java10.02编不了中文_Java_util_02_Java判断字符串是中文还是英文

1 packageorg.liufeng.course.util;2 importjava.util.regex.Matcher;3 importjava.util.regex.Pattern;4 /**

5 * Description 提供判断字符串是中文或者是英文的一种思路6 *7 */

8 public classChineseAndEnglish_Util {9 public static voidmain(String[] args) {10 String str = "我爱你，！？()：；“”、。";11 char[] charArray =str.toCharArray();12 for (int i = 0; i < charArray.length; i++) {13 isChinese(charArray[i]);14 }15 String chinese = "中国god damn";16 System.out.println(isContainChinese(chinese));17 String english = "dfafdabac";18 System.out.println(isEnglish(english));19 }20

21 /**

22 * 1.判断字节是否是中文23 *24 * CJK的意思是“Chinese，Japanese，Korea”的简写 ，实际上就是指中日韩三国的象形文字的Unicode编码25 * Character.UnicodeBlock.CJK_UNIFIED_IDEOGRAPHS ：4E00-9FBF：CJK 统一表意符号26 * Character.UnicodeBlock.CJK_COMPATIBILITY_IDEOGRAPHS ：F900-FAFF：CJK 兼容象形文字27 * Character.UnicodeBlock.CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A ：3400-4DBF：CJK 统一表意符号扩展 A28 * Character.UnicodeBlock.GENERAL_PUNCTUATION ：2000-206F：常用标点29 * Character.UnicodeBlock.CJK_SYMBOLS_AND_PUNCTUATION ：3000-303F：CJK 符号和标点30 * Character.UnicodeBlock.HALFWIDTH_AND_FULLWIDTH_FORMS ：FF00-FFEF：半角及全角形式31 *32 */

33 public static boolean isChinese(charc) {34 Character.UnicodeBlock ub =Character.UnicodeBlock.of(c);35 if (ub ==Character.UnicodeBlock.CJK_UNIFIED_IDEOGRAPHS36 || ub ==Character.UnicodeBlock.CJK_COMPATIBILITY_IDEOGRAPHS37 || ub ==Character.UnicodeBlock.CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A38 || ub ==Character.UnicodeBlock.GENERAL_PUNCTUATION39 || ub ==Character.UnicodeBlock.CJK_SYMBOLS_AND_PUNCTUATION40 || ub ==Character.UnicodeBlock.HALFWIDTH_AND_FULLWIDTH_FORMS) {41 return true;42 }43 return false;44 }45 //2.检测是否包含英文

46 public static booleanisEnglish(String charaString) {47 return charaString.matches("^[a-zA-Z]*");48 }49 //3.检测是否包含中文

50 public static booleanisContainChinese(String str) {51 String regEx = "[\\u4E00-\\u9FA5]+";52 Pattern p =Pattern.compile(regEx);53 Matcher m =p.matcher(str);54 if(m.find()) {55 return true;56 } else{57 return false;58 }59 }60 }