Merge branch 'xy/format-patch-base'

"git format-patch" learned a new "--base" option to record what
(public, well-known) commit the original series was built on in
its output.

* xy/format-patch-base:
  format-patch: introduce format.useAutoBase configuration
  format-patch: introduce --base=auto option
  format-patch: add '--base' option to record base tree info
  patch-ids: make commit_patch_id() a public helper function

6 files changed, 340 insertions, 1 deletions

diff --git a/Documentation/config.txt b/Documentation/config.txt
index 54253d1635..ea928a729f 100644
--- a/Documentation/config.txt
+++ b/Documentation/config.txt
@@ -1290,6 +1290,10 @@ format.outputDirectory::
 	Set a custom directory to store the resulting files instead of the
 	current working directory.
 
+format.useAutoBase::
+	A boolean value which lets you enable the `--base=auto` option of
+	format-patch by default.
+
 filter.<driver>.clean::
 	The command which is used to convert the content of a worktree
 	file to a blob upon checkin.  See linkgit:gitattributes[5] for
diff --git a/Documentation/git-format-patch.txt b/Documentation/git-format-patch.txt
index 6821441d7d..bdeecd59e0 100644
--- a/Documentation/git-format-patch.txt
+++ b/Documentation/git-format-patch.txt
@@ -265,6 +265,11 @@ you can use `--suffix=-patch` to get `0001-description-of-my-change-patch`.
   Output an all-zero hash in each patch's From header instead
   of the hash of the commit.
 
+--base=<commit>::
+	Record the base tree information to identify the state the
+	patch series applies to.  See the BASE TREE INFORMATION section
+	below for details.
+
 --root::
 	Treat the revision argument as a <revision range>, even if it
 	is just a single commit (that would normally be treated as a
@@ -520,6 +525,61 @@ This should help you to submit patches inline using KMail.
 5. Back in the compose window: add whatever other text you wish to the
    message, complete the addressing and subject fields, and press send.
 
+BASE TREE INFORMATION
+---------------------
+
+The base tree information block is used for maintainers or third party
+testers to know the exact state the patch series applies to. It consists
+of the 'base commit', which is a well-known commit that is part of the
+stable part of the project history everybody else works off of, and zero
+or more 'prerequisite patches', which are well-known patches in flight
+that is not yet part of the 'base commit' that need to be applied on top
+of 'base commit' in topological order before the patches can be applied.
+
+The 'base commit' is shown as "base-commit: " followed by the 40-hex of
+the commit object name.  A 'prerequisite patch' is shown as
+"prerequisite-patch-id: " followed by the 40-hex 'patch id', which can
+be obtained by passing the patch through the `git patch-id --stable`
+command.
+
+Imagine that on top of the public commit P, you applied well-known
+patches X, Y and Z from somebody else, and then built your three-patch
+series A, B, C, the history would be like:
+
+................................................
+---P---X---Y---Z---A---B---C
+................................................
+
+With `git format-patch --base=P -3 C` (or variants thereof, e.g. with
+`--cover-letter` of using `Z..C` instead of `-3 C` to specify the
+range), the base tree information block is shown at the end of the
+first message the command outputs (either the first patch, or the
+cover letter), like this:
+
+------------
+base-commit: P
+prerequisite-patch-id: X
+prerequisite-patch-id: Y
+prerequisite-patch-id: Z
+------------
+
+For non-linear topology, such as
+
+................................................
+---P---X---A---M---C
+    \         /
+     Y---Z---B
+................................................
+
+You can also use `git format-patch --base=P -3 C` to generate patches
+for A, B and C, and the identifiers for P, X, Y, Z are appended at the
+end of the first message.
+
+If set `--base=auto` in cmdline, it will track base commit automatically,
+the base commit will be the merge base of tip commit of the remote-tracking
+branch and revision-range specified in cmdline.
+For a local branch, you need to track a remote branch by `git branch
+--set-upstream-to` before using this option.
 
 EXAMPLES
 --------
diff --git a/builtin/log.c b/builtin/log.c
index dff3fbbb43..099f4f7be9 100644
--- a/builtin/log.c
+++ b/builtin/log.c
@@ -702,6 +702,7 @@ static void add_header(const char *value)
 #define THREAD_DEEP 2
 static int thread;
 static int do_signoff;
+static int base_auto;
 static const char *signature = git_version_string;
 static const char *signature_file;
 static int config_cover_letter;
@@ -786,6 +787,10 @@ static int git_format_config(const char *var, const char *value, void *cb)
 	}
 	if (!strcmp(var, "format.outputdirectory"))
 		return git_config_string(&config_output_directory, var, value);
+	if (!strcmp(var, "format.useautobase")) {
+		base_auto = git_config_bool(var, value);
+		return 0;
+	}
 
 	return git_log_config(var, value, cb);
 }
@@ -1191,6 +1196,155 @@ static int from_callback(const struct option *opt, const char *arg, int unset)
 	return 0;
 }
 
+struct base_tree_info {
+	struct object_id base_commit;
+	int nr_patch_id, alloc_patch_id;
+	struct object_id *patch_id;
+};
+
+static struct commit *get_base_commit(const char *base_commit,
+				      struct commit **list,
+				      int total)
+{
+	struct commit *base = NULL;
+	struct commit **rev;
+	int i = 0, rev_nr = 0;
+
+	if (base_commit && strcmp(base_commit, "auto")) {
+		base = lookup_commit_reference_by_name(base_commit);
+		if (!base)
+			die(_("Unknown commit %s"), base_commit);
+	} else if ((base_commit && !strcmp(base_commit, "auto")) || base_auto) {
+		struct branch *curr_branch = branch_get(NULL);
+		const char *upstream = branch_get_upstream(curr_branch, NULL);
+		if (upstream) {
+			struct commit_list *base_list;
+			struct commit *commit;
+			unsigned char sha1[20];
+
+			if (get_sha1(upstream, sha1))
+				die(_("Failed to resolve '%s' as a valid ref."), upstream);
+			commit = lookup_commit_or_die(sha1, "upstream base");
+			base_list = get_merge_bases_many(commit, total, list);
+			/* There should be one and only one merge base. */
+			if (!base_list || base_list->next)
+				die(_("Could not find exact merge base."));
+			base = base_list->item;
+			free_commit_list(base_list);
+		} else {
+			die(_("Failed to get upstream, if you want to record base commit automatically,\n"
+			      "please use git branch --set-upstream-to to track a remote branch.\n"
+			      "Or you could specify base commit by --base=<base-commit-id> manually."));
+		}
+	}
+
+	ALLOC_ARRAY(rev, total);
+	for (i = 0; i < total; i++)
+		rev[i] = list[i];
+
+	rev_nr = total;
+	/*
+	 * Get merge base through pair-wise computations
+	 * and store it in rev[0].
+	 */
+	while (rev_nr > 1) {
+		for (i = 0; i < rev_nr / 2; i++) {
+			struct commit_list *merge_base;
+			merge_base = get_merge_bases(rev[2 * i], rev[2 * i + 1]);
+			if (!merge_base || merge_base->next)
+				die(_("Failed to find exact merge base"));
+
+			rev[i] = merge_base->item;
+		}
+
+		if (rev_nr % 2)
+			rev[i] = rev[2 * i];
+		rev_nr = (rev_nr + 1) / 2;
+	}
+
+	if (!in_merge_bases(base, rev[0]))
+		die(_("base commit should be the ancestor of revision list"));
+
+	for (i = 0; i < total; i++) {
+		if (base == list[i])
+			die(_("base commit shouldn't be in revision list"));
+	}
+
+	free(rev);
+	return base;
+}
+
+static void prepare_bases(struct base_tree_info *bases,
+			  struct commit *base,
+			  struct commit **list,
+			  int total)
+{
+	struct commit *commit;
+	struct rev_info revs;
+	struct diff_options diffopt;
+	int i;
+
+	if (!base)
+		return;
+
+	diff_setup(&diffopt);
+	DIFF_OPT_SET(&diffopt, RECURSIVE);
+	diff_setup_done(&diffopt);
+
+	oidcpy(&bases->base_commit, &base->object.oid);
+
+	init_revisions(&revs, NULL);
+	revs.max_parents = 1;
+	revs.topo_order = 1;
+	for (i = 0; i < total; i++) {
+		list[i]->object.flags &= ~UNINTERESTING;
+		add_pending_object(&revs, &list[i]->object, "rev_list");
+		list[i]->util = (void *)1;
+	}
+	base->object.flags |= UNINTERESTING;
+	add_pending_object(&revs, &base->object, "base");
+
+	if (prepare_revision_walk(&revs))
+		die(_("revision walk setup failed"));
+	/*
+	 * Traverse the commits list, get prerequisite patch ids
+	 * and stuff them in bases structure.
+	 */
+	while ((commit = get_revision(&revs)) != NULL) {
+		unsigned char sha1[20];
+		struct object_id *patch_id;
+		if (commit->util)
+			continue;
+		if (commit_patch_id(commit, &diffopt, sha1))
+			die(_("cannot get patch id"));
+		ALLOC_GROW(bases->patch_id, bases->nr_patch_id + 1, bases->alloc_patch_id);
+		patch_id = bases->patch_id + bases->nr_patch_id;
+		hashcpy(patch_id->hash, sha1);
+		bases->nr_patch_id++;
+	}
+}
+
+static void print_bases(struct base_tree_info *bases)
+{
+	int i;
+
+	/* Only do this once, either for the cover or for the first one */
+	if (is_null_oid(&bases->base_commit))
+		return;
+
+	/* Show the base commit */
+	printf("base-commit: %s\n", oid_to_hex(&bases->base_commit));
+
+	/* Show the prerequisite patches */
+	for (i = bases->nr_patch_id - 1; i >= 0; i--)
+		printf("prerequisite-patch-id: %s\n", oid_to_hex(&bases->patch_id[i]));
+
+	free(bases->patch_id);
+	bases->nr_patch_id = 0;
+	bases->alloc_patch_id = 0;
+	oidclr(&bases->base_commit);
+}
+
 int cmd_format_patch(int argc, const char **argv, const char *prefix)
 {
 	struct commit *commit;
@@ -1215,6 +1369,9 @@ int cmd_format_patch(int argc, const char **argv, const char *prefix)
 	int reroll_count = -1;
 	char *branch_name = NULL;
 	char *from = NULL;
+	char *base_commit = NULL;
+	struct base_tree_info bases;
+
 	const struct option builtin_format_patch_options[] = {
 		{ OPTION_CALLBACK, 'n', "numbered", &numbered, NULL,
 			    N_("use [PATCH n/m] even with a single patch"),
@@ -1277,6 +1434,8 @@ int cmd_format_patch(int argc, const char **argv, const char *prefix)
 			    PARSE_OPT_OPTARG, thread_callback },
 		OPT_STRING(0, "signature", &signature, N_("signature"),
 			    N_("add a signature")),
+		OPT_STRING(0, "base", &base_commit, N_("base-commit"),
+			   N_("add prerequisite tree info to the patch series")),
 		OPT_FILENAME(0, "signature-file", &signature_file,
 				N_("add a signature from a file")),
 		OPT__QUIET(&quiet, N_("don't print the patch filenames")),
@@ -1514,6 +1673,13 @@ int cmd_format_patch(int argc, const char **argv, const char *prefix)
 		signature = strbuf_detach(&buf, NULL);
 	}
 
+	memset(&bases, 0, sizeof(bases));
+	if (base_commit || base_auto) {
+		struct commit *base = get_base_commit(base_commit, list, nr);
+		reset_revision_walk();
+		prepare_bases(&bases, base, list, nr);
+	}
+
 	if (in_reply_to || thread || cover_letter)
 		rev.ref_message_ids = xcalloc(1, sizeof(struct string_list));
 	if (in_reply_to) {
@@ -1527,6 +1693,7 @@ int cmd_format_patch(int argc, const char **argv, const char *prefix)
 			gen_message_id(&rev, "cover");
 		make_cover_letter(&rev, use_stdout,
 				  origin, nr, list, branch_name, quiet);
+		print_bases(&bases);
 		total++;
 		start_number--;
 	}
@@ -1592,6 +1759,7 @@ int cmd_format_patch(int argc, const char **argv, const char *prefix)
 				       rev.mime_boundary);
 			else
 				print_signature();
+			print_bases(&bases);
 		}
 		if (!use_stdout)
 			fclose(stdout);
diff --git a/patch-ids.c b/patch-ids.c
index b7b3e5a1a7..a4d0016664 100644
--- a/patch-ids.c
+++ b/patch-ids.c
@@ -4,7 +4,7 @@
 #include "sha1-lookup.h"
 #include "patch-ids.h"
 
-static int commit_patch_id(struct commit *commit, struct diff_options *options,
+int commit_patch_id(struct commit *commit, struct diff_options *options,
 		    unsigned char *sha1)
 {
 	if (commit->parents)
diff --git a/patch-ids.h b/patch-ids.h
index c8c7ca110a..eeb56b307f 100644
--- a/patch-ids.h
+++ b/patch-ids.h
@@ -13,6 +13,8 @@ struct patch_ids {
 	struct patch_id_bucket *patches;
 };
 
+int commit_patch_id(struct commit *commit, struct diff_options *options,
+		    unsigned char *sha1);
 int init_patch_ids(struct patch_ids *);
 int free_patch_ids(struct patch_ids *);
 struct patch_id *add_commit_patch_id(struct commit *, struct patch_ids *);
diff --git a/t/t4014-format-patch.sh b/t/t4014-format-patch.sh
index eed2981b96..8049cad374 100755
--- a/t/t4014-format-patch.sh
+++ b/t/t4014-format-patch.sh
@@ -1460,4 +1460,109 @@ test_expect_success 'format-patch -o overrides format.outputDirectory' '
 	test_path_is_dir patchset
 '
 
+test_expect_success 'format-patch --base' '
+	git checkout side &&
+	git format-patch --stdout --base=HEAD~3 -1 >patch &&
+	grep "^base-commit:" patch >actual &&
+	grep "^prerequisite-patch-id:" patch >>actual &&
+	echo "base-commit: $(git rev-parse HEAD~3)" >expected &&
+	echo "prerequisite-patch-id: $(git show --patch HEAD~2 | git patch-id --stable | awk "{print \$1}")" >>expected &&
+	echo "prerequisite-patch-id: $(git show --patch HEAD~1 | git patch-id --stable | awk "{print \$1}")" >>expected &&
+	test_cmp expected actual
+'
+
+test_expect_success 'format-patch --base errors out when base commit is in revision list' '
+	test_must_fail git format-patch --base=HEAD -2 &&
+	test_must_fail git format-patch --base=HEAD~1 -2 &&
+	git format-patch --stdout --base=HEAD~2 -2 >patch &&
+	grep "^base-commit:" patch >actual &&
+	echo "base-commit: $(git rev-parse HEAD~2)" >expected &&
+	test_cmp expected actual
+'
+
+test_expect_success 'format-patch --base errors out when base commit is not ancestor of revision list' '
+	# For history as below:
+	#
+	#    ---Q---P---Z---Y---*---X
+	#	 \             /
+	#	  ------------W
+	#
+	# If "format-patch Z..X" is given, P and Z can not be specified as the base commit
+	git checkout -b topic1 master &&
+	git rev-parse HEAD >commit-id-base &&
+	test_commit P &&
+	git rev-parse HEAD >commit-id-P &&
+	test_commit Z &&
+	git rev-parse HEAD >commit-id-Z &&
+	test_commit Y &&
+	git checkout -b topic2 master &&
+	test_commit W &&
+	git merge topic1 &&
+	test_commit X &&
+	test_must_fail git format-patch --base=$(cat commit-id-P) -3 &&
+	test_must_fail git format-patch --base=$(cat commit-id-Z) -3 &&
+	git format-patch --stdout --base=$(cat commit-id-base) -3 >patch &&
+	grep "^base-commit:" patch >actual &&
+	echo "base-commit: $(cat commit-id-base)" >expected &&
+	test_cmp expected actual
+'
+
+test_expect_success 'format-patch --base=auto' '
+	git checkout -b upstream master &&
+	git checkout -b local upstream &&
+	git branch --set-upstream-to=upstream &&
+	test_commit N1 &&
+	test_commit N2 &&
+	git format-patch --stdout --base=auto -2 >patch &&
+	grep "^base-commit:" patch >actual &&
+	echo "base-commit: $(git rev-parse upstream)" >expected &&
+	test_cmp expected actual
+'
+
+test_expect_success 'format-patch errors out when history involves criss-cross' '
+	# setup criss-cross history
+	#
+	#   B---M1---D
+	#  / \ /
+	# A   X
+	#  \ / \
+	#   C---M2---E
+	#
+	git checkout master &&
+	test_commit A &&
+	git checkout -b xb master &&
+	test_commit B &&
+	git checkout -b xc master &&
+	test_commit C &&
+	git checkout -b xbc xb -- &&
+	git merge xc &&
+	git checkout -b xcb xc -- &&
+	git branch --set-upstream-to=xbc &&
+	git merge xb &&
+	git checkout xbc &&
+	test_commit D &&
+	git checkout xcb &&
+	test_commit E &&
+	test_must_fail 	git format-patch --base=auto -1
+'
+
+test_expect_success 'format-patch format.useAutoBaseoption' '
+	test_when_finished "git config --unset format.useAutoBase" &&
+	git checkout local &&
+	git config format.useAutoBase true &&
+	git format-patch --stdout -1 >patch &&
+	grep "^base-commit:" patch >actual &&
+	echo "base-commit: $(git rev-parse upstream)" >expected &&
+	test_cmp expected actual
+'
+
+test_expect_success 'format-patch --base overrides format.useAutoBase' '
+	test_when_finished "git config --unset format.useAutoBase" &&
+	git config format.useAutoBase true &&
+	git format-patch --stdout --base=HEAD~1 -1 >patch &&
+	grep "^base-commit:" patch >actual &&
+	echo "base-commit: $(git rev-parse HEAD~1)" >expected &&
+	test_cmp expected actual
+'
+
 test_done