xdiff: split xrecord_t.ha into line_hash and minimal_perfect_hash

The ha field is serving two different purposes, which makes the code
harder to read. At first glance, it looks like many places assume
there could never be hash collisions between lines of the two input
files. In reality, line_hash is used together with xdl_recmatch() to
ensure correct comparisons of lines, even when collisions occur.

To make this clearer, the old ha field has been split:
  * line_hash: a straightforward hash of a line, independent of any
    external context. Its type is uint64_t, as it comes from a fixed
    width hash function.
  * minimal_perfect_hash: Not a new concept, but now a separate
    field. It comes from the classifier's general-purpose hash table,
    which assigns each line a unique and minimal hash across the two
    files. A size_t is used here because it's meant to be used to
    index an array. This also avoids ` as usize` casts on the Rust
    side when using it to index a slice.

Signed-off-by: Ezekiel Newren <ezekielnewren@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
main
Ezekiel Newren 2025-11-18 22:34:18 +00:00 committed by Junio C Hamano
parent b0d4ae30f5
commit 6a26019c81
5 changed files with 21 additions and 20 deletions

View File

@ -22,9 +22,9 @@

#include "xinclude.h"

static unsigned long get_hash(xdfile_t *xdf, long index)
static size_t get_hash(xdfile_t *xdf, long index)
{
return xdf->recs[xdf->rindex[index]].ha;
return xdf->recs[xdf->rindex[index]].minimal_perfect_hash;
}

#define XDL_MAX_COST_MIN 256
@ -385,7 +385,7 @@ static xdchange_t *xdl_add_change(xdchange_t *xscr, long i1, long i2, long chg1,

static int recs_match(xrecord_t *rec1, xrecord_t *rec2)
{
return (rec1->ha == rec2->ha);
return rec1->minimal_perfect_hash == rec2->minimal_perfect_hash;
}

/*

View File

@ -90,7 +90,7 @@ struct region {

static int cmp_recs(xrecord_t *r1, xrecord_t *r2)
{
return r1->ha == r2->ha;
return r1->minimal_perfect_hash == r2->minimal_perfect_hash;

}

@ -98,7 +98,7 @@ static int cmp_recs(xrecord_t *r1, xrecord_t *r2)
(cmp_recs(REC(i->env, s1, l1), REC(i->env, s2, l2)))

#define TABLE_HASH(index, side, line) \
XDL_HASHLONG((REC(index->env, side, line))->ha, index->table_bits)
XDL_HASHLONG((REC(index->env, side, line))->minimal_perfect_hash, index->table_bits)

static int scanA(struct histindex *index, int line1, int count1)
{

View File

@ -48,7 +48,7 @@
struct hashmap {
int nr, alloc;
struct entry {
unsigned long hash;
size_t minimal_perfect_hash;
/*
* 0 = unused entry, 1 = first line, 2 = second, etc.
* line2 is NON_UNIQUE if the line is not unique
@ -101,10 +101,10 @@ static void insert_record(xpparam_t const *xpp, int line, struct hashmap *map,
* So we multiply ha by 2 in the hope that the hashing was
* "unique enough".
*/
int index = (int)((record->ha << 1) % map->alloc);
int index = (int)((record->minimal_perfect_hash << 1) % map->alloc);

while (map->entries[index].line1) {
if (map->entries[index].hash != record->ha) {
if (map->entries[index].minimal_perfect_hash != record->minimal_perfect_hash) {
if (++index >= map->alloc)
index = 0;
continue;
@ -120,7 +120,7 @@ static void insert_record(xpparam_t const *xpp, int line, struct hashmap *map,
if (pass == 2)
return;
map->entries[index].line1 = line;
map->entries[index].hash = record->ha;
map->entries[index].minimal_perfect_hash = record->minimal_perfect_hash;
map->entries[index].anchor = is_anchor(xpp, (const char *)map->env->xdf1.recs[line - 1].ptr);
if (!map->first)
map->first = map->entries + index;
@ -248,7 +248,7 @@ static int match(struct hashmap *map, int line1, int line2)
{
xrecord_t *record1 = &map->env->xdf1.recs[line1 - 1];
xrecord_t *record2 = &map->env->xdf2.recs[line2 - 1];
return record1->ha == record2->ha;
return record1->minimal_perfect_hash == record2->minimal_perfect_hash;
}

static int patience_diff(xpparam_t const *xpp, xdfenv_t *env,

View File

@ -93,12 +93,12 @@ static void xdl_free_classifier(xdlclassifier_t *cf) {


static int xdl_classify_record(unsigned int pass, xdlclassifier_t *cf, xrecord_t *rec) {
long hi;
size_t hi;
xdlclass_t *rcrec;

hi = (long) XDL_HASHLONG(rec->ha, cf->hbits);
hi = XDL_HASHLONG(rec->line_hash, cf->hbits);
for (rcrec = cf->rchash[hi]; rcrec; rcrec = rcrec->next)
if (rcrec->rec.ha == rec->ha &&
if (rcrec->rec.line_hash == rec->line_hash &&
xdl_recmatch((const char *)rcrec->rec.ptr, (long)rcrec->rec.size,
(const char *)rec->ptr, (long)rec->size, cf->flags))
break;
@ -120,7 +120,7 @@ static int xdl_classify_record(unsigned int pass, xdlclassifier_t *cf, xrecord_t

(pass == 1) ? rcrec->len1++ : rcrec->len2++;

rec->ha = (unsigned long) rcrec->idx;
rec->minimal_perfect_hash = (size_t)rcrec->idx;

return 0;
}
@ -158,7 +158,7 @@ static int xdl_prepare_ctx(unsigned int pass, mmfile_t *mf, long narec, xpparam_
crec = &xdf->recs[xdf->nrec++];
crec->ptr = prev;
crec->size = cur - prev;
crec->ha = hav;
crec->line_hash = hav;
if (xdl_classify_record(pass, cf, crec) < 0)
goto abort;
}
@ -290,7 +290,7 @@ static int xdl_cleanup_records(xdlclassifier_t *cf, xdfile_t *xdf1, xdfile_t *xd
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];
rcrec = cf->rcrecs[recs->minimal_perfect_hash];
nm = rcrec ? rcrec->len2 : 0;
action1[i] = (nm == 0) ? DISCARD: (nm >= mlim && !need_min) ? INVESTIGATE: KEEP;
}
@ -298,7 +298,7 @@ static int xdl_cleanup_records(xdlclassifier_t *cf, xdfile_t *xdf1, xdfile_t *xd
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];
rcrec = cf->rcrecs[recs->minimal_perfect_hash];
nm = rcrec ? rcrec->len1 : 0;
action2[i] = (nm == 0) ? DISCARD: (nm >= mlim && !need_min) ? INVESTIGATE: KEEP;
}
@ -350,7 +350,7 @@ static int xdl_trim_ends(xdfile_t *xdf1, xdfile_t *xdf2) {
recs2 = xdf2->recs;
for (i = 0, lim = XDL_MIN(xdf1->nrec, xdf2->nrec); i < lim;
i++, recs1++, recs2++)
if (recs1->ha != recs2->ha)
if (recs1->minimal_perfect_hash != recs2->minimal_perfect_hash)
break;

xdf1->dstart = xdf2->dstart = i;
@ -358,7 +358,7 @@ static int xdl_trim_ends(xdfile_t *xdf1, xdfile_t *xdf2) {
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)
if (recs1->minimal_perfect_hash != recs2->minimal_perfect_hash)
break;

xdf1->dend = xdf1->nrec - i - 1;

View File

@ -41,7 +41,8 @@ typedef struct s_chastore {
typedef struct s_xrecord {
uint8_t const *ptr;
size_t size;
unsigned long ha;
uint64_t line_hash;
size_t minimal_perfect_hash;
} xrecord_t;

typedef struct s_xdfile {