[b]Scanner[/b]与正则表达式运用
自定义Scanner的分割符,默认是空白
import java.util.regex.*;
import java.util.*;
public class ThreatAnalyzer {
static String threatData =
"58.27.82.161@02/10/2005\n" +
"204.45.234.40@02/11/2005\n" +
"58.27.82.161@02/11/2005\n" +
"58.27.82.161@02/12/2005\n" +
"58.27.82.161@02/12/2005\n" +
"[Next log section with different data format]";
public static void main(String[] args) {
Scanner sc = new Scanner(threatData);
String pattern = "(\\d+[.]\\d+[.]\\d+[.]\\d+)@(\\d{2}/\\d{2}/\\d{4})";
while (sc.hasNext(pattern)) {
sc.next(pattern);
MatchResult match = sc.match();
String ip = match.group(1);
String date = match.group(2);
System.out.printf("Threat on %s from %s\n", ip, date);
// Threat on 02/10/2005 from 58.27.82.161
}
}
} /* Output:
Threat on 02/10/2005 from 58.27.82.161
Threat on 02/11/2005 from 204.45.234.40
Threat on 02/11/2005 from 58.27.82.161
Threat on 02/12/2005 from 58.27.82.161
Threat on 02/12/2005 from 58.27.82.161
自定义Scanner的分割符,默认是空白
import java.util.*;
public class ScannerDelimiter {
public static void main(String[] args) {
Scanner scanner = new Scanner("12, 42, 78, 99, 42");
scanner.useDelimiter("\\s*,\\s*");
while(scanner.hasNextInt())
System.out.println(scanner.nextInt());
}
} /* Output:
12
42
78
99
42
//简单认识正则表达式的概念
p("abc".matches("..."));
p("a8729a".replaceAll("\\d", "-"));
Pattern p = Pattern.compile("[a-z]{3}");
Matcher m = p.matcher("fgh");
p(m.matches());
p("fgha".matches("[a-z]{3}"));
//初步认识. * + ?
p("a".matches("."));
p("aa".matches("aa"));
p("aaaa".matches("a*"));
p("aaaa".matches("a+"));
p("".matches("a*"));
p("aaaa".matches("a?"));
p("".matches("a?"));
p("a".matches("a?"));
p("214523145234532".matches("\\d{3,100}"));
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]"));
//范围
p("a".matches("[abc]"));
p("a".matches("[^abc]"));
p("A".matches("[a-zA-Z]"));
p("A".matches("[a-z]|[A-Z]"));
p("A".matches("[a-z[A-Z]]"));
p("R".matches("[A-Z&&[RFG]]"));
//认识\s \w \d \
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
p("hello sir".matches("^h.*"));
p("hello sir".matches(".*ir$"));
p("hello sir".matches("^h[a-z]{1,3}o\\b.*"));
p("hellosir".matches("^h[a-z]{1,3}o\\b.*"));
//whilte lines
p(" \n".matches("^[\\s&&[^\\n]]*\\n$"));
p("aaa 8888c".matches(".*\\d{4}."));
p("aaa 8888c".matches(".*\\b\\d{4}."));
p("aaa8888c".matches(".*\\d{4}."));
p("aaa8888c".matches(".*\\b\\d{4}."));
//email
Pattern p = Pattern.compile("[\\w[.-]]+@[\\w[.-]]+\\.[\\w]+");
p("asdfasdfsafsf@dsdfsdf.com".matches("[\\w[.-]]+@[\\w[.-]]+\\.[\\w]+"));
//matches find lookingAt
Pattern p = Pattern.compile("\\d{3,5}");
String s = "123-34345-234-00";
Matcher m = p.matcher(s);
p(m.matches());
m.reset();
p(m.find());
p(m.start() + "-" + m.end());
p(m.find());
p(m.start() + "-" + m.end());
p(m.find());
p(m.start() + "-" + m.end());
p(m.find());
//p(m.start() + "-" + m.end());
p(m.lookingAt());
p(m.lookingAt());
p(m.lookingAt());
p(m.lookingAt());
//replacement
Pattern p = Pattern.compile("java", Pattern.CASE_INSENSITIVE);
Matcher m = p.matcher("java Java JAVa JaVa IloveJAVA you hateJava afasdfasdf");
StringBuffer buf = new StringBuffer();
int i=0;
while(m.find()) {
i++;
if(i%2 == 0) {
m.appendReplacement(buf, "java");
} else {
m.appendReplacement(buf, "JAVA");
}
}
m.appendTail(buf);
p(buf);
//group
Pattern p = Pattern.compile("(\\d{3,5})([a-z]{2})");
String s = "123aa-34345bb-234cc-00";
Matcher m = p.matcher(s);
while(m.find()) {
p(m.group());
}
//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
Pattern p = Pattern.compile(".{3}(?=a)");
String s = "444a66b";
Matcher m = p.matcher(s);
while(m.find()) {
p(m.group());
}
//back refenrences
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);
p("Java".matches("(?i)(java)"));