UTF-8编码中的特殊空格之C2 A0 -> NO-BREAK SPACE

package com.lingyejun.dating.chap11;

import java.nio.charset.StandardCharsets;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

public class SpecialSpace {

    public static void main(String[] args) {
        String str1 = "lingyejun ";
        byte[] str1Bytes = str1.getBytes();
        String space = new String(str1Bytes, StandardCharsets.UTF_8);
        System.out.println("带有32 Space的字符串:" + space);
        System.out.println("使用trim去掉32 -> Space:" + space.trim());

        byte[] str2Bytes = new byte[11];
        System.arraycopy(str1Bytes, 0, str2Bytes, 0, str1Bytes.length);
        str2Bytes[9] = (byte) 0xC2;
        str2Bytes[10] = (byte) 0xA0;
        String noBreakSpace = new String(str2Bytes, StandardCharsets.UTF_8);
        System.out.println("带有C2 A0 -> NO-BREAK SPACE的字符串:" + noBreakSpace);
        System.out.println("使用trim无法去掉C2 A0 -> NO-BREAK SPACE:" + noBreakSpace.trim());

        // 32为我们平常谈论的Space空格 -> SPACE
        byte[] bytes1 = new byte[]{(byte) 0x20};
        String space1 = new String(bytes1, StandardCharsets.UTF_8);
        System.out.println("UTF-8 字符编码号32 -> 0x1F 输出:" + space1);

        // 0xC2=194 0xA0=160  -> NO-BREAK SPACE
        byte[] bytes2 = new byte[]{(byte) 0xC2, (byte) 0xA0};
        String space2 = new String(bytes2, StandardCharsets.UTF_8);
        char[] chars3 = space2.toCharArray();
        System.out.println("UTF-8 字符编码号194 -> 0xC2 160 -> 0xA0 输出:" + space2);

        byte[] bytes3 = new byte[]{(byte) 0xC2, (byte) 0xA0};
        String c2a0Space = new String(bytes3, StandardCharsets.UTF_8);
        Pattern p = Pattern.compile(c2a0Space);
        Matcher m = null;
        m = p.matcher(noBreakSpace);
        noBreakSpace = m.replaceAll("");
        System.out.println("使用正则去掉C2 A0 -> NO-BREAK SPACE:" + noBreakSpace);
    }
}