clone: do not include authentication data in guessed dir

If the URI contains authentication data and the URI's path
component is empty, we fail to guess a sensible directory name.
E.g. cloning a repository 'ssh://user:password@example.com/' we
guess a directory name 'password@example.com' where we would want
the hostname only, e.g. 'example.com'.

The naive way of just adding '@' as a path separator would break
cloning repositories like 'foo/bar@baz.git' (which would
currently become 'bar@baz' but would then become 'baz' only).
Instead fix this by first dropping the scheme and then greedily
scanning for an '@' sign until we find the first path separator.

Signed-off-by: Patrick Steinhardt <ps@pks.im>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
This commit is contained in:
Patrick Steinhardt 2015-08-10 17:48:23 +02:00 committed by Junio C Hamano
parent db2e220447
commit e895986727
2 changed files with 33 additions and 12 deletions

View File

@ -146,30 +146,51 @@ static char *get_repo_path(const char *repo, int *is_bundle)
static char *guess_dir_name(const char *repo, int is_bundle, int is_bare)
{
const char *end = repo + strlen(repo), *start;
const char *end = repo + strlen(repo), *start, *ptr;
size_t len;
char *dir;
/*
* Skip scheme.
*/
start = strstr(repo, "://");
if (start == NULL)
start = repo;
else
start += 3;
/*
* Skip authentication data. The stripping does happen
* greedily, such that we strip up to the last '@' inside
* the host part.
*/
for (ptr = start; ptr < end && !is_dir_sep(*ptr); ptr++) {
if (*ptr == '@')
start = ptr + 1;
}
/*
* Strip trailing spaces, slashes and /.git
*/
while (repo < end && (is_dir_sep(end[-1]) || isspace(end[-1])))
while (start < end && (is_dir_sep(end[-1]) || isspace(end[-1])))
end--;
if (end - repo > 5 && is_dir_sep(end[-5]) &&
if (end - start > 5 && is_dir_sep(end[-5]) &&
!strncmp(end - 4, ".git", 4)) {
end -= 5;
while (repo < end && is_dir_sep(end[-1]))
while (start < end && is_dir_sep(end[-1]))
end--;
}
/*
* Find last component, but be prepared that repo could have
* the form "remote.example.com:foo.git", i.e. no slash
* in the directory part.
* Find last component. To remain backwards compatible we
* also regard colons as path separators, such that
* cloning a repository 'foo:bar.git' would result in a
* directory 'bar' being guessed.
*/
start = end;
while (repo < start && !is_dir_sep(start[-1]) && start[-1] != ':')
start--;
ptr = end;
while (start < ptr && !is_dir_sep(ptr[-1]) && ptr[-1] != ':')
ptr--;
start = ptr;
/*
* Strip .{bundle,git}.

View File

@ -77,11 +77,11 @@ test_clone_dir host:foo/.git/// foo
# omitting the path should default to the hostname
test_clone_dir ssh://host/ host
test_clone_dir ssh://host:1234/ host fail
test_clone_dir ssh://user@host/ host fail
test_clone_dir ssh://user@host/ host
test_clone_dir host:/ host fail
# auth materials should be redacted
test_clone_dir ssh://user:password@host/ host fail
test_clone_dir ssh://user:password@host/ host
test_clone_dir ssh://user:password@host:1234/ host fail
test_clone_dir ssh://user:passw@rd@host:1234/ host fail
test_clone_dir user@host:/ host fail