path: root/src/parser/scanner.lxx

/*
    Copyright (C) 2005-2009  Michel de Boer <michel@twinklephone.com>

    This program is free software; you can redistribute it and/or modify
    it under the terms of the GNU General Public License as published by
    the Free Software Foundation; either version 2 of the License, or
    (at your option) any later version.

    This program is distributed in the hope that it will be useful,
    but WITHOUT ANY WARRANTY; without even the implied warranty of
    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
    GNU General Public License for more details.

    You should have received a copy of the GNU General Public License
    along with this program.  If not, see <https://www.gnu.org/licenses/>.
*/

%{
#include <cstdio>
#include <cstring>
#include <math.h>
#include <string>
#include "parse_ctrl.h"
#include "parser.hxx"
#include "util.h"
#include "audits/memman.h"

using namespace std;
%}

%option noyywrap
%option stack

DIGIT		[0-9]
HEXDIG		[0-9a-fA-F]
ALPHA		[a-zA-Z]
CAPITALS	[A-Z]
ALNUM		[a-zA-Z0-9]
TOKEN_SYM	[[:alnum:]\-\.!%\*_\+\`\'~]
WORD_SYM	[[:alnum:]\-\.!%\*_\+\`\'~\(\)<>:\\\"\/\[\]\?\{\}]

%x C_URI
%x C_URI_SPECIAL
%x C_QSTRING
%x C_LANG
%x C_WORD
%x C_NUM
%x C_DATE
%x C_LINE
%x C_COMMENT
%x C_NEW
%x C_AUTH_SCHEME
%x C_RPAREN
%x C_IPV6ADDR
%x C_PARAMVAL

%%
	switch (t_parser::context) {
	case t_parser::X_URI:		BEGIN(C_URI); break;
	case t_parser::X_URI_SPECIAL:	BEGIN(C_URI_SPECIAL); break;
	case t_parser::X_LANG:		BEGIN(C_LANG); break;
	case t_parser::X_WORD:		BEGIN(C_WORD); break;
	case t_parser::X_NUM:		BEGIN(C_NUM); break;
	case t_parser::X_DATE:		BEGIN(C_DATE); break;
	case t_parser::X_LINE:		BEGIN(C_LINE); break;
	case t_parser::X_COMMENT:	BEGIN(C_COMMENT); break;
	case t_parser::X_NEW:		BEGIN(C_NEW); break;
	case t_parser::X_AUTH_SCHEME:	BEGIN(C_AUTH_SCHEME); break;
	case t_parser::X_IPV6ADDR:	BEGIN(C_IPV6ADDR); break;
	case t_parser::X_PARAMVAL:	BEGIN(C_PARAMVAL); break;
	default:			BEGIN(INITIAL);
	}

	/* Headers */
^Accept			{ return T_HDR_ACCEPT; }
^Accept-Encoding	{ return T_HDR_ACCEPT_ENCODING; }
^Accept-Language	{ return T_HDR_ACCEPT_LANGUAGE; }
^Alert-Info		{ return T_HDR_ALERT_INFO; }
^Allow			{ return T_HDR_ALLOW; }
^(Allow-Events)|u	{ return T_HDR_ALLOW_EVENTS; }
^Authentication-Info	{ return T_HDR_AUTHENTICATION_INFO; }
^Authorization		{ return T_HDR_AUTHORIZATION; }
^(Call-ID)|i		{ return T_HDR_CALL_ID; }
^Call-Info		{ return T_HDR_CALL_INFO; }
^(Contact)|m		{ return T_HDR_CONTACT; }
^Content-Disposition	{ return T_HDR_CONTENT_DISP; }
^(Content-Encoding)|e	{ return T_HDR_CONTENT_ENCODING; }
^Content-Language	{ return T_HDR_CONTENT_LANGUAGE; }
^(Content-Length)|l	{ return T_HDR_CONTENT_LENGTH; }
^(Content-Type)|c	{ return T_HDR_CONTENT_TYPE; }
^CSeq			{ return T_HDR_CSEQ; }
^Date			{ return T_HDR_DATE; }
^Error-Info		{ return T_HDR_ERROR_INFO; }
^(Event)|o		{ return T_HDR_EVENT; }
^Expires		{ return T_HDR_EXPIRES; }
^(From|f)		{ return T_HDR_FROM; }
^In-Reply-To		{ return T_HDR_IN_REPLY_TO; }
^Max-Forwards		{ return T_HDR_MAX_FORWARDS; }
^Min-Expires		{ return T_HDR_MIN_EXPIRES; }
^MIME-Version		{ return T_HDR_MIME_VERSION; }
^Organization		{ return T_HDR_ORGANIZATION; }
^P-Asserted-Identity	{ return T_HDR_P_ASSERTED_IDENTITY; }
^P-Preferred-Identity	{ return T_HDR_P_PREFERRED_IDENTITY; }
^Priority		{ return T_HDR_PRIORITY; }
^Privacy		{ return T_HDR_PRIVACY; }
^Proxy-Authenticate	{ return T_HDR_PROXY_AUTHENTICATE; }
^Proxy-Authorization	{ return T_HDR_PROXY_AUTHORIZATION; }
^Proxy-Require		{ return T_HDR_PROXY_REQUIRE; }
^RAck			{ return T_HDR_RACK; }
^Record-Route		{ return T_HDR_RECORD_ROUTE; }
^Service-Route		{ return T_HDR_SERVICE_ROUTE; }
^Refer-Sub		{ return T_HDR_REFER_SUB; }
^(Refer-To)|r		{ return T_HDR_REFER_TO; }
^(Referred-By)|b	{ return T_HDR_REFERRED_BY; }
^Replaces		{ return T_HDR_REPLACES; }
^Reply-To		{ return T_HDR_REPLY_TO; }
^Require		{ return T_HDR_REQUIRE; }
^(Request-Disposition)|d {return T_HDR_REQUEST_DISPOSITION; }
^Retry-After		{ return T_HDR_RETRY_AFTER; }
^Route			{ return T_HDR_ROUTE; }
^RSeq			{ return T_HDR_RSEQ; }
^Server			{ return T_HDR_SERVER; }
^SIP-ETag		{ return T_HDR_SIP_ETAG; }
^SIP-If-Match		{ return T_HDR_SIP_IF_MATCH; }
^(Subject)|s		{ return T_HDR_SUBJECT; }
^Subscription-State	{ return T_HDR_SUBSCRIPTION_STATE; }
^(Supported)|k		{ return T_HDR_SUPPORTED; }
^Timestamp		{ return T_HDR_TIMESTAMP; }
^(To)|t			{ return T_HDR_TO; }
^unsupported		{ return T_HDR_UNSUPPORTED; }
^User-Agent		{ return T_HDR_USER_AGENT; }
^(Via)|v		{ return T_HDR_VIA; }
^Warning		{ return T_HDR_WARNING; }
^WWW-Authenticate	{ return T_HDR_WWW_AUTHENTICATE; }
^{TOKEN_SYM}+		{ yylval.yyt_str = new string(yytext);
			  MEMMAN_NEW(yylval.yyt_str);
			  return T_HDR_UNKNOWN; }

	/* Token as define in RFC 3261 */
{TOKEN_SYM}+ 	{ yylval.yyt_str = new string(yytext);
		  MEMMAN_NEW(yylval.yyt_str);
		  return T_TOKEN; }

	/* Switch to quoted string context */
\"		{ yy_push_state(C_QSTRING); }

	/* End of line */
\r\n		{ return T_CRLF; }
\n		{ return T_CRLF; }

[[:blank:]]	/* Skip white space */

	/* Single character token */
.		{ return yytext[0]; }

	/* URI. 
	   This context scans a URI including parameters.
	   The syntax of a URI will be checked outside the scanner 
	 */
<C_URI>\"		{ yy_push_state(C_QSTRING); }
<C_URI>{TOKEN_SYM}({TOKEN_SYM}|[[:blank:]])*/< {
			yylval.yyt_str = new string(yytext);
			MEMMAN_NEW(yylval.yyt_str);
			return T_DISPLAY; }
<C_URI>[^[:blank:]<>\r\n]+/[[:blank:]]*> {
			yylval.yyt_str = new string(yytext);
			MEMMAN_NEW(yylval.yyt_str);
			return T_URI; }
<C_URI>\*		{ return T_URI_WILDCARD; }
<C_URI>[^[:blank:]<>\"\r\n]+ {
			yylval.yyt_str = new string(yytext);
			MEMMAN_NEW(yylval.yyt_str);
			return T_URI; }
<C_URI>[[:blank:]]	 /* Skip white space */
<C_URI>.		 { return yytext[0]; }
<C_URI>\n		 { return T_ERROR; }

	/* URI special case.
	   In several headers (eg. From, To, Contact, Reply-To) the URI
	   can be enclosed by < and >
	   If it is enclosed then parameters belong to the URI, if it
	   is not enclosed then parameters belong to the header.
	   Parameters are seperated by a semi-colon. 
	   For the URI special case, parameters belong to the header.
	   If the parser receives a < from the scanner, then the parser
	   will switch to the normal URI case.
	   The syntax of a URI will be checked outside the scanner 
	 */
<C_URI_SPECIAL>\"	{ yy_push_state(C_QSTRING); }
<C_URI_SPECIAL>{TOKEN_SYM}({TOKEN_SYM}|[[:blank:]])*/< {
			yylval.yyt_str = new string(yytext);
			MEMMAN_NEW(yylval.yyt_str);
			return T_DISPLAY; }
<C_URI_SPECIAL>\*		{ return T_URI_WILDCARD; }
<C_URI_SPECIAL>[^[:blank:]<>;\"\r\n]+ {
			yylval.yyt_str = new string(yytext);
			MEMMAN_NEW(yylval.yyt_str);
			return T_URI; }
<C_URI_SPECIAL>[[:blank:]]	 /* Skip white space */
<C_URI_SPECIAL>.		 { return yytext[0]; }
<C_URI_SPECIAL>\n		 { return T_ERROR; }

	/* Quoted string (starting after open quote, closing quote
	   will be consumed but not returned. */
<C_QSTRING>\\			{ yymore(); }
<C_QSTRING>[^\"\\\r\n]*\\\"	{ yymore(); }
<C_QSTRING>[^\"\\\r\n]*\"	{ yy_pop_state();
			  	  yytext[strlen(yytext)-1] = '\0';
			  	  yylval.yyt_str = new string(unescape(string(yytext)));
				  MEMMAN_NEW(yylval.yyt_str);
			  	  return T_QSTRING; }
<C_QSTRING>[^\"\\\n]*\n		{ yy_pop_state(); return T_ERROR; }
<C_QSTRING>.			{ yy_pop_state(); return T_ERROR; }

	/* Comment (starting after LPAREN till RPAREN) */
<C_COMMENT>\\			{ yymore(); }
<C_COMMENT>[^\(\)\\\r\n]*\\\)	{ yymore(); }
<C_COMMENT>[^\(\)\\\r\n]*\\\(	{ yymore(); }
<C_COMMENT>[^\(\)\\\r\n]*\(	{ t_parser::inc_comment_level(); yymore(); }
<C_COMMENT>[^\(\)\\\r\n]*/\)	{ if (t_parser::dec_comment_level()) {
					BEGIN(C_RPAREN);
					yymore();
				  } else {
				  	yylval.yyt_str = new string(yytext);
					MEMMAN_NEW(yylval.yyt_str);
			  	  	return T_COMMENT;
				  }
				}
<C_COMMENT>[^\(\)\\\n]*\n	{ return T_ERROR; }
<C_COMMENT>.			{ return T_ERROR; }
<C_RPAREN>\)			{ BEGIN(C_COMMENT); yymore(); }

	/* Language tag */
<C_LANG>{ALPHA}{1,8}(\-{ALPHA}{1,8})*	{ yylval.yyt_str = new string(yytext);
					  MEMMAN_NEW(yylval.yyt_str);
					  return T_LANG; }
<C_LANG>[[:blank:]]			/* Skip white space */
<C_LANG>.				{ return yytext[0]; }
<C_LANG>\r\n				{ return T_CRLF; }
<C_LANG>\n				{ return T_CRLF; }

	/* Word */
<C_WORD>{WORD_SYM}+	{ yylval.yyt_str = new string(yytext);
			  MEMMAN_NEW(yylval.yyt_str);
			  return T_WORD; }
<C_WORD>[[:blank:]]	/* Skip white space */
<C_WORD>.		{ return yytext[0]; }
<C_WORD>\r\n				{ return T_CRLF; }
<C_WORD>\n				{ return T_CRLF; }

	/* Number */
<C_NUM>{DIGIT}+		{ yylval.yyt_ulong = strtoul(yytext, NULL, 10); return T_NUM; }
<C_NUM>[[:blank:]]	/* Skip white space */
<C_NUM>.		{ return yytext[0]; }
<C_NUM>\r\n		{ return T_CRLF; }
<C_NUM>\n		{ return T_CRLF; }

	/* Date */
<C_DATE>Mon		{ yylval.yyt_int = 1; return T_WKDAY; }
<C_DATE>Tue		{ yylval.yyt_int = 2; return T_WKDAY; }
<C_DATE>Wed		{ yylval.yyt_int = 3; return T_WKDAY; }
<C_DATE>Thu		{ yylval.yyt_int = 4; return T_WKDAY; }
<C_DATE>Fri		{ yylval.yyt_int = 5; return T_WKDAY; }
<C_DATE>Sat		{ yylval.yyt_int = 6; return T_WKDAY; }
<C_DATE>Sun		{ yylval.yyt_int = 0; return T_WKDAY; }
<C_DATE>Jan		{ yylval.yyt_int = 0; return T_MONTH; }
<C_DATE>Feb		{ yylval.yyt_int = 1; return T_MONTH; }
<C_DATE>Mar		{ yylval.yyt_int = 2; return T_MONTH; }
<C_DATE>Apr		{ yylval.yyt_int = 3; return T_MONTH; }
<C_DATE>May		{ yylval.yyt_int = 4; return T_MONTH; }
<C_DATE>Jun		{ yylval.yyt_int = 5; return T_MONTH; }
<C_DATE>Jul		{ yylval.yyt_int = 6; return T_MONTH; }
<C_DATE>Aug		{ yylval.yyt_int = 7; return T_MONTH; }
<C_DATE>Sep		{ yylval.yyt_int = 8; return T_MONTH; }
<C_DATE>Oct		{ yylval.yyt_int = 9; return T_MONTH; }
<C_DATE>Nov		{ yylval.yyt_int = 10; return T_MONTH; }
<C_DATE>Dec		{ yylval.yyt_int = 11; return T_MONTH; }
<C_DATE>GMT		{ return T_GMT; }
<C_DATE>{DIGIT}+	{ yylval.yyt_ulong = strtoul(yytext, NULL, 10); return T_NUM; }
<C_DATE>[[:blank:]]	/* Skip white space */
<C_DATE>.		{ return yytext[0]; }
<C_DATE>\r\n		{ return T_CRLF; }
<C_DATE>\n		{ return T_CRLF; }

	/* Get all text till end of line */
<C_LINE>[^\r\n]+	{ yylval.yyt_str = new string(yytext);
			  MEMMAN_NEW(yylval.yyt_str);
			  return T_LINE; }
<C_LINE>\r\n		{ return T_CRLF; }
<C_LINE>\n		{ return T_CRLF; }
<C_LINE>\r		{ return T_CRLF; }

	/* Start of a new message */
<C_NEW>SIP		{ return T_SIP; }
<C_NEW>{CAPITALS}+	{ yylval.yyt_str = new string(yytext);
			  MEMMAN_NEW(yylval.yyt_str);
			  return T_METHOD; }
<C_NEW>[[:blank:]]	/* Skip white space */
<C_NEW>.		{ return T_ERROR; }
<C_NEW>\r\n		{ return T_CRLF; }
<C_NEW>\n		{ return T_CRLF; }

	/* Authorization scheme */
<C_AUTH_SCHEME>[Dd][Ii][Gg][Ee][Ss][Tt]	{ return T_AUTH_DIGEST; }
<C_AUTH_SCHEME>{TOKEN_SYM}+ 	{ yylval.yyt_str = new string(yytext);
			 	  MEMMAN_NEW(yylval.yyt_str);
				  return T_AUTH_OTHER; }
<C_AUTH_SCHEME>[[:blank:]]	/* Skip white space */
<C_AUTH_SCHEME>.		{ return T_ERROR; }
<C_AUTH_SCHEME>\r\n		{ return T_CRLF; }
<C_AUTH_SCHEME>\n		{ return T_CRLF; }

	/* IPv6 address
	 * NOTE: the validity of the format is not checked here.
	 */
<C_IPV6ADDR>({HEXDIG}|[:\.])+	{ yylval.yyt_str = new string(yytext);
				  MEMMAN_NEW(yylval.yyt_str);
				  return T_IPV6ADDR; }
<C_IPV6ADDR>[[:blank:]]	/* Skip white space */
<C_IPV6ADDR>.		{ return T_ERROR; }
<C_IPV6ADDR>\r\n	{ return T_CRLF; }
<C_IPV6ADDR>\n		{ return T_CRLF; }

	/* Parameter values may contain an IPv6 address or reference. */
<C_PARAMVAL>({TOKEN_SYM}|[:\[\]])+ { yylval.yyt_str = new string(yytext);
				     MEMMAN_NEW(yylval.yyt_str);
				     return T_PARAMVAL; }
<C_PARAMVAL>\"		{ yy_push_state(C_QSTRING); }
<C_PARAMVAL>[[:blank:]]	/* Skip white space */
<C_PARAMVAL>.		{ return T_ERROR; }
<C_PARAMVAL>\r\n	{ return T_CRLF; }
<C_PARAMVAL>\n		{ return T_CRLF; }