From: Derrick Stolee <dstolee@xxxxxxxxxxxxx> Instead of parsing the table of contents directly, use the chunk-format API methods read_table_of_contents() and pair_chunk(). While the current implementation loses the duplicate-chunk detection, that will be added in a future change. Signed-off-by: Derrick Stolee <dstolee@xxxxxxxxxxxxx> --- commit-graph.c | 209 ++++++++++++++++++++-------------------- t/t5318-commit-graph.sh | 2 +- 2 files changed, 108 insertions(+), 103 deletions(-) diff --git a/commit-graph.c b/commit-graph.c index b2c0f233eab..44c06d0fb67 100644 --- a/commit-graph.c +++ b/commit-graph.c @@ -299,15 +299,99 @@ static int verify_commit_graph_lite(struct commit_graph *g) return 0; } +static int graph_read_oid_fanout(const unsigned char *chunk_start, + size_t chunk_size, void *data) +{ + struct commit_graph *g = (struct commit_graph *)data; + g->chunk_oid_fanout = (uint32_t*)chunk_start; + return 0; +} + +static int graph_read_oid_lookup(const unsigned char *chunk_start, + size_t chunk_size, void *data) +{ + struct commit_graph *g = (struct commit_graph *)data; + g->chunk_oid_lookup = chunk_start; + g->num_commits = chunk_size / g->hash_len; + return 0; +} + +static int graph_read_data(const unsigned char *chunk_start, + size_t chunk_size, void *data) +{ + struct commit_graph *g = (struct commit_graph *)data; + g->chunk_commit_data = chunk_start; + return 0; +} + +static int graph_read_extra_edges(const unsigned char *chunk_start, + size_t chunk_size, void *data) +{ + struct commit_graph *g = (struct commit_graph *)data; + g->chunk_extra_edges = chunk_start; + return 0; +} + +static int graph_read_base_graphs(const unsigned char *chunk_start, + size_t chunk_size, void *data) +{ + struct commit_graph *g = (struct commit_graph *)data; + g->chunk_base_graphs = chunk_start; + return 0; +} + +static int graph_read_generation_data(const unsigned char *chunk_start, + size_t chunk_size, void *data) +{ + struct commit_graph *g = (struct commit_graph *)data; + g->chunk_generation_data = chunk_start; + return 0; +} + +static int graph_read_generation_overflow(const unsigned char *chunk_start, + size_t chunk_size, void *data) +{ + struct commit_graph *g = (struct commit_graph *)data; + g->chunk_generation_data_overflow = chunk_start; + return 0; +} + +static int graph_read_bloom_indices(const unsigned char *chunk_start, + size_t chunk_size, void *data) +{ + struct commit_graph *g = (struct commit_graph *)data; + g->chunk_bloom_indexes = chunk_start; + return 0; +} + +static int graph_read_bloom_data(const unsigned char *chunk_start, + size_t chunk_size, void *data) +{ + struct commit_graph *g = (struct commit_graph *)data; + uint32_t hash_version; + g->chunk_bloom_data = chunk_start; + hash_version = get_be32(chunk_start); + + if (hash_version != 1) + return 0; + + g->bloom_filter_settings = xmalloc(sizeof(struct bloom_filter_settings)); + g->bloom_filter_settings->hash_version = hash_version; + g->bloom_filter_settings->num_hashes = get_be32(chunk_start + 4); + g->bloom_filter_settings->bits_per_entry = get_be32(chunk_start + 8); + g->bloom_filter_settings->max_changed_paths = DEFAULT_BLOOM_MAX_CHANGES; + + return 0; +} + struct commit_graph *parse_commit_graph(struct repository *r, void *graph_map, size_t graph_size) { - const unsigned char *data, *chunk_lookup; - uint32_t i; + const unsigned char *data; struct commit_graph *graph; - uint64_t next_chunk_offset; uint32_t graph_signature; unsigned char graph_version, hash_version; + struct chunkfile *cf = NULL; if (!graph_map) return NULL; @@ -356,108 +440,27 @@ struct commit_graph *parse_commit_graph(struct repository *r, return NULL; } - chunk_lookup = data + 8; - next_chunk_offset = get_be64(chunk_lookup + 4); - for (i = 0; i < graph->num_chunks; i++) { - uint32_t chunk_id; - uint64_t chunk_offset = next_chunk_offset; - int chunk_repeated = 0; - - chunk_id = get_be32(chunk_lookup + 0); - - 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), - (uint32_t)chunk_offset); - goto free_and_return; - } - - switch (chunk_id) { - case GRAPH_CHUNKID_OIDFANOUT: - if (graph->chunk_oid_fanout) - chunk_repeated = 1; - else - graph->chunk_oid_fanout = (uint32_t*)(data + chunk_offset); - break; - - case GRAPH_CHUNKID_OIDLOOKUP: - if (graph->chunk_oid_lookup) - chunk_repeated = 1; - else { - graph->chunk_oid_lookup = data + chunk_offset; - graph->num_commits = (next_chunk_offset - chunk_offset) - / graph->hash_len; - } - break; - - case GRAPH_CHUNKID_DATA: - if (graph->chunk_commit_data) - chunk_repeated = 1; - else - graph->chunk_commit_data = data + chunk_offset; - break; - - case GRAPH_CHUNKID_GENERATION_DATA: - if (graph->chunk_generation_data) - chunk_repeated = 1; - else - graph->chunk_generation_data = data + chunk_offset; - break; + cf = init_chunkfile(NULL); - case GRAPH_CHUNKID_GENERATION_DATA_OVERFLOW: - if (graph->chunk_generation_data_overflow) - chunk_repeated = 1; - else - graph->chunk_generation_data_overflow = data + chunk_offset; - break; - - case GRAPH_CHUNKID_EXTRAEDGES: - if (graph->chunk_extra_edges) - chunk_repeated = 1; - else - graph->chunk_extra_edges = data + chunk_offset; - break; - - case GRAPH_CHUNKID_BASE: - if (graph->chunk_base_graphs) - chunk_repeated = 1; - else - graph->chunk_base_graphs = data + chunk_offset; - break; - - case GRAPH_CHUNKID_BLOOMINDEXES: - if (graph->chunk_bloom_indexes) - chunk_repeated = 1; - else if (r->settings.commit_graph_read_changed_paths) - graph->chunk_bloom_indexes = data + chunk_offset; - break; - - case GRAPH_CHUNKID_BLOOMDATA: - if (graph->chunk_bloom_data) - chunk_repeated = 1; - else if (r->settings.commit_graph_read_changed_paths) { - uint32_t hash_version; - graph->chunk_bloom_data = data + chunk_offset; - hash_version = get_be32(data + chunk_offset); - - if (hash_version != 1) - break; + if (read_table_of_contents(cf, graph->data, graph_size, + GRAPH_HEADER_SIZE, graph->num_chunks)) + goto free_and_return; - graph->bloom_filter_settings = xmalloc(sizeof(struct bloom_filter_settings)); - graph->bloom_filter_settings->hash_version = hash_version; - graph->bloom_filter_settings->num_hashes = get_be32(data + chunk_offset + 4); - graph->bloom_filter_settings->bits_per_entry = get_be32(data + chunk_offset + 8); - graph->bloom_filter_settings->max_changed_paths = DEFAULT_BLOOM_MAX_CHANGES; - } - break; - } + pair_chunk(cf, GRAPH_CHUNKID_OIDFANOUT, graph_read_oid_fanout, graph); + pair_chunk(cf, GRAPH_CHUNKID_OIDLOOKUP, graph_read_oid_lookup, graph); + pair_chunk(cf, GRAPH_CHUNKID_DATA, graph_read_data, graph); + pair_chunk(cf, GRAPH_CHUNKID_EXTRAEDGES, graph_read_extra_edges, graph); + pair_chunk(cf, GRAPH_CHUNKID_BASE, graph_read_base_graphs, graph); + pair_chunk(cf, GRAPH_CHUNKID_GENERATION_DATA, + graph_read_generation_data, graph); + pair_chunk(cf, GRAPH_CHUNKID_GENERATION_DATA_OVERFLOW, + graph_read_generation_overflow, graph); - if (chunk_repeated) { - error(_("commit-graph chunk id %08x appears multiple times"), chunk_id); - goto free_and_return; - } + if (r->settings.commit_graph_read_changed_paths) { + pair_chunk(cf, GRAPH_CHUNKID_BLOOMINDEXES, + graph_read_bloom_indices, graph); + pair_chunk(cf, GRAPH_CHUNKID_BLOOMDATA, + graph_read_bloom_data, graph); } if (graph->chunk_bloom_indexes && graph->chunk_bloom_data) { @@ -474,9 +477,11 @@ struct commit_graph *parse_commit_graph(struct repository *r, if (verify_commit_graph_lite(graph)) goto free_and_return; + free_chunkfile(cf); return graph; free_and_return: + free_chunkfile(cf); free(graph->bloom_filter_settings); free(graph); return NULL; diff --git a/t/t5318-commit-graph.sh b/t/t5318-commit-graph.sh index fa27df579a5..c7da741284e 100755 --- a/t/t5318-commit-graph.sh +++ b/t/t5318-commit-graph.sh @@ -564,7 +564,7 @@ test_expect_success 'detect bad hash version' ' test_expect_success 'detect low chunk count' ' corrupt_graph_and_verify $GRAPH_BYTE_CHUNK_COUNT "\01" \ - "missing the .* chunk" + "final chunk has non-zero id" ' test_expect_success 'detect missing OID fanout chunk' ' -- gitgitgadget