专业背景：计算机科学 研究方向与兴趣: JavaEE-Web软件开发, 生物信息学, 数据挖掘与机器学习, 智能信息系统 目前工作: 基因组, 转录组, NGS高通量数据分析, 生物数据挖掘, 植物系统发育和比较进化基因组学
http://fuliang.javaeye.com/blog/175035
关键字: java regex, regular expression
Matcher类:
使用Matcher类,最重要的一个概念必须清楚:组(Group),在正则表达式中
()定义了一个组,由于一个正则表达式可以包含很多的组,所以下面先说说怎么划分组的,
以及这些组和组的下标怎么对应的.
下面我们看看一个小例子,来说明这个问题
引用
\w(\d\d)(\w+)
这个正则表达式有三个组:
整个\w(\d\d)(\w+) 是第0组 group(0)
(\d\d)是第1组 group(1)
(\w+)是第2组 group(2)
我们看看和正则表达式匹配的一个字符串x99SuperJava，
group(0)永远都是匹配整个表达式的字符串的那部分x99SuperJava
group(1)是第1组(\d\d)匹配的部分:99
group(2)是第二组(\w+)匹配的那部分SuperJava
下面我们写一个程序来验证一下：
Java代码 
package edu.jlu.fuliang;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
public class RegexTest {
public static void main(String[] args) {
String regex = "\\w(\\d\\d)(\\w+)";
String candidate = "x99SuperJava";
Pattern p = Pattern.compile(regex);
Matcher matcher = p.matcher(candidate);
if(matcher.find()){
int gc = matcher.groupCount();
for(int i = 0; i <= gc; i++)
System.out.println("group " + i + " :" + matcher.group(i));
}
}
}
package edu.jlu.fuliang; import java.util.regex.Matcher; import java.util.regex.Pattern; public class RegexTest { public static void main(String[] args) { String regex = "\\w(\\d\\d)(\\w+)"; String candidate = "x99SuperJava"; Pattern p = Pattern.compile(regex); Matcher matcher = p.matcher(candidate); if(matcher.find()){ int gc = matcher.groupCount(); for(int i = 0; i <= gc; i++) System.out.println("group " + i + " :" + matcher.group(i)); } } } 
99SuperJava import java.util.regex.*; public class MatcherPatternExample{ public static void main(String args[]){ test(); } public static void test(){ Pattern p = Pattern.compile("\\d"); Matcher m1 = p.matcher("55"); Matcher m2 = p.matcher("fdshfdgdfh"); System.out.println(m1.pattern() == m2.pattern()); //return true } } public class MatcherStartExample{ public static void main(String args[]){ test(); } public static void test(){ //create a Matcher and use the Matcher.start() method String candidateString = "My name is Bond. James Bond."; String matchHelper[] = {" ^"," ^"}; Pattern p = Pattern.compile("Bond"); Matcher matcher = p.matcher(candidateString); //Find the starting point of the first 'Bond' matcher.find(); int startIndex = matcher.start(); System.out.println(candidateString); System.out.println(matchHelper[0] + startIndex); //Find the starting point of the second 'Bond' matcher.find(); int nextIndex = matcher.start(); System.out.println(candidateString); System.out.println(matchHelper[1] + nextIndex); } import java.util.regex.*; public class MatcherGroupExample{ public static void main(String args[]){ test(); } public static void test(){ //create a Pattern Pattern p = Pattern.compile("Bond"); //create a Matcher and use the Matcher.group() method String candidateString = "My name is Bond. James Bond."; Matcher matcher = p.matcher(candidateString); //extract the group matcher.find(); System.out.println(matcher.group()); } } import java.util.regex.*; public class MatcherGroupParamExample{ public static void main(String args[]){ test(); } public static void test(){ //create a Pattern Pattern p = Pattern.compile("B(ond)"); //create a Matcher and use the Matcher.group(int) method String candidateString = "My name is Bond. James Bond."; //create a helpful index for the sake of output Matcher matcher = p.matcher(candidateString); //Find group number 0 of the first find matcher.find(); String group_0 = matcher.group(0); String group_1 = matcher.group(1); System.out.println("Group 0 " + group_0); System.out.println("Group 1 " + group_1); System.out.println(candidateString); //Find group number 1 of the second find matcher.find(); group_0 = matcher.group(0); group_1 = matcher.group(1); System.out.println("Group 0 " + group_0); System.out.println("Group 1 " + group_1); System.out.println(candidateString); } } while(matcher.find()){ //在匹配的区域，使用group,replace等进行查看和替换操作 } StringBuffer sb = new StringBuffer(); String replacement = "Smith"; Pattern pattern = Pattern.compile("Bond"); Matcher matcher =pattern.matcher("My name is Bond. James Bond. I would like a martini."); while(matcher.find()){ matcher.appendReplacement(sb,replacement);//结果是My name is Smith. James Smith } while(matcher.find()){ matcher.appendReplacement(sb,replacement);//结果是My name is Smith. James Smith } matcher.appendTail(sb); public String replaceFirst(String replacement)
评论