Hi I need help on my lexical analyzer homework using C language., So Basically w

Question

Hi I need help on my lexical analyzer homework using C language.,

So Basically we are given an input file below and we are to recognize each tokens seperated by the Whitespace.

inputfile.txt

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

MyShopPurchaseOrders DEFINITIONS AUTOMATIC TAGS ::= BEGIN

PurchaseOrder ::= SEQUENCE {
dateOfOrder DATE,
customer CustomerInfo,
items ListOfItems
}

CustomerInfo ::= SEQUENCE {
companyName VisibleString (SIZE (3..50)),
billingAddress Address,
contactPhone NumericString (SIZE (7..12))
}

Address::= SEQUENCE {
street VisibleString (SIZE (5 .. 50)) OPTIONAL,
city VisibleString (SIZE (2..30)),
state VisibleString (SIZE(2) FROM ("A".."Z")),
zipCode NumericString (SIZE(5 | 9))
}

ListOfItems ::= SEQUENCE (SIZE (1..100)) OF Item

Item ::= SEQUENCE {
itemCode INTEGER (1..99999),
color VisibleString ("Black" | "Blue" | "Brown"),
power INTEGER (110 | 220),
deliveryTime INTEGER (8..12 | 14..19),
quantity INTEGER (1..1000),
unitPrice INTEGER (1 .. 9999),
isTaxable BOOLEAN
}
END

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

Alphabet Set :

a-z
A-Z
0-9
"  
(  
)
,  
-
:
=
{
}
|

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

RESERVED WORDS:

{"AUTOMATIC", "BEGIN", "BOOLEAN", "DEFINITIONS", "END", "FROM",

"INTEGER", "NumericString", "OPTIONAL", "SEQUENCE", "SIZE", "TAGS", "VisibleString"};

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

Tokens

a. Type references

Name of lexical item – typereference

A "typereference" shall consist of an arbitrary number (one or more) of letters, digits, and hyphens. The initial character shall be an upper-case letter. A hyphen shall not be the last character. A hyphen shall not be immediately followed by another hyphen.

NOTE – The rules concerning hyphen are designed to a void ambiguity with (possibly following) comment.

example of typereference on the input file: MyShopPurchaseOrders , PurchaseOrder, CustomerInfo, etc..

b. Identifiers

Name of lexical item – identifier

An "identifier" shall consist of an arbitrary number (one or more) of letters, digits, and hyphens. The initial character shall be a lower-case letter. A hyphen shall not be the last character. A hyphen shall not be immediately followed by another hyphen.

example of identifier on the inputfile: dateOfOrder, customer, items, companyName, etc...

c. Numbers

Name of lexical item – number

A "number" shall consist of one or more digits. The first digit shall not be zero unless the "number" is a single digit.

d. Assignment lexical item

Name of lexical item – "::="

This lexical item shall consist of the sequence of characters: ::=

e. Range separator

Name of lexical item – ".."

This lexical item shall consist of the sequence of characters: " .. "

f. “{“ - LURLY

g. “}” – RCURLY

h. “,” – COMMA

i. “(“ – LPAREN

j. “)” – RPAREN

k. “|” – BAR

l. “ – QUOTE

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

Sample output of program:

typereference: MyShopPurchaseOrders

reserveword: DEFINITION

reserveword:AUTOMATIC

reserveword TAGS

assignment: ::=

reserveword: BEGIN

typereference: PurchaseOrder

and so on...

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

Here is my initial code:

#include <stdio.h>

#include <stdlib.h>

#include <string.h>

int main(int argc, char *argv[]){ //running it in command line LINUX

FILE *filePtr;

switch (argc) {

case 1: // No parameters, use stdin

// printf("NO argument provided ");

filePtr = stdin;

break;

case 2: // One parameter, use .txt file supplied

if ( (filePtr = fopen(strcat(argv[1], ".txt"), "r")) == NULL ) {

printf("Cannot open input file. ");

exit(1);

}

break;

default:

printf("Syntax: scanner [file] (.txt is implicit) ");

exit(0);

}

//check if empty

fseek(filePtr, 0, SEEK_END);

if (ftell(filePtr) == 0) {

printf("File is empty. ");

exit(1);

} else {

rewind(filePtr);

}

char *ReserveWord[13] = {"AUTOMATIC", "BEGIN", "BOOLEAN", "DEFINITIONS", "END", "FROM",

"INTEGER", "NumericString", "OPTIONAL",

"SEQUENCE", "SIZE", "TAGS", "VisibleString"};

char *assignment[] = {":=="};

char *range_separator[] = {".."};

char LCURLY = {'{'};

char RCURLY = {'}'};

char COMMA = {','};

char LPAREN = {'('};

char RPAREN = {')'};

char BAR = {'|'};

char QUOTE = {'"'};

int numline = 1;

char c;

while((c = fgetc(filePtr)) != EOF){

if ( c == ' '){

numline++;

}

if (c <= 65 && c >= 90 ){ //A-Z for typeref

}

}

fclose(filePtr);

}

Explanation / Answer

#include <stdio.h>

#include <stdlib.h>

#include <string.h>

int main(int argc, char *argv[]){ //running it in command line LINUX

FILE *filePtr;

int initial_index=0,i; // Index of storing data
char store[100]; //To store data retrived from file

switch (argc) {

case 1: // No parameters, use stdin

// printf("NO argument provided ");

filePtr = stdin;

break;

case 2: // One parameter, use .txt file supplied

if ( (filePtr = fopen(strcat(argv[1], ".txt"), "r")) == NULL ) {

printf("Cannot open input file. ");

exit(1);

}

break;

default:

printf("Syntax: scanner [file] (.txt is implicit) ");

exit(0);

}

//check if empty

fseek(filePtr, 0, SEEK_END);

if (ftell(filePtr) == 0) {

printf("File is empty. ");

exit(1);

} else {

rewind(filePtr);

}

char *ReserveWord[13] = {"AUTOMATIC", "BEGIN", "BOOLEAN", "DEFINITIONS", "END", "FROM",

"INTEGER", "NumericString", "OPTIONAL",

"SEQUENCE", "SIZE", "TAGS", "VisibleString"};

char *assignment[] = {":=="};

char *range_separator[] = {".."};

char LCURLY = {'{'};

char RCURLY = {'}'};

char COMMA = {','};

char LPAREN = {'('};

char RPAREN = {')'};

char BAR = {'|'};

char QUOTE = {'"'};

int numline = 1;

char c;

while((c = fgetc(filePtr)) != EOF){

if ( c == ' '){

numline++;

}

if (c <= 65 && c >= 90 ){ //A-Z for typeref
  
}

if(c == ' ') //To check for the spaces
{
for(i=0;i<initial_index;i++)
printf("%c",store[i]);
printf(" ");
initial_index=0; //Reset to initial index
}
else //Storing file data
store[initial_index++]=c;
}

fclose(filePtr);

}

// Please go through the code first

In the code, I have added one array to store the data and one more extra variable. Also added one more if condition to check whether the retrieved character is space or not.

Related Questions

Navigate

• Browse (All)
• Browse H
• Subjects

---

---

Integrity-first tutoring: explanations and feedback only — we do not complete graded work. Learn more.