@@ -1,3 +1,10 @@

+Mon Sep 17 21:06:59 EEST 2007(edwin)

+------------------------------------

+ * libclamav/regex/: add regcomp(), regexec() impl. from OpenBSD's libc.

+ 	This code is licensed under the 3-clause BSD.

+	This will be used instead of system provided regexec()/regcomp() to

+	have consistent behaviour across platforms.

+

 Mon Sep 17 17:12:27 BST 2007 (njh)

 ----------------------------------

   * libclamav/mbox.c:	Bugs 665/667

@@ -207,9 +207,6 @@

 /* Define to 1 if you have the `recvmsg' function. */

 #undef HAVE_RECVMSG

-/* Define to 1 if you have the <regex.h> header file. */

-#undef HAVE_REGEX_H

-

 /* have resolv.h */

 #undef HAVE_RESOLV_H

@@ -19993,8 +19993,7 @@ fi

-

-for ac_header in stdint.h unistd.h sys/int_types.h dlfcn.h inttypes.h sys/inttypes.h memory.h ndir.h stdlib.h strings.h string.h sys/mman.h sys/param.h sys/stat.h sys/types.h malloc.h poll.h regex.h limits.h sys/filio.h sys/uio.h termios.h iconv.h stdbool.h pwd.h grp.h

+for ac_header in stdint.h unistd.h sys/int_types.h dlfcn.h inttypes.h sys/inttypes.h memory.h ndir.h stdlib.h strings.h string.h sys/mman.h sys/param.h sys/stat.h sys/types.h malloc.h poll.h limits.h sys/filio.h sys/uio.h termios.h iconv.h stdbool.h pwd.h grp.h

 do

 as_ac_Header=`echo "ac_cv_header_$ac_header" | $as_tr_sh`

 if { as_var=$as_ac_Header; eval "test \"\${$as_var+set}\" = set"; }; then

@@ -40,7 +40,7 @@ AC_DEFINE(SCANBUFF, 131072, [scan buffer size])

 AC_DEFINE(FILEBUFF, 8192,   [file i/o buffer size])

 AC_HEADER_STDC

-AC_CHECK_HEADERS(stdint.h unistd.h sys/int_types.h dlfcn.h inttypes.h sys/inttypes.h memory.h ndir.h stdlib.h strings.h string.h sys/mman.h sys/param.h sys/stat.h sys/types.h malloc.h poll.h regex.h limits.h sys/filio.h sys/uio.h termios.h iconv.h stdbool.h pwd.h grp.h)

+AC_CHECK_HEADERS(stdint.h unistd.h sys/int_types.h dlfcn.h inttypes.h sys/inttypes.h memory.h ndir.h stdlib.h strings.h string.h sys/mman.h sys/param.h sys/stat.h sys/types.h malloc.h poll.h limits.h sys/filio.h sys/uio.h termios.h iconv.h stdbool.h pwd.h grp.h)

 AC_CHECK_HEADER(syslog.h,AC_DEFINE(USE_SYSLOG,1,[use syslog]),)

 AC_TYPE_OFF_T

@@ -110,6 +110,11 @@ libclamav_la_SOURCES = \

 	is_tar.h \

 	tnef.c \

 	tnef.h \

+	regex/strlcpy.c \

+	regex/regcomp.c \

+	regex/regerror.c \

+	regex/regexec.c \

+	regex/regfree.c \

 	unrar/unrar15.c \

 	unrar/unrar20.h \

 	unrar/unrarcmd.h \

@@ -58,7 +58,7 @@ host_triplet = @host@

 target_triplet = @target@

 subdir = libclamav

 DIST_COMMON = $(include_HEADERS) $(srcdir)/Makefile.am \

-	$(srcdir)/Makefile.in

+	$(srcdir)/Makefile.in COPYING

 ACLOCAL_M4 = $(top_srcdir)/aclocal.m4

 am__aclocal_m4_deps = $(top_srcdir)/acinclude.m4 \

 	$(top_srcdir)/configure.in

@@ -84,10 +84,11 @@ am_libclamav_la_OBJECTS = matcher-ac.lo matcher-bm.lo matcher.lo \

 	pe.lo upx.lo htmlnorm.lo chmunpack.lo rebuildpe.lo petite.lo \

 	wwunpack.lo unsp.lo aspack.lo packlibs.lo fsg.lo mew.lo \

 	upack.lo line.lo untar.lo unzip.lo special.lo binhex.lo \

-	is_tar.lo tnef.lo unrar15.lo unrarvm.lo unrar.lo \

-	unrarfilter.lo unrarppm.lo unrar20.lo unrarcmd.lo unarj.lo \

-	LZMADecode.lo bzlib.lo infblock.lo nulsft.lo pdf.lo spin.lo \

-	yc.lo elf.lo sis.lo uuencode.lo pst.lo phishcheck.lo \

+	is_tar.lo tnef.lo strlcpy.lo regcomp.lo regerror.lo regexec.lo \

+	regfree.lo unrar15.lo unrarvm.lo unrar.lo unrarfilter.lo \

+	unrarppm.lo unrar20.lo unrarcmd.lo unarj.lo LZMADecode.lo \

+	bzlib.lo infblock.lo nulsft.lo pdf.lo spin.lo yc.lo elf.lo \

+	sis.lo uuencode.lo pst.lo phishcheck.lo \

 	phish_domaincheck_db.lo phish_whitelist.lo regex_list.lo \

 	sha256.lo mspack.lo cab.lo entconv.lo hashtab.lo dconf.lo \

 	lockdb.lo

@@ -325,6 +326,11 @@ libclamav_la_SOURCES = \

 	is_tar.h \

 	tnef.c \

 	tnef.h \

+	regex/strlcpy.c \

+	regex/regcomp.c \

+	regex/regerror.c \

+	regex/regexec.c \

+	regex/regfree.c \

 	unrar/unrar15.c \

 	unrar/unrar20.h \

 	unrar/unrarcmd.h \

@@ -505,7 +511,11 @@ distclean-compile:

 @AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/pst.Plo@am__quote@

 @AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/readdb.Plo@am__quote@

 @AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/rebuildpe.Plo@am__quote@

+@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/regcomp.Plo@am__quote@

+@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/regerror.Plo@am__quote@

 @AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/regex_list.Plo@am__quote@

+@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/regexec.Plo@am__quote@

+@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/regfree.Plo@am__quote@

 @AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/rtf.Plo@am__quote@

 @AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/scanners.Plo@am__quote@

 @AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/sha256.Plo@am__quote@

@@ -514,6 +524,7 @@ distclean-compile:

 @AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/special.Plo@am__quote@

 @AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/spin.Plo@am__quote@

 @AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/str.Plo@am__quote@

+@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/strlcpy.Plo@am__quote@

 @AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/table.Plo@am__quote@

 @AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/text.Plo@am__quote@

 @AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/tnef.Plo@am__quote@

@@ -556,6 +567,41 @@ distclean-compile:

 @AMDEP_TRUE@@am__fastdepCC_FALSE@	DEPDIR=$(DEPDIR) $(CCDEPMODE) $(depcomp) @AMDEPBACKSLASH@

 @am__fastdepCC_FALSE@	$(LTCOMPILE) -c -o $@ $<

+strlcpy.lo: regex/strlcpy.c

+@am__fastdepCC_TRUE@	if $(LIBTOOL) --tag=CC --mode=compile $(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(AM_CFLAGS) $(CFLAGS) -MT strlcpy.lo -MD -MP -MF "$(DEPDIR)/strlcpy.Tpo" -c -o strlcpy.lo `test -f 'regex/strlcpy.c' || echo '$(srcdir)/'`regex/strlcpy.c; \

+@am__fastdepCC_TRUE@	then mv -f "$(DEPDIR)/strlcpy.Tpo" "$(DEPDIR)/strlcpy.Plo"; else rm -f "$(DEPDIR)/strlcpy.Tpo"; exit 1; fi

+@AMDEP_TRUE@@am__fastdepCC_FALSE@	source='regex/strlcpy.c' object='strlcpy.lo' libtool=yes @AMDEPBACKSLASH@

+@AMDEP_TRUE@@am__fastdepCC_FALSE@	DEPDIR=$(DEPDIR) $(CCDEPMODE) $(depcomp) @AMDEPBACKSLASH@

+@am__fastdepCC_FALSE@	$(LIBTOOL) --tag=CC --mode=compile $(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(AM_CFLAGS) $(CFLAGS) -c -o strlcpy.lo `test -f 'regex/strlcpy.c' || echo '$(srcdir)/'`regex/strlcpy.c

+

+regcomp.lo: regex/regcomp.c

+@am__fastdepCC_TRUE@	if $(LIBTOOL) --tag=CC --mode=compile $(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(AM_CFLAGS) $(CFLAGS) -MT regcomp.lo -MD -MP -MF "$(DEPDIR)/regcomp.Tpo" -c -o regcomp.lo `test -f 'regex/regcomp.c' || echo '$(srcdir)/'`regex/regcomp.c; \

+@am__fastdepCC_TRUE@	then mv -f "$(DEPDIR)/regcomp.Tpo" "$(DEPDIR)/regcomp.Plo"; else rm -f "$(DEPDIR)/regcomp.Tpo"; exit 1; fi

+@AMDEP_TRUE@@am__fastdepCC_FALSE@	source='regex/regcomp.c' object='regcomp.lo' libtool=yes @AMDEPBACKSLASH@

+@AMDEP_TRUE@@am__fastdepCC_FALSE@	DEPDIR=$(DEPDIR) $(CCDEPMODE) $(depcomp) @AMDEPBACKSLASH@

+@am__fastdepCC_FALSE@	$(LIBTOOL) --tag=CC --mode=compile $(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(AM_CFLAGS) $(CFLAGS) -c -o regcomp.lo `test -f 'regex/regcomp.c' || echo '$(srcdir)/'`regex/regcomp.c

+

+regerror.lo: regex/regerror.c

+@am__fastdepCC_TRUE@	if $(LIBTOOL) --tag=CC --mode=compile $(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(AM_CFLAGS) $(CFLAGS) -MT regerror.lo -MD -MP -MF "$(DEPDIR)/regerror.Tpo" -c -o regerror.lo `test -f 'regex/regerror.c' || echo '$(srcdir)/'`regex/regerror.c; \

+@am__fastdepCC_TRUE@	then mv -f "$(DEPDIR)/regerror.Tpo" "$(DEPDIR)/regerror.Plo"; else rm -f "$(DEPDIR)/regerror.Tpo"; exit 1; fi

+@AMDEP_TRUE@@am__fastdepCC_FALSE@	source='regex/regerror.c' object='regerror.lo' libtool=yes @AMDEPBACKSLASH@

+@AMDEP_TRUE@@am__fastdepCC_FALSE@	DEPDIR=$(DEPDIR) $(CCDEPMODE) $(depcomp) @AMDEPBACKSLASH@

+@am__fastdepCC_FALSE@	$(LIBTOOL) --tag=CC --mode=compile $(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(AM_CFLAGS) $(CFLAGS) -c -o regerror.lo `test -f 'regex/regerror.c' || echo '$(srcdir)/'`regex/regerror.c

+

+regexec.lo: regex/regexec.c

+@am__fastdepCC_TRUE@	if $(LIBTOOL) --tag=CC --mode=compile $(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(AM_CFLAGS) $(CFLAGS) -MT regexec.lo -MD -MP -MF "$(DEPDIR)/regexec.Tpo" -c -o regexec.lo `test -f 'regex/regexec.c' || echo '$(srcdir)/'`regex/regexec.c; \

+@am__fastdepCC_TRUE@	then mv -f "$(DEPDIR)/regexec.Tpo" "$(DEPDIR)/regexec.Plo"; else rm -f "$(DEPDIR)/regexec.Tpo"; exit 1; fi

+@AMDEP_TRUE@@am__fastdepCC_FALSE@	source='regex/regexec.c' object='regexec.lo' libtool=yes @AMDEPBACKSLASH@

+@AMDEP_TRUE@@am__fastdepCC_FALSE@	DEPDIR=$(DEPDIR) $(CCDEPMODE) $(depcomp) @AMDEPBACKSLASH@

+@am__fastdepCC_FALSE@	$(LIBTOOL) --tag=CC --mode=compile $(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(AM_CFLAGS) $(CFLAGS) -c -o regexec.lo `test -f 'regex/regexec.c' || echo '$(srcdir)/'`regex/regexec.c

+

+regfree.lo: regex/regfree.c

+@am__fastdepCC_TRUE@	if $(LIBTOOL) --tag=CC --mode=compile $(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(AM_CFLAGS) $(CFLAGS) -MT regfree.lo -MD -MP -MF "$(DEPDIR)/regfree.Tpo" -c -o regfree.lo `test -f 'regex/regfree.c' || echo '$(srcdir)/'`regex/regfree.c; \

+@am__fastdepCC_TRUE@	then mv -f "$(DEPDIR)/regfree.Tpo" "$(DEPDIR)/regfree.Plo"; else rm -f "$(DEPDIR)/regfree.Tpo"; exit 1; fi

+@AMDEP_TRUE@@am__fastdepCC_FALSE@	source='regex/regfree.c' object='regfree.lo' libtool=yes @AMDEPBACKSLASH@

+@AMDEP_TRUE@@am__fastdepCC_FALSE@	DEPDIR=$(DEPDIR) $(CCDEPMODE) $(depcomp) @AMDEPBACKSLASH@

+@am__fastdepCC_FALSE@	$(LIBTOOL) --tag=CC --mode=compile $(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(AM_CFLAGS) $(CFLAGS) -c -o regfree.lo `test -f 'regex/regfree.c' || echo '$(srcdir)/'`regex/regfree.c

+

 unrar15.lo: unrar/unrar15.c

 @am__fastdepCC_TRUE@	if $(LIBTOOL) --tag=CC --mode=compile $(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(AM_CFLAGS) $(CFLAGS) -MT unrar15.lo -MD -MP -MF "$(DEPDIR)/unrar15.Tpo" -c -o unrar15.lo `test -f 'unrar/unrar15.c' || echo '$(srcdir)/'`unrar/unrar15.c; \

 @am__fastdepCC_TRUE@	then mv -f "$(DEPDIR)/unrar15.Tpo" "$(DEPDIR)/unrar15.Plo"; else rm -f "$(DEPDIR)/unrar15.Tpo"; exit 1; fi

@@ -353,17 +353,17 @@ static int build_regex(regex_t* preg,const char* regex,int nosub)

 {

 	int rc;

 	cli_dbgmsg("Phishcheck: Compiling regex: %s\n",regex);

-	rc = regcomp(preg,regex,REG_EXTENDED|REG_ICASE|(nosub ? REG_NOSUB :0));

+	rc = cli_regcomp(preg,regex,REG_EXTENDED|REG_ICASE|(nosub ? REG_NOSUB :0));

 	if(rc) {

 #ifdef	C_WINDOWS

 		cli_errmsg("Phishcheck: Error in compiling regex, disabling phishing checks\n");

 #else

-		size_t buflen =	regerror(rc,preg,NULL,0);

+		size_t buflen =	cli_regerror(rc,preg,NULL,0);

 		char *errbuf = cli_malloc(buflen);

 		if(errbuf) {

-			regerror(rc,preg,errbuf,buflen);

+			cli_regerror(rc,preg,errbuf,buflen);

 			cli_errmsg("Phishcheck: Error in compiling regex:%s\nDisabling phishing checks\n",errbuf);

 			free(errbuf);

 		} else

@@ -446,7 +446,7 @@ static int get_host(const struct phishcheck* s,struct string* dest,const char* U

 static int isCountryCode(const struct phishcheck* s,const char* str)

 {

-	return str ? !regexec(&s->preg_cctld,str,0,NULL,0) : 0;

+	return str ? !cli_regexec(&s->preg_cctld,str,0,NULL,0) : 0;

 }

 static int isTLD(const struct phishcheck* pchk,const char* str,int len)

@@ -461,7 +461,7 @@ static int isTLD(const struct phishcheck* pchk,const char* str,int len)

 			return CL_EMEM;

 		strncpy(s,str,len);

 		s[len]='\0';

-		rc = !regexec(&pchk->preg_tld,s,0,NULL,0);

+		rc = !cli_regexec(&pchk->preg_tld,s,0,NULL,0);

 		free(s);

 		return rc ? 1 : 0;

 	}

@@ -880,7 +880,7 @@ static char hex2int(const unsigned char* src)

 static void free_regex(regex_t* p)

 {

 	if(p) {

-		regfree(p);

+		cli_regfree(p);

 	}

 }

@@ -977,12 +977,12 @@ void phishing_done(struct cl_engine* engine)

  */

 static int isURL(const struct phishcheck* pchk,const char* URL)

 {

-	return URL ? !regexec(&pchk->preg,URL,0,NULL,0) : 0;

+	return URL ? !cli_regexec(&pchk->preg,URL,0,NULL,0) : 0;

 }

 static int isNumericURL(const struct phishcheck* pchk,const char* URL)

 {

-	return URL ? !regexec(&pchk->preg_numeric,URL,0,NULL,0) : 0;

+	return URL ? !cli_regexec(&pchk->preg_numeric,URL,0,NULL,0) : 0;

 }

 /* Cleans up @urls

@@ -1013,7 +1013,7 @@ static int url_get_host(const struct phishcheck* pchk, struct url_check* url,str

 		string_free(host);

 		return CL_PHISH_TEXTURL;

 	}

-	if(url->flags&CHECK_CLOAKING && !regexec(&pchk->preg_hexurl,host->data,0,NULL,0)) {

+	if(url->flags&CHECK_CLOAKING && !cli_regexec(&pchk->preg_hexurl,host->data,0,NULL,0)) {

 		/* uses a regex here, so that we don't accidentally block 0xacab.net style hosts */

 		string_free(host);

 		return CL_PHISH_HEX_URL;

@@ -20,9 +20,7 @@

 #ifndef _PHISH_CHECK_H

 #define _PHISH_CHECK_H

-#ifdef	HAVE_REGEX_H

-#include <regex.h>

-#endif

+#include "regex/regex.h"

 #define CL_PHISH_BASE 100

 enum phish_status {CL_PHISH_NODECISION=0,CL_PHISH_CLEAN=CL_PHISH_BASE, CL_PHISH_CLEANUP_OK,CL_PHISH_HOST_OK, CL_PHISH_DOMAIN_OK,

new file mode 100644

@@ -0,0 +1,68 @@

+/*-

+ * This code is derived from OpenBSD's libc/regex, original license follows:

+ *

+ * 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.

+ *

+ *	@(#)cclass.h	8.3 (Berkeley) 3/20/94

+ */

+

+/* character-class table */

+static struct cclass {

+	const char *name;

+	const char *chars;

+	const char *multis;

+} cclasses[] = {

+	{ "alnum",	"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz\

+0123456789",				""} ,

+	{ "alpha",	"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz",

+					""} ,

+	{ "blank",	" \t",		""} ,

+	{ "cntrl",	"\007\b\t\n\v\f\r\1\2\3\4\5\6\16\17\20\21\22\23\24\

+\25\26\27\30\31\32\33\34\35\36\37\177",	""} ,

+	{ "digit",	"0123456789",	""} ,

+	{ "graph",	"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz\

+0123456789!\"#$%&'()*+,-./:;<=>?@[\\]^_`{|}~",

+					""} ,

+	{ "lower",	"abcdefghijklmnopqrstuvwxyz",

+					""} ,

+	{ "print",	"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz\

+0123456789!\"#$%&'()*+,-./:;<=>?@[\\]^_`{|}~ ",

+					""} ,

+	{ "punct",	"!\"#$%&'()*+,-./:;<=>?@[\\]^_`{|}~",

+					""} ,

+	{ "space",	"\t\n\v\f\r ",	""} ,

+	{ "upper",	"ABCDEFGHIJKLMNOPQRSTUVWXYZ",

+					""} ,

+	{ "xdigit",	"0123456789ABCDEFabcdef",

+					""} ,

+	{ NULL,		0,		"" }

+};

new file mode 100644

@@ -0,0 +1,139 @@

+/*-

+ * This code is derived from OpenBSD's libc/regex, original license follows:

+ *

+ * 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.

+ *

+ *	@(#)cname.h	8.3 (Berkeley) 3/20/94

+ */

+

+/* character-name table */

+static struct cname {

+	const char *name;

+	char code;

+} cnames[] = {

+	{ "NUL",			'\0' },

+	{ "SOH",			'\001' },

+	{ "STX",			'\002' },

+	{ "ETX",			'\003' },

+	{ "EOT",			'\004' },

+	{ "ENQ",			'\005' },

+	{ "ACK",			'\006' },

+	{ "BEL",			'\007' },

+	{ "alert",			'\007' },

+	{ "BS",				'\010' },

+	{ "backspace",			'\b' },

+	{ "HT",				'\011' },

+	{ "tab",			'\t' },

+	{ "LF",				'\012' },

+	{ "newline",			'\n' },

+	{ "VT",				'\013' },

+	{ "vertical-tab",		'\v' },

+	{ "FF",				'\014' },

+	{ "form-feed",			'\f' },

+	{ "CR",				'\015' },

+	{ "carriage-return",		'\r' },

+	{ "SO",				'\016' },

+	{ "SI",				'\017' },

+	{ "DLE",			'\020' },

+	{ "DC1",			'\021' },

+	{ "DC2",			'\022' },

+	{ "DC3",			'\023' },

+	{ "DC4",			'\024' },

+	{ "NAK",			'\025' },

+	{ "SYN",			'\026' },

+	{ "ETB",			'\027' },

+	{ "CAN",			'\030' },

+	{ "EM",				'\031' },

+	{ "SUB",			'\032' },

+	{ "ESC",			'\033' },

+	{ "IS4",			'\034' },

+	{ "FS",				'\034' },

+	{ "IS3",			'\035' },

+	{ "GS",				'\035' },

+	{ "IS2",			'\036' },

+	{ "RS",				'\036' },

+	{ "IS1",			'\037' },

+	{ "US",				'\037' },

+	{ "space",			' ' },

+	{ "exclamation-mark",		'!' },

+	{ "quotation-mark",		'"' },

+	{ "number-sign",		'#' },

+	{ "dollar-sign",		'$' },

+	{ "percent-sign",		'%' },

+	{ "ampersand",			'&' },

+	{ "apostrophe",			'\'' },

+	{ "left-parenthesis",		'(' },

+	{ "right-parenthesis",		')' },

+	{ "asterisk",			'*' },

+	{ "plus-sign",			'+' },

+	{ "comma",			',' },

+	{ "hyphen",			'-' },

+	{ "hyphen-minus",		'-' },

+	{ "period",			'.' },

+	{ "full-stop",			'.' },

+	{ "slash",			'/' },

+	{ "solidus",			'/' },

+	{ "zero",			'0' },

+	{ "one",			'1' },

+	{ "two",			'2' },

+	{ "three",			'3' },

+	{ "four",			'4' },

+	{ "five",			'5' },

+	{ "six",			'6' },

+	{ "seven",			'7' },

+	{ "eight",			'8' },

+	{ "nine",			'9' },

+	{ "colon",			':' },

+	{ "semicolon",			';' },

+	{ "less-than-sign",		'<' },

+	{ "equals-sign",		'=' },

+	{ "greater-than-sign",		'>' },

+	{ "question-mark",		'?' },

+	{ "commercial-at",		'@' },

+	{ "left-square-bracket",	'[' },

+	{ "backslash",			'\\' },

+	{ "reverse-solidus",		'\\' },

+	{ "right-square-bracket",	']' },

+	{ "circumflex",			'^' },

+	{ "circumflex-accent",		'^' },

+	{ "underscore",			'_' },

+	{ "low-line",			'_' },

+	{ "grave-accent",		'`' },

+	{ "left-brace",			'{' },

+	{ "left-curly-bracket",		'{' },

+	{ "vertical-line",		'|' },

+	{ "right-brace",		'}' },

+	{ "right-curly-bracket",	'}' },

+	{ "tilde",			'~' },

+	{ "DEL",			'\177' },

+	{ NULL,				0 }

+};

new file mode 100644

@@ -0,0 +1,1020 @@

+/*-

+ * This code is derived from OpenBSD's libc/regex, original license follows:

+ *

+ * 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.

+ *

+ *	@(#)engine.c	8.5 (Berkeley) 3/20/94

+ */

+

+/*

+ * The matching engine and friends.  This file is #included by regexec.c

+ * after suitable #defines of a variety of macros used herein, so that

+ * different state representations can be used without duplicating masses

+ * of code.

+ */

+

+#ifdef SNAMES

+#define	matcher	smatcher

+#define	fast	sfast

+#define	slow	sslow

+#define	dissect	sdissect

+#define	backref	sbackref

+#define	step	sstep

+#define	print	sprint

+#define	at	sat

+#define	match	smat

+#define	nope	snope

+#endif

+#ifdef LNAMES

+#define	matcher	lmatcher

+#define	fast	lfast

+#define	slow	lslow

+#define	dissect	ldissect

+#define	backref	lbackref

+#define	step	lstep

+#define	print	lprint

+#define	at	lat

+#define	match	lmat

+#define	nope	lnope

+#endif

+

+/* another structure passed up and down to avoid zillions of parameters */

+struct match {

+	struct re_guts *g;

+	int eflags;

+	regmatch_t *pmatch;	/* [nsub+1] (0 element unused) */

+	char *offp;		/* offsets work from here */

+	char *beginp;		/* start of string -- virtual NUL precedes */

+	char *endp;		/* end of string -- virtual NUL here */

+	char *coldp;		/* can be no match starting before here */

+	char **lastpos;		/* [nplus+1] */

+	STATEVARS;

+	states st;		/* current states */

+	states fresh;		/* states for a fresh start */

+	states tmp;		/* temporary */

+	states empty;		/* empty set of states */

+};

+

+static int matcher(struct re_guts *, char *, size_t, regmatch_t[], int);

+static char *dissect(struct match *, char *, char *, sopno, sopno);

+static char *backref(struct match *, char *, char *, sopno, sopno, sopno, int);

+static char *fast(struct match *, char *, char *, sopno, sopno);

+static char *slow(struct match *, char *, char *, sopno, sopno);

+static states step(struct re_guts *, sopno, sopno, states, int, states);

+#define MAX_RECURSION	100

+#define	BOL	(OUT+1)

+#define	EOL	(BOL+1)

+#define	BOLEOL	(BOL+2)

+#define	NOTHING	(BOL+3)

+#define	BOW	(BOL+4)

+#define	EOW	(BOL+5)

+#define	CODEMAX	(BOL+5)		/* highest code used */

+#define	NONCHAR(c)	((c) > CHAR_MAX)

+#define	NNONCHAR	(CODEMAX-CHAR_MAX)

+#ifdef REDEBUG

+static void print(struct match *, char *, states, int, FILE *);

+#endif

+#ifdef REDEBUG

+static void at(struct match *, char *, char *, char *, sopno, sopno);

+#endif

+#ifdef REDEBUG

+static char *pchar(int);

+#endif

+

+#ifdef REDEBUG

+#define	SP(t, s, c)	print(m, t, s, c, stdout)

+#define	AT(t, p1, p2, s1, s2)	at(m, t, p1, p2, s1, s2)

+#define	NOTE(str)	{ if (m->eflags&REG_TRACE) (void)printf("=%s\n", (str)); }

+static int nope = 0;

+#else

+#define	SP(t, s, c)	/* nothing */

+#define	AT(t, p1, p2, s1, s2)	/* nothing */

+#define	NOTE(s)	/* nothing */

+#endif

+

+/*

+ - matcher - the actual matching engine

+ */

+static int			/* 0 success, REG_NOMATCH failure */

+matcher(struct re_guts *g, char *string, size_t nmatch, regmatch_t pmatch[],

+    int eflags)

+{

+	char *endp;

+	size_t i;

+	struct match mv;

+	struct match *m = &mv;

+	char *dp;

+	const sopno gf = g->firststate+1;	/* +1 for OEND */

+	const sopno gl = g->laststate;

+	char *start;

+	char *stop;

+

+	/* simplify the situation where possible */

+	if (g->cflags&REG_NOSUB)

+		nmatch = 0;

+	if (eflags&REG_STARTEND) {

+		start = string + pmatch[0].rm_so;

+		stop = string + pmatch[0].rm_eo;

+	} else {

+		start = string;

+		stop = start + strlen(start);

+	}

+	if (stop < start)

+		return(REG_INVARG);

+

+	/* prescreening; this does wonders for this rather slow code */

+	if (g->must != NULL) {

+		for (dp = start; dp < stop; dp++)

+			if (*dp == g->must[0] && stop - dp >= g->mlen &&

+				memcmp(dp, g->must, (size_t)g->mlen) == 0)

+				break;

+		if (dp == stop)		/* we didn't find g->must */

+			return(REG_NOMATCH);

+	}

+

+	/* match struct setup */

+	m->g = g;

+	m->eflags = eflags;

+	m->pmatch = NULL;

+	m->lastpos = NULL;

+	m->offp = string;

+	m->beginp = start;

+	m->endp = stop;

+	STATESETUP(m, 4);

+	SETUP(m->st);

+	SETUP(m->fresh);

+	SETUP(m->tmp);

+	SETUP(m->empty);

+	CLEAR(m->empty);

+

+	/* this loop does only one repetition except for backrefs */

+	for (;;) {

+		endp = fast(m, start, stop, gf, gl);

+		if (endp == NULL) {		/* a miss */

+			free(m->pmatch);

+			free(m->lastpos);

+			STATETEARDOWN(m);

+			return(REG_NOMATCH);

+		}

+		if (nmatch == 0 && !g->backrefs)

+			break;		/* no further info needed */

+

+		/* where? */

+		assert(m->coldp != NULL);

+		for (;;) {

+			NOTE("finding start");

+			endp = slow(m, m->coldp, stop, gf, gl);

+			if (endp != NULL)

+				break;

+			assert(m->coldp < m->endp);

+			m->coldp++;

+		}

+		if (nmatch == 1 && !g->backrefs)

+			break;		/* no further info needed */

+

+		/* oh my, he wants the subexpressions... */

+		if (m->pmatch == NULL)

+			m->pmatch = (regmatch_t *)cli_malloc((m->g->nsub + 1) *

+							sizeof(regmatch_t));

+		if (m->pmatch == NULL) {

+			STATETEARDOWN(m);

+			return(REG_ESPACE);

+		}

+		for (i = 1; i <= m->g->nsub; i++)

+			m->pmatch[i].rm_so = m->pmatch[i].rm_eo = -1;

+		if (!g->backrefs && !(m->eflags&REG_BACKR)) {

+			NOTE("dissecting");

+			dp = dissect(m, m->coldp, endp, gf, gl);

+		} else {

+			if (g->nplus > 0 && m->lastpos == NULL)

+				m->lastpos = (char **)cli_malloc((g->nplus+1) *

+							sizeof(char *));

+			if (g->nplus > 0 && m->lastpos == NULL) {

+				free(m->pmatch);

+				STATETEARDOWN(m);

+				return(REG_ESPACE);

+			}

+			NOTE("backref dissect");

+			dp = backref(m, m->coldp, endp, gf, gl, (sopno)0, 0);

+		}

+		if (dp != NULL)

+			break;

+

+		/* uh-oh... we couldn't find a subexpression-level match */

+		assert(g->backrefs);	/* must be back references doing it */

+		assert(g->nplus == 0 || m->lastpos != NULL);

+		for (;;) {

+			if (dp != NULL || endp <= m->coldp)

+				break;		/* defeat */

+			NOTE("backoff");

+			endp = slow(m, m->coldp, endp-1, gf, gl);

+			if (endp == NULL)

+				break;		/* defeat */

+			/* try it on a shorter possibility */

+#ifndef NDEBUG

+			for (i = 1; i <= m->g->nsub; i++) {

+				assert(m->pmatch[i].rm_so == -1);

+				assert(m->pmatch[i].rm_eo == -1);

+			}

+#endif

+			NOTE("backoff dissect");

+			dp = backref(m, m->coldp, endp, gf, gl, (sopno)0, 0);

+		}

+		assert(dp == NULL || dp == endp);

+		if (dp != NULL)		/* found a shorter one */

+			break;

+

+		/* despite initial appearances, there is no match here */

+		NOTE("false alarm");

+		if (m->coldp == stop)

+			break;

+		start = m->coldp + 1;	/* recycle starting later */

+	}

+

+	/* fill in the details if requested */

+	if (nmatch > 0) {

+		pmatch[0].rm_so = m->coldp - m->offp;

+		pmatch[0].rm_eo = endp - m->offp;

+	}

+	if (nmatch > 1) {

+		assert(m->pmatch != NULL);

+		for (i = 1; i < nmatch; i++)

+			if (i <= m->g->nsub)

+				pmatch[i] = m->pmatch[i];

+			else {

+				pmatch[i].rm_so = -1;

+				pmatch[i].rm_eo = -1;

+			}

+	}

+

+	if (m->pmatch != NULL)

+		free((char *)m->pmatch);

+	if (m->lastpos != NULL)

+		free((char *)m->lastpos);

+	STATETEARDOWN(m);

+	return(0);

+}

+

+/*

+ - dissect - figure out what matched what, no back references

+ */

+static char *			/* == stop (success) always */

+dissect(struct match *m, char *start, char *stop, sopno startst, sopno stopst)

+{

+	int i;

+	sopno ss;	/* start sop of current subRE */

+	sopno es;	/* end sop of current subRE */

+	char *sp;	/* start of string matched by it */

+	char *stp;	/* string matched by it cannot pass here */

+	char *rest;	/* start of rest of string */

+	char *tail;	/* string unmatched by rest of RE */

+	sopno ssub;	/* start sop of subsubRE */

+	sopno esub;	/* end sop of subsubRE */

+	char *ssp;	/* start of string matched by subsubRE */

+	char *sep;	/* end of string matched by subsubRE */

+	char *oldssp;	/* previous ssp */

+	char *dp;

+

+	AT("diss", start, stop, startst, stopst);

+	sp = start;

+	for (ss = startst; ss < stopst; ss = es) {

+		/* identify end of subRE */

+		es = ss;

+		switch (OP(m->g->strip[es])) {

+		case OPLUS_:

+		case OQUEST_:

+			es += OPND(m->g->strip[es]);

+			break;

+		case OCH_:

+			while (OP(m->g->strip[es]) != O_CH)

+				es += OPND(m->g->strip[es]);

+			break;

+		}

+		es++;

+

+		/* figure out what it matched */

+		switch (OP(m->g->strip[ss])) {

+		case OEND:

+			assert(nope);

+			break;

+		case OCHAR:

+			sp++;

+			break;

+		case OBOL:

+		case OEOL:

+		case OBOW:

+		case OEOW:

+			break;

+		case OANY:

+		case OANYOF:

+			sp++;

+			break;

+		case OBACK_:

+		case O_BACK:

+			assert(nope);

+			break;

+		/* cases where length of match is hard to find */

+		case OQUEST_:

+			stp = stop;

+			for (;;) {

+				/* how long could this one be? */

+				rest = slow(m, sp, stp, ss, es);

+				assert(rest != NULL);	/* it did match */

+				/* could the rest match the rest? */

+				tail = slow(m, rest, stop, es, stopst);

+				if (tail == stop)

+					break;		/* yes! */

+				/* no -- try a shorter match for this one */

+				stp = rest - 1;

+				assert(stp >= sp);	/* it did work */

+			}

+			ssub = ss + 1;

+			esub = es - 1;

+			/* did innards match? */

+			if (slow(m, sp, rest, ssub, esub) != NULL) {

+				dp = dissect(m, sp, rest, ssub, esub);

+				assert(dp == rest);

+			} else		/* no */

+				assert(sp == rest);

+			sp = rest;

+			break;

+		case OPLUS_:

+			stp = stop;

+			for (;;) {

+				/* how long could this one be? */

+				rest = slow(m, sp, stp, ss, es);

+				assert(rest != NULL);	/* it did match */

+				/* could the rest match the rest? */

+				tail = slow(m, rest, stop, es, stopst);

+				if (tail == stop)

+					break;		/* yes! */

+				/* no -- try a shorter match for this one */

+				stp = rest - 1;

+				assert(stp >= sp);	/* it did work */

+			}

+			ssub = ss + 1;

+			esub = es - 1;

+			ssp = sp;

+			oldssp = ssp;

+			for (;;) {	/* find last match of innards */

+				sep = slow(m, ssp, rest, ssub, esub);

+				if (sep == NULL || sep == ssp)

+					break;	/* failed or matched null */

+				oldssp = ssp;	/* on to next try */

+				ssp = sep;

+			}

+			if (sep == NULL) {

+				/* last successful match */

+				sep = ssp;

+				ssp = oldssp;

+			}

+			assert(sep == rest);	/* must exhaust substring */

+			assert(slow(m, ssp, sep, ssub, esub) == rest);

+			dp = dissect(m, ssp, sep, ssub, esub);

+			assert(dp == sep);

+			sp = rest;

+			break;

+		case OCH_:

+			stp = stop;

+			for (;;) {

+				/* how long could this one be? */

+				rest = slow(m, sp, stp, ss, es);

+				assert(rest != NULL);	/* it did match */

+				/* could the rest match the rest? */

+				tail = slow(m, rest, stop, es, stopst);

+				if (tail == stop)

+					break;		/* yes! */

+				/* no -- try a shorter match for this one */

+				stp = rest - 1;

+				assert(stp >= sp);	/* it did work */

+			}

+			ssub = ss + 1;

+			esub = ss + OPND(m->g->strip[ss]) - 1;