static int xdl_classify_record(xdlclassifier_t *cf, xrecord_t **rhash, unsigned int hbits,
xrecord_t *rec) {
long hi;
char const *line;
xdlclass_t *rcrec;
line = rec->ptr;
hi = (long) XDL_HASHLONG(rec->ha, cf->hbits);
for (rcrec = cf->rchash[hi]; rcrec; rcrec = rcrec->next)
if (rcrec->ha == rec->ha &&
xdl_recmatch(rcrec->line, rcrec->size,
rec->ptr, rec->size, cf->flags))
break;
if (!rcrec) {
if (!(rcrec = xdl_cha_alloc(&cf->ncha))) {
return -1;
}
rcrec->idx = cf->count++;
rcrec->line = line;
rcrec->size = rec->size;
rcrec->ha = rec->ha;
rcrec->next = cf->rchash[hi];
cf->rchash[hi] = rcrec;
}
rec->ha = (unsigned long) rcrec->idx;
hi = (long) XDL_HASHLONG(rec->ha, hbits);
rec->next = rhash[hi];
rhash[hi] = rec;
return 0;
}
static int scanA(struct histindex *index, int line1, int count1)
{
int ptr, tbl_idx;
unsigned int chain_len;
struct record **rec_chain, *rec;
for (ptr = LINE_END(1); line1 <= ptr; ptr--) {
tbl_idx = TABLE_HASH(index, 1, ptr);
rec_chain = index->records + tbl_idx;
rec = *rec_chain;
chain_len = 0;
while (rec) {
if (CMP(index, 1, rec->ptr, 1, ptr)) {
/*
* ptr is identical to another element. Insert
* it onto the front of the existing element
* chain.
*/
NEXT_PTR(index, ptr) = rec->ptr;
rec->ptr = ptr;
/* cap rec->cnt at MAX_CNT */
rec->cnt = XDL_MIN(MAX_CNT, rec->cnt + 1);
LINE_MAP(index, ptr) = rec;
goto continue_scan;
}
rec = rec->next;
chain_len++;
}
if (chain_len == index->max_chain_length)
return -1;
/*
* This is the first time we have ever seen this particular
* element in the sequence. Construct a new chain for it.
*/
if (!(rec = xdl_cha_alloc(&index->rcha)))
return -1;
rec->ptr = ptr;
rec->cnt = 1;
rec->next = *rec_chain;
*rec_chain = rec;
LINE_MAP(index, ptr) = rec;
continue_scan:
; /* no op */
}
return 0;
}
static int xdl_prepare_ctx(mmfile_t *mf, long narec, xpparam_t const *xpp,
xdlclassifier_t *cf, xdfile_t *xdf) {
unsigned int hbits;
long i, nrec, hsize, bsize;
unsigned long hav;
char const *blk, *cur, *top, *prev;
xrecord_t *crec;
xrecord_t **recs, **rrecs;
xrecord_t **rhash;
unsigned long *ha;
char *rchg;
long *rindex;
if (xdl_cha_init(&xdf->rcha, sizeof(xrecord_t), narec / 4 + 1) < 0) {
return -1;
}
if (!(recs = (xrecord_t **) xdl_malloc(narec * sizeof(xrecord_t *)))) {
xdl_cha_free(&xdf->rcha);
return -1;
}
hbits = xdl_hashbits((unsigned int) narec);
hsize = 1 << hbits;
if (!(rhash = (xrecord_t **) xdl_malloc(hsize * sizeof(xrecord_t *)))) {
xdl_free(recs);
xdl_cha_free(&xdf->rcha);
return -1;
}
for (i = 0; i < hsize; i++)
rhash[i] = NULL;
nrec = 0;
if ((cur = blk = xdl_mmfile_first(mf, &bsize)) != NULL) {
for (top = blk + bsize;;) {
if (cur >= top) {
if (!(cur = blk = xdl_mmfile_next(mf, &bsize)))
break;
top = blk + bsize;
}
prev = cur;
hav = xdl_hash_record(&cur, top, xpp->flags);
if (nrec >= narec) {
narec *= 2;
if (!(rrecs = (xrecord_t **) xdl_realloc(recs, narec * sizeof(xrecord_t *)))) {
xdl_free(rhash);
xdl_free(recs);
xdl_cha_free(&xdf->rcha);
return -1;
}
recs = rrecs;
}
if (!(crec = xdl_cha_alloc(&xdf->rcha))) {
xdl_free(rhash);
xdl_free(recs);
xdl_cha_free(&xdf->rcha);
return -1;
}
crec->ptr = prev;
crec->size = (long) (cur - prev);
crec->ha = hav;
recs[nrec++] = crec;
if (xdl_classify_record(cf, rhash, hbits, crec) < 0) {
xdl_free(rhash);
xdl_free(recs);
xdl_cha_free(&xdf->rcha);
return -1;
}
}
}
if (!(rchg = (char *) xdl_malloc((nrec + 2) * sizeof(char)))) {
xdl_free(rhash);
xdl_free(recs);
xdl_cha_free(&xdf->rcha);
return -1;
}
memset(rchg, 0, (nrec + 2) * sizeof(char));
if (!(rindex = (long *) xdl_malloc((nrec + 1) * sizeof(long)))) {
xdl_free(rchg);
xdl_free(rhash);
xdl_free(recs);
xdl_cha_free(&xdf->rcha);
return -1;
}
if (!(ha = (unsigned long *) xdl_malloc((nrec + 1) * sizeof(unsigned long)))) {
xdl_free(rindex);
xdl_free(rchg);
xdl_free(rhash);
xdl_free(recs);
xdl_cha_free(&xdf->rcha);
return -1;
}
xdf->nrec = nrec;
xdf->recs = recs;
xdf->hbits = hbits;
xdf->rhash = rhash;
xdf->rchg = rchg + 1;
xdf->rindex = rindex;
xdf->nreff = 0;
xdf->ha = ha;
xdf->dstart = 0;
xdf->dend = nrec - 1;
return 0;
}
