xdiff: reduce size of action arrays
When the myers algorithm is selected the input files are pre-processed to remove any common prefix and suffix. Then any lines that appear only in one side of the diff are marked as changed and frequently occurring lines are marked as changed if they are adjacent to a changed line. This step requires a couple of temporary arrays. As as the common prefix and suffix have already been removed, the arrays only need to be big enough to hold the lines between them, not the whole file. Reduce the size of the arrays and adjust the loops that use them accordingly while taking care to keep indexing the arrays in xdfile_t with absolute line numbers. Signed-off-by: Phillip Wood <phillip.wood@dunelm.org.uk> Signed-off-by: Junio C Hamano <gitster@pobox.com>
Phillip Wood committed
May 4, 2026 at 15:06 UTC
a81411253323208e1e8d3591247c27fefa8a2045
1 file changed
+17
-14
xdiff/xprepare.c
+17
-14
@@ -273,16 +273,19 @@ static int xdl_cleanup_records(xdlclassifier_t *cf, xdfile_t *xdf1, xdfile_t *xd
273
uint8_t *action1 = NULL, *action2 = NULL;
274
bool need_min = !!(cf->flags & XDF_NEED_MINIMAL);
275
int ret = 0;
276
+ ptrdiff_t off = xdf1->dstart;
277
+ ptrdiff_t len1 = xdf1->dend - off + 1;
278
+ ptrdiff_t len2 = xdf2->dend - off + 1;
279
280
/*
281
* Create temporary arrays that will help us decide if
282
* changed[i] should remain false, or become true.
283
*/
281
- if (!XDL_CALLOC_ARRAY(action1, xdf1->nrec + 1)) {
284
+ if (!XDL_CALLOC_ARRAY(action1, len1)) {
285
ret = -1;
286
goto cleanup;
287
}
285
- if (!XDL_CALLOC_ARRAY(action2, xdf2->nrec + 1)) {
288
+ if (!XDL_CALLOC_ARRAY(action2, len2)) {
289
ret = -1;
290
goto cleanup;
291
}
@@ -298,8 +301,8 @@ static int xdl_cleanup_records(xdlclassifier_t *cf, xdfile_t *xdf1, xdfile_t *xd
301
if (mlim1 > XDL_MAX_EQLIMIT)
302
mlim1 = XDL_MAX_EQLIMIT;
303
}
301
- for (i = xdf1->dstart; i <= xdf1->dend; i++) {
302
- size_t mph1 = xdf1->recs[i].minimal_perfect_hash;
304
+ for (i = 0; i < len1; i++) {
305
+ size_t mph1 = xdf1->recs[i + off].minimal_perfect_hash;
306
rcrec = cf->rcrecs[mph1];
307
nm = rcrec ? rcrec->len2 : 0;
308
if (nm == 0)
@@ -318,8 +321,8 @@ static int xdl_cleanup_records(xdlclassifier_t *cf, xdfile_t *xdf1, xdfile_t *xd
321
if (mlim2 > XDL_MAX_EQLIMIT)
322
mlim2 = XDL_MAX_EQLIMIT;
323
}
321
- for (i = xdf2->dstart; i <= xdf2->dend; i++) {
322
- size_t mph2 = xdf2->recs[i].minimal_perfect_hash;
324
+ for (i = 0; i < len2; i++) {
325
+ size_t mph2 = xdf2->recs[i + off].minimal_perfect_hash;
326
rcrec = cf->rcrecs[mph2];
327
nm = rcrec ? rcrec->len1 : 0;
328
if (nm == 0)
@@ -335,42 +338,42 @@ static int xdl_cleanup_records(xdlclassifier_t *cf, xdfile_t *xdf1, xdfile_t *xd
338
* false, or become true.
339
*/
340
xdf1->nreff = 0;
338
- for (i = xdf1->dstart; i <= xdf1->dend; i++) {
341
+ for (i = 0; i < len1; i++) {
342
uint8_t action = action1[i];
343
344
if (action == INVESTIGATE) {
342
- if (!xdl_clean_mmatch(action1, i, xdf1->dstart, xdf1->dend))
345
+ if (!xdl_clean_mmatch(action1, i, 0, len1 - 1))
346
action = KEEP;
347
else
348
action = DISCARD;
349
}
350
351
if (action == KEEP) {
349
- xdf1->reference_index[xdf1->nreff++] = i;
352
+ xdf1->reference_index[xdf1->nreff++] = i + off;
353
/* changed[i] remains false */
354
} else if (action == DISCARD) {
352
- xdf1->changed[i] = true;
355
+ xdf1->changed[i + off] = true;
356
} else {
357
BUG("Illegal state for action");
358
}
359
}
360
361
xdf2->nreff = 0;
359
- for (i = xdf2->dstart; i <= xdf2->dend; i++) {
362
+ for (i = 0; i < len2; i++) {
363
uint8_t action = action2[i];
364
365
if (action == INVESTIGATE) {
363
- if (!xdl_clean_mmatch(action2, i, xdf2->dstart, xdf2->dend))
366
+ if (!xdl_clean_mmatch(action2, i, 0, len2 - 1))
367
action = KEEP;
368
else
369
action = DISCARD;
370
}
371
372
if (action == KEEP) {
370
- xdf2->reference_index[xdf2->nreff++] = i;
373
+ xdf2->reference_index[xdf2->nreff++] = i + off;
374
/* changed[i] remains false */
375
} else if (action == DISCARD) {
373
- xdf2->changed[i] = true;
376
+ xdf2->changed[i + off] = true;
377
} else {
378
BUG("Illegal state for action");
379
}