int xdl_do_diff(mmfile_t *mf1, mmfile_t *mf2, xpparam_t const *xpp,
xdfenv_t *xe) {
long ndiags;
long *kvd, *kvdf, *kvdb;
xdalgoenv_t xenv;
diffdata_t dd1, dd2;
if (XDF_DIFF_ALG(xpp->flags) == XDF_PATIENCE_DIFF)
return xdl_do_patience_diff(mf1, mf2, xpp, xe);
if (XDF_DIFF_ALG(xpp->flags) == XDF_HISTOGRAM_DIFF)
return xdl_do_histogram_diff(mf1, mf2, xpp, xe);
if (xdl_prepare_env(mf1, mf2, xpp, xe) < 0) {
return -1;
}
/*
* Allocate and setup K vectors to be used by the differential algorithm.
* One is to store the forward path and one to store the backward path.
*/
ndiags = xe->xdf1.nreff + xe->xdf2.nreff + 3;
if (!(kvd = (long *) xdl_malloc((2 * ndiags + 2) * sizeof(long)))) {
xdl_free_env(xe);
return -1;
}
kvdf = kvd;
kvdb = kvdf + ndiags;
kvdf += xe->xdf2.nreff + 1;
kvdb += xe->xdf2.nreff + 1;
xenv.mxcost = xdl_bogosqrt(ndiags);
if (xenv.mxcost < XDL_MAX_COST_MIN)
xenv.mxcost = XDL_MAX_COST_MIN;
xenv.snake_cnt = XDL_SNAKE_CNT;
xenv.heur_min = XDL_HEUR_MIN_COST;
dd1.nrec = xe->xdf1.nreff;
dd1.ha = xe->xdf1.ha;
dd1.rchg = xe->xdf1.rchg;
dd1.rindex = xe->xdf1.rindex;
dd2.nrec = xe->xdf2.nreff;
dd2.ha = xe->xdf2.ha;
dd2.rchg = xe->xdf2.rchg;
dd2.rindex = xe->xdf2.rindex;
if (xdl_recs_cmp(&dd1, 0, dd1.nrec, &dd2, 0, dd2.nrec,
kvdf, kvdb, (xpp->flags & XDF_NEED_MINIMAL) != 0, &xenv) < 0) {
xdl_free(kvd);
xdl_free_env(xe);
return -1;
}
xdl_free(kvd);
return 0;
}
/*
* 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 happear in a run of discardable.
*/
static int xdl_cleanup_records(xdfile_t *xdf1, xdfile_t *xdf2) {
long i, nm, rhi, nreff, mlim;
unsigned long hav;
xrecord_t **recs;
xrecord_t *rec;
char *dis, *dis1, *dis2;
if (!(dis = (char *) xdl_malloc(xdf1->nrec + xdf2->nrec + 2))) {
return -1;
}
memset(dis, 0, xdf1->nrec + xdf2->nrec + 2);
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++) {
hav = (*recs)->ha;
rhi = (long) XDL_HASHLONG(hav, xdf2->hbits);
for (nm = 0, rec = xdf2->rhash[rhi]; rec; rec = rec->next)
if (rec->ha == hav && ++nm == mlim)
break;
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++) {
hav = (*recs)->ha;
rhi = (long) XDL_HASHLONG(hav, xdf1->hbits);
for (nm = 0, rec = xdf1->rhash[rhi]; rec; rec = rec->next)
if (rec->ha == hav && ++nm == mlim)
break;
dis2[i] = (nm == 0) ? 0: (nm >= mlim) ? 2: 1;
}
for (nreff = 0, i = xdf1->dstart, recs = &xdf1->recs[xdf1->dstart];
i <= xdf1->dend; i++, recs++) {
if (dis1[i] == 1 ||
(dis1[i] == 2 && !xdl_clean_mmatch(dis1, i, xdf1->dstart, xdf1->dend))) {
xdf1->rindex[nreff] = i;
xdf1->ha[nreff] = (*recs)->ha;
nreff++;
} else
xdf1->rchg[i] = 1;
}
xdf1->nreff = nreff;
for (nreff = 0, i = xdf2->dstart, recs = &xdf2->recs[xdf2->dstart];
i <= xdf2->dend; i++, recs++) {
if (dis2[i] == 1 ||
(dis2[i] == 2 && !xdl_clean_mmatch(dis2, i, xdf2->dstart, xdf2->dend))) {
xdf2->rindex[nreff] = i;
xdf2->ha[nreff] = (*recs)->ha;
nreff++;
} else
xdf2->rchg[i] = 1;
}
xdf2->nreff = nreff;
xdl_free(dis);
return 0;
}
