java替换特殊字符

版权声明：本文为博主原创文章，未经博主允许不得转载。 https://blog.csdn.net/qq_26346941/article/details/82802671

今天处理bug，接口输入特殊字符（零宽空白），一种前端js控制替换特殊字符；一种java后端控制

package com.shallowan.spring.boot.blog;

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

public class StringUtilTools {
    //替换特殊字符
    private static String zerolize(String s) {
        if (s.length() < 4) {
            s = "000".substring(0, 4 - s.length()) + s;
        }
        return s;
    }

    public static void main(String[] args) throws IOException {
        int[] input = new int[] { 0x7f, 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, 0x88, 0x89, 0x8a,
                0x8b, 0x8c, 0x8d, 0x8e, 0x8f, 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, 0x98, 0x99,
                0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f, 0xad, 0x483, 0x484, 0x485, 0x486, 0x487, 0x488, 0x489,
                0x559, 0x55a, 0x58a, 0x591, 0x592, 0x593, 0x594, 0x595, 0x596, 0x597, 0x598, 0x599, 0x59a,
                0x59b, 0x59c, 0x59d, 0x59e, 0x59f, 0x5a0, 0x5a1, 0x5a2, 0x5a3, 0x5a4, 0x5a5, 0x5a6, 0x5a7,
                0x5a8, 0x5a9, 0x5aa, 0x5ab, 0x5ac, 0x5ad, 0x5ae, 0x5af, 0x5b0, 0x5b1, 0x5b2, 0x5b3, 0x5b4,
                0x5b5, 0x5b6, 0x5b7, 0x5b8, 0x5b9, 0x5ba, 0x5bb, 0x5bc, 0x5bd, 0x5bf, 0x5c1, 0x5c2, 0x5c4,
                0x5c5, 0x5c6, 0x5c7, 0x606, 0x607, 0x608, 0x609, 0x60a, 0x63b, 0x63c, 0x63d, 0x63e, 0x63f,
                0x674, 0x6e5, 0x6e6, 0x70f, 0x76e, 0x76f, 0x770, 0x771, 0x772, 0x773, 0x774, 0x775, 0x776,
                0x777, 0x778, 0x779, 0x77a, 0x77b, 0x77c, 0x77d, 0x77e, 0x77f, 0xa51, 0xa75, 0xb44, 0xb62,
                0xb63, 0xc62, 0xc63, 0xce2, 0xce3, 0xd62, 0xd63, 0x135f, 0x200b, 0x200c, 0x200d, 0x200e,
                0x200f, 0x2028, 0x2029, 0x202a, 0x202b, 0x202c, 0x202d, 0x202e, 0x2044, 0x2071, 0xf701,
                0xf702, 0xf703, 0xf704, 0xf705, 0xf706, 0xf707, 0xf708, 0xf709, 0xf70a, 0xf70b, 0xf70c,
                0xf70d, 0xf70e, 0xf710, 0xf711, 0xf712, 0xf713, 0xf714, 0xf715, 0xf716, 0xf717, 0xf718,
                0xf719, 0xf71a, 0xfb1e, 0xfc5e, 0xfc5f, 0xfc60, 0xfc61, 0xfc62, 0xfeff, 0xfffc };
        StringBuilder b = new StringBuilder();
        int lastContinuous = -1;
        int span = 0;
        for (int i = 0; i < input.length; i++) {
            if (lastContinuous == -1 && i < input.length - 1 && input[i] + 1 == input[i + 1]) {
                lastContinuous = input[i];
                span = 1;
            } else {
                if (input[i] == lastContinuous + span) {
                    span++;
                } else if (lastContinuous != -1) {
                    if (b.length() > 0)
                        b.append("|");
                    b.append(String.format("[\\u%s-\\u%s]", zerolize(Integer.toHexString(lastContinuous)),
                            zerolize(Integer.toHexString(lastContinuous + span - 1))));
                    span = 0;
                    lastContinuous = -1;
                    i--;
                } else {
                    b.append("|\\u" + zerolize(Integer.toHexString(input[i])));
                }
            }
        }
        if (lastContinuous != -1) {
            if (b.length() > 0)
                b.append("|");
            b.append(String.format("[\\u%s-\\u%s]", zerolize(Integer.toHexString(lastContinuous)),
                    zerolize(Integer.toHexString(lastContinuous + span - 1))));
        }
        System.out.println(b.toString());
        Pattern pattern = Pattern.compile(b.toString());
        Matcher matcher = pattern.matcher("刘发仁\u200B");
        System.out.println(matcher.replaceAll(""));
    }
}

附上问题上半部分：https://blog.csdn.net/qq_26346941/article/details/80945453