Java to determine whether strings are Chinese or English tool class sharing
- 2020-04-01 03:30:17
- OfStack
Direct code:
import java.util.regex.Matcher;
import java.util.regex.Pattern;
/**
*
* <p>
* ClassName ShowChineseInUnicodeBlock
* </p>
* <p>
* Description Provides an idea of whether a string is in Chinese or English
* </p>
*
* @author wangxu wangx89@126.com
* <p>
* Date 2014-9-16 In the afternoon 06:45:35
* </p>
* @version V1.0
*
*/
public class ShowChineseInUnicodeBlock {
public static void main(String[] args) {
String str = " I love you,! ? : (); "",. ";
char[] charArray = str.toCharArray();
for (int i = 0; i < charArray.length; i++) {
isChinese(charArray[i]);
}
String chinese = " China god damn";
System.out.println(isContainChinese(chinese));
String english = "dfafdabac";
System.out.println(isEnglish(english));
}
/**
*
* <p>
* Title: isChinese
* </p>
* <p>
* Description: This function is just going to print some characters and see what they belong to
* </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 Extension Chinese character
//CJK Unified Ideographs Extension A; Ideogram extension A
//CJK Unified Ideographs Extension B < br / >
System.out.println(c + "--CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A");
} else if (ub == Character.UnicodeBlock.GENERAL_PUNCTUATION) {//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) {//Detect if Chinese
is included
String regEx = "[\u4E00-\u9FA5]+";
Pattern p = Pattern.compile(regEx);
Matcher m = p.matcher(str);
if (m.find()) {
return true;
} else {
return false;
}
}
}