Merge branch 'sb/diff-blobfind-pickaxe'

"diff" family of commands learned "--find-object=<object-id>" option
to limit the findings to changes that involve the named object.

* sb/diff-blobfind-pickaxe:
  diff: use HAS_MULTI_BITS instead of counting bits manually
  diff: properly error out when combining multiple pickaxe options
  diffcore: add a pickaxe option to find a specific blob
  diff: introduce DIFF_PICKAXE_KINDS_MASK
  diff: migrate diff_flags.pickaxe_ignore_case to a pickaxe_opts bit
  diff.h: make pickaxe_opts an unsigned bit field

8 files changed, 155 insertions, 40 deletions

diff --git a/Documentation/diff-options.txt b/Documentation/diff-options.txt
index 743af97b06..c330c01ff0 100644
--- a/Documentation/diff-options.txt
+++ b/Documentation/diff-options.txt
@@ -508,6 +508,15 @@ 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
@@ -516,6 +525,7 @@ 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/builtin/log.c b/builtin/log.c
index 14fdf39165..46b4ca13e5 100644
--- a/builtin/log.c
+++ b/builtin/log.c
@@ -188,8 +188,8 @@ static void cmd_log_init_finish(int argc, const char **argv, const char *prefix,
 	if (rev->show_notes)
 		init_display_notes(&rev->notes_opt);
 
-	if (rev->diffopt.pickaxe || rev->diffopt.filter ||
-	    rev->diffopt.flags.follow_renames)
+	if ((rev->diffopt.pickaxe_opts & DIFF_PICKAXE_KINDS_MASK) ||
+	    rev->diffopt.filter || rev->diffopt.flags.follow_renames)
 		rev->always_show_header = 0;
 
 	if (source)
diff --git a/combine-diff.c b/combine-diff.c
index 2505de119a..bc08c4c5b1 100644
--- a/combine-diff.c
+++ b/combine-diff.c
@@ -1438,7 +1438,7 @@ void diff_tree_combined(const struct object_id *oid,
 			opt->flags.follow_renames	||
 			opt->break_opt != -1	||
 			opt->detect_rename	||
-			opt->pickaxe		||
+			(opt->pickaxe_opts & DIFF_PICKAXE_KINDS_MASK)	||
 			opt->filter;
 
 
diff --git a/diff.c b/diff.c
index db4696fdf5..0a9a0cdf18 100644
--- a/diff.c
+++ b/diff.c
@@ -4086,6 +4086,7 @@ 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;
@@ -4110,22 +4111,20 @@ void diff_setup(struct diff_options *options)
 
 void diff_setup_done(struct diff_options *options)
 {
-	int count = 0;
+	unsigned check_mask = DIFF_FORMAT_NAME |
+			      DIFF_FORMAT_NAME_STATUS |
+			      DIFF_FORMAT_CHECKDIFF |
+			      DIFF_FORMAT_NO_OUTPUT;
 
 	if (options->set_default)
 		options->set_default(options);
 
-	if (options->output_format & DIFF_FORMAT_NAME)
-		count++;
-	if (options->output_format & DIFF_FORMAT_NAME_STATUS)
-		count++;
-	if (options->output_format & DIFF_FORMAT_CHECKDIFF)
-		count++;
-	if (options->output_format & DIFF_FORMAT_NO_OUTPUT)
-		count++;
-	if (count > 1)
+	if (HAS_MULTI_BITS(options->output_format & check_mask))
 		die(_("--name-only, --name-status, --check and -s are mutually exclusive"));
 
+	if (HAS_MULTI_BITS(options->pickaxe_opts & DIFF_PICKAXE_KINDS_MASK))
+		die(_("-G, -S and --find-object are mutually exclusive"));
+
 	/*
 	 * Most of the time we can say "there are changes"
 	 * only by checking if there are changed paths, but
@@ -4175,7 +4174,7 @@ void diff_setup_done(struct diff_options *options)
 	/*
 	 * Also pickaxe would not work very well if you do not say recursive
 	 */
-	if (options->pickaxe)
+	if (options->pickaxe_opts & DIFF_PICKAXE_KINDS_MASK)
 		options->flags.recursive = 1;
 	/*
 	 * When patches are generated, submodules diffed against the work tree
@@ -4489,6 +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_opts |= DIFF_PICKAXE_KIND_OBJFIND;
+	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 +4752,8 @@ 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)
@@ -5783,7 +5800,7 @@ void diffcore_std(struct diff_options *options)
 		if (options->break_opt != -1)
 			diffcore_merge_broken();
 	}
-	if (options->pickaxe)
+	if (options->pickaxe_opts & DIFF_PICKAXE_KINDS_MASK)
 		diffcore_pickaxe(options);
 	if (options->orderfile)
 		diffcore_order(options->orderfile);
diff --git a/diff.h b/diff.h
index 7cf276f077..6bd278aac1 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;
@@ -91,7 +92,6 @@ struct diff_flags {
 	unsigned override_submodule_config:1;
 	unsigned dirstat_by_line:1;
 	unsigned funccontext:1;
-	unsigned pickaxe_ignore_case:1;
 	unsigned default_follow_renames:1;
 };
 
@@ -146,7 +146,7 @@ struct diff_options {
 	int skip_stat_unmatch;
 	int line_termination;
 	int output_format;
-	int pickaxe_opts;
+	unsigned pickaxe_opts;
 	int rename_score;
 	int rename_limit;
 	int needed_rename_limit;
@@ -178,6 +178,8 @@ 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;
 
@@ -330,6 +332,13 @@ extern void diff_setup_done(struct diff_options *);
 
 #define DIFF_PICKAXE_KIND_S	4 /* traditional plumbing counter */
 #define DIFF_PICKAXE_KIND_G	8 /* grep in the patch */
+#define DIFF_PICKAXE_KIND_OBJFIND	16 /* specific object IDs */
+
+#define DIFF_PICKAXE_KINDS_MASK (DIFF_PICKAXE_KIND_S | \
+				 DIFF_PICKAXE_KIND_G | \
+				 DIFF_PICKAXE_KIND_OBJFIND)
+
+#define DIFF_PICKAXE_IGNORE_CASE	32
 
 extern void diffcore_std(struct diff_options *);
 extern void diffcore_fix_diff_index(struct diff_options *);
diff --git a/diffcore-pickaxe.c b/diffcore-pickaxe.c
index 9476bd2108..239ce5122b 100644
--- a/diffcore-pickaxe.c
+++ b/diffcore-pickaxe.c
@@ -124,13 +124,20 @@ 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) {
+		return  (DIFF_FILE_VALID(p->one) &&
+			 oidset_contains(o->objfind, &p->one->oid)) ||
+			(DIFF_FILE_VALID(p->two) &&
+			 oidset_contains(o->objfind, &p->two->oid));
+	}
+
+	if (!o->pickaxe[0])
+		return 0;
+
 	if (o->flags.allow_textconv) {
 		textconv_one = get_textconv(p->one);
 		textconv_two = get_textconv(p->two);
@@ -222,33 +229,34 @@ void diffcore_pickaxe(struct diff_options *o)
 
 	if (opts & (DIFF_PICKAXE_REGEX | DIFF_PICKAXE_KIND_G)) {
 		int cflags = REG_EXTENDED | REG_NEWLINE;
-		if (o->flags.pickaxe_ignore_case)
+		if (o->pickaxe_opts & DIFF_PICKAXE_IGNORE_CASE)
 			cflags |= REG_ICASE;
 		regcomp_or_die(&regex, needle, cflags);
 		regexp = &regex;
-	} else if (o->flags.pickaxe_ignore_case &&
-		   has_non_ascii(needle)) {
-		struct strbuf sb = STRBUF_INIT;
-		int cflags = REG_NEWLINE | REG_ICASE;
-
-		basic_regex_quote_buf(&sb, needle);
-		regcomp_or_die(&regex, sb.buf, cflags);
-		strbuf_release(&sb);
-		regexp = &regex;
-	} else {
-		kws = kwsalloc(o->flags.pickaxe_ignore_case
-			       ? tolower_trans_tbl : NULL);
-		kwsincr(kws, needle, strlen(needle));
-		kwsprep(kws);
+	} else if (opts & DIFF_PICKAXE_KIND_S) {
+		if (o->pickaxe_opts & DIFF_PICKAXE_IGNORE_CASE &&
+		    has_non_ascii(needle)) {
+			struct strbuf sb = STRBUF_INIT;
+			int cflags = REG_NEWLINE | REG_ICASE;
+
+			basic_regex_quote_buf(&sb, needle);
+			regcomp_or_die(&regex, sb.buf, cflags);
+			strbuf_release(&sb);
+			regexp = &regex;
+		} else {
+			kws = kwsalloc(o->pickaxe_opts & DIFF_PICKAXE_IGNORE_CASE
+				       ? tolower_trans_tbl : NULL);
+			kwsincr(kws, needle, strlen(needle));
+			kwsprep(kws);
+		}
 	}
 
-	/* Might want to warn when both S and G are on; I don't care... */
 	pickaxe(&diff_queued_diff, o, regexp, kws,
 		(opts & DIFF_PICKAXE_KIND_G) ? diff_grep : has_changes);
 
 	if (regexp)
 		regfree(regexp);
-	else
+	if (kws)
 		kwsfree(kws);
 	return;
 }
diff --git a/revision.c b/revision.c
index 1f7454c947..a60628fbff 100644
--- a/revision.c
+++ b/revision.c
@@ -2078,7 +2078,7 @@ static int handle_revision_opt(struct rev_info *revs, int argc, const char **arg
 		revs->grep_filter.pattern_type_option = GREP_PATTERN_TYPE_ERE;
 	} else if (!strcmp(arg, "--regexp-ignore-case") || !strcmp(arg, "-i")) {
 		revs->grep_filter.ignore_case = 1;
-		revs->diffopt.flags.pickaxe_ignore_case = 1;
+		revs->diffopt.pickaxe_opts |= DIFF_PICKAXE_IGNORE_CASE;
 	} else if (!strcmp(arg, "--fixed-strings") || !strcmp(arg, "-F")) {
 		revs->grep_filter.pattern_type_option = GREP_PATTERN_TYPE_FIXED;
 	} else if (!strcmp(arg, "--perl-regexp") || !strcmp(arg, "-P")) {
@@ -2409,11 +2409,14 @@ int setup_revisions(int argc, const char **argv, struct rev_info *revs, struct s
 		revs->diff = 1;
 
 	/* Pickaxe, diff-filter and rename following need diffs */
-	if (revs->diffopt.pickaxe ||
+	if ((revs->diffopt.pickaxe_opts & DIFF_PICKAXE_KINDS_MASK) ||
 	    revs->diffopt.filter ||
 	    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