git@vger.kernel.org mailing list mirror (one of many)
 help / Atom feed
From: Stefan Beller <sbeller@google.com>
To: sbeller@google.com
Cc: git@vger.kernel.org, gitster@pobox.com, peff@peff.net
Subject: [PATCH] diffcore: add a filter to find a specific blob
Date: Mon, 11 Dec 2017 17:24:22 -0800
Message-ID: <20171212012422.123332-1-sbeller@google.com> (raw)
In-Reply-To: <CAGZ79kaJgCchQKcRMkW-cjRmx_7eYQDqLs5GgDOgLEb1H=w-0g@mail.gmail.com>

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])

One might be tempted to extend git-describe to also work with blobs,
such that `git describe <blob-id>` gives a description as
'<commit-ish>:<path>'.  This was implemented at [2]; as seen by the sheer
number of responses (>110), it turns out this is tricky to get right.
The hard part to get right is picking the correct 'commit-ish' as that
could be the commit that (re-)introduced the blob or the blob that
removed the blob; the blob could exist in different branches.

Junio hinted at a different approach of solving this problem, which this
patch implements. Teach the diff machinery another flag for restricting
the information to what is shown. For example:

  $ ./git log --oneline --find-object=v2.0.0:Makefile
  b2feb64309 Revert the whole "ask curl-config" topic for now
  47fbfded53 i18n: only extract comments marked with "TRANSLATORS:"

we observe that the Makefile as shipped with 2.0 was appeared in
v1.9.2-471-g47fbfded53 and in v2.0.0-rc1-5-gb2feb6430b.  The
reason why these commits both occur prior to v2.0.0 are evil
merges that are not found using this new mechanism.

[1] https://stackoverflow.com/questions/223678/which-commit-has-this-blob
[2] https://public-inbox.org/git/20171028004419.10139-1-sbeller@google.com/

Signed-off-by: Stefan Beller <sbeller@google.com>

asdf

Signed-off-by: Stefan Beller <sbeller@google.com>
---
 Documentation/diff-options.txt |  6 ++++
 Makefile                       |  1 +
 builtin/log.c                  |  2 +-
 diff.c                         | 20 ++++++++++++-
 diff.h                         |  3 ++
 diffcore-objfind.c             | 42 ++++++++++++++++++++++++++
 diffcore.h                     |  1 +
 revision.c                     |  5 +++-
 t/t4064-diff-oidfind.sh        | 68 ++++++++++++++++++++++++++++++++++++++++++
 9 files changed, 145 insertions(+), 3 deletions(-)
 create mode 100644 diffcore-objfind.c
 create mode 100755 t/t4064-diff-oidfind.sh

diff --git a/Documentation/diff-options.txt b/Documentation/diff-options.txt
index dd0dba5b1d..21d1776996 100644
--- a/Documentation/diff-options.txt
+++ b/Documentation/diff-options.txt
@@ -500,6 +500,12 @@ information.
 --pickaxe-regex::
 	Treat the <string> given to `-S` as an extended POSIX regular
 	expression to match.
+
+--find-object=<object-id>::
+	Restrict the output such that one side of the diff
+	matches the given object id. The object can be a blob,
+	gitlink entry or tree (when `-t` is given).
+
 endif::git-format-patch[]
 
 -O<orderfile>::
diff --git a/Makefile b/Makefile
index ee9d5eb11e..c26596c30a 100644
--- a/Makefile
+++ b/Makefile
@@ -775,6 +775,7 @@ LIB_OBJS += date.o
 LIB_OBJS += decorate.o
 LIB_OBJS += diffcore-break.o
 LIB_OBJS += diffcore-delta.o
+LIB_OBJS += diffcore-objfind.o
 LIB_OBJS += diffcore-order.o
 LIB_OBJS += diffcore-pickaxe.o
 LIB_OBJS += diffcore-rename.o
diff --git a/builtin/log.c b/builtin/log.c
index 6c1fa896ad..08ea82d69f 100644
--- a/builtin/log.c
+++ b/builtin/log.c
@@ -181,7 +181,7 @@ static void cmd_log_init_finish(int argc, const char **argv, const char *prefix,
 		init_display_notes(&rev->notes_opt);
 
 	if (rev->diffopt.pickaxe || rev->diffopt.filter ||
-	    rev->diffopt.flags.follow_renames)
+	    rev->diffopt.flags.follow_renames || rev->diffopt.objfind)
 		rev->always_show_header = 0;
 
 	if (source)
diff --git a/diff.c b/diff.c
index 0763e89263..e13b8229d3 100644
--- a/diff.c
+++ b/diff.c
@@ -4082,6 +4082,7 @@ void diff_setup(struct diff_options *options)
 	options->interhunkcontext = diff_interhunk_context_default;
 	options->ws_error_highlight = ws_error_highlight_default;
 	options->flags.rename_empty = 1;
+	options->objfind = NULL;
 
 	/* pathchange left =NULL by default */
 	options->change = diff_change;
@@ -4487,6 +4488,19 @@ static int parse_ws_error_highlight_opt(struct diff_options *opt, const char *ar
 	return 1;
 }
 
+static int parse_objfind_opt(struct diff_options *opt, const char *arg)
+{
+	struct object_id oid;
+
+	if (get_oid(arg, &oid))
+		return error("unable to resolve '%s'", arg);
+
+	if (!opt->objfind)
+		opt->objfind = xcalloc(1, sizeof(*opt->objfind));
+	oidset_insert(opt->objfind, &oid);
+	return 1;
+}
+
 int diff_opt_parse(struct diff_options *options,
 		   const char **av, int ac, const char *prefix)
 {
@@ -4736,7 +4750,8 @@ int diff_opt_parse(struct diff_options *options,
 	else if ((argcount = short_opt('O', av, &optarg))) {
 		options->orderfile = prefix_filename(prefix, optarg);
 		return argcount;
-	}
+	} else if (skip_prefix(arg, "--find-object=", &arg))
+		return parse_objfind_opt(options, arg);
 	else if ((argcount = parse_long_opt("diff-filter", av, &optarg))) {
 		int offending = parse_diff_filter_opt(optarg, options);
 		if (offending)
@@ -5770,6 +5785,9 @@ void diffcore_std(struct diff_options *options)
 		diffcore_skip_stat_unmatch(options);
 	if (!options->found_follow) {
 		/* See try_to_follow_renames() in tree-diff.c */
+
+		if (options->objfind)
+			diffcore_objfind(options);
 		if (options->break_opt != -1)
 			diffcore_break(options->break_opt);
 		if (options->detect_rename)
diff --git a/diff.h b/diff.h
index 0fb18dd735..8fa2ad8e2d 100644
--- a/diff.h
+++ b/diff.h
@@ -7,6 +7,7 @@
 #include "tree-walk.h"
 #include "pathspec.h"
 #include "object.h"
+#include "oidset.h"
 
 struct rev_info;
 struct diff_options;
@@ -174,6 +175,8 @@ struct diff_options {
 	enum diff_words_type word_diff;
 	enum diff_submodule_format submodule_format;
 
+	struct oidset *objfind;
+
 	/* this is set by diffcore for DIFF_FORMAT_PATCH */
 	int found_changes;
 
diff --git a/diffcore-objfind.c b/diffcore-objfind.c
new file mode 100644
index 0000000000..676bbfff00
--- /dev/null
+++ b/diffcore-objfind.c
@@ -0,0 +1,42 @@
+/*
+ * Copyright (c) 2017 Google Inc.
+ */
+#include "cache.h"
+#include "diff.h"
+#include "diffcore.h"
+
+static void diffcore_filter_blobs(struct diff_queue_struct *q,
+				  struct diff_options *options)
+{
+	int src, dst;
+
+	if (!options->objfind)
+		BUG("objfind oidset not initialized???");
+
+	for (src = dst = 0; src < q->nr; src++) {
+		struct diff_filepair *p = q->queue[src];
+
+		if (!DIFF_PAIR_UNMERGED(p) &&
+		    ((DIFF_FILE_VALID(p->one) &&
+		     oidset_contains(options->objfind, &p->one->oid)) ||
+		    (DIFF_FILE_VALID(p->two) &&
+		     oidset_contains(options->objfind, &p->two->oid)))) {
+			q->queue[dst] = p;
+			dst++;
+		} else {
+			diff_free_filepair(p);
+		}
+	}
+
+	if (!dst) {
+		free(q->queue);
+		DIFF_QUEUE_CLEAR(q);
+	} else {
+		q->nr = dst;
+	}
+}
+
+void diffcore_objfind(struct diff_options *options)
+{
+	diffcore_filter_blobs(&diff_queued_diff, options);
+}
diff --git a/diffcore.h b/diffcore.h
index a30da161da..cbde777bdd 100644
--- a/diffcore.h
+++ b/diffcore.h
@@ -107,6 +107,7 @@ extern struct diff_filepair *diff_queue(struct diff_queue_struct *,
 					struct diff_filespec *);
 extern void diff_q(struct diff_queue_struct *, struct diff_filepair *);
 
+extern void diffcore_objfind(struct diff_options *);
 extern void diffcore_break(int);
 extern void diffcore_rename(struct diff_options *);
 extern void diffcore_merge_broken(void);
diff --git a/revision.c b/revision.c
index e2e691dd5a..0a797bdfc7 100644
--- a/revision.c
+++ b/revision.c
@@ -2409,7 +2409,8 @@ int setup_revisions(int argc, const char **argv, struct rev_info *revs, struct s
 	/* Pickaxe, diff-filter and rename following need diffs */
 	if (revs->diffopt.pickaxe ||
 	    revs->diffopt.filter ||
-	    revs->diffopt.flags.follow_renames)
+	    revs->diffopt.flags.follow_renames ||
+	    revs->diffopt.objfind)
 		revs->diff = 1;
 
 	if (revs->topo_order)
@@ -2883,6 +2884,8 @@ int prepare_revision_walk(struct rev_info *revs)
 		simplify_merges(revs);
 	if (revs->children.name)
 		set_children(revs);
+	if (revs->diffopt.objfind)
+		revs->simplify_history = 0;
 	return 0;
 }
 
diff --git a/t/t4064-diff-oidfind.sh b/t/t4064-diff-oidfind.sh
new file mode 100755
index 0000000000..3bdf317af8
--- /dev/null
+++ b/t/t4064-diff-oidfind.sh
@@ -0,0 +1,68 @@
+#!/bin/sh
+
+test_description='test finding specific blobs in the revision walking'
+. ./test-lib.sh
+
+test_expect_success 'setup ' '
+	git commit --allow-empty -m "empty initial commit" &&
+
+	echo "Hello, world!" >greeting &&
+	git add greeting &&
+	git commit -m "add the greeting blob" && # borrowed from Git from the Bottom Up
+	git tag -m "the blob" greeting $(git rev-parse HEAD:greeting) &&
+
+	echo asdf >unrelated &&
+	git add unrelated &&
+	git commit -m "unrelated history" &&
+
+	git revert HEAD^ &&
+
+	git commit --allow-empty -m "another unrelated commit"
+'
+
+test_expect_success 'find the greeting blob' '
+	cat >expect <<-EOF &&
+	Revert "add the greeting blob"
+	add the greeting blob
+	EOF
+
+	git log --format=%s --find-object=greeting^{blob} >actual &&
+
+	test_cmp expect actual
+'
+
+test_expect_success 'setup a tree' '
+	mkdir a &&
+	echo asdf >a/file &&
+	git add a/file &&
+	git commit -m "add a file in a subdirectory"
+'
+
+test_expect_success 'find a tree' '
+	cat >expect <<-EOF &&
+	add a file in a subdirectory
+	EOF
+
+	git log --format=%s -t --find-object=HEAD:a >actual &&
+
+	test_cmp expect actual
+'
+
+test_expect_success 'setup a submodule' '
+	test_create_repo sub &&
+	test_commit -C sub sub &&
+	git submodule add ./sub sub &&
+	git commit -a -m "add sub"
+'
+
+test_expect_success 'find a submodule' '
+	cat >expect <<-EOF &&
+	add sub
+	EOF
+
+	git log --format=%s --find-object=HEAD:sub >actual &&
+
+	test_cmp expect actual
+'
+
+test_done
-- 
2.15.1.504.g5279b80103-goog


  reply index

Thread overview: 25+ messages in thread (expand / mbox.gz / Atom feed / [top])
2017-12-08  0:24 [PATCH 0/1] diffcore-blobfind Stefan Beller
2017-12-08  0:24 ` [PATCH 1/1] diffcore: add a filter to find a specific blob Stefan Beller
2017-12-08  9:34   ` Jeff King
2017-12-08 16:28     ` Ramsay Jones
2017-12-08 20:19       ` Jeff King
2017-12-08 20:39         ` Stefan Beller
2017-12-08 21:38           ` Jeff King
2017-12-08 15:04   ` Junio C Hamano
2017-12-08 17:21     ` Junio C Hamano
2017-12-08 21:11     ` Stefan Beller
2017-12-08 21:15       ` Junio C Hamano
2017-12-11 19:58 ` [PATCH 0/1] diff-core blobfind Stefan Beller
2017-12-11 19:58   ` [PATCH 1/1] diffcore: add a filter to find a specific blob Stefan Beller
2017-12-11 23:17     ` Junio C Hamano
2017-12-12  0:21       ` Stefan Beller
2017-12-12  1:24         ` Stefan Beller [this message]
2017-12-12 18:36           ` [PATCH] " Junio C Hamano
2017-12-14 21:22           ` Jonathan Nieder
2017-12-14 22:30             ` Stefan Beller
2017-12-14 22:52               ` Jonathan Nieder
2017-12-15  2:18                 ` Junio C Hamano
2017-12-27 18:49                   ` Stefan Beller
2017-12-27 18:59                     ` Jonathan Nieder
2017-12-27 19:57                       ` Junio C Hamano
2017-12-14 22:44             ` Junio C Hamano

Reply instructions:

You may reply publically to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

  List information: http://vger.kernel.org/majordomo-info.html

* Reply to all the recipients using the --to, --cc,
  and --in-reply-to switches of git-send-email(1):

  git send-email \
    --in-reply-to=20171212012422.123332-1-sbeller@google.com \
    --to=sbeller@google.com \
    --cc=git@vger.kernel.org \
    --cc=gitster@pobox.com \
    --cc=peff@peff.net \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

git@vger.kernel.org mailing list mirror (one of many)

Archives are clonable:
	git clone --mirror https://public-inbox.org/git
	git clone --mirror http://ou63pmih66umazou.onion/git
	git clone --mirror http://czquwvybam4bgbro.onion/git
	git clone --mirror http://hjrcffqmbrq6wope.onion/git

Newsgroups are available over NNTP:
	nntp://news.public-inbox.org/inbox.comp.version-control.git
	nntp://ou63pmih66umazou.onion/inbox.comp.version-control.git
	nntp://czquwvybam4bgbro.onion/inbox.comp.version-control.git
	nntp://hjrcffqmbrq6wope.onion/inbox.comp.version-control.git
	nntp://news.gmane.org/gmane.comp.version-control.git

 note: .onion URLs require Tor: https://www.torproject.org/
       or Tor2web: https://www.tor2web.org/

AGPL code for this site: git clone https://public-inbox.org/ public-inbox