diffcore: add a pickaxe option to find a specific 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])

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>

1 files changed, 27 insertions, 18 deletions

diff --git a/diffcore-pickaxe.c b/diffcore-pickaxe.c
index 4b5d88ea46..72bb5a9514 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);
@@ -226,20 +233,22 @@ void diffcore_pickaxe(struct diff_options *o)
 			cflags |= REG_ICASE;
 		regcomp_or_die(&regex, needle, cflags);
 		regexp = &regex;
-	} else 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);
+	} 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... */
@@ -248,7 +257,7 @@ void diffcore_pickaxe(struct diff_options *o)
 
 	if (regexp)
 		regfree(regexp);
-	else
+	if (kws)
 		kwsfree(kws);
 	return;
 }