[Java]Url路徑的Encode和Decode

1. Jdk自帶的

@Test
public void test01() throws Exception{
    String content = "http://localhost:8081/data/get Linkage?name=Product Hierarchy ABC";
    //进行encode
    String encode = null;
    try {
        encode = URLEncoder.encode(content, "utf-8");
        System.out.println(encode);
    } catch (UnsupportedEncodingException e) {
        e.printStackTrace();
    }

}

它處理的結果很蛋疼，空格變加號，斜杠也轉義了。

@Test
public void test02(){
    String content = "https://dev.ww.com/secure/31304/%E4%B8%9C%E8%8E%9EADD.xlsx";
    //进行decode
    String decode = null;
    try {
        decode = URLDecoder.decode(content, "utf-8");
        System.out.println(decode);
    } catch (UnsupportedEncodingException e) {
        e.printStackTrace();
    }

}

而當我們使用瀏覽器發請求時，他只是把空額用%20替換掉。

2. 升級版

吃水不忘挖井人，感謝大佬分享

blog.csdn.net/KokJuis/art…

2.1 URIEncoder

import java.io.UnsupportedEncodingException;

public class URIEncoder {
    public static final String ALLOWED_CHARS = "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_.!~*'()";

    public static String encodeURI(String str) throws UnsupportedEncodingException {
        String isoStr = new String(str.getBytes("UTF8"), "ISO-8859-1");
        char[] chars = isoStr.toCharArray();
        StringBuffer sb = new StringBuffer();
        for (int i = 0; i < chars.length; i++) {
            if ((chars[i] <= 'z' && chars[i] >= 'a') || (chars[i] <= 'Z' && chars[i] >= 'A')
                    || chars[i] == '-' || chars[i] == '_' || chars[i] == '.' || chars[i] == '!'
                    || chars[i] == '~' || chars[i] == '*' || chars[i] == ''' || chars[i] == '('
                    || chars[i] == ')' || chars[i] == ';' || chars[i] == '/' || chars[i] == '?'
                    || chars[i] == ':' || chars[i] == '@' || chars[i] == '&' || chars[i] == '='
                    || chars[i] == '+' || chars[i] == '$' || chars[i] == ',' || chars[i] == '#'
                    || (chars[i] <= '9' && chars[i] >= '0')) {
                sb.append(chars[i]);
            } else {
                sb.append("%");
                sb.append(Integer.toHexString(chars[i]));
            }
        }
        return sb.toString();
    }

    public static String encodeURIComponent(String input) {
        if (null == input || "".equals(input.trim())) {
            return input;
        }

        int l = input.length();
        StringBuilder o = new StringBuilder(l * 3);
        try {
            for (int i = 0; i < l; i++) {
                String e = input.substring(i, i + 1);
                if (ALLOWED_CHARS.indexOf(e) == -1) {
                    byte[] b = e.getBytes("utf-8");
                    o.append(getHex(b));
                    continue;
                }
                o.append(e);
            }
            return o.toString();
        } catch (UnsupportedEncodingException e) {
            e.printStackTrace();
        }
        return input;
    }

    private static String getHex(byte buf[]) {
        StringBuilder o = new StringBuilder(buf.length * 3);
        for (int i = 0; i < buf.length; i++) {
            int n = (int) buf[i] & 0xff;
            o.append("%");
            if (n < 0x10) {
                o.append("0");
            }
            o.append(Long.toString(n, 16).toUpperCase());
        }
        return o.toString();
    }
}

2.1 URIDecoder

public class URIDecoder {

    public static String decodeURIComponent(String encodedURI) {
        char actualChar;

        StringBuffer buffer = new StringBuffer();

        int bytePattern, sumb = 0;

        for (int i = 0, more = -1; i < encodedURI.length(); i++) {
            actualChar = encodedURI.charAt(i);

            switch (actualChar) {
                case '%': {
                    actualChar = encodedURI.charAt(++i);
                    int hb = (Character.isDigit(actualChar) ? actualChar - '0' : 10 + Character.toLowerCase(actualChar) - 'a') & 0xF;
                    actualChar = encodedURI.charAt(++i);
                    int lb = (Character.isDigit(actualChar) ? actualChar - '0' : 10 + Character.toLowerCase(actualChar) - 'a') & 0xF;
                    bytePattern = (hb << 4) | lb;
                    break;
                }
                case '+': {
                    bytePattern = ' ';
                    break;
                }
                default: {
                    bytePattern = actualChar;
                }
            }

            if ((bytePattern & 0xc0) == 0x80) { // 10xxxxxx
                sumb = (sumb << 6) | (bytePattern & 0x3f);
                if (--more == 0) buffer.append((char) sumb);
            } else if ((bytePattern & 0x80) == 0x00) { // 0xxxxxxx
                buffer.append((char) bytePattern);
            } else if ((bytePattern & 0xe0) == 0xc0) { // 110xxxxx
                sumb = bytePattern & 0x1f;
                more = 1;
            } else if ((bytePattern & 0xf0) == 0xe0) { // 1110xxxx
                sumb = bytePattern & 0x0f;
                more = 2;
            } else if ((bytePattern & 0xf8) == 0xf0) { // 11110xxx
                sumb = bytePattern & 0x07;
                more = 3;
            } else if ((bytePattern & 0xfc) == 0xf8) { // 111110xx
                sumb = bytePattern & 0x03;
                more = 4;
            } else { // 1111110x
                sumb = bytePattern & 0x01;
                more = 5;
            }
        }
        return buffer.toString();
    }

}