#include "xinclude.h"
-
#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 {
xdlclass_t **rchash;
chastore_t ncha;
long count;
+ long flags;
} xdlclassifier_t;
-static int xdl_init_classifier(xdlclassifier_t *cf, long size);
+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_init_classifier(xdlclassifier_t *cf, long size) {
- long i;
+static int xdl_init_classifier(xdlclassifier_t *cf, long size, long flags) {
+ cf->flags = flags;
cf->hbits = xdl_hashbits((unsigned int) size);
cf->hsize = 1 << cf->hbits;
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->count = 0;
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 && rcrec->size == rec->size &&
- !memcmp(line, rcrec->line, rec->size))
+ if (rcrec->ha == rec->ha &&
+ xdl_recmatch(rcrec->line, rcrec->size,
+ rec->ptr, rec->size, cf->flags))
break;
if (!rcrec) {
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;
+ 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;
+ 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 *));
}
- 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;
- }
+ for (top = blk + bsize; cur < top; ) {
prev = cur;
- hav = xdl_hash_record(&cur, top);
+ 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(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;
+ /*
+ * 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) < 0) {
+ if (!(xpp->flags & XDF_HISTOGRAM_DIFF) &&
+ xdl_init_classifier(&cf, enl1 + enl2 + 1, xpp->flags) < 0) {
return -1;
}
return -1;
}
- xdl_free_classifier(&cf);
+ if (!(xpp->flags & XDF_HISTOGRAM_DIFF))
+ xdl_free_classifier(&cf);
- if (xdl_optimize_ctxs(&xe->xdf1, &xe->xdf2) < 0) {
+ if (!(xpp->flags & XDF_PATIENCE_DIFF) &&
+ !(xpp->flags & XDF_HISTOGRAM_DIFF) &&
+ xdl_optimize_ctxs(&xe->xdf1, &xe->xdf2) < 0) {
xdl_free_ctx(&xe->xdf2);
xdl_free_ctx(&xe->xdf1);
static int xdl_clean_mmatch(char const *dis, long i, long s, long e) {
- long r, rdis, rpdis;
-
- for (r = 1, rdis = 0, rpdis = 1; (i - r) >= s; r++) {
+ long r, rdis0, rpdis0, rdis1, rpdis1;
+
+ /*
+ * Limits the window the is examined during the similar-lines
+ * scan. The loops below stops when dis[i - r] == 1 (line that
+ * has no match), but there are corner cases where the loop
+ * proceed all the way to the extremities by causing huge
+ * performance penalties in case of big files.
+ */
+ if (i - s > XDL_SIMSCAN_WINDOW)
+ s = i - XDL_SIMSCAN_WINDOW;
+ if (e - i > XDL_SIMSCAN_WINDOW)
+ e = i + XDL_SIMSCAN_WINDOW;
+
+ /*
+ * Scans the lines before 'i' to find a run of lines that either
+ * have no match (dis[j] == 0) or have multiple matches (dis[j] > 1).
+ * Note that we always call this function with dis[i] > 1, so the
+ * current line (i) is already a multimatch line.
+ */
+ for (r = 1, rdis0 = 0, rpdis0 = 1; (i - r) >= s; r++) {
if (!dis[i - r])
- rdis++;
+ rdis0++;
else if (dis[i - r] == 2)
- rpdis++;
+ rpdis0++;
else
break;
}
- for (r = 1; (i + r) <= e; r++) {
+ /*
+ * If the run before the line 'i' found only multimatch lines, we
+ * return 0 and hence we don't make the current line (i) discarded.
+ * We want to discard multimatch lines only when they appear in the
+ * middle of runs with nomatch lines (dis[j] == 0).
+ */
+ if (rdis0 == 0)
+ return 0;
+ for (r = 1, rdis1 = 0, rpdis1 = 1; (i + r) <= e; r++) {
if (!dis[i + r])
- rdis++;
+ rdis1++;
else if (dis[i + r] == 2)
- rpdis++;
+ rpdis1++;
else
break;
}
-
- return rpdis * XDL_KPDIS_RUN < (rpdis + rdis);
+ /*
+ * If the run after the line 'i' found only multimatch lines, we
+ * return 0 and hence we don't make the current line (i) discarded.
+ */
+ if (rdis1 == 0)
+ return 0;
+ rdis1 += rdis0;
+ rpdis1 += rpdis0;
+
+ return rpdis1 * XDL_KPDIS_RUN < (rpdis1 + rdis1);
}
* 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, rhi, nreff;
+ 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) * sizeof(char)))) {
+ if (!(dis = (char *) xdl_malloc(xdf1->nrec + xdf2->nrec + 2))) {
return -1;
}
- memset(dis, 0, (xdf1->nrec + xdf2->nrec + 2) * sizeof(char));
+ 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 (rec = xdf2->rhash[rhi]; rec; rec = rec->next)
- if (rec->ha == hav && ++dis1[i] == 2)
+ 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 (rec = xdf1->rhash[rhi]; rec; rec = rec->next)
- if (rec->ha == hav && ++dis2[i] == 2)
+ 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];
return 0;
}
-