averello/vim-mirror
1
0
Fork 0
mirror of https://github.com/vim/vim.git synced 2025-12-18 12:01:36 +01:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'xdiff-new' into xdiff-upstream-v2.52.0

Browse Source
This commit is contained in:
Yee Cheng Chin
2025-11-17 16:26:15 -08:00
parent c4f8b15dd9 d741f0e230
commit d353c6f2c8
11 changed files with 409 additions and 401 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/xdiff/xdiff.h
View File

@@ -87,7 +87,7 @@ typedef struct s_xpparam {
size_t ignore_regex_nr;
#endif
/* See Documentation/diff-options.txt. */
/* See Documentation/diff-options.adoc. */
char **anchors;
size_t anchors_nr;
} xpparam_t;

118
src/xdiff/xdiffi.c
View File

@@ -22,6 +22,11 @@
#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_HEUR_MIN_COST 256
#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
* search and to return a suboptimal point.
*/
static long xdl_split(unsigned long const *ha1, long off1, long lim1,
unsigned long const *ha2, long off2, long lim2,
static long xdl_split(xdfile_t *xdf1, long off1, long lim1,
xdfile_t *xdf2, long off2, long lim2,
long *kvdf, long *kvdb, int need_min, xdpsplit_t *spl,
xdalgoenv_t *xenv) {
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];
prev1 = i1;
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)
got_snake = 1;
kvdf[d] = i1;
@@ -124,7 +129,7 @@ static long xdl_split(unsigned long const *ha1, long off1, long lim1,
i1 = kvdb[d + 1] - 1;
prev1 = i1;
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)
got_snake = 1;
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 &&
off1 + xenv->snake_cnt <= i1 && i1 < lim1 &&
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) {
best = v;
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 &&
off1 < i1 && i1 <= lim1 - 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) {
best = v;
spl->i1 = i1;
@@ -211,8 +216,10 @@ static long xdl_split(unsigned long const *ha1, long off1, long lim1,
for (d = fmax; d >= fmin; d -= 2) {
i1 = XDL_MIN(kvdf[d], lim1);
i2 = i1 - d;
if (lim2 < i2)
i1 = lim2 + d, i2 = lim2;
if (lim2 < i2) {
i1 = lim2 + d;
i2 = lim2;
}
if (fbest < i1 + i2) {
fbest = i1 + i2;
fbest1 = i1;
@@ -223,8 +230,10 @@ static long xdl_split(unsigned long const *ha1, long off1, long lim1,
for (d = bmax; d >= bmin; d -= 2) {
i1 = XDL_MAX(off1, kvdb[d]);
i2 = i1 - d;
if (i2 < off2)
i1 = off2 + d, i2 = off2;
if (i2 < off2) {
i1 = off2 + d;
i2 = off2;
}
if (i1 + i2 < bbest) {
bbest = i1 + i2;
bbest1 = i1;
@@ -253,33 +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
* (marking changed lines) is done in the two boundary reaching checks.
*/
int xdl_recs_cmp(diffdata_t *dd1, long off1, long lim1,
diffdata_t *dd2, long off2, long lim2,
int xdl_recs_cmp(xdfile_t *xdf1, long off1, long lim1,
xdfile_t *xdf2, long off2, long lim2,
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).
*/
for (; off1 < lim1 && off2 < lim2 && ha1[off1] == ha2[off2]; off1++, off2++);
for (; off1 < lim1 && off2 < lim2 && ha1[lim1 - 1] == ha2[lim2 - 1]; lim1--, lim2--);
for (; off1 < lim1 && off2 < lim2 && get_hash(xdf1, off1) == get_hash(xdf2, off2); off1++, off2++);
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
* be obviously changed.
*/
if (off1 == lim1) {
char *rchg2 = dd2->rchg;
long *rindex2 = dd2->rindex;
for (; off2 < lim2; off2++)
rchg2[rindex2[off2]] = 1;
xdf2->changed[xdf2->rindex[off2]] = true;
} else if (off2 == lim2) {
char *rchg1 = dd1->rchg;
long *rindex1 = dd1->rindex;
for (; off1 < lim1; off1++)
rchg1[rindex1[off1]] = 1;
xdf1->changed[xdf1->rindex[off1]] = true;
} else {
xdpsplit_t spl;
spl.i1 = spl.i2 = 0;
@@ -287,7 +289,7 @@ int xdl_recs_cmp(diffdata_t *dd1, long off1, long lim1,
/*
* 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) {
return -1;
@@ -296,9 +298,9 @@ int xdl_recs_cmp(diffdata_t *dd1, long off1, long lim1,
/*
* ... 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 ||
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) {
return -1;
@@ -314,7 +316,6 @@ int xdl_do_diff(mmfile_t *mf1, mmfile_t *mf2, xpparam_t const *xpp,
long ndiags;
long *kvd, *kvdf, *kvdb;
xdalgoenv_t xenv;
diffdata_t dd1, dd2;
int res;
if (xdl_prepare_env(mf1, mf2, xpp, xe) < 0)
@@ -353,16 +354,7 @@ int xdl_do_diff(mmfile_t *mf1, mmfile_t *mf2, xpparam_t const *xpp,
xenv.snake_cnt = XDL_SNAKE_CNT;
xenv.heur_min = XDL_HEUR_MIN_COST;
dd1.nrec = xe->xdf1.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,
res = xdl_recs_cmp(&xe->xdf1, 0, xe->xdf1.nreff, &xe->xdf2, 0, xe->xdf2.nreff,
kvdf, kvdb, (xpp->flags & XDF_NEED_MINIMAL) != 0,
&xenv);
xdl_free(kvd);
@@ -497,13 +489,13 @@ static void measure_split(const xdfile_t *xdf, long split,
m->indent = -1;
} else {
m->end_of_file = 0;
m->indent = xget_indent(xdf->recs[split]);
m->indent = xget_indent(&xdf->recs[split]);
}
m->pre_blank = 0;
m->pre_indent = -1;
for (i = split - 1; i >= 0; i--) {
m->pre_indent = xget_indent(xdf->recs[i]);
m->pre_indent = xget_indent(&xdf->recs[i]);
if (m->pre_indent != -1)
break;
m->pre_blank += 1;
@@ -516,7 +508,7 @@ static void measure_split(const xdfile_t *xdf, long split,
m->post_blank = 0;
m->post_indent = -1;
for (i = split + 1; i < xdf->nrec; i++) {
m->post_indent = xget_indent(xdf->recs[i]);
m->post_indent = xget_indent(&xdf->recs[i]);
if (m->post_indent != -1)
break;
m->post_blank += 1;
@@ -716,7 +708,7 @@ struct xdlgroup {
static void group_init(xdfile_t *xdf, struct xdlgroup *g)
{
g->start = g->end = 0;
while (xdf->rchg[g->end])
while (xdf->changed[g->end])
g->end++;
}
@@ -730,7 +722,7 @@ static inline int group_next(xdfile_t *xdf, struct xdlgroup *g)
return -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;
@@ -746,7 +738,7 @@ static inline int group_previous(xdfile_t *xdf, struct xdlgroup *g)
return -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;
@@ -760,11 +752,11 @@ static inline int group_previous(xdfile_t *xdf, struct xdlgroup *g)
static int group_slide_down(xdfile_t *xdf, struct xdlgroup *g)
{
if (g->end < xdf->nrec &&
recs_match(xdf->recs[g->start], xdf->recs[g->end])) {
xdf->rchg[g->start++] = 0;
xdf->rchg[g->end++] = 1;
recs_match(&xdf->recs[g->start], &xdf->recs[g->end])) {
xdf->changed[g->start++] = false;
xdf->changed[g->end++] = true;
while (xdf->rchg[g->end])
while (xdf->changed[g->end])
g->end++;
return 0;
@@ -781,11 +773,11 @@ static int group_slide_down(xdfile_t *xdf, struct xdlgroup *g)
static int group_slide_up(xdfile_t *xdf, struct xdlgroup *g)
{
if (g->start > 0 &&
recs_match(xdf->recs[g->start - 1], xdf->recs[g->end - 1])) {
xdf->rchg[--g->start] = 1;
xdf->rchg[--g->end] = 0;
recs_match(&xdf->recs[g->start - 1], &xdf->recs[g->end - 1])) {
xdf->changed[--g->start] = true;
xdf->changed[--g->end] = false;
while (xdf->rchg[g->start - 1])
while (xdf->changed[g->start - 1])
g->start--;
return 0;
@@ -794,7 +786,7 @@ static int group_slide_up(xdfile_t *xdf, struct xdlgroup *g)
}
}
static void xdl_bug(const char *msg)
void xdl_bug(const char *msg)
{
fprintf(stderr, "BUG: %s\n", msg);
exit(1);
@@ -946,16 +938,16 @@ int xdl_change_compact(xdfile_t *xdf, xdfile_t *xdfo, long flags) {
int xdl_build_script(xdfenv_t *xe, xdchange_t **xscr) {
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;
/*
* 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--)
if (rchg1[i1 - 1] || rchg2[i2 - 1]) {
for (l1 = i1; rchg1[i1 - 1]; i1--);
for (l2 = i2; rchg2[i2 - 1]; i2--);
if (changed1[i1 - 1] || changed2[i2 - 1]) {
for (l1 = i1; changed1[i1 - 1]; i1--);
for (l2 = i2; changed2[i2 - 1]; i2--);
if (!(xch = xdl_add_change(cscr, i1, i2, l1 - i1, l2 - i2))) {
xdl_free_script(cscr);
@@ -1002,16 +994,16 @@ static void xdl_mark_ignorable_lines(xdchange_t *xscr, xdfenv_t *xe, long flags)
for (xch = xscr; xch; xch = xch->next) {
int ignore = 1;
xrecord_t **rec;
xrecord_t *rec;
long i;
rec = &xe->xdf1.recs[xch->i1];
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];
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;
}
@@ -1020,7 +1012,7 @@ static void xdl_mark_ignorable_lines(xdchange_t *xscr, xdfenv_t *xe, long flags)
#if 0 // unused by Vim
static int record_matches_regex(xrecord_t *rec, xpparam_t const *xpp) {
regmatch_t regmatch;
int i;
size_t i;
for (i = 0; i < xpp->ignore_regex_nr; i++)
if (!regexec_buf(xpp->ignore_regex[i], rec->ptr, rec->size, 1,
@@ -1036,7 +1028,7 @@ static void xdl_mark_ignorable_regex(xdchange_t *xscr, const xdfenv_t *xe,
xdchange_t *xch;
for (xch = xscr; xch; xch = xch->next) {
xrecord_t **rec;
xrecord_t *rec;
int ignore = 1;
long i;
@@ -1048,11 +1040,11 @@ static void xdl_mark_ignorable_regex(xdchange_t *xscr, const xdfenv_t *xe,
rec = &xe->xdf1.recs[xch->i1];
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];
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;
}

11
src/xdiff/xdiffi.h
View File

@@ -24,13 +24,6 @@
#define XDIFFI_H
typedef struct s_diffdata {
long nrec;
unsigned long const *ha;
long *rindex;
char *rchg;
} diffdata_t;
typedef struct s_xdalgoenv {
long mxcost;
long snake_cnt;
@@ -46,8 +39,8 @@ typedef struct s_xdchange {
int xdl_recs_cmp(diffdata_t *dd1, long off1, long lim1,
diffdata_t *dd2, long off2, long lim2,
int xdl_recs_cmp(xdfile_t *xdf1, long off1, long lim1,
xdfile_t *xdf2, long off2, long lim2,
long *kvdf, long *kvdb, int need_min, xdalgoenv_t *xenv);
int xdl_do_diff(mmfile_t *mf1, mmfile_t *mf2, xpparam_t const *xpp,
xdfenv_t *xe);

55
src/xdiff/xemit.c
View File

@@ -22,27 +22,26 @@
#include "xinclude.h"
static long xdl_get_rec(xdfile_t *xdf, long ri, char const **rec) {
*rec = xdf->recs[ri]->ptr;
return xdf->recs[ri]->size;
}
static int xdl_emit_record(xdfile_t *xdf, long ri, char const *pre, xdemitcb_t *ecb) {
long size, psize = (long)strlen(pre);
char const *rec;
size = xdl_get_rec(xdf, ri, &rec);
if (xdl_emit_diffrec(rec, size, pre, psize, ecb) < 0) {
static int xdl_emit_record(xdfile_t *xdf, long ri, char const *pre, xdemitcb_t *ecb)
{
xrecord_t *rec = &xdf->recs[ri];
if (xdl_emit_diffrec(rec->ptr, rec->size, pre, (long)strlen(pre), ecb) < 0)
return -1;
}
return 0;
}
#define signed_add_overflows(a, b) \
((b) > LONG_MAX - (a))
static long saturating_add(long a, long b)
{
return signed_add_overflows(a, b) ? LONG_MAX : a + b;
}
#undef signed_add_overflows
/*
* Starting at the passed change atom, find the latest change atom to be included
@@ -52,9 +51,11 @@ static int xdl_emit_record(xdfile_t *xdf, long ri, char const *pre, xdemitcb_t *
xdchange_t *xdl_get_hunk(xdchange_t **xscr, xdemitconf_t const *xecfg)
{
xdchange_t *xch, *xchp, *lxch;
long max_common = 2 * xecfg->ctxlen + xecfg->interhunkctxlen;
long max_common = saturating_add(saturating_add(xecfg->ctxlen,
xecfg->ctxlen),
xecfg->interhunkctxlen);
long max_ignorable = xecfg->ctxlen;
unsigned long ignored = 0; /* number of ignored blank lines */
long ignored = 0; /* number of ignored blank lines */
/* remove ignorable changes that are too far before other changes */
for (xchp = *xscr; xchp && xchp->ignore; xchp = xchp->next) {
@@ -81,7 +82,7 @@ xdchange_t *xdl_get_hunk(xdchange_t **xscr, xdemitconf_t const *xecfg)
} else if (distance < max_ignorable && xch->ignore) {
ignored += xch->chg2;
} else if (lxch != xchp &&
xch->i1 + (long)ignored - (lxch->i1 + lxch->chg1) > max_common) {
xch->i1 + ignored - (lxch->i1 + lxch->chg1) > max_common) {
break;
} else if (!xch->ignore) {
lxch = xch;
@@ -117,11 +118,11 @@ 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,
char *buf, long sz)
{
const char *rec;
long len = xdl_get_rec(xdf, ri, &rec);
xrecord_t *rec = &xdf->recs[ri];
if (!xecfg->find_func)
return def_ff(rec, len, buf, sz);
return xecfg->find_func(rec, len, buf, sz, xecfg->find_func_priv);
return def_ff(rec->ptr, rec->size, buf, sz);
return xecfg->find_func(rec->ptr, rec->size, buf, sz, xecfg->find_func_priv);
}
#endif
@@ -163,14 +164,12 @@ static long get_func_line(xdfenv_t *xe, xdemitconf_t const *xecfg,
#if 0
static int is_empty_rec(xdfile_t *xdf, long ri)
{
const char *rec;
long len = xdl_get_rec(xdf, ri, &rec);
xrecord_t *rec = &xdf->recs[ri];
long i = 0;
while (len > 0 && XDL_ISSPACE(*rec)) {
rec++;
len--;
}
return !len;
for (; i < rec->size && XDL_ISSPACE(rec->ptr[i]); i++);
return i == rec->size;
}
#endif

24
src/xdiff/xhistogram.c
View File

@@ -43,8 +43,8 @@
#include "xinclude.h"
#define MAX_PTR INT_MAX
#define MAX_CNT INT_MAX
#define MAX_PTR UINT_MAX
#define MAX_CNT UINT_MAX
#define LINE_END(n) (line##n + count##n - 1)
#define LINE_END_PTR(n) (*line##n + *count##n - 1)
@@ -86,7 +86,7 @@ struct region {
((LINE_MAP(index, ptr))->cnt)
#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)
{
@@ -102,11 +102,11 @@ static int cmp_recs(xrecord_t *r1, xrecord_t *r2)
static int scanA(struct histindex *index, int line1, int count1)
{
int ptr, tbl_idx;
unsigned int ptr, tbl_idx;
unsigned int chain_len;
struct record **rec_chain, *rec;
for (ptr = LINE_END(1); line1 <= ptr; ptr--) {
for (ptr = LINE_END(1); (unsigned int)line1 <= ptr; ptr--) {
tbl_idx = TABLE_HASH(index, 1, ptr);
rec_chain = index->records + tbl_idx;
rec = *rec_chain;
@@ -181,14 +181,14 @@ static int try_lcs(struct histindex *index, struct region *lcs, int b_ptr,
be = bs;
rc = rec->cnt;
while (line1 < (int)as && line2 < (int)bs
while ((unsigned int)line1 < as && (unsigned int)line2 < bs
&& CMP(index, 1, as - 1, 2, bs - 1)) {
as--;
bs--;
if (1 < rc)
rc = XDL_MIN(rc, CNT(index, as));
}
while ((int)ae < LINE_END(1) && (int)be < LINE_END(2)
while (ae < (unsigned int)LINE_END(1) && be < (unsigned int)LINE_END(2)
&& CMP(index, 1, ae + 1, 2, be + 1)) {
ae++;
be++;
@@ -313,16 +313,16 @@ redo:
if (count1 <= 0 && count2 <= 0)
return 0;
if (LINE_END(1) >= MAX_PTR)
if ((unsigned int)LINE_END(1) >= MAX_PTR)
return -1;
if (!count1) {
while(count2--)
env->xdf2.rchg[line2++ - 1] = 1;
env->xdf2.changed[line2++ - 1] = true;
return 0;
} else if (!count2) {
while(count1--)
env->xdf1.rchg[line1++ - 1] = 1;
env->xdf1.changed[line1++ - 1] = true;
return 0;
}
@@ -335,9 +335,9 @@ redo:
else {
if (lcs.begin1 == 0 && lcs.begin2 == 0) {
while (count1--)
env->xdf1.rchg[line1++ - 1] = 1;
env->xdf1.changed[line1++ - 1] = true;
while (count2--)
env->xdf2.rchg[line2++ - 1] = 1;
env->xdf2.changed[line2++ - 1] = true;
result = 0;
} else {
result = histogram_diff(xpp, env,

3
src/xdiff/xinclude.h
View File

@@ -43,6 +43,9 @@
# define inline __inline
#endif
// Vim replacement for BUG()
void xdl_bug(const char *msg);
#if !defined(XINCLUDE_H)
#define XINCLUDE_H

25
src/xdiff/xpatience.c
View File

@@ -19,6 +19,7 @@
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include "xinclude.h"
/*
@@ -63,7 +64,7 @@ struct hashmap {
/*
* If 1, this entry can serve as an anchor. See
* Documentation/diff-options.txt for more information.
* Documentation/diff-options.adoc for more information.
*/
unsigned anchor : 1;
} *entries, *first, *last;
@@ -75,8 +76,8 @@ struct hashmap {
static int is_anchor(xpparam_t const *xpp, const char *line)
{
int i;
for (i = 0; i < (int)xpp->anchors_nr; i++) {
size_t i;
for (i = 0; i < xpp->anchors_nr; i++) {
if (!strncmp(line, xpp->anchors[i], strlen(xpp->anchors[i])))
return 1;
}
@@ -87,9 +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,
int pass)
{
xrecord_t **records = pass == 1 ?
xrecord_t *records = pass == 1 ?
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
* xdl_classify_record()), the "ha" member of the records (AKA lines)
@@ -120,7 +121,7 @@ static void insert_record(xpparam_t const *xpp, int line, struct hashmap *map,
return;
map->entries[index].line1 = line;
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)
map->first = map->entries + index;
if (map->last) {
@@ -245,8 +246,8 @@ static int find_longest_common_sequence(struct hashmap *map, struct entry **res)
static int match(struct hashmap *map, int line1, int line2)
{
xrecord_t *record1 = map->env->xdf1.recs[line1 - 1];
xrecord_t *record2 = map->env->xdf2.recs[line2 - 1];
xrecord_t *record1 = &map->env->xdf1.recs[line1 - 1];
xrecord_t *record2 = &map->env->xdf2.recs[line2 - 1];
return record1->ha == record2->ha;
}
@@ -330,11 +331,11 @@ static int patience_diff(xpparam_t const *xpp, xdfenv_t *env,
/* trivial case: one side is empty */
if (!count1) {
while(count2--)
env->xdf2.rchg[line2++ - 1] = 1;
env->xdf2.changed[line2++ - 1] = true;
return 0;
} else if (!count2) {
while(count1--)
env->xdf1.rchg[line1++ - 1] = 1;
env->xdf1.changed[line1++ - 1] = true;
return 0;
}
@@ -346,9 +347,9 @@ static int patience_diff(xpparam_t const *xpp, xdfenv_t *env,
/* are there any matching lines at all? */
if (!map.has_matches) {
while(count1--)
env->xdf1.rchg[line1++ - 1] = 1;
env->xdf1.changed[line1++ - 1] = true;
while(count2--)
env->xdf2.rchg[line2++ - 1] = 1;
env->xdf2.changed[line2++ - 1] = true;
xdl_free(map.entries);
return 0;
}

469
src/xdiff/xprepare.c
View File

@@ -29,12 +29,13 @@
#define XDL_GUESS_NLINES1 256
#define XDL_GUESS_NLINES2 20
#define DISCARD 0
#define KEEP 1
#define INVESTIGATE 2
typedef struct s_xdlclass {
struct s_xdlclass *next;
unsigned long ha;
char const *line;
long size;
xrecord_t rec;
long idx;
long len1, len2;
} 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) {
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,
unsigned int hbits, xrecord_t *rec) {
static int xdl_classify_record(unsigned int pass, xdlclassifier_t *cf, xrecord_t *rec) {
long hi;
char const *line;
xdlclass_t *rcrec;
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,
if (rcrec->rec.ha == rec->ha &&
xdl_recmatch(rcrec->rec.ptr, rcrec->rec.size,
rec->ptr, rec->size, cf->flags))
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))
return -1;
cf->rcrecs[rcrec->idx] = rcrec;
rcrec->line = line;
rcrec->size = rec->size;
rcrec->ha = rec->ha;
rcrec->rec = *rec;
rcrec->len1 = rcrec->len2 = 0;
rcrec->next = cf->rchash[hi];
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;
hi = (long) XDL_HASHLONG(rec->ha, hbits);
rec->next = rhash[hi];
rhash[hi] = rec;
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,
xdlclassifier_t *cf, xdfile_t *xdf) {
unsigned int hbits;
long nrec, hsize, bsize;
long bsize;
unsigned long hav;
char const *blk, *cur, *top, *prev;
xrecord_t *crec;
xrecord_t **recs;
xrecord_t **rhash;
unsigned long *ha;
char *rchg;
long *rindex;
ha = NULL;
rindex = NULL;
rchg = NULL;
rhash = NULL;
recs = NULL;
xdf->rindex = NULL;
xdf->changed = NULL;
xdf->recs = NULL;
if (xdl_cha_init(&xdf->rcha, sizeof(xrecord_t), narec / 4 + 1) < 0)
goto abort;
if (!XDL_ALLOC_ARRAY(recs, narec))
if (!XDL_ALLOC_ARRAY(xdf->recs, narec))
goto abort;
hbits = xdl_hashbits((unsigned int) narec);
hsize = 1 << hbits;
if (!XDL_CALLOC_ARRAY(rhash, hsize))
goto abort;
nrec = 0;
xdf->nrec = 0;
if ((cur = blk = xdl_mmfile_first(mf, &bsize))) {
for (top = blk + bsize; cur < top; ) {
prev = cur;
hav = xdl_hash_record(&cur, top, xpp->flags);
if (XDL_ALLOC_GROW(recs, nrec + 1, narec))
goto abort;
if (!(crec = xdl_cha_alloc(&xdf->rcha)))
if (XDL_ALLOC_GROW(xdf->recs, xdf->nrec + 1, narec))
goto abort;
crec = &xdf->recs[xdf->nrec++];
crec->ptr = prev;
crec->size = (long) (cur - prev);
crec->ha = hav;
recs[nrec++] = crec;
if (xdl_classify_record(pass, cf, rhash, hbits, crec) < 0)
if (xdl_classify_record(pass, cf, crec) < 0)
goto abort;
}
}
if (!XDL_CALLOC_ARRAY(rchg, nrec + 2))
if (!XDL_CALLOC_ARRAY(xdf->changed, xdf->nrec + 2))
goto abort;
if ((XDF_DIFF_ALG(xpp->flags) != XDF_PATIENCE_DIFF) &&
(XDF_DIFF_ALG(xpp->flags) != XDF_HISTOGRAM_DIFF)) {
if (!XDL_ALLOC_ARRAY(rindex, nrec + 1))
goto abort;
if (!XDL_ALLOC_ARRAY(ha, nrec + 1))
if (!XDL_ALLOC_ARRAY(xdf->rindex, xdf->nrec + 1))
goto abort;
}
xdf->nrec = nrec;
xdf->recs = recs;
xdf->hbits = hbits;
xdf->rhash = rhash;
xdf->rchg = rchg + 1;
xdf->rindex = rindex;
xdf->changed += 1;
xdf->nreff = 0;
xdf->ha = ha;
xdf->dstart = 0;
xdf->dend = nrec - 1;
xdf->dend = xdf->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);
xdl_free_ctx(xdf);
return -1;
}
static void xdl_free_ctx(xdfile_t *xdf) {
void xdl_free_env(xdfenv_t *xe) {
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);
xdl_free_ctx(&xe->xdf2);
xdl_free_ctx(&xe->xdf1);
}
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
xdl_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
xdl_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,
xdfenv_t *xe) {
long enl1, enl2, sample;
@@ -291,171 +428,3 @@ int xdl_prepare_env(mmfile_t *mf1, mmfile_t *mf2, xpparam_t const *xpp,
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 (!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) ? 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;
}

9
src/xdiff/xtypes.h
View File

@@ -39,23 +39,18 @@ typedef struct s_chastore {
} chastore_t;
typedef struct s_xrecord {
struct s_xrecord *next;
char const *ptr;
long size;
unsigned long ha;
} xrecord_t;
typedef struct s_xdfile {
chastore_t rcha;
xrecord_t *recs;
long nrec;
unsigned int hbits;
xrecord_t **rhash;
long dstart, dend;
xrecord_t **recs;
char *rchg;
bool *changed;
long *rindex;
long nreff;
unsigned long *ha;
} xdfile_t;
typedef struct s_xdfenv {

84
src/xdiff/xutils.c
View File

@@ -249,7 +249,7 @@ int xdl_recmatch(const char *l1, long s1, const char *l2, long s2, long flags)
return 1;
}
static unsigned long xdl_hash_record_with_whitespace(char const **data,
unsigned long xdl_hash_record_with_whitespace(char const **data,
char const *top, long flags) {
unsigned long ha = 5381;
char const *ptr = *data;
@@ -294,19 +294,67 @@ static unsigned long xdl_hash_record_with_whitespace(char const **data,
return ha;
}
unsigned long xdl_hash_record(char const **data, char const *top, long flags) {
unsigned long ha = 5381;
/*
* Compiler reassociation barrier: pretend to modify X and Y to disallow
* changing evaluation order with respect to following uses of X and Y.
*/
#ifdef __GNUC__
#define REASSOC_FENCE(x, y) __asm__("" : "+r"(x), "+r"(y))
#else
#define REASSOC_FENCE(x, y)
#endif
unsigned long xdl_hash_record_verbatim(char const **data, char const *top) {
unsigned long ha = 5381, c0, c1;
char const *ptr = *data;
if (flags & XDF_WHITESPACE_FLAGS)
return xdl_hash_record_with_whitespace(data, top, flags);
#if 0
/*
* The baseline form of the optimized loop below. This is the djb2
* hash (the above function uses a variant with XOR instead of ADD).
*/
for (; ptr < top && *ptr != '\n'; ptr++) {
ha += (ha << 5);
ha ^= (unsigned long) *ptr;
ha += (unsigned long) *ptr;
}
*data = ptr < top ? ptr + 1: ptr;
#else
/* Process two characters per iteration. */
if (top - ptr >= 2) do {
if ((c0 = ptr[0]) == '\n') {
*data = ptr + 1;
return ha;
}
if ((c1 = ptr[1]) == '\n') {
*data = ptr + 2;
c0 += ha;
REASSOC_FENCE(c0, ha);
ha = ha * 32 + c0;
return ha;
}
/*
* Combine characters C0 and C1 into the hash HA. We have
* HA = (HA * 33 + C0) * 33 + C1, and we want to ensure
* that dependency chain over HA is just one multiplication
* and one addition, i.e. we want to evaluate this as
* HA = HA * 33 * 33 + (C0 * 33 + C1), and likewise prefer
* (C0 * 32 + (C0 + C1)) for the expression in parenthesis.
*/
ha *= 33 * 33;
c1 += c0;
REASSOC_FENCE(c1, c0);
c1 += c0 * 32;
REASSOC_FENCE(c1, ha);
ha += c1;
ptr += 2;
} while (ptr < top - 1);
*data = top;
if (ptr < top && (c0 = ptr[0]) != '\n') {
c0 += ha;
REASSOC_FENCE(c0, ha);
ha = ha * 32 + c0;
}
#endif
return ha;
}
@@ -375,7 +423,7 @@ static int xdl_format_hunk_hdr(long s1, long c1, long s2, long c2,
nb += 3;
if (func && funclen) {
buf[nb++] = ' ';
if (funclen > (long)sizeof(buf) - nb - 1)
if ((size_t)funclen > sizeof(buf) - nb - 1)
funclen = sizeof(buf) - nb - 1;
memcpy(buf + nb, func, funclen);
nb += funclen;
@@ -416,17 +464,17 @@ int xdl_fall_back_diff(xdfenv_t *diff_env, xpparam_t const *xpp,
mmfile_t subfile1, subfile2;
xdfenv_t env;
subfile1.ptr = (char *)diff_env->xdf1.recs[line1 - 1]->ptr;
subfile1.size = diff_env->xdf1.recs[line1 + count1 - 2]->ptr +
diff_env->xdf1.recs[line1 + count1 - 2]->size - subfile1.ptr;
subfile2.ptr = (char *)diff_env->xdf2.recs[line2 - 1]->ptr;
subfile2.size = diff_env->xdf2.recs[line2 + count2 - 2]->ptr +
diff_env->xdf2.recs[line2 + count2 - 2]->size - subfile2.ptr;
subfile1.ptr = (char *)diff_env->xdf1.recs[line1 - 1].ptr;
subfile1.size = diff_env->xdf1.recs[line1 + count1 - 2].ptr +
diff_env->xdf1.recs[line1 + count1 - 2].size - subfile1.ptr;
subfile2.ptr = (char *)diff_env->xdf2.recs[line2 - 1].ptr;
subfile2.size = diff_env->xdf2.recs[line2 + count2 - 2].ptr +
diff_env->xdf2.recs[line2 + count2 - 2].size - subfile2.ptr;
if (xdl_do_diff(&subfile1, &subfile2, xpp, &env) < 0)
return -1;
memcpy(diff_env->xdf1.rchg + line1 - 1, env.xdf1.rchg, count1);
memcpy(diff_env->xdf2.rchg + line2 - 1, env.xdf2.rchg, count2);
memcpy(diff_env->xdf1.changed + line1 - 1, env.xdf1.changed, count1);
memcpy(diff_env->xdf2.changed + line2 - 1, env.xdf2.changed, count2);
xdl_free_env(&env);
@@ -437,7 +485,7 @@ void* xdl_alloc_grow_helper(void *p, long nr, long *alloc, size_t size)
{
void *tmp = NULL;
size_t n = ((LONG_MAX - 16) / 2 >= *alloc) ? 2 * *alloc + 16 : LONG_MAX;
if (nr > (long)n)
if ((size_t)nr > n)
n = nr;
if (SIZE_MAX / size >= n)
tmp = xdl_realloc(p, n * size);

10
src/xdiff/xutils.h
View File

@@ -34,7 +34,15 @@ void *xdl_cha_alloc(chastore_t *cha);
long xdl_guess_lines(mmfile_t *mf, long sample);
int xdl_blankline(const char *line, long size, long flags);
int xdl_recmatch(const char *l1, long s1, const char *l2, long s2, long flags);
unsigned long xdl_hash_record(char const **data, char const *top, long flags);
unsigned long xdl_hash_record_verbatim(char const **data, char const *top);
unsigned long xdl_hash_record_with_whitespace(char const **data, char const *top, long flags);
static inline unsigned long xdl_hash_record(char const **data, char const *top, long flags)
{
if (flags & XDF_WHITESPACE_FLAGS)
return xdl_hash_record_with_whitespace(data, top, flags);
else
return xdl_hash_record_verbatim(data, top);
}
unsigned int xdl_hashbits(unsigned int size);
int xdl_num_out(char *out, long val);
int xdl_emit_hunk_hdr(long s1, long c1, long s2, long c2,