[PATCH v2 11/14] object-name: simplify computing common prefixes
- From
Patrick Steinhardt <ps@pks.im>
- Date
- Mar 20, 2026, 07:07 UTC
- Message-ID
- <20260320-b4-pks-odb-source-abbrev-v2-11-fe65dcd8c735@pks.im>
- In-Reply-To
- <20260320-b4-pks-odb-source-abbrev-v2-0-fe65dcd8c735@pks.im>
The function `extend_abbrev_len()` computes the length of common hex characters between two object IDs. This is done by:
- Making the caller provide the `hex` string for the needle object ID.
- Comparing every hex position of the haystack object ID with
`get_hex_char_from_oid()`.Turning the binary representation into hex first is roundabout though: we can simply compare the binary representation and give some special attention to the final nibble.
Introduce a new function `oid_common_prefix_hexlen()` that does exactly this and refactor the code to use the new function. This allows us to drop the `struct min_abbrev_data::hex` field. Furthermore, this function will be used in by some other callsites in subsequent commits.
Signed-off-by: Patrick Steinhardt <ps@pks.im> --- hash.c | 18 ++++++++++++++++++ hash.h | 3 +++ object-name.c | 23 +++-------------------- 3 files changed, 24 insertions(+), 20 deletions(-)
diff --git a/hash.c b/hash.c index 553f2008ea..e925b9754e 100644 --- a/hash.c +++ b/hash.c @@ -317,3 +317,21 @@ const struct git_hash_algo *unsafe_hash_algo(const struct git_hash_algo *algop) /* Otherwise use the default one. */ return algop; } + +unsigned oid_common_prefix_hexlen(const struct object_id *a, + const struct object_id *b) +{ + unsigned rawsz = hash_algos[a->algo].rawsz; + + for (unsigned i = 0; i < rawsz; i++) { + if (a->hash[i] == b->hash[i]) + continue; + + if ((a->hash[i] ^ b->hash[i]) & 0xf0) + return i * 2; + else + return i * 2 + 1; + } + + return rawsz * 2; +} diff --git a/hash.h b/hash.h index d51efce1d3..c082a53c9a 100644 --- a/hash.h +++ b/hash.h @@ -396,6 +396,9 @@ static inline int oideq(const struct object_id *oid1, const struct object_id *oi return !memcmp(oid1->hash, oid2->hash, GIT_MAX_RAWSZ); } +unsigned oid_common_prefix_hexlen(const struct object_id *a, + const struct object_id *b); + static inline void oidcpy(struct object_id *dst, const struct object_id *src) { memcpy(dst->hash, src->hash, GIT_MAX_RAWSZ); diff --git a/object-name.c b/object-name.c index d82fb49f39..32e9c23e40 100644 --- a/object-name.c +++ b/object-name.c @@ -585,32 +585,16 @@ static unsigned msb(unsigned long val) struct min_abbrev_data { unsigned int init_len; unsigned int cur_len; - char *hex; struct repository *repo; const struct object_id *oid; }; -static inline char get_hex_char_from_oid(const struct object_id *oid, - unsigned int pos) -{ - static const char hex[] = "0123456789abcdef"; - - if ((pos & 1) == 0) - return hex[oid->hash[pos >> 1] >> 4]; - else - return hex[oid->hash[pos >> 1] & 0xf]; -} - static int extend_abbrev_len(const struct object_id *oid, struct min_abbrev_data *mad) { - unsigned int i = mad->init_len; - while (mad->hex[i] && mad->hex[i] == get_hex_char_from_oid(oid, i)) - i++; - - if (mad->hex[i] && i >= mad->cur_len) - mad->cur_len = i + 1; - + unsigned len = oid_common_prefix_hexlen(oid, mad->oid); + if (len != hash_algos[oid->algo].hexsz && len >= mad->cur_len) + mad->cur_len = len + 1; return 0; } @@ -785,7 +769,6 @@ int repo_find_unique_abbrev_r(struct repository *r, char *hex, mad.repo = r; mad.init_len = len; mad.cur_len = len; - mad.hex = hex; mad.oid = oid; find_abbrev_len_packed(&mad);
-- 2.53.0.1055.ga2ffed1127.dirty