Javaで正規表現を使う

詳しくは 本家サイトを参考に。
とりあえず基本的な使い方を以下に書いてみます。


◆セパレータを指定した文字列の分解

/*
 * Uses split to break up a string of input separated by
 * commas and/or whitespace.
 */
import java.util.regex.*;

public class Splitter {
    public static void main(String[] args) throws Exception {
        // Create a pattern to match breaks
        Pattern p = Pattern.compile("[,\\s]+");
        // Split input with the pattern
        String[] result =
                 p.split("１２, ３   ４ ,  ５");
        for (int i=0; i<result.length; i++)
            System.out.println(result[i]);
    }
}

Deja-Groove:/cygdrive/d/Work/java-test/regex> java -cp . Splitter
１２
３
４
５

◆文字列置換

/*
 * This code writes "我輩は犬である。犬も人並みにブログを書くのである。"
 * to the standard-output stream:
 */
import java.util.regex.*;

public class Replacement {
    public static void main(String[] args)
                         throws Exception {
        // Create a pattern to match cat
        Pattern p = Pattern.compile("猫");
        // Create a matcher with an input string
        Matcher m = p.matcher("我輩は猫である。猫も人並みにブログを書くのである。");

        StringBuffer sb = new StringBuffer();

        boolean result = m.find();
        // Loop through and create a new String
        // with the replacements
        while(result) {
            m.appendReplacement(sb, "犬");
            result = m.find();
        }
        // Add the last segment of input to
        // the new String
        m.appendTail(sb);
        System.out.println(sb.toString());
    }
}

Deja-Groove:/cygdrive/d/Work/java-test/regex> java -cp . Replacement
我輩は犬である。犬も人並みにブログを書くのである。


/*
* Checks for invalid characters
* in email addresses
*/
import java.util.regex.*;
import java.io.*;

public class EmailValidation {
   public static void main(String[] args)
                                 throws Exception {

      String input = args[0];

      //Checks for email addresses starting with
      //inappropriate symbols like dots or @ signs.
      Pattern p = Pattern.compile("^\\.|^\\@");
      Matcher m = p.matcher(input);
      if (m.find())
         System.err.println("Email addresses don't start" +
                            " with dots or @ signs.");
      //Checks for email addresses that start with
      //www. and prints a message if it does.
      p = Pattern.compile("^www\\.");
      m = p.matcher(input);
      if (m.find()) {
        System.out.println("Email addresses don't start" +
                " with \"www.\", only web pages do.");
      }
      p = Pattern.compile("[^A-Za-z0-9\\.\\@_\\-~#]+");
      m = p.matcher(input);
      StringBuffer sb = new StringBuffer();
      boolean result = m.find();
      boolean deletedIllegalChars = false;

      while(result) {
         deletedIllegalChars = true;
         m.appendReplacement(sb, "");
         result = m.find();
      }

      // Add the last segment of input to the new String
      m.appendTail(sb);

      input = sb.toString();

      if (deletedIllegalChars) {
         System.out.println("It contained incorrect characters" +
                           " , such as spaces or commas.");
      }
   }
}

Deja-Groove:/cygdrive/d/Work/java-test/regex> java -cp . EmailValidation .hhhhh@hhhh
Email addresses don't start with dots or @ signs.