[PATCH 08/10] commit-graph: simplify parse_commit_graph() #2

["SZEDER Gábor via GitGitGadget" <gitgitgadget@xxxxxxxxx>]

From: =?UTF-8?q?SZEDER=20G=C3=A1bor?= <szeder.dev@xxxxxxxxx>

The Chunk Lookup table stores the chunks' starting offset in the
commit-graph file, not their sizes.  Consequently, the size of a chunk
can only be calculated by subtracting its offset from the offset of
the subsequent chunk (or that of the terminating label).  This is
currenly implemented in a bit complicated way: as we iterate over the
entries of the Chunk Lookup table, we check the id of each chunk and
store its starting offset, then we check the id of the last seen chunk
and calculate its size using its previously saved offset.  At the
moment there is only one chunk for which we calculate its size, but
this patch series will add more, and the repeated chunk id checks are
not that pretty.

Instead let's read ahead the offset of the next chunk on each
iteration, so we can calculate the size of each chunk right away,
right where we store its starting offset.

Signed-off-by: SZEDER Gábor <szeder.dev@xxxxxxxxx>
Signed-off-by: Derrick Stolee <dstolee@xxxxxxxxxxxxx>
---
 commit-graph.c | 26 +++++++++-----------------
 1 file changed, 9 insertions(+), 17 deletions(-)

diff --git a/commit-graph.c b/commit-graph.c
index 9927762f18c..84206f0f512 100644
--- a/commit-graph.c
+++ b/commit-graph.c
@@ -230,8 +230,7 @@ struct commit_graph *parse_commit_graph(void *graph_map, int fd,
 	const unsigned char *data, *chunk_lookup;
 	uint32_t i;
 	struct commit_graph *graph;
-	uint64_t last_chunk_offset;
-	uint32_t last_chunk_id;
+	uint64_t next_chunk_offset;
 	uint32_t graph_signature;
 	unsigned char graph_version, hash_version;
 
@@ -281,18 +280,17 @@ struct commit_graph *parse_commit_graph(void *graph_map, int fd,
 		return NULL;
 	}
 
-	last_chunk_id = 0;
-	last_chunk_offset = 8;
 	chunk_lookup = data + 8;
-	for (i = 0; i <= graph->num_chunks; i++) {
+	next_chunk_offset = get_be64(chunk_lookup + 4);
+	for (i = 0; i < graph->num_chunks; i++) {
 		uint32_t chunk_id;
-		uint64_t chunk_offset;
+		uint64_t chunk_offset = next_chunk_offset;
 		int chunk_repeated = 0;
 
 		chunk_id = get_be32(chunk_lookup + 0);
-		chunk_offset = get_be64(chunk_lookup + 4);
 
 		chunk_lookup += GRAPH_CHUNKLOOKUP_WIDTH;
+		next_chunk_offset = get_be64(chunk_lookup + 4);
 
 		if (chunk_offset > graph_size - the_hash_algo->rawsz) {
 			error(_("commit-graph improper chunk offset %08x%08x"), (uint32_t)(chunk_offset >> 32),
@@ -312,8 +310,11 @@ struct commit_graph *parse_commit_graph(void *graph_map, int fd,
 		case GRAPH_CHUNKID_OIDLOOKUP:
 			if (graph->chunk_oid_lookup)
 				chunk_repeated = 1;
-			else
+			else {
 				graph->chunk_oid_lookup = data + chunk_offset;
+				graph->num_commits = (next_chunk_offset - chunk_offset)
+						     / graph->hash_len;
+			}
 			break;
 
 		case GRAPH_CHUNKID_DATA:
@@ -368,15 +369,6 @@ struct commit_graph *parse_commit_graph(void *graph_map, int fd,
 			free(graph);
 			return NULL;
 		}
-
-		if (last_chunk_id == GRAPH_CHUNKID_OIDLOOKUP)
-		{
-			graph->num_commits = (chunk_offset - last_chunk_offset)
-					     / graph->hash_len;
-		}
-
-		last_chunk_id = chunk_id;
-		last_chunk_offset = chunk_offset;
 	}
 
 	if (graph->chunk_bloom_indexes && graph->chunk_bloom_data) {
-- 
gitgitgadget