返回true或false
exec	在字符串中执行匹配搜索，返回结果数组

代码如下：

 

/**
* new创建的正则表达式的test
*/
var pattern =newRegExp('box');//验证test
var str1 ='box';
var str2 ='Box';
print('pattern.test(str1) = '+ pattern.test(str1));
print('pattern.test(str2) = '+ pattern.test(str2));
var pattern2 =newRegExp('box','i');//不区分大小写
print('pattern2.test(str1) = '+ pattern2.test(str1));
print('pattern2.test(str2) = '+ pattern2.test(str2));


/**
* 使用一条语句实现的正则匹配
*/
var pattern3 =/box/i;
var str3 ='This is a Box';
print("pattern3.test(str3) = "+ pattern3.test(str3));
print("/box/i.test('This is a Box') = "+/box/i.test('This is a Box'));


/**
* exec方法
* 返回匹配到的字符串数组，如果没有就返回null
*/
var pattern4 =/box/i;
var ret1 = pattern4.exec(str3);
print("ret1 = "+ ret1);
print("typeof ret1 = "+typeof ret1);
var str4 ='ssss';
var ret2 = pattern4.exec(str4);
print("ret2 = "+ ret2);
print("typeof ret2 = "+typeof ret2);
print("typeof null = "+typeofnull);

 

运行结果如下：

pattern.test(str1) = true
pattern.test(str2) = false
pattern2.test(str1) = true
pattern2.test(str2) = true
pattern3.test(str3) = true
/box/i.test('This is a Box') = true
ret1 = Box
typeof ret1 = object
ret2 = null
typeof ret2 = object
typeof null = object

 

Ⅲ.字符串的正则表达式方法

String对象提供了4个使用正则表达式的方法

方法	含义
match(pattern)	返回pattern中的子串或null
search(pattern)	返回字符串中pattern的开始位置
replace(pattern, replacement)	用replacement替换pattern
split(pattern)	返回字符串按指定pattern拆分的数组

代码如下：

 

/**
* match方法
* 如果不开启全局就只返回匹配到的第一个字符串
* 如果开启全局就返回所有的被匹配字符串数组
*/
var pattern1 =/box/;
var pattern2 =/box/g;//开启全局
var str ='This is a box, That is a box!';
print("str.match(pattern1) = "+ str.match(pattern1));
var ret1 = str.match(pattern2);
print("ret1 = "+ ret1);
print("ret1[0] = "+ ret1[0]);


/**
* search方法
* 返回第一个匹配的位置，这里没有必要设置全局
* 找不到返回-1
*/
var pattern3 =/box/;
var ret2 = str.search(pattern3);
print("ret2 = "+ ret2);
print("'This is a BOX!'.search(pattern3) = "+'This is a BOX!'.search(pattern3));


/**
* replace方法
* 需要设置全局才会替换所有匹配到的字符串
*/
var str2 ='This is a box, That is a Box!';
var pattern4 =/box/i;
var pattern5 =/box/ig;
var replacement ='tom';
var ret3 = str.replace(pattern4, replacement);
var ret4 = str.replace(pattern5, replacement);
print("ret3 = "+ ret3);
print("ret4 = "+ ret4);


/**
* split方法
*/
var str3 ='This is a box! That is a Box!';
var pattern6 =/!/g;
var pattern7 =/ /g;
var ret5 = str3.split(pattern6);
var ret6 = str3.split(pattern7);
print("ret5 = "+ ret5);
print("ret5.length = "+ ret5.length);
print("ret6 = "+ ret6);
print("ret6.length = "+ ret6.length);

 

运行结果如下：

str.match(pattern1) = box
ret1 = box,box
ret1[0] = box
ret2 = 10
'This is a BOX!'.search(pattern3) = -1
ret3 = This is a tom, That is a box!
ret4 = This is a tom, That is a tom!
ret5 = This is a box, That is a Box,
ret5.length = 3
ret6 = This,is,a,box!,That,is,a,Box!
ret6.length = 8

 

Ⅳ.正则表达式静态属性

属性	短名	含义
input	$_	当前被匹配的字符串
lastMatch	$&	最后一个匹配字符串
lastParen	$+	最后一对圆括号内的匹配子串
leftContext	$`	最后一次匹配前的子串
rightContext	$'	上次匹配之后的子串
multiline	$*	用于指定是否所有的表达式都用于多行的布尔值

代码如下：

 

/**
* 正则表达式静态属性
*/
print("RegExp.input = "+RegExp.input);
var pattern =/google/i;
var str ='This is a google! That is a GOOGLE!';
pattern.test(str);//必须执行一下，静态属性才有效
//需要在浏览器中使用alert运行才能打印出当前的匹配字符串
print("RegExp.input = "+RegExp.input);
print("RegExp.leftContext = "+RegExp.leftContext);
print("RegExp.rightContext = "+RegExp.rightContext);
print("RegExp.lastMatch = "+RegExp.lastMatch);

var pattern2 =/(g)oogle/i;
var str2 ='This is a gogle! That is a GOOGLE!';
pattern2.test(str2);
print("RegExp.lastParen = "+RegExp.lastParen);//会打印匹配的在圆括号里字符串
print("RegExp.multiline = "+RegExp.multiline);


/**
* 所有的属性可以通过短名来操作
*/
var pattern3 =/google/i;
var str3 ='This is a google! That is a GOOGLE!';
pattern3.test(str3);
print("RegExp['$&'] = "+RegExp['$&']);
print("RegExp.$_ = "+RegExp.$_);

 

运行结果如下：

RegExp.input = 
RegExp.input = 
RegExp.leftContext = This is a 
RegExp.rightContext = ! That is a GOOGLE!
RegExp.lastMatch = google
RegExp.lastParen = G
RegExp.multiline = false
RegExp['$&'] = google
RegExp.$_ = 

 

Ⅴ.正则表达式实例属性

属性	含义
global	全局是否设置
ignoreCase	忽略大小写是否设置
multiline	多行是否设置
source	正则表达式的源字符串
lastIndex	下次匹配将从字符串的哪里开始

代码如下：

 

/**
* 正则表达式实例属性
*/
var pattern1 =/google/;
var pattern2 =/google/g;
var pattern3 =/google/ig;
var pattern4 =/google/igm;
print("pattern1.global = "+ pattern1.global);
print("pattern2.global = "+ pattern2.global);
print("pattern2.ignoreCase = "+ pattern2.ignoreCase);
print("pattern3.ignoreCase = "+ pattern3.ignoreCase);
print("pattern3.ignoreCase = "+ pattern3.multiline);
print("pattern4.ignoreCase = "+ pattern4.multiline);
print("pattern4.source = "+ pattern4.source);


/**
* lastIndex动态属性
*/
var str ='google google google';
print("pattern2.lastIndex = "+ pattern2.lastIndex);
for(var i =6;--i !=0;){
pattern2.test(str);
print("pattern2.lastIndex = "+ pattern2.lastIndex);
}
pattern2.lastIndex =100;
print("pattern2.lastIndex = "+ pattern2.lastIndex);

 

运行结果如下：

pattern1.global = false
pattern2.global = true
pattern2.ignoreCase = false
pattern3.ignoreCase = true
pattern3.ignoreCase = false
pattern4.ignoreCase = true
pattern4.source = google
pattern2.lastIndex = 0
pattern2.lastIndex = 6
pattern2.lastIndex = 13
pattern2.lastIndex = 20
pattern2.lastIndex = 0
pattern2.lastIndex = 6
pattern2.lastIndex = 100

 

Ⅵ.获取控制

正则表达式元字符是包含特殊含义的字符，
它们可以控制匹配模式的方式，
反斜杠后的元字符将失去其特殊意义。

元字符	匹配情况
.	匹配出换行符外的任意字符

 

1.点元字符，匹配除换行符外的任意字符

代码：

 

/**
* 点元字符：匹配除换行符外的任意字符
*/
var pattern1 =/g..gle/;
var str1 ='google';
print("pattern1.test(str1) = "+ pattern1.test(str1));
print("pattern1.test('g\\ngle') = "+ pattern1.test('g\ngle'));
print("pattern1.test('g12gle') = "+ pattern1.test('g12gle'));
print("pattern1.test('g3gle') = "+ pattern1.test('g3gle'));

 

运行结果：

pattern1.test(str1) = true
pattern1.test('g\ngle') = false
pattern1.test('g12gle') = true
pattern1.test('g3gle') = false

 

2.重复字符

元字符	匹配情况
x*	匹配0个或多个x
x?	匹配0个或1个x
x+	匹配1个或多个x
(xyz)+	匹配1个或多个(xyz)
x{m,n}	匹配m个到n个x

其中，前面的x也可以与点元字符一起使用，
例如：/.?/表示0个或一个任意字符

代码：

 

1. /**
2. * 重复字符
3. */
4. var pattern1 =/go*gle/;
5. var str1 ='gooooooogle';
6. print("pattern1.test(str1) = "+ pattern1.test(str1));
7. print("pattern1.test('gobbbgle') = "+ pattern1.test('gobbbgle'));
8. print("pattern1.test('go12gle') = "+/go+gle/.test('go12gle'));
9. print("pattern1.test('ggle') = "+ pattern1.test('ggle'));
11. var pattern2 =/go+gle/;
12. print("pattern2.test(str1) = "+ pattern2.test(str1));
13. print("pattern2.test('gogle') = "+ pattern2.test('gogle'));
14. print("pattern2.test('ggle') = "+ pattern2.test('ggle'));
16. var pattern3 =/go?gle/;
17. print("pattern3.test(str1) = "+ pattern3.test(str1));
18. print("pattern3.test('gogle') = "+ pattern3.test('gogle'));
19. print("pattern3.test('ggle') = "+ pattern3.test('ggle'));
20. print("pattern3.test('gXgle') = "+ pattern3.test('gXgle'));
22. var pattern4 =/g.?gle/;
23. print("pattern4.test('ggle') = "+ pattern4.test('ggle'));
24. print("pattern4.test('gXgle') = "+ pattern4.test('gXgle'));
25. print("pattern4.test('gXXgle') = "+ pattern4.test('gXXgle'));
27. var pattern5 =/go{2,4}gle/;
28. var str2 ='google';
29. print("pattern5.test(str2) = "+ pattern5.test(str2));
30. print("pattern5.test('goooogle') = "+ pattern5.test('goooogle'));
31. print("pattern5.test('gooooogle') = "+ pattern5.test('gooooogle'));
32. print("pattern5.test('ggle') = "+ pattern5.test('ggle'));
34. var pattern6 =/go{3}gle/;
35. print("pattern6.test('google') = "+ pattern6.test('google'));
36. print("pattern6.test('gooogle') = "+ pattern6.test('gooogle'));
37. print("pattern6.test('goooogle') = "+ pattern6.test('goooogle'));
39. var pattern7 =/go{3,}gle/;
40. print("pattern7.test('google') = "+ pattern7.test('google'));
41. print("pattern7.test('gooogle') = "+ pattern7.test('gooogle'));
42. print("pattern7.test('gooooooogle') = "+ pattern7.test('gooooooogle'));

运行结果：

pattern1.test(str1) = true
pattern1.test('gobbbgle') = false
pattern1.test('go12gle') = false
pattern1.test('ggle') = true
pattern2.test(str1) = true
pattern2.test('gogle') = true
pattern2.test('ggle') = false
pattern3.test(str1) = false
pattern3.test('gogle') = true
pattern3.test('ggle') = true
pattern3.test('gXgle') = false
pattern4.test('ggle') = true
pattern4.test('gXgle') = true
pattern4.test('gXXgle') = false
pattern5.test(str2) = true
pattern5.test('goooogle') = true
pattern5.test('gooooogle') = false
pattern5.test('ggle') = false
pattern6.test('google') = false
pattern6.test('gooogle') = true
pattern6.test('goooogle') = false
pattern7.test('google') = false
pattern7.test('gooogle') = true
pattern7.test('gooooooogle') = true

 

3.字符类匹配

元字符	匹配情况
.	除换行符外的任意字符
[a-z0-9]	括号中字符集中的任意字符
[^a-z0-9]	不在括号中字符集中的任意字符
\d	数字
\D	非数字
\w	字母数字下划线
\W	非字母数字下划线

代码：

 

1. /**
2. * [a-z]表示26个小写字母的任意一个
3. */
4. var pattern1 =/[a-z]oogle/;
5. var str1 ='google';
6. print("pattern1.test(str1) = "+ pattern1.test(str1));
7. print("pattern1.test('boogle') = "+ pattern1.test('boogle'));
8. print("pattern1.test('6oogle') = "+ pattern1.test('6oogle'));
10. var pattern2 =/[A-Z]oogle/;
11. print("pattern2.test(str1) = "+ pattern2.test(str1));
12. print("/[A-Z]oogle/i.test(str1) = "+/[A-Z]oogle/i.test(str1));
14. var pattern3 =/[0-9]oogle/;
15. print("pattern3.test(str1) = "+ pattern3.test(str1));
16. print("pattern3.test('4oogle') = "+ pattern3.test('4oogle'));
17. print("pattern3.test('44oogle') = "+ pattern3.test('44oogle'));
19. var pattern4 =/[0-9]*oogle/;//[0-9]*表示0个或多个数字
20. print("pattern4.test('444oogle') = "+ pattern4.test('444oogle'));
22. var pattern5 =/[a-zA-Z0-9]oogle/;
23. print("pattern5.test('boogle') = "+ pattern5.test('boogle'));
24. print("pattern5.test('Boogle') = "+ pattern5.test('Boogle'));
25. print("pattern5.test('6oogle') = "+ pattern5.test('6oogle'));
26. print("pattern5.test('oogle') = "+ pattern5.test('oogle'));
28. var pattern6 =/[^0-9]oogle/;
29. print("pattern6.test('444oogle') = "+ pattern6.test('444oogle'));
30. print("pattern6.test('_oogle') = "+ pattern6.test('_oogle'));

运行结果：

pattern1.test(str1) = true
pattern1.test('boogle') = true
pattern1.test('6oogle') = false
pattern2.test(str1) = false
/[A-Z]oogle/i.test(str1) = true
pattern3.test(str1) = false
pattern3.test('4oogle') = true
pattern3.test('44oogle') = true
pattern4.test('444oogle') = true
pattern5.test('boogle') = true
pattern5.test('Boogle') = true
pattern5.test('6oogle') = true
pattern5.test('oogle') = false
pattern6.test('444oogle') = false
pattern6.test('_oogle') = true

 

4.锚元字符

元字符	匹配情况
^	行首匹配
$	行尾匹配
\A	只有匹配字符串开始处
\b	匹配单词边界，词在[]中时无效
\G	匹配当前搜索的开始位置
\Z	匹配字符串结束处或行尾
\z	只匹配字符串结束处

代码：

 

1. /**
2. * 锚元字符
3. */
4. var pattern1 =/^[0-9]oogle/;
5. var pattern2 =/^[0-9]+oogle/;
6. var str1 ='4oogle';
7. var str2 ='4444oogle';
8. print("pattern1.test(str1) = "+ pattern1.test(str1));
9. print("pattern1.test(str2) = "+ pattern1.test(str2));
10. print("pattern2.test(str1) = "+ pattern2.test(str1));
11. print("pattern2.test(str2) = "+ pattern2.test(str2));
13. var pattern3 =/\woogle/;
14. var pattern4 =/\Woogle/;
15. print("pattern3.test('aoogle') = "+ pattern3.test('aoogle'));
16. print("pattern3.test('_oogle') = "+ pattern3.test('_oogle'));
17. print("pattern3.test('-oogle') = "+ pattern3.test('-oogle'));
18. print("pattern4.test('aoogle') = "+ pattern4.test('aoogle'));
19. print("pattern4.test('_oogle') = "+ pattern4.test('_oogle'));
20. print("pattern4.test('-oogle') = "+ pattern4.test('-oogle'));
22. var pattern5 =/\doogle/;
23. var pattern6 =/\Doogle/;
24. print("pattern5.test('aoogle') = "+ pattern5.test('aoogle'));
25. print("pattern5.test('9oogle') = "+ pattern5.test('9oogle'));
26. print("pattern6.test('aoogle') = "+ pattern6.test('aoogle'));
27. print("pattern6.test('9oogle') = "+ pattern6.test('9oogle'));
29. var pattern7 =/^google/;
30. var pattern8 =/^[a-z]oog[0-9]$/;
31. var str3 ='This is google search engine';
32. print("pattern7.test(str3) = "+ pattern7.test(str3));
33. print("pattern8.test(str3) = "+ pattern8.test(str3));
34. print("pattern8.test('google') = "+ pattern8.test('google'));
35. print("pattern8.test('goog5') = "+ pattern8.test('goog5'));

运行结果：

pattern1.test(str1) = true
pattern1.test(str2) = false
pattern2.test(str1) = true
pattern2.test(str2) = true
pattern3.test('aoogle') = true
pattern3.test('_oogle') = true
pattern3.test('-oogle') = false
pattern4.test('aoogle') = false
pattern4.test('_oogle') = false
pattern4.test('-oogle') = true
pattern5.test('aoogle') = false
pattern5.test('9oogle') = true
pattern6.test('aoogle') = true
pattern6.test('9oogle') = false
pattern7.test(str3) = false
pattern8.test(str3) = false
pattern8.test('google') = false
pattern8.test('goog5') = true

 

5.空白字符

元字符	匹配情况
\0	null
\b	空格
\f	进纸
\n	换行
\r	回车
\t	制表
\s	空白空格制表换行
\S	非空白字符

代码：

 

1. /**
2. * 空白字符
3. */
4. var pattern1 =/goo gle/;
5. var str1 ='goo gle';
6. print("pattern1.test(str1) = "+ pattern1.test(str1));
8. var pattern2 =/goo\sgle/;
9. var str2 ='goo gle';
10. print("pattern2.test(str2) = "+ pattern2.test(str2));
11. print("/goo\\bgle/.test(str2) = "+/goo\bgle/.test(str2));
13. var pattern3 =/google\b/;
14. print("pattern3.test('google') = "+ pattern3.test('google'));
15. print("pattern3.test('googleee') = "+ pattern3.test('googleee'));

运行结果：

pattern1.test(str1) = true
pattern2.test(str2) = true
/goo\bgle/.test(str2) = false
pattern3.test('google') = true
pattern3.test('googleee') = false

 

6.或匹配

被|隔开的字符串有一个匹配到就返回true

代码：

 

1. var pattern1 =/google|baidu|bing/;
2. var str1 ='bing';
3. var str2 ='soso';
4. var str3 ='this is google';
5. print("pattern1.test(str1) = "+ pattern1.test(str1));
6. print("pattern1.test(str2) = "+ pattern1.test(str2));
7. print("pattern1.test(str3) = "+ pattern1.test(str3));

运行结果

pattern1.test(str1) = true
pattern1.test(str2) = false
pattern1.test(str3) = true

 

7.分组匹配

可以把分组后的字符串看成一个字符

元字符	匹配情况
(string)	用于反向引用的分组
\1或$1	匹配第一个分组中的内容
\2或$2	匹配第二个分组中的内容
\3或$3	匹配第三个分组中的内容

RegExp.$1表示获取模式中的一个分组对应的字符串，
在获取之前必须要运行一下正则表达式

代码：

 

1. /**
2. * 分组匹配
3. */
4. var pattern1 =/google{4,8}/;
5. var pattern2 =/google{4,8}$/;
6. var str1 ='googleeeeee';
7. print("pattern1.test(str1) = "+ pattern1.test(str1));
8. print("pattern1.test('googleeeeeeeeeee') = "+ pattern1.test('googleeeeeeeeeee'));
9. print("pattern2.test('googleee') = "+ pattern2.test('googleee'));
10. print("pattern2.test('googleeee') = "+ pattern2.test('googleeee'));
11. print("pattern2.test('googleeeeeeeeeee') = "+ pattern2.test('googleeeeeeeeeee'));
13. var pattern3 =/(google){4,8}$/;
14. var str2 ='googlee';
15. var str3 ='googlegooglegooglegoogle';
16. print("pattern3.test(str2) = "+ pattern3.test(str2));
17. print("pattern3.test(str3) = "+ pattern3.test(str3));
20. /**
21. * 获取匹配到的字符串
22. */
23. var pattern4 =/8(.*)8/;
24. var pattern5 =/8.*8/;
25. var str4 ='this is 8google8';
26. print("pattern4.test(str4) = "+ pattern4.test(str4));
27. print("RegExp.$1 = "+RegExp.$1);
28. print("pattern5.test(str4) = "+ pattern5.test(str4));
29. print("RegExp.$1 = "+RegExp.$1);
31. var str5 ='this is a 8GooGle8';
32. var ret1 = str5.replace(pattern4,'123');
33. print("ret1 = "+ ret1);
34. var ret2 = str5.replace(pattern4,'<strong>GooGle</strong>');
35. print("ret2 = "+ ret2);
36. var str6 ='this is a 8BaiDu8';
37. var ret3 = str6.replace(pattern4,'<strong>$1</strong>');
38. print("ret3 = "+ ret3);
40. var pattern6 =/(.*)\s(.*)/;
41. var str7 ='google baidu';
42. var ret4 = str7.replace(pattern6,'$2 $1');
43. print("ret4 = "+ ret4);

运行结果

pattern1.test(str1) = true
pattern1.test('googleeeeeeeeeee') = true
pattern2.test('googleee') = false
pattern2.test('googleeee') = true
pattern2.test('googleeeeeeeeeee') = false
pattern3.test(str2) = false
pattern3.test(str3) = true
pattern4.test(str4) = true
RegExp.$1 = google
pattern5.test(str4) = true
RegExp.$1 = 
ret1 = this is a 123
ret2 = this is a <strong>GooGle</strong>
ret3 = this is a <strong>BaiDu</strong>
ret4 = baidu google

 

8.贪婪与惰性

贪婪	惰性
+	+?
?	??
*	*?
{n}	{n}?
{n,}	{n,}?
{n,m}	{n,m}?

代码：

 

1. /**
2. * 贪婪与惰性
3. */
4. var pattern1 =/[a-z]/;
5. var pattern2 =/[a-z]+/;
6. var pattern3 =/[a-z]+?/;
7. var pattern4 =/[a-z]+?/g;
8. var str1 ='abcdef';
9. var ret1 = str1.replace(pattern1,'1');
10. var ret2 = str1.replace(pattern2,'1');
11. var ret3 = str1.replace(pattern3,'1');
12. var ret4 = str1.replace(pattern4,'1');
13. print("ret1 = "+ ret1);
14. print("ret2 = "+ ret2);
15. print("ret3 = "+ ret3);
16. print("ret4 = "+ ret4);
19. /**
20. * 禁止了贪婪，开启了全局
21. */
22. var pattern5 =/8(.*)8/;
23. var pattern6 =/8(.*?)8/;
24. var pattern7 =/8(.*?)8/g;
25. var str2 ='8google8 8google8 8google8 8google8';
26. var ret5 = str2.replace(pattern5,'<strong>$1</strong>');
27. var ret6 = str2.replace(pattern6,'<strong>$1</strong>');
28. var ret7 = str2.replace(pattern7,'<strong>$1</strong>');
29. print("ret5 = "+ ret5);
30. print("ret6 = "+ ret6);
31. print("ret7 = "+ ret7);
34. /**
35. * 除了正则表达式里两边的8不要匹配
36. */
37. var pattern8 =/8([^8]*)8/g;
38. var pattern9 =/8(.*)8/g;
39. var str3 ='8google8 8google8 8google8';
40. var ret8 = str3.replace(pattern8,'<strong>$1</strong>');
41. var ret9 = str3.replace(pattern9,'<strong>$1</strong>');
42. print("ret8 = "+ ret8);
43. print("ret9 = "+ ret9);

运行结果:

ret1 = 1bcdef
ret2 = 1
ret3 = 1bcdef
ret4 = 111111
ret5 = <strong>google8 8google8 8google8 8google</strong>
ret6 = <strong>google</strong> 8google8 8google8 8google8
ret7 = <strong>google</strong> <strong>google</strong> <strong>google</strong> <strong>google</strong>
ret8 = <strong>google</strong> <strong>google</strong> <strong>google</strong>
ret9 = <strong>google8 8google8 8google</strong>

 

9.返回数组

捕获性分组，所有的分组都捕获返回
非捕获性分组只需要在不需要捕获的分组前加上?:

代码：

 

1. /**
2. * 返回数组
3. */
4. var pattern1 =/^[a-z]+\s[0-9]{4}$/;
5. var str1 ='google 2015';
6. print("pattern1.test(str1) = "+ pattern1.test(str1));
7. var ret1 = pattern1.exec(str1);
8. print("ret1 = "+ ret1);
9. print("typeof ret1 = "+typeof ret1);
11. var pattern2 =/^[a-z]+/;
12. var ret2 = pattern2.exec(str1);
13. print("ret2 = "+ ret2);
14. print("typeof ret2 = "+typeof ret2);
17. /**
18. * 分组返回
19. */
20. var pattern3 =/^([a-z]+)\s([0-9]{4})$/;
21. var ret3 = pattern3.exec(str1);
22. print("ret3 = "+ ret3);
23. print("typeof ret3 = "+typeof ret3);
24. print("ret3[0] = "+ ret3[0]);//匹配到的整个字符串
25. print("ret3[1] = "+ ret3[1]);//匹配到的第1个字符串
26. print("ret3[2] = "+ ret3[2]);//匹配到的第2个字符串
29. /**
30. * 捕获性分组，所有的分组都捕获返回
31. * 非捕获性分组只需要在不需要捕获的分组前加上?:
32. */
33. var pattern4 =/(\d+)([a-z]+)/;
34. var pattern5 =/(\d+)(?:[a-z]+)/;
35. var str2 ='123abc';
36. print("pattern4.exec(str2) = "+ pattern4.exec(str2));
37. print("pattern5.exec(str2) = "+ pattern5.exec(str2));
40. /**
41. * 分组嵌套
42. */
43. var pattern6 =/(a?(b?(c?)))/;
44. var str3 ='abc';
45. var ret4 = pattern6.exec(str3);
46. print("ret4 = "+ ret4);
47. print("ret4[1] = "+ ret4[1]);//匹配到第1个分组(a?(b?(c?)))
48. print("ret4[2] = "+ ret4[2]);//匹配到第2个分组(b?(c?))
49. print("ret4[3] = "+ ret4[3]);//匹配到第3个分组(c?)

运行结果：

pattern1.test(str1) = true
ret1 = google 2015
typeof ret1 = object
ret2 = google
typeof ret2 = object
ret3 = google 2015,google,2015
typeof ret3 = object
ret3[0] = google 2015
ret3[1] = google
ret3[2] = 2015
pattern4.exec(str2) = 123abc,123,abc
pattern5.exec(str2) = 123abc,123
ret4 = abc,abc,bc,c
ret4[1] = abc
ret4[2] = bc
ret4[3] = c

 

10.前瞻捕获

匹配的字符串后面必须是另一个匹配的字符串

代码:

 

1. /**
2. * 前瞻捕获
3. */
4. var pattern1 =/goo(?=gle)/;
5. var str1 ='goobbb';
6. var str2 ='google';
7. var ret1 = pattern1.exec(str1);
8. var ret2 = pattern1.exec(str2);
9. print("ret1 = "+ ret1);
10. print("ret2 = "+ ret2);

运行结果：

ret1 = null
ret2 = goo

 

11.特殊字符匹配

代码:

 

1. /**
2. * 特殊字符匹配
3. * 用反斜杠转义正则里的特殊字符才能匹配
4. */
5. var pattern2 =/\[/;
6. var str3 ='[';
7. var ret3 = pattern2.exec(str3);
8. print("ret3 = "+ ret3);

运行结果：

ret3 = [

 

12.换行匹配

代码:

 

1. /**
2. * 换行模式
3. */
4. var pattern3 =/^\d+/;
5. var pattern4 =/^\d+/g;
6. var pattern5 =/^\d+/gm;
7. var str3 ='1.baidu\n2.google\n3.bing';
8. var ret3 = str3.replace(pattern3,'#');
9. var ret4 = str3.replace(pattern4,'#');
10. var ret5 = str3.replace(pattern5,'#');
11. print("ret3 = \n"+ ret3);
12. print("ret4 = \n"+ ret4);
13. print("ret5 = \n"+ ret5);

运行结果：

ret3 = 
#.baidu
2.google
3.bing
ret4 = 
#.baidu
2.google
3.bing
ret5 = 
#.baidu
#.google
#.bing

 

Ⅶ.常用正则表达式

代码如下：

 

1. /**
2. * 邮政编码
3. * 必须是六位，必须是数字，首位不为零
4. */
5. var pattern1 =/[1-9][0-9]{5}/;
6. var str1 ='This is 224000!';
7. var ret1 = pattern1.test(str1);
8. print("ret1 = "+ ret1);
11. /**
12. * 压缩文件
13. * (文件名).(扩展名)
14. */
15. var pattern2 =/^\w+\.zip|gz|rar$/;
16. var str2 ='213.zip';
17. var ret2 = pattern2.test(str2);
18. print("ret2 = "+ ret2);
19. var str3 ='21-3.zip';
20. var ret3 = pattern2.test(str3);
21. print("ret3 = "+ ret3);
24. /**
25. * 删除空格
26. */
27. var pattern3 =/\s/g;
28. var str4 ='111 222 33 44 555';
29. var ret4 = str4.replace(pattern3,'');
30. print("ret4 = "+ ret4);
33. /**
34. * 删除首尾空格
35. */
36. var pattern4 =/^\s+/;
37. var str5 =' goo gle ';
38. var ret5 = str5.replace(pattern4,'');
39. print("ret5 = |"+ ret5 +"|");
40. var pattern5 =/\s+$/;
41. var ret6 = ret5.replace(pattern5,'');
42. print("ret6 = |"+ ret6 +"|");
45. /**
46. * 删除首尾空格
47. * 使用惰性模式的分组匹配
48. */
49. var pattern6 =/^\s+(.+)\s+$/;
50. var str6 =' goo gle ';
51. var ret7 = pattern6.exec(str6);
52. var str7 = ret7[1];
53. print("str7 = |"+ str7 +"|");
55. var pattern7 =/^\s+(.+?)\s+$/;
56. var str7 =' goo gle ';
57. var ret8 = pattern7.exec(str7);
58. var str8 = ret8[1];
59. print("str8 = |"+ str8 +"|");
61. var ret9 = str7.replace(pattern7,'$1');
62. print("ret9 = |"+ ret9 +"|");
65. /**
66. * 简单电子邮件匹配
67. */
68. var pattern8 =/^([\w\.\-]+)@([\w\-]+)\.([a-zA-Z]{2,4})$/;
69. var str8 ='[email protected]';
70. var ret10 = pattern8.test(str8);
71. print("ret10 = "+ ret10);

运行结果：

ret1 = true
ret2 = true
ret3 = false
ret4 = 1112223344555
ret5 = |goo  gle   |
ret6 = |goo  gle|
str7 = |goo  gle  |
str8 = |goo  gle|
ret9 = |goo  gle|
ret10 = true

 

Ⅷ.Another

运行上面的javascript代码使用的是Eclipse Kepler自带的Rhino解释器，
原来使用IntelliJ IDEA的童鞋可以试试用一下Eclipse Kepler。

本文的编辑使用了作业部落的css样式以及它们的markdown编辑器
点击可以访问原文：https://www.zybuluo.com/thorncorona/note/71406

如果觉得此文不错的话可以点击下面红色的小按钮关注我
更多文章请点击http://www.cnblogs.com/kodoyang/访问我的博客园主页。
大家阅读愉快。

参考链接：
- 李炎恢的正则表达式专题
- 参考w3school

孔东阳
二〇一五年二月十四日