From: Ezekiel Newren via GitGitGadget Date: Fri, 27 Mar 2026 19:23:47 GMT Subject: [PATCH v3 0/6] Xdiff cleanup part 3 Message-ID: In-Reply-To: Changes in v3: * run make DEVELOPER=1 on each commit and fix all compiler issues v2 is a radical departure from v1 Changes in v2: * make the flow of xdl_cleanup_records() easier to follow There is no performance or behavioral change introduced in this patch series. === original cover letter bellow === Patch series summary: * patch 1: Introduce the ivec type * patch 2: Create the function xdl_do_classic_diff() * patches 3-4: generic cleanup * patches 5-8: convert from dstart/dend (in xdfile_t) to delta_start/delta_end (in xdfenv_t) * patches 9-10: move xdl_cleanup_records(), and related, from xprepare.c to xdiffi.c Things that will be addressed in future patch series: * Make xdl_cleanup_records() easier to read * convert recs/nrec into an ivec * convert changed to an ivec * remove reference_index/nreff from xdfile_t and turn it into an ivec * splitting minimal_perfect_hash out as its own ivec * improve the performance of the classifier and parsing/hashing lines === before this patch series typedef struct s_xdfile { xrecord_t *recs; size_t nrec; ptrdiff_t dstart, dend; bool *changed; size_t *reference_index; size_t nreff; } xdfile_t; typedef struct s_xdfenv { xdfile_t xdf1, xdf2; } xdfenv_t; === after this patch series typedef struct s_xdfile { xrecord_t *recs; size_t nrec; bool *changed; size_t *reference_index; size_t nreff; } xdfile_t; typedef struct s_xdfenv { xdfile_t xdf1, xdf2; size_t delta_start, delta_end; size_t mph_size; } xdfenv_t; Ezekiel Newren (6): xdiff/xdl_cleanup_records: delete local recs pointer xdiff: use unambiguous types in xdl_bogo_sqrt() xdiff/xdl_cleanup_records: use unambiguous types xdiff/xdl_cleanup_records: make limits more clear xdiff/xdl_cleanup_records: make setting action easier to follow xdiff/xdl_cleanup_records: simplify INVESTIGATE handling for clarity xdiff/xdiffi.c | 2 +- xdiff/xprepare.c | 84 ++++++++++++++++++++++++++++++++---------------- xdiff/xutils.c | 4 +-- xdiff/xutils.h | 2 +- 4 files changed, 60 insertions(+), 32 deletions(-) base-commit: ca1db8a0f7dc0dbea892e99f5b37c5fe5861be71 Published-As: https://github.com/gitgitgadget/git/releases/tag/pr-git-2156%2Fezekielnewren%2Fxdiff-cleanup-3-v3 Fetch-It-Via: git fetch https://github.com/gitgitgadget/git pr-git-2156/ezekielnewren/xdiff-cleanup-3-v3 Pull-Request: https://github.com/git/git/pull/2156 Range-diff vs v2: 1: 8f9165d477 = 1: da32a9747c xdiff/xdl_cleanup_records: delete local recs pointer -: ---------- > 2: 86b0ad100c xdiff: use unambiguous types in xdl_bogo_sqrt() 5: a52787f019 ! 3: 39a35365ae xdiff/xdl_cleanup_records: use unambiguous types @@ Commit message xdiff/xdl_cleanup_records: use unambiguous types Change the parameters of xdl_clean_mmatch() and the local variables - i, nm in xdl_cleanup_records() to use unambiguous types. Best viewed - with --color-words. + i, nm, mlim in xdl_cleanup_records() to use unambiguous types. Best + viewed with --color-words. Signed-off-by: Ezekiel Newren @@ xdiff/xprepare.c: static bool xdl_clean_mmatch(uint8_t const *action, long i, lo * might be potentially discarded if they appear in a run of discardable. */ static int xdl_cleanup_records(xdlclassifier_t *cf, xdfile_t *xdf1, xdfile_t *xdf2) { -- long i, nm; -- size_t mlim1, mlim2; -+ ptrdiff_t i; -+ size_t nm, mlim1, mlim2; +- long i, nm, mlim; ++ ptrdiff_t i, nm, mlim; xdlclass_t *rcrec; uint8_t *action1 = NULL, *action2 = NULL; bool need_min = !!(cf->flags & XDF_NEED_MINIMAL); -@@ xdiff/xprepare.c: static int xdl_cleanup_records(xdlclassifier_t *cf, xdfile_t *xdf1, xdfile_t *xd - for (i = xdf1->dstart; i <= xdf1->dend; i++) { - size_t mph1 = xdf1->recs[i].minimal_perfect_hash; - rcrec = cf->rcrecs[mph1]; -- nm = rcrec ? rcrec->len2 : 0; -+ nm = rcrec ? (size_t)rcrec->len2 : 0; - if (nm == 0) - action1[i] = DISCARD; - else if (nm < mlim1) -@@ xdiff/xprepare.c: static int xdl_cleanup_records(xdlclassifier_t *cf, xdfile_t *xdf1, xdfile_t *xd - for (i = xdf2->dstart; i <= xdf2->dend; i++) { - size_t mph2 = xdf2->recs[i].minimal_perfect_hash; - rcrec = cf->rcrecs[mph2]; -- nm = rcrec ? rcrec->len1 : 0; -+ nm = rcrec ? (size_t)rcrec->len1 : 0; - if (nm == 0) - action2[i] = DISCARD; - else if (nm < mlim2) 2: 62adaa8e5a ! 4: 86dd98db9b xdiff/xdl_cleanup_records: make limits more clear @@ Commit message Signed-off-by: Ezekiel Newren ## xdiff/xprepare.c ## -@@ xdiff/xprepare.c: static bool xdl_clean_mmatch(uint8_t const *action, long i, long s, long e) { +@@ xdiff/xprepare.c: static bool xdl_clean_mmatch(uint8_t const *action, ptrdiff_t i, ptrdiff_t s, pt * might be potentially discarded if they appear in a run of discardable. */ static int xdl_cleanup_records(xdlclassifier_t *cf, xdfile_t *xdf1, xdfile_t *xdf2) { -- long i, nm, mlim; -+ long i, nm; -+ size_t mlim1, mlim2; +- ptrdiff_t i, nm, mlim; ++ ptrdiff_t i, nm, mlim1, mlim2; xdlclass_t *rcrec; uint8_t *action1 = NULL, *action2 = NULL; bool need_min = !!(cf->flags & XDF_NEED_MINIMAL); @@ xdiff/xprepare.c: static int xdl_cleanup_records(xdlclassifier_t *cf, xdfile_t * /* * Initialize temporary arrays with DISCARD, KEEP, or INVESTIGATE. */ -- if ((mlim = xdl_bogosqrt((long)xdf1->nrec)) > XDL_MAX_EQLIMIT) +- if ((mlim = (long)xdl_bogosqrt((uint64_t)xdf1->nrec)) > XDL_MAX_EQLIMIT) - mlim = XDL_MAX_EQLIMIT; for (i = xdf1->dstart; i <= xdf1->dend; i++) { size_t mph1 = xdf1->recs[i].minimal_perfect_hash; @@ xdiff/xprepare.c: static int xdl_cleanup_records(xdlclassifier_t *cf, xdfile_t * + action1[i] = (nm == 0) ? DISCARD: nm >= mlim1 ? INVESTIGATE: KEEP; } -- if ((mlim = xdl_bogosqrt((long)xdf2->nrec)) > XDL_MAX_EQLIMIT) +- if ((mlim = (long)xdl_bogosqrt((uint64_t)xdf2->nrec)) > XDL_MAX_EQLIMIT) - mlim = XDL_MAX_EQLIMIT; for (i = xdf2->dstart; i <= xdf2->dend; i++) { size_t mph2 = xdf2->recs[i].minimal_perfect_hash; 3: 8be7e4781a = 5: ecc25be32f xdiff/xdl_cleanup_records: make setting action easier to follow 4: 6abd052c34 = 6: 8f4def8814 xdiff/xdl_cleanup_records: simplify INVESTIGATE handling for clarity -- gitgitgadget