Skip to content

Instantly share code, notes, and snippets.

@fajarlabs

fajarlabs/contoh_lexical.c

Created April 8, 2016 01:59
Show Gist options
  • Save fajarlabs/c8271098daa44f397b84abd443eb934f to your computer and use it in GitHub Desktop.
Save fajarlabs/c8271098daa44f397b84abd443eb934f to your computer and use it in GitHub Desktop.
Download ZIP
Raw
contoh_lexical.c
#include <stdlib.h>
#include <stdio.h>
#include <string.h>
#include <conio.h>
typedef struct t1tag
{
char nm[20];
} t1;
t1 Typs[] = {"keyword", "operator", "identifier", "number", "string", "illegal character",
"assignment", "paranthesis", "end of series", "relational operator",
"array start", "array end", "seperator", "Unary operator",
"compiler directive", "converter", "range"};
// Ini adalah beberapa kata-kata dicadangkan di Pascal.
t1 Rsrv[] = {"BEGIN","END","IF","THEN","ELSE","DO","FOR","TO","WHILE","REPEAT",
"UNTIL","PROCEDURE","FUNCTION","INTEGER","REAL","BYTE","CHAR",
"TEXT", "ARRAY","VAR","RECORD","SET","TYPE","AND","CASE","CONST",
"DIV", "DOWNTO","EXTERNAL","FILE","FORWARD","GOTO","IN","INLINE",
"INTERRUPT", "LABEL","MOD","NIL","NOT","OF","OR","PACKED","PROGRAM",
"WITH", "BOOLEAN","INPUT","OUTPUT", "WRITE", "WRITELN" };
long s = 49;
// Ini adalah operator
char oprtr[] = { '.', ',', ';', '=', ':', '[', ']', '(', ')', '-', '+', '/', '*','>', '<', '$', '#', '@'};
long t = 18;
typedef struct ttyptg
{
long no;
char ctkn[50];
int typ;
long lline;
} ttyp;
int isReserved(char tmp[])
{
long i=0;
char *str;
str = _strupr( _strdup( tmp ) );
while ( (i < s) && ( strcmp(str, Rsrv[i].nm) != 0) )
{
i++;
}
if ( strcmp(str, Rsrv[i].nm) != 0) // tidak sama atau bukan keyword
return 1;
return 0;
}
// RUN PROGRAM
void main(void)
{
long i, j, ind, zz, N, NN, ln;
char ch, nxt, instr[1024], tmp[100], FName[256];
ttyp Token[1024];
FILE *f;
printf("Enter a Pascal File Name: n");
scanf("%s", FName);
f = fopen(FName,"r");
ln = 0;
NN = 0;
while (!feof(f))
{
N = 0;
ch = 0;
while ( ('n' != (ch = getc(f))) && (!feof(f)) ) // end of line check
{
instr[N] = ch;
N++;
}
instr[N] = 0;
N++;
// TOKEN construction starts here
ind = 0;
while (ind < (N-1)) //
{
ch = instr[ind];
while (ch == 32) // space check
{
ind++;
ch = instr[ind];
}
if ( ind < N ) // if whole line has spaces, wil not be gone in.
{
// first 'operator' control will be done.
j = 0;
while( (j < t) && (ch != oprtr[j]) )
j++;
if ( ch == oprtr[j] ) // so ch is an operant.
{
zz = 0;
tmp[0] = ch;
if ( ind < N )
nxt = instr[ind + 1];
if ((nxt == '>') || (nxt == '=')) // can be one of "<>, <=, >=, :=" .
{
zz++;
tmp[1] = nxt;
ind +=2;
if ( nxt == '>' )
Token[NN].typ = 9; // relational operator
}
else if ( (ch == '.') && (nxt == '.'))
{
zz++;
tmp[1] = nxt;
ind +=2;
Token[NN].typ = 16; // range
}
else
ind++;
switch (ch)
{
case ':': if (nxt == '=')
Token[NN].typ = 6;
else
Token[NN].typ = 1;
break;
case '+':
case '-':
case '*':
case '/': Token[NN].typ = 1; break; // operator
case '.': if ( nxt != '.')
Token[NN].typ = 1; break; // operator
case ';': Token[NN].typ = 8; break; // end of series
case ',': Token[NN].typ = 12; break; // seperator
case '=':
case '>':
case '<': Token[NN].typ = 9; break; // relational oparator
case '[': Token[NN].typ = 10; break; // array start
case ']': Token[NN].typ = 11; break; // array end
case '(':
case ')': Token[NN].typ = 7; break; // paranthesis
case '$': Token[NN].typ = 14; break; // compiler directive
case '#': Token[NN].typ = 15; break; // ASCII converter
case '@': Token[NN].typ = 13; break; // unary operator
}
zz++;
tmp[zz] = 0;
Token[NN].no = NN;
strcpy(Token[NN].ctkn, tmp);
Token[NN].lline = ln;
NN++;
}
else if (ch == 39) // 39 = " ' " : String start
{
zz = 0;
ind++;
nxt = instr[ind];
tmp[0] = nxt;
while ( nxt != 39) // end of string
{
zz++;
ind++;
tmp[zz] = nxt = instr[ind];
}
tmp[zz] = 0;
Token[NN].no = NN;
strcpy(Token[NN].ctkn, tmp);
Token[NN].typ = 4;
Token[NN].lline = ln;
NN++;
ind++;
}
else if ( ((ch >= 65) && (ch <= 90)) || ((ch >= 97) &&
(ch <= 122)) || (ch == 95) )
// if ch is A..Z or a..z or '_' it is identifier or reserved word
{
zz = 0;
tmp[0] = ch;
nxt = instr[ind + 1];
zz++;
while ( ((nxt >= 65) && (nxt <= 90)) || ((nxt >= 97) &&
(nxt <= 122)) || (nxt == 95) || ((nxt >= 48) && (nxt <= 57)) )
// A..Z arasy, a..z arasy, '_', 0..9 arasy
{
ind++;
ch = instr[ind];
tmp[zz] = ch;
zz++;
nxt = instr[ind + 1];
}
tmp[zz] = 0;
if ( isReserved(tmp) == 0)
Token[NN].typ = 0; // keyword = reserved
else
Token[NN].typ = 2; // identifier
Token[NN].no = NN;
strcpy(Token[NN].ctkn, tmp);
Token[NN].lline = ln;
NN++;
ind++;
}
else if ( (ch >= 48) && (ch <= 57) ) // 0..9 : 'number'
{
zz = 0;
tmp[0] = ch;
nxt = instr[ind + 1];
zz++;
while ( ((nxt >= 48) && (nxt <= 57)) ) // take all 0..9 numbers.
{
ind++;
ch = instr[ind];
tmp[zz] = ch;
zz++;
nxt = instr[ind + 1];
}
tmp[zz] = 0;
Token[NN].typ = 3; // constant
Token[NN].no = NN;
strcpy(Token[NN].ctkn, tmp);
Token[NN].lline = ln;
NN++;
ind++;
}
else // illegal charater
{
Token[NN].no = NN;
Token[NN].ctkn[0] = ch;
Token[NN].ctkn[1] = 0;
Token[NN].typ = 5;
Token[NN].lline = ln;
NN++;
ind++;
} // if
} // if
} // while
ln++; // increase line number by one
} // while
fclose(f);
f = fopen("Token.txt", "w");
fprintf(f, "n NO LINE TOKEN TIPn");
fprintf(f, "__________________________________________________________________________n");
for(i=0;i<NN;i++)
{
fprintf(f, " %4ld %4ld %30s %20sn",
Token[i].no, Token[i].lline, Token[i].ctkn, Typs[Token[i].typ].nm);
}
fclose(f);
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment