commit: record buffer length in cache

Most callsites which use the commit buffer try to use the
cached version attached to the commit, rather than
re-reading from disk. Unfortunately, that interface provides
only a pointer to the NUL-terminated buffer, with no
indication of the original length.

For the most part, this doesn't matter. People do not put
NULs in their commit messages, and the log code is happy to
treat it all as a NUL-terminated string. However, some code
paths do care. For example, when checking signatures, we
want to be very careful that we verify all the bytes to
avoid malicious trickery.

This patch just adds an optional "size" out-pointer to
get_commit_buffer and friends. The existing callers all pass
NULL (there did not seem to be any obvious sites where we
could avoid an immediate strlen() call, though perhaps with
some further refactoring we could).

Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

6 files changed, 18 insertions, 6 deletions

diff --git a/builtin/blame.c b/builtin/blame.c
index 857d98a324..b84e375b5c 100644
--- a/builtin/blame.c
+++ b/builtin/blame.c
@@ -1999,6 +1999,18 @@ static void append_merge_parents(struct commit_list **tail)
 }
 
 /*
+ * This isn't as simple as passing sb->buf and sb->len, because we
+ * want to transfer ownership of the buffer to the commit (so we
+ * must use detach).
+ */
+static void set_commit_buffer_from_strbuf(struct commit *c, struct strbuf *sb)
+{
+	size_t len;
+	void *buf = strbuf_detach(sb, &len);
+	set_commit_buffer(c, buf, len);
+}
+
+/*
  * Prepare a dummy commit that represents the work tree (or staged) item.
  * Note that annotating work tree item never works in the reverse.
  */
@@ -2046,7 +2058,7 @@ static struct commit *fake_working_tree_commit(struct diff_options *opt,
 		    ident, ident, path,
 		    (!contents_from ? path :
 		     (!strcmp(contents_from, "-") ? "standard input" : contents_from)));
-	set_commit_buffer(commit, strbuf_detach(&msg, NULL));
+	set_commit_buffer_from_strbuf(commit, &msg);
 
 	if (!contents_from || strcmp("-", contents_from)) {
 		struct stat st;
diff --git a/builtin/fast-export.c b/builtin/fast-export.c
index 7ee5e08442..05d161f19f 100644
--- a/builtin/fast-export.c
+++ b/builtin/fast-export.c
@@ -289,7 +289,7 @@ static void handle_commit(struct commit *commit, struct rev_info *rev)
 	rev->diffopt.output_format = DIFF_FORMAT_CALLBACK;
 
 	parse_commit_or_die(commit);
-	commit_buffer = get_commit_buffer(commit);
+	commit_buffer = get_commit_buffer(commit, NULL);
 	author = strstr(commit_buffer, "\nauthor ");
 	if (!author)
 		die ("Could not find author in commit %s",
diff --git a/builtin/fmt-merge-msg.c b/builtin/fmt-merge-msg.c
index 01f6d59eef..ef8b254ef2 100644
--- a/builtin/fmt-merge-msg.c
+++ b/builtin/fmt-merge-msg.c
@@ -236,7 +236,7 @@ static void record_person(int which, struct string_list *people,
 	const char *field;
 
 	field = (which == 'a') ? "\nauthor " : "\ncommitter ";
-	buffer = get_commit_buffer(commit);
+	buffer = get_commit_buffer(commit, NULL);
 	name = strstr(buffer, field);
 	if (!name)
 		return;
diff --git a/builtin/index-pack.c b/builtin/index-pack.c
index 42551ce4ff..459b9f07bb 100644
--- a/builtin/index-pack.c
+++ b/builtin/index-pack.c
@@ -774,7 +774,7 @@ static void sha1_object(const void *data, struct object_entry *obj_entry,
 			}
 			if (obj->type == OBJ_COMMIT) {
 				struct commit *commit = (struct commit *) obj;
-				if (detach_commit_buffer(commit) != data)
+				if (detach_commit_buffer(commit, NULL) != data)
 					die("BUG: parse_object_buffer transmogrified our buffer");
 			}
 			obj->flags |= FLAG_CHECKED;
diff --git a/builtin/log.c b/builtin/log.c
index 2c742606bc..c599eacf72 100644
--- a/builtin/log.c
+++ b/builtin/log.c
@@ -919,7 +919,7 @@ static void make_cover_letter(struct rev_info *rev, int use_stdout,
 				&need_8bit_cte);
 
 	for (i = 0; !need_8bit_cte && i < nr; i++) {
-		const char *buf = get_commit_buffer(list[i]);
+		const char *buf = get_commit_buffer(list[i], NULL);
 		if (has_non_ascii(buf))
 			need_8bit_cte = 1;
 		unuse_commit_buffer(list[i], buf);
diff --git a/builtin/rev-list.c b/builtin/rev-list.c
index 3fcbf21c03..ff84a825ff 100644
--- a/builtin/rev-list.c
+++ b/builtin/rev-list.c
@@ -106,7 +106,7 @@ static void show_commit(struct commit *commit, void *data)
 	else
 		putchar('\n');
 
-	if (revs->verbose_header && get_cached_commit_buffer(commit)) {
+	if (revs->verbose_header && get_cached_commit_buffer(commit, NULL)) {
 		struct strbuf buf = STRBUF_INIT;
 		struct pretty_print_context ctx = {0};
 		ctx.abbrev = revs->abbrev;