t[0] = '\0';
for (i = 0, j = 0; s[i] != '\0'; i++) {
if (s[i] == '/') {
- memcpy(&t[j], "%2f", 3);
- j += 3;
- } else if (s[i] == '%') {
- memcpy(&t[j], "%25", 3);
- j += 3;
+ memcpy(&t[j], "\\x2f", 4);
+ j += 4;
+ } else if (s[i] == '\\') {
+ memcpy(&t[j], "\\x5c", 4);
+ j += 4;
} else {
t[j] = s[i];
j++;
size_t i, j;
for (i = 0, j = 0; s[i] != '\0'; j++) {
- if (memcmp(&s[i], "%2f", 3) == 0) {
+ if (memcmp(&s[i], "\\x2f", 4) == 0) {
s[j] = '/';
- i += 3;
- }else if (memcmp(&s[i], "%25", 3) == 0) {
- s[j] = '%';
- i += 3;
+ i += 4;
+ }else if (memcmp(&s[i], "\\x5c", 4) == 0) {
+ s[j] = '\\';
+ i += 4;
} else {
s[j] = s[i];
i++;
if ((str[i] >= '0' && str[i] <= '9') ||
(str[i] >= 'A' && str[i] <= 'Z') ||
(str[i] >= 'a' && str[i] <= 'z') ||
- strchr(" #$%+-./:=?@_,", str[i])) {
+ strchr("#$%+-./:=?@_,", str[i])) {
i++;
continue;
}
+
+ /* hex encoding */
+ if (str[i] == '\\' && str[i+1] == 'x') {
+ i += 2;
+ continue;
+ }
+
/* valid utf8 is accepted */
len = utf8_encoded_valid_unichar(&str[i]);
if (len > 1) {
continue;
}
+ /* whitespace replaced with ordinary space */
+ if (isspace(str[i])) {
+ str[i] = ' ';
+ i++;
+ replaced++;
+ continue;
+ }
+
/* everything else is garbage */
str[i] = '_';
i++;