Re: [PATCH v5 4/6] xdiff/xdl_cleanup_records: make limits more clear
- From
- Phillip Wood <phillip.wood123@gmail.com>
- Date
- Apr 14, 2026, 10:09 UTC
- Message-ID
- <d88af7e1-e8dd-4423-9c6c-977e1f1dc074@gmail.com>
- In-Reply-To
- <fec2b0f38ae30deceda104ec140fa4d404324103.1775679988.git.gitgitgadget@gmail.com>
On 08/04/2026 21:26, Ezekiel Newren via GitGitGadget wrote:
Show 7 quoted lines
> From: Ezekiel Newren <ezekielnewren@gmail.com> > > Make the handling of per-file limits and the minimal-case clearer. > * Use explicit per-file limit variables (mlim1, mlim2) and initialize > them. > * The additional condition `!need_min` is redudant now, remove it. > Best viewed with --color-words.
This still suffers from double evaluation in XDL_MIN(), perhaps we could do something like the diff below instead?
Thanks
Phillip
---- 8< ----
diff --git a/xdiff/xprepare.c b/xdiff/xprepare.c index 386668a92d7..bde3cc7f3e5 100644 --- a/xdiff/xprepare.c +++ b/xdiff/xprepare.c @@ -290,22 +290,30 @@ static int xdl_cleanup_records(xdlclassifier_t *cf, xdfile_t *xdf1, xdfile_t *xd /* * Initialize temporary arrays with DISCARD, KEEP, or INVESTIGATE. */ - if ((mlim = (long)xdl_bogosqrt((uint64_t)xdf1->nrec)) > XDL_MAX_EQLIMIT) - mlim = XDL_MAX_EQLIMIT; + if (need_min) { + mlim = PTRDIFF_MAX; + } else { + mlim = xdl_bogosqrt((uint64_t)xdf1->nrec); + if (mlim > XDL_MAX_EQLIMIT) + mlim = XDL_MAX_EQLIMIT; + } 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; - action1[i] = (nm == 0) ? DISCARD: (nm >= mlim && !need_min) ? INVESTIGATE: KEEP; + action1[i] = (nm == 0) ? DISCARD: nm >= mlim ? INVESTIGATE: KEEP; } - if ((mlim = (long)xdl_bogosqrt((uint64_t)xdf2->nrec)) > XDL_MAX_EQLIMIT) - mlim = XDL_MAX_EQLIMIT; + if (!need_min) { + mlim = xdl_bogosqrt((uint64_t)xdf2->nrec); + if (mlim > XDL_MAX_EQLIMIT) + mlim = XDL_MAX_EQLIMIT; + } 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; - action2[i] = (nm == 0) ? DISCARD: (nm >= mlim && !need_min) ? INVESTIGATE: KEEP; + action2[i] = (nm == 0) ? DISCARD: nm >= mlim ? INVESTIGATE: KEEP; } /* ---- >8 ---- > Signed-off-by: Ezekiel Newren <ezekielnewren@gmail.com> > --- > xdiff/xprepare.c | 19 ++++++++++++------- > 1 file changed, 12 insertions(+), 7 deletions(-) > > diff --git a/xdiff/xprepare.c b/xdiff/xprepare.c > index 386668a92d..bd8baf214d 100644 > --- a/xdiff/xprepare.c > +++ b/xdiff/xprepare.c > @@ -268,7 +268,7 @@ 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) { > - 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); > @@ -287,25 +287,30 @@ static int xdl_cleanup_records(xdlclassifier_t *cf, xdfile_t *xdf1, xdfile_t *xd > goto cleanup; > } > > + if (need_min) { > + /* i.e. infinity */ > + mlim1 = PTRDIFF_MAX; > + mlim2 = PTRDIFF_MAX; > + } else { > + mlim1 = XDL_MIN(xdl_bogosqrt(xdf1->nrec), XDL_MAX_EQLIMIT); > + mlim2 = XDL_MIN(xdl_bogosqrt(xdf2->nrec), XDL_MAX_EQLIMIT); > + } > + > /* > * Initialize temporary arrays with DISCARD, KEEP, or INVESTIGATE. > */ > - 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; > rcrec = cf->rcrecs[mph1]; > nm = rcrec ? rcrec->len2 : 0; > - action1[i] = (nm == 0) ? DISCARD: (nm >= mlim && !need_min) ? INVESTIGATE: KEEP; > + action1[i] = (nm == 0) ? DISCARD: nm >= mlim1 ? INVESTIGATE: KEEP; > } > > - 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; > rcrec = cf->rcrecs[mph2]; > nm = rcrec ? rcrec->len1 : 0; > - action2[i] = (nm == 0) ? DISCARD: (nm >= mlim && !need_min) ? INVESTIGATE: KEEP; > + action2[i] = (nm == 0) ? DISCARD: nm >= mlim2 ? INVESTIGATE: KEEP; > } > > /*