Hash :
3a5ad90a
Author :
Date :
2012-01-24T12:23:20
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483
/*
* LibXDiff by Davide Libenzi ( File Differential Library )
* Copyright (C) 2003 Davide Libenzi
*
* This library is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2.1 of the License, or (at your option) any later version.
*
* This library is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public
* License along with this library; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#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 {
struct s_xdlclass *next;
unsigned long ha;
char const *line;
long size;
long idx;
long len1, len2;
} xdlclass_t;
typedef struct s_xdlclassifier {
unsigned int hbits;
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(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(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(xdlclassifier_t *cf, xdfile_t *xdf1, xdfile_t *xdf2);
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;
if (xdl_cha_init(&cf->ncha, sizeof(xdlclass_t), size / 4 + 1) < 0) {
return -1;
}
if (!(cf->rchash = (xdlclass_t **) xdl_malloc(cf->hsize * sizeof(xdlclass_t *)))) {
xdl_cha_free(&cf->ncha);
return -1;
}
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;
return 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(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);
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++;
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);
rec->next = rhash[hi];
rhash[hi] = rec;
return 0;
}
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 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;
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 *));
}
nrec = 0;
if ((cur = blk = xdl_mmfile_first(mf, &bsize)) != NULL) {
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 *))))
goto abort;
recs = rrecs;
}
if (!(crec = xdl_cha_alloc(&xdf->rcha)))
goto abort;
crec->ptr = prev;
crec->size = (long) (cur - prev);
crec->ha = hav;
recs[nrec++] = crec;
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))))
goto abort;
memset(rchg, 0, (nrec + 2) * sizeof(char));
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->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;
abort:
xdl_free(ha);
xdl_free(rindex);
xdl_free(rchg);
xdl_free(rhash);
xdl_free(recs);
xdl_cha_free(&xdf->rcha);
return -1;
}
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);
}
int xdl_prepare_env(mmfile_t *mf1, mmfile_t *mf2, xpparam_t const *xpp,
xdfenv_t *xe) {
long enl1, enl2, sample;
xdlclassifier_t cf;
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 (!(xpp->flags & XDF_HISTOGRAM_DIFF) &&
xdl_init_classifier(&cf, enl1 + enl2 + 1, xpp->flags) < 0) {
return -1;
}
if (xdl_prepare_ctx(1, mf1, enl1, xpp, &cf, &xe->xdf1) < 0) {
xdl_free_classifier(&cf);
return -1;
}
if (xdl_prepare_ctx(2, mf2, enl2, xpp, &cf, &xe->xdf2) < 0) {
xdl_free_ctx(&xe->xdf1);
xdl_free_classifier(&cf);
return -1;
}
if (!(xpp->flags & XDF_PATIENCE_DIFF) &&
!(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;
}
void xdl_free_env(xdfenv_t *xe) {
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, 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])
rdis0++;
else if (dis[i - r] == 2)
rpdis0++;
else
break;
}
/*
* 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])
rdis1++;
else if (dis[i + r] == 2)
rpdis1++;
else
break;
}
/*
* 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);
}
/*
* 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(xdlclassifier_t *cf, xdfile_t *xdf1, xdfile_t *xdf2) {
long i, nm, nreff, mlim;
xrecord_t **recs;
xdlclass_t *rcrec;
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++) {
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++) {
rcrec = cf->rcrecs[(*recs)->ha];
nm = rcrec ? rcrec->len1 : 0;
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;
}
/*
* Early trim initial and terminal matching records.
*/
static int xdl_trim_ends(xdfile_t *xdf1, xdfile_t *xdf2) {
long i, lim;
xrecord_t **recs1, **recs2;
recs1 = xdf1->recs;
recs2 = xdf2->recs;
for (i = 0, lim = XDL_MIN(xdf1->nrec, xdf2->nrec); i < lim;
i++, recs1++, recs2++)
if ((*recs1)->ha != (*recs2)->ha)
break;
xdf1->dstart = xdf2->dstart = i;
recs1 = xdf1->recs + xdf1->nrec - 1;
recs2 = xdf2->recs + xdf2->nrec - 1;
for (lim -= i, i = 0; i < lim; i++, recs1--, recs2--)
if ((*recs1)->ha != (*recs2)->ha)
break;
xdf1->dend = xdf1->nrec - i - 1;
xdf2->dend = xdf2->nrec - i - 1;
return 0;
}
static int xdl_optimize_ctxs(xdlclassifier_t *cf, xdfile_t *xdf1, xdfile_t *xdf2) {
if (xdl_trim_ends(xdf1, xdf2) < 0 ||
xdl_cleanup_records(cf, xdf1, xdf2) < 0) {
return -1;
}
return 0;
}