long enl1, enl2, sample;
xdlclassifier_t cf;
+ memset(&cf, 0, sizeof(cf));
+
/*
* For histogram diff, we can afford a smaller sample size and
* thus a poorer estimate of the number of lines, as the hash
* might be potentially discarded if they happear in a run of discardable.
*/
static int xdl_cleanup_records(xdlclassifier_t *cf, xdfile_t *xdf1, xdfile_t *xdf2) {
- long i, nm, nreff;
+ long i, nm, nreff, mlim;
xrecord_t **recs;
xdlclass_t *rcrec;
char *dis, *dis1, *dis2;
dis1 = dis;
dis2 = dis1 + xdf1->nrec + 1;
+ if ((mlim = xdl_bogosqrt(xdf1->nrec)) > XDL_MAX_EQLIMIT)
+ mlim = XDL_MAX_EQLIMIT;
for (i = xdf1->dstart, recs = &xdf1->recs[xdf1->dstart]; i <= xdf1->dend; i++, recs++) {
rcrec = cf->rcrecs[(*recs)->ha];
nm = rcrec ? rcrec->len2 : 0;
- dis1[i] = (nm == 0) ? 0: 1;
+ dis1[i] = (nm == 0) ? 0: (nm >= mlim) ? 2: 1;
}
+ if ((mlim = xdl_bogosqrt(xdf2->nrec)) > XDL_MAX_EQLIMIT)
+ mlim = XDL_MAX_EQLIMIT;
for (i = xdf2->dstart, recs = &xdf2->recs[xdf2->dstart]; i <= xdf2->dend; i++, recs++) {
rcrec = cf->rcrecs[(*recs)->ha];
nm = rcrec ? rcrec->len1 : 0;
- dis2[i] = (nm == 0) ? 0: 1;
+ dis2[i] = (nm == 0) ? 0: (nm >= mlim) ? 2: 1;
}
for (nreff = 0, i = xdf1->dstart, recs = &xdf1->recs[xdf1->dstart];