xdiff/xhistogram.c

   1 /*
   2  * Copyright (C) 2010, Google Inc.
   3  * and other copyright owners as documented in JGit's IP log.
   4  *
   5  * This program and the accompanying materials are made available
   6  * under the terms of the Eclipse Distribution License v1.0 which
   7  * accompanies this distribution, is reproduced below, and is
   8  * available at http://www.eclipse.org/org/documents/edl-v10.php
   9  *
  10  * All rights reserved.
  11  *
  12  * Redistribution and use in source and binary forms, with or
  13  * without modification, are permitted provided that the following
  14  * conditions are met:
  15  *
  16  * - Redistributions of source code must retain the above copyright
  17  *   notice, this list of conditions and the following disclaimer.
  18  *
  19  * - Redistributions in binary form must reproduce the above
  20  *   copyright notice, this list of conditions and the following
  21  *   disclaimer in the documentation and/or other materials provided
  22  *   with the distribution.
  23  *
  24  * - Neither the name of the Eclipse Foundation, Inc. nor the
  25  *   names of its contributors may be used to endorse or promote
  26  *   products derived from this software without specific prior
  27  *   written permission.
  28  *
  29  * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND
  30  * CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES,
  31  * INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
  32  * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
  33  * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR
  34  * CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
  35  * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
  36  * NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
  37  * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
  38  * CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT,
  39  * STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
  40  * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
  41  * ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  42  */
  43
  44 #include "xinclude.h"
  45
  46 #define MAX_PTR UINT_MAX
  47 #define MAX_CNT UINT_MAX
  48
  49 #define LINE_END(n) (line##n + count##n - 1)
  50 #define LINE_END_PTR(n) (*line##n + *count##n - 1)
  51
  52 struct histindex {
  53         struct record {
  54                 unsigned int ptr, cnt;
  55                 struct record *next;
  56         } **records, /* an occurrence */
  57           **line_map; /* map of line to record chain */
  58         chastore_t rcha;
  59         unsigned int *next_ptrs;
  60         unsigned int table_bits,
  61                      records_size,
  62                      line_map_size;
  63
  64         unsigned int max_chain_length,
  65                      key_shift,
  66                      ptr_shift;
  67
  68         unsigned int cnt,
  69                      has_common;
  70
  71         xdfenv_t *env;
  72         xpparam_t const *xpp;
  73 };
  74
  75 struct region {
  76         unsigned int begin1, end1;
  77         unsigned int begin2, end2;
  78 };
  79
  80 #define LINE_MAP(i, a) (i->line_map[(a) - i->ptr_shift])
  81
  82 #define NEXT_PTR(index, ptr) \
  83         (index->next_ptrs[(ptr) - index->ptr_shift])
  84
  85 #define CNT(index, ptr) \
  86         ((LINE_MAP(index, ptr))->cnt)
  87
  88 #define REC(env, s, l) \
  89         (env->xdf##s.recs[l - 1])
  90
  91 static int cmp_recs(xpparam_t const *xpp,
  92         xrecord_t *r1, xrecord_t *r2)
  93 {
  94         return r1->ha == r2->ha &&
  95                 xdl_recmatch(r1->ptr, r1->size, r2->ptr, r2->size,
  96                             xpp->flags);
  97 }
  98
  99 #define CMP_ENV(xpp, env, s1, l1, s2, l2) \
 100         (cmp_recs(xpp, REC(env, s1, l1), REC(env, s2, l2)))
 101
 102 #define CMP(i, s1, l1, s2, l2) \
 103         (cmp_recs(i->xpp, REC(i->env, s1, l1), REC(i->env, s2, l2)))
 104
 105 #define TABLE_HASH(index, side, line) \
 106         XDL_HASHLONG((REC(index->env, side, line))->ha, index->table_bits)
 107
 108 static int scanA(struct histindex *index, int line1, int count1)
 109 {
 110         unsigned int ptr, tbl_idx;
 111         unsigned int chain_len;
 112         struct record **rec_chain, *rec;
 113
 114         for (ptr = LINE_END(1); line1 <= ptr; ptr--) {
 115                 tbl_idx = TABLE_HASH(index, 1, ptr);
 116                 rec_chain = index->records + tbl_idx;
 117                 rec = *rec_chain;
 118
 119                 chain_len = 0;
 120                 while (rec) {
 121                         if (CMP(index, 1, rec->ptr, 1, ptr)) {
 122                                 /*
 123                                  * ptr is identical to another element. Insert
 124                                  * it onto the front of the existing element
 125                                  * chain.
 126                                  */
 127                                 NEXT_PTR(index, ptr) = rec->ptr;
 128                                 rec->ptr = ptr;
 129                                 /* cap rec->cnt at MAX_CNT */
 130                                 rec->cnt = XDL_MIN(MAX_CNT, rec->cnt + 1);
 131                                 LINE_MAP(index, ptr) = rec;
 132                                 goto continue_scan;
 133                         }
 134
 135                         rec = rec->next;
 136                         chain_len++;
 137                 }
 138
 139                 if (chain_len == index->max_chain_length)
 140                         return -1;
 141
 142                 /*
 143                  * This is the first time we have ever seen this particular
 144                  * element in the sequence. Construct a new chain for it.
 145                  */
 146                 if (!(rec = xdl_cha_alloc(&index->rcha)))
 147                         return -1;
 148                 rec->ptr = ptr;
 149                 rec->cnt = 1;
 150                 rec->next = *rec_chain;
 151                 *rec_chain = rec;
 152                 LINE_MAP(index, ptr) = rec;
 153
 154 continue_scan:
 155                 ; /* no op */
 156         }
 157
 158         return 0;
 159 }
 160
 161 static int try_lcs(struct histindex *index, struct region *lcs, int b_ptr,
 162         int line1, int count1, int line2, int count2)
 163 {
 164         unsigned int b_next = b_ptr + 1;
 165         struct record *rec = index->records[TABLE_HASH(index, 2, b_ptr)];
 166         unsigned int as, ae, bs, be, np, rc;
 167         int should_break;
 168
 169         for (; rec; rec = rec->next) {
 170                 if (rec->cnt > index->cnt) {
 171                         if (!index->has_common)
 172                                 index->has_common = CMP(index, 1, rec->ptr, 2, b_ptr);
 173                         continue;
 174                 }
 175
 176                 as = rec->ptr;
 177                 if (!CMP(index, 1, as, 2, b_ptr))
 178                         continue;
 179
 180                 index->has_common = 1;
 181                 for (;;) {
 182                         should_break = 0;
 183                         np = NEXT_PTR(index, as);
 184                         bs = b_ptr;
 185                         ae = as;
 186                         be = bs;
 187                         rc = rec->cnt;
 188
 189                         while (line1 < as && line2 < bs
 190                                 && CMP(index, 1, as - 1, 2, bs - 1)) {
 191                                 as--;
 192                                 bs--;
 193                                 if (1 < rc)
 194                                         rc = XDL_MIN(rc, CNT(index, as));
 195                         }
 196                         while (ae < LINE_END(1) && be < LINE_END(2)
 197                                 && CMP(index, 1, ae + 1, 2, be + 1)) {
 198                                 ae++;
 199                                 be++;
 200                                 if (1 < rc)
 201                                         rc = XDL_MIN(rc, CNT(index, ae));
 202                         }
 203
 204                         if (b_next <= be)
 205                                 b_next = be + 1;
 206                         if (lcs->end1 - lcs->begin1 < ae - as || rc < index->cnt) {
 207                                 lcs->begin1 = as;
 208                                 lcs->begin2 = bs;
 209                                 lcs->end1 = ae;
 210                                 lcs->end2 = be;
 211                                 index->cnt = rc;
 212                         }
 213
 214                         if (np == 0)
 215                                 break;
 216
 217                         while (np <= ae) {
 218                                 np = NEXT_PTR(index, np);
 219                                 if (np == 0) {
 220                                         should_break = 1;
 221                                         break;
 222                                 }
 223                         }
 224
 225                         if (should_break)
 226                                 break;
 227
 228                         as = np;
 229                 }
 230         }
 231         return b_next;
 232 }
 233
 234 static int fall_back_to_classic_diff(xpparam_t const *xpp, xdfenv_t *env,
 235                 int line1, int count1, int line2, int count2)
 236 {
 237         xpparam_t xpparam;
 238
 239         memset(&xpparam, 0, sizeof(xpparam));
 240         xpparam.flags = xpp->flags & ~XDF_DIFF_ALGORITHM_MASK;
 241
 242         return xdl_fall_back_diff(env, &xpparam,
 243                                   line1, count1, line2, count2);
 244 }
 245
 246 static inline void free_index(struct histindex *index)
 247 {
 248         xdl_free(index->records);
 249         xdl_free(index->line_map);
 250         xdl_free(index->next_ptrs);
 251         xdl_cha_free(&index->rcha);
 252 }
 253
 254 static int find_lcs(xpparam_t const *xpp, xdfenv_t *env,
 255                     struct region *lcs,
 256                     int line1, int count1, int line2, int count2)
 257 {
 258         int b_ptr;
 259         int sz, ret = -1;
 260         struct histindex index;
 261
 262         memset(&index, 0, sizeof(index));
 263
 264         index.env = env;
 265         index.xpp = xpp;
 266
 267         index.records = NULL;
 268         index.line_map = NULL;
 269         /* in case of early xdl_cha_free() */
 270         index.rcha.head = NULL;
 271
 272         index.table_bits = xdl_hashbits(count1);
 273         sz = index.records_size = 1 << index.table_bits;
 274         sz *= sizeof(struct record *);
 275         if (!(index.records = (struct record **) xdl_malloc(sz)))
 276                 goto cleanup;
 277         memset(index.records, 0, sz);
 278
 279         sz = index.line_map_size = count1;
 280         sz *= sizeof(struct record *);
 281         if (!(index.line_map = (struct record **) xdl_malloc(sz)))
 282                 goto cleanup;
 283         memset(index.line_map, 0, sz);
 284
 285         sz = index.line_map_size;
 286         sz *= sizeof(unsigned int);
 287         if (!(index.next_ptrs = (unsigned int *) xdl_malloc(sz)))
 288                 goto cleanup;
 289         memset(index.next_ptrs, 0, sz);
 290
 291         /* lines / 4 + 1 comes from xprepare.c:xdl_prepare_ctx() */
 292         if (xdl_cha_init(&index.rcha, sizeof(struct record), count1 / 4 + 1) < 0)
 293                 goto cleanup;
 294
 295         index.ptr_shift = line1;
 296         index.max_chain_length = 64;
 297
 298         if (scanA(&index, line1, count1))
 299                 goto cleanup;
 300
 301         index.cnt = index.max_chain_length + 1;
 302
 303         for (b_ptr = line2; b_ptr <= LINE_END(2); )
 304                 b_ptr = try_lcs(&index, lcs, b_ptr, line1, count1, line2, count2);
 305
 306         if (index.has_common && index.max_chain_length < index.cnt)
 307                 ret = 1;
 308         else
 309                 ret = 0;
 310
 311 cleanup:
 312         free_index(&index);
 313         return ret;
 314 }
 315
 316 static int histogram_diff(xpparam_t const *xpp, xdfenv_t *env,
 317         int line1, int count1, int line2, int count2)
 318 {
 319         struct region lcs;
 320         int lcs_found;
 321         int result;
 322 redo:
 323         result = -1;
 324
 325         if (count1 <= 0 && count2 <= 0)
 326                 return 0;
 327
 328         if (LINE_END(1) >= MAX_PTR)
 329                 return -1;
 330
 331         if (!count1) {
 332                 while(count2--)
 333                         env->xdf2.rchg[line2++ - 1] = 1;
 334                 return 0;
 335         } else if (!count2) {
 336                 while(count1--)
 337                         env->xdf1.rchg[line1++ - 1] = 1;
 338                 return 0;
 339         }
 340
 341         memset(&lcs, 0, sizeof(lcs));
 342         lcs_found = find_lcs(xpp, env, &lcs, line1, count1, line2, count2);
 343         if (lcs_found < 0)
 344                 goto out;
 345         else if (lcs_found)
 346                 result = fall_back_to_classic_diff(xpp, env, line1, count1, line2, count2);
 347         else {
 348                 if (lcs.begin1 == 0 && lcs.begin2 == 0) {
 349                         while (count1--)
 350                                 env->xdf1.rchg[line1++ - 1] = 1;
 351                         while (count2--)
 352                                 env->xdf2.rchg[line2++ - 1] = 1;
 353                         result = 0;
 354                 } else {
 355                         result = histogram_diff(xpp, env,
 356                                                 line1, lcs.begin1 - line1,
 357                                                 line2, lcs.begin2 - line2);
 358                         if (result)
 359                                 goto out;
 360                         /*
 361                          * result = histogram_diff(xpp, env,
 362                          *            lcs.end1 + 1, LINE_END(1) - lcs.end1,
 363                          *            lcs.end2 + 1, LINE_END(2) - lcs.end2);
 364                          * but let's optimize tail recursion ourself:
 365                         */
 366                         count1 = LINE_END(1) - lcs.end1;
 367                         line1 = lcs.end1 + 1;
 368                         count2 = LINE_END(2) - lcs.end2;
 369                         line2 = lcs.end2 + 1;
 370                         goto redo;
 371                 }
 372         }
 373 out:
 374         return result;
 375 }
 376
 377 int xdl_do_histogram_diff(mmfile_t *file1, mmfile_t *file2,
 378         xpparam_t const *xpp, xdfenv_t *env)
 379 {
 380         if (xdl_prepare_env(file1, file2, xpp, env) < 0)
 381                 return -1;
 382
 383         return histogram_diff(xpp, env,
 384                 env->xdf1.dstart + 1, env->xdf1.dend - env->xdf1.dstart + 1,
 385                 env->xdf2.dstart + 1, env->xdf2.dend - env->xdf2.dstart + 1);
 386 }