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

> @@ -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;
>  }