wslexer.c

The Kannel Open Source WAP and SMS gateway works as both an SMS gateway, for implementing keyword b

/* ==================================================================== 
 * The Kannel Software License, Version 1.0 
 * 
 * Copyright (c) 2001-2004 Kannel Group  
 * Copyright (c) 1998-2001 WapIT Ltd.   
 * All rights reserved. 
 * 
 * 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. The end-user documentation included with the redistribution, 
 *    if any, must include the following acknowledgment: 
 *       "This product includes software developed by the 
 *        Kannel Group (http://www.kannel.org/)." 
 *    Alternately, this acknowledgment may appear in the software itself, 
 *    if and wherever such third-party acknowledgments normally appear. 
 * 
 * 4. The names "Kannel" and "Kannel Group" must not be used to 
 *    endorse or promote products derived from this software without 
 *    prior written permission. For written permission, please  
 *    contact [e-mail]. 
 * 
 * 5. Products derived from this software may not be called "Kannel", 
 *    nor may "Kannel" appear in their name, without prior written 
 *    permission of the Kannel Group. 
 * 
 * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESSED 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 KANNEL GROUP OR ITS 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. 
 * ==================================================================== 
 * 
 * This software consists of voluntary contributions made by many 
 * individuals on behalf of the Kannel Group.  For more information on  
 * the Kannel Group, please see <http://www.kannel.org/>. 
 * 
 * Portions of this software are based upon software originally written at  
 * WapIT Ltd., Helsinki, Finland for the Kannel project.  
 */ 

/*
 *
 * wslexer.c
 *
 * Author: Markku Rossi <[e-mail]>
 *
 * Copyright (c) 1999-2000 WAPIT OY LTD.
 *		 All rights reserved.
 *
 * Lexical analyzer.
 *
 */

#include "wsint.h"
#include "wsstree.h"
#include "wsgram.h"

/********************* Types and definitions ****************************/

/* A predicate to check whether the character `ch' is a decimal
   digit. */
#define WS_IS_DECIMAL_DIGIT(ch) ('0' <= (ch) && (ch) <= '9')

/* Convert the decimal digit `ch' to an integer number. */
#define WS_DECIMAL_TO_INT(ch) ((ch) - '0')

/* A predicate to check whether the character `ch' is a non-zero
   decimal digit. */
#define WS_IS_NON_ZERO_DIGIT(ch) ('1' <= (ch) && (ch) <= '9')

/* A predicate to check whether the character `ch' is an octal digit. */
#define WS_IS_OCTAL_DIGIT(ch) ('0' <= (ch) && (ch) <= '7')

/* Convert the octal digit `ch' to an integer number. */
#define WS_OCTAL_TO_INT(ch) ((ch) - '0')

/* A predicate to check whether the character `ch' is a hex digit. */
#define WS_IS_HEX_DIGIT(ch) (('0' <= (ch) && (ch) <= '9')	\
                             || ('a' <= (ch) && (ch) <= 'f')	\
                             || ('A' <= (ch) && (ch) <= 'F'))

/* Convert the hex digit `ch' to an integer number. */
#define WS_HEX_TO_INT(ch)		\
    ('0' <= (ch) && (ch) <= '9'		\
     ? ((ch) - '0')			\
     : ('a' <= (ch) && (ch) <= 'f'	\
       ? ((ch) - 'a' + 10)		\
       : (ch) - 'A' + 10))

/* A predicate to check whether the character `ch' is an identifier
   starter letter. */
#define WS_IS_IDENTIFIER_LETTER(ch)	\
    (('a' <= (ch) && (ch) <= 'z')		\
     || ('A' <= (ch) && (ch) <= 'Z')	\
     || (ch) == '_')

/********************* Prototypes for static functions ******************/

/* Check whether the identifier `id', `len' is a keyword.  If the
   identifier is a keyword, the function returns WS_TRUE and sets the
   keywords token ID to `token_return'.  Otherwise the function
   returns WS_FALSE. */
static WsBool lookup_keyword(char *id, size_t len, int *token_return);

/* Convert literal integer number, stored to the buffer `buffer', into
   a 32 bit integer number.  The function will report possible integer
   overflows to the compiler `compiler'.  The function modifies the
   contents of the buffer `buffer' but it does not free it. */
static WsUInt32 buffer_to_int(WsCompilerPtr compiler, WsBuffer *buffer);

/* Read a floating point number from the decimal point to the buffer
   `buffer'.  The buffer `buffer' might already contain some leading
   digits of the number and it always contains the decimal point.  If
   the operation is successful, the function returns WS_TRUE and it
   returns the resulting floating point number in `result'.  Otherwise
   the function returns WS_FALSE.  The buffer `buffer' must be
   initialized before this function is called and it must be
   uninitialized by the caller. */
static WsBool read_float_from_point(WsCompiler *compiler, WsBuffer *buffer,
                                    WsFloat *result);

/* Read a floating point number from the exponent part to the buffer
   `buffer'.  The buffer might already contain some leading digits and
   fields of the floating poit number.  Otherwise, the function works
   like read_float_from_point(). */
static WsBool read_float_from_exp(WsCompiler *compiler, WsBuffer *buffer,
                                  WsFloat *result);

/********************* Static variables *********************************/

/* A helper macro which expands to a strings and its length excluding
   the trailing '\0' character. */
#define N(n) n, sizeof(n) - 1

/* They keywords of the WMLScript language.  This array must be sorted
   by the keyword names. */
static struct
{
    char *name;
    size_t name_len;
    int token;
} keywords[] = {
        {N("access"), tACCESS},
        {N("agent"), tAGENT},
        {N("break"), tBREAK},
        {N("case"), tCASE},
        {N("catch"), tCATCH},
        {N("class"), tCLASS},
        {N("const"), tCONST},
        {N("continue"), tCONTINUE},
        {N("debugger"), tDEBUGGER},
        {N("default"), tDEFAULT},
        {N("delete"), tDELETE},
        {N("div"), tIDIV},
        {N("do"), tDO},
        {N("domain"), tDOMAIN},
        {N("else"), tELSE},
        {N("enum"), tENUM},
        {N("equiv"), tEQUIV},
        {N("export"), tEXPORT},
        {N("extends"), tEXTENDS},
        {N("extern"), tEXTERN},
        {N("false"), tFALSE},
        {N("finally"), tFINALLY},
        {N("for"), tFOR},
        {N("function"), tFUNCTION},
        {N("header"), tHEADER},
        {N("http"), tHTTP},
        {N("if"), tIF},
        {N("import"), tIMPORT},
        {N("in"), tIN},
        {N("invalid"), tINVALID},
        {N("isvalid"), tISVALID},
        {N("lib"), tLIB},
        {N("meta"), tMETA},
        {N("name"), tNAME},
        {N("new"), tNEW},
        {N("null"), tNULL},
        {N("path"), tPATH},
        {N("private"), tPRIVATE},
        {N("public"), tPUBLIC},
        {N("return"), tRETURN},
        {N("sizeof"), tSIZEOF},
        {N("struct"), tSTRUCT},
        {N("super"), tSUPER},
        {N("switch"), tSWITCH},
        {N("this"), tTHIS},
        {N("throw"), tTHROW},
        {N("true"), tTRUE},
        {N("try"), tTRY},
        {N("typeof"), tTYPEOF},
        {N("url"), tURL},
        {N("use"), tUSE},
        {N("user"), tUSER},
        {N("var"), tVAR},
        {N("void"), tVOID},
        {N("while"), tWHILE},
        {N("with"), tWITH},
};

static int num_keywords = sizeof(keywords) / sizeof(keywords[0]);

/********************* Global functions *********************************/

int ws_yy_lex(YYSTYPE *yylval, YYLTYPE *yylloc, void *context)
{
    WsCompiler *compiler = (WsCompiler *) context;
    WsUInt32 ch, ch2;
    WsBuffer buffer;
    unsigned char *p;
    WsBool success;

    /* Just check that we get the correct amount of arguments. */
    gw_assert(compiler->magic == COMPILER_MAGIC);

    while (ws_stream_getc(compiler->input, &ch)) {
        /* Save the token's line number. */
        yylloc->first_line = compiler->linenum;

        switch (ch) {
        case '\t': 		/* Whitespace characters. */
        case '\v':
        case '\f':
        case ' ':
            continue;

        case '\n': 		/* Line terminators. */
        case '\r':
            if (ch == '\r' && ws_stream_getc(compiler->input, &ch2)) {
                if (ch2 != '\n')
                    ws_stream_ungetc(compiler->input, ch2);
            }
            compiler->linenum++;
            continue;

        case '!': 		/* !, != */
            if (ws_stream_getc(compiler->input, &ch2)) {
                if (ch2 == '=')
                    return tNE;

                ws_stream_ungetc(compiler->input, ch2);
            }
            return '!';

        case '%': 		/* %, %= */
            if (ws_stream_getc(compiler->input, &ch2)) {
                if (ch2 == '=')
                    return tREMA;

                ws_stream_ungetc(compiler->input, ch2);
            }
            return '%';

        case '&': 		/* &, &&, &= */
            if (ws_stream_getc(compiler->input, &ch2)) {
                if (ch2 == '&')
                    return tAND;
                if (ch2 == '=')
                    return tANDA;

                ws_stream_ungetc(compiler->input, ch2);
            }
            return '&';

        case '*': 		/* *, *= */
            if (ws_stream_getc(compiler->input, &ch2)) {
                if (ch2 == '=')
                    return tMULA;

                ws_stream_ungetc(compiler->input, ch2);
            }
            return '*';

        case '+': 		/* +, ++, += */
            if (ws_stream_getc(compiler->input, &ch2)) {
                if (ch2 == '+')
                    return tPLUSPLUS;
                if (ch2 == '=')
                    return tADDA;

                ws_stream_ungetc(compiler->input, ch2);
            }
            return '+';

        case '-': 		/* -, --, -= */
            if (ws_stream_getc(compiler->input, &ch2)) {
                if (ch2 == '-')
                    return tMINUSMINUS;
                if (ch2 == '=')
                    return tSUBA;

                ws_stream_ungetc(compiler->input, ch2);
            }
            return '-';

        case '.':
            if (ws_stream_getc(compiler->input, &ch2)) {
                if (WS_IS_DECIMAL_DIGIT(ch2)) {
                    /* DecimalFloatLiteral. */
                    ws_buffer_init(&buffer);

                    if (!ws_buffer_append_space(&buffer, &p, 2)) {
                        ws_error_memory(compiler);
                        ws_buffer_uninit(&buffer);
                        return EOF;
                    }

                    p[0] = '.';
                    p[1] = (unsigned char) ch2;

                    success = read_float_from_point(compiler, &buffer,
                                                    &yylval->vfloat);
                    ws_buffer_uninit(&buffer);

                    if (!success)
                        return EOF;

                    return tFLOAT;
                }

                ws_stream_ungetc(compiler->input, ch2);
            }
            return '.';

        case '/': 		/* /, /=, block or a single line comment */
            if (ws_stream_getc(compiler->input, &ch2)) {
                if (ch2 == '*') {
                    /* Block comment. */
                    while (1) {
                        if (!ws_stream_getc(compiler->input, &ch)) {
                            ws_src_error(compiler, 0, "EOF in comment");
                            return EOF;