2010-05-23 17:17:55 +08:00
|
|
|
#include "cache.h"
|
|
|
|
|
|
|
|
int is_urlschemechar(int first_flag, int ch)
|
|
|
|
{
|
|
|
|
/*
|
|
|
|
* The set of valid URL schemes, as per STD66 (RFC3986) is
|
|
|
|
* '[A-Za-z][A-Za-z0-9+.-]*'. But use sightly looser check
|
|
|
|
* of '[A-Za-z0-9][A-Za-z0-9+.-]*' because earlier version
|
|
|
|
* of check used '[A-Za-z0-9]+' so not to break any remote
|
|
|
|
* helpers.
|
|
|
|
*/
|
|
|
|
int alphanumeric, special;
|
|
|
|
alphanumeric = ch > 0 && isalnum(ch);
|
|
|
|
special = ch == '+' || ch == '-' || ch == '.';
|
|
|
|
return alphanumeric || (!first_flag && special);
|
|
|
|
}
|
|
|
|
|
|
|
|
int is_url(const char *url)
|
|
|
|
{
|
|
|
|
const char *url2, *first_slash;
|
|
|
|
|
|
|
|
if (!url)
|
|
|
|
return 0;
|
|
|
|
url2 = url;
|
|
|
|
first_slash = strchr(url, '/');
|
|
|
|
|
|
|
|
/* Input with no slash at all or slash first can't be URL. */
|
|
|
|
if (!first_slash || first_slash == url)
|
|
|
|
return 0;
|
|
|
|
/* Character before must be : and next must be /. */
|
|
|
|
if (first_slash[-1] != ':' || first_slash[1] != '/')
|
|
|
|
return 0;
|
|
|
|
/* There must be something before the :// */
|
|
|
|
if (first_slash == url + 1)
|
|
|
|
return 0;
|
|
|
|
/*
|
|
|
|
* Check all characters up to first slash - 1. Only alphanum
|
|
|
|
* is allowed.
|
|
|
|
*/
|
|
|
|
url2 = url;
|
|
|
|
while (url2 < first_slash - 1) {
|
|
|
|
if (!is_urlschemechar(url2 == url, (unsigned char)*url2))
|
|
|
|
return 0;
|
|
|
|
url2++;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Valid enough. */
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int url_decode_char(const char *q)
|
|
|
|
{
|
|
|
|
int i;
|
|
|
|
unsigned char val = 0;
|
|
|
|
for (i = 0; i < 2; i++) {
|
|
|
|
unsigned char c = *q++;
|
|
|
|
val <<= 4;
|
|
|
|
if (c >= '0' && c <= '9')
|
|
|
|
val += c - '0';
|
|
|
|
else if (c >= 'a' && c <= 'f')
|
|
|
|
val += c - 'a' + 10;
|
|
|
|
else if (c >= 'A' && c <= 'F')
|
|
|
|
val += c - 'A' + 10;
|
|
|
|
else
|
|
|
|
return -1;
|
|
|
|
}
|
|
|
|
return val;
|
|
|
|
}
|
|
|
|
|
2010-06-24 01:27:39 +08:00
|
|
|
static char *url_decode_internal(const char **query, const char *stop_at, struct strbuf *out)
|
2010-05-23 17:17:55 +08:00
|
|
|
{
|
|
|
|
const char *q = *query;
|
|
|
|
|
|
|
|
do {
|
|
|
|
unsigned char c = *q;
|
|
|
|
|
|
|
|
if (!c)
|
|
|
|
break;
|
|
|
|
if (stop_at && strchr(stop_at, c)) {
|
|
|
|
q++;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (c == '%') {
|
|
|
|
int val = url_decode_char(q + 1);
|
|
|
|
if (0 <= val) {
|
2010-06-24 01:27:39 +08:00
|
|
|
strbuf_addch(out, val);
|
2010-05-23 17:17:55 +08:00
|
|
|
q += 3;
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
if (c == '+')
|
2010-06-24 01:27:39 +08:00
|
|
|
strbuf_addch(out, ' ');
|
2010-05-23 17:17:55 +08:00
|
|
|
else
|
2010-06-24 01:27:39 +08:00
|
|
|
strbuf_addch(out, c);
|
2010-05-23 17:17:55 +08:00
|
|
|
q++;
|
|
|
|
} while (1);
|
|
|
|
*query = q;
|
2010-06-24 01:27:39 +08:00
|
|
|
return strbuf_detach(out, NULL);
|
2010-05-23 17:17:55 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
char *url_decode(const char *url)
|
|
|
|
{
|
2010-06-24 01:27:39 +08:00
|
|
|
struct strbuf out = STRBUF_INIT;
|
2010-06-25 04:36:30 +08:00
|
|
|
const char *colon = strchr(url, ':');
|
2010-06-24 01:27:39 +08:00
|
|
|
|
|
|
|
/* Skip protocol part if present */
|
2010-06-25 04:36:30 +08:00
|
|
|
if (colon && url < colon) {
|
|
|
|
strbuf_add(&out, url, colon - url);
|
|
|
|
url = colon;
|
2010-06-24 01:27:39 +08:00
|
|
|
}
|
|
|
|
return url_decode_internal(&url, NULL, &out);
|
2010-05-23 17:17:55 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
char *url_decode_parameter_name(const char **query)
|
|
|
|
{
|
2010-06-24 01:27:39 +08:00
|
|
|
struct strbuf out = STRBUF_INIT;
|
|
|
|
return url_decode_internal(query, "&=", &out);
|
2010-05-23 17:17:55 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
char *url_decode_parameter_value(const char **query)
|
|
|
|
{
|
2010-06-24 01:27:39 +08:00
|
|
|
struct strbuf out = STRBUF_INIT;
|
|
|
|
return url_decode_internal(query, "&", &out);
|
2010-05-23 17:17:55 +08:00
|
|
|
}
|