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;
}
int xdl_bpatch_multi(mmbuffer_t *base, mmbuffer_t *mbpch, int n, xdemitcb_t *ecb) {
int i, nobf, fnobf;
mmoffbuffer_t *obf, *fobf;
nobf = 1;
if ((obf = (mmoffbuffer_t *) xdl_malloc(nobf * sizeof(mmoffbuffer_t))) == NULL) {
return -1;
}
obf->off = 0;
obf->ptr = base->ptr;
obf->size = base->size;
for (i = 0; i < n; i++) {
if (xdl_bmerge(obf, nobf, &mbpch[i], &fobf, &fnobf) < 0) {
xdl_free(obf);
return -1;
}
xdl_free(obf);
obf = fobf;
nobf = fnobf;
}
if (xdl_bmerge_synt(obf, nobf, ecb) < 0) {
xdl_free(obf);
return -1;
}
xdl_free(obf);
return 0;
}
static inline void free_index(struct histindex *index)
{
xdl_free(index->records);
xdl_free(index->line_map);
xdl_free(index->next_ptrs);
xdl_cha_free(&index->rcha);
}
/*
* The idea is to start with the list of common unique lines sorted by
* the order in file1. For each of these pairs, the longest (partial)
* sequence whose last element's line2 is smaller is determined.
*
* For efficiency, the sequences are kept in a list containing exactly one
* item per sequence length: the sequence with the smallest last
* element (in terms of line2).
*/
static struct entry *find_longest_common_sequence(struct hashmap *map)
{
struct entry **sequence = xdl_malloc(map->nr * sizeof(struct entry *));
int longest = 0, i;
struct entry *entry;
for (entry = map->first; entry; entry = entry->next) {
if (!entry->line2 || entry->line2 == NON_UNIQUE)
continue;
i = binary_search(sequence, longest, entry);
entry->previous = i < 0 ? NULL : sequence[i];
sequence[++i] = entry;
if (i == longest)
longest++;
}
/* No common unique lines were found */
if (!longest) {
xdl_free(sequence);
return NULL;
}
/* Iterate starting at the last element, adjusting the "next" members */
entry = sequence[longest - 1];
entry->next = NULL;
while (entry->previous) {
entry->previous->next = entry;
entry = entry->previous;
}
xdl_free(sequence);
return entry;
}
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 (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;
/*
* Classical integer square root approximation using shifts.
*/
xenv.mxcost = 1;
for (; ndiags; ndiags >>= 2)
xenv.mxcost <<= 1;
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;
}
static void xdl_free_ctx(xdfile_t *xdf) {
xdl_free(xdf->rhash);
xdl_free(xdf->rindex);
xdl_free(xdf->rchg - 1);
xdl_free(xdf->ha);
xdl_free(xdf->recs);
xdl_cha_free(&xdf->rcha);
}
/*
* The idea is to start with the list of common unique lines sorted by
* the order in file1. For each of these pairs, the longest (partial)
* sequence whose last element's line2 is smaller is determined.
*
* For efficiency, the sequences are kept in a list containing exactly one
* item per sequence length: the sequence with the smallest last
* element (in terms of line2).
*/
static struct entry *find_longest_common_sequence(struct hashmap *map)
{
struct entry **sequence = (struct entry **)xdl_malloc(map->nr * sizeof(struct entry *));
int longest = 0, i;
struct entry *entry;
/*
* If not -1, this entry in sequence must never be overridden.
* Therefore, overriding entries before this has no effect, so
* do not do that either.
*/
int anchor_i = -1;
/* Added to silence Coverity. */
if (sequence == NULL)
return map->first;
for (entry = map->first; entry; entry = entry->next) {
if (!entry->line2 || entry->line2 == NON_UNIQUE)
continue;
i = binary_search(sequence, longest, entry);
entry->previous = i < 0 ? NULL : sequence[i];
++i;
if (i <= anchor_i)
continue;
sequence[i] = entry;
if (entry->anchor) {
anchor_i = i;
longest = anchor_i + 1;
} else if (i == longest) {
longest++;
}
}
/* No common unique lines were found */
if (!longest) {
xdl_free(sequence);
return NULL;
}
/* Iterate starting at the last element, adjusting the "next" members */
entry = sequence[longest - 1];
entry->next = NULL;
while (entry->previous) {
entry->previous->next = entry;
entry = entry->previous;
}
xdl_free(sequence);
return entry;
}
void xdl_free_script(xdchange_t *xscr) {
xdchange_t *xch;
while ((xch = xscr) != NULL) {
xscr = xscr->next;
xdl_free(xch);
}
}
void xdl_cha_free(chastore_t *cha) {
chanode_t *cur, *tmp;
for (cur = cha->head; (tmp = cur) != NULL;) {
cur = cur->next;
xdl_free(tmp);
}
}
void xdl_free_mmfile(mmfile_t *mmf) {
mmblock_t *cur, *tmp;
for (cur = mmf->head; (tmp = cur) != NULL;) {
cur = cur->next;
xdl_free(tmp);
}
}
/*
* Recursively find the longest common sequence of unique lines,
* and if none was found, ask xdl_do_diff() to do the job.
*
* This function assumes that env was prepared with xdl_prepare_env().
*/
static int patience_diff(mmfile_t *file1, mmfile_t *file2,
xpparam_t const *xpp, xdfenv_t *env,
int line1, int count1, int line2, int count2)
{
struct hashmap map;
struct entry *first;
int result = 0;
/* trivial case: one side is empty */
if (!count1) {
while(count2--)
env->xdf2.rchg[line2++ - 1] = 1;
return 0;
} else if (!count2) {
while(count1--)
env->xdf1.rchg[line1++ - 1] = 1;
return 0;
}
memset(&map, 0, sizeof(map));
if (fill_hashmap(file1, file2, xpp, env, &map,
line1, count1, line2, count2))
return -1;
/* are there any matching lines at all? */
if (!map.has_matches) {
while(count1--)
env->xdf1.rchg[line1++ - 1] = 1;
while(count2--)
env->xdf2.rchg[line2++ - 1] = 1;
xdl_free(map.entries);
return 0;
}
first = find_longest_common_sequence(&map);
if (first)
result = walk_common_sequence(&map, first,
line1, count1, line2, count2);
else
result = fall_back_to_classic_diff(&map,
line1, count1, line2, count2);
xdl_free(map.entries);
return result;
}
static int xdl_bmerge_synt(mmoffbuffer_t *obf, int n, xdemitcb_t *ecb) {
int i;
mmbuffer_t *mb;
if ((mb = (mmbuffer_t *) xdl_malloc(n * sizeof(mmbuffer_t))) == NULL) {
return -1;
}
for (i = 0; i < n; i++) {
mb[i].ptr = obf[i].ptr;
mb[i].size = obf[i].size;
}
if (ecb->outf(ecb->priv, mb, n) < 0) {
xdl_free(mb);
return -1;
}
xdl_free(mb);
return 0;
}
static int xdl_init_recfile(mmfile_t *mf, int ispatch, recfile_t *rf) {
long narec, nrec, bsize;
recinfo_t *recs, *rrecs;
char const *blk, *cur, *top, *eol;
narec = xdl_guess_lines(mf);
if (!(recs = (recinfo_t *) xdl_malloc(narec * sizeof(recinfo_t)))) {
return -1;
}
nrec = 0;
if ((cur = blk = (char const *)xdl_mmfile_first(mf, &bsize)) != NULL) {
for (top = blk + bsize;;) {
if (cur >= top) {
if (!(cur = blk = (char const *)xdl_mmfile_next(mf, &bsize)))
break;
top = blk + bsize;
}
if (nrec >= narec) {
narec *= 2;
if (!(rrecs = (recinfo_t *)
xdl_realloc(recs, narec * sizeof(recinfo_t)))) {
xdl_free(recs);
return -1;
}
recs = rrecs;
}
recs[nrec].ptr = cur;
if (!(eol = (char*)memchr(cur, '\n', top - cur)))
eol = top - 1;
recs[nrec].size = (long) (eol - cur) + 1;
if (ispatch && *cur == '\\' && nrec > 0 && recs[nrec - 1].size > 0 &&
recs[nrec - 1].ptr[recs[nrec - 1].size - 1] == '\n')
recs[nrec - 1].size--;
else
nrec++;
cur = eol + 1;
}
}
rf->mf = mf;
rf->nrec = nrec;
rf->recs = recs;
return 0;
}
int xdlt_auto_mbinregress(bdiffparam_t const *bdp, long size,
double rmod, int chmax, int n) {
int i, res;
mmbuffer_t *mbb;
mmfile_t *mf, *mfc, *mfx;
mmfile_t mfn, mff, mfd, mfb;
xdemitcb_t ecb;
if ((mbb = (mmbuffer_t *) xdl_malloc((n + 2) * sizeof(mmbuffer_t))) == NULL) {
return -1;
}
if ((mf = mfc = (mmfile_t *) xdl_malloc((n + 2) * sizeof(mmfile_t))) == NULL) {
xdl_free(mbb);
return -1;
}
if (xdlt_create_file(mfc, size) < 0) {
xdl_free(mf);
xdl_free(mbb);
return -1;
}
mbb[0].ptr = (char *) xdl_mmfile_first(mfc, &mbb[0].size);
mfc++;
mfx = mf;
for (i = 0; i < n; i++) {
if (xdlt_change_file(mfx, &mfn, rmod, chmax) < 0) {
if (mfx != mf) xdl_free_mmfile(mfx);
for (; i >= 0; i--)
xdl_free_mmfile(mf + i);
xdl_free(mf);
xdl_free(mbb);
return -1;
}
if (xdl_mmfile_compact(&mfn, &mff, XDLT_STD_BLKSIZE, XDL_MMF_ATOMIC) < 0) {
xdl_free_mmfile(&mfn);
if (mfx != mf) xdl_free_mmfile(mfx);
for (; i >= 0; i--)
xdl_free_mmfile(mf + i);
xdl_free(mf);
xdl_free(mbb);
return -1;
}
xdl_free_mmfile(&mfn);
if (xdlt_do_bindiff(mfx, &mff, bdp, &mfd) < 0) {
xdl_free_mmfile(&mff);
if (mfx != mf) xdl_free_mmfile(mfx);
for (; i >= 0; i--)
xdl_free_mmfile(mf + i);
xdl_free(mf);
xdl_free(mbb);
return -1;
}
if (mfx != mf) xdl_free_mmfile(mfx);
mfx = &mfb;
*mfx = mff;
if (xdl_mmfile_compact(&mfd, mfc, XDLT_STD_BLKSIZE, XDL_MMF_ATOMIC) < 0) {
xdl_free_mmfile(&mfd);
xdl_free_mmfile(mfx);
for (; i >= 0; i--)
xdl_free_mmfile(mf + i);
xdl_free(mf);
xdl_free(mbb);
return -1;
}
mbb[i + 1].ptr = (char *) xdl_mmfile_first(mfc, &mbb[i + 1].size);
mfc++;
xdl_free_mmfile(&mfd);
}
if (xdl_init_mmfile(mfc, XDLT_STD_BLKSIZE, XDL_MMF_ATOMIC) < 0) {
xdl_free_mmfile(mfx);
for (i = n; i >= 0; i--)
xdl_free_mmfile(mf + i);
xdl_free(mf);
xdl_free(mbb);
return -1;
}
ecb.priv = mfc;
ecb.outf = xdlt_mmfile_outf;
if ((res = xdl_bpatch_multi(&mbb[0], &mbb[1], n, &ecb)) == 0)
res = xdl_mmfile_cmp(mfx, mfc);
xdl_free_mmfile(mfx);
for (i = n + 1; i >= 0; i--)
xdl_free_mmfile(mf + i);
xdl_free(mf);
xdl_free(mbb);
return res;
}
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;
}
static int xdl_bmerge(mmoffbuffer_t *obf, int n, mmbuffer_t *mbfp, mmoffbuffer_t **probf,
int *pnobf) {
int i, aobf, nobf;
long ooff, off, csize;
unsigned long fp, ofp;
unsigned char const *data, *top;
mmoffbuffer_t *robf, *cobf;
if (mbfp->size < XDL_BPATCH_HDR_SIZE) {
return -1;
}
data = (unsigned char const *) mbfp->ptr;
top = data + mbfp->size;
ofp = xdl_mmob_adler32(obf, n);
XDL_LE32_GET(data, fp);
data += 4;
XDL_LE32_GET(data, csize);
data += 4;
if (fp != ofp || csize != xdl_mmob_size(obf, n)) {
return -1;
}
aobf = XDL_MOBF_MINALLOC;
nobf = 0;
if ((robf = (mmoffbuffer_t *) xdl_malloc(aobf * sizeof(mmoffbuffer_t))) == NULL) {
return -1;
}
for (ooff = 0; data < top;) {
if (*data == XDL_BDOP_INS) {
data++;
if ((cobf = xdl_mmob_new(&robf, &nobf, &aobf)) == NULL) {
xdl_free(robf);
return -1;
}
cobf->off = ooff;
cobf->size = (long) *data++;
cobf->ptr = (char *) data;
data += cobf->size;
ooff += cobf->size;
} else if (*data == XDL_BDOP_INSB) {
data++;
XDL_LE32_GET(data, csize);
data += 4;
if ((cobf = xdl_mmob_new(&robf, &nobf, &aobf)) == NULL) {
xdl_free(robf);
return -1;
}
cobf->off = ooff;
cobf->size = csize;
cobf->ptr = (char *) data;
data += cobf->size;
ooff += cobf->size;
} else if (*data == XDL_BDOP_CPY) {
data++;
XDL_LE32_GET(data, off);
data += 4;
XDL_LE32_GET(data, csize);
data += 4;
if ((i = xdl_mmob_find_cntr(obf, n, off)) < 0) {
xdl_free(robf);
return -1;
}
off -= obf[i].off;
for (; i < n && csize > 0; i++, off = 0) {
if ((cobf = xdl_mmob_new(&robf, &nobf, &aobf)) == NULL) {
xdl_free(robf);
return -1;
}
cobf->off = ooff;
cobf->size = XDL_MIN(csize, obf[i].size - off);
cobf->ptr = obf[i].ptr + off;
ooff += cobf->size;
csize -= cobf->size;
}
if (csize > 0) {
xdl_free(robf);
return -1;
}
} else {
xdl_free(robf);
return -1;
}
}
*probf = robf;
*pnobf = nobf;
return 0;
}
static int histogram_diff(xpparam_t const *xpp, xdfenv_t *env,
int line1, int count1, int line2, int count2)
{
struct histindex index;
struct region lcs;
int sz;
int result = -1;
if (count1 <= 0 && count2 <= 0)
return 0;
if (LINE_END(1) >= MAX_PTR)
return -1;
if (!count1) {
while(count2--)
env->xdf2.rchg[line2++ - 1] = 1;
return 0;
} else if (!count2) {
while(count1--)
env->xdf1.rchg[line1++ - 1] = 1;
return 0;
}
memset(&index, 0, sizeof(index));
index.env = env;
index.xpp = xpp;
index.records = NULL;
index.line_map = NULL;
/* in case of early xdl_cha_free() */
index.rcha.head = NULL;
index.table_bits = xdl_hashbits(count1);
sz = index.records_size = 1 << index.table_bits;
sz *= sizeof(struct record *);
if (!(index.records = (struct record **) xdl_malloc(sz)))
goto cleanup;
memset(index.records, 0, sz);
sz = index.line_map_size = count1;
sz *= sizeof(struct record *);
if (!(index.line_map = (struct record **) xdl_malloc(sz)))
goto cleanup;
memset(index.line_map, 0, sz);
sz = index.line_map_size;
sz *= sizeof(unsigned int);
if (!(index.next_ptrs = (unsigned int *) xdl_malloc(sz)))
goto cleanup;
memset(index.next_ptrs, 0, sz);
/* lines / 4 + 1 comes from xprepare.c:xdl_prepare_ctx() */
if (xdl_cha_init(&index.rcha, sizeof(struct record), count1 / 4 + 1) < 0)
goto cleanup;
index.ptr_shift = line1;
index.max_chain_length = 64;
memset(&lcs, 0, sizeof(lcs));
if (find_lcs(&index, &lcs, line1, count1, line2, count2))
result = fall_back_to_classic_diff(&index, line1, count1, line2, count2);
else {
if (lcs.begin1 == 0 && lcs.begin2 == 0) {
while (count1--)
env->xdf1.rchg[line1++ - 1] = 1;
while (count2--)
env->xdf2.rchg[line2++ - 1] = 1;
result = 0;
} else {
result = histogram_diff(xpp, env,
line1, lcs.begin1 - line1,
line2, lcs.begin2 - line2);
if (result)
goto cleanup;
result = histogram_diff(xpp, env,
lcs.end1 + 1, LINE_END(1) - lcs.end1,
lcs.end2 + 1, LINE_END(2) - lcs.end2);
if (result)
goto cleanup;
}
}
cleanup:
xdl_free(index.records);
xdl_free(index.line_map);
xdl_free(index.next_ptrs);
xdl_cha_free(&index.rcha);
return result;
}
static void xdl_free_recfile(recfile_t *rf) {
xdl_free(rf->recs);
}
/*
* 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;
}
static void xdl_free_classifier(xdlclassifier_t *cf) {
xdl_free(cf->rchash);
xdl_cha_free(&cf->ncha);
}
