Function ap_proxy_canonenc_ex

modules/proxy/proxy_util.c:220–313

* Convert a URL-encoded string to canonical form. * It decodes characters which need not be encoded, * and encodes those which must be encoded, and does not touch * those which must not be touched. */

 * those which must not be touched.
 */
PROXY_DECLARE(char *)ap_proxy_canonenc_ex(apr_pool_t *p, const char *x, int len,
                                          enum enctype t, int flags,
                                          int proxyreq)
{
    int i, j, ch;
    char *y;
    char *allowed;  /* characters which should not be encoded */
    char *reserved; /* characters which much not be en/de-coded */
    int forcedec = flags & PROXY_CANONENC_FORCEDEC;
    int noencslashesenc = flags & PROXY_CANONENC_NOENCODEDSLASHENCODING;

/*
 * N.B. in addition to :@&=, this allows ';' in an http path
 * and '?' in an ftp path -- this may be revised
 *
 * Also, it makes a '+' character in a search string reserved, as
 * it may be form-encoded. (Although RFC 1738 doesn't allow this -
 * it only permits ; / ? : @ = & as reserved chars.)
 */
    if (t == enc_path) {
        allowed = "~$-_.+!*'(),;:@&=";
    }
    else if (t == enc_search) {
        allowed = "$-_.!*'(),;:@&=";
    }
    else if (t == enc_user) {
        allowed = "$-_.+!*'(),;@&=";
    }
    else if (t == enc_fpath) {
        allowed = "$-_.+!*'(),?:@&=";
    }
    else {            /* if (t == enc_parm) */
        allowed = "$-_.+!*'(),?/:@&=";
    }

    if (t == enc_path) {
        reserved = "/";
    }
    else if (t == enc_search) {
        reserved = "+";
    }
    else {
        reserved = "";
    }

    y = apr_palloc(p, 3 * len + 1);

    for (i = 0, j = 0; i < len; i++, j++) {
/* always handle '/' first */
        ch = x[i];
        if (strchr(reserved, ch)) {
            y[j] = ch;
            continue;
        }
/*
 * decode it if not already done. do not decode reverse proxied URLs
 * unless specifically forced
 */