re_guts catspace[] is only written to (via categories[]), and never used
for anything, so don't bother keeping that.
Index: lib/libc/regex/regcomp.c
===================================================================
RCS file: /OpenBSD/src/lib/libc/regex/regcomp.c,v
retrieving revision 1.38
diff -u -p -r1.38 regcomp.c
--- lib/libc/regex/regcomp.c 30 Dec 2020 08:59:17 -0000 1.38
+++ lib/libc/regex/regcomp.c 31 Dec 2020 07:20:39 -0000
@@ -92,7 +92,6 @@ static int firstch(struct parse *, cset
static int nch(struct parse *, cset *);
static int isinsets(struct re_guts *, int);
static int samesets(struct re_guts *, int, int);
-static void categorize(struct parse *, struct re_guts *);
static sopno dupl(struct parse *, sopno, sopno);
static void doemit(struct parse *, sop, size_t);
static void doinsert(struct parse *, sop, size_t, sopno);
@@ -198,9 +197,6 @@ regcomp(regex_t *preg, const char *patte
g->must = NULL;
g->mlen = 0;
g->nsub = 0;
- g->ncategories = 1; /* category 0 is "everything else" */
- g->categories = &g->catspace[-(CHAR_MIN)];
- memset(g->catspace, 0, sizeof(g->catspace));
g->backrefs = 0;
/* do it */
@@ -216,7 +212,6 @@ regcomp(regex_t *preg, const char *patte
g->laststate = THERE();
/* tidy up loose ends and fill things in */
- categorize(p, g);
stripsnug(p, g);
findmust(p, g);
g->nplus = pluscount(p, g);
@@ -883,15 +878,10 @@ bothcases(struct parse *p, int ch)
static void
ordinary(struct parse *p, int ch)
{
- cat_t *cap = p->g->categories;
-
if ((p->g->cflags®_ICASE) && isalpha((uch)ch) && othercase(ch) != ch)
bothcases(p, ch);
- else {
+ else
EMIT(OCHAR, (uch)ch);
- if (cap[ch] == 0)
- cap[ch] = p->g->ncategories++;
- }
}
/*
@@ -1195,31 +1180,6 @@ samesets(struct re_guts *g, int c1, int
if (col[uc1] != col[uc2])
return(0);
return(1);
-}
-
-/*
- - categorize - sort out character categories
- */
-static void
-categorize(struct parse *p, struct re_guts *g)
-{
- cat_t *cats = g->categories;
- int c;
- int c2;
- cat_t cat;
-
- /* avoid making error situations worse */
- if (p->error != 0)
- return;
-
- for (c = CHAR_MIN; c <= CHAR_MAX; c++)
- if (cats[c] == 0 && isinsets(g, c)) {
- cat = g->ncategories++;
- cats[c] = cat;
- for (c2 = c+1; c2 <= CHAR_MAX; c2++)
- if (cats[c2] == 0 && samesets(g, c, c2))
- cats[c2] = cat;
- }
}
/*
Index: lib/libc/regex/regex2.h
===================================================================
RCS file: /OpenBSD/src/lib/libc/regex/regex2.h,v
retrieving revision 1.9
diff -u -p -r1.9 regex2.h
--- lib/libc/regex/regex2.h 30 Dec 2020 08:54:42 -0000 1.9
+++ lib/libc/regex/regex2.h 31 Dec 2020 07:20:39 -0000
@@ -112,9 +112,6 @@ typedef struct {
#define CHsub(cs, c) ((cs)->ptr[(uch)(c)] &= ~(cs)->mask, (cs)->hash
-= (c))
#define CHIN(cs, c) ((cs)->ptr[(uch)(c)] & (cs)->mask)
-/* stuff for character categories */
-typedef unsigned char cat_t;
-
/*
* main compiled-expression structure
*/
@@ -136,15 +133,11 @@ struct re_guts {
# define BAD 04 /* something wrong */
int nbol; /* number of ^ used */
int neol; /* number of $ used */
- int ncategories; /* how many character categories */
- cat_t *categories; /* ->catspace[-CHAR_MIN] */
char *must; /* match must contain this string */
int mlen; /* length of must */
size_t nsub; /* copy of re_nsub */
int backrefs; /* does it use back references? */
sopno nplus; /* how deep does it nest +s? */
- /* catspace must be last */
- cat_t catspace[NC]; /* actually [NC] */
};
/* misc utilities */
Index: regress/lib/libc/regex/debug.c
===================================================================
RCS file: /OpenBSD/src/regress/lib/libc/regex/debug.c,v
retrieving revision 1.4
diff -u -p -r1.4 debug.c
--- regress/lib/libc/regex/debug.c 31 Jul 2003 21:48:03 -0000 1.4
+++ regress/lib/libc/regex/debug.c 31 Dec 2020 07:20:39 -0000
@@ -26,10 +26,8 @@ FILE *d;
register int i;
register int c;
register int last;
- int nincat[NC];
- fprintf(d, "%ld states, %d categories", (long)g->nstates,
- g->ncategories);
+ fprintf(d, "%ld states", (long)g->nstates);
fprintf(d, ", first %ld last %ld", (long)g->firststate,
(long)g->laststate);
if (g->iflags&USEBOL)
@@ -49,41 +47,6 @@ FILE *d;
fprintf(d, ", nplus %ld", (long)g->nplus);
fprintf(d, "\n");
s_print(g, d);
- for (i = 0; i < g->ncategories; i++) {
- nincat[i] = 0;
- for (c = CHAR_MIN; c <= CHAR_MAX; c++)
- if (g->categories[c] == i)
- nincat[i]++;
- }
- fprintf(d, "cc0#%d", nincat[0]);
- for (i = 1; i < g->ncategories; i++)
- if (nincat[i] == 1) {
- for (c = CHAR_MIN; c <= CHAR_MAX; c++)
- if (g->categories[c] == i)
- break;
- fprintf(d, ", %d=%s", i, regchar(c));
- }
- fprintf(d, "\n");
- for (i = 1; i < g->ncategories; i++)
- if (nincat[i] != 1) {
- fprintf(d, "cc%d\t", i);
- last = -1;
- for (c = CHAR_MIN; c <= CHAR_MAX+1; c++) /* +1
does flush */
- if (c <= CHAR_MAX && g->categories[c] == i) {
- if (last < 0) {
- fprintf(d, "%s", regchar(c));
- last = c;
- }
- } else {
- if (last >= 0) {
- if (last != c-1)
- fprintf(d, "-%s",
- regchar(c-1));
- last = -1;
- }
- }
- fprintf(d, "\n");
- }
}
/*
