Pascal subset lexical analyzer

Enter comments ^ o ^

Test with Pascal code snippets
Begin
Ab2a: = 9;
If x> = 0 then x: = x + 1;
While a = 0 do
B: = a * x/33455;
End
#

---------------------------------------------------------------------
Test Results
Syn | value
________ | ________
1 | begin
10 | ab2a
18 |: =
11 | 9
26 |;
2 | if
10 | x
24 |> =
11 | 0
3 | then
10 | x
18 |: =
10 | x
14 | +
11 | 1
26 |;
4 | while
10 |
25 | =
11 | 0
5 | do
10 | B
18 |: =
10 |
16 | *
10 | x
17 |/
11 | 33455
26 |;
6 | End
0 | #
Press any key to continue

The C-code parser of analyzer ------------------------------------------------------------------------------------------

# Include <stdio. h>
# Include <stdlib. h>
# Include <string. h>
# Include <ctype. h>
# Define max_wd_len 255.
# Define max_int 32767
# Define max_src_len 1000
# Define max_wd_cnt 100
# Define kwd_cnt 6
/*************************************** *********/

Union value_type {
Int D;
Char C;
Char s [MAX_WD_LEN];
};

Typedef struct {
Int syn;
Union value_type value;
} Word_type;

/*************************************** *********/
Char * keywords [20] = {"begin", "if", "then", "while", "do", "end "};
Char source [MAX_SRC_LEN];
Word_type word_stack [MAX_WD_CNT];
Int line = 1, wtop = 0, ip = 0;

/*************************************** *********/
Void p_word_stack (){
Int I; word_type w;
Printf ("syn/t | value/n ");
Printf ("________ | ________/n ");
For (I = 0; I <wtop; I ++ ){
W = word_stack [I];
If (w. syn> = 1 & w. syn <= 10) | w. syn = 18 | w. syn = 21 | w. syn = 22
| W. syn = 24)
Printf ("% d/t | % s/n", w. syn, w. value. s );
Else if (w. syn = 11)
Printf ("% d/t | % d/n", w. syn, w. value. d );
Else
Printf ("% d/t | % c/n", w. syn, w. value. c );
}
Return;
}
Void tell_err (){
Printf ("error in line % d/n", line );
Exit (1 );
Return;
}
Void scan (){
Word_type w;
Char c;
Int j = 0;
If (isdigit (c = source [ip]) {
W. syn = 11;/* dd **/
W. value. d = c-'0 ';
While (isdigit (c = source [++ ip])
W. value. d = w. value. d * 10 + c-'0 ';
If (! Isalpha (c ))
Word_stack [wtop ++] = w;
Else
Tell_err ();
Return;
}
If (isalpha (C = source [IP]) {
W. SYN = 10;/* (LL | D )*/
W. value. s [0] = C;
While (isalpha (C = source [++ IP]) | isdigit (c ))
W. value. s [++ J] = C;
W. value. s [J + 1] = '/0 ';
For (j = 0; j <kwd_cnt; j ++ ){
If (strcmp (keywords [j], w. value. s) = 0)
W. syn = j + 1;
}
Word_stack [wtop ++] = w;
Return;
}
Switch (c = source [ip]) {
Case '+ ':
W. syn = 14;/* '+ '*/
W. value. c = '+ ';
Word_stack [wtop ++] = w;
Ip ++;
Break;
Case '-':
W. syn = 15 ;/*'-'*/
W. value. c = '-';
Word_stack [wtop ++] = w;
Ip ++;
Break;
Case '*':
W. syn = 16 ;/*'*'*/
W. value. c = '*';
Word_stack [wtop ++] = w;
Ip ++;
Break;
Case '/':
W. syn = 17;
W. value. c = '/';
Word_stack [wtop ++] = w;
Ip ++;
Break;
Case ':':
W. SYN = 19;
W. value. c = ':';
If (C = source [++ IP])! = '){
Word_stack [wtop ++] = W;

}
Else if (C = '){
Strcpy (W. value. S, ": = ");
W. SYN = 18;
Word_stack [wtop ++] = W;
Ip ++;
}
Break;
Case '<':
W. syn = 20;
W. value. c = '<';
If (C = source [++ IP])! = '>' & C! = '){
Word_stack [wtop ++] = W;
}
Else if (C = '> '){
W. SYN = 21;
Strcpy (w. value. s, "<> ");
Word_stack [wtop ++] = w;
Ip ++;
}
Else if (c = '){
W. SYN = 22;
Strcpy (W. value. S, "<= ");
Word_stack [wtop ++] = W;
IP ++;
}
Break;
Case '> ':
W. syn = 23;
W. value. c = '> ';
If (c = source [++ ip])! = '){
Word_stack [wtop ++] = w;
}
Else if (C = '){
W. SYN = 24;
Strcpy (W. value. S, "> = ");
Word_stack [wtop ++] = W;
Ip ++;
}
Break;
Case '= ':
W. syn = 25;
W. value. c = ';
Word_stack [wtop ++] = w;
Ip ++;
Break;
Case ';':
W. syn = 26;
W. value. c = ';';
Word_stack [wtop ++] = W;
IP ++;
Break;
Case '(':
W. SYN = 27;
W. value. c = '(';
Word_stack [wtop ++] = W;
IP ++;
Break;
Case ')':
W. SYN = 28;
W. value. c = ')';
Word_stack [wtop ++] = w;
Ip ++;
Break;
Case '':
While (source [++ ip] = '');
Break;
Case '/N ':
Line ++;
While (source [++ ip] = '/N') line ++;
Break;

Case '/t ':
While (source [++ ip] = '/t ');
Break;
Case '/R ':
While (source [++ IP] = '/R ');
Break;
Default:
Tell_err ();
}
Return;
}
Int main (){
File * FP;
Int I = 0;
Word_type W;
Fp = fopen ("input.txt", "R ");
While (! Feof (FP ))
Source [I ++] = GETC (FP );
Fclose (FP );
While (source [IP]! = '#')
Scan (IP );
W. SYN = 0;
W. value. c = '#';
Word_stack [wtop ++] = W;
P_word_stack ();
}