RegularExpressions:用途——字符串匹配(字符匹配)、字符串查找、字符串替换;例如:IP地址是否正确、从网页中揪出Email、从网页中揪出链接;类——java.lang.String、java.util.regex.Pattern、java.util.regex.Matcher
import java.util.regex.Matcher;
import java.util.regex.Pattern;
public class Test {
public static void main(String arg[]) {
// 简单认识正则表达式的概念
p("abc".matches("...")); //字符串"abc"符合"..."这种模式
p("a8729a".replaceAll("\\d", "-")); //将所有的数字转换为'-',转义字符'\'
Pattern p = Pattern.compile("[a-z]{3}"); //编译正则表达式,表示由字符a-z组成的3个字符的字符串
Matcher m = p.matcher("fgh"); //进行匹配,结果保留在Matcher的对象m中
p(m.matches());
p("fgha".matches("[a-z]{3}")); //将上面3语句综合
//初步认识. * + ?
p("aa".matches("..")); //.代表一个
p("aa".matches("aa"));
p("aaaa".matches("a*"));//*代表0个或多个
p("aaaa".matches("a+")); //+代表一个或多个
p("".matches("a*"));
p("aaaa".matches("a?")); //?代表一个或0个
p("".matches("a?")); //零宽度匹配
p("a".matches("a?"));
p("214523145234532".matches("\\d{3,100}")); //{}代表数字出现至少3次,至多100次(3到100为)
p("192.168.0.aaa".matches("\\d{1,3}\\.\\d{1,3}\\.\\d{1,3}\\.\\d{1,3}"));
p("192".matches("[0-2][0-9][0-9]")); //[]表示在范围内
//范围
p("a".matches("[abc]")); //abc中取一个
p("a".matches("[^abc]")); //取除了a
p("A".matches("[a-zA-Z]")); // 取a-z 或A-Z
p("A".matches("[a-z]|[A-Z]")); //取a-z 或A-Z
p("A".matches("[a-z[A-Z]]")); // 取a-z 或A-Z
p("R".matches("[A-Z&&[RFG]]")); // 取交集
//认识\s() \w(a-zA-Z_0-9) \d(一位数字) \D(非数字字符) \()
p(" \n\r\t".matches("\\s{4}"));
p(" ".matches("\\S"));
p("a_8".matches("\\w{3}"));
p("abc888&^%".matches("[a-z]{1,3}\\d+[&^#%]+"));
p("\\".matches("\\\\"));
//POSIX Style
p("a".matches("\\p{Lower}"));
//boundary 开始和结尾
p("hello sir".matches("^h.*")); //以h开头
p("hello sir".matches(".*ir$"));
p("hello sir".matches("^h[a-z]{1,3}o\\b.*"));
p("hellosir".matches("^h[a-z]{1,3}o\\b.*"));
//whilte lines
p(" \n".matches("^[\\s&&[^\\n]]*\\n$"));
//email
p("asdfasdfsafsf@dsdfsdf.com".matches("[\\w[.-]]+@[\\w[.-]]+\\.[\\w]+"));
//matches find lookingAt
Pattern p = Pattern.compile("\\d{3,5}"); //3-5位的数数字字符串
String s = "123-34345-234-00";
Matcher m = p.matcher(s); //matcher()匹配整个字符串,停留在不匹配处
p(m.matches());
m.reset(); //reset 重新设置0处为开始查找的位置
p(m.find()); //找字串Pattern.compile("\\d{3,5}");部分,找到则去掉
p(m.start() + "-" + m.end());
p(m.find());
p(m.start() + "-" + m.end()); //起始结束位置
p(m.find());
p(m.start() + "-" + m.end());
p(m.find());
//p(m.start() + "-" + m.end());
p(m.lookingAt()); //从开始位置开始查找
p(m.lookingAt());
p(m.lookingAt());
p(m.lookingAt());
//replacement 替换
Pattern p = Pattern.compile("java", Pattern.CASE_INSENSITIVE); //忽略大小写
Matcher m = p.matcher("java Java adadas JAVa JaVa IloveJAVA you hateJava afasdfasdf");
StringBuffer buf = new StringBuffer();
int i=0;
while(m.find()) { //查找Pattern.compile部分
i++;
if(i%2 == 0) {
m.appendReplacement(buf, "java"); //替换
} else {
m.appendReplacement(buf, "JAVA");
}
}
m.appendTail(buf); //添加尾巴,结尾部分
p(buf);
//group 分组
Pattern p = Pattern.compile("(\\d{3,5})([a-z]{2})");//分组用"()"
String s = "123aa-34345bb-234cc-00";
Matcher m = p.matcher(s);
while(m.find()) {
p(m.group(0)); //打印第一组
p(m.group(1)); //从左边起按'('分组,第几个就是第几组
p(m.group(2));
}
//qulifiers
Pattern p = Pattern.compile(".{3,10}+[0-9]");
String s = "aaaa5bbbb68";
Matcher m = p.matcher(s);
if(m.find())
p(m.start() + "-" + m.end());
else
p("not match!");
//non-capturing groups 非捕获
//(?=a)在前面,以a开始3个
Pattern p = Pattern.compile(".{3}(?=a)"); //3个字符,(?=a)在后面表示a前面3个,以a(不包含a)结束
String s = "4474a66b";
Matcher m = p.matcher(s);
while(m.find()) {
p(m.group());
}
//back refenrences 向前引用
Pattern p = Pattern.compile("(\\d(\\d))\\2");
String s = "122";
Matcher m = p.matcher(s);
p(m.matches());
//flags的简写
//Pattern p = Pattern.compile("java", Pattern.CASE_INSENSITIVE); //忽略大小写
p("Java".matches("(?i)(java)")); //(?i) 为上面简写
}
public static void p(Object o) {
System.out.println(o); //默认调用o的toString方法
}
}