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

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



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 --blobfind=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 introduced in
v1.9.2-471-g47fbfded53 and replaced in v2.0.0-rc1-5-gb2feb64309 by
a different blob.

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

Signed-off-by: Stefan Beller <sbeller@xxxxxxxxxx>
---
 Documentation/diff-options.txt |  5 +++++
 Makefile                       |  1 +
 builtin/log.c                  |  2 +-
 diff.c                         | 20 +++++++++++++++++++-
 diff.h                         |  3 +++
 diffcore-blobfind.c            | 41 +++++++++++++++++++++++++++++++++++++++++
 diffcore.h                     |  1 +
 revision.c                     |  5 ++++-
 t/t4064-diff-blobfind.sh       | 35 +++++++++++++++++++++++++++++++++++
 9 files changed, 110 insertions(+), 3 deletions(-)
 create mode 100644 diffcore-blobfind.c
 create mode 100755 t/t4064-diff-blobfind.sh

diff --git a/Documentation/diff-options.txt b/Documentation/diff-options.txt
index dd0dba5b1d..34d53b95f1 100644
--- a/Documentation/diff-options.txt
+++ b/Documentation/diff-options.txt
@@ -500,6 +500,11 @@ information.
 --pickaxe-regex::
 	Treat the <string> given to `-S` as an extended POSIX regular
 	expression to match.
+
+--blobfind=<blob-id>::
+	Restrict the output such that one side of the diff
+	matches the given blob-id.
+
 endif::git-format-patch[]
 
 -O<orderfile>::
diff --git a/Makefile b/Makefile
index ee9d5eb11e..fdfa8f38f6 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-blobfind.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..7b91f61423 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.blobfind)
 		rev->always_show_header = 0;
 
 	if (source)
diff --git a/diff.c b/diff.c
index 0763e89263..8861f89ab1 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->blobfind = 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_blobfind_opt(struct diff_options *opt, const char *arg)
+{
+	struct object_id oid;
+
+	if (get_oid_blob(arg, &oid) || sha1_object_info(oid.hash, NULL) != OBJ_BLOB)
+		return error("object '%s' is not a blob", arg);
+
+	if (!opt->blobfind)
+		opt->blobfind = xcalloc(1, sizeof(*opt->blobfind));
+	oidset_insert(opt->blobfind, &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, "--blobfind=", &arg))
+		return parse_blobfind_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->blobfind)
+			diffcore_blobfind(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..9178e498fa 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 *blobfind;
+
 	/* this is set by diffcore for DIFF_FORMAT_PATCH */
 	int found_changes;
 
diff --git a/diffcore-blobfind.c b/diffcore-blobfind.c
new file mode 100644
index 0000000000..e65c7cad6e
--- /dev/null
+++ b/diffcore-blobfind.c
@@ -0,0 +1,41 @@
+/*
+ * 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->blobfind)
+		BUG("blobfind oidset not initialized???");
+
+	for (src = dst = 0; src < q->nr; src++) {
+		struct diff_filepair *p = q->queue[src];
+
+		if ((DIFF_FILE_VALID(p->one) &&
+		     oidset_contains(options->blobfind, &p->one->oid)) ||
+		    (DIFF_FILE_VALID(p->two) &&
+		     oidset_contains(options->blobfind, &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_blobfind(struct diff_options *options)
+{
+	diffcore_filter_blobs(&diff_queued_diff, options);
+}
diff --git a/diffcore.h b/diffcore.h
index a30da161da..431917672f 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_blobfind(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..8e1a89f832 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.blobfind)
 		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.blobfind)
+		revs->simplify_history = 0;
 	return 0;
 }
 
diff --git a/t/t4064-diff-blobfind.sh b/t/t4064-diff-blobfind.sh
new file mode 100755
index 0000000000..b2c2964d77
--- /dev/null
+++ b/t/t4064-diff-blobfind.sh
@@ -0,0 +1,35 @@
+#!/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 --abbrev=12 --oneline --blobfind=greeting^{blob} >actual.raw &&
+	cut -c 14- actual.raw >actual &&
+
+	test_cmp expect actual
+'
+
+test_done
-- 
2.15.1.424.g9478a66081-goog




[Index of Archives]     [Linux Kernel Development]     [Gcc Help]     [IETF Annouce]     [DCCP]     [Netdev]     [Networking]     [Security]     [V4L]     [Bugtraq]     [Yosemite]     [MIPS Linux]     [ARM Linux]     [Linux Security]     [Linux RAID]     [Linux SCSI]     [Fedora Users]

  Powered by Linux