commons-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From mt...@apache.org
Subject svn commit: r807635 [2/2] - in /commons/sandbox/runtime/trunk/src/main/native: ./ include/ shared/ srclib/regex/ test/
Date Tue, 25 Aug 2009 13:57:08 GMT
Added: commons/sandbox/runtime/trunk/src/main/native/srclib/regex/regcomp.c
URL: http://svn.apache.org/viewvc/commons/sandbox/runtime/trunk/src/main/native/srclib/regex/regcomp.c?rev=807635&view=auto
==============================================================================
--- commons/sandbox/runtime/trunk/src/main/native/srclib/regex/regcomp.c (added)
+++ commons/sandbox/runtime/trunk/src/main/native/srclib/regex/regcomp.c Tue Aug 25 13:57:05 2009
@@ -0,0 +1,1514 @@
+/*-
+ * Copyright (c) 1992, 1993, 1994 Henry Spencer.
+ * Copyright (c) 1992, 1993, 1994
+ *	The Regents of the University of California.  All rights reserved.
+ *
+ * This code is derived from software contributed to Berkeley by
+ * Henry Spencer.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * 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.
+ * 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.
+ * 3. 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.
+ *
+ * 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
+ * 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)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE.
+ *
+ *	@(#)regcomp.c	8.5 (Berkeley) 3/20/94
+ */
+
+#include "acr.h"
+#include "acr_private.h"
+#include "acr_arch.h"
+
+#include "regex.h"
+
+#include "utils.h"
+#include "regex2.h"
+
+#include "cclass.h"
+#include "cname.h"
+
+/*
+ * 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 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) */
+};
+
+static void p_ere(struct parse *, int);
+static void p_ere_exp(struct parse *);
+static void p_str(struct parse *);
+static void p_bre(struct parse *, int, int);
+static int p_simp_re(struct parse *, int);
+static int p_count(struct parse *);
+static void p_bracket(struct parse *);
+static void p_b_term(struct parse *, cset *);
+static void p_b_cclass(struct parse *, cset *);
+static void p_b_eclass(struct parse *, cset *);
+static char p_b_symbol(struct parse *);
+static char p_b_coll_elem(struct parse *, int);
+static char othercase(int);
+static void bothcases(struct parse *, int);
+static void ordinary(struct parse *, int);
+static void nonnewline(struct parse *);
+static void repeat(struct parse *, sopno, int, int);
+static int seterr(struct parse *, int);
+static cset *allocset(struct parse *);
+static void freeset(struct parse *, cset *);
+static int freezeset(struct parse *, cset *);
+static int firstch(struct parse *, cset *);
+static int nch(struct parse *, cset *);
+static void mcadd(struct parse *, cset *, char *);
+static void mcinvert(struct parse *, cset *);
+static void mccase(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);
+static void dofwd(struct parse *, sopno, sop);
+static void enlarge(struct parse *, sopno);
+static void stripsnug(struct parse *, struct re_guts *);
+static void findmust(struct parse *, struct re_guts *);
+static sopno pluscount(struct parse *, struct re_guts *);
+
+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' !!!
+ */
+#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)	(void) ((co) || SETERROR(e))
+#define	MUSTSEE(c, e)	(REQUIRE(MORE() && PEEK() == (c), e))
+#define	MUSTEAT(c, e)	(void) (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 */
+#else
+#define	never	0		/* some <assert.h>s have bugs too */
+#endif
+
+/*
+ - regcomp - interface for parser and compilation
+ */
+int				/* 0 success, otherwise REG_something */
+regcomp(regex_t *preg, const char *pattern, int cflags)
+{
+	struct parse pa;
+	struct re_guts *g;
+	struct parse *p = &pa;
+	int i;
+	size_t len;
+#ifdef REDEBUG
+#	define	GOODFLAGS(f)	(f)
+#else
+#	define	GOODFLAGS(f)	((f)&~REG_DUMP)
+#endif
+
+	cflags = GOODFLAGS(cflags);
+	if ((cflags&REG_EXTENDED) && (cflags&REG_NOSPEC))
+		return(REG_INVARG);
+
+	if (cflags&REG_PEND) {
+		if (preg->re_endp < pattern)
+			return(REG_INVARG);
+		len = preg->re_endp - 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));
+	if (g == NULL)
+		return(REG_ESPACE);
+	p->ssize = len/(size_t)2*(size_t)3 + (size_t)1;	/* ugh */
+	p->strip = (sop *)calloc(p->ssize, sizeof(sop));
+	p->slen = 0;
+	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->end = p->next + len;
+	p->error = 0;
+	p->ncsalloc = 0;
+	for (i = 0; i < NPAREN; i++) {
+		p->pbegin[i] = 0;
+		p->pend[i] = 0;
+	}
+	g->csetsize = NC;
+	g->sets = NULL;
+	g->setbits = NULL;
+	g->ncsets = 0;
+	g->cflags = cflags;
+	g->iflags = 0;
+	g->nbol = 0;
+	g->neol = 0;
+	g->must = NULL;
+	g->mlen = 0;
+	g->nsub = 0;
+	g->ncategories = 1;	/* category 0 is "everything else" */
+	g->categories = &g->catspace[-(CHAR_MIN)];
+	(void) memset((char *)g->catspace, 0, NC*sizeof(cat_t));
+	g->backrefs = 0;
+
+	/* do it */
+	EMIT(OEND, 0);
+	g->firststate = THERE();
+	if (cflags&REG_EXTENDED)
+		p_ere(p, OUT);
+	else if (cflags&REG_NOSPEC)
+		p_str(p);
+	else
+		p_bre(p, OUT, OUT);
+	EMIT(OEND, 0);
+	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);
+	g->magic = MAGIC2;
+	preg->re_nsub = g->nsub;
+	preg->re_g = g;
+	preg->re_magic = MAGIC1;
+#ifndef REDEBUG
+	/* not debugging, so can't rely on the assert() in regexec() */
+	if (g->iflags&BAD)
+		SETERROR(REG_ASSERT);
+#endif
+
+	/* win or lose, we're done */
+	if (p->error != 0)	/* lose */
+		regfree(preg);
+	return(p->error);
+}
+
+/*
+ - p_ere - ERE parser top level, concatenation and alternation
+ */
+static void
+p_ere(struct parse *p, int stop)	/* character this ERE should end at */
+{
+	char c;
+	sopno prevback = 0;
+	sopno prevfwd = 0;
+	sopno conc;
+	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 */
+
+		if (!EAT('|'))
+			break;		/* NOTE BREAK OUT */
+
+		if (first) {
+			INSERT(OCH_, conc);	/* offset is wrong */
+			prevfwd = conc;
+			prevback = conc;
+			first = 0;
+		}
+		ASTERN(OOR1, prevback);
+		prevback = THERE();
+		AHEAD(prevfwd);			/* fix previous offset */
+		prevfwd = HERE();
+		EMIT(OOR2, 0);			/* offset is very wrong */
+	}
+
+	if (!first) {		/* tail-end fixups */
+		AHEAD(prevfwd);
+		ASTERN(O_CH, prevback);
+	}
+
+	assert(!MORE() || SEE(stop));
+}
+
+/*
+ - p_ere_exp - parse one subERE, an atom possibly followed by a repetition op
+ */
+static void
+p_ere_exp(struct parse *p)
+{
+	char c;
+	sopno pos;
+	int count;
+	int count2;
+	sopno subno;
+	int wascaret = 0;
+
+	assert(MORE());		/* caller should have ensured this */
+	c = GETNEXT();
+
+	pos = HERE();
+	switch (c) {
+	case '(':
+		REQUIRE(MORE(), REG_EPAREN);
+		p->g->nsub++;
+		subno = p->g->nsub;
+		if (subno < NPAREN)
+			p->pbegin[subno] = HERE();
+		EMIT(OLPAREN, subno);
+		if (!SEE(')'))
+			p_ere(p, ')');
+		if (subno < NPAREN) {
+			p->pend[subno] = HERE();
+			assert(p->pend[subno] != 0);
+		}
+		EMIT(ORPAREN, subno);
+		MUSTEAT(')', REG_EPAREN);
+		break;
+#ifndef POSIX_MISTAKE
+	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.
+		 */
+		SETERROR(REG_EPAREN);
+		break;
+#endif
+	case '^':
+		EMIT(OBOL, 0);
+		p->g->iflags |= USEBOL;
+		p->g->nbol++;
+		wascaret = 1;
+		break;
+	case '$':
+		EMIT(OEOL, 0);
+		p->g->iflags |= USEEOL;
+		p->g->neol++;
+		break;
+	case '|':
+		SETERROR(REG_EMPTY);
+		break;
+	case '*':
+	case '+':
+	case '?':
+		SETERROR(REG_BADRPT);
+		break;
+	case '.':
+		if (p->g->cflags&REG_NEWLINE)
+			nonnewline(p);
+		else
+			EMIT(OANY, 0);
+		break;
+	case '[':
+		p_bracket(p);
+		break;
+	case '\\':
+		REQUIRE(MORE(), REG_EESCAPE);
+		c = GETNEXT();
+		ordinary(p, c);
+		break;
+	case '{':		/* okay as ordinary except if digit follows */
+		REQUIRE(!MORE() || !isdigit((uch)PEEK()), REG_BADRPT);
+		/* FALLTHROUGH */
+	default:
+		ordinary(p, c);
+		break;
+	}
+
+	if (!MORE())
+		return;
+	c = PEEK();
+	/* we call { a repetition if followed by a digit */
+	if (!( c == '*' || c == '+' || c == '?' ||
+				(c == '{' && MORE2() && isdigit((uch)PEEK2())) ))
+		return;		/* no repetition, we're done */
+	NEXT();
+
+	REQUIRE(!wascaret, REG_BADRPT);
+	switch (c) {
+	case '*':	/* 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);
+		break;
+	case '+':
+		INSERT(OPLUS_, pos);
+		ASTERN(O_PLUS, pos);
+		break;
+	case '?':
+		/* 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_ */
+		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((uch)PEEK())) {
+				count2 = p_count(p);
+				REQUIRE(count <= count2, REG_BADBR);
+			} else		/* single number with comma */
+				count2 = INFINITY;
+		} else		/* just a single number */
+			count2 = count;
+		repeat(p, pos, count, count2);
+		if (!EAT('}')) {	/* error heuristics */
+			while (MORE() && PEEK() != '}')
+				NEXT();
+			REQUIRE(MORE(), REG_EBRACE);
+			SETERROR(REG_BADBR);
+		}
+		break;
+	}
+
+	if (!MORE())
+		return;
+	c = PEEK();
+	if (!( c == '*' || c == '+' || c == '?' ||
+				(c == '{' && MORE2() && isdigit((uch)PEEK2())) ) )
+		return;
+	SETERROR(REG_BADRPT);
+}
+
+/*
+ - p_str - string (no metacharacters) "parser"
+ */
+static void
+p_str(struct parse *p)
+{
+	REQUIRE(MORE(), REG_EMPTY);
+	while (MORE())
+		ordinary(p, GETNEXT());
+}
+
+/*
+ - p_bre - BRE parser top level, anchoring and concatenation
+ * 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.
+ * The amount of lookahead needed to avoid this kludge is excessive.
+ */
+static void
+p_bre(struct parse *p,
+    int end1,		/* first terminating character */
+    int end2)		/* second terminating character */
+{
+	sopno start = HERE();
+	int first = 1;			/* first subexpression? */
+	int wasdollar = 0;
+
+	if (EAT('^')) {
+		EMIT(OBOL, 0);
+		p->g->iflags |= USEBOL;
+		p->g->nbol++;
+	}
+	while (MORE() && !SEETWO(end1, end2)) {
+		wasdollar = p_simp_re(p, first);
+		first = 0;
+	}
+	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 */
+}
+
+/*
+ - p_simp_re - parse a simple RE, an atom possibly followed by a repetition
+ */
+static int			/* was the simple RE an unbackslashed $? */
+p_simp_re(struct parse *p,
+    int starordinary)		/* is a leading * an ordinary character? */
+{
+	int c;
+	int count;
+	int count2;
+	sopno pos;
+	int i;
+	sopno subno;
+#	define	BACKSL	(1<<CHAR_BIT)
+
+	pos = HERE();		/* repetion op, if any, covers from here */
+
+	assert(MORE());		/* caller should have ensured this */
+	c = GETNEXT();
+	if (c == '\\') {
+		REQUIRE(MORE(), REG_EESCAPE);
+		c = BACKSL | GETNEXT();
+	}
+	switch (c) {
+	case '.':
+		if (p->g->cflags&REG_NEWLINE)
+			nonnewline(p);
+		else
+			EMIT(OANY, 0);
+		break;
+	case '[':
+		p_bracket(p);
+		break;
+	case BACKSL|'{':
+		SETERROR(REG_BADRPT);
+		break;
+	case BACKSL|'(':
+		p->g->nsub++;
+		subno = p->g->nsub;
+		if (subno < NPAREN)
+			p->pbegin[subno] = HERE();
+		EMIT(OLPAREN, subno);
+		/* the MORE here is an error heuristic */
+		if (MORE() && !SEETWO('\\', ')'))
+			p_bre(p, '\\', ')');
+		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|'}':
+		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';
+		assert(i < NPAREN);
+		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);
+			(void) dupl(p, p->pbegin[i]+1, p->pend[i]);
+			EMIT(O_BACK, i);
+		} else
+			SETERROR(REG_ESUBREG);
+		p->g->backrefs = 1;
+		break;
+	case '*':
+		REQUIRE(starordinary, REG_BADRPT);
+		/* FALLTHROUGH */
+	default:
+		ordinary(p, (char)c);
+		break;
+	}
+
+	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('\\', '{')) {
+		count = p_count(p);
+		if (EAT(',')) {
+			if (MORE() && isdigit((uch)PEEK())) {
+				count2 = p_count(p);
+				REQUIRE(count <= count2, REG_BADBR);
+			} else		/* single number with comma */
+				count2 = INFINITY;
+		} else		/* just a single number */
+			count2 = count;
+		repeat(p, pos, count, count2);
+		if (!EATTWO('\\', '}')) {	/* error heuristics */
+			while (MORE() && !SEETWO('\\', '}'))
+				NEXT();
+			REQUIRE(MORE(), REG_EBRACE);
+			SETERROR(REG_BADBR);
+		}
+	} else if (c == '$')	/* $ (but not \$) ends it */
+		return(1);
+
+	return(0);
+}
+
+/*
+ - p_count - parse a repetition count
+ */
+static int			/* the value */
+p_count(struct parse *p)
+{
+	int count = 0;
+	int ndigits = 0;
+
+	while (MORE() && isdigit((uch)PEEK()) && count <= DUPMAX) {
+		count = count*10 + (GETNEXT() - '0');
+		ndigits++;
+	}
+
+	REQUIRE(ndigits > 0 && count <= DUPMAX, REG_BADBR);
+	return(count);
+}
+
+/*
+ - p_bracket - parse a bracketed character list
+ *
+ * Note a significant property of this code:  if the allocset() did SETERROR,
+ * no set operations are done.
+ */
+static void
+p_bracket(struct parse *p)
+{
+	cset *cs;
+	int invert = 0;
+
+	/* Dept of Truly Sickening Special-Case Kludges */
+	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) {
+		EMIT(OEOW, 0);
+		NEXTn(6);
+		return;
+	}
+
+	if ((cs = allocset(p)) == NULL) {
+		/* allocset did set error status in p */
+		return;
+	}
+
+	if (EAT('^'))
+		invert++;	/* make note to invert set at end */
+	if (EAT(']'))
+		CHadd(cs, ']');
+	else if (EAT('-'))
+		CHadd(cs, '-');
+	while (MORE() && PEEK() != ']' && !SEETWO('-', ']'))
+		p_b_term(p, cs);
+	if (EAT('-'))
+		CHadd(cs, '-');
+	MUSTEAT(']', REG_EBRACK);
+
+	if (p->error != 0) {	/* don't mess things up further */
+		freeset(p, cs);
+		return;
+	}
+
+	if (p->g->cflags&REG_ICASE) {
+		int i;
+		int ci;
+
+		for (i = p->g->csetsize - 1; i >= 0; i--)
+			if (CHIN(cs, i) && isalpha(i)) {
+				ci = othercase(i);
+				if (ci != i)
+					CHadd(cs, ci);
+			}
+		if (cs->multis != NULL)
+			mccase(p, cs);
+	}
+	if (invert) {
+		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)
+			CHsub(cs, '\n');
+		if (cs->multis != NULL)
+			mcinvert(p, cs);
+	}
+
+	assert(cs->multis == NULL);		/* xxx */
+
+	if (nch(p, cs) == 1) {		/* optimize singleton sets */
+		ordinary(p, firstch(p, cs));
+		freeset(p, cs);
+	} else
+		EMIT(OANYOF, freezeset(p, cs));
+}
+
+/*
+ - p_b_term - parse one term of a bracketed character list
+ */
+static void
+p_b_term(struct parse *p, cset *cs)
+{
+	char c;
+	char start, finish;
+	int i;
+
+	/* classify what we've got */
+	switch ((MORE()) ? PEEK() : '\0') {
+	case '[':
+		c = (MORE2()) ? PEEK2() : '\0';
+		break;
+	case '-':
+		SETERROR(REG_ERANGE);
+		return;			/* NOTE RETURN */
+		break;
+	default:
+		c = '\0';
+		break;
+	}
+
+	switch (c) {
+	case ':':		/* character class */
+		NEXT2();
+		REQUIRE(MORE(), REG_EBRACK);
+		c = PEEK();
+		REQUIRE(c != '-' && c != ']', REG_ECTYPE);
+		p_b_cclass(p, cs);
+		REQUIRE(MORE(), REG_EBRACK);
+		REQUIRE(EATTWO(':', ']'), REG_ECTYPE);
+		break;
+	case '=':		/* equivalence class */
+		NEXT2();
+		REQUIRE(MORE(), REG_EBRACK);
+		c = PEEK();
+		REQUIRE(c != '-' && c != ']', REG_ECOLLATE);
+		p_b_eclass(p, cs);
+		REQUIRE(MORE(), REG_EBRACK);
+		REQUIRE(EATTWO('=', ']'), REG_ECOLLATE);
+		break;
+	default:		/* symbol, ordinary character, or range */
+/* xxx revision needed for multichar stuff */
+		start = p_b_symbol(p);
+		if (SEE('-') && MORE2() && PEEK2() != ']') {
+			/* range */
+			NEXT();
+			if (EAT('-'))
+				finish = '-';
+			else
+				finish = p_b_symbol(p);
+		} else
+			finish = start;
+/* xxx what about signed chars here... */
+		REQUIRE(start <= finish, REG_ERANGE);
+		for (i = start; i <= finish; i++)
+			CHadd(cs, i);
+		break;
+	}
+}
+
+/*
+ - p_b_cclass - parse a character-class name and deal with it
+ */
+static void
+p_b_cclass(struct parse *p, cset *cs)
+{
+	char *sp = p->next;
+	struct cclass *cp;
+	size_t len;
+	char *u;
+	char c;
+
+	while (MORE() && isalpha(PEEK()))
+		NEXT();
+	len = p->next - sp;
+	for (cp = cclasses; cp->name != NULL; cp++)
+		if (strncmp(cp->name, sp, len) == 0 && cp->name[len] == '\0')
+			break;
+	if (cp->name == NULL) {
+		/* oops, didn't find it */
+		SETERROR(REG_ECTYPE);
+		return;
+	}
+
+	u = cp->chars;
+	while ((c = *u++) != '\0')
+		CHadd(cs, c);
+	for (u = cp->multis; *u != '\0'; u += strlen(u) + 1)
+		MCadd(p, cs, u);
+}
+
+/*
+ - p_b_eclass - parse an equivalence-class name and deal with it
+ *
+ * This implementation is incomplete. xxx
+ */
+static void
+p_b_eclass(struct parse *p, cset *cs)
+{
+	char c;
+
+	c = p_b_coll_elem(p, '=');
+	CHadd(cs, c);
+}
+
+/*
+ - p_b_symbol - parse a character or [..]ed multicharacter collating symbol
+ */
+static char			/* value of symbol */
+p_b_symbol(struct parse *p)
+{
+	char value;
+
+	REQUIRE(MORE(), REG_EBRACK);
+	if (!EATTWO('[', '.'))
+		return(GETNEXT());
+
+	/* collating symbol */
+	value = p_b_coll_elem(p, '.');
+	REQUIRE(EATTWO('.', ']'), REG_ECOLLATE);
+	return(value);
+}
+
+/*
+ - p_b_coll_elem - parse a collating-element name and look it up
+ */
+static char			/* value of collating element */
+p_b_coll_elem(struct parse *p,
+    int endc)			/* name ended by endc,']' */
+{
+	char *sp = p->next;
+	struct cname *cp;
+	int len;
+
+	while (MORE() && !SEETWO(endc, ']'))
+		NEXT();
+	if (!MORE()) {
+		SETERROR(REG_EBRACK);
+		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 */
+	if (len == 1)
+		return(*sp);	/* single character */
+	SETERROR(REG_ECOLLATE);			/* neither */
+	return(0);
+}
+
+/*
+ - othercase - return the case counterpart of an alphabetic
+ */
+static char			/* if no counterpart, return ch */
+othercase(int ch)
+{
+	ch = (uch)ch;
+	assert(isalpha(ch));
+	if (isupper(ch))
+		return ((uch)tolower(ch));
+	else if (islower(ch))
+		return ((uch)toupper(ch));
+	else			/* peculiar, but could happen */
+		return(ch);
+}
+
+/*
+ - bothcases - emit a dualcase version of a two-case character
+ *
+ * Boy, is this implementation ever a kludge...
+ */
+static void
+bothcases(struct parse *p, int ch)
+{
+	char *oldnext = p->next;
+	char *oldend = p->end;
+	char bracket[3];
+
+	ch = (uch)ch;
+	assert(othercase(ch) != ch);	/* p_bracket() would recurse */
+	p->next = bracket;
+	p->end = bracket+2;
+	bracket[0] = ch;
+	bracket[1] = ']';
+	bracket[2] = '\0';
+	p_bracket(p);
+	assert(p->next == bracket+2);
+	p->next = oldnext;
+	p->end = oldend;
+}
+
+/*
+ - ordinary - emit an ordinary character
+ */
+static void
+ordinary(struct parse *p, int ch)
+{
+	cat_t *cap = p->g->categories;
+
+	if ((p->g->cflags&REG_ICASE) && isalpha((uch)ch) && othercase(ch) != ch)
+		bothcases(p, ch);
+	else {
+		EMIT(OCHAR, (uch)ch);
+		if (cap[ch] == 0)
+			cap[ch] = p->g->ncategories++;
+	}
+}
+
+/*
+ - nonnewline - emit REG_NEWLINE version of OANY
+ *
+ * Boy, is this implementation ever a kludge...
+ */
+static void
+nonnewline(struct parse *p)
+{
+	char *oldnext = p->next;
+	char *oldend = p->end;
+	char bracket[4];
+
+	p->next = bracket;
+	p->end = bracket+3;
+	bracket[0] = '^';
+	bracket[1] = '\n';
+	bracket[2] = ']';
+	bracket[3] = '\0';
+	p_bracket(p);
+	assert(p->next == bracket+3);
+	p->next = oldnext;
+	p->end = oldend;
+}
+
+/*
+ - repeat - generate code for a bounded repetition, recursively if needed
+ */
+static void
+repeat(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 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)
+	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 */
+		break;
+	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);
+		ASTERN(OOR1, start);
+		AHEAD(start);			/* ... fix it */
+		EMIT(OOR2, 0);
+		AHEAD(THERE());
+		ASTERN(O_CH, THERETHERE());
+		break;
+	case REP(1, 1):			/* trivial case */
+		/* done */
+		break;
+	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);
+		AHEAD(start);
+		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);
+		break;
+	case REP(1, INF):		/* as x+ */
+		INSERT(OPLUS_, start);
+		ASTERN(O_PLUS, start);
+		break;
+	case REP(N, N):			/* as xx{m-1,n-1} */
+		copy = dupl(p, start, finish);
+		repeat(p, copy, from-1, to-1);
+		break;
+	case REP(N, INF):		/* as xx{n-1,INF} */
+		copy = dupl(p, start, finish);
+		repeat(p, copy, from-1, to);
+		break;
+	default:			/* "can't happen" */
+		SETERROR(REG_ASSERT);	/* just in case */
+		break;
+	}
+}
+
+/*
+ - seterr - set an error condition
+ */
+static int			/* useless but makes type checking happy */
+seterr(struct parse *p, int e)
+{
+	if (p->error == 0)	/* keep earliest error condition */
+		p->error = e;
+	p->next = nuls;		/* try to bring things to a halt */
+	p->end = nuls;
+	return(0);		/* make the return value well-defined */
+}
+
+/*
+ - allocset - allocate a set of characters for []
+ */
+static cset *
+allocset(struct parse *p)
+{
+	int no = p->g->ncsets++;
+	size_t nc;
+	size_t nbytes;
+	cset *cs;
+	size_t css = (size_t)p->g->csetsize;
+	int i;
+
+	if (no >= p->ncsalloc) {	/* need another column of space */
+		void *ptr;
+
+		p->ncsalloc += CHAR_BIT;
+		nc = p->ncsalloc;
+		assert(nc % CHAR_BIT == 0);
+		nbytes = nc / CHAR_BIT * css;
+
+		ptr = (cset *)realloc((char *)p->g->sets, nc * sizeof(cset));
+		if (ptr == NULL)
+			goto nomem;
+		p->g->sets = ptr;
+
+		ptr = (uch *)realloc((char *)p->g->setbits, nbytes);
+		if (ptr == NULL)
+			goto nomem;
+		p->g->setbits = ptr;
+
+		for (i = 0; i < no; i++)
+			p->g->sets[i].ptr = p->g->setbits + css*(i/CHAR_BIT);
+
+		(void) memset((char *)p->g->setbits + (nbytes - css), 0, css);
+	}
+	/* XXX should not happen */
+	if (p->g->sets == NULL || p->g->setbits == NULL)
+		goto nomem;
+
+	cs = &p->g->sets[no];
+	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);
+nomem:
+	free(p->g->sets);
+	p->g->sets = NULL;
+	free(p->g->setbits);
+	p->g->setbits = NULL;
+
+	SETERROR(REG_ESPACE);
+	/* caller's responsibility not to do set ops */
+	return(NULL);
+}
+
+/*
+ - freeset - free a now-unused set
+ */
+static void
+freeset(struct parse *p, cset *cs)
+{
+	int i;
+	cset *top = &p->g->sets[p->g->ncsets];
+	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 */
+		p->g->ncsets--;
+}
+
+/*
+ - freezeset - final processing on a set of characters
+ *
+ * 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
+ * is done using addition rather than xor -- all ASCII [aA] sets xor to
+ * the same value!
+ */
+static int			/* set number */
+freezeset(struct parse *p, cset *cs)
+{
+	uch h = cs->hash;
+	int i;
+	cset *top = &p->g->sets[p->g->ncsets];
+	cset *cs2;
+	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) {
+			/* maybe */
+			for (i = 0; i < css; i++)
+				if (!!CHIN(cs2, i) != !!CHIN(cs, i))
+					break;		/* no */
+			if (i == css)
+				break;			/* yes */
+		}
+
+	if (cs2 < top) {	/* found one */
+		freeset(p, cs);
+		cs = cs2;
+	}
+
+	return((int)(cs - p->g->sets));
+}
+
+/*
+ - firstch - return first character in a set (which must have at least one)
+ */
+static int			/* character; there is no "none" value */
+firstch(struct parse *p, cset *cs)
+{
+	int i;
+	size_t css = (size_t)p->g->csetsize;
+
+	for (i = 0; i < css; i++)
+		if (CHIN(cs, i))
+			return((char)i);
+	assert(never);
+	return(0);		/* arbitrary */
+}
+
+/*
+ - nch - number of characters in a set
+ */
+static int
+nch(struct parse *p, cset *cs)
+{
+	int i;
+	size_t css = (size_t)p->g->csetsize;
+	int n = 0;
+
+	for (i = 0; i < css; i++)
+		if (CHIN(cs, i))
+			n++;
+	return(n);
+}
+
+/*
+ - mcadd - add a collating element to a cset
+ */
+static void
+mcadd( struct parse *p, cset *cs, char *cp)
+{
+	size_t oldend = cs->smultis;
+	void *np;
+
+	cs->smultis += strlen(cp) + 1;
+	np = realloc(cs->multis, cs->smultis);
+	if (np == NULL) {
+		if (cs->multis)
+			free(cs->multis);
+		cs->multis = NULL;
+		SETERROR(REG_ESPACE);
+		return;
+	}
+	cs->multis = np;
+
+	strlcpy(cs->multis + oldend - 1, cp, cs->smultis - oldend + 1);
+}
+
+/*
+ - mcinvert - invert the list of collating elements in a cset
+ *
+ * This would have to know the set of possibilities.  Implementation
+ * is deferred.
+ */
+/* ARGSUSED */
+static void
+mcinvert(struct parse *p, cset *cs)
+{
+	assert(cs->multis == NULL);	/* xxx */
+}
+
+/*
+ - mccase - add case counterparts of the list of collating elements in a cset
+ *
+ * This would have to know the set of possibilities.  Implementation
+ * is deferred.
+ */
+/* ARGSUSED */
+static void
+mccase(struct parse *p, cset *cs)
+{
+	assert(cs->multis == NULL);	/* xxx */
+}
+
+/*
+ - isinsets - is this character in any sets?
+ */
+static int			/* predicate */
+isinsets(struct re_guts *g, int c)
+{
+	uch *col;
+	int i;
+	int ncols = (g->ncsets+(CHAR_BIT-1)) / CHAR_BIT;
+	unsigned uc = (uch)c;
+
+	for (i = 0, col = g->setbits; i < ncols; i++, col += g->csetsize)
+		if (col[uc] != 0)
+			return(1);
+	return(0);
+}
+
+/*
+ - samesets - are these two characters in exactly the same sets?
+ */
+static int			/* predicate */
+samesets(struct re_guts *g, int c1, int c2)
+{
+	uch *col;
+	int i;
+	int ncols = (g->ncsets+(CHAR_BIT-1)) / CHAR_BIT;
+	unsigned uc1 = (uch)c1;
+	unsigned uc2 = (uch)c2;
+
+	for (i = 0, col = g->setbits; i < ncols; i++, col += g->csetsize)
+		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;
+		}
+}
+
+/*
+ - dupl - emit a duplicate of a bunch of sops
+ */
+static sopno			/* start of duplicate */
+dupl(struct parse *p,
+    sopno start,		/* from here */
+    sopno finish)		/* to this less one */
+{
+	sopno ret = HERE();
+	sopno len = finish - start;
+
+	assert(finish >= start);
+	if (len == 0)
+		return(ret);
+	enlarge(p, p->ssize + len);	/* this many unexpected additions */
+	assert(p->ssize >= p->slen + len);
+	(void) memcpy((char *)(p->strip + p->slen),
+		(char *)(p->strip + start), (size_t)len*sizeof(sop));
+	p->slen += len;
+	return(ret);
+}
+
+/*
+ - doemit - emit a strip operator
+ *
+ * It might seem better to implement this as a macro with a function as
+ * hard-case backup, but it's just too big and messy unless there are
+ * some changes to the data structures.  Maybe later.
+ */
+static void
+doemit(struct parse *p, 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);
+
+	/* deal with undersized strip */
+	if (p->slen >= p->ssize)
+		enlarge(p, (p->ssize+1) / 2 * 3);	/* +50% */
+	assert(p->slen < p->ssize);
+
+	/* finally, it's all reduced to the easy case */
+	p->strip[p->slen++] = SOP(op, opnd);
+}
+
+/*
+ - doinsert - insert a sop into the strip
+ */
+static void
+doinsert(struct parse *p, sop op, size_t opnd, sopno pos)
+{
+	sopno sn;
+	sop s;
+	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);
+	s = p->strip[sn];
+
+	/* adjust paren pointers */
+	assert(pos > 0);
+	for (i = 1; i < NPAREN; i++) {
+		if (p->pbegin[i] >= pos) {
+			p->pbegin[i]++;
+		}
+		if (p->pend[i] >= pos) {
+			p->pend[i]++;
+		}
+	}
+
+	memmove((char *)&p->strip[pos+1], (char *)&p->strip[pos],
+						(HERE()-pos-1)*sizeof(sop));
+	p->strip[pos] = s;
+}
+
+/*
+ - dofwd - complete a forward reference
+ */
+static void
+dofwd(struct parse *p, sopno pos, sop value)
+{
+	/* avoid making error situations worse */
+	if (p->error != 0)
+		return;
+
+	assert(value < 1<<OPSHIFT);
+	p->strip[pos] = OP(p->strip[pos]) | value;
+}
+
+/*
+ - enlarge - enlarge the strip
+ */
+static void
+enlarge(struct parse *p, sopno size)
+{
+	sop *sp;
+
+	if (p->ssize >= size)
+		return;
+
+	sp = (sop *)realloc(p->strip, size*sizeof(sop));
+	if (sp == NULL) {
+		SETERROR(REG_ESPACE);
+		return;
+	}
+	p->strip = sp;
+	p->ssize = size;
+}
+
+/*
+ - stripsnug - compact the strip
+ */
+static void
+stripsnug(struct parse *p, struct re_guts *g)
+{
+	g->nstates = p->slen;
+	g->strip = (sop *)realloc((char *)p->strip, p->slen * sizeof(sop));
+	if (g->strip == NULL) {
+		SETERROR(REG_ESPACE);
+		g->strip = p->strip;
+	}
+}
+
+/*
+ - findmust - fill in must and mlen with longest mandatory literal string
+ *
+ * This algorithm could do fancy things like analyzing the operands of |
+ * for common subsequences.  Someday.  This code is simple and finds most
+ * of the interesting cases.
+ *
+ * Note that must and mlen got initialized during setup.
+ */
+static void
+findmust(struct parse *p, struct re_guts *g)
+{
+	sop *scan;
+	sop *start;    /* start initialized in the default case, after that */
+	sop *newstart; /* newstart was initialized in the OCHAR case */
+	sopno newlen;
+	sop s;
+	char *cp;
+	sopno i;
+
+	/* avoid making error situations worse */
+	if (p->error != 0)
+		return;
+
+	/* find the longest OCHAR sequence in strip */
+	newlen = 0;
+	scan = g->strip + 1;
+	do {
+		s = *scan++;
+		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 OLPAREN:
+		case ORPAREN:
+			break;
+		case OQUEST_:		/* things that must be skipped */
+		case OCH_:
+			scan--;
+			do {
+				scan += OPND(s);
+				s = *scan;
+				/* assert() interferes w debug printouts */
+				if (OP(s) != O_QUEST && OP(s) != O_CH &&
+							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 */
+				start = newstart;
+				g->mlen = newlen;
+			}
+			newlen = 0;
+			break;
+		}
+	} while (OP(s) != OEND);
+
+	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->mlen = 0;
+		return;
+	}
+	cp = g->must;
+	scan = start;
+	for (i = g->mlen; i > 0; i--) {
+		while (OP(s = *scan++) != OCHAR)
+			continue;
+		assert(cp < g->must + g->mlen);
+		*cp++ = (char)OPND(s);
+	}
+	assert(cp == g->must + g->mlen);
+	*cp++ = '\0';		/* just on general principles */
+}
+
+/*
+ - pluscount - count + nesting
+ */
+static sopno			/* nesting depth */
+pluscount(struct parse *p, struct re_guts *g)
+{
+	sop *scan;
+	sop s;
+	sopno plusnest = 0;
+	sopno maxnest = 0;
+
+	if (p->error != 0)
+		return(0);	/* there may not be an OEND */
+
+	scan = g->strip + 1;
+	do {
+		s = *scan++;
+		switch (OP(s)) {
+		case OPLUS_:
+			plusnest++;
+			break;
+		case O_PLUS:
+			if (plusnest > maxnest)
+				maxnest = plusnest;
+			plusnest--;
+			break;
+		}
+	} while (OP(s) != OEND);
+	if (plusnest != 0)
+		g->iflags |= BAD;
+	return(maxnest);
+}

Propchange: commons/sandbox/runtime/trunk/src/main/native/srclib/regex/regcomp.c
------------------------------------------------------------------------------
    svn:eol-style = native

Added: commons/sandbox/runtime/trunk/src/main/native/srclib/regex/regerror.c
URL: http://svn.apache.org/viewvc/commons/sandbox/runtime/trunk/src/main/native/srclib/regex/regerror.c?rev=807635&view=auto
==============================================================================
--- commons/sandbox/runtime/trunk/src/main/native/srclib/regex/regerror.c (added)
+++ commons/sandbox/runtime/trunk/src/main/native/srclib/regex/regerror.c Tue Aug 25 13:57:05 2009
@@ -0,0 +1,127 @@
+/*	$OpenBSD: regerror.c,v 1.13 2005/08/05 13:03:00 espie Exp $ */
+/*-
+ * Copyright (c) 1992, 1993, 1994 Henry Spencer.
+ * Copyright (c) 1992, 1993, 1994
+ *	The Regents of the University of California.  All rights reserved.
+ *
+ * This code is derived from software contributed to Berkeley by
+ * Henry Spencer.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * 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.
+ * 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.
+ * 3. 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.
+ *
+ * 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
+ * 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)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE.
+ *
+ *	@(#)regerror.c	8.4 (Berkeley) 3/20/94
+ */
+
+#include "acr.h"
+#include "acr_private.h"
+#include "acr_arch.h"
+#include "regex.h"
+
+#include "utils.h"
+
+static char *regatoi(const regex_t *, char *, int);
+
+static struct rerr {
+	int code;
+	char *name;
+	char *explain;
+} rerrs[] = {
+	{ REG_NOMATCH,	"REG_NOMATCH",	"regexec() failed to match" },
+	{ REG_BADPAT,	"REG_BADPAT",	"invalid regular expression" },
+	{ REG_ECOLLATE,	"REG_ECOLLATE",	"invalid collating element" },
+	{ REG_ECTYPE,	"REG_ECTYPE",	"invalid character class" },
+	{ REG_EESCAPE,	"REG_EESCAPE",	"trailing backslash (\\)" },
+	{ REG_ESUBREG,	"REG_ESUBREG",	"invalid backreference number" },
+	{ REG_EBRACK,	"REG_EBRACK",	"brackets ([ ]) not balanced" },
+	{ REG_EPAREN,	"REG_EPAREN",	"parentheses not balanced" },
+	{ REG_EBRACE,	"REG_EBRACE",	"braces not balanced" },
+	{ REG_BADBR,	"REG_BADBR",	"invalid repetition count(s)" },
+	{ REG_ERANGE,	"REG_ERANGE",	"invalid character range" },
+	{ REG_ESPACE,	"REG_ESPACE",	"out of memory" },
+	{ REG_BADRPT,	"REG_BADRPT",	"repetition-operator operand invalid" },
+	{ REG_EMPTY,	"REG_EMPTY",	"empty (sub)expression" },
+	{ REG_ASSERT,	"REG_ASSERT",	"\"can't happen\" -- you found a bug" },
+	{ REG_INVARG,	"REG_INVARG",	"invalid argument to regex routine" },
+	{ 0,		"",		"*** unknown regexp error code ***" }
+};
+
+/*
+ - regerror - the interface to error numbers
+ = extern size_t regerror(int, const regex_t *, char *, size_t);
+ */
+/* ARGSUSED */
+size_t
+regerror(int errcode, const regex_t *preg, char *errbuf, size_t errbuf_size)
+{
+	struct rerr *r;
+	size_t len;
+	int target = errcode &~ REG_ITOA;
+	char *s;
+	char convbuf[50];
+
+	if (errcode == REG_ATOI)
+		s = regatoi(preg, convbuf, sizeof convbuf);
+	else {
+		for (r = rerrs; r->code != 0; r++)
+			if (r->code == target)
+				break;
+	
+		if (errcode&REG_ITOA) {
+			if (r->code != 0) {
+				assert(strlen(r->name) < sizeof(convbuf));
+				(void) strlcpy(convbuf, r->name, sizeof convbuf);
+			} else
+				(void)snprintf(convbuf, sizeof convbuf,
+				    "REG_0x%x", target);
+			s = convbuf;
+		} else
+			s = r->explain;
+	}
+
+	len = strlen(s) + 1;
+	if (errbuf_size > 0) {
+		strlcpy(errbuf, s, errbuf_size);
+	}
+
+	return(len);
+}
+
+/*
+ - regatoi - internal routine to implement REG_ATOI
+ */
+static char *
+regatoi(const regex_t *preg, char *localbuf, int localbufsize)
+{
+	struct rerr *r;
+
+	for (r = rerrs; r->code != 0; r++)
+		if (strcmp(r->name, preg->re_endp) == 0)
+			break;
+	if (r->code == 0)
+		return("0");
+
+	(void)snprintf(localbuf, localbufsize, "%d", r->code);
+	return(localbuf);
+}

Propchange: commons/sandbox/runtime/trunk/src/main/native/srclib/regex/regerror.c
------------------------------------------------------------------------------
    svn:eol-style = native

Added: commons/sandbox/runtime/trunk/src/main/native/srclib/regex/regex.h
URL: http://svn.apache.org/viewvc/commons/sandbox/runtime/trunk/src/main/native/srclib/regex/regex.h?rev=807635&view=auto
==============================================================================
--- commons/sandbox/runtime/trunk/src/main/native/srclib/regex/regex.h (added)
+++ commons/sandbox/runtime/trunk/src/main/native/srclib/regex/regex.h Tue Aug 25 13:57:05 2009
@@ -0,0 +1,125 @@
+/*-
+ * Copyright (c) 1992 Henry Spencer.
+ * Copyright (c) 1992, 1993
+ *	The Regents of the University of California.  All rights reserved.
+ *
+ * This code is derived from software contributed to Berkeley by
+ * Henry Spencer of the University of Toronto.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * 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.
+ * 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.
+ * 3. 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.
+ *
+ * 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
+ * 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)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE.
+ *
+ *	@(#)regex.h	8.1 (Berkeley) 6/2/93
+ */
+
+#ifndef _REGEX_H_
+#define _REGEX_H_
+
+#include <sys/types.h>
+
+#define RE_PREFIX
+
+/*
+ * If you *really* need a unique prefix for all types and library functions,
+ * compile with -DRE_PREFIX. The "standard" regex should be compiled without it.
+ */
+
+#ifdef RE_PREFIX
+#  define regoff_t          acr_regoff_t
+#  define regex_t           acr_regex_t
+#  define regmatch_t        acr_regmatch_t
+#  define regcomp           acr_regcomp
+#  define regerror          acr_regerror
+#  define regexec           acr_regexec
+#  define regfree           acr_regfree
+#endif
+
+/* types */
+typedef off_t regoff_t;
+
+typedef struct {
+	int re_magic;
+	size_t re_nsub;	/* number of parenthesized subexpressions */
+	const char *re_endp;	/* end pointer for REG_PEND */
+	struct re_guts *re_g;	/* none of your business :-) */
+} regex_t;
+
+typedef struct {
+	regoff_t rm_so;		/* start of match */
+	regoff_t rm_eo;		/* end of match */
+} regmatch_t;
+
+/* regcomp() flags */
+#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
+
+/* regerror() flags */
+#define	REG_NOMATCH	 1
+#define	REG_BADPAT	 2
+#define	REG_ECOLLATE	 3
+#define	REG_ECTYPE	 4
+#define	REG_EESCAPE	 5
+#define	REG_ESUBREG	 6
+#define	REG_EBRACK	 7
+#define	REG_EPAREN	 8
+#define	REG_EBRACE	 9
+#define	REG_BADBR	10
+#define	REG_ERANGE	11
+#define	REG_ESPACE	12
+#define	REG_BADRPT	13
+#define	REG_EMPTY	14
+#define	REG_ASSERT	15
+#define	REG_INVARG	16
+#define	REG_ATOI	255	/* convert name to number (!) */
+#define	REG_ITOA	0400	/* convert number to name (!) */
+
+/* regexec() flags */
+#define	REG_NOTBOL	00001
+#define	REG_NOTEOL	00002
+#define	REG_STARTEND	00004
+#define	REG_TRACE	00400	/* tracing of execution */
+#define	REG_LARGE	01000	/* force large representation */
+#define	REG_BACKR	02000	/* force use of backref code */
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+int	regcomp(regex_t *, const char *, int);
+size_t	regerror(int, const regex_t *, char *, size_t);
+int	regexec(const regex_t *, const char *, size_t, regmatch_t [], int);
+void	regfree(regex_t *);
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* !_REGEX_H_ */
+

Propchange: commons/sandbox/runtime/trunk/src/main/native/srclib/regex/regex.h
------------------------------------------------------------------------------
    svn:eol-style = native

Added: commons/sandbox/runtime/trunk/src/main/native/srclib/regex/regex2.h
URL: http://svn.apache.org/viewvc/commons/sandbox/runtime/trunk/src/main/native/srclib/regex/regex2.h?rev=807635&view=auto
==============================================================================
--- commons/sandbox/runtime/trunk/src/main/native/srclib/regex/regex2.h (added)
+++ commons/sandbox/runtime/trunk/src/main/native/srclib/regex/regex2.h Tue Aug 25 13:57:05 2009
@@ -0,0 +1,157 @@
+/*	$OpenBSD: regex2.h,v 1.7 2004/11/30 17:04:23 otto Exp $	*/
+
+/*-
+ * Copyright (c) 1992, 1993, 1994 Henry Spencer.
+ * Copyright (c) 1992, 1993, 1994
+ *	The Regents of the University of California.  All rights reserved.
+ *
+ * This code is derived from software contributed to Berkeley by
+ * Henry Spencer.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * 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.
+ * 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.
+ * 3. 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.
+ *
+ * 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
+ * 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)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE.
+ *
+ *	@(#)regex2.h	8.4 (Berkeley) 3/20/94
+ */
+
+/*
+ * internals of regex_t
+ */
+#define	MAGIC1	((('r'^0200)<<8) | 'e')
+
+/*
+ * The internal representation is a *strip*, a sequence of
+ * operators ending with an endmarker.  (Some terminology etc. is a
+ * historical relic of earlier versions which used multiple strips.)
+ * Certain oddities in the representation are there to permit running
+ * the machinery backwards; in particular, any deviation from sequential
+ * flow must be marked at both its source and its destination.  Some
+ * fine points:
+ *
+ * - OPLUS_ and O_PLUS are *inside* the loop they create.
+ * - OQUEST_ and O_QUEST are *outside* the bypass they create.
+ * - OCH_ and O_CH are *outside* the multi-way branch they create, while
+ *   OOR1 and OOR2 are respectively the end and the beginning of one of
+ *   the branches.  Note that there is an implicit OOR2 following OCH_
+ *   and an implicit OOR1 preceding O_CH.
+ *
+ * In state representations, an operator's bit is on to signify a state
+ * immediately *preceding* "execution" of that operator.
+ */
+typedef unsigned long sop;	/* strip operator */
+typedef long sopno;
+#define	OPRMASK	0xf8000000LU
+#define	OPDMASK	0x07ffffffLU
+#define	OPSHIFT	((unsigned)27)
+#define	OP(n)	((n)&OPRMASK)
+#define	OPND(n)	((n)&OPDMASK)
+#define	SOP(op, opnd)	((op)|(opnd))
+/* operators			   meaning	operand			*/
+/*						(back, fwd are offsets)	*/
+#define	OEND	(1LU<<OPSHIFT)	/* endmarker	-			*/
+#define	OCHAR	(2LU<<OPSHIFT)	/* character	unsigned char		*/
+#define	OBOL	(3LU<<OPSHIFT)	/* left anchor	-			*/
+#define	OEOL	(4LU<<OPSHIFT)	/* right anchor	-			*/
+#define	OANY	(5LU<<OPSHIFT)	/* .		-			*/
+#define	OANYOF	(6LU<<OPSHIFT)	/* [...]	set number		*/
+#define	OBACK_	(7LU<<OPSHIFT)	/* begin \d	paren number		*/
+#define	O_BACK	(8LU<<OPSHIFT)	/* end \d	paren number		*/
+#define	OPLUS_	(9LU<<OPSHIFT)	/* + prefix	fwd to suffix		*/
+#define	O_PLUS	(10LU<<OPSHIFT)	/* + suffix	back to prefix		*/
+#define	OQUEST_	(11LU<<OPSHIFT)	/* ? prefix	fwd to suffix		*/
+#define	O_QUEST	(12LU<<OPSHIFT)	/* ? suffix	back to prefix		*/
+#define	OLPAREN	(13LU<<OPSHIFT)	/* (		fwd to )		*/
+#define	ORPAREN	(14LU<<OPSHIFT)	/* )		back to (		*/
+#define	OCH_	(15LU<<OPSHIFT)	/* begin choice	fwd to OOR2		*/
+#define	OOR1	(16LU<<OPSHIFT)	/* | pt. 1	back to OOR1 or OCH_	*/
+#define	OOR2	(17LU<<OPSHIFT)	/* | pt. 2	fwd to OOR2 or O_CH	*/
+#define	O_CH	(18LU<<OPSHIFT)	/* end choice	back to OOR1		*/
+#define	OBOW	(19LU<<OPSHIFT)	/* begin word	-			*/
+#define	OEOW	(20LU<<OPSHIFT)	/* end word	-			*/
+
+/*
+ * Structure for [] character-set representation.  Character sets are
+ * done as bit vectors, grouped 8 to a byte vector for compactness.
+ * The individual set therefore has both a pointer to the byte vector
+ * and a mask to pick out the relevant bit of each byte.  A hash code
+ * simplifies testing whether two sets could be identical.
+ *
+ * This will get trickier for multicharacter collating elements.  As
+ * preliminary hooks for dealing with such things, we also carry along
+ * a string of multi-character elements, and decide the size of the
+ * vectors at run time.
+ */
+typedef struct {
+	uch *ptr;		/* -> uch [csetsize] */
+	uch mask;		/* bit within array */
+	uch hash;		/* hash code */
+	size_t smultis;
+	char *multis;		/* -> char[smulti]  ab\0cd\0ef\0\0 */
+} cset;
+/* note that CHadd and CHsub are unsafe, and CHIN doesn't yield 0/1 */
+#define	CHadd(cs, c)	((cs)->ptr[(uch)(c)] |= (cs)->mask, (cs)->hash += (c))
+#define	CHsub(cs, c)	((cs)->ptr[(uch)(c)] &= ~(cs)->mask, (cs)->hash -= (c))
+#define	CHIN(cs, c)	((cs)->ptr[(uch)(c)] & (cs)->mask)
+#define	MCadd(p, cs, cp)	mcadd(p, cs, cp)	/* regcomp() internal fns */
+#define	MCsub(p, cs, cp)	mcsub(p, cs, cp)
+#define	MCin(p, cs, cp)	mcin(p, cs, cp)
+
+/* stuff for character categories */
+typedef unsigned char cat_t;
+
+/*
+ * main compiled-expression structure
+ */
+struct re_guts {
+	int magic;
+#		define	MAGIC2	((('R'^0200)<<8)|'E')
+	sop *strip;		/* malloced area for strip */
+	int csetsize;		/* number of bits in a cset vector */
+	int ncsets;		/* number of csets in use */
+	cset *sets;		/* -> cset [ncsets] */
+	uch *setbits;		/* -> uch[csetsize][ncsets/CHAR_BIT] */
+	int cflags;		/* copy of regcomp() cflags argument */
+	sopno nstates;		/* = number of sops */
+	sopno firststate;	/* the initial OEND (normally 0) */
+	sopno laststate;	/* the final OEND */
+	int iflags;		/* internal flags */
+#		define	USEBOL	01	/* used ^ */
+#		define	USEEOL	02	/* used $ */
+#		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[1];	/* actually [NC] */
+};
+
+/* misc utilities */
+#define	OUT	(CHAR_MAX+1)	/* a non-character value */
+#define	ISWORD(c)	(isalnum(c) || (c) == '_')

Propchange: commons/sandbox/runtime/trunk/src/main/native/srclib/regex/regex2.h
------------------------------------------------------------------------------
    svn:eol-style = native

Added: commons/sandbox/runtime/trunk/src/main/native/srclib/regex/regexec.c
URL: http://svn.apache.org/viewvc/commons/sandbox/runtime/trunk/src/main/native/srclib/regex/regexec.c?rev=807635&view=auto
==============================================================================
--- commons/sandbox/runtime/trunk/src/main/native/srclib/regex/regexec.c (added)
+++ commons/sandbox/runtime/trunk/src/main/native/srclib/regex/regexec.c Tue Aug 25 13:57:05 2009
@@ -0,0 +1,156 @@
+/*-
+ * Copyright (c) 1992, 1993, 1994 Henry Spencer.
+ * Copyright (c) 1992, 1993, 1994
+ *	The Regents of the University of California.  All rights reserved.
+ *
+ * This code is derived from software contributed to Berkeley by
+ * Henry Spencer.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * 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.
+ * 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.
+ * 3. 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.
+ *
+ * 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
+ * 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)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE.
+ *
+ *	@(#)regexec.c	8.3 (Berkeley) 3/20/94
+ */
+
+/*
+ * the outer shell of regexec()
+ *
+ * This file includes engine.c *twice*, after muchos fiddling with the
+ * macros that code uses.  This lets the same code operate on two different
+ * representations for state sets.
+ */
+#include "acr.h"
+#include "acr_private.h"
+#include "acr_arch.h"
+#include "regex.h"
+
+#include "utils.h"
+#include "regex2.h"
+
+/* macros for manipulating states, small version */
+#define	states	long
+#define	states1	states		/* for later use in regexec() decision */
+#define	CLEAR(v)	((v) = 0)
+#define	SET0(v, n)	((v) &= ~((unsigned long)1 << (n)))
+#define	SET1(v, n)	((v) |= (unsigned long)1 << (n))
+#define	ISSET(v, n)	(((v) & ((unsigned long)1 << (n))) != 0)
+#define	ASSIGN(d, s)	((d) = (s))
+#define	EQ(a, b)	((a) == (b))
+#define	STATEVARS	long dummy	/* dummy version */
+#define	STATESETUP(m, n)	/* nothing */
+#define	STATETEARDOWN(m)	/* nothing */
+#define	SETUP(v)	((v) = 0)
+#define	onestate	long
+#define	INIT(o, n)	((o) = (unsigned long)1 << (n))
+#define	INC(o)		((o) <<= 1)
+#define	ISSTATEIN(v, o)	(((v) & (o)) != 0)
+/* some abbreviations; note that some of these know variable names! */
+/* do "if I'm here, I can also be there" etc without branches */
+#define	FWD(dst, src, n)	((dst) |= ((unsigned long)(src)&(here)) << (n))
+#define	BACK(dst, src, n)	((dst) |= ((unsigned long)(src)&(here)) >> (n))
+#define	ISSETBACK(v, n)		(((v) & ((unsigned long)here >> (n))) != 0)
+/* function names */
+#define SNAMES			/* engine.c looks after details */
+
+#include "engine.c"
+
+/* now undo things */
+#undef	states
+#undef	CLEAR
+#undef	SET0
+#undef	SET1
+#undef	ISSET
+#undef	ASSIGN
+#undef	EQ
+#undef	STATEVARS
+#undef	STATESETUP
+#undef	STATETEARDOWN
+#undef	SETUP
+#undef	onestate
+#undef	INIT
+#undef	INC
+#undef	ISSTATEIN
+#undef	FWD
+#undef	BACK
+#undef	ISSETBACK
+#undef	SNAMES
+
+/* macros for manipulating states, large version */
+#define	states	char *
+#define	CLEAR(v)	memset(v, 0, m->g->nstates)
+#define	SET0(v, n)	((v)[n] = 0)
+#define	SET1(v, n)	((v)[n] = 1)
+#define	ISSET(v, n)	((v)[n])
+#define	ASSIGN(d, s)	memcpy(d, s, m->g->nstates)
+#define	EQ(a, b)	(memcmp(a, b, m->g->nstates) == 0)
+#define	STATEVARS	long vn; char *space
+#define	STATESETUP(m, nv)	{ (m)->space = malloc((nv)*(m)->g->nstates); \
+				if ((m)->space == NULL) return(REG_ESPACE); \
+				(m)->vn = 0; }
+#define	STATETEARDOWN(m)	{ free((m)->space); }
+#define	SETUP(v)	((v) = &m->space[m->vn++ * m->g->nstates])
+#define	onestate	long
+#define	INIT(o, n)	((o) = (n))
+#define	INC(o)	((o)++)
+#define	ISSTATEIN(v, o)	((v)[o])
+/* some abbreviations; note that some of these know variable names! */
+/* do "if I'm here, I can also be there" etc without branches */
+#define	FWD(dst, src, n)	((dst)[here+(n)] |= (src)[here])
+#define	BACK(dst, src, n)	((dst)[here-(n)] |= (src)[here])
+#define	ISSETBACK(v, n)	((v)[here - (n)])
+/* function names */
+#define	LNAMES			/* flag */
+
+#include "engine.c"
+
+/*
+ - regexec - interface for matching
+ *
+ * We put this here so we can exploit knowledge of the state representation
+ * when choosing which matcher to call.  Also, by this point the matchers
+ * have been prototyped.
+ */
+int				/* 0 success, REG_NOMATCH failure */
+regexec(const regex_t *preg, const char *string, size_t nmatch,
+    regmatch_t pmatch[], int eflags)
+{
+	struct re_guts *g = preg->re_g;
+#ifdef REDEBUG
+#	define	GOODFLAGS(f)	(f)
+#else
+#	define	GOODFLAGS(f)	((f)&(REG_NOTBOL|REG_NOTEOL|REG_STARTEND))
+#endif
+
+	if (preg->re_magic != MAGIC1 || g->magic != MAGIC2)
+		return(REG_BADPAT);
+	assert(!(g->iflags&BAD));
+	if (g->iflags&BAD)		/* backstop for no-debug case */
+		return(REG_BADPAT);
+	eflags = GOODFLAGS(eflags);
+
+	if (g->nstates <= CHAR_BIT*sizeof(states1) && !(eflags&REG_LARGE))
+		return(smatcher(g, (char *)string, nmatch, pmatch, eflags));
+	else
+		return(lmatcher(g, (char *)string, nmatch, pmatch, eflags));
+}

Propchange: commons/sandbox/runtime/trunk/src/main/native/srclib/regex/regexec.c
------------------------------------------------------------------------------
    svn:eol-style = native

Added: commons/sandbox/runtime/trunk/src/main/native/srclib/regex/regfree.c
URL: http://svn.apache.org/viewvc/commons/sandbox/runtime/trunk/src/main/native/srclib/regex/regfree.c?rev=807635&view=auto
==============================================================================
--- commons/sandbox/runtime/trunk/src/main/native/srclib/regex/regfree.c (added)
+++ commons/sandbox/runtime/trunk/src/main/native/srclib/regex/regfree.c Tue Aug 25 13:57:05 2009
@@ -0,0 +1,70 @@
+/*-
+ * Copyright (c) 1992, 1993, 1994 Henry Spencer.
+ * Copyright (c) 1992, 1993, 1994
+ *	The Regents of the University of California.  All rights reserved.
+ *
+ * This code is derived from software contributed to Berkeley by
+ * Henry Spencer.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * 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.
+ * 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.
+ * 3. 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.
+ *
+ * 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
+ * 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)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE.
+ *
+ *	@(#)regfree.c	8.3 (Berkeley) 3/20/94
+ */
+
+#include <sys/types.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include "regex.h"
+
+#include "utils.h"
+#include "regex2.h"
+
+/*
+ - regfree - free everything
+ */
+void
+regfree(regex_t *preg)
+{
+	struct re_guts *g;
+
+	if (preg->re_magic != MAGIC1)	/* oops */
+		return;			/* nice to complain, but hard */
+
+	g = preg->re_g;
+	if (g == NULL || g->magic != MAGIC2)	/* oops again */
+		return;
+	preg->re_magic = 0;		/* mark it invalid */
+	g->magic = 0;			/* mark it invalid */
+
+	if (g->strip != NULL)
+		free((char *)g->strip);
+	if (g->sets != NULL)
+		free((char *)g->sets);
+	if (g->setbits != NULL)
+		free((char *)g->setbits);
+	if (g->must != NULL)
+		free(g->must);
+	free((char *)g);
+}

Propchange: commons/sandbox/runtime/trunk/src/main/native/srclib/regex/regfree.c
------------------------------------------------------------------------------
    svn:eol-style = native

Added: commons/sandbox/runtime/trunk/src/main/native/srclib/regex/utils.h
URL: http://svn.apache.org/viewvc/commons/sandbox/runtime/trunk/src/main/native/srclib/regex/utils.h?rev=807635&view=auto
==============================================================================
--- commons/sandbox/runtime/trunk/src/main/native/srclib/regex/utils.h (added)
+++ commons/sandbox/runtime/trunk/src/main/native/srclib/regex/utils.h Tue Aug 25 13:57:05 2009
@@ -0,0 +1,55 @@
+/*	$OpenBSD: utils.h,v 1.4 2003/06/02 20:18:36 millert Exp $	*/
+
+/*-
+ * Copyright (c) 1992, 1993, 1994 Henry Spencer.
+ * Copyright (c) 1992, 1993, 1994
+ *	The Regents of the University of California.  All rights reserved.
+ *
+ * This code is derived from software contributed to Berkeley by
+ * Henry Spencer.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * 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.
+ * 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.
+ * 3. 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.
+ *
+ * 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
+ * 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)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE.
+ *
+ *	@(#)utils.h	8.3 (Berkeley) 3/20/94
+ */
+
+/* utility definitions */
+#define	DUPMAX		_POSIX2_RE_DUP_MAX	/* xxx is this right? */
+#define	INFINITY	(DUPMAX + 1)
+#define	NC		(CHAR_MAX - CHAR_MIN + 1)
+typedef unsigned char uch;
+
+/* switch off assertions (if not already off) if no REDEBUG */
+#ifndef REDEBUG
+#ifndef NDEBUG
+#define	NDEBUG	/* no assertions please */
+#endif
+#endif
+#include <assert.h>
+
+/* for old systems with bcopy() but no memmove() */
+#ifdef USEBCOPY
+#define	memmove(d, s, c)	bcopy(s, d, c)
+#endif

Propchange: commons/sandbox/runtime/trunk/src/main/native/srclib/regex/utils.h
------------------------------------------------------------------------------
    svn:eol-style = native

Modified: commons/sandbox/runtime/trunk/src/main/native/test/sample.conf
URL: http://svn.apache.org/viewvc/commons/sandbox/runtime/trunk/src/main/native/test/sample.conf?rev=807635&r1=807634&r2=807635&view=diff
==============================================================================
--- commons/sandbox/runtime/trunk/src/main/native/test/sample.conf (original)
+++ commons/sandbox/runtime/trunk/src/main/native/test/sample.conf Tue Aug 25 13:57:05 2009
@@ -21,7 +21,7 @@
         <level2.1>
             XML2 = based like data
             <level3.1>
-                XML3 = based like data \
+                XML3 = ${Second} based like data \
     that goes over multiple lines
             </level3.1>
         </level2.1>

Modified: commons/sandbox/runtime/trunk/src/main/native/test/sample.ini
URL: http://svn.apache.org/viewvc/commons/sandbox/runtime/trunk/src/main/native/test/sample.ini?rev=807635&r1=807634&r2=807635&view=diff
==============================================================================
--- commons/sandbox/runtime/trunk/src/main/native/test/sample.ini (original)
+++ commons/sandbox/runtime/trunk/src/main/native/test/sample.ini Tue Aug 25 13:57:05 2009
@@ -44,6 +44,8 @@
 section=can be repeted multiple times
 [duplicate]
 # variable order is preserved
+string=string ${expansion) is done using $() or ${} \
+ ${USER}@$(HOSTNAME) \'${HOME}' = ${HOME}
 
 
 



Mime
View raw message