Merge branch 'db/vcs-helper'

* db/vcs-helper:
  Makefile: remove remnant of separate http/https/ftp helpers
  Use a clearer style to issue commands to remote helpers
  Make the "traditionally-supported" URLs a special case
  Makefile: install hardlinks for git-remote-<scheme> supported by libcurl if possible
  Makefile: do not link three copies of git-remote-* programs
  Makefile: git-http-fetch does not need expat
  http-fetch: Fix Makefile dependancies
  Add transport native helper executables to .gitignore
  git-http-fetch: not a builtin
  Use an external program to implement fetching with curl
  Add support for external programs for handling native fetches

9 files changed, 406 insertions, 144 deletions

diff --git a/.gitignore b/.gitignore
index 10808e3a7..47672b0c1 100644
--- a/.gitignore
+++ b/.gitignore
@@ -104,6 +104,7 @@ git-receive-pack
 git-reflog
 git-relink
 git-remote
+git-remote-curl
 git-repack
 git-replace
 git-repo-config
diff --git a/Documentation/git-remote-helpers.txt b/Documentation/git-remote-helpers.txt
new file mode 100644
index 000000000..173ee232f
--- /dev/null
+++ b/Documentation/git-remote-helpers.txt
@@ -0,0 +1,71 @@
+git-remote-helpers(1)
+=====================
+
+NAME
+----
+git-remote-helpers - Helper programs for interoperation with remote git
+
+SYNOPSIS
+--------
+'git remote-<transport>' <remote>
+
+DESCRIPTION
+-----------
+
+These programs are normally not used directly by end users, but are
+invoked by various git programs that interact with remote repositories
+when the repository they would operate on will be accessed using
+transport code not linked into the main git binary. Various particular
+helper programs will behave as documented here.
+
+COMMANDS
+--------
+
+Commands are given by the caller on the helper's standard input, one per line.
+
+'capabilities'::
+	Lists the capabilities of the helper, one per line, ending
+	with a blank line.
+
+'list'::
+	Lists the refs, one per line, in the format "<value> <name>
+	[<attr> ...]". The value may be a hex sha1 hash, "@<dest>" for
+	a symref, or "?" to indicate that the helper could not get the
+	value of the ref. A space-separated list of attributes follows
+	the name; unrecognized attributes are ignored. After the
+	complete list, outputs a blank line.
+
+'fetch' <sha1> <name>::
+	Fetches the given object, writing the necessary objects to the
+	database. Outputs a blank line when the fetch is
+	complete. Only objects which were reported in the ref list
+	with a sha1 may be fetched this way.
++
+Supported if the helper has the "fetch" capability.
+
+If a fatal error occurs, the program writes the error message to
+stderr and exits. The caller should expect that a suitable error
+message has been printed if the child closes the connection without
+completing a valid response for the current command.
+
+Additional commands may be supported, as may be determined from
+capabilities reported by the helper.
+
+CAPABILITIES
+------------
+
+'fetch'::
+	This helper supports the 'fetch' command.
+
+REF LIST ATTRIBUTES
+-------------------
+
+None are defined yet, but the caller must accept any which are supplied.
+
+Documentation
+-------------
+Documentation by Daniel Barkalow.
+
+GIT
+---
+Part of the linkgit:git[1] suite
diff --git a/Makefile b/Makefile
index 1cc9a4183..01eea770d 100644
--- a/Makefile
+++ b/Makefile
@@ -380,7 +380,8 @@ BUILT_INS += git-stage$X
 BUILT_INS += git-status$X
 BUILT_INS += git-whatchanged$X
 
-# what 'all' will build and 'install' will install, in gitexecdir
+# what 'all' will build and 'install' will install in gitexecdir,
+# excluding programs for built-in commands
 ALL_PROGRAMS = $(PROGRAMS) $(SCRIPTS)
 
 # what 'all' will build but not install in gitexecdir
@@ -547,6 +548,7 @@ LIB_OBJS += symlinks.o
 LIB_OBJS += tag.o
 LIB_OBJS += trace.o
 LIB_OBJS += transport.o
+LIB_OBJS += transport-helper.o
 LIB_OBJS += tree-diff.o
 LIB_OBJS += tree.o
 LIB_OBJS += tree-walk.o
@@ -973,9 +975,7 @@ else
 	else
 		CURL_LIBCURL = -lcurl
 	endif
-	BUILTIN_OBJS += builtin-http-fetch.o
-	EXTLIBS += $(CURL_LIBCURL)
-	LIB_OBJS += http.o http-walker.o
+	PROGRAMS += git-remote-curl$X git-http-fetch$X
 	curl_check := $(shell (echo 070908; curl-config --vernum) | sort -r | sed -ne 2p)
 	ifeq "$(curl_check)" "070908"
 		ifndef NO_EXPAT
@@ -1249,6 +1249,7 @@ ifndef V
 	QUIET_LINK     = @echo '   ' LINK $@;
 	QUIET_BUILT_IN = @echo '   ' BUILTIN $@;
 	QUIET_GEN      = @echo '   ' GEN $@;
+	QUIET_LNCP     = @echo '   ' LN/CP $@;
 	QUIET_SUBDIR0  = +@subdir=
 	QUIET_SUBDIR1  = ;$(NO_SUBDIR) echo '   ' SUBDIR $$subdir; \
 			 $(MAKE) $(PRINT_DIR) -C $$subdir
@@ -1476,12 +1477,21 @@ git-imap-send$X: imap-send.o $(GITLIBS)
 	$(QUIET_LINK)$(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) $(filter %.o,$^) \
 		$(LIBS) $(OPENSSL_LINK) $(OPENSSL_LIBSSL)
 
-http.o http-walker.o http-push.o transport.o: http.h
+http.o http-walker.o http-push.o: http.h
 
+http.o http-walker.o: $(LIB_H)
+
+git-http-fetch$X: revision.o http.o http-walker.o http-fetch.o $(GITLIBS)
+	$(QUIET_LINK)$(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) $(filter %.o,$^) \
+		$(LIBS) $(CURL_LIBCURL)
 git-http-push$X: revision.o http.o http-push.o $(GITLIBS)
 	$(QUIET_LINK)$(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) $(filter %.o,$^) \
 		$(LIBS) $(CURL_LIBCURL) $(EXPAT_LIBEXPAT)
 
+git-remote-curl$X: remote-curl.o http.o http-walker.o $(GITLIBS)
+	$(QUIET_LINK)$(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) $(filter %.o,$^) \
+		$(LIBS) $(CURL_LIBCURL) $(EXPAT_LIBEXPAT)
+
 $(LIB_OBJS) $(BUILTIN_OBJS): $(LIB_H)
 $(patsubst git-%$X,%.o,$(PROGRAMS)) git.o: $(LIB_H) $(wildcard */*.h)
 builtin-revert.o wt-status.o: wt-status.h
diff --git a/git.c b/git.c
index 271579c35..9883009b5 100644
--- a/git.c
+++ b/git.c
@@ -312,9 +312,6 @@ static void handle_internal_command(int argc, const char **argv)
 		{ "get-tar-commit-id", cmd_get_tar_commit_id },
 		{ "grep", cmd_grep, RUN_SETUP | USE_PAGER },
 		{ "help", cmd_help },
-#ifndef NO_CURL
-		{ "http-fetch", cmd_http_fetch, RUN_SETUP },
-#endif
 		{ "init", cmd_init_db },
 		{ "init-db", cmd_init_db },
 		{ "log", cmd_log, RUN_SETUP | USE_PAGER },
diff --git a/builtin-http-fetch.c b/http-fetch.c
index f3e63d720..e8f44babd 100644
--- a/builtin-http-fetch.c
+++ b/http-fetch.c
@@ -1,8 +1,9 @@
 #include "cache.h"
 #include "walker.h"
 
-int cmd_http_fetch(int argc, const char **argv, const char *prefix)
+int main(int argc, const char **argv)
 {
+	const char *prefix;
 	struct walker *walker;
 	int commits_on_stdin = 0;
 	int commits;
@@ -18,6 +19,8 @@ int cmd_http_fetch(int argc, const char **argv, const char *prefix)
 	int get_verbosely = 0;
 	int get_recover = 0;
 
+	prefix = setup_git_directory();
+
 	git_config(git_default_config, NULL);
 
 	while (arg < argc && argv[arg][0] == '-') {
diff --git a/remote-curl.c b/remote-curl.c
new file mode 100644
index 000000000..ad6a1637b
--- /dev/null
+++ b/remote-curl.c
@@ -0,0 +1,139 @@
+#include "cache.h"
+#include "remote.h"
+#include "strbuf.h"
+#include "walker.h"
+#include "http.h"
+
+static struct ref *get_refs(struct walker *walker, const char *url)
+{
+	struct strbuf buffer = STRBUF_INIT;
+	char *data, *start, *mid;
+	char *ref_name;
+	char *refs_url;
+	int i = 0;
+	int http_ret;
+
+	struct ref *refs = NULL;
+	struct ref *ref = NULL;
+	struct ref *last_ref = NULL;
+
+	refs_url = xmalloc(strlen(url) + 11);
+	sprintf(refs_url, "%s/info/refs", url);
+
+	http_ret = http_get_strbuf(refs_url, &buffer, HTTP_NO_CACHE);
+	switch (http_ret) {
+	case HTTP_OK:
+		break;
+	case HTTP_MISSING_TARGET:
+		die("%s not found: did you run git update-server-info on the"
+		    " server?", refs_url);
+	default:
+		http_error(refs_url, http_ret);
+		die("HTTP request failed");
+	}
+
+	data = buffer.buf;
+	start = NULL;
+	mid = data;
+	while (i < buffer.len) {
+		if (!start) {
+			start = &data[i];
+		}
+		if (data[i] == '\t')
+			mid = &data[i];
+		if (data[i] == '\n') {
+			data[i] = 0;
+			ref_name = mid + 1;
+			ref = xmalloc(sizeof(struct ref) +
+				      strlen(ref_name) + 1);
+			memset(ref, 0, sizeof(struct ref));
+			strcpy(ref->name, ref_name);
+			get_sha1_hex(start, ref->old_sha1);
+			if (!refs)
+				refs = ref;
+			if (last_ref)
+				last_ref->next = ref;
+			last_ref = ref;
+			start = NULL;
+		}
+		i++;
+	}
+
+	strbuf_release(&buffer);
+
+	ref = alloc_ref("HEAD");
+	if (!walker->fetch_ref(walker, ref) &&
+	    !resolve_remote_symref(ref, refs)) {
+		ref->next = refs;
+		refs = ref;
+	} else {
+		free(ref);
+	}
+
+	strbuf_release(&buffer);
+	free(refs_url);
+	return refs;
+}
+
+int main(int argc, const char **argv)
+{
+	struct remote *remote;
+	struct strbuf buf = STRBUF_INIT;
+	const char *url;
+	struct walker *walker = NULL;
+
+	setup_git_directory();
+	if (argc < 2) {
+		fprintf(stderr, "Remote needed\n");
+		return 1;
+	}
+
+	remote = remote_get(argv[1]);
+
+	if (argc > 2) {
+		url = argv[2];
+	} else {
+		url = remote->url[0];
+	}
+
+	do {
+		if (strbuf_getline(&buf, stdin, '\n') == EOF)
+			break;
+		if (!prefixcmp(buf.buf, "fetch ")) {
+			char *obj = buf.buf + strlen("fetch ");
+			if (!walker)
+				walker = get_http_walker(url, remote);
+			walker->get_all = 1;
+			walker->get_tree = 1;
+			walker->get_history = 1;
+			walker->get_verbosely = 0;
+			walker->get_recover = 0;
+			if (walker_fetch(walker, 1, &obj, NULL, NULL))
+				die("Fetch failed.");
+			printf("\n");
+			fflush(stdout);
+		} else if (!strcmp(buf.buf, "list")) {
+			struct ref *refs;
+			struct ref *posn;
+			if (!walker)
+				walker = get_http_walker(url, remote);
+			refs = get_refs(walker, url);
+			for (posn = refs; posn; posn = posn->next) {
+				if (posn->symref)
+					printf("@%s %s\n", posn->symref, posn->name);
+				else
+					printf("%s %s\n", sha1_to_hex(posn->old_sha1), posn->name);
+			}
+			printf("\n");
+			fflush(stdout);
+		} else if (!strcmp(buf.buf, "capabilities")) {
+			printf("fetch\n");
+			printf("\n");
+			fflush(stdout);
+		} else {
+			return 1;
+		}
+		strbuf_reset(&buf);
+	} while (1);
+	return 0;
+}
diff --git a/transport-helper.c b/transport-helper.c
new file mode 100644
index 000000000..b1ea7e6f4
--- /dev/null
+++ b/transport-helper.c
@@ -0,0 +1,172 @@
+#include "cache.h"
+#include "transport.h"
+
+#include "run-command.h"
+#include "commit.h"
+#include "diff.h"
+#include "revision.h"
+
+struct helper_data
+{
+	const char *name;
+	struct child_process *helper;
+	unsigned fetch : 1;
+};
+
+static struct child_process *get_helper(struct transport *transport)
+{
+	struct helper_data *data = transport->data;
+	struct strbuf buf = STRBUF_INIT;
+	struct child_process *helper;
+	FILE *file;
+
+	if (data->helper)
+		return data->helper;
+
+	helper = xcalloc(1, sizeof(*helper));
+	helper->in = -1;
+	helper->out = -1;
+	helper->err = 0;
+	helper->argv = xcalloc(4, sizeof(*helper->argv));
+	strbuf_addf(&buf, "remote-%s", data->name);
+	helper->argv[0] = strbuf_detach(&buf, NULL);
+	helper->argv[1] = transport->remote->name;
+	helper->argv[2] = transport->url;
+	helper->git_cmd = 1;
+	if (start_command(helper))
+		die("Unable to run helper: git %s", helper->argv[0]);
+	data->helper = helper;
+
+	strbuf_addstr(&buf, "capabilities\n");
+	write_in_full(helper->in, buf.buf, buf.len);
+	strbuf_reset(&buf);
+
+	file = fdopen(helper->out, "r");
+	while (1) {
+		if (strbuf_getline(&buf, file, '\n') == EOF)
+			exit(128); /* child died, message supplied already */
+
+		if (!*buf.buf)
+			break;
+		if (!strcmp(buf.buf, "fetch"))
+			data->fetch = 1;
+	}
+	return data->helper;
+}
+
+static int disconnect_helper(struct transport *transport)
+{
+	struct helper_data *data = transport->data;
+	if (data->helper) {
+		write_in_full(data->helper->in, "\n", 1);
+		close(data->helper->in);
+		finish_command(data->helper);
+		free((char *)data->helper->argv[0]);
+		free(data->helper->argv);
+		free(data->helper);
+		data->helper = NULL;
+	}
+	return 0;
+}
+
+static int fetch_with_fetch(struct transport *transport,
+			    int nr_heads, const struct ref **to_fetch)
+{
+	struct child_process *helper = get_helper(transport);
+	FILE *file = fdopen(helper->out, "r");
+	int i;
+	struct strbuf buf = STRBUF_INIT;
+
+	for (i = 0; i < nr_heads; i++) {
+		const struct ref *posn = to_fetch[i];
+		if (posn->status & REF_STATUS_UPTODATE)
+			continue;
+
+		strbuf_addf(&buf, "fetch %s %s\n",
+			    sha1_to_hex(posn->old_sha1), posn->name);
+		write_in_full(helper->in, buf.buf, buf.len);
+		strbuf_reset(&buf);
+
+		if (strbuf_getline(&buf, file, '\n') == EOF)
+			exit(128); /* child died, message supplied already */
+	}
+	return 0;
+}
+
+static int fetch(struct transport *transport,
+		 int nr_heads, const struct ref **to_fetch)
+{
+	struct helper_data *data = transport->data;
+	int i, count;
+
+	count = 0;
+	for (i = 0; i < nr_heads; i++)
+		if (!(to_fetch[i]->status & REF_STATUS_UPTODATE))
+			count++;
+
+	if (!count)
+		return 0;
+
+	if (data->fetch)
+		return fetch_with_fetch(transport, nr_heads, to_fetch);
+
+	return -1;
+}
+
+static struct ref *get_refs_list(struct transport *transport, int for_push)
+{
+	struct child_process *helper;
+	struct ref *ret = NULL;
+	struct ref **tail = &ret;
+	struct ref *posn;
+	struct strbuf buf = STRBUF_INIT;
+	FILE *file;
+
+	helper = get_helper(transport);
+
+	strbuf_addstr(&buf, "list\n");
+	write_in_full(helper->in, buf.buf, buf.len);
+	strbuf_reset(&buf);
+
+	file = fdopen(helper->out, "r");
+	while (1) {
+		char *eov, *eon;
+		if (strbuf_getline(&buf, file, '\n') == EOF)
+			exit(128); /* child died, message supplied already */
+
+		if (!*buf.buf)
+			break;
+
+		eov = strchr(buf.buf, ' ');
+		if (!eov)
+			die("Malformed response in ref list: %s", buf.buf);
+		eon = strchr(eov + 1, ' ');
+		*eov = '\0';
+		if (eon)
+			*eon = '\0';
+		*tail = alloc_ref(eov + 1);
+		if (buf.buf[0] == '@')
+			(*tail)->symref = xstrdup(buf.buf + 1);
+		else if (buf.buf[0] != '?')
+			get_sha1_hex(buf.buf, (*tail)->old_sha1);
+		tail = &((*tail)->next);
+	}
+	strbuf_release(&buf);
+
+	for (posn = ret; posn; posn = posn->next)
+		resolve_remote_symref(posn, ret);
+
+	return ret;
+}
+
+int transport_helper_init(struct transport *transport, const char *name)
+{
+	struct helper_data *data = xcalloc(sizeof(*data), 1);
+	data->name = name;
+
+	transport->data = data;
+	transport->get_refs_list = get_refs_list;
+	transport->fetch = fetch;
+	transport->disconnect = disconnect_helper;
+	return 0;
+}
diff --git a/transport.c b/transport.c
index d6c35d91c..4cb807700 100644
--- a/transport.c
+++ b/transport.c
@@ -1,9 +1,6 @@
 #include "cache.h"
 #include "transport.h"
 #include "run-command.h"
-#ifndef NO_CURL
-#include "http.h"
-#endif
 #include "pkt-line.h"
 #include "fetch-pack.h"
 #include "send-pack.h"
@@ -352,45 +349,6 @@ static int rsync_transport_push(struct transport *transport,
 	return result;
 }
 
-/* Generic functions for using commit walkers */
-
-#ifndef NO_CURL /* http fetch is the only user */
-static int fetch_objs_via_walker(struct transport *transport,
-				 int nr_objs, const struct ref **to_fetch)
-{
-	char *dest = xstrdup(transport->url);
-	struct walker *walker = transport->data;
-	char **objs = xmalloc(nr_objs * sizeof(*objs));
-	int i;
-
-	walker->get_all = 1;
-	walker->get_tree = 1;
-	walker->get_history = 1;
-	walker->get_verbosely = transport->verbose >= 0;
-	walker->get_recover = 0;
-
-	for (i = 0; i < nr_objs; i++)
-		objs[i] = xstrdup(sha1_to_hex(to_fetch[i]->old_sha1));
-
-	if (walker_fetch(walker, nr_objs, objs, NULL, NULL))
-		die("Fetch failed.");
-
-	for (i = 0; i < nr_objs; i++)
-		free(objs[i]);
-	free(objs);
-	free(dest);
-	return 0;
-}
-#endif /* NO_CURL */
-
-static int disconnect_walker(struct transport *transport)
-{
-	struct walker *walker = transport->data;
-	if (walker)
-		walker_free(walker);
-	return 0;
-}
-
 #ifndef NO_CURL
 static int curl_transport_push(struct transport *transport, int refspec_nr, const char **refspec, int flags)
 {
@@ -418,96 +376,6 @@ static int curl_transport_push(struct transport *transport, int refspec_nr, cons
 	return !!run_command_v_opt(argv, RUN_GIT_CMD);
 }
 
-static struct ref *get_refs_via_curl(struct transport *transport, int for_push)
-{
-	struct strbuf buffer = STRBUF_INIT;
-	char *data, *start, *mid;
-	char *ref_name;
-	char *refs_url;
-	int i = 0;
-	int http_ret;
-
-	struct ref *refs = NULL;
-	struct ref *ref = NULL;
-	struct ref *last_ref = NULL;
-
-	struct walker *walker;
-
-	if (for_push)
-		return NULL;
-
-	if (!transport->data)
-		transport->data = get_http_walker(transport->url,
-						transport->remote);
-
-	walker = transport->data;
-
-	refs_url = xmalloc(strlen(transport->url) + 11);
-	sprintf(refs_url, "%s/info/refs", transport->url);
-
-	http_ret = http_get_strbuf(refs_url, &buffer, HTTP_NO_CACHE);
-	switch (http_ret) {
-	case HTTP_OK:
-		break;
-	case HTTP_MISSING_TARGET:
-		die("%s not found: did you run git update-server-info on the"
-		    " server?", refs_url);
-	default:
-		http_error(refs_url, http_ret);
-		die("HTTP request failed");
-	}
-
-	data = buffer.buf;
-	start = NULL;
-	mid = data;
-	while (i < buffer.len) {
-		if (!start)
-			start = &data[i];
-		if (data[i] == '\t')
-			mid = &data[i];
-		if (data[i] == '\n') {
-			data[i] = 0;
-			ref_name = mid + 1;
-			ref = xmalloc(sizeof(struct ref) +
-				      strlen(ref_name) + 1);
-			memset(ref, 0, sizeof(struct ref));
-			strcpy(ref->name, ref_name);
-			get_sha1_hex(start, ref->old_sha1);
-			if (!refs)
-				refs = ref;
-			if (last_ref)
-				last_ref->next = ref;
-			last_ref = ref;
-			start = NULL;
-		}
-		i++;
-	}
-
-	strbuf_release(&buffer);
-
-	ref = alloc_ref("HEAD");
-	if (!walker->fetch_ref(walker, ref) &&
-	    !resolve_remote_symref(ref, refs)) {
-		ref->next = refs;
-		refs = ref;
-	} else {
-		free(ref);
-	}
-
-	strbuf_release(&buffer);
-	free(refs_url);
-	return refs;
-}
-
-static int fetch_objs_via_curl(struct transport *transport,
-				 int nr_objs, const struct ref **to_fetch)
-{
-	if (!transport->data)
-		transport->data = get_http_walker(transport->url,
-						transport->remote);
-	return fetch_objs_via_walker(transport, nr_objs, to_fetch);
-}
-
 #endif
 
 struct bundle_transport_data {
@@ -955,14 +823,12 @@ struct transport *transport_get(struct remote *remote, const char *url)
 	} else if (!prefixcmp(url, "http://")
 	        || !prefixcmp(url, "https://")
 	        || !prefixcmp(url, "ftp://")) {
+		transport_helper_init(ret, "curl");
 #ifdef NO_CURL
 		error("git was compiled without libcurl support.");
 #else
-		ret->get_refs_list = get_refs_via_curl;
-		ret->fetch = fetch_objs_via_curl;
 		ret->push = curl_transport_push;
 #endif
-		ret->disconnect = disconnect_walker;
 
 	} else if (is_local(url) && is_file(url)) {
 		struct bundle_transport_data *data = xcalloc(1, sizeof(*data));
diff --git a/transport.h b/transport.h
index 171a01c7a..c14da6f1e 100644
--- a/transport.h
+++ b/transport.h
@@ -79,4 +79,7 @@ void transport_unlock_pack(struct transport *transport);
 int transport_disconnect(struct transport *transport);
 char *transport_anonymize_url(const char *url);
 
+/* Transport methods defined outside transport.c */
+int transport_helper_init(struct transport *transport, const char *name);
+
 #endif