kernel
/
git
mirror of https://git.kernel.org/pub/scm/git/git.git
1
0
Fork 0
Code Releases Activity

Merge branch 'en/xdiff-cleanup' 

A lot of code clean-up of xdiff.
Split out of a larger topic.

* en/xdiff-cleanup:
  xdiff: change type of xdfile_t.changed from char to bool
  xdiff: add macros DISCARD(0), KEEP(1), INVESTIGATE(2) in xprepare.c
  xdiff: rename rchg -> changed in xdfile_t
  xdiff: delete chastore from xdfile_t
  xdiff: delete fields ha, line, size in xdlclass_t in favor of an xrecord_t
  xdiff: delete redundant array xdfile_t.ha
  xdiff: delete struct diffdata_t
  xdiff: delete local variables that alias fields in xrecord_t
  xdiff: delete superfluous function xdl_get_rec() in xemit
  xdiff: delete unnecessary fields from xrecord_t and xdfile_t
  xdiff: delete local variables and initialize/free xdfile_t directly
  xdiff: delete static forward declarations in xprepare
main
Junio C Hamano 2025-10-14 12:56:09 -07:00
parent 243a61d2cf 8b9c5d2e3a
commit 9ff172d0ee
9 changed files with 331 additions and 399 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

102
xdiff/xdiffi.c
View File

@ -22,6 +22,11 @@


#include "xinclude.h" #include "xinclude.h"


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

#define XDL_MAX_COST_MIN 256 #define XDL_MAX_COST_MIN 256
#define XDL_HEUR_MIN_COST 256 #define XDL_HEUR_MIN_COST 256
#define XDL_LINE_MAX (long)((1UL << (CHAR_BIT * sizeof(long) - 1)) - 1) #define XDL_LINE_MAX (long)((1UL << (CHAR_BIT * sizeof(long) - 1)) - 1)
@ -42,8 +47,8 @@ typedef struct s_xdpsplit {
* using this algorithm, so a little bit of heuristic is needed to cut the * using this algorithm, so a little bit of heuristic is needed to cut the
* search and to return a suboptimal point. * search and to return a suboptimal point.
*/ */
static long xdl_split(unsigned long const *ha1, long off1, long lim1, static long xdl_split(xdfile_t *xdf1, long off1, long lim1,
unsigned long const *ha2, long off2, long lim2, xdfile_t *xdf2, long off2, long lim2,
long *kvdf, long *kvdb, int need_min, xdpsplit_t *spl, long *kvdf, long *kvdb, int need_min, xdpsplit_t *spl,
xdalgoenv_t *xenv) { xdalgoenv_t *xenv) {
long dmin = off1 - lim2, dmax = lim1 - off2; long dmin = off1 - lim2, dmax = lim1 - off2;
@ -87,7 +92,7 @@ static long xdl_split(unsigned long const *ha1, long off1, long lim1,
i1 = kvdf[d + 1]; i1 = kvdf[d + 1];
prev1 = i1; prev1 = i1;
i2 = i1 - d; i2 = i1 - d;
for (; i1 < lim1 && i2 < lim2 && ha1[i1] == ha2[i2]; i1++, i2++); for (; i1 < lim1 && i2 < lim2 && get_hash(xdf1, i1) == get_hash(xdf2, i2); i1++, i2++);
if (i1 - prev1 > xenv->snake_cnt) if (i1 - prev1 > xenv->snake_cnt)
got_snake = 1; got_snake = 1;
kvdf[d] = i1; kvdf[d] = i1;
@ -124,7 +129,7 @@ static long xdl_split(unsigned long const *ha1, long off1, long lim1,
i1 = kvdb[d + 1] - 1; i1 = kvdb[d + 1] - 1;
prev1 = i1; prev1 = i1;
i2 = i1 - d; i2 = i1 - d;
for (; i1 > off1 && i2 > off2 && ha1[i1 - 1] == ha2[i2 - 1]; i1--, i2--); for (; i1 > off1 && i2 > off2 && get_hash(xdf1, i1 - 1) == get_hash(xdf2, i2 - 1); i1--, i2--);
if (prev1 - i1 > xenv->snake_cnt) if (prev1 - i1 > xenv->snake_cnt)
got_snake = 1; got_snake = 1;
kvdb[d] = i1; kvdb[d] = i1;
@ -159,7 +164,7 @@ static long xdl_split(unsigned long const *ha1, long off1, long lim1,
if (v > XDL_K_HEUR * ec && v > best && if (v > XDL_K_HEUR * ec && v > best &&
off1 + xenv->snake_cnt <= i1 && i1 < lim1 && off1 + xenv->snake_cnt <= i1 && i1 < lim1 &&
off2 + xenv->snake_cnt <= i2 && i2 < lim2) { off2 + xenv->snake_cnt <= i2 && i2 < lim2) {
for (k = 1; ha1[i1 - k] == ha2[i2 - k]; k++) for (k = 1; get_hash(xdf1, i1 - k) == get_hash(xdf2, i2 - k); k++)
if (k == xenv->snake_cnt) { if (k == xenv->snake_cnt) {
best = v; best = v;
spl->i1 = i1; spl->i1 = i1;
@ -183,7 +188,7 @@ static long xdl_split(unsigned long const *ha1, long off1, long lim1,
if (v > XDL_K_HEUR * ec && v > best && if (v > XDL_K_HEUR * ec && v > best &&
off1 < i1 && i1 <= lim1 - xenv->snake_cnt && off1 < i1 && i1 <= lim1 - xenv->snake_cnt &&
off2 < i2 && i2 <= lim2 - xenv->snake_cnt) { off2 < i2 && i2 <= lim2 - xenv->snake_cnt) {
for (k = 0; ha1[i1 + k] == ha2[i2 + k]; k++) for (k = 0; get_hash(xdf1, i1 + k) == get_hash(xdf2, i2 + k); k++)
if (k == xenv->snake_cnt - 1) { if (k == xenv->snake_cnt - 1) {
best = v; best = v;
spl->i1 = i1; spl->i1 = i1;
@ -257,33 +262,26 @@ static long xdl_split(unsigned long const *ha1, long off1, long lim1,
* sub-boxes by calling the box splitting function. Note that the real job * sub-boxes by calling the box splitting function. Note that the real job
* (marking changed lines) is done in the two boundary reaching checks. * (marking changed lines) is done in the two boundary reaching checks.
*/ */
int xdl_recs_cmp(diffdata_t *dd1, long off1, long lim1, int xdl_recs_cmp(xdfile_t *xdf1, long off1, long lim1,
diffdata_t *dd2, long off2, long lim2, xdfile_t *xdf2, long off2, long lim2,
long *kvdf, long *kvdb, int need_min, xdalgoenv_t *xenv) { long *kvdf, long *kvdb, int need_min, xdalgoenv_t *xenv) {
unsigned long const *ha1 = dd1->ha, *ha2 = dd2->ha;


/* /*
* Shrink the box by walking through each diagonal snake (SW and NE). * Shrink the box by walking through each diagonal snake (SW and NE).
*/ */
for (; off1 < lim1 && off2 < lim2 && ha1[off1] == ha2[off2]; off1++, off2++); for (; off1 < lim1 && off2 < lim2 && get_hash(xdf1, off1) == get_hash(xdf2, off2); off1++, off2++);
for (; off1 < lim1 && off2 < lim2 && ha1[lim1 - 1] == ha2[lim2 - 1]; lim1--, lim2--); for (; off1 < lim1 && off2 < lim2 && get_hash(xdf1, lim1 - 1) == get_hash(xdf2, lim2 - 1); lim1--, lim2--);


/* /*
* If one dimension is empty, then all records on the other one must * If one dimension is empty, then all records on the other one must
* be obviously changed. * be obviously changed.
*/ */
if (off1 == lim1) { if (off1 == lim1) {
char *rchg2 = dd2->rchg;
long *rindex2 = dd2->rindex;

for (; off2 < lim2; off2++) for (; off2 < lim2; off2++)
rchg2[rindex2[off2]] = 1; xdf2->changed[xdf2->rindex[off2]] = true;
} else if (off2 == lim2) { } else if (off2 == lim2) {
char *rchg1 = dd1->rchg;
long *rindex1 = dd1->rindex;

for (; off1 < lim1; off1++) for (; off1 < lim1; off1++)
rchg1[rindex1[off1]] = 1; xdf1->changed[xdf1->rindex[off1]] = true;
} else { } else {
xdpsplit_t spl; xdpsplit_t spl;
spl.i1 = spl.i2 = 0; spl.i1 = spl.i2 = 0;
@ -291,7 +289,7 @@ int xdl_recs_cmp(diffdata_t *dd1, long off1, long lim1,
/* /*
* Divide ... * Divide ...
*/ */
if (xdl_split(ha1, off1, lim1, ha2, off2, lim2, kvdf, kvdb, if (xdl_split(xdf1, off1, lim1, xdf2, off2, lim2, kvdf, kvdb,
need_min, &spl, xenv) < 0) { need_min, &spl, xenv) < 0) {


return -1; return -1;
@ -300,9 +298,9 @@ int xdl_recs_cmp(diffdata_t *dd1, long off1, long lim1,
/* /*
* ... et Impera. * ... et Impera.
*/ */
if (xdl_recs_cmp(dd1, off1, spl.i1, dd2, off2, spl.i2, if (xdl_recs_cmp(xdf1, off1, spl.i1, xdf2, off2, spl.i2,
kvdf, kvdb, spl.min_lo, xenv) < 0 || kvdf, kvdb, spl.min_lo, xenv) < 0 ||
xdl_recs_cmp(dd1, spl.i1, lim1, dd2, spl.i2, lim2, xdl_recs_cmp(xdf1, spl.i1, lim1, xdf2, spl.i2, lim2,
kvdf, kvdb, spl.min_hi, xenv) < 0) { kvdf, kvdb, spl.min_hi, xenv) < 0) {


return -1; return -1;
@ -318,7 +316,6 @@ int xdl_do_diff(mmfile_t *mf1, mmfile_t *mf2, xpparam_t const *xpp,
long ndiags; long ndiags;
long *kvd, *kvdf, *kvdb; long *kvd, *kvdf, *kvdb;
xdalgoenv_t xenv; xdalgoenv_t xenv;
diffdata_t dd1, dd2;
int res; int res;


if (xdl_prepare_env(mf1, mf2, xpp, xe) < 0) if (xdl_prepare_env(mf1, mf2, xpp, xe) < 0)
@ -357,16 +354,7 @@ int xdl_do_diff(mmfile_t *mf1, mmfile_t *mf2, xpparam_t const *xpp,
xenv.snake_cnt = XDL_SNAKE_CNT; xenv.snake_cnt = XDL_SNAKE_CNT;
xenv.heur_min = XDL_HEUR_MIN_COST; xenv.heur_min = XDL_HEUR_MIN_COST;


dd1.nrec = xe->xdf1.nreff; res = xdl_recs_cmp(&xe->xdf1, 0, xe->xdf1.nreff, &xe->xdf2, 0, xe->xdf2.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;

res = xdl_recs_cmp(&dd1, 0, dd1.nrec, &dd2, 0, dd2.nrec,
kvdf, kvdb, (xpp->flags & XDF_NEED_MINIMAL) != 0, kvdf, kvdb, (xpp->flags & XDF_NEED_MINIMAL) != 0,
&xenv); &xenv);
xdl_free(kvd); xdl_free(kvd);
@ -501,13 +489,13 @@ static void measure_split(const xdfile_t *xdf, long split,
m->indent = -1; m->indent = -1;
} else { } else {
m->end_of_file = 0; m->end_of_file = 0;
m->indent = get_indent(xdf->recs[split]); m->indent = get_indent(&xdf->recs[split]);
} }


m->pre_blank = 0; m->pre_blank = 0;
m->pre_indent = -1; m->pre_indent = -1;
for (i = split - 1; i >= 0; i--) { for (i = split - 1; i >= 0; i--) {
m->pre_indent = get_indent(xdf->recs[i]); m->pre_indent = get_indent(&xdf->recs[i]);
if (m->pre_indent != -1) if (m->pre_indent != -1)
break; break;
m->pre_blank += 1; m->pre_blank += 1;
@ -520,7 +508,7 @@ static void measure_split(const xdfile_t *xdf, long split,
m->post_blank = 0; m->post_blank = 0;
m->post_indent = -1; m->post_indent = -1;
for (i = split + 1; i < xdf->nrec; i++) { for (i = split + 1; i < xdf->nrec; i++) {
m->post_indent = get_indent(xdf->recs[i]); m->post_indent = get_indent(&xdf->recs[i]);
if (m->post_indent != -1) if (m->post_indent != -1)
break; break;
m->post_blank += 1; m->post_blank += 1;
@ -720,7 +708,7 @@ struct xdlgroup {
static void group_init(xdfile_t *xdf, struct xdlgroup *g) static void group_init(xdfile_t *xdf, struct xdlgroup *g)
{ {
g->start = g->end = 0; g->start = g->end = 0;
while (xdf->rchg[g->end]) while (xdf->changed[g->end])
g->end++; g->end++;
} }


@ -734,7 +722,7 @@ static inline int group_next(xdfile_t *xdf, struct xdlgroup *g)
return -1; return -1;


g->start = g->end + 1; g->start = g->end + 1;
for (g->end = g->start; xdf->rchg[g->end]; g->end++) for (g->end = g->start; xdf->changed[g->end]; g->end++)
; ;


return 0; return 0;
@ -750,7 +738,7 @@ static inline int group_previous(xdfile_t *xdf, struct xdlgroup *g)
return -1; return -1;


g->end = g->start - 1; g->end = g->start - 1;
for (g->start = g->end; xdf->rchg[g->start - 1]; g->start--) for (g->start = g->end; xdf->changed[g->start - 1]; g->start--)
; ;


return 0; return 0;
@ -764,11 +752,11 @@ static inline int group_previous(xdfile_t *xdf, struct xdlgroup *g)
static int group_slide_down(xdfile_t *xdf, struct xdlgroup *g) static int group_slide_down(xdfile_t *xdf, struct xdlgroup *g)
{ {
if (g->end < xdf->nrec && if (g->end < xdf->nrec &&
recs_match(xdf->recs[g->start], xdf->recs[g->end])) { recs_match(&xdf->recs[g->start], &xdf->recs[g->end])) {
xdf->rchg[g->start++] = 0; xdf->changed[g->start++] = false;
xdf->rchg[g->end++] = 1; xdf->changed[g->end++] = true;


while (xdf->rchg[g->end]) while (xdf->changed[g->end])
g->end++; g->end++;


return 0; return 0;
@ -785,11 +773,11 @@ static int group_slide_down(xdfile_t *xdf, struct xdlgroup *g)
static int group_slide_up(xdfile_t *xdf, struct xdlgroup *g) static int group_slide_up(xdfile_t *xdf, struct xdlgroup *g)
{ {
if (g->start > 0 && if (g->start > 0 &&
recs_match(xdf->recs[g->start - 1], xdf->recs[g->end - 1])) { recs_match(&xdf->recs[g->start - 1], &xdf->recs[g->end - 1])) {
xdf->rchg[--g->start] = 1; xdf->changed[--g->start] = true;
xdf->rchg[--g->end] = 0; xdf->changed[--g->end] = false;


while (xdf->rchg[g->start - 1]) while (xdf->changed[g->start - 1])
g->start--; g->start--;


return 0; return 0;
@ -944,16 +932,16 @@ int xdl_change_compact(xdfile_t *xdf, xdfile_t *xdfo, long flags) {


int xdl_build_script(xdfenv_t *xe, xdchange_t **xscr) { int xdl_build_script(xdfenv_t *xe, xdchange_t **xscr) {
xdchange_t *cscr = NULL, *xch; xdchange_t *cscr = NULL, *xch;
char *rchg1 = xe->xdf1.rchg, *rchg2 = xe->xdf2.rchg; bool *changed1 = xe->xdf1.changed, *changed2 = xe->xdf2.changed;
long i1, i2, l1, l2; long i1, i2, l1, l2;


/* /*
* Trivial. Collects "groups" of changes and creates an edit script. * Trivial. Collects "groups" of changes and creates an edit script.
*/ */
for (i1 = xe->xdf1.nrec, i2 = xe->xdf2.nrec; i1 >= 0 || i2 >= 0; i1--, i2--) for (i1 = xe->xdf1.nrec, i2 = xe->xdf2.nrec; i1 >= 0 || i2 >= 0; i1--, i2--)
if (rchg1[i1 - 1] || rchg2[i2 - 1]) { if (changed1[i1 - 1] || changed2[i2 - 1]) {
for (l1 = i1; rchg1[i1 - 1]; i1--); for (l1 = i1; changed1[i1 - 1]; i1--);
for (l2 = i2; rchg2[i2 - 1]; i2--); for (l2 = i2; changed2[i2 - 1]; i2--);


if (!(xch = xdl_add_change(cscr, i1, i2, l1 - i1, l2 - i2))) { if (!(xch = xdl_add_change(cscr, i1, i2, l1 - i1, l2 - i2))) {
xdl_free_script(cscr); xdl_free_script(cscr);
@ -1000,16 +988,16 @@ static void xdl_mark_ignorable_lines(xdchange_t *xscr, xdfenv_t *xe, long flags)


for (xch = xscr; xch; xch = xch->next) { for (xch = xscr; xch; xch = xch->next) {
int ignore = 1; int ignore = 1;
xrecord_t **rec; xrecord_t *rec;
long i; long i;


rec = &xe->xdf1.recs[xch->i1]; rec = &xe->xdf1.recs[xch->i1];
for (i = 0; i < xch->chg1 && ignore; i++) for (i = 0; i < xch->chg1 && ignore; i++)
ignore = xdl_blankline(rec[i]->ptr, rec[i]->size, flags); ignore = xdl_blankline(rec[i].ptr, rec[i].size, flags);


rec = &xe->xdf2.recs[xch->i2]; rec = &xe->xdf2.recs[xch->i2];
for (i = 0; i < xch->chg2 && ignore; i++) for (i = 0; i < xch->chg2 && ignore; i++)
ignore = xdl_blankline(rec[i]->ptr, rec[i]->size, flags); ignore = xdl_blankline(rec[i].ptr, rec[i].size, flags);


xch->ignore = ignore; xch->ignore = ignore;
} }
@ -1033,7 +1021,7 @@ static void xdl_mark_ignorable_regex(xdchange_t *xscr, const xdfenv_t *xe,
xdchange_t *xch; xdchange_t *xch;


for (xch = xscr; xch; xch = xch->next) { for (xch = xscr; xch; xch = xch->next) {
xrecord_t **rec; xrecord_t *rec;
int ignore = 1; int ignore = 1;
long i; long i;


@ -1045,11 +1033,11 @@ static void xdl_mark_ignorable_regex(xdchange_t *xscr, const xdfenv_t *xe,


rec = &xe->xdf1.recs[xch->i1]; rec = &xe->xdf1.recs[xch->i1];
for (i = 0; i < xch->chg1 && ignore; i++) for (i = 0; i < xch->chg1 && ignore; i++)
ignore = record_matches_regex(rec[i], xpp); ignore = record_matches_regex(&rec[i], xpp);


rec = &xe->xdf2.recs[xch->i2]; rec = &xe->xdf2.recs[xch->i2];
for (i = 0; i < xch->chg2 && ignore; i++) for (i = 0; i < xch->chg2 && ignore; i++)
ignore = record_matches_regex(rec[i], xpp); ignore = record_matches_regex(&rec[i], xpp);


xch->ignore = ignore; xch->ignore = ignore;
} }

11
xdiff/xdiffi.h
View File

@ -24,13 +24,6 @@
#define XDIFFI_H #define XDIFFI_H




typedef struct s_diffdata {
long nrec;
unsigned long const *ha;
long *rindex;
char *rchg;
} diffdata_t;

typedef struct s_xdalgoenv { typedef struct s_xdalgoenv {
long mxcost; long mxcost;
long snake_cnt; long snake_cnt;
@ -46,8 +39,8 @@ typedef struct s_xdchange {






int xdl_recs_cmp(diffdata_t *dd1, long off1, long lim1, int xdl_recs_cmp(xdfile_t *xdf1, long off1, long lim1,
diffdata_t *dd2, long off2, long lim2, xdfile_t *xdf2, long off2, long lim2,
long *kvdf, long *kvdb, int need_min, xdalgoenv_t *xenv); long *kvdf, long *kvdb, int need_min, xdalgoenv_t *xenv);
int xdl_do_diff(mmfile_t *mf1, mmfile_t *mf2, xpparam_t const *xpp, int xdl_do_diff(mmfile_t *mf1, mmfile_t *mf2, xpparam_t const *xpp,
xdfenv_t *xe); xdfenv_t *xe);

38
xdiff/xemit.c
View File

@ -22,23 +22,13 @@


#include "xinclude.h" #include "xinclude.h"


static long xdl_get_rec(xdfile_t *xdf, long ri, char const **rec) {


*rec = xdf->recs[ri]->ptr; static int xdl_emit_record(xdfile_t *xdf, long ri, char const *pre, xdemitcb_t *ecb)

{
return xdf->recs[ri]->size; xrecord_t *rec = &xdf->recs[ri];
}


static int xdl_emit_record(xdfile_t *xdf, long ri, char const *pre, xdemitcb_t *ecb) {
long size, psize = strlen(pre);
char const *rec;

size = xdl_get_rec(xdf, ri, &rec);
if (xdl_emit_diffrec(rec, size, pre, psize, ecb) < 0) {


if (xdl_emit_diffrec(rec->ptr, rec->size, pre, strlen(pre), ecb) < 0)
return -1; return -1;
}


return 0; return 0;
} }
@ -120,11 +110,11 @@ static long def_ff(const char *rec, long len, char *buf, long sz)
static long match_func_rec(xdfile_t *xdf, xdemitconf_t const *xecfg, long ri, static long match_func_rec(xdfile_t *xdf, xdemitconf_t const *xecfg, long ri,
char *buf, long sz) char *buf, long sz)
{ {
const char *rec; xrecord_t *rec = &xdf->recs[ri];
long len = xdl_get_rec(xdf, ri, &rec);
if (!xecfg->find_func) if (!xecfg->find_func)
return def_ff(rec, len, buf, sz); return def_ff(rec->ptr, rec->size, buf, sz);
return xecfg->find_func(rec, len, buf, sz, xecfg->find_func_priv); return xecfg->find_func(rec->ptr, rec->size, buf, sz, xecfg->find_func_priv);
} }


static int is_func_rec(xdfile_t *xdf, xdemitconf_t const *xecfg, long ri) static int is_func_rec(xdfile_t *xdf, xdemitconf_t const *xecfg, long ri)
@ -160,14 +150,12 @@ static long get_func_line(xdfenv_t *xe, xdemitconf_t const *xecfg,


static int is_empty_rec(xdfile_t *xdf, long ri) static int is_empty_rec(xdfile_t *xdf, long ri)
{ {
const char *rec; xrecord_t *rec = &xdf->recs[ri];
long len = xdl_get_rec(xdf, ri, &rec); long i = 0;


while (len > 0 && XDL_ISSPACE(*rec)) { for (; i < rec->size && XDL_ISSPACE(rec->ptr[i]); i++);
rec++;
len--; return i == rec->size;
}
return !len;
} }


int xdl_emit_diff(xdfenv_t *xe, xdchange_t *xscr, xdemitcb_t *ecb, int xdl_emit_diff(xdfenv_t *xe, xdchange_t *xscr, xdemitcb_t *ecb,

10
xdiff/xhistogram.c
View File

@ -86,7 +86,7 @@ struct region {
((LINE_MAP(index, ptr))->cnt) ((LINE_MAP(index, ptr))->cnt)


#define REC(env, s, l) \ #define REC(env, s, l) \
(env->xdf##s.recs[l - 1]) (&env->xdf##s.recs[l - 1])


static int cmp_recs(xrecord_t *r1, xrecord_t *r2) static int cmp_recs(xrecord_t *r1, xrecord_t *r2)
{ {
@ -318,11 +318,11 @@ redo:


if (!count1) { if (!count1) {
while(count2--) while(count2--)
env->xdf2.rchg[line2++ - 1] = 1; env->xdf2.changed[line2++ - 1] = true;
return 0; return 0;
} else if (!count2) { } else if (!count2) {
while(count1--) while(count1--)
env->xdf1.rchg[line1++ - 1] = 1; env->xdf1.changed[line1++ - 1] = true;
return 0; return 0;
} }


@ -335,9 +335,9 @@ redo:
else { else {
if (lcs.begin1 == 0 && lcs.begin2 == 0) { if (lcs.begin1 == 0 && lcs.begin2 == 0) {
while (count1--) while (count1--)
env->xdf1.rchg[line1++ - 1] = 1; env->xdf1.changed[line1++ - 1] = true;
while (count2--) while (count2--)
env->xdf2.rchg[line2++ - 1] = 1; env->xdf2.changed[line2++ - 1] = true;
result = 0; result = 0;
} else { } else {
result = histogram_diff(xpp, env, result = histogram_diff(xpp, env,

56
xdiff/xmerge.c
View File

@ -97,12 +97,12 @@ static int xdl_merge_cmp_lines(xdfenv_t *xe1, int i1, xdfenv_t *xe2, int i2,
int line_count, long flags) int line_count, long flags)
{ {
int i; int i;
xrecord_t **rec1 = xe1->xdf2.recs + i1; xrecord_t *rec1 = xe1->xdf2.recs + i1;
xrecord_t **rec2 = xe2->xdf2.recs + i2; xrecord_t *rec2 = xe2->xdf2.recs + i2;


for (i = 0; i < line_count; i++) { for (i = 0; i < line_count; i++) {
int result = xdl_recmatch(rec1[i]->ptr, rec1[i]->size, int result = xdl_recmatch(rec1[i].ptr, rec1[i].size,
rec2[i]->ptr, rec2[i]->size, flags); rec2[i].ptr, rec2[i].size, flags);
if (!result) if (!result)
return -1; return -1;
} }
@ -111,7 +111,7 @@ static int xdl_merge_cmp_lines(xdfenv_t *xe1, int i1, xdfenv_t *xe2, int i2,


static int xdl_recs_copy_0(int use_orig, xdfenv_t *xe, int i, int count, int needs_cr, int add_nl, char *dest) static int xdl_recs_copy_0(int use_orig, xdfenv_t *xe, int i, int count, int needs_cr, int add_nl, char *dest)
{ {
xrecord_t **recs; xrecord_t *recs;
int size = 0; int size = 0;


recs = (use_orig ? xe->xdf1.recs : xe->xdf2.recs) + i; recs = (use_orig ? xe->xdf1.recs : xe->xdf2.recs) + i;
@ -119,12 +119,12 @@ static int xdl_recs_copy_0(int use_orig, xdfenv_t *xe, int i, int count, int nee
if (count < 1) if (count < 1)
return 0; return 0;


for (i = 0; i < count; size += recs[i++]->size) for (i = 0; i < count; size += recs[i++].size)
if (dest) if (dest)
memcpy(dest + size, recs[i]->ptr, recs[i]->size); memcpy(dest + size, recs[i].ptr, recs[i].size);
if (add_nl) { if (add_nl) {
i = recs[count - 1]->size; i = recs[count - 1].size;
if (i == 0 || recs[count - 1]->ptr[i - 1] != '\n') { if (i == 0 || recs[count - 1].ptr[i - 1] != '\n') {
if (needs_cr) { if (needs_cr) {
if (dest) if (dest)
dest[size] = '\r'; dest[size] = '\r';
@ -160,22 +160,22 @@ static int is_eol_crlf(xdfile_t *file, int i)


if (i < file->nrec - 1) if (i < file->nrec - 1)
/* All lines before the last *must* end in LF */ /* All lines before the last *must* end in LF */
return (size = file->recs[i]->size) > 1 && return (size = file->recs[i].size) > 1 &&
file->recs[i]->ptr[size - 2] == '\r'; file->recs[i].ptr[size - 2] == '\r';
if (!file->nrec) if (!file->nrec)
/* Cannot determine eol style from empty file */ /* Cannot determine eol style from empty file */
return -1; return -1;
if ((size = file->recs[i]->size) && if ((size = file->recs[i].size) &&
file->recs[i]->ptr[size - 1] == '\n') file->recs[i].ptr[size - 1] == '\n')
/* Last line; ends in LF; Is it CR/LF? */ /* Last line; ends in LF; Is it CR/LF? */
return size > 1 && return size > 1 &&
file->recs[i]->ptr[size - 2] == '\r'; file->recs[i].ptr[size - 2] == '\r';
if (!i) if (!i)
/* The only line has no eol */ /* The only line has no eol */
return -1; return -1;
/* Determine eol from second-to-last line */ /* Determine eol from second-to-last line */
return (size = file->recs[i - 1]->size) > 1 && return (size = file->recs[i - 1].size) > 1 &&
file->recs[i - 1]->ptr[size - 2] == '\r'; file->recs[i - 1].ptr[size - 2] == '\r';
} }


static int is_cr_needed(xdfenv_t *xe1, xdfenv_t *xe2, xdmerge_t *m) static int is_cr_needed(xdfenv_t *xe1, xdfenv_t *xe2, xdmerge_t *m)
@ -334,22 +334,22 @@ static int recmatch(xrecord_t *rec1, xrecord_t *rec2, unsigned long flags)
static void xdl_refine_zdiff3_conflicts(xdfenv_t *xe1, xdfenv_t *xe2, xdmerge_t *m, static void xdl_refine_zdiff3_conflicts(xdfenv_t *xe1, xdfenv_t *xe2, xdmerge_t *m,
xpparam_t const *xpp) xpparam_t const *xpp)
{ {
xrecord_t **rec1 = xe1->xdf2.recs, **rec2 = xe2->xdf2.recs; xrecord_t *rec1 = xe1->xdf2.recs, *rec2 = xe2->xdf2.recs;
for (; m; m = m->next) { for (; m; m = m->next) {
/* let's handle just the conflicts */ /* let's handle just the conflicts */
if (m->mode) if (m->mode)
continue; continue;


while(m->chg1 && m->chg2 && while(m->chg1 && m->chg2 &&
recmatch(rec1[m->i1], rec2[m->i2], xpp->flags)) { recmatch(&rec1[m->i1], &rec2[m->i2], xpp->flags)) {
m->chg1--; m->chg1--;
m->chg2--; m->chg2--;
m->i1++; m->i1++;
m->i2++; m->i2++;
} }
while (m->chg1 && m->chg2 && while (m->chg1 && m->chg2 &&
recmatch(rec1[m->i1 + m->chg1 - 1], recmatch(&rec1[m->i1 + m->chg1 - 1],
rec2[m->i2 + m->chg2 - 1], xpp->flags)) { &rec2[m->i2 + m->chg2 - 1], xpp->flags)) {
m->chg1--; m->chg1--;
m->chg2--; m->chg2--;
} }
@ -381,12 +381,12 @@ static int xdl_refine_conflicts(xdfenv_t *xe1, xdfenv_t *xe2, xdmerge_t *m,
* This probably does not work outside git, since * This probably does not work outside git, since
* we have a very simple mmfile structure. * we have a very simple mmfile structure.
*/ */
t1.ptr = (char *)xe1->xdf2.recs[m->i1]->ptr; t1.ptr = (char *)xe1->xdf2.recs[m->i1].ptr;
t1.size = xe1->xdf2.recs[m->i1 + m->chg1 - 1]->ptr t1.size = xe1->xdf2.recs[m->i1 + m->chg1 - 1].ptr
+ xe1->xdf2.recs[m->i1 + m->chg1 - 1]->size - t1.ptr; + xe1->xdf2.recs[m->i1 + m->chg1 - 1].size - t1.ptr;
t2.ptr = (char *)xe2->xdf2.recs[m->i2]->ptr; t2.ptr = (char *)xe2->xdf2.recs[m->i2].ptr;
t2.size = xe2->xdf2.recs[m->i2 + m->chg2 - 1]->ptr t2.size = xe2->xdf2.recs[m->i2 + m->chg2 - 1].ptr
+ xe2->xdf2.recs[m->i2 + m->chg2 - 1]->size - t2.ptr; + xe2->xdf2.recs[m->i2 + m->chg2 - 1].size - t2.ptr;
if (xdl_do_diff(&t1, &t2, xpp, &xe) < 0) if (xdl_do_diff(&t1, &t2, xpp, &xe) < 0)
return -1; return -1;
if (xdl_change_compact(&xe.xdf1, &xe.xdf2, xpp->flags) < 0 || if (xdl_change_compact(&xe.xdf1, &xe.xdf2, xpp->flags) < 0 ||
@ -440,8 +440,8 @@ static int line_contains_alnum(const char *ptr, long size)
static int lines_contain_alnum(xdfenv_t *xe, int i, int chg) static int lines_contain_alnum(xdfenv_t *xe, int i, int chg)
{ {
for (; chg; chg--, i++) for (; chg; chg--, i++)
if (line_contains_alnum(xe->xdf2.recs[i]->ptr, if (line_contains_alnum(xe->xdf2.recs[i].ptr,
xe->xdf2.recs[i]->size)) xe->xdf2.recs[i].size))
return 1; return 1;
return 0; return 0;
} }

18
xdiff/xpatience.c
View File

@ -88,9 +88,9 @@ static int is_anchor(xpparam_t const *xpp, const char *line)
static void insert_record(xpparam_t const *xpp, int line, struct hashmap *map, static void insert_record(xpparam_t const *xpp, int line, struct hashmap *map,
int pass) int pass)
{ {
xrecord_t **records = pass == 1 ? xrecord_t *records = pass == 1 ?
map->env->xdf1.recs : map->env->xdf2.recs; map->env->xdf1.recs : map->env->xdf2.recs;
xrecord_t *record = records[line - 1]; xrecord_t *record = &records[line - 1];
/* /*
* After xdl_prepare_env() (or more precisely, due to * After xdl_prepare_env() (or more precisely, due to
* xdl_classify_record()), the "ha" member of the records (AKA lines) * xdl_classify_record()), the "ha" member of the records (AKA lines)
@ -121,7 +121,7 @@ static void insert_record(xpparam_t const *xpp, int line, struct hashmap *map,
return; return;
map->entries[index].line1 = line; map->entries[index].line1 = line;
map->entries[index].hash = record->ha; map->entries[index].hash = record->ha;
map->entries[index].anchor = is_anchor(xpp, map->env->xdf1.recs[line - 1]->ptr); map->entries[index].anchor = is_anchor(xpp, map->env->xdf1.recs[line - 1].ptr);
if (!map->first) if (!map->first)
map->first = map->entries + index; map->first = map->entries + index;
if (map->last) { if (map->last) {
@ -246,8 +246,8 @@ static int find_longest_common_sequence(struct hashmap *map, struct entry **res)


static int match(struct hashmap *map, int line1, int line2) static int match(struct hashmap *map, int line1, int line2)
{ {
xrecord_t *record1 = map->env->xdf1.recs[line1 - 1]; xrecord_t *record1 = &map->env->xdf1.recs[line1 - 1];
xrecord_t *record2 = map->env->xdf2.recs[line2 - 1]; xrecord_t *record2 = &map->env->xdf2.recs[line2 - 1];
return record1->ha == record2->ha; return record1->ha == record2->ha;
} }


@ -331,11 +331,11 @@ static int patience_diff(xpparam_t const *xpp, xdfenv_t *env,
/* trivial case: one side is empty */ /* trivial case: one side is empty */
if (!count1) { if (!count1) {
while(count2--) while(count2--)
env->xdf2.rchg[line2++ - 1] = 1; env->xdf2.changed[line2++ - 1] = true;
return 0; return 0;
} else if (!count2) { } else if (!count2) {
while(count1--) while(count1--)
env->xdf1.rchg[line1++ - 1] = 1; env->xdf1.changed[line1++ - 1] = true;
return 0; return 0;
} }


@ -347,9 +347,9 @@ static int patience_diff(xpparam_t const *xpp, xdfenv_t *env,
/* are there any matching lines at all? */ /* are there any matching lines at all? */
if (!map.has_matches) { if (!map.has_matches) {
while(count1--) while(count1--)
env->xdf1.rchg[line1++ - 1] = 1; env->xdf1.changed[line1++ - 1] = true;
while(count2--) while(count2--)
env->xdf2.rchg[line2++ - 1] = 1; env->xdf2.changed[line2++ - 1] = true;
xdl_free(map.entries); xdl_free(map.entries);
return 0; return 0;
} }

470
xdiff/xprepare.c
View File

@ -29,12 +29,13 @@
#define XDL_GUESS_NLINES1 256 #define XDL_GUESS_NLINES1 256
#define XDL_GUESS_NLINES2 20 #define XDL_GUESS_NLINES2 20


#define DISCARD 0
#define KEEP 1
#define INVESTIGATE 2


typedef struct s_xdlclass { typedef struct s_xdlclass {
struct s_xdlclass *next; struct s_xdlclass *next;
unsigned long ha; xrecord_t rec;
char const *line;
long size;
long idx; long idx;
long len1, len2; long len1, len2;
} xdlclass_t; } xdlclass_t;
@ -53,21 +54,6 @@ typedef struct s_xdlclassifier {






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) { static int xdl_init_classifier(xdlclassifier_t *cf, long size, long flags) {
cf->flags = flags; cf->flags = flags;


@ -106,17 +92,14 @@ static void xdl_free_classifier(xdlclassifier_t *cf) {
} }




static int xdl_classify_record(unsigned int pass, xdlclassifier_t *cf, xrecord_t **rhash, static int xdl_classify_record(unsigned int pass, xdlclassifier_t *cf, xrecord_t *rec) {
unsigned int hbits, xrecord_t *rec) {
long hi; long hi;
char const *line;
xdlclass_t *rcrec; xdlclass_t *rcrec;


line = rec->ptr;
hi = (long) XDL_HASHLONG(rec->ha, cf->hbits); hi = (long) XDL_HASHLONG(rec->ha, cf->hbits);
for (rcrec = cf->rchash[hi]; rcrec; rcrec = rcrec->next) for (rcrec = cf->rchash[hi]; rcrec; rcrec = rcrec->next)
if (rcrec->ha == rec->ha && if (rcrec->rec.ha == rec->ha &&
xdl_recmatch(rcrec->line, rcrec->size, xdl_recmatch(rcrec->rec.ptr, rcrec->rec.size,
rec->ptr, rec->size, cf->flags)) rec->ptr, rec->size, cf->flags))
break; break;


@ -129,9 +112,7 @@ static int xdl_classify_record(unsigned int pass, xdlclassifier_t *cf, xrecord_t
if (XDL_ALLOC_GROW(cf->rcrecs, cf->count, cf->alloc)) if (XDL_ALLOC_GROW(cf->rcrecs, cf->count, cf->alloc))
return -1; return -1;
cf->rcrecs[rcrec->idx] = rcrec; cf->rcrecs[rcrec->idx] = rcrec;
rcrec->line = line; rcrec->rec = *rec;
rcrec->size = rec->size;
rcrec->ha = rec->ha;
rcrec->len1 = rcrec->len2 = 0; rcrec->len1 = rcrec->len2 = 0;
rcrec->next = cf->rchash[hi]; rcrec->next = cf->rchash[hi];
cf->rchash[hi] = rcrec; cf->rchash[hi] = rcrec;
@ -141,107 +122,263 @@ static int xdl_classify_record(unsigned int pass, xdlclassifier_t *cf, xrecord_t


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


hi = (long) XDL_HASHLONG(rec->ha, hbits);
rec->next = rhash[hi];
rhash[hi] = rec;

return 0; return 0;
} }




static void xdl_free_ctx(xdfile_t *xdf)
{
xdl_free(xdf->rindex);
xdl_free(xdf->changed - 1);
xdl_free(xdf->recs);
}


static int xdl_prepare_ctx(unsigned int pass, mmfile_t *mf, long narec, xpparam_t const *xpp, static int xdl_prepare_ctx(unsigned int pass, mmfile_t *mf, long narec, xpparam_t const *xpp,
xdlclassifier_t *cf, xdfile_t *xdf) { xdlclassifier_t *cf, xdfile_t *xdf) {
unsigned int hbits; long bsize;
long nrec, hsize, bsize;
unsigned long hav; unsigned long hav;
char const *blk, *cur, *top, *prev; char const *blk, *cur, *top, *prev;
xrecord_t *crec; xrecord_t *crec;
xrecord_t **recs;
xrecord_t **rhash;
unsigned long *ha;
char *rchg;
long *rindex;


ha = NULL; xdf->rindex = NULL;
rindex = NULL; xdf->changed = NULL;
rchg = NULL; xdf->recs = NULL;
rhash = NULL;
recs = NULL;


if (xdl_cha_init(&xdf->rcha, sizeof(xrecord_t), narec / 4 + 1) < 0) if (!XDL_ALLOC_ARRAY(xdf->recs, narec))
goto abort;
if (!XDL_ALLOC_ARRAY(recs, narec))
goto abort; goto abort;


hbits = xdl_hashbits((unsigned int) narec); xdf->nrec = 0;
hsize = 1 << hbits;
if (!XDL_CALLOC_ARRAY(rhash, hsize))
goto abort;

nrec = 0;
if ((cur = blk = xdl_mmfile_first(mf, &bsize))) { if ((cur = blk = xdl_mmfile_first(mf, &bsize))) {
for (top = blk + bsize; cur < top; ) { for (top = blk + bsize; cur < top; ) {
prev = cur; prev = cur;
hav = xdl_hash_record(&cur, top, xpp->flags); hav = xdl_hash_record(&cur, top, xpp->flags);
if (XDL_ALLOC_GROW(recs, nrec + 1, narec)) if (XDL_ALLOC_GROW(xdf->recs, xdf->nrec + 1, narec))
goto abort;
if (!(crec = xdl_cha_alloc(&xdf->rcha)))
goto abort; goto abort;
crec = &xdf->recs[xdf->nrec++];
crec->ptr = prev; crec->ptr = prev;
crec->size = (long) (cur - prev); crec->size = (long) (cur - prev);
crec->ha = hav; crec->ha = hav;
recs[nrec++] = crec; if (xdl_classify_record(pass, cf, crec) < 0)
if (xdl_classify_record(pass, cf, rhash, hbits, crec) < 0)
goto abort; goto abort;
} }
} }


if (!XDL_CALLOC_ARRAY(rchg, nrec + 2)) if (!XDL_CALLOC_ARRAY(xdf->changed, xdf->nrec + 2))
goto abort; goto abort;


if ((XDF_DIFF_ALG(xpp->flags) != XDF_PATIENCE_DIFF) && if ((XDF_DIFF_ALG(xpp->flags) != XDF_PATIENCE_DIFF) &&
(XDF_DIFF_ALG(xpp->flags) != XDF_HISTOGRAM_DIFF)) { (XDF_DIFF_ALG(xpp->flags) != XDF_HISTOGRAM_DIFF)) {
if (!XDL_ALLOC_ARRAY(rindex, nrec + 1)) if (!XDL_ALLOC_ARRAY(xdf->rindex, xdf->nrec + 1))
goto abort;
if (!XDL_ALLOC_ARRAY(ha, nrec + 1))
goto abort; goto abort;
} }


xdf->nrec = nrec; xdf->changed += 1;
xdf->recs = recs;
xdf->hbits = hbits;
xdf->rhash = rhash;
xdf->rchg = rchg + 1;
xdf->rindex = rindex;
xdf->nreff = 0; xdf->nreff = 0;
xdf->ha = ha;
xdf->dstart = 0; xdf->dstart = 0;
xdf->dend = nrec - 1; xdf->dend = xdf->nrec - 1;


return 0; return 0;


abort: abort:
xdl_free(ha); xdl_free_ctx(xdf);
xdl_free(rindex);
xdl_free(rchg);
xdl_free(rhash);
xdl_free(recs);
xdl_cha_free(&xdf->rcha);
return -1; return -1;
} }




static void xdl_free_ctx(xdfile_t *xdf) { void xdl_free_env(xdfenv_t *xe) {


xdl_free(xdf->rhash); xdl_free_ctx(&xe->xdf2);
xdl_free(xdf->rindex); xdl_free_ctx(&xe->xdf1);
xdl_free(xdf->rchg - 1);
xdl_free(xdf->ha);
xdl_free(xdf->recs);
xdl_cha_free(&xdf->rcha);
} }




static bool xdl_clean_mmatch(uint8_t const *action, long i, long s, long e) {
long r, rdis0, rpdis0, rdis1, rpdis1;

/*
* Limits the window that is examined during the similar-lines
* scan. The loops below stops when action[i - r] == KEEP
* (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 (action[j] == DISCARD) or have multiple matches
* (action[j] == INVESTIGATE). Note that we always call this
* function with action[i] == INVESTIGATE, so the current line
* (i) is already a multimatch line.
*/
for (r = 1, rdis0 = 0, rpdis0 = 1; (i - r) >= s; r++) {
if (action[i - r] == DISCARD)
rdis0++;
else if (action[i - r] == INVESTIGATE)
rpdis0++;
else if (action[i - r] == KEEP)
break;
else
BUG("Illegal value for action[i - r]");
}
/*
* If the run before the line 'i' found only multimatch lines,
* we return false 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
* (action[j] == DISCARD).
*/
if (rdis0 == 0)
return 0;
for (r = 1, rdis1 = 0, rpdis1 = 1; (i + r) <= e; r++) {
if (action[i + r] == DISCARD)
rdis1++;
else if (action[i + r] == INVESTIGATE)
rpdis1++;
else if (action[i + r] == KEEP)
break;
else
BUG("Illegal value for action[i + r]");
}
/*
* If the run after the line 'i' found only multimatch lines,
* we return false and hence we don't make the current line (i)
* discarded.
*/
if (rdis1 == 0)
return false;
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 appear 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;
uint8_t *action1 = NULL, *action2 = NULL;
bool need_min = !!(cf->flags & XDF_NEED_MINIMAL);
int ret = 0;

/*
* Create temporary arrays that will help us decide if
* changed[i] should remain false, or become true.
*/
if (!XDL_CALLOC_ARRAY(action1, xdf1->nrec + 1)) {
ret = -1;
goto cleanup;
}
if (!XDL_CALLOC_ARRAY(action2, xdf2->nrec + 1)) {
ret = -1;
goto cleanup;
}

/*
* Initialize temporary arrays with DISCARD, KEEP, or INVESTIGATE.
*/
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;
action1[i] = (nm == 0) ? DISCARD: (nm >= mlim && !need_min) ? INVESTIGATE: KEEP;
}

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;
action2[i] = (nm == 0) ? DISCARD: (nm >= mlim && !need_min) ? INVESTIGATE: KEEP;
}

/*
* Use temporary arrays to decide if changed[i] should remain
* false, or become true.
*/
for (nreff = 0, i = xdf1->dstart, recs = &xdf1->recs[xdf1->dstart];
i <= xdf1->dend; i++, recs++) {
if (action1[i] == KEEP ||
(action1[i] == INVESTIGATE && !xdl_clean_mmatch(action1, i, xdf1->dstart, xdf1->dend))) {
xdf1->rindex[nreff++] = i;
/* changed[i] remains false, i.e. keep */
} else
xdf1->changed[i] = true;
/* i.e. discard */
}
xdf1->nreff = nreff;

for (nreff = 0, i = xdf2->dstart, recs = &xdf2->recs[xdf2->dstart];
i <= xdf2->dend; i++, recs++) {
if (action2[i] == KEEP ||
(action2[i] == INVESTIGATE && !xdl_clean_mmatch(action2, i, xdf2->dstart, xdf2->dend))) {
xdf2->rindex[nreff++] = i;
/* changed[i] remains false, i.e. keep */
} else
xdf2->changed[i] = true;
/* i.e. discard */
}
xdf2->nreff = nreff;

cleanup:
xdl_free(action1);
xdl_free(action2);

return ret;
}


/*
* 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;
}

int xdl_prepare_env(mmfile_t *mf1, mmfile_t *mf2, xpparam_t const *xpp, int xdl_prepare_env(mmfile_t *mf1, mmfile_t *mf2, xpparam_t const *xpp,
xdfenv_t *xe) { xdfenv_t *xe) {
long enl1, enl2, sample; long enl1, enl2, sample;
@ -291,172 +428,3 @@ int xdl_prepare_env(mmfile_t *mf1, mmfile_t *mf2, xpparam_t const *xpp,


return 0; 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;
int need_min = !!(cf->flags & XDF_NEED_MINIMAL);

if (!XDL_CALLOC_ARRAY(dis, xdf1->nrec + xdf2->nrec + 2))
return -1;
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 && !need_min) ? 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 && !need_min) ? 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;
}

9
xdiff/xtypes.h
View File

@ -39,23 +39,18 @@ typedef struct s_chastore {
} chastore_t; } chastore_t;


typedef struct s_xrecord { typedef struct s_xrecord {
struct s_xrecord *next;
char const *ptr; char const *ptr;
long size; long size;
unsigned long ha; unsigned long ha;
} xrecord_t; } xrecord_t;


typedef struct s_xdfile { typedef struct s_xdfile {
chastore_t rcha; xrecord_t *recs;
long nrec; long nrec;
unsigned int hbits;
xrecord_t **rhash;
long dstart, dend; long dstart, dend;
xrecord_t **recs; bool *changed;
char *rchg;
long *rindex; long *rindex;
long nreff; long nreff;
unsigned long *ha;
} xdfile_t; } xdfile_t;


typedef struct s_xdfenv { typedef struct s_xdfenv {

16
xdiff/xutils.c
View File

@ -464,17 +464,17 @@ int xdl_fall_back_diff(xdfenv_t *diff_env, xpparam_t const *xpp,
mmfile_t subfile1, subfile2; mmfile_t subfile1, subfile2;
xdfenv_t env; xdfenv_t env;


subfile1.ptr = (char *)diff_env->xdf1.recs[line1 - 1]->ptr; subfile1.ptr = (char *)diff_env->xdf1.recs[line1 - 1].ptr;
subfile1.size = diff_env->xdf1.recs[line1 + count1 - 2]->ptr + subfile1.size = diff_env->xdf1.recs[line1 + count1 - 2].ptr +
diff_env->xdf1.recs[line1 + count1 - 2]->size - subfile1.ptr; diff_env->xdf1.recs[line1 + count1 - 2].size - subfile1.ptr;
subfile2.ptr = (char *)diff_env->xdf2.recs[line2 - 1]->ptr; subfile2.ptr = (char *)diff_env->xdf2.recs[line2 - 1].ptr;
subfile2.size = diff_env->xdf2.recs[line2 + count2 - 2]->ptr + subfile2.size = diff_env->xdf2.recs[line2 + count2 - 2].ptr +
diff_env->xdf2.recs[line2 + count2 - 2]->size - subfile2.ptr; diff_env->xdf2.recs[line2 + count2 - 2].size - subfile2.ptr;
if (xdl_do_diff(&subfile1, &subfile2, xpp, &env) < 0) if (xdl_do_diff(&subfile1, &subfile2, xpp, &env) < 0)
return -1; return -1;


memcpy(diff_env->xdf1.rchg + line1 - 1, env.xdf1.rchg, count1); memcpy(diff_env->xdf1.changed + line1 - 1, env.xdf1.changed, count1);
memcpy(diff_env->xdf2.rchg + line2 - 1, env.xdf2.rchg, count2); memcpy(diff_env->xdf2.changed + line2 - 1, env.xdf2.changed, count2);


xdl_free_env(&env); xdl_free_env(&env);