Java에서 문자열을 중국어나 영어로 판단하는 도구 클래스 공유

직접 코드:

import java.util.regex.Matcher;
import java.util.regex.Pattern;

/**
 *
 * <p>
 * ClassName ShowChineseInUnicodeBlock
 * </p>
 * <p>
 * Description
 * </p>
 *
 * @author wangxu [email protected]
 *         <p>
 *         Date 2014-9-16 06:45:35
 *         </p>
 * @version V1.0
 *
 */
public class ShowChineseInUnicodeBlock {
 public static void main(String[] args) {
  String str = " ,!?():;“”、。";
  char[] charArray = str.toCharArray();
  for (int i = 0; i < charArray.length; i++) {
   isChinese(charArray[i]);
  }
  String chinese = " god damn";
  System.out.println(isContainChinese(chinese));
  String english = "dfafdabac";
  System.out.println(isEnglish(english));
 }

 /**
  *
  * <p>
  * Title: isChinese
  * </p>
  * <p>
  * Description:
  * </p>
  *
  * @param c
  *
  */
 public static void isChinese(char c) {
  Character.UnicodeBlock ub = Character.UnicodeBlock.of(c);
  if (ub == Character.UnicodeBlock.CJK_UNIFIED_IDEOGRAPHS) {
   System.out.println(c + "--CJK_UNIFIED_IDEOGRAPHS");
  } else if (ub == Character.UnicodeBlock.CJK_COMPATIBILITY_IDEOGRAPHS) {
   System.out.println(c + "--CJK_COMPATIBILITY_IDEOGRAPHS");
  } else if (ub == Character.UnicodeBlock.CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A) {
   // CJK Unified Ideographs Extension WikipediaUnicode
   // CJK Unified Ideographs Extension A A ; A
   // CJK Unified Ideographs Extension B B
   System.out.println(c + "--CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A");
  } else if (ub == Character.UnicodeBlock.GENERAL_PUNCTUATION) {//
   System.out.println(c + "--GENERAL_PUNCTUATION");

  } else if (ub == Character.UnicodeBlock.CJK_SYMBOLS_AND_PUNCTUATION) {
   System.out.println(c + "--CJK_SYMBOLS_AND_PUNCTUATION");

  } else if (ub == Character.UnicodeBlock.HALFWIDTH_AND_FULLWIDTH_FORMS) {
   System.out.println(c + "--HALFWIDTH_AND_FULLWIDTH_FORMS");

  }
 }

 public static boolean isEnglish(String charaString) {
  return charaString.matches("^[a-zA-Z]*");
 }

 public static boolean isContainChinese(String str) {//
  String regEx = "[\\u4E00-\\u9FA5]+";
  Pattern p = Pattern.compile(regEx);
  Matcher m = p.matcher(str);
  if (m.find()) {
   return true;
  } else {
   return false;
  }
 }
}

좋은 웹페이지 즐겨찾기