Java 实现 JavaScript 版本的 URL 编解码
encodeURIComponent
encodeURIComponent
安全字符(不会被编码的字符)为 a-z、A-Z、0-9、~、_、.、. (实际上 JavaScript 版本的安全字符还要更多一些,不过这些字符即使编码也不会影响使用)
private static final String HEX = "0123456789ABCDEF";
public static String encodeURIComponent(String str) {
if (str == null) return null;
byte[] bytes = str.getBytes(StandardCharsets.UTF_8);
StringBuilder builder = new StringBuilder(bytes.length);
for (byte c : bytes) {
if (c >= 'a' ? c <= 'z' || c == '~' :
c >= 'A' ? c <= 'Z' || c == '_' :
c >= '0' ? c <= '9' : c == '-' || c == '.')
builder.append((char)c);
else
builder.append('%')
.append(HEX.charAt(c >> 4 & 0xf))
.append(HEX.charAt(c & 0xf));
}
return builder.toString();
}decodeURIComponent
public static String decodeURIComponent(String str) {
if (str == null) return null;
int length = str.length();
byte[] bytes = new byte[length / 3];
StringBuilder builder = new StringBuilder(length);
for (int i = 0; i < length; ) {
char c = str.charAt(i);
if (c != '%') {
builder.append(c);
i += 1;
} else {
int j = 0;
do {
char h = str.charAt(i + 1);
char l = str.charAt(i + 2);
i += 3;
h -= '0';
if (h >= 10) {
h |= ' ';
h -= 'a' - '0';
if (h >= 6) throw new IllegalArgumentException();
h += 10;
}
l -= '0';
if (l >= 10) {
l |= ' ';
l -= 'a' - '0';
if (l >= 6) throw new IllegalArgumentException();
l += 10;
}
bytes[j++] = (byte)(h << 4 | l);
if (i >= length) break;
c = str.charAt(i);
} while (c == '%');
builder.append(new String(bytes, 0, j, UTF_8));
}
}
return builder.toString();
}参考链接
- https://stackoverflow.com/questions/607176/java-equivalent-to-javascripts-encodeuricomponent-that-produces-identical-outpu
- https://www.rfc-editor.org/rfc/rfc3986#section-2.2
- https://guava.dev/releases/19.0/api/docs/com/google/common/net/PercentEscaper.html