aboutsummaryrefslogtreecommitdiff
path: root/src/backend/regex/regcomp.c
diff options
context:
space:
mode:
Diffstat (limited to 'src/backend/regex/regcomp.c')
-rw-r--r--src/backend/regex/regcomp.c1114
1 files changed, 601 insertions, 513 deletions
diff --git a/src/backend/regex/regcomp.c b/src/backend/regex/regcomp.c
index 364573e2b5b..dcb95173c06 100644
--- a/src/backend/regex/regcomp.c
+++ b/src/backend/regex/regcomp.c
@@ -1,7 +1,7 @@
/*-
* Copyright (c) 1992, 1993, 1994 Henry Spencer.
* Copyright (c) 1992, 1993, 1994
- * The Regents of the University of California. All rights reserved.
+ * The Regents of the University of California. All rights reserved.
*
* This code is derived from software contributed to Berkeley by
* Henry Spencer.
@@ -10,22 +10,22 @@
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
+ * notice, this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
- * notice, this list of conditions and the following disclaimer in the
- * documentation and/or other materials provided with the distribution.
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
* 3. All advertising materials mentioning features or use of this software
- * must display the following acknowledgement:
- * This product includes software developed by the University of
- * California, Berkeley and its contributors.
+ * must display the following acknowledgement:
+ * This product includes software developed by the University of
+ * California, Berkeley and its contributors.
* 4. Neither the name of the University nor the names of its contributors
- * may be used to endorse or promote products derived from this software
- * without specific prior written permission.
+ * may be used to endorse or promote products derived from this software
+ * without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
* OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
@@ -34,12 +34,13 @@
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
* SUCH DAMAGE.
*
- * @(#)regcomp.c 8.5 (Berkeley) 3/20/94
+ * @(#)regcomp.c 8.5 (Berkeley) 3/20/94
*/
#if defined(LIBC_SCCS) && !defined(lint)
-static char sccsid[] = "@(#)regcomp.c 8.5 (Berkeley) 3/20/94";
-#endif /* LIBC_SCCS and not lint */
+static char sccsid[] = "@(#)regcomp.c 8.5 (Berkeley) 3/20/94";
+
+#endif /* LIBC_SCCS and not lint */
#include <sys/types.h>
#include <stdio.h>
@@ -49,7 +50,7 @@ static char sccsid[] = "@(#)regcomp.c 8.5 (Berkeley) 3/20/94";
#include <stdlib.h>
#include <assert.h>
-#include <regex/regex.h>
+#include <regex/regex.h>
#include <regex/utils.h>
#include <regex/regex2.h>
#include <regex/cclass.h>
@@ -59,167 +60,179 @@ static char sccsid[] = "@(#)regcomp.c 8.5 (Berkeley) 3/20/94";
* parse structure, passed up and down to avoid global variables and
* other clumsinesses
*/
-struct parse {
- char *next; /* next character in RE */
- char *end; /* end of string (-> NUL normally) */
- int error; /* has an error been seen? */
- sop *strip; /* malloced strip */
- sopno ssize; /* malloced strip size (allocated) */
- sopno slen; /* malloced strip length (used) */
- int ncsalloc; /* number of csets allocated */
+struct parse
+{
+ char *next; /* next character in RE */
+ char *end; /* end of string (-> NUL normally) */
+ int error; /* has an error been seen? */
+ sop *strip; /* malloced strip */
+ sopno ssize; /* malloced strip size (allocated) */
+ sopno slen; /* malloced strip length (used) */
+ int ncsalloc; /* number of csets allocated */
struct re_guts *g;
-# define NPAREN 10 /* we need to remember () 1-9 for back refs */
- sopno pbegin[NPAREN]; /* -> ( ([0] unused) */
- sopno pend[NPAREN]; /* -> ) ([0] unused) */
+#define NPAREN 10 /* we need to remember () 1-9 for back
+ * refs */
+ sopno pbegin[NPAREN]; /* -> ( ([0] unused) */
+ sopno pend[NPAREN]; /* -> ) ([0] unused) */
};
/* ========= begin header generated by ./mkh ========= */
#ifdef __cplusplus
-extern "C" {
+extern "C"
+{
#endif
/* === regcomp.c === */
-static void p_ere(struct parse *p, int stop);
-static void p_ere_exp(struct parse *p);
-static void p_str(struct parse *p);
-static void p_bre(struct parse *p, int end1, int end2);
-static int p_simp_re(struct parse *p, int starordinary);
-static int p_count(struct parse *p);
-static void p_bracket(struct parse *p);
-static void p_b_term(struct parse *p, cset *cs);
-static void p_b_cclass(struct parse *p, cset *cs);
-static void p_b_eclass(struct parse *p, cset *cs);
-static char p_b_symbol(struct parse *p);
-static char p_b_coll_elem(struct parse *p, int endc);
-static char othercase(int ch);
-static void bothcases(struct parse *p, int ch);
-static void ordinary(struct parse *p, int ch);
-static void nonnewline(struct parse *p);
-static void repeat(struct parse *p, sopno start, int from, int to);
-static int seterr(struct parse *p, int e);
-static cset *allocset(struct parse *p);
-static void freeset(struct parse *p, cset *cs);
-static int freezeset(struct parse *p, cset *cs);
-static int firstch(struct parse *p, cset *cs);
-static int nch(struct parse *p, cset *cs);
-static void mcadd(struct parse *p, cset *cs, char *cp);
-static void mcinvert(struct parse *p, cset *cs);
-static void mccase(struct parse *p, cset *cs);
-static int isinsets(struct re_guts *g, int c);
-static int samesets(struct re_guts *g, int c1, int c2);
-static void categorize(struct parse *p, struct re_guts *g);
-static sopno dupl(struct parse *p, sopno start, sopno finish);
-static void doemit(struct parse *p, sop op, size_t opnd);
-static void doinsert(struct parse *p, sop op, size_t opnd, sopno pos);
-static void dofwd(struct parse *p, sopno pos, sop value);
-static void enlarge(struct parse *p, sopno size);
-static void stripsnug(struct parse *p, struct re_guts *g);
-static void findmust(struct parse *p, struct re_guts *g);
-static sopno pluscount(struct parse *p, struct re_guts *g);
+ static void p_ere(struct parse * p, int stop);
+ static void p_ere_exp(struct parse * p);
+ static void p_str(struct parse * p);
+ static void p_bre(struct parse * p, int end1, int end2);
+ static int p_simp_re(struct parse * p, int starordinary);
+ static int p_count(struct parse * p);
+ static void p_bracket(struct parse * p);
+ static void p_b_term(struct parse * p, cset * cs);
+ static void p_b_cclass(struct parse * p, cset * cs);
+ static void p_b_eclass(struct parse * p, cset * cs);
+ static char p_b_symbol(struct parse * p);
+ static char p_b_coll_elem(struct parse * p, int endc);
+ static char othercase(int ch);
+ static void bothcases(struct parse * p, int ch);
+ static void ordinary(struct parse * p, int ch);
+ static void nonnewline(struct parse * p);
+ static void repeat(struct parse * p, sopno start, int from, int to);
+ static int seterr(struct parse * p, int e);
+ static cset *allocset(struct parse * p);
+ static void freeset(struct parse * p, cset * cs);
+ static int freezeset(struct parse * p, cset * cs);
+ static int firstch(struct parse * p, cset * cs);
+ static int nch(struct parse * p, cset * cs);
+ static void mcadd(struct parse * p, cset * cs, char *cp);
+ static void mcinvert(struct parse * p, cset * cs);
+ static void mccase(struct parse * p, cset * cs);
+ static int isinsets(struct re_guts * g, int c);
+ static int samesets(struct re_guts * g, int c1, int c2);
+ static void categorize(struct parse * p, struct re_guts * g);
+ static sopno dupl(struct parse * p, sopno start, sopno finish);
+ static void doemit(struct parse * p, sop op, size_t opnd);
+ static void doinsert(struct parse * p, sop op, size_t opnd, sopno pos);
+ static void dofwd(struct parse * p, sopno pos, sop value);
+ static void enlarge(struct parse * p, sopno size);
+ static void stripsnug(struct parse * p, struct re_guts * g);
+ static void findmust(struct parse * p, struct re_guts * g);
+ static sopno pluscount(struct parse * p, struct re_guts * g);
#ifdef __cplusplus
}
+
#endif
/* ========= end header generated by ./mkh ========= */
-static char nuls[10]; /* place to point scanner in event of error */
+static char nuls[10]; /* place to point scanner in event of
+ * error */
/*
* macros for use with parse structure
- * BEWARE: these know that the parse structure is named `p' !!!
+ * BEWARE: these know that the parse structure is named `p' !!!
*/
-#define PEEK() (*p->next)
-#define PEEK2() (*(p->next+1))
-#define MORE() (p->next < p->end)
-#define MORE2() (p->next+1 < p->end)
-#define SEE(c) (MORE() && PEEK() == (c))
-#define SEETWO(a, b) (MORE() && MORE2() && PEEK() == (a) && PEEK2() == (b))
-#define EAT(c) ((SEE(c)) ? (NEXT(), 1) : 0)
-#define EATTWO(a, b) ((SEETWO(a, b)) ? (NEXT2(), 1) : 0)
-#define NEXT() (p->next++)
-#define NEXT2() (p->next += 2)
-#define NEXTn(n) (p->next += (n))
-#define GETNEXT() (*p->next++)
-#define SETERROR(e) seterr(p, (e))
-#define REQUIRE(co, e) if (!(co)) SETERROR(e)
-#define MUSTSEE(c, e) REQUIRE(MORE() && PEEK() == (c), e)
-#define MUSTEAT(c, e) REQUIRE(MORE() && GETNEXT() == (c), e)
-#define MUSTNOTSEE(c, e) REQUIRE(!MORE() || PEEK() != (c), e)
-#define EMIT(op, sopnd) doemit(p, (sop)(op), (size_t)(sopnd))
-#define INSERT(op, pos) doinsert(p, (sop)(op), HERE()-(pos)+1, pos)
-#define AHEAD(pos) dofwd(p, pos, HERE()-(pos))
-#define ASTERN(sop, pos) EMIT(sop, HERE()-pos)
-#define HERE() (p->slen)
-#define THERE() (p->slen - 1)
-#define THERETHERE() (p->slen - 2)
-#define DROP(n) (p->slen -= (n))
+#define PEEK() (*p->next)
+#define PEEK2() (*(p->next+1))
+#define MORE() (p->next < p->end)
+#define MORE2() (p->next+1 < p->end)
+#define SEE(c) (MORE() && PEEK() == (c))
+#define SEETWO(a, b) (MORE() && MORE2() && PEEK() == (a) && PEEK2() == (b))
+#define EAT(c) ((SEE(c)) ? (NEXT(), 1) : 0)
+#define EATTWO(a, b) ((SEETWO(a, b)) ? (NEXT2(), 1) : 0)
+#define NEXT() (p->next++)
+#define NEXT2() (p->next += 2)
+#define NEXTn(n) (p->next += (n))
+#define GETNEXT() (*p->next++)
+#define SETERROR(e) seterr(p, (e))
+#define REQUIRE(co, e) if (!(co)) SETERROR(e)
+#define MUSTSEE(c, e) REQUIRE(MORE() && PEEK() == (c), e)
+#define MUSTEAT(c, e) REQUIRE(MORE() && GETNEXT() == (c), e)
+#define MUSTNOTSEE(c, e) REQUIRE(!MORE() || PEEK() != (c), e)
+#define EMIT(op, sopnd) doemit(p, (sop)(op), (size_t)(sopnd))
+#define INSERT(op, pos) doinsert(p, (sop)(op), HERE()-(pos)+1, pos)
+#define AHEAD(pos) dofwd(p, pos, HERE()-(pos))
+#define ASTERN(sop, pos) EMIT(sop, HERE()-pos)
+#define HERE() (p->slen)
+#define THERE() (p->slen - 1)
+#define THERETHERE() (p->slen - 2)
+#define DROP(n) (p->slen -= (n))
#ifndef NDEBUG
-static int never = 0; /* for use in asserts; shuts lint up */
+static int never = 0; /* for use in asserts; shuts lint up */
+
#else
-#define never 0 /* some <assert.h>s have bugs too */
+#define never 0 /* some <assert.h>s have bugs too */
#endif
/*
- regcomp - interface for parser and compilation
= extern int regcomp(regex_t *, const char *, int);
- = #define REG_BASIC 0000
- = #define REG_EXTENDED 0001
- = #define REG_ICASE 0002
- = #define REG_NOSUB 0004
- = #define REG_NEWLINE 0010
- = #define REG_NOSPEC 0020
- = #define REG_PEND 0040
- = #define REG_DUMP 0200
+ = #define REG_BASIC 0000
+ = #define REG_EXTENDED 0001
+ = #define REG_ICASE 0002
+ = #define REG_NOSUB 0004
+ = #define REG_NEWLINE 0010
+ = #define REG_NOSPEC 0020
+ = #define REG_PEND 0040
+ = #define REG_DUMP 0200
*/
-int /* 0 success, otherwise REG_something */
+int /* 0 success, otherwise REG_something */
pg95_regcomp(preg, pattern, cflags)
-regex_t *preg;
-const char *pattern;
-int cflags;
+regex_t *preg;
+const char *pattern;
+int cflags;
{
- struct parse pa;
+ struct parse pa;
register struct re_guts *g;
register struct parse *p = &pa;
- register int i;
+ register int i;
register size_t len;
+
#ifdef REDEBUG
-# define GOODFLAGS(f) (f)
+#define GOODFLAGS(f) (f)
#else
-# define GOODFLAGS(f) ((f)&~REG_DUMP)
+#define GOODFLAGS(f) ((f)&~REG_DUMP)
#endif
cflags = GOODFLAGS(cflags);
- if ((cflags&REG_EXTENDED) && (cflags&REG_NOSPEC))
- return(REG_INVARG);
+ if ((cflags & REG_EXTENDED) && (cflags & REG_NOSPEC))
+ return (REG_INVARG);
- if (cflags&REG_PEND) {
+ if (cflags & REG_PEND)
+ {
if (preg->re_endp < pattern)
- return(REG_INVARG);
+ return (REG_INVARG);
len = preg->re_endp - pattern;
- } else
- len = strlen((char *)pattern);
+ }
+ else
+ len = strlen((char *) pattern);
/* do the mallocs early so failure handling is easy */
- g = (struct re_guts *)malloc(sizeof(struct re_guts) +
- (NC-1)*sizeof(cat_t));
+ g = (struct re_guts *) malloc(sizeof(struct re_guts) +
+ (NC - 1) * sizeof(cat_t));
if (g == NULL)
- return(REG_ESPACE);
- p->ssize = len/(size_t)2*(size_t)3 + (size_t)1; /* ugh */
- p->strip = (sop *)malloc(p->ssize * sizeof(sop));
+ return (REG_ESPACE);
+ p->ssize = len / (size_t) 2 *(size_t) 3 + (size_t) 1; /* ugh */
+
+ p->strip = (sop *) malloc(p->ssize * sizeof(sop));
p->slen = 0;
- if (p->strip == NULL) {
- free((char *)g);
- return(REG_ESPACE);
+ if (p->strip == NULL)
+ {
+ free((char *) g);
+ return (REG_ESPACE);
}
/* set things up */
p->g = g;
- p->next = (char *)pattern; /* convenience; we do not modify it */
+ p->next = (char *) pattern; /* convenience; we do not modify it */
p->end = p->next + len;
p->error = 0;
p->ncsalloc = 0;
- for (i = 0; i < NPAREN; i++) {
+ for (i = 0; i < NPAREN; i++)
+ {
p->pbegin[i] = 0;
p->pend[i] = 0;
}
@@ -234,17 +247,17 @@ int cflags;
g->must = NULL;
g->mlen = 0;
g->nsub = 0;
- g->ncategories = 1; /* category 0 is "everything else" */
+ g->ncategories = 1; /* category 0 is "everything else" */
g->categories = &g->catspace[-(CHAR_MIN)];
- memset((char *)g->catspace, 0, NC*sizeof(cat_t));
+ memset((char *) g->catspace, 0, NC * sizeof(cat_t));
g->backrefs = 0;
/* do it */
EMIT(OEND, 0);
g->firststate = THERE();
- if (cflags&REG_EXTENDED)
+ if (cflags & REG_EXTENDED)
p_ere(p, OUT);
- else if (cflags&REG_NOSPEC)
+ else if (cflags & REG_NOSPEC)
p_str(p);
else
p_bre(p, OUT, OUT);
@@ -262,14 +275,14 @@ int cflags;
preg->re_magic = MAGIC1;
#ifndef REDEBUG
/* not debugging, so can't rely on the assert() in regexec() */
- if (g->iflags&BAD)
+ if (g->iflags & BAD)
SETERROR(REG_ASSERT);
#endif
/* win or lose, we're done */
- if (p->error != 0) /* lose */
+ if (p->error != 0) /* lose */
pg95_regfree(preg);
- return(p->error);
+ return (p->error);
}
/*
@@ -279,26 +292,28 @@ int cflags;
static void
p_ere(p, stop)
register struct parse *p;
-int stop; /* character this ERE should end at */
+int stop; /* character this ERE should end at */
{
- register char c;
- register sopno prevback = 0;
- register sopno prevfwd = 0;
- register sopno conc;
- register int first = 1; /* is this the first alternative? */
-
- for (;;) {
+ register char c;
+ register sopno prevback = 0;
+ register sopno prevfwd = 0;
+ register sopno conc;
+ register int first = 1; /* is this the first alternative? */
+
+ for (;;)
+ {
/* do a bunch of concatenated expressions */
conc = HERE();
while (MORE() && (c = PEEK()) != '|' && c != stop)
p_ere_exp(p);
- REQUIRE(HERE() != conc, REG_EMPTY); /* require nonempty */
+ REQUIRE(HERE() != conc, REG_EMPTY); /* require nonempty */
if (!EAT('|'))
- break; /* NOTE BREAK OUT */
+ break; /* NOTE BREAK OUT */
- if (first) {
- INSERT(OCH_, conc); /* offset is wrong */
+ if (first)
+ {
+ INSERT(OCH_, conc); /* offset is wrong */
prevfwd = conc;
prevback = conc;
first = 0;
@@ -310,7 +325,8 @@ int stop; /* character this ERE should end at */
EMIT(OOR2, 0); /* offset is very wrong */
}
- if (!first) { /* tail-end fixups */
+ if (!first)
+ { /* tail-end fixups */
AHEAD(prevfwd);
ASTERN(O_CH, prevback);
}
@@ -326,18 +342,19 @@ static void
p_ere_exp(p)
register struct parse *p;
{
- register char c;
- register sopno pos;
- register int count;
- register int count2;
- register sopno subno;
- int wascaret = 0;
-
- assert(MORE()); /* caller should have ensured this */
+ register char c;
+ register sopno pos;
+ register int count;
+ register int count2;
+ register sopno subno;
+ int wascaret = 0;
+
+ assert(MORE()); /* caller should have ensured this */
c = GETNEXT();
pos = HERE();
- switch (c) {
+ switch (c)
+ {
case '(':
REQUIRE(MORE(), REG_EPAREN);
p->g->nsub++;
@@ -347,7 +364,8 @@ register struct parse *p;
EMIT(OLPAREN, subno);
if (!SEE(')'))
p_ere(p, ')');
- if (subno < NPAREN) {
+ if (subno < NPAREN)
+ {
p->pend[subno] = HERE();
assert(p->pend[subno] != 0);
}
@@ -355,13 +373,13 @@ register struct parse *p;
MUSTEAT(')', REG_EPAREN);
break;
#ifndef POSIX_MISTAKE
- case ')': /* happens only if no current unmatched ( */
+ case ')': /* happens only if no current unmatched ( */
+
/*
- * You may ask, why the ifndef? Because I didn't notice
- * this until slightly too late for 1003.2, and none of the
- * other 1003.2 regular-expression reviewers noticed it at
- * all. So an unmatched ) is legal POSIX, at least until
- * we can get it fixed.
+ * You may ask, why the ifndef? Because I didn't notice this
+ * until slightly too late for 1003.2, and none of the other
+ * 1003.2 regular-expression reviewers noticed it at all. So an
+ * unmatched ) is legal POSIX, at least until we can get it fixed.
*/
SETERROR(REG_EPAREN);
break;
@@ -386,7 +404,7 @@ register struct parse *p;
SETERROR(REG_BADRPT);
break;
case '.':
- if (p->g->cflags&REG_NEWLINE)
+ if (p->g->cflags & REG_NEWLINE)
nonnewline(p);
else
EMIT(OANY, 0);
@@ -399,7 +417,8 @@ register struct parse *p;
c = GETNEXT();
ordinary(p, c);
break;
- case '{': /* okay as ordinary except if digit follows */
+ case '{': /* okay as ordinary except if digit
+ * follows */
REQUIRE(!MORE() || !isdigit(PEEK()), REG_BADRPT);
/* FALLTHROUGH */
default:
@@ -411,14 +430,15 @@ register struct parse *p;
return;
c = PEEK();
/* we call { a repetition if followed by a digit */
- if (!( c == '*' || c == '+' || c == '?' ||
- (c == '{' && MORE2() && isdigit(PEEK2())) ))
- return; /* no repetition, we're done */
+ if (!(c == '*' || c == '+' || c == '?' ||
+ (c == '{' && MORE2() && isdigit(PEEK2()))))
+ return; /* no repetition, we're done */
NEXT();
REQUIRE(!wascaret, REG_BADRPT);
- switch (c) {
- case '*': /* implemented as +? */
+ switch (c)
+ {
+ case '*': /* implemented as +? */
/* this case does not require the (y|) trick, noKLUDGE */
INSERT(OPLUS_, pos);
ASTERN(O_PLUS, pos);
@@ -433,23 +453,30 @@ register struct parse *p;
/* KLUDGE: emit y? as (y|) until subtle bug gets fixed */
INSERT(OCH_, pos); /* offset slightly wrong */
ASTERN(OOR1, pos); /* this one's right */
- AHEAD(pos); /* fix the OCH_ */
+ AHEAD(pos); /* fix the OCH_ */
EMIT(OOR2, 0); /* offset very wrong... */
AHEAD(THERE()); /* ...so fix it */
ASTERN(O_CH, THERETHERE());
break;
case '{':
count = p_count(p);
- if (EAT(',')) {
- if (isdigit(PEEK())) {
+ if (EAT(','))
+ {
+ if (isdigit(PEEK()))
+ {
count2 = p_count(p);
REQUIRE(count <= count2, REG_BADBR);
- } else /* single number with comma */
+ }
+ else
+/* single number with comma */
count2 = INFINITY;
- } else /* just a single number */
+ }
+ else
+/* just a single number */
count2 = count;
repeat(p, pos, count, count2);
- if (!EAT('}')) { /* error heuristics */
+ if (!EAT('}'))
+ { /* error heuristics */
while (MORE() && PEEK() != '}')
NEXT();
REQUIRE(MORE(), REG_EBRACE);
@@ -461,8 +488,8 @@ register struct parse *p;
if (!MORE())
return;
c = PEEK();
- if (!( c == '*' || c == '+' || c == '?' ||
- (c == '{' && MORE2() && isdigit(PEEK2())) ) )
+ if (!(c == '*' || c == '+' || c == '?' ||
+ (c == '{' && MORE2() && isdigit(PEEK2()))))
return;
SETERROR(REG_BADRPT);
}
@@ -483,72 +510,78 @@ register struct parse *p;
/*
- p_bre - BRE parser top level, anchoring and concatenation
== static void p_bre(register struct parse *p, register int end1, \
- == register int end2);
+ == register int end2);
* Giving end1 as OUT essentially eliminates the end1/end2 check.
*
* This implementation is a bit of a kludge, in that a trailing $ is first
* taken as an ordinary character and then revised to be an anchor. The
* only undesirable side effect is that '$' gets included as a character
- * category in such cases. This is fairly harmless; not worth fixing.
+ * category in such cases. This is fairly harmless; not worth fixing.
* The amount of lookahead needed to avoid this kludge is excessive.
*/
static void
p_bre(p, end1, end2)
register struct parse *p;
-register int end1; /* first terminating character */
-register int end2; /* second terminating character */
+register int end1; /* first terminating character */
+register int end2; /* second terminating character */
{
- register sopno start = HERE();
- register int first = 1; /* first subexpression? */
- register int wasdollar = 0;
+ register sopno start = HERE();
+ register int first = 1; /* first subexpression? */
+ register int wasdollar = 0;
- if (EAT('^')) {
+ if (EAT('^'))
+ {
EMIT(OBOL, 0);
p->g->iflags |= USEBOL;
p->g->nbol++;
}
- while (MORE() && !SEETWO(end1, end2)) {
+ while (MORE() && !SEETWO(end1, end2))
+ {
wasdollar = p_simp_re(p, first);
first = 0;
}
- if (wasdollar) { /* oops, that was a trailing anchor */
+ if (wasdollar)
+ { /* oops, that was a trailing anchor */
DROP(1);
EMIT(OEOL, 0);
p->g->iflags |= USEEOL;
p->g->neol++;
}
- REQUIRE(HERE() != start, REG_EMPTY); /* require nonempty */
+ REQUIRE(HERE() != start, REG_EMPTY); /* require nonempty */
}
/*
- p_simp_re - parse a simple RE, an atom possibly followed by a repetition
== static int p_simp_re(register struct parse *p, int starordinary);
*/
-static int /* was the simple RE an unbackslashed $? */
+static int /* was the simple RE an unbackslashed $? */
p_simp_re(p, starordinary)
register struct parse *p;
-int starordinary; /* is a leading * an ordinary character? */
+int starordinary; /* is a leading * an ordinary character? */
{
- register int c;
- register int count;
- register int count2;
- register sopno pos;
- register int i;
- register sopno subno;
-# define BACKSL (1<<CHAR_BIT)
+ register int c;
+ register int count;
+ register int count2;
+ register sopno pos;
+ register int i;
+ register sopno subno;
- pos = HERE(); /* repetion op, if any, covers from here */
+#define BACKSL (1<<CHAR_BIT)
- assert(MORE()); /* caller should have ensured this */
+ pos = HERE(); /* repetion op, if any, covers from here */
+
+ assert(MORE()); /* caller should have ensured this */
c = GETNEXT();
- if (c == '\\') {
+ if (c == '\\')
+ {
REQUIRE(MORE(), REG_EESCAPE);
- c = BACKSL | (unsigned char)GETNEXT();
+ c = BACKSL | (unsigned char) GETNEXT();
}
- switch (c) {
+ switch (c)
+ {
case '.':
- if (p->g->cflags&REG_NEWLINE)
+ if (p->g->cflags & REG_NEWLINE)
nonnewline(p);
else
EMIT(OANY, 0);
@@ -556,10 +589,10 @@ int starordinary; /* is a leading * an ordinary character? */
case '[':
p_bracket(p);
break;
- case BACKSL|'{':
+ case BACKSL | '{':
SETERROR(REG_BADRPT);
break;
- case BACKSL|'(':
+ case BACKSL | '(':
p->g->nsub++;
subno = p->g->nsub;
if (subno < NPAREN)
@@ -568,37 +601,40 @@ int starordinary; /* is a leading * an ordinary character? */
/* the MORE here is an error heuristic */
if (MORE() && !SEETWO('\\', ')'))
p_bre(p, '\\', ')');
- if (subno < NPAREN) {
+ if (subno < NPAREN)
+ {
p->pend[subno] = HERE();
assert(p->pend[subno] != 0);
}
EMIT(ORPAREN, subno);
REQUIRE(EATTWO('\\', ')'), REG_EPAREN);
break;
- case BACKSL|')': /* should not get here -- must be user */
- case BACKSL|'}':
+ case BACKSL | ')': /* should not get here -- must be user */
+ case BACKSL | '}':
SETERROR(REG_EPAREN);
break;
- case BACKSL|'1':
- case BACKSL|'2':
- case BACKSL|'3':
- case BACKSL|'4':
- case BACKSL|'5':
- case BACKSL|'6':
- case BACKSL|'7':
- case BACKSL|'8':
- case BACKSL|'9':
- i = (c&~BACKSL) - '0';
+ case BACKSL | '1':
+ case BACKSL | '2':
+ case BACKSL | '3':
+ case BACKSL | '4':
+ case BACKSL | '5':
+ case BACKSL | '6':
+ case BACKSL | '7':
+ case BACKSL | '8':
+ case BACKSL | '9':
+ i = (c & ~BACKSL) - '0';
assert(i < NPAREN);
- if (p->pend[i] != 0) {
+ if (p->pend[i] != 0)
+ {
assert(i <= p->g->nsub);
EMIT(OBACK_, i);
assert(p->pbegin[i] != 0);
assert(OP(p->strip[p->pbegin[i]]) == OLPAREN);
assert(OP(p->strip[p->pend[i]]) == ORPAREN);
- dupl(p, p->pbegin[i]+1, p->pend[i]);
+ dupl(p, p->pbegin[i] + 1, p->pend[i]);
EMIT(O_BACK, i);
- } else
+ }
+ else
SETERROR(REG_ESUBREG);
p->g->backrefs = 1;
break;
@@ -606,57 +642,69 @@ int starordinary; /* is a leading * an ordinary character? */
REQUIRE(starordinary, REG_BADRPT);
/* FALLTHROUGH */
default:
- ordinary(p, c &~ BACKSL);
+ ordinary(p, c & ~BACKSL);
break;
}
- if (EAT('*')) { /* implemented as +? */
+ if (EAT('*'))
+ { /* implemented as +? */
/* this case does not require the (y|) trick, noKLUDGE */
INSERT(OPLUS_, pos);
ASTERN(O_PLUS, pos);
INSERT(OQUEST_, pos);
ASTERN(O_QUEST, pos);
- } else if (EATTWO('\\', '{')) {
+ }
+ else if (EATTWO('\\', '{'))
+ {
count = p_count(p);
- if (EAT(',')) {
- if (MORE() && isdigit(PEEK())) {
+ if (EAT(','))
+ {
+ if (MORE() && isdigit(PEEK()))
+ {
count2 = p_count(p);
REQUIRE(count <= count2, REG_BADBR);
- } else /* single number with comma */
+ }
+ else
+/* single number with comma */
count2 = INFINITY;
- } else /* just a single number */
+ }
+ else
+/* just a single number */
count2 = count;
repeat(p, pos, count, count2);
- if (!EATTWO('\\', '}')) { /* error heuristics */
+ if (!EATTWO('\\', '}'))
+ { /* error heuristics */
while (MORE() && !SEETWO('\\', '}'))
NEXT();
REQUIRE(MORE(), REG_EBRACE);
SETERROR(REG_BADBR);
}
- } else if (c == (unsigned char)'$') /* $ (but not \$) ends it */
- return(1);
+ }
+ else if (c == (unsigned char) '$') /* $ (but not \$) ends it */
+ return (1);
- return(0);
+ return (0);
}
/*
- p_count - parse a repetition count
== static int p_count(register struct parse *p);
*/
-static int /* the value */
+static int /* the value */
p_count(p)
register struct parse *p;
{
- register int count = 0;
- register int ndigits = 0;
+ register int count = 0;
+ register int ndigits = 0;
- while (MORE() && isdigit(PEEK()) && count <= DUPMAX) {
- count = count*10 + (GETNEXT() - '0');
+ while (MORE() && isdigit(PEEK()) && count <= DUPMAX)
+ {
+ count = count * 10 + (GETNEXT() - '0');
ndigits++;
}
REQUIRE(ndigits > 0 && count <= DUPMAX, REG_BADBR);
- return(count);
+ return (count);
}
/*
@@ -670,23 +718,25 @@ static void
p_bracket(p)
register struct parse *p;
{
- register cset *cs = allocset(p);
- register int invert = 0;
+ register cset *cs = allocset(p);
+ register int invert = 0;
/* Dept of Truly Sickening Special-Case Kludges */
- if (p->next + 5 < p->end && strncmp(p->next, "[:<:]]", 6) == 0) {
+ if (p->next + 5 < p->end && strncmp(p->next, "[:<:]]", 6) == 0)
+ {
EMIT(OBOW, 0);
NEXTn(6);
return;
}
- if (p->next + 5 < p->end && strncmp(p->next, "[:>:]]", 6) == 0) {
+ if (p->next + 5 < p->end && strncmp(p->next, "[:>:]]", 6) == 0)
+ {
EMIT(OEOW, 0);
NEXTn(6);
return;
}
if (EAT('^'))
- invert++; /* make note to invert set at end */
+ invert++; /* make note to invert set at end */
if (EAT(']'))
CHadd(cs, ']');
else if (EAT('-'))
@@ -697,15 +747,17 @@ register struct parse *p;
CHadd(cs, '-');
MUSTEAT(']', REG_EBRACK);
- if (p->error != 0) /* don't mess things up further */
+ if (p->error != 0) /* don't mess things up further */
return;
- if (p->g->cflags&REG_ICASE) {
- register int i;
- register int ci;
+ if (p->g->cflags & REG_ICASE)
+ {
+ register int i;
+ register int ci;
for (i = p->g->csetsize - 1; i >= 0; i--)
- if (CHIN(cs, i) && isalpha(i)) {
+ if (CHIN(cs, i) && isalpha(i))
+ {
ci = othercase(i);
if (ci != i)
CHadd(cs, ci);
@@ -713,26 +765,29 @@ register struct parse *p;
if (cs->multis != NULL)
mccase(p, cs);
}
- if (invert) {
- register int i;
+ if (invert)
+ {
+ register int i;
for (i = p->g->csetsize - 1; i >= 0; i--)
if (CHIN(cs, i))
CHsub(cs, i);
else
CHadd(cs, i);
- if (p->g->cflags&REG_NEWLINE)
+ if (p->g->cflags & REG_NEWLINE)
CHsub(cs, '\n');
if (cs->multis != NULL)
mcinvert(p, cs);
}
- assert(cs->multis == NULL); /* xxx */
+ assert(cs->multis == NULL); /* xxx */
- if (nch(p, cs) == 1) { /* optimize singleton sets */
+ if (nch(p, cs) == 1)
+ { /* optimize singleton sets */
ordinary(p, firstch(p, cs));
freeset(p, cs);
- } else
+ }
+ else
EMIT(OANYOF, freezeset(p, cs));
}
@@ -743,28 +798,31 @@ register struct parse *p;
static void
p_b_term(p, cs)
register struct parse *p;
-register cset *cs;
+register cset *cs;
{
- register char c;
- register char start, finish;
- register int i;
+ register char c;
+ register char start,
+ finish;
+ register int i;
/* classify what we've got */
- switch ((MORE()) ? PEEK() : '\0') {
+ switch ((MORE()) ? PEEK() : '\0')
+ {
case '[':
c = (MORE2()) ? PEEK2() : '\0';
break;
case '-':
SETERROR(REG_ERANGE);
- return; /* NOTE RETURN */
+ return; /* NOTE RETURN */
break;
default:
c = '\0';
break;
}
- switch (c) {
- case ':': /* character class */
+ switch (c)
+ {
+ case ':': /* character class */
NEXT2();
REQUIRE(MORE(), REG_EBRACK);
c = PEEK();
@@ -773,7 +831,7 @@ register cset *cs;
REQUIRE(MORE(), REG_EBRACK);
REQUIRE(EATTWO(':', ']'), REG_ECTYPE);
break;
- case '=': /* equivalence class */
+ case '=': /* equivalence class */
NEXT2();
REQUIRE(MORE(), REG_EBRACK);
c = PEEK();
@@ -782,17 +840,19 @@ register cset *cs;
REQUIRE(MORE(), REG_EBRACK);
REQUIRE(EATTWO('=', ']'), REG_ECOLLATE);
break;
- default: /* symbol, ordinary character, or range */
+ default: /* symbol, ordinary character, or range */
/* xxx revision needed for multichar stuff */
start = p_b_symbol(p);
- if (SEE('-') && MORE2() && PEEK2() != ']') {
+ if (SEE('-') && MORE2() && PEEK2() != ']')
+ {
/* range */
NEXT();
if (EAT('-'))
finish = '-';
else
finish = p_b_symbol(p);
- } else
+ }
+ else
finish = start;
/* xxx what about signed chars here... */
REQUIRE(start <= finish, REG_ERANGE);
@@ -809,13 +869,13 @@ register cset *cs;
static void
p_b_cclass(p, cs)
register struct parse *p;
-register cset *cs;
+register cset *cs;
{
- register char *sp = p->next;
+ register char *sp = p->next;
register struct cclass *cp;
register size_t len;
- register char *u;
- register char c;
+ register char *u;
+ register char c;
while (MORE() && isalpha(PEEK()))
NEXT();
@@ -823,7 +883,8 @@ register cset *cs;
for (cp = cclasses; cp->name != NULL; cp++)
if (strncmp(cp->name, sp, len) == 0 && cp->name[len] == '\0')
break;
- if (cp->name == NULL) {
+ if (cp->name == NULL)
+ {
/* oops, didn't find it */
SETERROR(REG_ECTYPE);
return;
@@ -845,9 +906,9 @@ register cset *cs;
static void
p_b_eclass(p, cs)
register struct parse *p;
-register cset *cs;
+register cset *cs;
{
- register char c;
+ register char c;
c = p_b_coll_elem(p, '=');
CHadd(cs, c);
@@ -857,66 +918,68 @@ register cset *cs;
- p_b_symbol - parse a character or [..]ed multicharacter collating symbol
== static char p_b_symbol(register struct parse *p);
*/
-static char /* value of symbol */
+static char /* value of symbol */
p_b_symbol(p)
register struct parse *p;
{
- register char value;
+ register char value;
REQUIRE(MORE(), REG_EBRACK);
if (!EATTWO('[', '.'))
- return(GETNEXT());
+ return (GETNEXT());
/* collating symbol */
value = p_b_coll_elem(p, '.');
REQUIRE(EATTWO('.', ']'), REG_ECOLLATE);
- return(value);
+ return (value);
}
/*
- p_b_coll_elem - parse a collating-element name and look it up
== static char p_b_coll_elem(register struct parse *p, int endc);
*/
-static char /* value of collating element */
+static char /* value of collating element */
p_b_coll_elem(p, endc)
register struct parse *p;
-int endc; /* name ended by endc,']' */
+int endc; /* name ended by endc,']' */
{
- register char *sp = p->next;
+ register char *sp = p->next;
register struct cname *cp;
- register int len;
+ register int len;
while (MORE() && !SEETWO(endc, ']'))
NEXT();
- if (!MORE()) {
+ if (!MORE())
+ {
SETERROR(REG_EBRACK);
- return(0);
+ return (0);
}
len = p->next - sp;
for (cp = cnames; cp->name != NULL; cp++)
if (strncmp(cp->name, sp, len) == 0 && cp->name[len] == '\0')
- return(cp->code); /* known name */
+ return (cp->code); /* known name */
if (len == 1)
- return(*sp); /* single character */
- SETERROR(REG_ECOLLATE); /* neither */
- return(0);
+ return (*sp); /* single character */
+ SETERROR(REG_ECOLLATE); /* neither */
+ return (0);
}
/*
- othercase - return the case counterpart of an alphabetic
== static char othercase(int ch);
*/
-static char /* if no counterpart, return ch */
+static char /* if no counterpart, return ch */
othercase(ch)
-int ch;
+int ch;
{
assert(isalpha(ch));
if (isupper(ch))
- return(tolower(ch));
+ return (tolower(ch));
else if (islower(ch))
- return(toupper(ch));
- else /* peculiar, but could happen */
- return(ch);
+ return (toupper(ch));
+ else
+/* peculiar, but could happen */
+ return (ch);
}
/*
@@ -928,20 +991,20 @@ int ch;
static void
bothcases(p, ch)
register struct parse *p;
-int ch;
+int ch;
{
- register char *oldnext = p->next;
- register char *oldend = p->end;
- char bracket[3];
+ register char *oldnext = p->next;
+ register char *oldend = p->end;
+ char bracket[3];
- assert(othercase(ch) != ch); /* p_bracket() would recurse */
+ assert(othercase(ch) != ch);/* p_bracket() would recurse */
p->next = bracket;
- p->end = bracket+2;
+ p->end = bracket + 2;
bracket[0] = ch;
bracket[1] = ']';
bracket[2] = '\0';
p_bracket(p);
- assert(p->next == bracket+2);
+ assert(p->next == bracket + 2);
p->next = oldnext;
p->end = oldend;
}
@@ -953,14 +1016,15 @@ int ch;
static void
ordinary(p, ch)
register struct parse *p;
-register int ch;
+register int ch;
{
register cat_t *cap = p->g->categories;
- if ((p->g->cflags&REG_ICASE) && isalpha(ch) && othercase(ch) != ch)
+ if ((p->g->cflags & REG_ICASE) && isalpha(ch) && othercase(ch) != ch)
bothcases(p, ch);
- else {
- EMIT(OCHAR, (unsigned char)ch);
+ else
+ {
+ EMIT(OCHAR, (unsigned char) ch);
if (cap[ch] == 0)
cap[ch] = p->g->ncategories++;
}
@@ -976,18 +1040,18 @@ static void
nonnewline(p)
register struct parse *p;
{
- register char *oldnext = p->next;
- register char *oldend = p->end;
- char bracket[4];
+ register char *oldnext = p->next;
+ register char *oldend = p->end;
+ char bracket[4];
p->next = bracket;
- p->end = bracket+3;
+ p->end = bracket + 3;
bracket[0] = '^';
bracket[1] = '\n';
bracket[2] = ']';
bracket[3] = '\0';
p_bracket(p);
- assert(p->next == bracket+3);
+ assert(p->next == bracket + 3);
p->next = oldnext;
p->end = oldend;
}
@@ -999,42 +1063,45 @@ register struct parse *p;
static void
repeat(p, start, from, to)
register struct parse *p;
-sopno start; /* operand from here to end of strip */
-int from; /* repeated from this number */
-int to; /* to this number of times (maybe INFINITY) */
+sopno start; /* operand from here to end of strip */
+int from; /* repeated from this number */
+int to; /* to this number of times (maybe
+ * INFINITY) */
{
- register sopno finish = HERE();
-# define N 2
-# define INF 3
-# define REP(f, t) ((f)*8 + (t))
-# define MAP(n) (((n) <= 1) ? (n) : ((n) == INFINITY) ? INF : N)
- register sopno copy;
-
- if (p->error != 0) /* head off possible runaway recursion */
+ register sopno finish = HERE();
+
+#define N 2
+#define INF 3
+#define REP(f, t) ((f)*8 + (t))
+#define MAP(n) (((n) <= 1) ? (n) : ((n) == INFINITY) ? INF : N)
+ register sopno copy;
+
+ if (p->error != 0) /* head off possible runaway recursion */
return;
assert(from <= to);
- switch (REP(MAP(from), MAP(to))) {
- case REP(0, 0): /* must be user doing this */
- DROP(finish-start); /* drop the operand */
+ switch (REP(MAP(from), MAP(to)))
+ {
+ case REP(0, 0): /* must be user doing this */
+ DROP(finish - start); /* drop the operand */
break;
- case REP(0, 1): /* as x{1,1}? */
- case REP(0, N): /* as x{1,n}? */
- case REP(0, INF): /* as x{1,}? */
+ case REP(0, 1): /* as x{1,1}? */
+ case REP(0, N): /* as x{1,n}? */
+ case REP(0, INF): /* as x{1,}? */
/* KLUDGE: emit y? as (y|) until subtle bug gets fixed */
- INSERT(OCH_, start); /* offset is wrong... */
- repeat(p, start+1, 1, to);
+ INSERT(OCH_, start); /* offset is wrong... */
+ repeat(p, start + 1, 1, to);
ASTERN(OOR1, start);
AHEAD(start); /* ... fix it */
EMIT(OOR2, 0);
AHEAD(THERE());
ASTERN(O_CH, THERETHERE());
break;
- case REP(1, 1): /* trivial case */
+ case REP(1, 1): /* trivial case */
/* done */
break;
- case REP(1, N): /* as x?x{1,n-1} */
+ case REP(1, N): /* as x?x{1,n-1} */
/* KLUDGE: emit y? as (y|) until subtle bug gets fixed */
INSERT(OCH_, start);
ASTERN(OOR1, start);
@@ -1042,23 +1109,23 @@ int to; /* to this number of times (maybe INFINITY) */
EMIT(OOR2, 0); /* offset very wrong... */
AHEAD(THERE()); /* ...so fix it */
ASTERN(O_CH, THERETHERE());
- copy = dupl(p, start+1, finish+1);
- assert(copy == finish+4);
- repeat(p, copy, 1, to-1);
+ copy = dupl(p, start + 1, finish + 1);
+ assert(copy == finish + 4);
+ repeat(p, copy, 1, to - 1);
break;
- case REP(1, INF): /* as x+ */
+ case REP(1, INF): /* as x+ */
INSERT(OPLUS_, start);
ASTERN(O_PLUS, start);
break;
- case REP(N, N): /* as xx{m-1,n-1} */
+ case REP(N, N): /* as xx{m-1,n-1} */
copy = dupl(p, start, finish);
- repeat(p, copy, from-1, to-1);
+ repeat(p, copy, from - 1, to - 1);
break;
- case REP(N, INF): /* as xx{n-1,INF} */
+ case REP(N, INF): /* as xx{n-1,INF} */
copy = dupl(p, start, finish);
- repeat(p, copy, from-1, to);
+ repeat(p, copy, from - 1, to);
break;
- default: /* "can't happen" */
+ default: /* "can't happen" */
SETERROR(REG_ASSERT); /* just in case */
break;
}
@@ -1068,71 +1135,74 @@ int to; /* to this number of times (maybe INFINITY) */
- seterr - set an error condition
== static int seterr(register struct parse *p, int e);
*/
-static int /* useless but makes type checking happy */
+static int /* useless but makes type checking happy */
seterr(p, e)
register struct parse *p;
-int e;
+int e;
{
- if (p->error == 0) /* keep earliest error condition */
+ if (p->error == 0) /* keep earliest error condition */
p->error = e;
- p->next = nuls; /* try to bring things to a halt */
+ p->next = nuls; /* try to bring things to a halt */
p->end = nuls;
- return(0); /* make the return value well-defined */
+ return (0); /* make the return value well-defined */
}
/*
- allocset - allocate a set of characters for []
== static cset *allocset(register struct parse *p);
*/
-static cset *
+static cset *
allocset(p)
register struct parse *p;
{
- register int no = p->g->ncsets++;
+ register int no = p->g->ncsets++;
register size_t nc;
register size_t nbytes;
- register cset *cs;
- register size_t css = (size_t)p->g->csetsize;
- register int i;
+ register cset *cs;
+ register size_t css = (size_t) p->g->csetsize;
+ register int i;
- if (no >= p->ncsalloc) { /* need another column of space */
+ if (no >= p->ncsalloc)
+ { /* need another column of space */
p->ncsalloc += CHAR_BIT;
nc = p->ncsalloc;
assert(nc % CHAR_BIT == 0);
nbytes = nc / CHAR_BIT * css;
if (p->g->sets == NULL)
- p->g->sets = (cset *)malloc(nc * sizeof(cset));
+ p->g->sets = (cset *) malloc(nc * sizeof(cset));
else
- p->g->sets = (cset *)realloc((char *)p->g->sets,
- nc * sizeof(cset));
+ p->g->sets = (cset *) realloc((char *) p->g->sets,
+ nc * sizeof(cset));
if (p->g->setbits == NULL)
- p->g->setbits = (uch *)malloc(nbytes);
- else {
- p->g->setbits = (uch *)realloc((char *)p->g->setbits,
- nbytes);
+ p->g->setbits = (uch *) malloc(nbytes);
+ else
+ {
+ p->g->setbits = (uch *) realloc((char *) p->g->setbits,
+ nbytes);
/* xxx this isn't right if setbits is now NULL */
for (i = 0; i < no; i++)
- p->g->sets[i].ptr = p->g->setbits + css*(i/CHAR_BIT);
+ p->g->sets[i].ptr = p->g->setbits + css * (i / CHAR_BIT);
}
if (p->g->sets != NULL && p->g->setbits != NULL)
- memset((char *)p->g->setbits + (nbytes - css),
- 0, css);
- else {
+ memset((char *) p->g->setbits + (nbytes - css),
+ 0, css);
+ else
+ {
no = 0;
SETERROR(REG_ESPACE);
/* caller's responsibility not to do set ops */
}
}
- assert(p->g->sets != NULL); /* xxx */
+ assert(p->g->sets != NULL); /* xxx */
cs = &p->g->sets[no];
- cs->ptr = p->g->setbits + css*((no)/CHAR_BIT);
+ cs->ptr = p->g->setbits + css * ((no) / CHAR_BIT);
cs->mask = 1 << ((no) % CHAR_BIT);
cs->hash = 0;
cs->smultis = 0;
cs->multis = NULL;
- return(cs);
+ return (cs);
}
/*
@@ -1142,15 +1212,15 @@ register struct parse *p;
static void
freeset(p, cs)
register struct parse *p;
-register cset *cs;
+register cset *cs;
{
- register int i;
- register cset *top = &p->g->sets[p->g->ncsets];
- register size_t css = (size_t)p->g->csetsize;
+ register int i;
+ register cset *top = &p->g->sets[p->g->ncsets];
+ register size_t css = (size_t) p->g->csetsize;
for (i = 0; i < css; i++)
CHsub(cs, i);
- if (cs == top-1) /* recover only the easy case */
+ if (cs == top - 1) /* recover only the easy case */
p->g->ncsets--;
}
@@ -1160,24 +1230,25 @@ register cset *cs;
*
* The main task here is merging identical sets. This is usually a waste
* of time (although the hash code minimizes the overhead), but can win
- * big if REG_ICASE is being used. REG_ICASE, by the way, is why the hash
+ * big if REG_ICASE is being used. REG_ICASE, by the way, is why the hash
* is done using addition rather than xor -- all ASCII [aA] sets xor to
* the same value!
*/
-static int /* set number */
+static int /* set number */
freezeset(p, cs)
register struct parse *p;
-register cset *cs;
+register cset *cs;
{
- register uch h = cs->hash;
- register int i;
- register cset *top = &p->g->sets[p->g->ncsets];
- register cset *cs2;
- register size_t css = (size_t)p->g->csetsize;
+ register uch h = cs->hash;
+ register int i;
+ register cset *top = &p->g->sets[p->g->ncsets];
+ register cset *cs2;
+ register size_t css = (size_t) p->g->csetsize;
/* look for an earlier one which is the same */
for (cs2 = &p->g->sets[0]; cs2 < top; cs2++)
- if (cs2->hash == h && cs2 != cs) {
+ if (cs2->hash == h && cs2 != cs)
+ {
/* maybe */
for (i = 0; i < css; i++)
if (!!CHIN(cs2, i) != !!CHIN(cs, i))
@@ -1186,31 +1257,32 @@ register cset *cs;
break; /* yes */
}
- if (cs2 < top) { /* found one */
+ if (cs2 < top)
+ { /* found one */
freeset(p, cs);
cs = cs2;
}
- return((int)(cs - p->g->sets));
+ return ((int) (cs - p->g->sets));
}
/*
- firstch - return first character in a set (which must have at least one)
== static int firstch(register struct parse *p, register cset *cs);
*/
-static int /* character; there is no "none" value */
+static int /* character; there is no "none" value */
firstch(p, cs)
register struct parse *p;
-register cset *cs;
+register cset *cs;
{
- register int i;
- register size_t css = (size_t)p->g->csetsize;
+ register int i;
+ register size_t css = (size_t) p->g->csetsize;
for (i = 0; i < css; i++)
if (CHIN(cs, i))
- return((char)i);
+ return ((char) i);
assert(never);
- return(0); /* arbitrary */
+ return (0); /* arbitrary */
}
/*
@@ -1220,28 +1292,28 @@ register cset *cs;
static int
nch(p, cs)
register struct parse *p;
-register cset *cs;
+register cset *cs;
{
- register int i;
- register size_t css = (size_t)p->g->csetsize;
- register int n = 0;
+ register int i;
+ register size_t css = (size_t) p->g->csetsize;
+ register int n = 0;
for (i = 0; i < css; i++)
if (CHIN(cs, i))
n++;
- return(n);
+ return (n);
}
/*
- mcadd - add a collating element to a cset
== static void mcadd(register struct parse *p, register cset *cs, \
- == register char *cp);
+ == register char *cp);
*/
static void
mcadd(p, cs, cp)
register struct parse *p;
-register cset *cs;
-register char *cp;
+register cset *cs;
+register char *cp;
{
register size_t oldend = cs->smultis;
@@ -1250,7 +1322,8 @@ register char *cp;
cs->multis = malloc(cs->smultis);
else
cs->multis = realloc(cs->multis, cs->smultis);
- if (cs->multis == NULL) {
+ if (cs->multis == NULL)
+ {
SETERROR(REG_ESPACE);
return;
}
@@ -1269,22 +1342,22 @@ mcsub(cs, cp)
register cset *cs;
register char *cp;
{
- register char *fp = mcfind(cs, cp);
- register size_t len = strlen(fp);
-
- assert(fp != NULL);
- memmove(fp, fp + len + 1,
- cs->smultis - (fp + len + 1 - cs->multis));
- cs->smultis -= len;
-
- if (cs->smultis == 0) {
- free(cs->multis);
- cs->multis = NULL;
- return;
- }
+ register char *fp = mcfind(cs, cp);
+ register size_t len = strlen(fp);
+
+ assert(fp != NULL);
+ memmove(fp, fp + len + 1,
+ cs->smultis - (fp + len + 1 - cs->multis));
+ cs->smultis -= len;
+
+ if (cs->smultis == 0) {
+ free(cs->multis);
+ cs->multis = NULL;
+ return;
+ }
- cs->multis = realloc(cs->multis, cs->smultis);
- assert(cs->multis != NULL);
+ cs->multis = realloc(cs->multis, cs->smultis);
+ assert(cs->multis != NULL);
}
*/
@@ -1298,7 +1371,7 @@ mcin(cs, cp)
register cset *cs;
register char *cp;
{
- return(mcfind(cs, cp) != NULL);
+ return(mcfind(cs, cp) != NULL);
}
*/
@@ -1312,14 +1385,14 @@ mcfind(cs, cp)
register cset *cs;
register char *cp;
{
- register char *p;
+ register char *p;
- if (cs->multis == NULL)
+ if (cs->multis == NULL)
+ return(NULL);
+ for (p = cs->multis; *p != '\0'; p += strlen(p) + 1)
+ if (strcmp(cp, p) == 0)
+ return(p);
return(NULL);
- for (p = cs->multis; *p != '\0'; p += strlen(p) + 1)
- if (strcmp(cp, p) == 0)
- return(p);
- return(NULL);
}
*/
/*
@@ -1332,9 +1405,9 @@ register char *cp;
static void
mcinvert(p, cs)
register struct parse *p;
-register cset *cs;
+register cset *cs;
{
- assert(cs->multis == NULL); /* xxx */
+ assert(cs->multis == NULL); /* xxx */
}
/*
@@ -1347,51 +1420,51 @@ register cset *cs;
static void
mccase(p, cs)
register struct parse *p;
-register cset *cs;
+register cset *cs;
{
- assert(cs->multis == NULL); /* xxx */
+ assert(cs->multis == NULL); /* xxx */
}
/*
- isinsets - is this character in any sets?
== static int isinsets(register struct re_guts *g, int c);
*/
-static int /* predicate */
+static int /* predicate */
isinsets(g, c)
register struct re_guts *g;
-int c;
+int c;
{
- register uch *col;
- register int i;
- register int ncols = (g->ncsets+(CHAR_BIT-1)) / CHAR_BIT;
- register unsigned uc = (unsigned char)c;
+ register uch *col;
+ register int i;
+ register int ncols = (g->ncsets + (CHAR_BIT - 1)) / CHAR_BIT;
+ register unsigned uc = (unsigned char) c;
for (i = 0, col = g->setbits; i < ncols; i++, col += g->csetsize)
if (col[uc] != 0)
- return(1);
- return(0);
+ return (1);
+ return (0);
}
/*
- samesets - are these two characters in exactly the same sets?
== static int samesets(register struct re_guts *g, int c1, int c2);
*/
-static int /* predicate */
+static int /* predicate */
samesets(g, c1, c2)
register struct re_guts *g;
-int c1;
-int c2;
+int c1;
+int c2;
{
- register uch *col;
- register int i;
- register int ncols = (g->ncsets+(CHAR_BIT-1)) / CHAR_BIT;
- register unsigned uc1 = (unsigned char)c1;
- register unsigned uc2 = (unsigned char)c2;
+ register uch *col;
+ register int i;
+ register int ncols = (g->ncsets + (CHAR_BIT - 1)) / CHAR_BIT;
+ register unsigned uc1 = (unsigned char) c1;
+ register unsigned uc2 = (unsigned char) c2;
for (i = 0, col = g->setbits; i < ncols; i++, col += g->csetsize)
if (col[uc1] != col[uc2])
- return(0);
- return(1);
+ return (0);
+ return (1);
}
/*
@@ -1400,23 +1473,24 @@ int c2;
*/
static void
categorize(p, g)
-struct parse *p;
+struct parse *p;
register struct re_guts *g;
{
register cat_t *cats = g->categories;
- register int c;
- register int c2;
- register cat_t cat;
+ register int c;
+ register int c2;
+ register 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)) {
+ if (cats[c] == 0 && isinsets(g, c))
+ {
cat = g->ncategories++;
cats[c] = cat;
- for (c2 = c+1; c2 <= CHAR_MAX; c2++)
+ for (c2 = c + 1; c2 <= CHAR_MAX; c2++)
if (cats[c2] == 0 && samesets(g, c, c2))
cats[c2] = cat;
}
@@ -1426,24 +1500,24 @@ register struct re_guts *g;
- dupl - emit a duplicate of a bunch of sops
== static sopno dupl(register struct parse *p, sopno start, sopno finish);
*/
-static sopno /* start of duplicate */
+static sopno /* start of duplicate */
dupl(p, start, finish)
register struct parse *p;
-sopno start; /* from here */
-sopno finish; /* to this less one */
+sopno start; /* from here */
+sopno finish; /* to this less one */
{
- register sopno ret = HERE();
- register sopno len = finish - start;
+ register sopno ret = HERE();
+ register sopno len = finish - start;
assert(finish >= start);
if (len == 0)
- return(ret);
- enlarge(p, p->ssize + len); /* this many unexpected additions */
+ return (ret);
+ enlarge(p, p->ssize + len); /* this many unexpected additions */
assert(p->ssize >= p->slen + len);
- memcpy((char *)(p->strip + p->slen),
- (char *)(p->strip + start), (size_t)len*sizeof(sop));
+ memcpy((char *) (p->strip + p->slen),
+ (char *) (p->strip + start), (size_t) len * sizeof(sop));
p->slen += len;
- return(ret);
+ return (ret);
}
/*
@@ -1457,19 +1531,19 @@ sopno finish; /* to this less one */
static void
doemit(p, op, opnd)
register struct parse *p;
-sop op;
-size_t opnd;
+sop op;
+size_t opnd;
{
/* avoid making error situations worse */
if (p->error != 0)
return;
/* deal with oversize operands ("can't happen", more or less) */
- assert(opnd < 1<<OPSHIFT);
+ assert(opnd < 1 << OPSHIFT);
/* deal with undersized strip */
if (p->slen >= p->ssize)
- enlarge(p, (p->ssize+1) / 2 * 3); /* +50% */
+ enlarge(p, (p->ssize + 1) / 2 * 3); /* +50% */
assert(p->slen < p->ssize);
/* finally, it's all reduced to the easy case */
@@ -1483,36 +1557,39 @@ size_t opnd;
static void
doinsert(p, op, opnd, pos)
register struct parse *p;
-sop op;
-size_t opnd;
-sopno pos;
+sop op;
+size_t opnd;
+sopno pos;
{
- register sopno sn;
- register sop s;
- register int i;
+ register sopno sn;
+ register sop s;
+ register int i;
/* avoid making error situations worse */
if (p->error != 0)
return;
sn = HERE();
- EMIT(op, opnd); /* do checks, ensure space */
- assert(HERE() == sn+1);
+ EMIT(op, opnd); /* do checks, ensure space */
+ assert(HERE() == sn + 1);
s = p->strip[sn];
/* adjust paren pointers */
assert(pos > 0);
- for (i = 1; i < NPAREN; i++) {
- if (p->pbegin[i] >= pos) {
+ for (i = 1; i < NPAREN; i++)
+ {
+ if (p->pbegin[i] >= pos)
+ {
p->pbegin[i]++;
}
- if (p->pend[i] >= pos) {
+ if (p->pend[i] >= pos)
+ {
p->pend[i]++;
}
}
- memmove((char *)&p->strip[pos+1], (char *)&p->strip[pos],
- (HERE()-pos-1)*sizeof(sop));
+ memmove((char *) &p->strip[pos + 1], (char *) &p->strip[pos],
+ (HERE() - pos - 1) * sizeof(sop));
p->strip[pos] = s;
}
@@ -1523,14 +1600,14 @@ sopno pos;
static void
dofwd(p, pos, value)
register struct parse *p;
-register sopno pos;
-sop value;
+register sopno pos;
+sop value;
{
/* avoid making error situations worse */
if (p->error != 0)
return;
- assert(value < 1<<OPSHIFT);
+ assert(value < 1 << OPSHIFT);
p->strip[pos] = OP(p->strip[pos]) | value;
}
@@ -1541,15 +1618,16 @@ sop value;
static void
enlarge(p, size)
register struct parse *p;
-register sopno size;
+register sopno size;
{
- register sop *sp;
+ register sop *sp;
if (p->ssize >= size)
return;
- sp = (sop *)realloc(p->strip, size*sizeof(sop));
- if (sp == NULL) {
+ sp = (sop *) realloc(p->strip, size * sizeof(sop));
+ if (sp == NULL)
+ {
SETERROR(REG_ESPACE);
return;
}
@@ -1567,8 +1645,9 @@ register struct parse *p;
register struct re_guts *g;
{
g->nstates = p->slen;
- g->strip = (sop *)realloc((char *)p->strip, p->slen * sizeof(sop));
- if (g->strip == NULL) {
+ g->strip = (sop *) realloc((char *) p->strip, p->slen * sizeof(sop));
+ if (g->strip == NULL)
+ {
SETERROR(REG_ESPACE);
g->strip = p->strip;
}
@@ -1586,16 +1665,16 @@ register struct re_guts *g;
*/
static void
findmust(p, g)
-struct parse *p;
+struct parse *p;
register struct re_guts *g;
{
- register sop *scan;
- sop *start = 0;
- register sop *newstart = 0;
- register sopno newlen;
- register sop s;
- register char *cp;
- register sopno i;
+ register sop *scan;
+ sop *start = 0;
+ register sop *newstart = 0;
+ register sopno newlen;
+ register sop s;
+ register char *cp;
+ register sopno i;
/* avoid making error situations worse */
if (p->error != 0)
@@ -1604,34 +1683,39 @@ register struct re_guts *g;
/* find the longest OCHAR sequence in strip */
newlen = 0;
scan = g->strip + 1;
- do {
+ do
+ {
s = *scan++;
- switch (OP(s)) {
- case OCHAR: /* sequence member */
- if (newlen == 0) /* new sequence */
+ switch (OP(s))
+ {
+ case OCHAR: /* sequence member */
+ if (newlen == 0) /* new sequence */
newstart = scan - 1;
newlen++;
break;
- case OPLUS_: /* things that don't break one */
+ case OPLUS_: /* things that don't break one */
case OLPAREN:
case ORPAREN:
break;
- case OQUEST_: /* things that must be skipped */
+ case OQUEST_: /* things that must be skipped */
case OCH_:
scan--;
- do {
+ do
+ {
scan += OPND(s);
s = *scan;
/* assert() interferes w debug printouts */
if (OP(s) != O_QUEST && OP(s) != O_CH &&
- OP(s) != OOR2) {
+ OP(s) != OOR2)
+ {
g->iflags |= BAD;
return;
}
} while (OP(s) != O_QUEST && OP(s) != O_CH);
/* fallthrough */
- default: /* things that break a sequence */
- if (newlen > g->mlen) { /* ends one */
+ default: /* things that break a sequence */
+ if (newlen > g->mlen)
+ { /* ends one */
start = newstart;
g->mlen = newlen;
}
@@ -1640,48 +1724,52 @@ register struct re_guts *g;
}
} while (OP(s) != OEND);
- if (g->mlen == 0) /* there isn't one */
+ if (g->mlen == 0) /* there isn't one */
return;
/* turn it into a character string */
- g->must = malloc((size_t)g->mlen + 1);
- if (g->must == NULL) { /* argh; just forget it */
+ g->must = malloc((size_t) g->mlen + 1);
+ if (g->must == NULL)
+ { /* argh; just forget it */
g->mlen = 0;
return;
}
cp = g->must;
scan = start;
- for (i = g->mlen; i > 0; i--) {
+ for (i = g->mlen; i > 0; i--)
+ {
while (OP(s = *scan++) != OCHAR)
continue;
assert(cp < g->must + g->mlen);
- *cp++ = (char)OPND(s);
+ *cp++ = (char) OPND(s);
}
assert(cp == g->must + g->mlen);
- *cp++ = '\0'; /* just on general principles */
+ *cp++ = '\0'; /* just on general principles */
}
/*
- pluscount - count + nesting
== static sopno pluscount(register struct parse *p, register struct re_guts *g);
*/
-static sopno /* nesting depth */
+static sopno /* nesting depth */
pluscount(p, g)
-struct parse *p;
+struct parse *p;
register struct re_guts *g;
{
- register sop *scan;
- register sop s;
- register sopno plusnest = 0;
- register sopno maxnest = 0;
+ register sop *scan;
+ register sop s;
+ register sopno plusnest = 0;
+ register sopno maxnest = 0;
if (p->error != 0)
- return(0); /* there may not be an OEND */
+ return (0); /* there may not be an OEND */
scan = g->strip + 1;
- do {
+ do
+ {
s = *scan++;
- switch (OP(s)) {
+ switch (OP(s))
+ {
case OPLUS_:
plusnest++;
break;
@@ -1694,5 +1782,5 @@ register struct re_guts *g;
} while (OP(s) != OEND);
if (plusnest != 0)
g->iflags |= BAD;
- return(maxnest);
+ return (maxnest);
}
generated by cgit v1.2.3 (git 2.25.1) at 2025-05-22 10:47:45 +0000