@matheusbsbs / matheus-bagliano / commits / 88e297275b

reftable: explicitly handle hash format IDs

The hash format IDs are used for two different things across the reftable codebase: - They are used as a 32 bit unsigned integer when reading and writing the header in order to identify the hash function. - They are used internally to identify which hash function is in use. When one only considers the second usecase one might think that one can easily change the representation of those hash IDs. But because those IDs end up in the reftable header and footer on disk it is important that those never change. Create separate constants `REFTABLE_FORMAT_ID_*` and use them in contexts where we read or write reftable headers. This serves multiple purposes: - It allows us to more easily discern cases where we actually use those constants for the on-disk format. - It detangles us from the same constants that are defined in libgit.a, which is another required step to convert the reftable library to become standalone. - It makes the next step easier where we stop using `GIT_*_FORMAT_ID` constants in favor of a custom enum. Signed-off-by: Patrick Steinhardt <ps@pks.im> Signed-off-by: Junio C Hamano <gitster@pobox.com>

Patrick Steinhardt committed Nov 18, 2024 at 16:33 UTC 88e297275b94f2fbbc60b770f37654796799b907
3 files changed +29 -5
reftable/basics.h
+8
@@ -150,4 +150,12 @@ int common_prefix_size(struct reftable_buf *a, struct reftable_buf *b);
150
151 int hash_size(uint32_t id);
152
153 +/*
154 + * Format IDs that identify the hash function used by a reftable. Note that
155 + * these constants end up on disk and thus mustn't change. The format IDs are
156 + * "sha1" and "s256" in big endian, respectively.
157 + */
158 +#define REFTABLE_FORMAT_ID_SHA1 ((uint32_t) 0x73686131)
159 +#define REFTABLE_FORMAT_ID_SHA256 ((uint32_t) 0x73323536)
160 +
161 #endif
reftable/reader.c
+6 -4
@@ -109,16 +109,18 @@ static int parse_footer(struct reftable_reader *r, uint8_t *footer,
109 if (r->version == 1) {
110 r->hash_id = GIT_SHA1_FORMAT_ID;
111 } else {
112 - r->hash_id = get_be32(f);
113 - switch (r->hash_id) {
114 - case GIT_SHA1_FORMAT_ID:
112 + switch (get_be32(f)) {
113 + case REFTABLE_FORMAT_ID_SHA1:
114 + r->hash_id = GIT_SHA1_FORMAT_ID;
115 break;
116 - case GIT_SHA256_FORMAT_ID:
116 + case REFTABLE_FORMAT_ID_SHA256:
117 + r->hash_id = GIT_SHA256_FORMAT_ID;
118 break;
119 default:
120 err = REFTABLE_FORMAT_ERROR;
121 goto done;
122 }
123 +
124 f += 4;
125 }
126
reftable/writer.c
+15 -1
@@ -103,8 +103,22 @@ static int writer_write_header(struct reftable_writer *w, uint8_t *dest)
103 put_be64(dest + 8, w->min_update_index);
104 put_be64(dest + 16, w->max_update_index);
105 if (writer_version(w) == 2) {
106 - put_be32(dest + 24, w->opts.hash_id);
106 + uint32_t hash_id;
107 +
108 + switch (w->opts.hash_id) {
109 + case GIT_SHA1_FORMAT_ID:
110 + hash_id = REFTABLE_FORMAT_ID_SHA1;
111 + break;
112 + case GIT_SHA256_FORMAT_ID:
113 + hash_id = REFTABLE_FORMAT_ID_SHA256;
114 + break;
115 + default:
116 + return -1;
117 + }
118 +
119 + put_be32(dest + 24, hash_id);
120 }
121 +
122 return header_size(writer_version(w));
123 }
124