Merge branch 'ds/bundle-uri-clone' into seen

Implement "git clone --bundle-uri".
source: <pull.1300.git.1658781277.gitgitgadget@gmail.com>

* ds/bundle-uri-clone:
  clone: --bundle-uri cannot be combined with --depth
  bundle-uri: add support for http(s):// and file://
  clone: add --bundle-uri option
  bundle-uri: create basic file-copy logic
  remote-curl: add 'get' capability

Documentation/git-clone.txt

@@ -323,6 +323,13 @@ or `--mirror` is given)
 	for `host.xz:foo/.git`).  Cloning into an existing directory
 	is only allowed if the directory is empty.
 
+--bundle-uri=<uri>::
+	Before fetching from the remote, fetch a bundle from the given
+	`<uri>` and unbundle the data into the local repository. The refs
+	in the bundle will be stored under the hidden `refs/bundle/*`
+	namespace. This option is incompatible with `--depth`,
+	`--shallow-since`, and `--shallow-exclude`.
+
 :git-clone: 1
 include::urls.txt[]
 

Documentation/gitremote-helpers.txt

@@ -168,6 +168,9 @@ Supported commands: 'list', 'import'.
 	Can guarantee that when a clone is requested, the received
 	pack is self contained and is connected.
 
+'get'::
+	Can use the 'get' command to download a file from a given URI.
+
 If a helper advertises 'connect', Git will use it if possible and
 fall back to another capability if the helper requests so when
 connecting (see the 'connect' command under COMMANDS).
@@ -418,6 +421,12 @@ Supported if the helper has the "connect" capability.
 +
 Supported if the helper has the "stateless-connect" capability.
 
+'get' <uri> <path>::
+	Downloads the file from the given `<uri>` to the given `<path>`. If
+	`<path>.temp` exists, then Git assumes that the `.temp` file is a
+	partial download from a previous attempt and will resume the
+	download from that position.
+
 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

Makefile

@@ -907,6 +907,7 @@ LIB_OBJS += blob.o
 LIB_OBJS += bloom.o
 LIB_OBJS += branch.o
 LIB_OBJS += bulk-checkin.o
+LIB_OBJS += bundle-uri.o
 LIB_OBJS += bundle.o
 LIB_OBJS += cache-tree.o
 LIB_OBJS += cbtree.o

builtin/clone.c

@@ -34,6 +34,7 @@
 #include "list-objects-filter-options.h"
 #include "hook.h"
 #include "bundle.h"
+#include "bundle-uri.h"
 
 /*
  * Overall FIXMEs:
@@ -77,6 +78,7 @@ static int option_filter_submodules = -1;    /* unspecified */
 static int config_filter_submodules = -1;    /* unspecified */
 static struct string_list server_options = STRING_LIST_INIT_NODUP;
 static int option_remote_submodules;
+static const char *bundle_uri;
 
 static int recurse_submodules_cb(const struct option *opt,
 				 const char *arg, int unset)
@@ -160,6 +162,8 @@ static struct option builtin_clone_options[] = {
 		    N_("any cloned submodules will use their remote-tracking branch")),
 	OPT_BOOL(0, "sparse", &option_sparse_checkout,
 		    N_("initialize sparse-checkout file to include only files at root")),
+	OPT_STRING(0, "bundle-uri", &bundle_uri,
+		   N_("uri"), N_("a URI for downloading bundles before fetching from origin remote")),
 	OPT_END()
 };
 
@@ -933,6 +937,9 @@ int cmd_clone(int argc, const char **argv, const char *prefix)
 		option_no_checkout = 1;
 	}
 
+	if (bundle_uri && deepen)
+		die(_("--bundle-uri is incompatible with --depth, --shallow-since, and --shallow-exclude"));
+
 	repo_name = argv[0];
 
 	path = get_repo_path(repo_name, &is_bundle);
@@ -1232,6 +1239,17 @@ int cmd_clone(int argc, const char **argv, const char *prefix)
 	if (transport->smart_options && !deepen && !filter_options.choice)
 		transport->smart_options->check_self_contained_and_connected = 1;
 
+	/*
+	 * Before fetching from the remote, download and install bundle
+	 * data from the --bundle-uri option.
+	 */
+	if (bundle_uri) {
+		/* At this point, we need the_repository to match the cloned repo. */
+		repo_init(the_repository, git_dir, work_tree);
+		if (fetch_bundle_uri(the_repository, bundle_uri))
+			warning(_("failed to fetch objects from bundle URI '%s'"),
+				bundle_uri);
+	}
 
 	strvec_push(&transport_ls_refs_options.ref_prefixes, "HEAD");
 	refspec_ref_prefixes(&remote->fetch,

bundle-uri.c

@@ -0,0 +1,168 @@
+#include "cache.h"
+#include "bundle-uri.h"
+#include "bundle.h"
+#include "object-store.h"
+#include "refs.h"
+#include "run-command.h"
+
+static int find_temp_filename(struct strbuf *name)
+{
+	int fd;
+	/*
+	 * Find a temporary filename that is available. This is briefly
+	 * racy, but unlikely to collide.
+	 */
+	fd = odb_mkstemp(name, "bundles/tmp_uri_XXXXXX");
+	if (fd < 0) {
+		warning(_("failed to create temporary file"));
+		return -1;
+	}
+
+	close(fd);
+	unlink(name->buf);
+	return 0;
+}
+
+static int download_https_uri_to_file(const char *file, const char *uri)
+{
+	int result = 0;
+	struct child_process cp = CHILD_PROCESS_INIT;
+	FILE *child_in = NULL, *child_out = NULL;
+	struct strbuf line = STRBUF_INIT;
+	int found_get = 0;
+
+	strvec_pushl(&cp.args, "git-remote-https", "origin", uri, NULL);
+	cp.in = -1;
+	cp.out = -1;
+
+	if (start_command(&cp))
+		return 1;
+
+	child_in = fdopen(cp.in, "w");
+	if (!child_in) {
+		result = 1;
+		goto cleanup;
+	}
+
+	child_out = fdopen(cp.out, "r");
+	if (!child_out) {
+		result = 1;
+		goto cleanup;
+	}
+
+	fprintf(child_in, "capabilities\n");
+	fflush(child_in);
+
+	while (!strbuf_getline(&line, child_out)) {
+		if (!line.len)
+			break;
+		if (!strcmp(line.buf, "get"))
+			found_get = 1;
+	}
+	strbuf_release(&line);
+
+	if (!found_get) {
+		result = error(_("insufficient capabilities"));
+		goto cleanup;
+	}
+
+	fprintf(child_in, "get %s %s\n\n", uri, file);
+
+cleanup:
+	if (child_in)
+		fclose(child_in);
+	if (finish_command(&cp))
+		return 1;
+	if (child_out)
+		fclose(child_out);
+	return result;
+}
+
+static int copy_uri_to_file(const char *filename, const char *uri)
+{
+	const char *out;
+
+	if (skip_prefix(uri, "https:", &out) ||
+	    skip_prefix(uri, "http:", &out))
+		return download_https_uri_to_file(filename, uri);
+
+	if (!skip_prefix(uri, "file://", &out))
+		out = uri;
+
+	/* Copy as a file */
+	return copy_file(filename, out, 0);
+}
+
+static int unbundle_from_file(struct repository *r, const char *file)
+{
+	int result = 0;
+	int bundle_fd;
+	struct bundle_header header = BUNDLE_HEADER_INIT;
+	struct string_list_item *refname;
+	struct strbuf bundle_ref = STRBUF_INIT;
+	size_t bundle_prefix_len;
+
+	if ((bundle_fd = read_bundle_header(file, &header)) < 0)
+		return 1;
+
+	if ((result = unbundle(r, &header, bundle_fd, NULL)))
+		return 1;
+
+	/*
+	 * Convert all refs/heads/ from the bundle into refs/bundles/
+	 * in the local repository.
+	 */
+	strbuf_addstr(&bundle_ref, "refs/bundles/");
+	bundle_prefix_len = bundle_ref.len;
+
+	for_each_string_list_item(refname, &header.references) {
+		struct object_id *oid = refname->util;
+		struct object_id old_oid;
+		const char *branch_name;
+		int has_old;
+
+		if (!skip_prefix(refname->string, "refs/heads/", &branch_name))
+			continue;
+
+		strbuf_setlen(&bundle_ref, bundle_prefix_len);
+		strbuf_addstr(&bundle_ref, branch_name);
+
+		has_old = !read_ref(bundle_ref.buf, &old_oid);
+		update_ref("fetched bundle", bundle_ref.buf, oid,
+			   has_old ? &old_oid : NULL,
+			   REF_SKIP_OID_VERIFICATION,
+			   UPDATE_REFS_MSG_ON_ERR);
+	}
+
+	bundle_header_release(&header);
+	return result;
+}
+
+int fetch_bundle_uri(struct repository *r, const char *uri)
+{
+	int result = 0;
+	struct strbuf filename = STRBUF_INIT;
+
+	if ((result = find_temp_filename(&filename)))
+		goto cleanup;
+
+	if ((result = copy_uri_to_file(filename.buf, uri))) {
+		warning(_("failed to download bundle from URI '%s'"), uri);
+		goto cleanup;
+	}
+
+	if ((result = !is_bundle(filename.buf, 0))) {
+		warning(_("file at URI '%s' is not a bundle"), uri);
+		goto cleanup;
+	}
+
+	if ((result = unbundle_from_file(r, filename.buf))) {
+		warning(_("failed to unbundle bundle from URI '%s'"), uri);
+		goto cleanup;
+	}
+
+cleanup:
+	unlink(filename.buf);
+	strbuf_release(&filename);
+	return result;
+}

bundle-uri.h

@@ -0,0 +1,14 @@
+#ifndef BUNDLE_URI_H
+#define BUNDLE_URI_H
+
+struct repository;
+
+/**
+ * Fetch data from the given 'uri' and unbundle the bundle data found
+ * based on that information.
+ *
+ * Returns non-zero if no bundle information is found at the given 'uri'.
+ */
+int fetch_bundle_uri(struct repository *r, const char *uri);
+
+#endif

remote-curl.c

@@ -1286,6 +1286,33 @@ static void parse_fetch(struct strbuf *buf)
 	strbuf_reset(buf);
 }
 
+static void parse_get(struct strbuf *buf)
+{
+	struct strbuf url = STRBUF_INIT;
+	struct strbuf path = STRBUF_INIT;
+	const char *p, *space;
+
+	if (!skip_prefix(buf->buf, "get ", &p))
+		die(_("http transport does not support %s"), buf->buf);
+
+	space = strchr(p, ' ');
+
+	if (!space)
+		die(_("protocol error: expected '<url> <path>', missing space"));
+
+	strbuf_add(&url, p, space - p);
+	strbuf_addstr(&path, space + 1);
+
+	if (http_get_file(url.buf, path.buf, NULL))
+		die(_("failed to download file at URL '%s'"), url.buf);
+
+	strbuf_release(&url);
+	strbuf_release(&path);
+	printf("\n");
+	fflush(stdout);
+	strbuf_reset(buf);
+}
+
 static int push_dav(int nr_spec, const char **specs)
 {
 	struct child_process child = CHILD_PROCESS_INIT;
@@ -1564,9 +1591,14 @@ int cmd_main(int argc, const char **argv)
 				printf("unsupported\n");
 			fflush(stdout);
 
+		} else if (skip_prefix(buf.buf, "get ", &arg)) {
+			parse_get(&buf);
+			fflush(stdout);
+
 		} else if (!strcmp(buf.buf, "capabilities")) {
 			printf("stateless-connect\n");
 			printf("fetch\n");
+			printf("get\n");
 			printf("option\n");
 			printf("push\n");
 			printf("check-connectivity\n");

t/t5557-http-get.sh

@@ -0,0 +1,37 @@
+#!/bin/sh
+
+test_description='test downloading a file by URL'
+
+. ./test-lib.sh
+
+. "$TEST_DIRECTORY"/lib-httpd.sh
+start_httpd
+
+test_expect_success 'get by URL: 404' '
+	url="$HTTPD_URL/none.txt" &&
+	cat >input <<-EOF &&
+	capabilities
+	get $url file1
+	EOF
+
+	test_must_fail git remote-http $url <input 2>err &&
+	test_path_is_missing file1 &&
+	grep "failed to download file at URL" err &&
+	rm file1.temp
+'
+
+test_expect_success 'get by URL: 200' '
+	echo data >"$HTTPD_DOCUMENT_ROOT_PATH/exists.txt" &&
+
+	url="$HTTPD_URL/exists.txt" &&
+	cat >input <<-EOF &&
+	capabilities
+	get $url file2
+
+	EOF
+
+	GIT_TRACE2_PERF=1 git remote-http $url <input &&
+	test_cmp "$HTTPD_DOCUMENT_ROOT_PATH/exists.txt" file2
+'
+
+test_done