Re: [PATCH 09/10] xdiff: remove dependence on xdlclassifier from xdl_cleanup_records()

[Phillip Wood <phillip.wood123@gmail.com>]

Hi Ezekiel

On 02/01/2026 18:52, Ezekiel Newren via GitGitGadget wrote:
> From: Ezekiel Newren <ezekielnewren@gmail.com>
> 
> Disentangle xdl_cleanup_records() from the classifier so that it can be
> moved from xprepare.c into xdiffi.c.
> 
> The classic diff is the only algorithm that needs to count the number
> of times each line occurs in each file. Make xdl_cleanup_records()
> count the number of lines instead of the classifier so it won't slow
> down patience or histogram.

Have you measured the speed up that this gives? It looks like it saves 
very little work for the patience or histogram algorithms and means we 
now make a second pass over the data in the myers case. If there is a 
reason to do this related to the rust conversion then that might be a 
more convincing argument. As Rene has said already this isn't a 
particularly interesting demonstration of struct IVec - it would be nice 
to see more of the API exercised.

Thanks

Phillip

> Signed-off-by: Ezekiel Newren <ezekielnewren@gmail.com>
> ---
>   xdiff/xprepare.c | 52 +++++++++++++++++++++++++++++++++---------------
>   xdiff/xtypes.h   |  1 +
>   2 files changed, 37 insertions(+), 16 deletions(-)
> 
> diff --git a/xdiff/xprepare.c b/xdiff/xprepare.c
> index d3cdb6ac02..b53a3b80c4 100644
> --- a/xdiff/xprepare.c
> +++ b/xdiff/xprepare.c
> @@ -21,6 +21,7 @@
>    */
>   
>   #include "xinclude.h"
> +#include "compat/ivec.h"
>   
>   
>   #define XDL_KPDIS_RUN 4
> @@ -35,7 +36,6 @@ typedef struct s_xdlclass {
>   	struct s_xdlclass *next;
>   	xrecord_t rec;
>   	long idx;
> -	long len1, len2;
>   } xdlclass_t;
>   
>   typedef struct s_xdlclassifier {
> @@ -92,7 +92,7 @@ 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(xdlclassifier_t *cf, xrecord_t *rec) {
>   	size_t hi;
>   	xdlclass_t *rcrec;
>   
> @@ -113,13 +113,10 @@ static int xdl_classify_record(unsigned int pass, xdlclassifier_t *cf, xrecord_t
>   				return -1;
>   		cf->rcrecs[rcrec->idx] = rcrec;
>   		rcrec->rec = *rec;
> -		rcrec->len1 = rcrec->len2 = 0;
>   		rcrec->next = cf->rchash[hi];
>   		cf->rchash[hi] = rcrec;
>   	}
>   
> -	(pass == 1) ? rcrec->len1++ : rcrec->len2++;
> -
>   	rec->minimal_perfect_hash = (size_t)rcrec->idx;
>   
>   	return 0;
> @@ -253,22 +250,44 @@ static bool xdl_clean_mmatch(uint8_t const *action, long i, long s, long e) {
>   	return rpdis1 * XDL_KPDIS_RUN < (rpdis1 + rdis1);
>   }
>   
> +struct xoccurrence
> +{
> +	size_t file1, file2;
> +};
> +
> +
> +DEFINE_IVEC_TYPE(struct xoccurrence, xoccurrence);
> +
>   
>   /*
>    * Try to reduce the problem complexity, discard records that have no
>    * matches on the other file. Also, lines that have multiple matches
>    * might be potentially discarded if they appear in a run of discardable.
>    */
> -static int xdl_cleanup_records(xdlclassifier_t *cf, xdfenv_t *xe) {
> -	long i, nm, mlim;
> +static int xdl_cleanup_records(xdfenv_t *xe, uint64_t flags) {
> +	long i;
> +	size_t nm, mlim;
>   	xrecord_t *recs;
> -	xdlclass_t *rcrec;
>   	uint8_t *action1 = NULL, *action2 = NULL;
> -	bool need_min = !!(cf->flags & XDF_NEED_MINIMAL);
> +	struct IVec_xoccurrence occ;
> +	bool need_min = !!(flags & XDF_NEED_MINIMAL);
>   	int ret = 0;
>   	ptrdiff_t dend1 = xe->xdf1.nrec - 1 - xe->delta_end;
>   	ptrdiff_t dend2 = xe->xdf2.nrec - 1 - xe->delta_end;
>   
> +	IVEC_INIT(occ);
> +	ivec_zero(&occ, xe->mph_size);
> +
> +	for (size_t j = 0; j < xe->xdf1.nrec; j++) {
> +		size_t mph1 = xe->xdf1.recs[j].minimal_perfect_hash;
> +		occ.ptr[mph1].file1 += 1;
> +	}
> +
> +	for (size_t j = 0; j < xe->xdf2.nrec; j++) {
> +		size_t mph2 = xe->xdf2.recs[j].minimal_perfect_hash;
> +		occ.ptr[mph2].file2 += 1;
> +	}
> +
>   	/*
>   	 * Create temporary arrays that will help us decide if
>   	 * changed[i] should remain false, or become true.
> @@ -288,16 +307,14 @@ 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->delta_start, recs = &xe->xdf1.recs[xe->delta_start]; i <= dend1; i++, recs++) {
> -		rcrec = cf->rcrecs[recs->minimal_perfect_hash];
> -		nm = rcrec ? rcrec->len2 : 0;
> +		nm = occ.ptr[recs->minimal_perfect_hash].file2;
>   		action1[i] = (nm == 0) ? DISCARD: (nm >= mlim && !need_min) ? INVESTIGATE: KEEP;
>   	}
>   
>   	if ((mlim = xdl_bogosqrt((long)xe->xdf2.nrec)) > XDL_MAX_EQLIMIT)
>   		mlim = XDL_MAX_EQLIMIT;
>   	for (i = xe->delta_start, recs = &xe->xdf2.recs[xe->delta_start]; i <= dend2; i++, recs++) {
> -		rcrec = cf->rcrecs[recs->minimal_perfect_hash];
> -		nm = rcrec ? rcrec->len1 : 0;
> +		nm = occ.ptr[recs->minimal_perfect_hash].file1;
>   		action2[i] = (nm == 0) ? DISCARD: (nm >= mlim && !need_min) ? INVESTIGATE: KEEP;
>   	}
>   
> @@ -332,6 +349,7 @@ static int xdl_cleanup_records(xdlclassifier_t *cf, xdfenv_t *xe) {
>   cleanup:
>   	xdl_free(action1);
>   	xdl_free(action2);
> +	ivec_free(&occ);
>   
>   	return ret;
>   }
> @@ -387,18 +405,20 @@ int xdl_prepare_env(mmfile_t *mf1, mmfile_t *mf2, xpparam_t const *xpp,
>   
>   	for (size_t i = 0; i < xe->xdf1.nrec; i++) {
>   		xrecord_t *rec = &xe->xdf1.recs[i];
> -		xdl_classify_record(1, &cf, rec);
> +		xdl_classify_record(&cf, rec);
>   	}
>   
>   	for (size_t i = 0; i < xe->xdf2.nrec; i++) {
>   		xrecord_t *rec = &xe->xdf2.recs[i];
> -		xdl_classify_record(2, &cf, rec);
> +		xdl_classify_record(&cf, rec);
>   	}
>   
> +	xe->mph_size = cf.count;
> +
>   	xdl_trim_ends(xe);
>   	if ((XDF_DIFF_ALG(xpp->flags) != XDF_PATIENCE_DIFF) &&
>   	    (XDF_DIFF_ALG(xpp->flags) != XDF_HISTOGRAM_DIFF) &&
> -	    xdl_cleanup_records(&cf, xe) < 0) {
> +	    xdl_cleanup_records(xe, xpp->flags) < 0) {
>   
>   		xdl_free_ctx(&xe->xdf2);
>   		xdl_free_ctx(&xe->xdf1);
> diff --git a/xdiff/xtypes.h b/xdiff/xtypes.h
> index a939396064..2528bd37e8 100644
> --- a/xdiff/xtypes.h
> +++ b/xdiff/xtypes.h
> @@ -56,6 +56,7 @@ typedef struct s_xdfile {
>   typedef struct s_xdfenv {
>   	xdfile_t xdf1, xdf2;
>   	size_t delta_start, delta_end;
> +	size_t mph_size;
>   } xdfenv_t;
>   
>