From a81411253323208e1e8d3591247c27fefa8a2045 Mon Sep 17 00:00:00 2001 From: Phillip Wood Date: Mon, 4 May 2026 15:06:18 +0100 Subject: [PATCH] xdiff: reduce size of action arrays When the myers algorithm is selected the input files are pre-processed to remove any common prefix and suffix. Then any lines that appear only in one side of the diff are marked as changed and frequently occurring lines are marked as changed if they are adjacent to a changed line. This step requires a couple of temporary arrays. As as the common prefix and suffix have already been removed, the arrays only need to be big enough to hold the lines between them, not the whole file. Reduce the size of the arrays and adjust the loops that use them accordingly while taking care to keep indexing the arrays in xdfile_t with absolute line numbers. Signed-off-by: Phillip Wood Signed-off-by: Junio C Hamano --- xdiff/xprepare.c | 31 +++++++++++++++++-------------- 1 file changed, 17 insertions(+), 14 deletions(-) diff --git a/xdiff/xprepare.c b/xdiff/xprepare.c index beef711067..3b6bae0d15 100644 --- a/xdiff/xprepare.c +++ b/xdiff/xprepare.c @@ -273,16 +273,19 @@ static int xdl_cleanup_records(xdlclassifier_t *cf, xdfile_t *xdf1, xdfile_t *xd uint8_t *action1 = NULL, *action2 = NULL; bool need_min = !!(cf->flags & XDF_NEED_MINIMAL); int ret = 0; + ptrdiff_t off = xdf1->dstart; + ptrdiff_t len1 = xdf1->dend - off + 1; + ptrdiff_t len2 = xdf2->dend - off + 1; /* * Create temporary arrays that will help us decide if * changed[i] should remain false, or become true. */ - if (!XDL_CALLOC_ARRAY(action1, xdf1->nrec + 1)) { + if (!XDL_CALLOC_ARRAY(action1, len1)) { ret = -1; goto cleanup; } - if (!XDL_CALLOC_ARRAY(action2, xdf2->nrec + 1)) { + if (!XDL_CALLOC_ARRAY(action2, len2)) { ret = -1; goto cleanup; } @@ -298,8 +301,8 @@ static int xdl_cleanup_records(xdlclassifier_t *cf, xdfile_t *xdf1, xdfile_t *xd if (mlim1 > XDL_MAX_EQLIMIT) mlim1 = XDL_MAX_EQLIMIT; } - for (i = xdf1->dstart; i <= xdf1->dend; i++) { - size_t mph1 = xdf1->recs[i].minimal_perfect_hash; + for (i = 0; i < len1; i++) { + size_t mph1 = xdf1->recs[i + off].minimal_perfect_hash; rcrec = cf->rcrecs[mph1]; nm = rcrec ? rcrec->len2 : 0; if (nm == 0) @@ -318,8 +321,8 @@ static int xdl_cleanup_records(xdlclassifier_t *cf, xdfile_t *xdf1, xdfile_t *xd if (mlim2 > XDL_MAX_EQLIMIT) mlim2 = XDL_MAX_EQLIMIT; } - for (i = xdf2->dstart; i <= xdf2->dend; i++) { - size_t mph2 = xdf2->recs[i].minimal_perfect_hash; + for (i = 0; i < len2; i++) { + size_t mph2 = xdf2->recs[i + off].minimal_perfect_hash; rcrec = cf->rcrecs[mph2]; nm = rcrec ? rcrec->len1 : 0; if (nm == 0) @@ -335,42 +338,42 @@ static int xdl_cleanup_records(xdlclassifier_t *cf, xdfile_t *xdf1, xdfile_t *xd * false, or become true. */ xdf1->nreff = 0; - for (i = xdf1->dstart; i <= xdf1->dend; i++) { + for (i = 0; i < len1; i++) { uint8_t action = action1[i]; if (action == INVESTIGATE) { - if (!xdl_clean_mmatch(action1, i, xdf1->dstart, xdf1->dend)) + if (!xdl_clean_mmatch(action1, i, 0, len1 - 1)) action = KEEP; else action = DISCARD; } if (action == KEEP) { - xdf1->reference_index[xdf1->nreff++] = i; + xdf1->reference_index[xdf1->nreff++] = i + off; /* changed[i] remains false */ } else if (action == DISCARD) { - xdf1->changed[i] = true; + xdf1->changed[i + off] = true; } else { BUG("Illegal state for action"); } } xdf2->nreff = 0; - for (i = xdf2->dstart; i <= xdf2->dend; i++) { + for (i = 0; i < len2; i++) { uint8_t action = action2[i]; if (action == INVESTIGATE) { - if (!xdl_clean_mmatch(action2, i, xdf2->dstart, xdf2->dend)) + if (!xdl_clean_mmatch(action2, i, 0, len2 - 1)) action = KEEP; else action = DISCARD; } if (action == KEEP) { - xdf2->reference_index[xdf2->nreff++] = i; + xdf2->reference_index[xdf2->nreff++] = i + off; /* changed[i] remains false */ } else if (action == DISCARD) { - xdf2->changed[i] = true; + xdf2->changed[i + off] = true; } else { BUG("Illegal state for action"); }