2024年4月28日发(作者:)

* The recommended encoding scheme to use is UTF-8. However,

* for compatibility reasons, if an encoding is not specified,

* then the default encoding of the platform is used.

*

*

*

* For example using UTF-8 as the encoding scheme the string "The

* string ü@foo-bar" would get converted to

* "The+string+%C3%BC%40foo-bar" because in UTF-8 the character

* ü is encoded as two bytes C3 (hex) and BC (hex), and the

* character @ is encoded as one byte 40 (hex).

*

* @author Herb Jellinek

* @since JDK1.0

*/

private static class URLEncoder {

static BitSet dontNeedEncoding;

static final int caseDiff = ('a' - 'A');

static String dfltEncName = null;

static {

/* The list of characters that are not encoded has been

* determined as follows:

*

* RFC 2396 states:

* -----

* Data characters that are allowed in a URI but do not have a

* reserved purpose are called unreserved. These include upper

* and lower case letters, decimal digits, and a limited set of

* punctuation marks and symbols.

*

* unreserved = alphanum | mark

*

* mark = "-" | "_" | "." | "!" | "~" | "*" | "'" | "(" | ")"

*

* Unreserved characters can be escaped without changing the

* semantics of the URI, but this should not be done unless the

* URI is being used in a context that does not allow the

* unescaped character to appear.

* -----

*

* It appears that both Netscape and Internet Explorer escape

* all special characters from this list with the exception

* of "-", "_", ".", "*". While it is not clear why they are

* escaping the other characters, perhaps it is safest to

* assume that there might be contexts in which the others

* are unsafe if not escaped. Therefore, we will use the same

* list. It is also noteworthy that this is consistent with

* O'Reilly's "HTML: The Definitive Guide" (page 164).

*

* As a last note, Intenet Explorer does not encode the "@"

* character which is clearly not unreserved according to the

* RFC. We are being consistent with the RFC in this matter,

* as is Netscape.

*

*/

dontNeedEncoding = new BitSet(256);

int i;

for (i = 'a'; i <= 'z'; i++) {

(i);

}

for (i = 'A'; i <= 'Z'; i++) {

(i);

}

for (i = '0'; i <= '9'; i++) {

(i);

}

(' '); /* encoding a space to a + is done

* in the encode() method */

('-');

('_');

('.');

('*');

// 排除这两个特殊字符的编码

(':');

('/');

dfltEncName = ileged(

new GetPropertyAction("ng")

);