正则表达式高级应用（java语言版）
1.边界
package 正则;
import java.util.ArrayList;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
public class Exp001 {
public static void main(String[] args) {
// TODO Auto-generated method stub
String string= "the cat scattered his food all over the room";
String regex = "(cat)";
int num=0;
Pattern pattern = Pattern.compile(regex);
Matcher p = pattern.matcher(string);
ArrayList<String> templist = new ArrayList<String>();
while(p.find()) {
num++;
templist.add(p.group());
}
System.out.println(num);
}
}
结果：2
package 正则;
import java.util.ArrayList;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
public class Exp001 {
public static void main(String[] args) {
// TODO Auto-generated method stub
String string= "the cat scattered his food all over the room";
String regex = "(\\bcat\\b)";
Pattern pattern = Pattern.compile(regex);
Matcher p = pattern.matcher(string);
ArrayList<String> templist = new ArrayList<String>();
while(p.find()) {
templist.add(p.group());
}
System.out.println(templist.size());
}
}
结果：1
对比上面两个结果，发现第一个也将scattered这个单词包含进去了。不符合我们需求，所以我们一般使用第二张方法（位置匹配）。
单向区间匹配：
package 正则;
import java.util.ArrayList;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
public class Exp001 {
public static void main(String[] args) {
// TODO Auto-generated method stub
String string[]= {"caption","cap","cape","capsize","recap"};
String regex = "(\\bcap)";
Pattern pattern = Pattern.compile(regex);
for (String xString: string)
{
Matcher p = pattern.matcher(xString);
if(p.find()) {
System.out.println(xString);
}
}
}
}
结果：
caption
cap
cape
capsize
package 正则;
import java.util.ArrayList;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
public class Exp001 {
public static void main(String[] args) {
// TODO Auto-generated method stub
String string[]= {"caption","cap","cape","capsize","recap"};
String regex = "(\\bcap)";
Pattern pattern = Pattern.compile(regex);
for (String xString: string)
{
Matcher p = pattern.matcher(xString);
if(p.find()) {
System.out.println(xString);
}
}
}
}
结果：
caption
cap
cape
capsize
下表列出了正则表达式中的边界匹配器
package 正则;
import java.util.ArrayList;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
public class Exp001 {
public static void main(String[] args) {
// TODO Auto-generated method stub
String string[]= {"caption-s","cap - s","a- b","a -b"};
String regex = "(\\B-\\B)";
Pattern pattern = Pattern.compile(regex);
for (String xString: string)
{
Matcher p = pattern.matcher(xString);
if(p.find()) {
System.out.println(xString);
}
}
}
}
结果：
cap - s
知识点：表明不匹配一个单词边境（既字母数字下划线之间，或者非字母数字下划线之间），请使用\B。
2.字符串边界
package 正则;
import java.util.ArrayList;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
public class Exp001 {
public static void main(String[] args) {
// TODO Auto-generated method stub
String string= "<?xml version=\"1.0\" encoding=\"utf-8\" ?>"
+ "wsdl:definitions targetNamespace=\"http://tips.cf\"";
String regex = "(<\\?xml.*\\?>)";
Pattern pattern = Pattern.compile(regex);
Matcher p = pattern.matcher(string);
if(p.find()) {
System.out.println(string);
}
}
}
结果：
<?xml version="1.0" encoding="utf-8" ?>wsdl:definitions targetNamespace="http://tips.cf"
package 正则;
import java.util.ArrayList;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
public class Exp001 {
public static void main(String[] args) {
// TODO Auto-generated method stub
String string= "it is not a xml"
+ "<?xml version=\"1.0\" encoding=\"utf-8\" ?>"
+ "wsdl:definitions targetNamespace=\"http://tips.cf\"";
String regex = "(<\\?xml.*\\?>)";
Pattern pattern = Pattern.compile(regex);
Matcher p = pattern.matcher(string);
if(p.find()) {
System.out.println(string);
}
}
}
结果：
<?xml version="1.0" encoding="utf-8" ?>wsdl:definitions targetNamespace="http://tips.cf"
在下面的例子里，虽然匹配到xml的开头部分，但位置完全不对，她匹配到的是第二行而不是第一行
package 正则;
import java.util.ArrayList;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
public class Exp001 {
public static void main(String[] args) {
// TODO Auto-generated method stub
String string= "it is not a xml"
+ "<?xml version=\"1.0\" encoding=\"utf-8\" ?>"
+ "wsdl:definitions targetNamespace=\"http://tips.cf\"";
String regex = "(^\\s*<\\?xml.*\\?>)";
Pattern pattern = Pattern.compile(regex);
Matcher p = pattern.matcher(string);
if( ! p.find()) {
System.out.println("这不是xml文件");
}
}
}
结果：
这不是xml文件
知识点：(^\\s*<\\?xml.*\\?>)分析:^\s*将匹配一个字符串的开头和随后的零个或多个空吧字符（这解决了<?xml>标签前允许有空格、制表符、换行符等空白字符的问题）。作为一个整体，此正则表达式还能对合法的空白字符做出妥善处理。
package 正则;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
public class Exp001 {
public static void main(String[] args) {
// TODO Auto-generated method stub
String string= "it is a html file </htMl>as";
String regex = "(</[hH][tT][Mm][lL]>\\s*$)";
Pattern pattern = Pattern.compile(regex);
Matcher p = pattern.matcher(string);
if( ! p.find()) {
System.out.println("这不是html文件，html文件标签下面不应该有任何实际内容");
}
}
}
结果：
这不是html文件，html文件标签下面不应该有任何实际内容
|
元字符 |
作用 |
|
^ |
判断开头 |
|
$ |
判断结尾 |
知识点：1.我们判断”\\”注释可以使用((?m)^\s\\.*$)。2.(^.$)该表达式几乎能匹配到任何字符，但是在string = “”;的时候不成立。
3.子表达式
分辨文本”[12.159.46.200]”
package 正则;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
public class Exp001 {
public static void main(String[] args) {
// TODO Auto-generated method stub
String string= "[12.159.46.200]";
String regex = "[(\\d{1,3}\\.){3}\\d{1,3}]";
Pattern pattern = Pattern.compile(regex);
Matcher p = pattern.matcher(string);
if(p.find()) {
System.out.println(string);
}
}
}
结果：
[12.159.46.200]
package 正则;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
public class Exp001 {
public static void main(String[] args) {
// TODO Auto-generated method stub
String string[]= {"ID:042","sex:M","DOB:1967-08-17","Status:Active"};
String regex = "19|20\\d{2}";
Pattern pattern = Pattern.compile(regex);
for (String xString:string) {
Matcher p = pattern.matcher(xString);
if(p.find()) {
System.out.println(xString);
}
}
}
}
结果：
DOB:1967-08-17
知识点：我们限定前两位数字是19/20，于是我们只要写19|20就可以二选一，后面的日期直接设定两位{2}。
小问题：如果我们匹配一个ipv4地址也可以类似于这样的式子[(\\d{1,3}\\.){3}\\d{1,3}]编写正则表达式吗？
package 正则;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
public class Exp001 {
public static void main(String[] args) {
// TODO Auto-generated method stub
String string[]= {"172.168.1.1","254.254.254.254","789.1.1.1","12.12.12.12"};
String regex = "(\\d{1,3}\\.){3}\\d{1,3}";
Pattern pattern = Pattern.compile(regex);
for (String xString:string) {
Matcher p = pattern.matcher(xString);
if(p.find()) {
System.out.println(xString);
}
}
}
}
结果：
172.168.1.1
254.254.254.254
789.1.1.1
12.12.12.12
以上的结果明显大错特错！Ipv4某一位怎么可能大于255！
package 正则;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
public class Exp001 {
public static void main(String[] args) {
// TODO Auto-generated method stub
String string[]= {"172.168.1.1","254.254.254.254","489.1.1.1","12.12.12.12"};
String regex = "(((\\d{1,2})|(1\\d{2})|(2[0-4]\\d)|(25[0-5]))\\.){3}"
+ "(((\\d{1,2})|(1\\d{2})|(2[0-4]\\d)|(25[0-5])))";
for (String xString:string) {
if(xString.matches(regex)) {
System.out.println(xString);
}
}
}
}
结果：
172.168.1.1
254.254.254.254
12.12.12.12
//由于用上面的方法有bug所以我换了一种方法。
4.1回溯引用有什么用
package 正则;
import java.util.ArrayList;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
public class Exp001 {
public static void main(String[] args) {
// TODO Auto-generated method stub
String string = "<H1>Welcome</H1>"
+ "<H2> my </H3>"
+ "<H3> Homepage</H3>";
String regex = "<[Hh]1>.*</[Hh]1>";
Pattern p = Pattern.compile(regex);
ArrayList<String> temp = new ArrayList<String>();
Matcher fMatcher = p.matcher(string);
while(fMatcher.find()) {
temp.add(fMatcher.group());
}
System.out.println(xString);
}
}
结果：
<H1>Welcome</H1>
知识点：<[Hh]1>.*</[Hh]1>只能匹配一级标题所以我们可以改进，再此基础上添加一个字符集合进去。
package 正则;
import java.util.ArrayList;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
public class Exp001 {
public static void main(String[] args) {
// TODO Auto-generated method stub
String string = "<H1>Welcome</H1>"
+ "<H2> my </H3>"
+ "<H3> Homepage</H3>";
String regex = "<[Hh][1-3]>.*</[Hh][1-3]>";
Pattern p = Pattern.compile(regex);
ArrayList<String> temp = new ArrayList<String>();
Matcher fMatcher = p.matcher(string);
while(fMatcher.find()) {
temp.add(fMatcher.group());
}
System.out.println(temp);
}
}
结果：
[<H1>Welcome</H1><H2> my </H3><H3> Homepage</H3>]
4.2回溯引用匹配
package 正则;
import java.util.ArrayList;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
public class Exp001 {
public static void main(String[] args) {
// TODO Auto-generated method stub
String string = "this is of of are here here they are are";
String regex = "[ ]+(\\w+)[ ]+\\1";
Pattern p = Pattern.compile(regex);
ArrayList<String> temp = new ArrayList<String>();
Matcher fMatcher = p.matcher(string);
while(fMatcher.find()) {
temp.add(fMatcher.group());
}
System.out.println(temp);
}
}
结果：
[ of of, here here, are are]
知识点：[ ]+匹配一个或者多个空格，\w+匹配一个胡哦多个字母数字字符，[ ]+匹配随后的空格。注意\\w+是括号里的，他是一个表达式。最后一个是\\1，这是一个回溯引用，而他应用的正是前面划分出去的那个子表达式：当(\\w+)匹配到单词of的时候，\\1也匹配的单词of。
4.3回溯引用在替换操作中的应用
package 正则;
import java.util.ArrayList;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
public class Exp001 {
public static void main(String[] args) {
// TODO Auto-generated method stub
String string = "hello,[email protected] is my e-mail address";
String regex1 = "(\\w+[\\w\\.]*@[\\w\\.]+\\.\\w+)";
String regex2 = "(<A HREF=\"mailto:$1\">$1</A>)";
Pattern p = Pattern.compile(regex1);
Matcher fMatcher = p.matcher(string);
StringBuffer sb = new StringBuffer();
fMatcher.reset();
while(fMatcher.find()) {
fMatcher.appendReplacement(sb, regex2);
}
fMatcher.appendTail(sb);
System.out.println(sb.toString());
}
}
结果：
hello,(<A HREF="mailto:[email protected]">[email protected]</A>) is my e-mail address
知识点：建议看一下这个博客http://blog.****.net/jiafu1115/article/details/6663812
package 正则;
import java.util.ArrayList;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
public class Exp001 {
public static void main(String[] args) {
// TODO Auto-generated method stub
String string[] = {"313-555-1253","343-555-3455","789-567-4565"};
String regex1 = "(\\d{3})(-)(\\d{3})(-)(\\d{4})";
String regex2 = "($1)-$3-$5";
Pattern p = Pattern.compile(regex1);
for(String str:string) {
Matcher fMatcher = p.matcher(str);
StringBuffer sb = new StringBuffer();
fMatcher.reset();
while(fMatcher.find()) {
fMatcher.appendReplacement(sb, regex2);
}
System.out.println(sb.toString());
}
}
}
结果：
(313)-555-1253
(343)-555-3455
(789)-567-4565
4.4大小写转换
package 正则;
import java.util.ArrayList;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
public class Exp001 {
public static void main(String[] args) {
// TODO Auto-generated method stub
String string[] = {"<H1>abc<H1>","<h3>bcd<h2>","<h4>fgh<H4>"};
String regex1 = "(<[hH]\\d>)(.*?)(<[hH]\\d>)";
String regex2 = "$1\\U$2\\E$3";
Pattern p = Pattern.compile(regex1);
for(String str:string) {
Matcher fMatcher = p.matcher(str);
StringBuffer sb = new StringBuffer();
fMatcher.reset();
while(fMatcher.find()) {
fMatcher.appendReplacement(sb, regex2);
}
System.out.println(sb.toString());
}
}
}
结果：
<H1>UabcE<H1>
<h3>UbcdE<h2>
<h4>UfghE<H4>
5. 向前查找
package 正则;
import java.util.ArrayList;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
public class Exp001 {
public static void main(String[] args) {
// TODO Auto-generated method stub
String string[] = {"http://www.a.com","http://wap.b.com","ftp://ftp.c.cn"};
String regex1 = ".+(?=:)";
Pattern p = Pattern.compile(regex1);
for(String str:string) {
Matcher fMatcher = p.matcher(str);
while(fMatcher.find()) {
System.out.println(str);
}
}
}
}
结果：
http://www.a.com
http://wap.b.com
ftp://ftp.c.cn
知识点：任何一个表达式都可以转换为一个向前查找表达式，只要给它加上一个”?=”前缀即可。
package 正则;
import java.util.ArrayList;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
public class Exp001 {
public static void main(String[] args) {
// TODO Auto-generated method stub
String string[] = {"a:$32.3","b:$332.3","c:$3452.3"};
String regex1 = "\\$[0-9.]+";
//String regex1 = "[0-9.]+";
Pattern p = Pattern.compile(regex1);
for(String str:string) {
Matcher fMatcher = p.matcher(str);
while(fMatcher.find()) {
System.out.println(str);
}
}
}
}
结果：
a:$32.3
b:$332.3
c:$3452.3
|
操作符 |
作用 |
|
(?=) |
正向前查找 |
|
(?!) |
负向前查找 |
|
(?<=) |
正向后查找 |
|
(?<!) |
负向后查找 |
package 正则;
import java.util.ArrayList;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
public class Exp001 {
public static void main(String[] args) {
// TODO Auto-generated method stub
String string = "i have $20 and i pay $10 to shop,and buy 3pears";
String regex1 = "(?<=\\$)\\d+";
ArrayList<String> temp = new ArrayList<String>();
Pattern p = Pattern.compile(regex1);
Matcher fMatcher = p.matcher(string);
while(fMatcher.find()) {
temp.add(fMatcher.group());
}
System.out.println(temp);
}
}
结果：
[20, 10]
package 正则;
import java.util.ArrayList;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
public class Exp001 {
public static void main(String[] args) {
// TODO Auto-generated method stub
String string = "i have $20 and i pay $10 to shop,and buy 3 pears for 3 day";
String regex1 = "\\b(?<!\\$)\\d+\\b";
ArrayList<String> temp = new ArrayList<String>();
Pattern p = Pattern.compile(regex1);
Matcher fMatcher = p.matcher(string);
while(fMatcher.find()) {
temp.add(fMatcher.group());
}
System.out.println(temp);
}
}
结果：
[3, 3]
package 正则;
import java.util.ArrayList;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
public class Exp001 {
public static void main(String[] args) {
// TODO Auto-generated method stub
String string = "i have $20 and i pay $10 to shop,and buy 3 pears for 3 day";
String regex1 = "(?<!\\$)\\d+";
ArrayList<String> temp = new ArrayList<String>();
Pattern p = Pattern.compile(regex1);
Matcher fMatcher = p.matcher(string);
while(fMatcher.find()) {
temp.add(fMatcher.group());
}
System.out.println(temp);
}
}
结果：
[0, 0, 3, 3]
6.嵌入条件
由于java不支持正则嵌入条件，so我也就没办法写。如果出现错误可以添加下面的qq和我联系，希望这些代码能给你带来帮助，谢谢。
技术讨论可加qq:1419561484