sip_parse_uri.c

VoIP use SIP protocol interface

/*
 * CDDL HEADER START
 *
 * The contents of this file are subject to the terms of the
 * Common Development and Distribution License (the "License").
 * You may not use this file except in compliance with the License.
 *
 * You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE
 * or http://www.opensolaris.org/os/licensing.
 * See the License for the specific language governing permissions
 * and limitations under the License.
 *
 * When distributing Covered Code, include this CDDL HEADER in each
 * file and include the License file at usr/src/OPENSOLARIS.LICENSE.
 * If applicable, add the following below this CDDL HEADER, with the
 * fields enclosed by brackets "[]" replaced with your own identifying
 * information: Portions Copyright [yyyy] [name of copyright owner]
 *
 * CDDL HEADER END
 */

/*
 * Copyright 2006 Sun Microsystems, Inc.  All rights reserved.
 * Use is subject to license terms.
 */
#pragma ident	"@(#)sip_parse_uri.c	1.3	06/08/16 SMI"

#include <stdlib.h>
#include <string.h>
#include <ctype.h>

#include "sip_parse_uri.h"

/*
 * SIP-URI          =  "sip:" [ userinfo ] hostport uri-parameters [ headers ]
 * SIPS-URI         =  "sips:" [ userinfo ] hostport uri-parameters [ headers ]
 * userinfo         =  ( user / telephone-subscriber ) [ ":" password ] "@"
 * user             =  1*( unreserved / escaped / user-unreserved )
 * user-unreserved  =  "&" / "=" / "+" / "$" / "," / ";" / "?" / "/"
 * password         =  *( unreserved / escaped / "&" / "=" / "+" / "$" / "," )
 * hostport         =  host [ ":" port ]
 * host             =  hostname / IPv4address / IPv6reference
 * hostname         =  *( domainlabel "." ) toplabel [ "." ]
 * domainlabel      =  alphanum / alphanum *( alphanum / "-" ) alphanum
 * toplabel         =  ALPHA / ALPHA *( alphanum / "-" ) alphanum
 * IPv4address    =  1*3DIGIT "." 1*3DIGIT "." 1*3DIGIT "." 1*3DIGIT
 * IPv6reference  =  "[" IPv6address "]"
 * IPv6address    =  hexpart [ ":" IPv4address ]
 * hexpart        =  hexseq / hexseq "::" [ hexseq ] / "::" [ hexseq ]
 * hexseq         =  hex4 *( ":" hex4)
 * hex4           =  1*4HEXDIG
 * port           =  1*DIGIT
 *
 * The BNF for telephone-subscriber can be found in RFC 2806 [9].  Note,
 * however, that any characters allowed there that are not allowed in
 * the user part of the SIP URI MUST be escaped.
 *
 * uri-parameters    =  *( ";" uri-parameter)
 * uri-parameter     =  transport-param / user-param / method-param
 *                      / ttl-param / maddr-param / lr-param / other-param
 * transport-param   =  "transport="( "udp" / "tcp" / "sctp" / "tls"
 *                     / other-transport)
 * other-transport   =  token
 * user-param        =  "user=" ( "phone" / "ip" / other-user)
 * other-user        =  token
 * method-param      =  "method=" Method
 * ttl-param         =  "ttl=" ttl
 * maddr-param       =  "maddr=" host
 * lr-param          =  "lr"
 * other-param       =  pname [ "=" pvalue ]
 * pname             =  1*paramchar
 * pvalue            =  1*paramchar
 * paramchar         =  param-unreserved / unreserved / escaped
 * param-unreserved  =  "[" / "]" / "/" / ":" / "&" / "+" / "$"
 * headers         =  "?" header *( "&" header )
 * header          =  hname "=" hvalue
 * hname           =  1*( hnv-unreserved / unreserved / escaped )
 * hvalue          =  *( hnv-unreserved / unreserved / escaped )
 * hnv-unreserved  =  "[" / "]" / "/" / "?" / ":" / "+" / "$"
 *
 */

#define	SIP_URI_MSG_BUF_SZ	100

#define	SIP_URI_ISHEX(c)					\
	(((int)(c) >= 0x30 && (int)(c) <= 0x39) || 	\
	((int)(c) >= 0x41 && (int)(c) <= 0x46) || 	\
	((int)(c) >= 0x61 && (int)(c) <= 0x66))

#define	SIP_URI_ISURLESCAPE(scan, end)			\
	((scan) + 2 < (end) && (scan)[0] == '%' && 	\
	SIP_URI_ISHEX((scan)[1]) && SIP_URI_ISHEX((scan[2])))

/*
 * URL character classes
 *  mark	- _ . ! ~ * ' ()
 *  reserved	; / ? : @ & = + $ ,    also [] for IPv6
 *  unreserved	alphanum mark
 *  pchar	: @ & = + $ , unreserved
 *  userinfo	; : & = + $ , unreserved escaped
 *  relsegment	; @ & = + $ , unreserved escaped
 *  reg_name	; : @ & = + $ , unreserved escaped
 *  token	- _ . ! ~ * ' %  + `
 *  param-unreserved  [ ] / : + $ &
 *  hnv-unreserved    [ ] / : + $ ?
 */
#define	SIP_URI_ALPHA_BIT		0x0001
#define	SIP_URI_DIGIT_BIT		0x0002
#define	SIP_URI_ALNUM_BITS		0x0003
#define	SIP_URI_SCHEME_BIT		0x0004	/* for - + . */
#define	SIP_URI_TOKEN_BIT		0x0008	/* for - _ . ! ~ * ' % + ` */
#define	SIP_URI_QUEST_BIT		0x0010	/* for ? */
#define	SIP_URI_AT_BIT			0x0020	/* for @ */
#define	SIP_URI_COLON_BIT		0x0040	/* for : */
#define	SIP_URI_SEMI_BIT		0x0080	/* for ; */
#define	SIP_URI_DASH_BIT		0x0100	/* for - */
#define	SIP_URI_MARK_BIT		0x0200	/* for - _ . ! ~ * ' ( ) */
#define	SIP_URI_AND_BIT			0x0400	/* for & */
#define	SIP_URI_PHCOMM_BIT		0x0800	/* for [ ] / : + $ */
#define	SIP_URI_OTHER_BIT		0x1000	/* for = + $ , */
#define	SIP_URI_SLASH_BIT		0x2000	/* for / */
#define	SIP_URI_VISUALSEP_BIT		0x4000	/* for -.() */
#define	SIP_URI_DTMFURI_DIGIT_BIT	0x8000	/* for *ABCD */

#define	a 			SIP_URI_ALPHA_BIT
#define	d 			SIP_URI_DIGIT_BIT
#define	s 			SIP_URI_SCHEME_BIT
#define	t 			SIP_URI_TOKEN_BIT
#define	q 			SIP_URI_QUEST_BIT
#define	m 			SIP_URI_AT_BIT
#define	c 			SIP_URI_COLON_BIT
#define	i 			SIP_URI_SEMI_BIT
#define	h 			SIP_URI_DASH_BIT
#define	k 			SIP_URI_MARK_BIT
#define	n 			SIP_URI_AND_BIT
#define	o 			SIP_URI_PHCOMM_BIT
#define	r 			SIP_URI_OTHER_BIT
#define	l 			SIP_URI_SLASH_BIT
#define	v 			SIP_URI_VISUALSEP_BIT
#define	f 			SIP_URI_DTMFURI_DIGIT_BIT

static const unsigned short sip_uri_table[256] = {
	0,	0,	0,	0,	0,	0,	0,	0,
	0,	0,	0,	0,	0,	0,	0,	0,
	0,	0,	0,	0,	0,	0,	0,	0,
	0,	0,	0,	0,	0,	0,	0,	0,
	0,	t|k,	0,	0,	o|r,	t,	n,	t|k,
	k|v,	k|v,	t|k|f, s|t|r|o,	r,  h|s|t|k|v, s|t|k|v,	o|l,
	d,	d,	d,	d,	d,	d,	d,	d,
	d,	d,	c|o,	i,	0,	r,	0,	q,
	m,	a|f,	a|f,	a|f,	a|f,	a,	a,	a,
	a,	a,	a,	a,	a,	a,	a,	a,
	a,	a,	a,	a,	a,	a,	a,	a,
	a,	a,	a,	o,	0,	o,	0,	t|k,
	t,	a,	a,	a,	a,	a,	a,	a,
	a,	a,	a,	a,	a,	a,	a,	a,
	a,	a,	a,	a,	a,	a,	a,	a,
	a,	a,	a,	0,	0,	0,	t|k,	0,
	0,	0,	0,	0,	0,	0,	0,	0,
	0,	0,	0,	0,	0,	0,	0,	0,
	0,	0,	0,	0,	0,	0,	0,	0,
	0,	0,	0,	0,	0,	0,	0,	0,
	0,	0,	0,	0,	0,	0,	0,	0,
	0,	0,	0,	0,	0,	0,	0,	0,
	0,	0,	0,	0,	0,	0,	0,	0,
	0,	0,	0,	0,	0,	0,	0,	0,
	0,	0,	0,	0,	0,	0,	0,	0,
	0,	0,	0,	0,	0,	0,	0,	0,
	0,	0,	0,	0,	0,	0,	0,	0,
	0,	0,	0,	0,	0,	0,	0,	0,
	0,	0,	0,	0,	0,	0,	0,	0,
	0,	0,	0,	0,	0,	0,	0,	0,
	0,	0,	0,	0,	0,	0,	0,	0,
	0,	0,	0,	0,	0,	0,	0,	0,
};

#undef	a
#undef	d
#undef	s
#undef	t
#undef	q
#undef	m
#undef	c
#undef	i
#undef	h
#undef	k
#undef	n
#undef	o
#undef	r
#undef	l
#undef	v
#undef	f

#define	SIP_URI_UT(c)			sip_uri_table[(unsigned char)(c)]
#define	SIP_URI_ISALPHA(c)		(SIP_URI_UT(c) & SIP_URI_ALPHA_BIT)
#define	SIP_URI_ISDIGIT(c)		(SIP_URI_UT(c) & SIP_URI_DIGIT_BIT)
#define	SIP_URI_ISALNUM(c)		(SIP_URI_UT(c) & SIP_URI_ALNUM_BITS)
#define	SIP_URI_ISSCHEME(c)		\
		(SIP_URI_UT(c) & (SIP_URI_ALNUM_BITS|SIP_URI_SCHEME_BIT))
#define	SIP_URI_ISTOKEN(c)		\
		(SIP_URI_UT(c) & (SIP_URI_ALNUM_BITS|SIP_URI_TOKEN_BIT))
#define	SIP_URI_ISSIPDELIM(c)		\
		(SIP_URI_UT(c) & (SIP_URI_SEMI_BIT|SIP_URI_QUEST_BIT))
#define	SIP_URI_ISSIPHDELIM(c)					\
	(SIP_URI_UT(c) & (SIP_URI_COLON_BIT|SIP_URI_SEMI_BIT|SIP_URI_QUEST_BIT))
#define	SIP_URI_ISHOST(c)		\
		(SIP_URI_UT(c) & (SIP_URI_ALNUM_BITS|SIP_URI_DASH_BIT))
#define	SIP_URI_ISUSER(c)						\
	(SIP_URI_UT(c) & (SIP_URI_OTHER_BIT|SIP_URI_SEMI_BIT|		\
	SIP_URI_QUEST_BIT|SIP_URI_SLASH_BIT|SIP_URI_AND_BIT))

#define	SIP_URI_ISABSHDELIM(c)					\
	(SIP_URI_UT(c) & \
	(SIP_URI_SLASH_BIT|SIP_URI_COLON_BIT|SIP_URI_QUEST_BIT))
#define	SIP_URI_ISABSDELIM(c)	\
	(SIP_URI_UT(c) & (SIP_URI_SLASH_BIT|SIP_URI_QUEST_BIT))
#define	SIP_URI_ISUNRESERVED(c)	\
	(SIP_URI_UT(c) & (SIP_URI_ALNUM_BITS|SIP_URI_MARK_BIT))
#define	SIP_URI_ISPARAM(c)						\
	(SIP_URI_UT(c) & (SIP_URI_PHCOMM_BIT|SIP_URI_AND_BIT|\
	SIP_URI_ALNUM_BITS|SIP_URI_MARK_BIT))
#define	SIP_URI_ISHEADER(c)						\
	(SIP_URI_UT(c) & (SIP_URI_PHCOMM_BIT|SIP_URI_QUEST_BIT|\
	SIP_URI_ALNUM_BITS|SIP_URI_MARK_BIT))
#define	SIP_URI_ISOTHER(c)		(SIP_URI_UT(c) & SIP_URI_OTHER_BIT)
#define	SIP_URI_ISRESERVED(c)					\
	(SIP_URI_UT(c) & (SIP_URI_SEMI_BIT|SIP_URI_SLASH_BIT|	\
	SIP_URI_QUEST_BIT| SIP_URI_COLON_BIT|SIP_URI_AT_BIT|	\
	SIP_URI_AND_BIT|SIP_URI_OTHER_BIT))
#define	SIP_URI_ISPCHAR(c)	\
	(SIP_URI_UT(c) & (SIP_URI_COLON_BIT|SIP_URI_AT_BIT|	\
	SIP_URI_AND_BIT|SIP_URI_OTHER_BIT))
#define	SIP_URI_ISREGNAME(c)					\
	(SIP_URI_UT(c) & 	\
	(SIP_URI_OTHER_BIT|SIP_URI_SEMI_BIT|SIP_URI_COLON_BIT|	\
	SIP_URI_AT_BIT|SIP_URI_AND_BIT))
#define	SIP_URI_ISPHONEDIGIT(c)	\
	(SIP_URI_UT(c) & (SIP_URI_DIGIT_BIT|SIP_URI_VISUALSEP_BIT))
#define	SIP_URI_ISDTMFDIGIT(c)	(SIP_URI_UT(c) & SIP_URI_DTMFURI_DIGIT_BIT)

/* static functions */
static int  sip_uri_url_casecmp(const char *, const char *, unsigned);
static void sip_uri_parse_params(_sip_uri_t *, char *, char *);
static void sip_uri_parse_headers(_sip_uri_t *, char *, char *);
static void sip_uri_parse_abs_opaque(_sip_uri_t *, char *, char *);
static void sip_uri_parse_abs_query(_sip_uri_t *, char *, char *);
static void sip_uri_parse_abs_path(_sip_uri_t *, char *, char *);
static void sip_uri_parse_abs_regname(_sip_uri_t *, char *, char *);
static int  sip_uri_parse_scheme(_sip_uri_t *, char *, char *);
static void sip_uri_parse_password(_sip_uri_t *, char *, char *);
static void sip_uri_parse_user(_sip_uri_t *, char *, char *);
static void sip_uri_parse_port(_sip_uri_t *, char *, char *);
static void sip_uri_parse_netpath(_sip_uri_t *, char **, char *, boolean_t);
static int  sip_uri_parse_ipv6(char *, char *);
static int  sip_uri_parse_ipv4(char *, char *);
static int  sip_uri_parse_hostname(char *, char *);
static int sip_uri_parse_tel(char *, char *);
static int sip_uri_parse_tel_areaspe(char *, char *);
static int sip_uri_parse_tel_servicepro(char *, char *);
static int sip_uri_parse_tel_futureext(char *, char *);
static int sip_uri_isTokenchar(char **, char *);
static int sip_uri_isEscapedPound(char **, char *);
static int sip_uri_hexVal(char *, char *);
static int SIP_URI_HEXVAL(int);

/*
 * get the hex value of a char
 */
static int
SIP_URI_HEXVAL(int c)
{
	if (c >= 0x30 && c <= 0x39)
		return (c - '0');
	if (c >= 0x41 && c <= 0x46)
		return (c - 'A' + 10);
	if (c >= 0x61 && c <= 0x66)
		return (c - 'a' + 10);
	return (c);
}

/*
 * basic ASCII case-insensitive comparison
 */
static int
sip_uri_url_casecmp(const char *str1, const char *str2, unsigned len)
{
	unsigned	j;

	for (j = 0; j < len && tolower(str1[j]) == tolower(str2[j]) &&
	    str1[j] != '\0'; ++j) {
		;
	}
	return (j == len ? 0 : tolower(str2[j]) - tolower(str1[j]));
}

/*
 * telephone-subscriber  = global-phone-number / local-phone-number
 * Please refer to RFC 2806
 */
static int
sip_uri_parse_tel(char *scan, char *uend)
{
	char	*mark = (char *)0;
	int	ret = 0;
	int	isGlobal = 0;
	int	quote = 0;

	if (scan == uend)
		return (0);
	if (*scan == '+') {
		++scan;
		isGlobal = 1;
	}
	mark = scan;
	if (isGlobal) {
		while (scan < uend && SIP_URI_ISPHONEDIGIT(*scan))
			++scan;
	} else {
		while (scan < uend &&
		    (SIP_URI_ISPHONEDIGIT(*scan) ||
		    SIP_URI_ISDTMFDIGIT(*scan) ||
		    sip_uri_isEscapedPound(&scan, uend) ||
		    *scan == 'p' || *scan == 'w')) {
			++scan;
		}
	}
	if (mark == scan || (scan < uend && *scan != ';'))
		return (0);

	/* parse isdn-subaddress */
	if (uend - scan > 6 && !sip_uri_url_casecmp(scan, ";isub=", 6)) {
		scan += 6;
		mark = scan;
		while (scan < uend && SIP_URI_ISPHONEDIGIT(*scan))
			++scan;
		if (mark == scan || (scan < uend && *scan != ';'))
			return (0);
	}

	/* parse post-dial */
	if (uend - scan > 7 && !sip_uri_url_casecmp(scan, ";postd=", 7)) {
		scan += 7;
		mark = scan;
		while (scan < uend &&
		    (SIP_URI_ISPHONEDIGIT(*scan) ||
		    SIP_URI_ISDTMFDIGIT(*scan) ||
		    sip_uri_isEscapedPound(&scan, uend) ||
		    *scan == 'p' || *scan == 'w')) {
			++scan;
		}
		if (mark == scan || (scan < uend && *scan != ';'))
			return (0);
	}

	if (!isGlobal) {
		/* parse area-specifier */
		if (uend - scan > 15 &&
		    !sip_uri_url_casecmp(scan, ";phone-context=", 15)) {
			scan += 15;
			mark = scan;
			while (scan < uend && *scan != ';')
				++scan;
			ret = sip_uri_parse_tel_areaspe(mark, scan);
		}
	} else {
		ret = 1;
	}

	/* parse area-specifier, service-provider, future-extension */
	while (scan < uend && ret) {
		if (uend - scan > 15 &&
			!sip_uri_url_casecmp(scan, ";phone-context=", 15)) {
			scan += 15;
			mark = scan;
			while (scan < uend && *scan != ';')
				++scan;
			ret = sip_uri_parse_tel_areaspe(mark, scan);
		} else if (uend - scan > 5 &&
		    !sip_uri_url_casecmp(scan, ";tsp=", 5)) {
			scan += 5;
			mark = scan;
			while (scan < uend && *scan != ';')
				++scan;
			ret = sip_uri_parse_tel_servicepro(mark, scan);
		} else {
			++scan;
			mark = scan;
			while (scan < uend && (*scan != ';' || quote)) {
				if (sip_uri_hexVal(scan, uend) == 0x22) {
					quote = !quote;
					scan += 3;
				} else {
					++scan;
				}
			}
			ret = sip_uri_parse_tel_futureext(mark, scan);
		}
	}
	return (ret && scan == uend);
}

/*
 * area-specifier        = ";" phone-context-tag "=" phone-context-ident
 * phone-context-tag     = "phone-context"
 * phone-context-ident   = network-prefix / private-prefix
 * network-prefix        = global-network-prefix / local-network-prefix
 * global-network-prefix = "+" 1*phonedigit
 * local-network-prefix  = 1*(phonedigit / dtmf-digit / pause-character)
 * private-prefix        = (%x21-22 / %x24-27 / %x2C / %x2F / %x3A /
 *                          %x3C-40 / %x45-4F / %x51-56 / %x58-60 /
 *                          %x65-6F / %x71-76 / %x78-7E)
 *                          *(%x21-3A / %x3C-7E)
 * phonedigit            = DIGIT / visual-separator
 * visual-separator      = "-" / "." / "(" / ")"
 * pause-character       = one-second-pause / wait-for-dial-tone
 * one-second-pause      = "p"
 * wait-for-dial-tone    = "w"
 * dtmf-digit            = "*" / "#" / "A" / "B" / "C" / "D"
 */
static int
sip_uri_parse_tel_areaspe(char *scan, char *uend)
{
	int	uri_hexValue;

	if (scan == uend)
		return (0);

	/* parse global-network-prefix */
	if (*scan == '+') {
		++scan;
		if (scan == uend)
			return (0);
		while (scan < uend && SIP_URI_ISPHONEDIGIT(*scan))
			++scan;
	/* parse local-network-prefix */
	} else if (SIP_URI_ISPHONEDIGIT(*scan) || SIP_URI_ISDTMFDIGIT(*scan) ||
	    sip_uri_isEscapedPound(&scan, uend) ||
	    *scan == 'p' || *scan == 'w') {
		++scan;
		while (scan < uend &&
		    (SIP_URI_ISPHONEDIGIT(*scan) ||
		    SIP_URI_ISDTMFDIGIT(*scan) ||
		    sip_uri_isEscapedPound(&scan, uend) ||
		    *scan == 'p' || *scan == 'w')) {
			++scan;
		}
	} else {
	/*
	 * parse private-prefix
	 *
	 * any characters allowed in RFC 2806 that are not allowed in
	 * the user part of the SIP URI MUST be escaped
	 *
	 * private-prefix	= (! $ & ', / = ? _
	 *			EFGHIJKLMNOQRSTUVXYZ efghijklmnoqrstuvxyz
	 *			{ } | ~ [ ] \ ^  ` " % : < > @)
	 *			*(%x21-3A / %x3C-7E)
	 *
	 * following characters are allowed in RFC 2806 and
	 * the user part of SIP URI
	 *  ! $ & ', / = ? _ EFGHIJKLMNOQRSTUVXYZ efghijklmnoqrstuvxyz
	 */
		if (*scan == '!' || *scan == '$' || *scan == '&' ||
		    *scan == '\'' || *scan == ',' || *scan == '/' ||
		    *scan == '=' || *scan == '?' || *scan == '_' ||
		    (*scan >= 'E' && *scan <= 'Z' &&
		    *scan != 'P' && *scan != 'W') ||
		    (*scan >= 'e' && *scan <= 'z' &&
		    *scan != 'p' && *scan != 'w')) {
			++scan;
		} else {
			uri_hexValue = sip_uri_hexVal(scan, uend);
			if (uri_hexValue == 0x21 || uri_hexValue == 0x22 ||
			    (uri_hexValue >= 0x24 && uri_hexValue <= 0x27) ||
			    uri_hexValue == 0x2c || uri_hexValue == 0x2f ||
			    uri_hexValue == 0x3a ||
			    (uri_hexValue >= 0x3c && uri_hexValue <= 0x40) ||
			    (uri_hexValue >= 0x45 && uri_hexValue <= 0x4f) ||
			    (uri_hexValue >= 0x51 && uri_hexValue <= 0x56) ||
			    (uri_hexValue >= 0x58 && uri_hexValue <= 0x60) ||
			    (uri_hexValue >= 0x65 && uri_hexValue <= 0x6f) ||
			    (uri_hexValue >= 0x71 && uri_hexValue <= 0x76) ||
			    (uri_hexValue >= 0x78 && uri_hexValue <= 0x7e)) {
				scan += 3;
			} else {
				return (0);
			}
		}
		/* parse *(%x21-3A / %x3C-7E) */
		while (scan < uend) {
			if (SIP_URI_ISUNRESERVED(*scan) ||
			    (SIP_URI_ISUSER(*scan) && *scan != ';')) {
				++scan;
			} else {
				uri_hexValue = sip_uri_hexVal(scan, uend);
				if (uri_hexValue >= 0x21 &&
				    uri_hexValue <= 0x7e &&
				    uri_hexValue != 0x3b) {
					scan += 3;
				} else {
					return (0);
				}