Re: [PATCH 07/10] xdiff: replace xdfile_t.dstart with xdfenv_t.delta_start
- From
- Phillip Wood <phillip.wood123@gmail.com>
- Date
- Jan 20, 2026, 16:32 UTC
- Message-ID
- <e9a031fd-072d-4810-b7e0-0d64ffedce10@gmail.com>
- In-Reply-To
- <d74722538b693fb26e8684f9dd3fbc319a2a575e.1767379944.git.gitgitgadget@gmail.com>
On 02/01/2026 18:52, Ezekiel Newren via GitGitGadget wrote:
Show 5 quoted lines
> From: Ezekiel Newren <ezekielnewren@gmail.com> > > Placing delta_start in xdfenv_t instead of xdfile_t provides a more > appropriate context since this variable only makes sense with a pair > of files. View with --color-words.
So as dstart and dend must be the same for both files we now store the values once in xdfenv_t. That explains why we start passing xdfenv_t around rather than xdfile_t in patch 5.
Thanks
Phillip
Show 129 quoted lines
> Signed-off-by: Ezekiel Newren <ezekielnewren@gmail.com>
> ---
> xdiff/xhistogram.c | 4 ++--
> xdiff/xpatience.c | 4 ++--
> xdiff/xprepare.c | 17 +++++++++--------
> xdiff/xtypes.h | 3 ++-
> 4 files changed, 15 insertions(+), 13 deletions(-)
>
> diff --git a/xdiff/xhistogram.c b/xdiff/xhistogram.c
> index 5ae1282c27..eb6a52d9ba 100644
> --- a/xdiff/xhistogram.c
> +++ b/xdiff/xhistogram.c
> @@ -365,6 +365,6 @@ out:
> int xdl_do_histogram_diff(xpparam_t const *xpp, xdfenv_t *env)
> {
> return histogram_diff(xpp, env,
> - env->xdf1.dstart + 1, env->xdf1.dend - env->xdf1.dstart + 1,
> - env->xdf2.dstart + 1, env->xdf2.dend - env->xdf2.dstart + 1);
> + env->delta_start + 1, env->xdf1.dend - env->delta_start + 1,
> + env->delta_start + 1, env->xdf2.dend - env->delta_start + 1);
> }
> diff --git a/xdiff/xpatience.c b/xdiff/xpatience.c
> index 2bce07cf48..bd0ffbb417 100644
> --- a/xdiff/xpatience.c
> +++ b/xdiff/xpatience.c
> @@ -374,6 +374,6 @@ static int patience_diff(xpparam_t const *xpp, xdfenv_t *env,
> int xdl_do_patience_diff(xpparam_t const *xpp, xdfenv_t *env)
> {
> return patience_diff(xpp, env,
> - env->xdf1.dstart + 1, env->xdf1.dend - env->xdf1.dstart + 1,
> - env->xdf2.dstart + 1, env->xdf2.dend - env->xdf2.dstart + 1);
> + env->delta_start + 1, env->xdf1.dend - env->delta_start + 1,
> + env->delta_start + 1, env->xdf2.dend - env->delta_start + 1);
> }
> diff --git a/xdiff/xprepare.c b/xdiff/xprepare.c
> index 06b6a6f804..e88468e74c 100644
> --- a/xdiff/xprepare.c
> +++ b/xdiff/xprepare.c
> @@ -173,7 +173,6 @@ static int xdl_prepare_ctx(mmfile_t *mf, xdfile_t *xdf, uint64_t flags) {
>
> xdf->changed += 1;
> xdf->nreff = 0;
> - xdf->dstart = 0;
> xdf->dend = xdf->nrec - 1;
>
> return 0;
> @@ -287,7 +286,7 @@ static int xdl_cleanup_records(xdlclassifier_t *cf, xdfenv_t *xe) {
> */
> if ((mlim = xdl_bogosqrt((long)xe->xdf1.nrec)) > XDL_MAX_EQLIMIT)
> mlim = XDL_MAX_EQLIMIT;
> - for (i = xe->xdf1.dstart, recs = &xe->xdf1.recs[xe->xdf1.dstart]; i <= xe->xdf1.dend; i++, recs++) {
> + for (i = xe->delta_start, recs = &xe->xdf1.recs[xe->delta_start]; i <= xe->xdf1.dend; i++, recs++) {
> rcrec = cf->rcrecs[recs->minimal_perfect_hash];
> nm = rcrec ? rcrec->len2 : 0;
> action1[i] = (nm == 0) ? DISCARD: (nm >= mlim && !need_min) ? INVESTIGATE: KEEP;
> @@ -295,7 +294,7 @@ static int xdl_cleanup_records(xdlclassifier_t *cf, xdfenv_t *xe) {
>
> if ((mlim = xdl_bogosqrt((long)xe->xdf2.nrec)) > XDL_MAX_EQLIMIT)
> mlim = XDL_MAX_EQLIMIT;
> - for (i = xe->xdf2.dstart, recs = &xe->xdf2.recs[xe->xdf2.dstart]; i <= xe->xdf2.dend; i++, recs++) {
> + for (i = xe->delta_start, recs = &xe->xdf2.recs[xe->delta_start]; i <= xe->xdf2.dend; i++, recs++) {
> rcrec = cf->rcrecs[recs->minimal_perfect_hash];
> nm = rcrec ? rcrec->len1 : 0;
> action2[i] = (nm == 0) ? DISCARD: (nm >= mlim && !need_min) ? INVESTIGATE: KEEP;
> @@ -306,10 +305,10 @@ static int xdl_cleanup_records(xdlclassifier_t *cf, xdfenv_t *xe) {
> * false, or become true.
> */
> xe->xdf1.nreff = 0;
> - for (i = xe->xdf1.dstart, recs = &xe->xdf1.recs[xe->xdf1.dstart];
> + for (i = xe->delta_start, recs = &xe->xdf1.recs[xe->delta_start];
> i <= xe->xdf1.dend; i++, recs++) {
> if (action1[i] == KEEP ||
> - (action1[i] == INVESTIGATE && !xdl_clean_mmatch(action1, i, xe->xdf1.dstart, xe->xdf1.dend))) {
> + (action1[i] == INVESTIGATE && !xdl_clean_mmatch(action1, i, xe->delta_start, xe->xdf1.dend))) {
> xe->xdf1.reference_index[xe->xdf1.nreff++] = i;
> /* changed[i] remains false, i.e. keep */
> } else
> @@ -318,10 +317,10 @@ static int xdl_cleanup_records(xdlclassifier_t *cf, xdfenv_t *xe) {
> }
>
> xe->xdf2.nreff = 0;
> - for (i = xe->xdf2.dstart, recs = &xe->xdf2.recs[xe->xdf2.dstart];
> + for (i = xe->delta_start, recs = &xe->xdf2.recs[xe->delta_start];
> i <= xe->xdf2.dend; i++, recs++) {
> if (action2[i] == KEEP ||
> - (action2[i] == INVESTIGATE && !xdl_clean_mmatch(action2, i, xe->xdf2.dstart, xe->xdf2.dend))) {
> + (action2[i] == INVESTIGATE && !xdl_clean_mmatch(action2, i, xe->delta_start, xe->xdf2.dend))) {
> xe->xdf2.reference_index[xe->xdf2.nreff++] = i;
> /* changed[i] remains false, i.e. keep */
> } else
> @@ -348,7 +347,7 @@ static void xdl_trim_ends(xdfenv_t *xe)
> size_t mph1 = xe->xdf1.recs[i].minimal_perfect_hash;
> size_t mph2 = xe->xdf2.recs[i].minimal_perfect_hash;
> if (mph1 != mph2) {
> - xe->xdf1.dstart = xe->xdf2.dstart = (ssize_t)i;
> + xe->delta_start = (ssize_t)i;
> lim -= i;
> break;
> }
> @@ -370,6 +369,8 @@ int xdl_prepare_env(mmfile_t *mf1, mmfile_t *mf2, xpparam_t const *xpp,
> xdfenv_t *xe) {
> xdlclassifier_t cf;
>
> + xe->delta_start = 0;
> +
> if (xdl_prepare_ctx(mf1, &xe->xdf1, xpp->flags) < 0) {
>
> return -1;
> diff --git a/xdiff/xtypes.h b/xdiff/xtypes.h
> index 979586f20a..bda1f85eb0 100644
> --- a/xdiff/xtypes.h
> +++ b/xdiff/xtypes.h
> @@ -48,7 +48,7 @@ typedef struct s_xrecord {
> typedef struct s_xdfile {
> xrecord_t *recs;
> size_t nrec;
> - ptrdiff_t dstart, dend;
> + ptrdiff_t dend;
> bool *changed;
> size_t *reference_index;
> size_t nreff;
> @@ -56,6 +56,7 @@ typedef struct s_xdfile {
>
> typedef struct s_xdfenv {
> xdfile_t xdf1, xdf2;
> + size_t delta_start;
> } xdfenv_t;
>
>