1
0
mirror of https://github.com/git/git.git synced 2024-11-18 15:53:54 +01:00
git/url.c
Junio C Hamano 963838402a Merge branch 'jk/http-auth'
* jk/http-auth:
  http_init: accept separate URL parameter
  http: use hostname in credential description
  http: retry authentication failures for all http requests
  remote-curl: don't retry auth failures with dumb protocol
  improve httpd auth tests
  url: decode buffers that are not NUL-terminated
2011-10-17 21:37:15 -07:00

133 lines
2.8 KiB
C

#include "cache.h"
#include "url.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)
{
/* Is "scheme" part reasonable? */
if (!url || !is_urlschemechar(1, *url++))
return 0;
while (*url && *url != ':') {
if (!is_urlschemechar(0, *url++))
return 0;
}
/* We've seen "scheme"; we want colon-slash-slash */
return (url[0] == ':' && url[1] == '/' && url[2] == '/');
}
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;
}
static char *url_decode_internal(const char **query, int len,
const char *stop_at, struct strbuf *out,
int decode_plus)
{
const char *q = *query;
while (len) {
unsigned char c = *q;
if (!c)
break;
if (stop_at && strchr(stop_at, c)) {
q++;
len--;
break;
}
if (c == '%') {
int val = url_decode_char(q + 1);
if (0 <= val) {
strbuf_addch(out, val);
q += 3;
len -= 3;
continue;
}
}
if (decode_plus && c == '+')
strbuf_addch(out, ' ');
else
strbuf_addch(out, c);
q++;
len--;
}
*query = q;
return strbuf_detach(out, NULL);
}
char *url_decode(const char *url)
{
return url_decode_mem(url, strlen(url));
}
char *url_decode_mem(const char *url, int len)
{
struct strbuf out = STRBUF_INIT;
const char *colon = memchr(url, ':', len);
/* Skip protocol part if present */
if (colon && url < colon) {
strbuf_add(&out, url, colon - url);
len -= colon - url;
url = colon;
}
return url_decode_internal(&url, len, NULL, &out, 0);
}
char *url_decode_parameter_name(const char **query)
{
struct strbuf out = STRBUF_INIT;
return url_decode_internal(query, -1, "&=", &out, 1);
}
char *url_decode_parameter_value(const char **query)
{
struct strbuf out = STRBUF_INIT;
return url_decode_internal(query, -1, "&", &out, 1);
}
void end_url_with_slash(struct strbuf *buf, const char *url)
{
strbuf_addstr(buf, url);
if (buf->len && buf->buf[buf->len - 1] != '/')
strbuf_addstr(buf, "/");
}
void str_end_url_with_slash(const char *url, char **dest) {
struct strbuf buf = STRBUF_INIT;
end_url_with_slash(&buf, url);
free(*dest);
*dest = strbuf_detach(&buf, NULL);
}