[PATCH 1/2] xdiff: remove "line_hash" field from xrecord_t
- From
- Phillip Wood <phillip.wood123@gmail.com>
- Date
- Jan 26, 2026, 10:48 UTC
- Message-ID
- <24a662ac0a939d284cb2370509327a2a81535247.1769424529.git.phillip.wood@dunelm.org.uk>
- In-Reply-To
- <cover.1769424529.git.phillip.wood@dunelm.org.uk>
From: Phillip Wood <phillip.wood@dunelm.org.uk>
Prior to commit 6a26019c81 (xdiff: split xrecord_t.ha into line_hash and minimal_perfect_hash, 2025-11-18) the "ha" field of xrecord_t initially held the "line_hash" value and once the line had been interned that field was updated to hold the "minimal_perfect_hash". The "line_hash" is only used to intern the line so there is no point in storing it after all the input lines have been interned.
Removing the "line_hash" field from xrecord_t and storing it in xdlclass_t where it is actually used makes it clearer that it is a temporary value and it should not be used once we're calculated the "minimal_perfect_hash". This also reduces the size of xrecord_t by 25% on 64-bit platforms and 40% on 32-bit platforms. While the struct is small we create one instance per input line so any saving is welcome.
Signed-off-by: Phillip Wood <phillip.wood@dunelm.org.uk> --- xdiff/xprepare.c | 12 +++++++----- xdiff/xtypes.h | 1 - 2 files changed, 7 insertions(+), 6 deletions(-)
diff --git a/xdiff/xprepare.c b/xdiff/xprepare.c index 34c82e4f8e1..08e5d3f4dfa 100644 --- a/xdiff/xprepare.c +++ b/xdiff/xprepare.c @@ -34,6 +34,7 @@ #define INVESTIGATE 2 typedef struct s_xdlclass { + uint64_t line_hash; struct s_xdlclass *next; xrecord_t rec; long idx; @@ -92,13 +93,14 @@ static void xdl_free_classifier(xdlclassifier_t *cf) { } -static int xdl_classify_record(unsigned int pass, xdlclassifier_t *cf, xrecord_t *rec) { +static int xdl_classify_record(unsigned int pass, xdlclassifier_t *cf, xrecord_t *rec, + uint64_t line_hash) { size_t hi; xdlclass_t *rcrec; - hi = XDL_HASHLONG(rec->line_hash, cf->hbits); + hi = XDL_HASHLONG(line_hash, cf->hbits); for (rcrec = cf->rchash[hi]; rcrec; rcrec = rcrec->next) - if (rcrec->rec.line_hash == rec->line_hash && + if (rcrec->line_hash == line_hash && xdl_recmatch((const char *)rcrec->rec.ptr, (long)rcrec->rec.size, (const char *)rec->ptr, (long)rec->size, cf->flags)) break; @@ -112,6 +114,7 @@ static int xdl_classify_record(unsigned int pass, xdlclassifier_t *cf, xrecord_t if (XDL_ALLOC_GROW(cf->rcrecs, cf->count, cf->alloc)) return -1; cf->rcrecs[rcrec->idx] = rcrec; + rcrec->line_hash = line_hash; rcrec->rec = *rec; rcrec->len1 = rcrec->len2 = 0; rcrec->next = cf->rchash[hi]; @@ -158,8 +161,7 @@ static int xdl_prepare_ctx(unsigned int pass, mmfile_t *mf, long narec, xpparam_ crec = &xdf->recs[xdf->nrec++]; crec->ptr = prev; crec->size = cur - prev; - crec->line_hash = hav; - if (xdl_classify_record(pass, cf, crec) < 0) + if (xdl_classify_record(pass, cf, crec, hav) < 0) goto abort; } } diff --git a/xdiff/xtypes.h b/xdiff/xtypes.h index 979586f20a6..50aee779be3 100644 --- a/xdiff/xtypes.h +++ b/xdiff/xtypes.h @@ -41,7 +41,6 @@ typedef struct s_chastore { typedef struct s_xrecord { uint8_t const *ptr; size_t size; - uint64_t line_hash; size_t minimal_perfect_hash; } xrecord_t;
-- 2.52.0.362.g884e03848a9