Revision 40a18fc77ca3ba1b018f0fbdcbdf4a6d237aadf3 authored by Jeff King on 25 February 2017, 19:18:31 UTC, committed by Junio C Hamano on 27 February 2017, 18:35:24 UTC
This variable needs to be specified to make some types of
non-basic authentication work, but ideally this would just
work out of the box for everyone.

However, simply setting it to "1" by default introduces an
extra round-trip for cases where it _isn't_ useful. We end
up sending a bogus empty credential that the server rejects.

Instead, let's introduce an automatic mode, that works like
this:

  1. We won't try to send the bogus credential on the first
     request. We'll wait to get an HTTP 401, as usual.

  2. After seeing an HTTP 401, the empty-auth hack will kick
     in only when we know there is an auth method available
     that might make use of it (i.e., something besides
     "Basic" or "Digest").

That should make it work out of the box, without incurring
any extra round-trips for people hitting Basic-only servers.

This _does_ incur an extra round-trip if you really want to
use "Basic" but your server advertises other methods (the
emptyauth hack will kick in but fail, and then Git will
actually ask for a password).

The auto mode may incur an extra round-trip over setting
http.emptyauth=true, because part of the emptyauth hack is
to feed this blank password to curl even before we've made a
single request.

Helped-by: Johannes Schindelin <Johannes.Schindelin@gmx.de>
Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
1 parent 840398f
Raw File
url.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 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 = hex2chr(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);
	strbuf_complete(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);
}
back to top