[PATCH v6 17/18] commit-graph: normalize commit-graph filenames

From: "Derrick Stolee via GitGitGadget" <gitgitgadget@gmail.com>
To: git@vger.kernel.org
Cc: peff@peff.net, avarab@gmail.com, git@jeffhostetler.com,
	jrnieder@google.com, steadmon@google.com,
	johannes.schindelin@gmx.de, philipoakley@iee.org,
	Junio C Hamano <gitster@pobox.com>,
	Derrick Stolee <dstolee@microsoft.com>
Subject: [PATCH v6 17/18] commit-graph: normalize commit-graph filenames
Date: Tue, 18 Jun 2019 11:14:36 -0700 (PDT)	[thread overview]
Message-ID: <fba62e7a42df630653092265999fb4a6e5aab81d.1560881661.git.gitgitgadget@gmail.com> (raw)
In-Reply-To: <pull.184.v6.git.gitgitgadget@gmail.com>

From: Derrick Stolee <dstolee@microsoft.com>

When writing commit-graph files, we append path data to an
object directory, which may be specified by the user via the
'--object-dir' option. If the user supplies a trailing slash,
or some other alternative path format, the resulting path may
be usable for writing to the correct location. However, when
expiring graph files from the <obj-dir>/info/commit-graphs
directory during a write, we need to compare paths with exact
string matches.

Normalize the commit-graph filenames to avoid ambiguity. This
creates extra allocations, but this is a constant multiple of
the number of commit-graph files, which should be a number in
the single digits.

Further normalize the object directory in the context. Due to
a comparison between g->obj_dir and ctx->obj_dir in
split_graph_merge_strategy(), a trailing slash would prevent
any merging of layers within the same object directory. The
check is there to ensure we do not merge across alternates.
Update the tests to include a case with this trailing slash
problem.

Signed-off-by: Derrick Stolee <dstolee@microsoft.com>
---
 commit-graph.c                | 30 +++++++++++++++++++++++-------
 t/t5324-split-commit-graph.sh |  7 ++++++-
 2 files changed, 29 insertions(+), 8 deletions(-)

diff --git a/commit-graph.c b/commit-graph.c
index 3599ae664d..c91e6f0fb8 100644
--- a/commit-graph.c
+++ b/commit-graph.c
@@ -43,15 +43,23 @@
 
 char *get_commit_graph_filename(const char *obj_dir)
 {
-	return xstrfmt("%s/info/commit-graph", obj_dir);
+	char *filename = xstrfmt("%s/info/commit-graph", obj_dir);
+	char *normalized = xmalloc(strlen(filename) + 1);
+	normalize_path_copy(normalized, filename);
+	free(filename);
+	return normalized;
 }
 
 static char *get_split_graph_filename(const char *obj_dir,
 				      const char *oid_hex)
 {
-	return xstrfmt("%s/info/commit-graphs/graph-%s.graph",
-		       obj_dir,
-		       oid_hex);
+	char *filename = xstrfmt("%s/info/commit-graphs/graph-%s.graph",
+				 obj_dir,
+				 oid_hex);
+	char *normalized = xmalloc(strlen(filename) + 1);
+	normalize_path_copy(normalized, filename);
+	free(filename);
+	return normalized;
 }
 
 static char *get_chain_filename(const char *obj_dir)
@@ -746,7 +754,7 @@ struct packed_oid_list {
 
 struct write_commit_graph_context {
 	struct repository *r;
-	const char *obj_dir;
+	char *obj_dir;
 	char *graph_name;
 	struct packed_oid_list oids;
 	struct packed_commit_list commits;
@@ -1729,7 +1737,6 @@ static void expire_commit_graphs(struct write_commit_graph_context *ctx)
 
 		if (!found)
 			unlink(path.buf);
-
 	}
 }
 
@@ -1741,6 +1748,7 @@ int write_commit_graph(const char *obj_dir,
 {
 	struct write_commit_graph_context *ctx;
 	uint32_t i, count_distinct = 0;
+	size_t len;
 	int res = 0;
 
 	if (!commit_graph_compatible(the_repository))
@@ -1748,7 +1756,14 @@ int write_commit_graph(const char *obj_dir,
 
 	ctx = xcalloc(1, sizeof(struct write_commit_graph_context));
 	ctx->r = the_repository;
-	ctx->obj_dir = obj_dir;
+
+	/* normalize object dir with no trailing slash */
+	ctx->obj_dir = xmallocz(strlen(obj_dir) + 1);
+	normalize_path_copy(ctx->obj_dir, obj_dir);
+	len = strlen(ctx->obj_dir);
+	if (len && ctx->obj_dir[len - 1] == '/')
+		ctx->obj_dir[len - 1] = 0;
+
 	ctx->append = flags & COMMIT_GRAPH_APPEND ? 1 : 0;
 	ctx->report_progress = flags & COMMIT_GRAPH_PROGRESS ? 1 : 0;
 	ctx->split = flags & COMMIT_GRAPH_SPLIT ? 1 : 0;
@@ -1856,6 +1871,7 @@ int write_commit_graph(const char *obj_dir,
 	free(ctx->graph_name);
 	free(ctx->commits.list);
 	free(ctx->oids.list);
+	free(ctx->obj_dir);
 
 	if (ctx->commit_graph_filenames_after) {
 		for (i = 0; i < ctx->num_commit_graphs_after; i++) {
diff --git a/t/t5324-split-commit-graph.sh b/t/t5324-split-commit-graph.sh
index 130f2baf44..fc0d00751c 100755
--- a/t/t5324-split-commit-graph.sh
+++ b/t/t5324-split-commit-graph.sh
@@ -163,7 +163,12 @@ test_expect_success 'create fork and chain across alternate' '
 		test_line_count = 1 graph-files &&
 		git -c core.commitGraph=true  rev-list HEAD >expect &&
 		git -c core.commitGraph=false rev-list HEAD >actual &&
-		test_cmp expect actual
+		test_cmp expect actual &&
+		test_commit 14 &&
+		git commit-graph write --reachable --split --object-dir=.git/objects/ &&
+		test_line_count = 3 $graphdir/commit-graph-chain &&
+		ls $graphdir/graph-*.graph >graph-files &&
+		test_line_count = 1 graph-files
 	)
 '
 
-- 
gitgitgadget

