mirror of
https://github.com/git-for-windows/git.git
synced 2026-06-27 22:28:38 -05:00
The Git project is not exactly the easiest project to get started in: it's written in C and POSIX shell, with bits of Perl, Rust and other languages sprinkled into it. On top of that, the project has grown somewhat organically over time, making the codebase hard to navigate. These are problems that we're aware of, and there have been and still are efforts to clean up some of the technical debt that is natural to exist an a project that is more than 20 years old. Furthermore, we provide resources to newcomers that help them out like our coding guidelines, code of conduct or "MyFirstContribution.adoc". But there is a rather practical problem: finding your way around in our project's tree is not easy. Doing a directory listing in the top-level directory will present you with more than 550 files, which makes it extremely hard for a newcomer to figure out what files they are even supposed to look at. This makes the onboarding experience somewhat harder than it really needs to be. This isn't only a problem for newcomers though, as I myself struggle to find the files I am looking for because of the sheer number of files. Besides the problem of discoverability it also creates a problem of structure. It is not obvious at all which files are part of "libgit.a" and which files are only linked into our final executables. So while we have this split in our build systems, that split is not evident at all in our tree. Introduce a new "lib/" directory and move all of our sources for "libgit.a" into it to fix these issues. It makes the split we have evident and reduces the number of files in our top-level tree from 550 files to ~80 files. This is still a lot of files, but it's significantly easier to navigate already. Furthermore, we can further iterate after this step and think about introducing a better structure for remaining files, as well. Signed-off-by: Patrick Steinhardt <ps@pks.im> Signed-off-by: Junio C Hamano <gitster@pobox.com>
158 lines
3.5 KiB
C
158 lines
3.5 KiB
C
#include "git-compat-util.h"
|
|
#include "hex-ll.h"
|
|
#include "strbuf.h"
|
|
#include "url.h"
|
|
|
|
int is_rfc3986_unreserved(char ch)
|
|
{
|
|
return isalnum(ch) ||
|
|
ch == '-' || ch == '_' || ch == '.' || ch == '~';
|
|
}
|
|
|
|
int is_casefolding_rfc3986_unreserved(char c)
|
|
{
|
|
return (c >= 'a' && c <= 'z') ||
|
|
(c >= '0' && c <= '9') ||
|
|
c == '-' || c == '.' || c == '_' || c == '~';
|
|
}
|
|
|
|
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 slightly 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 == '%' && (len < 0 || len >= 3)) {
|
|
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_percent_decode(const char *encoded)
|
|
{
|
|
struct strbuf out = STRBUF_INIT;
|
|
return url_decode_internal(&encoded, strlen(encoded), 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);
|
|
}
|
|
|
|
int url_is_local_not_ssh(const char *url)
|
|
{
|
|
const char *colon = strchr(url, ':');
|
|
const char *slash = strchr(url, '/');
|
|
return !colon || (slash && slash < colon) ||
|
|
(has_dos_drive_prefix(url) && is_valid_path(url));
|
|
}
|
|
|
|
enum url_scheme url_get_scheme(const char *name)
|
|
{
|
|
if (!strcmp(name, "ssh"))
|
|
return URL_SCHEME_SSH;
|
|
if (!strcmp(name, "git"))
|
|
return URL_SCHEME_GIT;
|
|
if (!strcmp(name, "git+ssh")) /* deprecated - do not use */
|
|
return URL_SCHEME_SSH;
|
|
if (!strcmp(name, "ssh+git")) /* deprecated - do not use */
|
|
return URL_SCHEME_SSH;
|
|
if (!strcmp(name, "file"))
|
|
return URL_SCHEME_FILE;
|
|
return URL_SCHEME_UNKNOWN;
|
|
}
|