git/list[1] front-page[2] threads[3] people[4] search[5] about
 

[PATCH] submodule: Port resolve_relative_url from shell to C

From
Stefan Beller <sbeller@google.com>
Date
Dec 10, 2015, 01:07 UTC
Message-ID
<1449709654-30189-1-git-send-email-sbeller@google.com>

This reimplements the helper function `resolve_relative_url` in shell in C. This functionality is needed in C for introducing the groups feature later on. When using groups, the user should not need to run `git submodule init`, but it should be implicit at all appropriate places, which are all in C code. As the we would not just call out to `git submodule init`, but do a more fine grained structure there, we actually need all the init functionality in C before attempting the groups feature. To get the init functionality in C, rewriting the resolve_relative_url subfunction is a major step.

This also improves the performance: (Best out of 3) time ./t7400-submodule-basic.sh Before: real 0m9.575s user 0m2.683s sys 0m6.773s After: real 0m9.293s user 0m2.691s sys 0m6.549s

Signed-off-by: Stefan Beller <sbeller@google.com>
---
 This applies on origin/master, and I'd carry as its own feature branch
 as I am nowhere near done with the groups feature after reading Jens feedback.
 (It took me a while to identify this as a next best step.)
 
 Thanks,
 Stefan
 builtin/submodule--helper.c | 120 ++++++++++++++++++++++++++++++++++++++++++++
 git-submodule.sh            |  81 ++----------------------------
 2 files changed, 124 insertions(+), 77 deletions(-)
diff --git a/builtin/submodule--helper.c b/builtin/submodule--helper.c
index f4c3eff..f48b5b5 100644
--- a/builtin/submodule--helper.c
+++ b/builtin/submodule--helper.c
@@ -9,6 +9,125 @@
 #include "submodule-config.h"
 #include "string-list.h"
 #include "run-command.h"
+#include "remote.h"
+#include "refs.h"
+
+static const char *get_default_remote(void)
+{
+	char *dest = NULL;
+	unsigned char sha1[20];
+	int flag;
+	struct strbuf sb = STRBUF_INIT;
+	const char *refname = resolve_ref_unsafe("HEAD", 0, sha1, &flag);
+
+	if (!refname)
+		die("No such ref: HEAD");
+
+	refname = shorten_unambiguous_ref(refname, 0);
+	strbuf_addf(&sb, "branch.%s.remote", refname);
+	if (git_config_get_string(sb.buf, &dest))
+		return "origin";
+	else
+		return xstrdup(dest);
+}
+
+/*
+ * The function takes at most 2 arguments. The first argument is the
+ * URL that navigates to the submodule origin repo. When relative, this URL
+ * is relative to the superproject origin URL repo. The second up_path
+ * argument, if specified, is the relative path that navigates
+ * from the submodule working tree to the superproject working tree.
+ *
+ * The output of the function is the origin URL of the submodule.
+ *
+ * The output will either be an absolute URL or filesystem path (if the
+ * superproject origin URL is an absolute URL or filesystem path,
+ * respectively) or a relative file system path (if the superproject
+ * origin URL is a relative file system path).
+ *
+ * When the output is a relative file system path, the path is either
+ * relative to the submodule working tree, if up_path is specified, or to
+ * the superproject working tree otherwise.
+ */
+static const char *relative_url(const char *url, const char *up_path)
+{
+	int is_relative = 0;
+	size_t len;
+	char *remoteurl = NULL;
+	char *sep = "/";
+	const char *out;
+	struct strbuf sb = STRBUF_INIT;
+	const char *remote = get_default_remote();
+	strbuf_addf(&sb, "remote.%s.url", remote);
+
+	if (git_config_get_string(sb.buf, &remoteurl))
+		/* the repository is its own authoritative upstream */
+		remoteurl = xgetcwd();
+
+	if (strip_suffix(remoteurl, "/", &len))
+		remoteurl[len] = '\0';
+
+	if (strchr(remoteurl, ':') || skip_prefix(remoteurl, "/", &out))
+		is_relative = 0;
+	else if (skip_prefix(remoteurl, "./", &out) ||
+		    skip_prefix(remoteurl, "../", &out))
+		is_relative = 1;
+	else {
+		is_relative = 1;
+		strbuf_reset(&sb);
+		strbuf_addf(&sb, "./%s", remoteurl);
+		remoteurl = strbuf_detach(&sb, NULL);
+	}
+
+	while (url) {
+		if (skip_prefix(url, "../", &out)) {
+			char *rfind;
+			url = out;
+
+			rfind = strrchr(remoteurl, '/');
+			if (rfind)
+				*rfind = '\0';
+			else {
+				rfind = strrchr(remoteurl, ':');
+				if (rfind) {
+					*rfind = '\0';
+					sep = ":";
+				} else {
+					if (is_relative || !strcmp(".", remoteurl))
+						die(N_("cannot strip one component off url '%s'"), remoteurl);
+					else
+						remoteurl = ".";
+				}
+			}
+		} else if (skip_prefix(url, "./", &out))
+			url = out;
+		else
+			break;
+	}
+	strbuf_reset(&sb);
+	strbuf_addf(&sb, "%s%s%s", remoteurl, sep, url);
+
+	if (!skip_prefix(sb.buf, "./", &out))
+		out = sb.buf;
+	out = xstrdup(out);
+
+	strbuf_reset(&sb);
+	strbuf_addf(&sb, "%s%s", is_relative && up_path ? up_path : "", out);
+
+	free((char*)out);
+	return strbuf_detach(&sb, NULL);
+}
+
+static int resolve_relative_url(int argc, const char **argv, const char *prefix)
+{
+	if (argc == 2)
+		printf("%s\n", relative_url(argv[1], NULL));
+	else if (argc == 3)
+		printf("%s\n", relative_url(argv[1], argv[2]));
+	else
+		die("BUG: resolve_relative_url only accepts one or two arguments");
+	return 0;
+}
 
 struct module_list {
 	const struct cache_entry **entries;
@@ -264,6 +383,7 @@ static struct cmd_struct commands[] = {
 	{"list", module_list},
 	{"name", module_name},
 	{"clone", module_clone},
+	{"resolve_relative_url", resolve_relative_url},
 };
 
 int cmd_submodule__helper(int argc, const char **argv, const char *prefix)
diff --git a/git-submodule.sh b/git-submodule.sh
index 9bc5c5f..6a7a3e4 100755
--- a/git-submodule.sh
+++ b/git-submodule.sh
@@ -46,79 +46,6 @@ prefix=
 custom_name=
 depth=
 
-# The function takes at most 2 arguments. The first argument is the
-# URL that navigates to the submodule origin repo. When relative, this URL
-# is relative to the superproject origin URL repo. The second up_path
-# argument, if specified, is the relative path that navigates
-# from the submodule working tree to the superproject working tree.
-#
-# The output of the function is the origin URL of the submodule.
-#
-# The output will either be an absolute URL or filesystem path (if the
-# superproject origin URL is an absolute URL or filesystem path,
-# respectively) or a relative file system path (if the superproject
-# origin URL is a relative file system path).
-#
-# When the output is a relative file system path, the path is either
-# relative to the submodule working tree, if up_path is specified, or to
-# the superproject working tree otherwise.
-resolve_relative_url ()
-{
-	remote=$(get_default_remote)
-	remoteurl=$(git config "remote.$remote.url") ||
-		remoteurl=$(pwd) # the repository is its own authoritative upstream
-	url="$1"
-	remoteurl=${remoteurl%/}
-	sep=/
-	up_path="$2"
-
-	case "$remoteurl" in
-	*:*|/*)
-		is_relative=
-		;;
-	./*|../*)
-		is_relative=t
-		;;
-	*)
-		is_relative=t
-		remoteurl="./$remoteurl"
-		;;
-	esac
-
-	while test -n "$url"
-	do
-		case "$url" in
-		../*)
-			url="${url#../}"
-			case "$remoteurl" in
-			*/*)
-				remoteurl="${remoteurl%/*}"
-				;;
-			*:*)
-				remoteurl="${remoteurl%:*}"
-				sep=:
-				;;
-			*)
-				if test -z "$is_relative" || test "." = "$remoteurl"
-				then
-					die "$(eval_gettext "cannot strip one component off url '\$remoteurl'")"
-				else
-					remoteurl=.
-				fi
-				;;
-			esac
-			;;
-		./*)
-			url="${url#./}"
-			;;
-		*)
-			break;;
-		esac
-	done
-	remoteurl="$remoteurl$sep${url%/}"
-	echo "${is_relative:+${up_path}}${remoteurl#./}"
-}
-
 # Resolve a path to be relative to another path.  This is intended for
 # converting submodule paths when git-submodule is run in a subdirectory
 # and only handles paths where the directory separator is '/'.
@@ -281,7 +208,7 @@ cmd_add()
 		die "$(gettext "Relative path can only be used from the toplevel of the working tree")"
 
 		# dereference source url relative to parent's url
-		realrepo=$(resolve_relative_url "$repo") || exit
+		realrepo=$(git submodule--helper resolve_relative_url "$repo") || exit
 		;;
 	*:*|/*)
 		# absolute url
@@ -485,7 +412,7 @@ cmd_init()
 			# Possibly a url relative to parent
 			case "$url" in
 			./*|../*)
-				url=$(resolve_relative_url "$url") || exit
+				url=$(git submodule--helper resolve_relative_url "$url") || exit
 				;;
 			esac
 			git config submodule."$name".url "$url" ||
@@ -1190,9 +1117,9 @@ cmd_sync()
 			# guarantee a trailing /
 			up_path=${up_path%/}/ &&
 			# path from submodule work tree to submodule origin repo
-			sub_origin_url=$(resolve_relative_url "$url" "$up_path") &&
+			sub_origin_url=$(git submodule--helper resolve_relative_url "$url" "$up_path") &&
 			# path from superproject work tree to submodule origin repo
-			super_config_url=$(resolve_relative_url "$url") || exit
+			super_config_url=$(git submodule--helper resolve_relative_url "$url") || exit
 			;;
 		*)
 			sub_origin_url="$url"
-- 
2.6.3.470.g4b82c23.dirty
Next: Johannes Sixt
Message 1 of 11 in “submodule: Port resolve_relative_url from shell to C”
  1. submodule: Port resolve_relative_url from shell to CStefan Beller, Dec 10, 2015
  2. Johannes SixtDec 10, 2015
  3. Stefan BellerDec 16, 2015
  4. [PATCHv2] Porting resolve_relative_url from shell to CStefan Beller, Dec 17, 2015
  5. [PATCHv2] submodule: Port resolve_relative_url from shell to CStefan Beller, Dec 17, 2015
  6. Eric SunshineDec 17, 2015
  7. Johannes SixtDec 17, 2015
  8. Johannes SixtDec 17, 2015
  9. Jeff KingDec 18, 2015
  10. Stefan BellerJan 11, 2016
  11. Torsten BögershausenDec 17, 2015

Read the whole thread, see it on lore, or plain text.

$ cat FOOTERMessages come from the public archive at lore.kernel.org/git, fetched every hour. The front page is chosen and written each morning by an AI editor and can be wrong; the threads themselves are the record. About and API. For agents: an MCP server at https://gitlist.dev/mcp, and any thread, story or person page as Markdown by adding .md to its URL (or sending Accept: text/markdown). Details in /llms.txt.