#define XDL_KPDIS_RUN 4
#define XDL_MAX_EQLIMIT 1024
#define XDL_SIMSCAN_WINDOW 100
+#define XDL_GUESS_NLINES1 256
+#define XDL_GUESS_NLINES2 20
typedef struct s_xdlclass {
char const *line;
long size;
long idx;
+ long len1, len2;
} xdlclass_t;
typedef struct s_xdlclassifier {
long hsize;
xdlclass_t **rchash;
chastore_t ncha;
+ xdlclass_t **rcrecs;
+ long alloc;
long count;
long flags;
} xdlclassifier_t;
static int xdl_init_classifier(xdlclassifier_t *cf, long size, long flags);
static void xdl_free_classifier(xdlclassifier_t *cf);
-static int xdl_classify_record(xdlclassifier_t *cf, xrecord_t **rhash, unsigned int hbits,
- xrecord_t *rec);
-static int xdl_prepare_ctx(mmfile_t *mf, long narec, xpparam_t const *xpp,
+static int xdl_classify_record(unsigned int pass, xdlclassifier_t *cf, xrecord_t **rhash,
+ unsigned int hbits, xrecord_t *rec);
+static int xdl_prepare_ctx(unsigned int pass, mmfile_t *mf, long narec, xpparam_t const *xpp,
xdlclassifier_t *cf, xdfile_t *xdf);
static void xdl_free_ctx(xdfile_t *xdf);
static int xdl_clean_mmatch(char const *dis, long i, long s, long e);
-static int xdl_cleanup_records(xdfile_t *xdf1, xdfile_t *xdf2);
+static int xdl_cleanup_records(xdlclassifier_t *cf, xdfile_t *xdf1, xdfile_t *xdf2);
static int xdl_trim_ends(xdfile_t *xdf1, xdfile_t *xdf2);
-static int xdl_optimize_ctxs(xdfile_t *xdf1, xdfile_t *xdf2);
+static int xdl_optimize_ctxs(xdlclassifier_t *cf, xdfile_t *xdf1, xdfile_t *xdf2);
static int xdl_init_classifier(xdlclassifier_t *cf, long size, long flags) {
- long i;
-
cf->flags = flags;
cf->hbits = xdl_hashbits((unsigned int) size);
xdl_cha_free(&cf->ncha);
return -1;
}
- for (i = 0; i < cf->hsize; i++)
- cf->rchash[i] = NULL;
+ memset(cf->rchash, 0, cf->hsize * sizeof(xdlclass_t *));
+
+ cf->alloc = size;
+ if (!(cf->rcrecs = (xdlclass_t **) xdl_malloc(cf->alloc * sizeof(xdlclass_t *)))) {
+
+ xdl_free(cf->rchash);
+ xdl_cha_free(&cf->ncha);
+ return -1;
+ }
cf->count = 0;
static void xdl_free_classifier(xdlclassifier_t *cf) {
+ xdl_free(cf->rcrecs);
xdl_free(cf->rchash);
xdl_cha_free(&cf->ncha);
}
-static int xdl_classify_record(xdlclassifier_t *cf, xrecord_t **rhash, unsigned int hbits,
- xrecord_t *rec) {
+static int xdl_classify_record(unsigned int pass, xdlclassifier_t *cf, xrecord_t **rhash,
+ unsigned int hbits, xrecord_t *rec) {
long hi;
char const *line;
xdlclass_t *rcrec;
+ xdlclass_t **rcrecs;
line = rec->ptr;
hi = (long) XDL_HASHLONG(rec->ha, cf->hbits);
return -1;
}
rcrec->idx = cf->count++;
+ if (cf->count > cf->alloc) {
+ cf->alloc *= 2;
+ if (!(rcrecs = (xdlclass_t **) xdl_realloc(cf->rcrecs, cf->alloc * sizeof(xdlclass_t *)))) {
+
+ return -1;
+ }
+ cf->rcrecs = rcrecs;
+ }
+ cf->rcrecs[rcrec->idx] = rcrec;
rcrec->line = line;
rcrec->size = rec->size;
rcrec->ha = rec->ha;
+ rcrec->len1 = rcrec->len2 = 0;
rcrec->next = cf->rchash[hi];
cf->rchash[hi] = rcrec;
}
+ (pass == 1) ? rcrec->len1++ : rcrec->len2++;
+
rec->ha = (unsigned long) rcrec->idx;
hi = (long) XDL_HASHLONG(rec->ha, hbits);
}
-static int xdl_prepare_ctx(mmfile_t *mf, long narec, xpparam_t const *xpp,
+static int xdl_prepare_ctx(unsigned int pass, mmfile_t *mf, long narec, xpparam_t const *xpp,
xdlclassifier_t *cf, xdfile_t *xdf) {
unsigned int hbits;
- long i, nrec, hsize, bsize;
+ long nrec, hsize, bsize;
unsigned long hav;
char const *blk, *cur, *top, *prev;
xrecord_t *crec;
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;
+ ha = NULL;
+ rindex = NULL;
+ rchg = NULL;
+ rhash = NULL;
+ recs = NULL;
+
+ if (xdl_cha_init(&xdf->rcha, sizeof(xrecord_t), narec / 4 + 1) < 0)
+ goto abort;
+ if (!(recs = (xrecord_t **) xdl_malloc(narec * sizeof(xrecord_t *))))
+ goto abort;
+
+ if (xpp->flags & XDF_HISTOGRAM_DIFF)
+ hbits = hsize = 0;
+ else {
+ hbits = xdl_hashbits((unsigned int) narec);
+ hsize = 1 << hbits;
+ if (!(rhash = (xrecord_t **) xdl_malloc(hsize * sizeof(xrecord_t *))))
+ goto abort;
+ memset(rhash, 0, hsize * sizeof(xrecord_t *));
}
- 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;
- }
+ for (top = blk + bsize; cur < top; ) {
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;
- }
+ if (!(rrecs = (xrecord_t **) xdl_realloc(recs, narec * sizeof(xrecord_t *))))
+ goto abort;
recs = rrecs;
}
- if (!(crec = xdl_cha_alloc(&xdf->rcha))) {
-
- xdl_free(rhash);
- xdl_free(recs);
- xdl_cha_free(&xdf->rcha);
- return -1;
- }
+ if (!(crec = xdl_cha_alloc(&xdf->rcha)))
+ goto abort;
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 (!(xpp->flags & XDF_HISTOGRAM_DIFF) &&
+ xdl_classify_record(pass, cf, rhash, hbits, crec) < 0)
+ goto abort;
}
}
- if (!(rchg = (char *) xdl_malloc((nrec + 2) * sizeof(char)))) {
-
- xdl_free(rhash);
- xdl_free(recs);
- xdl_cha_free(&xdf->rcha);
- return -1;
- }
+ if (!(rchg = (char *) xdl_malloc((nrec + 2) * sizeof(char))))
+ goto abort;
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;
- }
+ if (!(rindex = (long *) xdl_malloc((nrec + 1) * sizeof(long))))
+ goto abort;
+ if (!(ha = (unsigned long *) xdl_malloc((nrec + 1) * sizeof(unsigned long))))
+ goto abort;
xdf->nrec = nrec;
xdf->recs = recs;
xdf->dend = nrec - 1;
return 0;
+
+abort:
+ xdl_free(ha);
+ xdl_free(rindex);
+ xdl_free(rchg);
+ xdl_free(rhash);
+ xdl_free(recs);
+ xdl_cha_free(&xdf->rcha);
+ return -1;
}
int xdl_prepare_env(mmfile_t *mf1, mmfile_t *mf2, xpparam_t const *xpp,
xdfenv_t *xe) {
- long enl1, enl2;
+ long enl1, enl2, sample;
xdlclassifier_t cf;
- enl1 = xdl_guess_lines(mf1) + 1;
- enl2 = xdl_guess_lines(mf2) + 1;
+ 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
+ * table (rhash) won't be filled up/grown. The number of lines
+ * (nrecs) will be updated correctly anyway by
+ * xdl_prepare_ctx().
+ */
+ sample = xpp->flags & XDF_HISTOGRAM_DIFF ? XDL_GUESS_NLINES2 : XDL_GUESS_NLINES1;
+
+ enl1 = xdl_guess_lines(mf1, sample) + 1;
+ enl2 = xdl_guess_lines(mf2, sample) + 1;
- if (xdl_init_classifier(&cf, enl1 + enl2 + 1, xpp->flags) < 0) {
+ if (!(xpp->flags & XDF_HISTOGRAM_DIFF) &&
+ xdl_init_classifier(&cf, enl1 + enl2 + 1, xpp->flags) < 0) {
return -1;
}
- if (xdl_prepare_ctx(mf1, enl1, xpp, &cf, &xe->xdf1) < 0) {
+ if (xdl_prepare_ctx(1, mf1, enl1, xpp, &cf, &xe->xdf1) < 0) {
xdl_free_classifier(&cf);
return -1;
}
- if (xdl_prepare_ctx(mf2, enl2, xpp, &cf, &xe->xdf2) < 0) {
+ if (xdl_prepare_ctx(2, mf2, enl2, xpp, &cf, &xe->xdf2) < 0) {
xdl_free_ctx(&xe->xdf1);
xdl_free_classifier(&cf);
return -1;
}
- xdl_free_classifier(&cf);
-
if (!(xpp->flags & XDF_PATIENCE_DIFF) &&
- xdl_optimize_ctxs(&xe->xdf1, &xe->xdf2) < 0) {
+ !(xpp->flags & XDF_HISTOGRAM_DIFF) &&
+ xdl_optimize_ctxs(&cf, &xe->xdf1, &xe->xdf2) < 0) {
xdl_free_ctx(&xe->xdf2);
xdl_free_ctx(&xe->xdf1);
return -1;
}
+ if (!(xpp->flags & XDF_HISTOGRAM_DIFF))
+ xdl_free_classifier(&cf);
+
return 0;
}
* 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;
+static int xdl_cleanup_records(xdlclassifier_t *cf, xdfile_t *xdf1, xdfile_t *xdf2) {
+ long i, nm, nreff, mlim;
xrecord_t **recs;
- xrecord_t *rec;
+ xdlclass_t *rcrec;
char *dis, *dis1, *dis2;
if (!(dis = (char *) xdl_malloc(xdf1->nrec + xdf2->nrec + 2))) {
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;
+ rcrec = cf->rcrecs[(*recs)->ha];
+ nm = rcrec ? rcrec->len2 : 0;
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;
+ rcrec = cf->rcrecs[(*recs)->ha];
+ nm = rcrec ? rcrec->len1 : 0;
dis2[i] = (nm == 0) ? 0: (nm >= mlim) ? 2: 1;
}
}
-static int xdl_optimize_ctxs(xdfile_t *xdf1, xdfile_t *xdf2) {
+static int xdl_optimize_ctxs(xdlclassifier_t *cf, xdfile_t *xdf1, xdfile_t *xdf2) {
if (xdl_trim_ends(xdf1, xdf2) < 0 ||
- xdl_cleanup_records(xdf1, xdf2) < 0) {
+ xdl_cleanup_records(cf, xdf1, xdf2) < 0) {
return -1;
}