submodule-config.c: strengthen URL fsck check

Update the validation of "curl URL" submodule URLs (i.e. those that specify
an "http[s]" or "ftp[s]" protocol) in 'check_submodule_url()' to catch more
invalid URLs. The existing validation using 'credential_from_url_gently()'
parses certain URLs incorrectly, leading to invalid submodule URLs passing
'git fsck' checks. Conversely, 'url_normalize()' - used to validate remote
URLs in 'remote_get()' - correctly identifies the invalid URLs missed by
'credential_from_url_gently()'.

To catch more invalid cases, replace 'credential_from_url_gently()' with
'url_normalize()' followed by a 'url_decode()' and a check for newlines
(mirroring 'check_url_component()' in the 'credential_from_url_gently()'
validation).

Signed-off-by: Victoria Dye <vdye@github.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
This commit is contained in:
Victoria Dye
2024-01-18 01:55:18 +00:00
committed by Junio C Hamano
parent 7e2fc39d8c
commit 8430b438f6
2 changed files with 12 additions and 15 deletions

View File

@ -15,7 +15,7 @@
#include "thread-utils.h"
#include "tree-walk.h"
#include "url.h"
#include "credential.h"
#include "urlmatch.h"
/*
* submodule cache lookup structure
@ -350,12 +350,18 @@ int check_submodule_url(const char *url)
}
else if (url_to_curl_url(url, &curl_url)) {
struct credential c = CREDENTIAL_INIT;
int ret = 0;
if (credential_from_url_gently(&c, curl_url, 1) ||
!*c.host)
char *normalized = url_normalize(curl_url, NULL);
if (normalized) {
char *decoded = url_decode(normalized);
if (strchr(decoded, '\n'))
ret = -1;
free(normalized);
free(decoded);
} else {
ret = -1;
credential_clear(&c);
}
return ret;
}