[PATCH 0/1] Add blob find pickaxe option

[PATCH 0/1] Add blob find pickaxe option

[Stefan Beller]

This is a resend for sb/diff-blobfind, but now the option --find-object
is a native of the pickaxe family.

Stefan Beller (1):
  diffcore: add a pickaxe option to find a specific blob

 Documentation/diff-options.txt | 10 +++++++
 diff.c                         | 21 ++++++++++++-
 diff.h                         |  3 ++
 diffcore-pickaxe.c             | 14 +++++++--
 revision.c                     |  3 ++
 t/t4064-diff-oidfind.sh        | 68 ++++++++++++++++++++++++++++++++++++++++++
 6 files changed, 115 insertions(+), 4 deletions(-)
 create mode 100755 t/t4064-diff-oidfind.sh

-- 
2.15.1.620.gb9897f4670-goog

diff --git c/Documentation/diff-options.txt w/Documentation/diff-options.txt
index 21d1776996..f9cf85db05 100644
--- c/Documentation/diff-options.txt
+++ w/Documentation/diff-options.txt
@@ -492,6 +492,15 @@ occurrences of that string did not change).
 See the 'pickaxe' entry in linkgit:gitdiffcore[7] for more
 information.
 
+--find-object=<object-id>::
+	Look for differences that change the number of occurrences of
+	the specified object. Similar to `-S`, just the argument is different
+	in that it doesn't search for a specific string but for a specific
+	object id.
++
+The object can be a blob or a submodule commit. It implies the `-t` option in
+`git-log` to also find trees.
+
 --pickaxe-all::
 	When `-S` or `-G` finds a change, show all the changes in that
 	changeset, not just the files that contain the change
@@ -501,11 +510,6 @@ information.
 	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 c/Makefile w/Makefile
index c26596c30a..ee9d5eb11e 100644
--- c/Makefile
+++ w/Makefile
@@ -775,7 +775,6 @@ 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 c/builtin/log.c w/builtin/log.c
index 08ea82d69f..6c1fa896ad 100644
--- c/builtin/log.c
+++ w/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.objfind)
+	    rev->diffopt.flags.follow_renames)
 		rev->always_show_header = 0;
 
 	if (source)
diff --git c/diff.c w/diff.c
index e13b8229d3..7acddaaee7 100644
--- c/diff.c
+++ w/diff.c
@@ -4497,6 +4497,10 @@ static int parse_objfind_opt(struct diff_options *opt, const char *arg)
 
 	if (!opt->objfind)
 		opt->objfind = xcalloc(1, sizeof(*opt->objfind));
+
+	opt->pickaxe = ""; /* trigger pickaxe */
+	opt->flags.recursive = 1;
+	opt->flags.tree_in_recursive = 1;
 	oidset_insert(opt->objfind, &oid);
 	return 1;
 }
@@ -5785,9 +5789,6 @@ 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 c/diffcore-objfind.c w/diffcore-objfind.c
deleted file mode 100644
index 676bbfff00..0000000000
--- c/diffcore-objfind.c
+++ /dev/null
@@ -1,42 +0,0 @@
-/*
- * 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 c/diffcore-pickaxe.c w/diffcore-pickaxe.c
index 9476bd2108..0d0c697ae7 100644
--- c/diffcore-pickaxe.c
+++ w/diffcore-pickaxe.c
@@ -124,13 +124,21 @@ static int pickaxe_match(struct diff_filepair *p, struct diff_options *o,
 	mmfile_t mf1, mf2;
 	int ret;
 
-	if (!o->pickaxe[0])
-		return 0;
-
 	/* ignore unmerged */
 	if (!DIFF_FILE_VALID(p->one) && !DIFF_FILE_VALID(p->two))
 		return 0;
 
+	if (o->objfind) {
+		if ((DIFF_FILE_VALID(p->one) &&
+		     oidset_contains(o->objfind, &p->one->oid)) ||
+		    (DIFF_FILE_VALID(p->two) &&
+		     oidset_contains(o->objfind, &p->two->oid)))
+			return 1;
+	}
+
+	if (!o->pickaxe[0])
+		return 0;
+
 	if (o->flags.allow_textconv) {
 		textconv_one = get_textconv(p->one);
 		textconv_two = get_textconv(p->two);
diff --git c/diffcore.h w/diffcore.h
index cbde777bdd..a30da161da 100644
--- c/diffcore.h
+++ w/diffcore.h
@@ -107,7 +107,6 @@ 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 c/revision.c w/revision.c
index 0a797bdfc7..43bb6265cd 100644
--- c/revision.c
+++ w/revision.c
@@ -2409,10 +2409,12 @@ 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.objfind)
+	    revs->diffopt.flags.follow_renames)
 		revs->diff = 1;
 
+	if (revs->diffopt.objfind)
+		revs->simplify_history = 0;
+
 	if (revs->topo_order)
 		revs->limited = 1;
 
@@ -2884,8 +2886,6 @@ 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 c/t/helper/test-lazy-init-name-hash.c w/t/helper/test-lazy-init-name-hash.c
index 6368a89345..297fb01d61 100644
--- c/t/helper/test-lazy-init-name-hash.c
+++ w/t/helper/test-lazy-init-name-hash.c
@@ -112,7 +112,7 @@ static void analyze_run(void)
 {
 	uint64_t t1s, t1m, t2s, t2m;
 	int cache_nr_limit;
-	int nr_threads_used;
+	int nr_threads_used = 0;
 	int i;
 	int nr;
 

[PATCH 1/1] diffcore: add a pickaxe option to find a specific blob

[Stefan Beller]

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>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
---
 Documentation/diff-options.txt | 10 +++++++
 diff.c                         | 21 ++++++++++++-
 diff.h                         |  3 ++
 diffcore-pickaxe.c             | 14 +++++++--
 revision.c                     |  3 ++
 t/t4064-diff-oidfind.sh        | 68 ++++++++++++++++++++++++++++++++++++++++++
 6 files changed, 115 insertions(+), 4 deletions(-)
 create mode 100755 t/t4064-diff-oidfind.sh

diff --git a/Documentation/diff-options.txt b/Documentation/diff-options.txt
index dd0dba5b1d..f9cf85db05 100644
--- a/Documentation/diff-options.txt
+++ b/Documentation/diff-options.txt
@@ -492,6 +492,15 @@ occurrences of that string did not change).
 See the 'pickaxe' entry in linkgit:gitdiffcore[7] for more
 information.
 
+--find-object=<object-id>::
+	Look for differences that change the number of occurrences of
+	the specified object. Similar to `-S`, just the argument is different
+	in that it doesn't search for a specific string but for a specific
+	object id.
++
+The object can be a blob or a submodule commit. It implies the `-t` option in
+`git-log` to also find trees.
+
 --pickaxe-all::
 	When `-S` or `-G` finds a change, show all the changes in that
 	changeset, not just the files that contain the change
@@ -500,6 +509,7 @@ information.
 --pickaxe-regex::
 	Treat the <string> given to `-S` as an extended POSIX regular
 	expression to match.
+
 endif::git-format-patch[]
 
 -O<orderfile>::
diff --git a/diff.c b/diff.c
index 0763e89263..7acddaaee7 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 +4488,23 @@ 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));
+
+	opt->pickaxe = ""; /* trigger pickaxe */
+	opt->flags.recursive = 1;
+	opt->flags.tree_in_recursive = 1;
+	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 +4754,8 @@ 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)
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-pickaxe.c b/diffcore-pickaxe.c
index 9476bd2108..0d0c697ae7 100644
--- a/diffcore-pickaxe.c
+++ b/diffcore-pickaxe.c
@@ -124,13 +124,21 @@ static int pickaxe_match(struct diff_filepair *p, struct diff_options *o,
 	mmfile_t mf1, mf2;
 	int ret;
 
-	if (!o->pickaxe[0])
-		return 0;
-
 	/* ignore unmerged */
 	if (!DIFF_FILE_VALID(p->one) && !DIFF_FILE_VALID(p->two))
 		return 0;
 
+	if (o->objfind) {
+		if ((DIFF_FILE_VALID(p->one) &&
+		     oidset_contains(o->objfind, &p->one->oid)) ||
+		    (DIFF_FILE_VALID(p->two) &&
+		     oidset_contains(o->objfind, &p->two->oid)))
+			return 1;
+	}
+
+	if (!o->pickaxe[0])
+		return 0;
+
 	if (o->flags.allow_textconv) {
 		textconv_one = get_textconv(p->one);
 		textconv_two = get_textconv(p->two);
diff --git a/revision.c b/revision.c
index e2e691dd5a..43bb6265cd 100644
--- a/revision.c
+++ b/revision.c
@@ -2412,6 +2412,9 @@ int setup_revisions(int argc, const char **argv, struct rev_info *revs, struct s
 	    revs->diffopt.flags.follow_renames)
 		revs->diff = 1;
 
+	if (revs->diffopt.objfind)
+		revs->simplify_history = 0;
+
 	if (revs->topo_order)
 		revs->limited = 1;
 
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
-- 
2.15.1.620.gb9897f4670-goog

Re: [PATCH 1/1] diffcore: add a pickaxe option to find a specific blob

[Junio C Hamano]

Stefan Beller <sbeller@google.com> writes:

> +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));
> +
> +	opt->pickaxe = ""; /* trigger pickaxe */

Hmmm.  This feels like an ugly hack to me.  Do we declare that "git
log -S''" never matches anything right now (if that is the case the
I do not think there is any compatibility issues)?

> diff --git a/diffcore-pickaxe.c b/diffcore-pickaxe.c
> index 9476bd2108..0d0c697ae7 100644
> --- a/diffcore-pickaxe.c
> +++ b/diffcore-pickaxe.c
> @@ -124,13 +124,21 @@ static int pickaxe_match(struct diff_filepair *p, struct diff_options *o,
>  	mmfile_t mf1, mf2;
>  	int ret;
>  
> -	if (!o->pickaxe[0])
> -		return 0;
> -
>  	/* ignore unmerged */
>  	if (!DIFF_FILE_VALID(p->one) && !DIFF_FILE_VALID(p->two))
>  		return 0;
>  
> +	if (o->objfind) {
> +		if ((DIFF_FILE_VALID(p->one) &&
> +		     oidset_contains(o->objfind, &p->one->oid)) ||
> +		    (DIFF_FILE_VALID(p->two) &&
> +		     oidset_contains(o->objfind, &p->two->oid)))
> +			return 1;
> +	}
> +
> +	if (!o->pickaxe[0])
> +		return 0;
> +

Very nice.  With just one place, the code covers both cases with and
without pickaxe-all option in effect.

Re: [PATCH 1/1] diffcore: add a pickaxe option to find a specific blob

[Stefan Beller]

On Thu, Dec 28, 2017 at 1:33 PM, Junio C Hamano <gitster@pobox.com> wrote:
> Stefan Beller <sbeller@google.com> writes:
>
>> +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));
>> +
>> +     opt->pickaxe = ""; /* trigger pickaxe */
>
> Hmmm.  This feels like an ugly hack to me.

Because it is.

$ git grep pickaxe diff.h
diff.h:94:      unsigned pickaxe_ignore_case:1;
diff.h:130:     const char *pickaxe;
diff.h:149:     int pickaxe_opts;
diff.h:361:"  --pickaxe-all\n" \

We could promote pickaxe_opts to be the important part
for pickaxing, currently we're using `pickaxe` in diff.c to
make a decision:

    if (options->pickaxe)
        diffcore_pickaxe(options);

So I think I'll cleanup the pickaxe_opts to be a real
unsigned flags field (such that pickaxe_ignore_case
could be part of it, too!) and put a new flag in
there in addition to DIFF_PICKAXE_KIND_{G, S}

> Do we declare that "git
> log -S''" never matches anything right now (if that is the case the
> I do not think there is any compatibility issues)?

Let's not go this route.


>
>> diff --git a/diffcore-pickaxe.c b/diffcore-pickaxe.c
>> index 9476bd2108..0d0c697ae7 100644
>> --- a/diffcore-pickaxe.c
>> +++ b/diffcore-pickaxe.c
>> @@ -124,13 +124,21 @@ static int pickaxe_match(struct diff_filepair *p, struct diff_options *o,
>>       mmfile_t mf1, mf2;
>>       int ret;
>>
>> -     if (!o->pickaxe[0])
>> -             return 0;
>> -
>>       /* ignore unmerged */
>>       if (!DIFF_FILE_VALID(p->one) && !DIFF_FILE_VALID(p->two))
>>               return 0;
>>
>> +     if (o->objfind) {
>> +             if ((DIFF_FILE_VALID(p->one) &&
>> +                  oidset_contains(o->objfind, &p->one->oid)) ||
>> +                 (DIFF_FILE_VALID(p->two) &&
>> +                  oidset_contains(o->objfind, &p->two->oid)))
>> +                     return 1;
>> +     }
>> +
>> +     if (!o->pickaxe[0])
>> +             return 0;
>> +
>
> Very nice.  With just one place, the code covers both cases with and
> without pickaxe-all option in effect.

and this is already fixed regarding the ugly hack, too.

Thanks,
Stefan