builtin/describe.c: describe a blob

Sometimes users are given a hash of an object and they want to
identify it further (ex.: Use verify-pack to find the largest blobs,
but what are these? or [1])

"This is an interesting endeavor, because describing things is hard."
  -- me, upon writing this patch.

When describing commits, we try to anchor them to tags or refs, as these
are conceptually on a higher level than the commit. And if there is no ref
or tag that matches exactly, we're out of luck.  So we employ a heuristic
to make up a name for the commit. These names are ambiguous, there might
be different tags or refs to anchor to, and there might be different
path in the DAG to travel to arrive at the commit precisely.

When describing a blob, we want to describe the blob from a higher layer
as well, which is a tuple of (commit, deep/path) as the tree objects
involved are rather uninteresting.  The same blob can be referenced by
multiple commits, so how we decide which commit to use?  This patch
implements a rather naive approach on this: As there are no back pointers
from blobs to commits in which the blob occurs, we'll start walking from
any tips available, listing the blobs in-order of the commit and once we
found the blob, we'll take the first commit that listed the blob.  For
source code this is likely not the first commit that introduced the blob,
but rather the latest commit that contained the blob.  For example:

  git describe v0.99:Makefile
  v0.99-5-gab6625e06a:Makefile

tells us the latest commit that contained the Makefile as it was in tag
v0.99 is commit v0.99-5-gab6625e06a (and at the same path), as the next
commit on top v0.99-6-gb1de9de2b9 ([PATCH] Bootstrap "make dist",
2005-07-11) touches the Makefile.

Let's see how this description turns out, if it is useful in day-to-day
use as I have the intuition that we'd rather want to see the *first*
commit that this blob was introduced to the repository (which can be
achieved easily by giving the `--reverse` flag in the describe_blob rev
walk).

[1] https://stackoverflow.com/questions/223678/which-commit-has-this-blob

Signed-off-by: Stefan Beller <[email protected]>
Signed-off-by: Junio C Hamano <[email protected]>

Author: stefanbeller

Documentation/git-describe.txt

@@ -3,14 +3,15 @@ git-describe(1)
 
 NAME
 ----
-git-describe - Describe a commit using the most recent tag reachable from it
+git-describe - Describe a commit or blob using the graph relations
 
 
 SYNOPSIS
 --------
 [verse]
 'git describe' [--all] [--tags] [--contains] [--abbrev=<n>] [<commit-ish>...]
 'git describe' [--all] [--tags] [--contains] [--abbrev=<n>] --dirty[=<mark>]
+'git describe' [<options>] <blob>
 
 DESCRIPTION
 -----------
@@ -24,6 +25,16 @@ By default (without --all or --tags) `git describe` only shows
 annotated tags.  For more information about creating annotated tags
 see the -a and -s options to linkgit:git-tag[1].
 
+If the given object refers to a blob, it will be described
+as `<commit-ish>:<path>`, such that the blob can be found
+at `<path>` in the `<commit-ish>`. Note, that the commit is likely
+not the commit that introduced the blob, but the one that was found
+first; to find the commit that introduced the blob, you need to find
+the commit that last touched the path, e.g.
+`git log <commit-description> -- <path>`.
+As blobs do not point at the commits they are contained in,
+describing blobs is slow as we have to walk the whole graph.
+
 OPTIONS
 -------
 <commit-ish>...::

builtin/describe.c

@@ -3,6 +3,7 @@
 #include "lockfile.h"
 #include "commit.h"
 #include "tag.h"
+#include "blob.h"
 #include "refs.h"
 #include "builtin.h"
 #include "exec_cmd.h"
@@ -11,8 +12,9 @@
 #include "hashmap.h"
 #include "argv-array.h"
 #include "run-command.h"
+#include "revision.h"
+#include "list-objects.h"
 
-#define SEEN		(1u << 0)
 #define MAX_TAGS	(FLAG_BITS - 1)
 
 static const char * const describe_usage[] = {
@@ -434,6 +436,56 @@ static void describe_commit(struct object_id *oid, struct strbuf *dst)
 		strbuf_addstr(dst, suffix);
 }
 
+struct process_commit_data {
+	struct object_id current_commit;
+	struct object_id looking_for;
+	struct strbuf *dst;
+	struct rev_info *revs;
+};
+
+static void process_commit(struct commit *commit, void *data)
+{
+	struct process_commit_data *pcd = data;
+	pcd->current_commit = commit->object.oid;
+}
+
+static void process_object(struct object *obj, const char *path, void *data)
+{
+	struct process_commit_data *pcd = data;
+
+	if (!oidcmp(&pcd->looking_for, &obj->oid) && !pcd->dst->len) {
+		reset_revision_walk();
+		describe_commit(&pcd->current_commit, pcd->dst);
+		strbuf_addf(pcd->dst, ":%s", path);
+		pcd->revs->max_count = 0;
+	}
+}
+
+static void describe_blob(struct object_id oid, struct strbuf *dst)
+{
+	struct rev_info revs;
+	struct argv_array args = ARGV_ARRAY_INIT;
+	struct process_commit_data pcd = { null_oid, oid, dst, &revs};
+
+	argv_array_pushl(&args, "internal: The first arg is not parsed",
+		"--all", "--reflog", /* as many starting points as possible */
+		/* NEEDSWORK: --all is incompatible with worktrees for now: */
+		"--single-worktree",
+		"--objects",
+		"--in-commit-order",
+		NULL);
+
+	init_revisions(&revs, NULL);
+	if (setup_revisions(args.argc, args.argv, &revs, NULL) > 1)
+		BUG("setup_revisions could not handle all args?");
+
+	if (prepare_revision_walk(&revs))
+		die("revision walk setup failed");
+
+	traverse_commit_list(&revs, process_commit, process_object, &pcd);
+	reset_revision_walk();
+}
+
 static void describe(const char *arg, int last_one)
 {
 	struct object_id oid;
@@ -445,11 +497,14 @@ static void describe(const char *arg, int last_one)
 
 	if (get_oid(arg, &oid))
 		die(_("Not a valid object name %s"), arg);
-	cmit = lookup_commit_reference(&oid);
-	if (!cmit)
-		die(_("%s is not a valid '%s' object"), arg, commit_type);
+	cmit = lookup_commit_reference_gently(&oid, 1);
 
-	describe_commit(&oid, &sb);
+	if (cmit)
+		describe_commit(&oid, &sb);
+	else if (lookup_blob(&oid))
+		describe_blob(oid, &sb);
+	else
+		die(_("%s is neither a commit nor blob"), arg);
 
 	puts(sb.buf);
 

t/t6120-describe.sh

@@ -310,6 +310,21 @@ test_expect_success 'describe ignoring a broken submodule' '
 	grep broken out
 '
 
+test_expect_success 'describe a blob at a tag' '
+	echo "make it a unique blob" >file &&
+	git add file && git commit -m "content in file" &&
+	git tag -a -m "latest annotated tag" unique-file &&
+	git describe HEAD:file >actual &&
+	echo "unique-file:file" >expect &&
+	test_cmp expect actual
+'
+
+test_expect_success 'describe a blob with commit-ish' '
+	git commit --allow-empty -m "empty commit" &&
+	git describe HEAD:file >actual &&
+	grep unique-file-1-g actual
+'
+
 test_expect_failure ULIMIT_STACK_SIZE 'name-rev works in a deep repo' '
 	i=1 &&
 	while test $i -lt 8000