[PATCH v6 0/4] branch: let --delete-merged find squash merged branches

["Harald Nordgren via GitGitGadget" <gitgitgadget@gmail.com>]

Branches merged on GitHub with "Squash and merge" or "Rebase and merge" are
never deleted by git branch --delete-merged, because their tips are not
reachable from the upstream. This treats such a branch as merged when some
upstream commit contains all of its changes, and names that commit in the
output:

Deleted branch topic (was 1a2b3c4, landed as 9f8e7d6).


Changes in v6:

 * Read the index before the file merge, so .gitattributes that are only in
   the index are honored too.
 * Renamed the diff_options variables from opt to diffopt.

Changes in v5:

 * git branch -h lists --delete-integrated in the usage lines
 * Giving both --delete-merged and --delete-integrated dies with a short
   "cannot be used together" message instead of the full usage text

Changes in v4:

 * --delete-merged works as it does on master again: it only deletes
   branches whose tip is reachable from their upstream
 * New --delete-integrated <pattern> also deletes branches that were rebase
   or squash merged, including those squashed after upstream changed the
   same files. It replaces --squashed
 * New prep commit lets delete_branches() take a map of where each branch
   landed, so "landed as" is printed there
 * Added Junio's test that --delete-merged keeps a branch when an unrelated
   upstream commit adds an identical file
 * --dry-run works with either option, and the two options can't be combined

Changes in v3:

 * Split into multiple commits, one for rebase merges and one for squash
   merges.
 * By default a branch counts as merged when an upstream commit has its
   exact version of every file it changed. This never reads file contents,
   so it stays cheap in a partial clone. It finds rebase merges, and squash
   merges where upstream left those files alone.
 * Replace --no-squashed with an opt-in --squashed, which also finds
   branches merged after upstream changed the same files by merging those
   files.
 * Add a test for a rebase merge, and check that a squash onto changed files
   is kept without --squashed and deleted with it.

Changes in v2:

 * Diff each upstream commit once and share the result between all branches,
   faster than v1.
 * Fix a branch merged with a merge commit being reported as "landed as" the
   merge when another branch was searched first, and add a test for it. Show
   the topic commit itself in "landed as" for work that arrived through a
   merge.
 * Use git merge --squash as the example in the commit message and mention
   GitHub's squash and rebase buttons.
 * Add --no-squashed to skip the squash search.

Harald Nordgren (4):
  branch: move the deleteMerged opt-out check into a helper
  branch: let delete_branches() name where a branch landed
  branch: add --delete-integrated to delete rebase and squash merged
    branches
  branch: let --delete-integrated find branches merged onto changed
    files

 Documentation/config/branch.adoc |   8 +-
 Documentation/git-branch.adoc    |  22 +-
 builtin/branch.c                 | 361 +++++++++++++++++++++++++++++--
 t/t3200-branch.sh                | 218 +++++++++++++++++++
 4 files changed, 579 insertions(+), 30 deletions(-)


base-commit: 50fe5cc63f9cd6e89b87a2c9ccf96a444f4cfdb7
Published-As: https://github.com/gitgitgadget/git/releases/tag/pr-git-2425%2FHaraldNordgren%2Fbranch-delete-squashed-v6
Fetch-It-Via: git fetch https://github.com/gitgitgadget/git pr-git-2425/HaraldNordgren/branch-delete-squashed-v6
Pull-Request: https://github.com/git/git/pull/2425

Range-diff vs v5:

 1:  090aec5725 = 1:  e728b4ed0d branch: move the deleteMerged opt-out check into a helper
 2:  24180bf4a2 = 2:  9858c8c81e branch: let delete_branches() name where a branch landed
 3:  bf30f57ceb ! 3:  92bd9afda4 branch: add --delete-integrated to delete rebase and squash merged branches
     @@ builtin/branch.c: static int branch_pushes_to_upstream(struct branch *branch,
      +static void collect_branch_changes(struct landing_search *search,
      +				   struct commit *base)
      +{
     -+	struct diff_options opt;
     ++	struct diff_options diffopt;
      +
     -+	repo_diff_setup(the_repository, &opt);
     -+	opt.flags.recursive = 1;
     -+	opt.output_format = DIFF_FORMAT_NO_OUTPUT;
     -+	diff_setup_done(&opt);
     ++	repo_diff_setup(the_repository, &diffopt);
     ++	diffopt.flags.recursive = 1;
     ++	diffopt.output_format = DIFF_FORMAT_NO_OUTPUT;
     ++	diff_setup_done(&diffopt);
      +	diff_tree_oid(get_commit_tree_oid(base),
     -+		      get_commit_tree_oid(search->rev), "", &opt);
     ++		      get_commit_tree_oid(search->rev), "", &diffopt);
      +	for (int i = 0; i < diff_queued_diff.nr; i++) {
      +		struct diff_filepair *p = diff_queued_diff.queue[i];
      +		struct branch_change *change;
     @@ builtin/branch.c: static int branch_pushes_to_upstream(struct branch *branch,
      +		       &p->two->oid : null_oid(the_hash_algo));
      +		change->branch_mode = p->two->mode;
      +	}
     -+	diff_flush(&opt);
     ++	diff_flush(&diffopt);
      +}
      +
      +static int change_landed(const struct branch_change *change,
     @@ builtin/branch.c: static int branch_pushes_to_upstream(struct branch *branch,
      +}
      +
      +static struct string_list *changed_paths_of(struct changed_paths *cache,
     -+					    struct diff_options *opt,
     ++					    struct diff_options *diffopt,
      +					    struct commit *commit)
      +{
      +	struct string_list **paths = changed_paths_at(cache, commit);
     @@ builtin/branch.c: static int branch_pushes_to_upstream(struct branch *branch,
      +		die(_("could not parse commit %s"),
      +		    oid_to_hex(&parent->object.oid));
      +	diff_tree_oid(parent ? get_commit_tree_oid(parent) : NULL,
     -+		      get_commit_tree_oid(commit), "", opt);
     ++		      get_commit_tree_oid(commit), "", diffopt);
      +	for (int i = 0; i < diff_queued_diff.nr; i++) {
      +		struct diff_filepair *p = diff_queued_diff.queue[i];
      +
      +		string_list_append(*paths, p->two->path);
      +	}
     -+	diff_flush(opt);
     ++	diff_flush(diffopt);
      +	string_list_sort(*paths);
      +	return *paths;
      +}
     @@ builtin/branch.c: static int branch_pushes_to_upstream(struct branch *branch,
      +
      +static struct commit *find_landed_commit(struct landing_search *search,
      +					 struct changed_paths *cache,
     -+					 struct diff_options *opt)
     ++					 struct diff_options *diffopt)
      +{
      +	struct commit *commit, *landed = NULL;
      +	struct strvec args = STRVEC_INIT;
     @@ builtin/branch.c: static int branch_pushes_to_upstream(struct branch *branch,
      +	if (prepare_revision_walk(&revs))
      +		die(_("revision walk setup failed"));
      +	while (!landed && (commit = get_revision(&revs)))
     -+		if (touches_changes(changed_paths_of(cache, opt, commit),
     ++		if (touches_changes(changed_paths_of(cache, diffopt, commit),
      +				    search) &&
      +		    changes_landed(search, commit))
      +			landed = commit;
     @@ builtin/branch.c: static int branch_pushes_to_upstream(struct branch *branch,
      +				struct strmap *landed_commits)
      +{
      +	struct changed_paths cache;
     -+	struct diff_options opt;
     ++	struct diff_options diffopt;
      +
      +	for (size_t i = 0; i < searches_nr; i++) {
      +		struct landing_search *search = &searches[i];
     @@ builtin/branch.c: static int branch_pushes_to_upstream(struct branch *branch,
      +		commit_list_free(merge_bases);
      +	}
      +
     -+	repo_diff_setup(the_repository, &opt);
     -+	opt.flags.recursive = 1;
     -+	opt.output_format = DIFF_FORMAT_NO_OUTPUT;
     -+	opt.no_free = 1;
     -+	diff_setup_done(&opt);
     ++	repo_diff_setup(the_repository, &diffopt);
     ++	diffopt.flags.recursive = 1;
     ++	diffopt.output_format = DIFF_FORMAT_NO_OUTPUT;
     ++	diffopt.no_free = 1;
     ++	diff_setup_done(&diffopt);
      +	init_changed_paths(&cache);
      +
      +	for (size_t i = 0; i < searches_nr; i++) {
     @@ builtin/branch.c: static int branch_pushes_to_upstream(struct branch *branch,
      +
      +		if (!searches[i].changes_nr)
      +			continue;
     -+		landed = find_landed_commit(&searches[i], &cache, &opt);
     ++		landed = find_landed_commit(&searches[i], &cache, &diffopt);
      +		if (landed)
      +			strmap_put(landed_commits, searches[i].branch_name,
      +				   landed);
      +	}
      +
      +	deep_clear_changed_paths(&cache, free_changed_paths);
     -+	opt.no_free = 0;
     -+	diff_free(&opt);
     ++	diffopt.no_free = 0;
     ++	diff_free(&diffopt);
      +}
      +
       static bool branch_opted_out(struct strbuf *key, const char *branch_name,
 4:  9443055242 ! 4:  006a57d7d1 branch: let --delete-integrated find branches merged onto changed files
     @@ builtin/branch.c: static void collect_branch_changes(struct landing_search *sear
       		       &p->two->oid : null_oid(the_hash_algo));
       		change->branch_mode = p->two->mode;
      @@ builtin/branch.c: static void collect_branch_changes(struct landing_search *search,
     - 	diff_flush(&opt);
     + 	diff_flush(&diffopt);
       }
       
      -static int change_landed(const struct branch_change *change,
     @@ builtin/branch.c: static void collect_branch_changes(struct landing_search *sear
      +	mmfile_t result = { 0 };
      +	int ret;
      +
     ++	repo_read_index(the_repository);
      +	read_mmblob(&base, the_repository->objects, &change->base_oid);
      +	read_mmblob(&upstream, the_repository->objects, &change->upstream_oid);
      +	read_mmblob(&branch, the_repository->objects, &change->branch_oid);

-- 
gitgitgadget