Write a C++ program that simulatesa lexical/syntax analyzer (parser) system for the following simple if ..else..statement.

The BNF is:

-> if () | if () else

-> OR |

-> AND |

-> TRUE | FALSE | NOT | ()

-> id = ; | id = ;

-> + | - |

-> * | / | % |

-> id | int_constant | ()

The EBNF is:

-> if () [else ]

-> {OR }

-> {AND }

-> TRUE | FALSE | NOT | ()

-> id = ; | id = ;

-> {( + | -) }

-> {( *|/|% ) }

-> id | int_constant | ()

NOTE:

Operator/keyword: +,-, *, /, %, (, ), ;, TRUE, FALSE, OR, AND, NOT, if, else

id: (a+b+...+z+A+B+...Z)(a+b+...+z+A+B+...Z+0+1+2+...+9)*

int_constant: (0+1+2+...+9)(0+1+2+...+9)*

/********************************************************************/

Sample syntax #1:

if (TRUE AND FALSE)

A=sum / (total+ 47);

B=( 4+ A)%3;

C=B - 15;

Sample syntax #2:

if (FALSE OR (NOT TRUE))

A= sum *( total- 47);

B=(4+ A )%3;

C=B-15;

else

A=(sum + total) * 4;

B=B+1;

C=B/2;

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

Lexical Analyzer - C++

/* Filename: LexicalAnalyzer.cpp CSC 340 - Programming Languages Dr.

A lexical analyzer system for simple arithmetic expressions.

Operator/keyword: +, -, * /, (, ) Identifer: (a+b+...+z+A+B+...Z)(a+b+...+z+A+B+...Z+0+1+2+...+9)* Integer: (0+1+2+...+9)(0+1+2+...+9)*

*/

#include #include #include using namespace std;

/* Global declarations */ /* Variables */

int charClass; char lexeme[100]; char nextChar; int lexLen; int token; int nextToken; ifstream in_fp("syntax.txt");

/* Function declarations */ void getChar(); void addChar(); void getNonBlank(); int lex(); // to get the nextToken

/* Character classes */ #define LETTER 0 #define DIGIT 1 #define UNKNOWN 99

/* Token codes */ #define INT_LIT 10 #define IDENT 11 #define ADD_OP 21 #define SUB_OP 22 #define MULT_OP 23 #define DIV_OP 24 #define LEFT_PAREN 25 #define RIGHT_PAREN 26

/******************************************************/ /* main driver */ void main() { /* Open the input data file and process its contents */

if (in_fp.fail()) { cout << "File could not be opened "; cin.get(); exit(1); } else { getChar(); do { lex(); // Getting the nextToken } while (nextToken != EOF); } in_fp.close(); }

/*****************************************************/ /* lookup - a function to lookup operators and parentheses and return the token */ int lookup(char ch) { switch (ch) { case '(': addChar(); nextToken = LEFT_PAREN; break; case ')': addChar(); nextToken = RIGHT_PAREN; break; case '+': addChar(); nextToken = ADD_OP; break; case '-': addChar(); nextToken = SUB_OP; break; case '*': addChar(); nextToken = MULT_OP; break; case '/': addChar(); nextToken = DIV_OP; break; default: addChar(); nextToken = EOF; break; } return nextToken; } /*****************************************************/ /* addChar - a function to add nextChar to lexeme */ void addChar() { if (lexLen <= 98) { lexeme[lexLen++] = nextChar; lexeme[lexLen] = 0; } else cout << " Error - lexeme is too long "; } /*****************************************************/ /* getChar - a function to get the next character of input and determine its character class */ void getChar() { in_fp.get(nextChar); if (in_fp.eof()) // if no more character in the file nextChar = EOF;

if (nextChar != EOF) { if (isalpha(nextChar)) charClass = LETTER; else if (isdigit(nextChar)) charClass = DIGIT; else charClass = UNKNOWN; } else charClass = EOF; } /*****************************************************/ /* getNonBlank - a function to call getChar until it returns a non-whitespace character */ void getNonBlank() { while (isspace(nextChar)) getChar(); } /***************************************************** / /* lex - a simple lexical analyzer for arithmetic expressions */ int lex() { lexLen = 0; getNonBlank(); switch (charClass) { /* Parse identifiers */ case LETTER: addChar(); getChar(); while (charClass == LETTER || charClass == DIGIT) { addChar(); getChar(); } nextToken = IDENT; break; /* Parse integer literals */ case DIGIT: addChar(); getChar(); while (charClass == DIGIT) { addChar(); getChar(); } nextToken = INT_LIT; break; /* Parentheses and operators */ case UNKNOWN: lookup(nextChar); getChar(); break; /* EOF */ case EOF: nextToken = EOF; lexeme[0] = 'E'; lexeme[1] = 'O'; lexeme[2] = 'F'; lexeme[3] = 0; break; } /* End of switch */ cout << "Next token is: " << nextToken << " Next lexeme is " << lexeme << " "; return nextToken; } /* End of function lex */