simple lexxer problem

closed account (zwA4jE8b)
Hey guys,
This program works just fine as long as the source code uses spaces to separate the state types.

Input file...

10 rem
12 input x,y2
13 if x < y2 then goto 15
14 z =x - y2
11 goto 16
15 z = x + y2
16 print x, y2, z
17 for i = 1 to 12 step 2
18 print i
19 next i
20 input st$
21 print "$", st%
22 input x
23 if x >= y2 then x = y ^ 2
24 print # x
25 end


Output from lexxer

integer     10          
reserved    rem         
integer     12          
variable    input      
variable    x           
variable    y2          
integer     13          
reserved    if          
variable    x           
delimeter   <           
variable    y2          
reserved    then        
reserved    goto        
integer     15          
integer     14          
variable    z           
delimeter   =           
delimeter   -           
variable    y2          
integer     11          
reserved    goto        
integer     16          
integer     15          
variable    z           
delimeter   =           
variable    x           
delimeter   +           
variable    y2          
integer     16          
reserved    print       
variable    x           
variable                
variable    y2          
variable    z           
integer     17          
reserved    for         
variable    i           
delimeter   =           
integer     1           
reserved    to          
integer     12          
reserved    step        
integer     2           
integer     18          
reserved    print       
variable    i           
integer     19          
reserved    next        
variable    i           
integer     20          
reserved    input       
variable    st          
integer     21          
reserved    print       
delimeter   "           Improper usage: $
delimeter   "           
variable    st          
integer     22          
reserved    input       
variable    x           
integer     23          
reserved    if          
variable    x           
delimeter   >           
variable    y2          
reserved    then        
variable    x           
delimeter   =           
variable    y           
delimeter   ^           
integer     2           
integer     24          
reserved    print       
Illegal character: #
variable    x           
integer     25          
reserved    end


as you can see it is mostly tokenized properly. the problems occur when two different statetypes follow each other without a space.


The functions tokenizer() and takeaction() is where the tokens are processedsource code is processed.

Here is the code.
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
 
#include <fstream>
#include <string>
#include <vector>
#include <iomanip>
using namespace std;

enum statetype {newtkn, resvd, var, intr, real, del1, laststate};
enum chartype {letter, digit, period, del2, blank, pod, eoln, illegal, lastchar};

string enumtostring(statetype);
statetype strtoenum(string);
chartype charreturn(char);
void codetostring(string&);
void compresvd(vector<string>&, string, statetype&);
void takeaction(int , int&, string& , char&, statetype& ,vector<string>&,  vector<vector<statetype>>&, chartype,  ofstream&); //Write takeaction
void tokenizer(vector<string>&, vector<vector<statetype>>&, vector<vector<int>>&, ofstream&);

int main()
{
	ofstream _outf("output.dat");
	vector<string> _reserve;
	vector<vector<int>> _action(laststate, vector<int>(lastchar));
	vector<vector<statetype>> _FSM(laststate, vector<statetype>(lastchar));
	
		readreserve(_reserve);
		writereserve(_reserve, _outf);
		readstate(_FSM);
		writestate(_FSM, _outf);
		readaction(_action);
		writeaction(_action, _outf);
		writeexp(_outf);
		
		tokenizer(_reserve, _FSM, _action, _outf);

	_outf.close();
	return 0;
}

//Missing code - not valid for problem

string enumtostring(statetype _s)
{
	string _temp;
	if(_s == newtkn)
		return "newtoken";
	else if(_s == resvd)
		return "reserved";
	else if(_s == var)
		return "variable";
	else if(_s == intr)
		return "integer";
	else if(_s == real)
		return "real";
	else if(_s == del1)
		return "delimeter";
	else
		return "laststate";
}

statetype strtoenum(string _s)
{
	if (_s == "newtkn")
		return newtkn;
	else if (_s == "resvd")
		return resvd;
	else if (_s == "var")
		return var;
	else if (_s == "intr")
		return intr;
	else if (_s == "real")
		return real;
	else if (_s == "del1")
		return del1;
	else
		return laststate;
}

chartype charreturn(char _ch)
{
	if ((_ch >= 'A' && _ch <= 'Z') || (_ch >= 'a' && _ch <= 'z'))
		return letter;
	else if (_ch >= '0' && _ch <= '9')
		return digit;
	else if (_ch == '.')
		return period;
	else if(_ch == '+'|| _ch == '-' || _ch == '/' || _ch == '*' ||
			_ch == '^' || _ch == '=' || _ch == '<' || _ch == '>' ||
			_ch == ',' || _ch == '\"')
		return del2;
	else if (_ch == ' ')
		return blank;
	else if (_ch == '%' || _ch == '$')
		return pod;
	else if (_ch == '\n')
		return eoln;
	else
		return illegal;
}

void codetostring(string& _temp)
{
	ifstream _inf("prog1.bas");
	char _ch;
	while (!_inf.eof())
	{
		_inf.get(_ch);
		_temp += _ch;
	}
	_inf.close();
}

void compresvd(vector<string>& _resvd, string _token, statetype& _st)
{
	vector<string>::iterator iter;
	for (iter = _resvd.begin(); iter != _resvd.end(); ++iter)
	{
		if (_token == *iter)
		{
			_st = resvd;
			break;
		}
		else
			_st = var;
	}
}

void takeaction(int _act, int& i, string& _token, char _ch,  statetype& _st, vector<string>& _resvd, string& _code,
				vector<vector<statetype>>& _state, chartype _ct, ofstream& _outf)
{
	switch(_act)
	{
	case 1:
		_token += _ch;
		_st = _state[_st][_ct];
		break;
	case 2:
		compresvd(_resvd, _token, _st);
		_outf << setw(12) << enumtostring(_st) << setw(12) << _token << endl;
		_token = "";
		_st = newtkn;
		break;
	case 3:
		_outf << setw(12) << enumtostring(_st) << setw(12) << _token << endl;
		_token = "";
		_st = newtkn;
		break;
	case 4:
		_outf << setw(12) << enumtostring(_st) << setw(12) << _token <<
				 setw(16) << "Improper usage: " << _ch << endl;
		_token = "";
		_st = newtkn;
		break;
	case 5:
		_outf << setw(16) << "Improper usage: " << _ch << endl;
		break;
	case 6:
		break;
	case 7:
		_outf << setw(19) << "Illegal character: " << _ch << endl;
		break;
	case 8:
		compresvd(_resvd, _token, _st);
		_outf << setw(12) << enumtostring(_st) << setw(12) << _token << endl;
		_token = "";
		break;
	case 9:
		_outf << setw(12) << enumtostring(_st) << setw(12) << _token << endl;
		_token = "";
		_st = newtkn;
		break;
	case 10:
		_st = var;
		_outf << setw(12) << enumtostring(_st) << setw(12) << _token << endl;
		_token = "";
		_st = newtkn;
		break;
	case 11:
		compresvd(_resvd, _token, _st);
		_outf << setw(12) << enumtostring(_st) << setw(12) << 
				 _token << setw(19) << "Illegal character" << _ch << endl;
		break;
	case 12:
		_outf << setw(12) << enumtostring(_st) << setw(12) << _token << endl;
		_token = "";
		_st = newtkn;
		break;
	case 13:
		_outf << setw(12) << enumtostring(_st) << setw(12) << 
				 _token << setw(19) << "Illegal character" << _ch << endl;
		_token = "";
		_st = newtkn;
		break;
	default:
		;;
	}
}

void tokenizer(vector<string>& _resvd, vector<vector<statetype>>& _state, vector<vector<int>>& _action, ofstream& _outf)
{
	string _code = "";
	char _ch;
	chartype _ct;
	string _token = "";
	statetype _st = newtkn;
	int _act;

	codetostring(_code);
	_outf << left;

	for (int i = 0; i < _code.length(); i++)
	{
		_ch = _code[i];
		_ct = charreturn(_ch);
		_act = _action[_st][_ct];
		takeaction(_act, i, _token, _ch, _st, _resvd, _code, _state, _ct, _outf);
	}
}


This is the table that explains what the action codes are supposed to do.

1) Load character and continue
2) Compare with table of reserved words, print token, reinitialize token
3) Print token, reinitialize token
4) Print token, write "Improper usage", print character, reinitialize token
5) Write "Improper usage", print character
6) Continue
7) Write "Illegal character", print character
8) Compare with table of reserved words, print token, reinitialize token, load char
9) Print token, reinitialize token, load character
10) Load character, change state to variable, print token, reinitialize token
11) Compare with table of reserved words, print token, write "Illegal character", print char
12) Load character, print token, reinitialize token
13) Print token, write "Illegal character", print character, reinitialize token


I believe my problem is with the load character parts one multiple actions.

So by looking at the input and output you can see when spaces are used the output is correct.

Thank you,
Mike
Last edited on
closed account (zwA4jE8b)
action 8 and 9 is where I am having the issue.
Last edited on
closed account (zwA4jE8b)
I fixed it by adding i-- to the actions.
1
2
3
4
5
6
7
8
9
10
11
12
13
 
case 8:
		compresvd(_resvd, _token, _st);
		_outf << setw(12) << enumtostring(_st) << setw(12) << _token << endl;
		_token = "";
		_st = newtkn;
		i--;
		break;
	case 9:
		_outf << setw(12) << enumtostring(_st) << setw(12) << _token << endl;
		_token = "";
		_st = newtkn;
		i--;
		break;


is that legal? I know a lexxer/scanner is supposed to go one char at a time, so is going backwards wrong?

So that has shown me that the character is being read, but then skipped, perhaps i need to restructure my reading loop.

so instead of 'i--;' i load the char into _token and reprocess it.
Last edited on
closed account (zwA4jE8b)
fixed... for anyone who is interested here is the code.

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
 
#include <fstream>
#include <string>
#include <vector>
#include <iomanip>
using namespace std;

enum statetype {newtkn, resvd, var, intr, real, del1, laststate};
enum chartype {letter, digit, period, del2, blank, pod, eoln, illegal, lastchar};

void readreserve(vector<string>&);
void writereserve(vector<string>&, ofstream&);
void readstate(vector<vector<statetype>>&);
void writestate(vector<vector<statetype>>&, ofstream&);
void readaction(vector<vector<int>>&);
void writeaction(vector<vector<int>>&, ofstream&);
void writeexp(ofstream&);
string enumtostring(statetype);
statetype strtoenum(string);
chartype charreturn(char);
void codetostring(string&);
void compresvd(vector<string>&, string, statetype&);
void takeaction(int , int&, string& , char&, statetype& ,vector<string>&,
				vector<vector<statetype>>&, chartype, bool&,  ofstream&);
void tokenizer(vector<string>&, vector<vector<statetype>>&, vector<vector<int>>&, ofstream&);

int main()
{
	ofstream _outf("output.dat");
	vector<string> _reserve;
	vector<vector<int>> _action(laststate, vector<int>(lastchar));
	vector<vector<statetype>> _FSM(laststate, vector<statetype>(lastchar));
	
		readreserve(_reserve);
		writereserve(_reserve, _outf);
		readstate(_FSM);
		writestate(_FSM, _outf);
		readaction(_action);
		writeaction(_action, _outf);
		writeexp(_outf);
		
		tokenizer(_reserve, _FSM, _action, _outf);

	_outf.close();
	return 0;
}

void readreserve(vector<string>& _r)
{
	ifstream _inf("reserve.dat");
	string _temp;
	while (!_inf.eof())
	{
		_inf >> _temp;
		_r.push_back(_temp);
	}
	_inf.close();
}

void writereserve(vector<string>& _r, ofstream& _outf)
{
	vector<string>::iterator iter;

	_outf << "Reserved words:" <<
			"\n---------------" << endl;

	for (iter = _r.begin(); iter != _r.end(); ++iter)
	{
		_outf << *iter <<  "  ";
	}
	_outf << endl << endl;
}

void readstate(vector<vector<statetype>>& _s)
{
	ifstream _inf("statetable.dat");
	string _temp;
	for (int i = newtkn; i < laststate; i++)
		for (int j = letter; j < lastchar; j++)
		{
			_inf >> _temp;
			_s[i][j] = strtoenum(_temp);
		}
	_inf.close();
}

void writestate(vector<vector<statetype>>& _s, ofstream& _outf)
{
	_outf << right << setw(58) << "State Table\n" <<
			setw(58) <<"-----------\n";
	_outf << left << setw(12) << " " << setw(12) << "Letter" << setw(12) << "Digit" <<
			setw(12) << "Period" << setw(12) << "Delimiter" << setw(12) << "Blank" <<
			setw(12) << "% or $" << setw(12) << "EOLN" << setw(12) << "Illegal" << endl;
	_outf << left << setfill('-') << setw(108) << "-" << setfill(' ') << endl;
	for (int i = newtkn; i < laststate; i++)
	{
		_outf << setw(10) << enumtostring((statetype)i) << "| ";
		for (int j = letter; j < lastchar; j++)
			_outf << setw(12) << enumtostring(_s[i][j]);
		_outf << endl;
	}
	_outf << endl;
}

void readaction(vector<vector<int>>& _a)
{
	ifstream _inf("actiontable.dat");
	for (int i = newtkn; i < laststate; i++)
		for (int j = letter; j < lastchar; j++)
			_inf >> _a[i][j];
	_inf.close();
}

void writeaction(vector<vector<int>>& _a, ofstream& _outf)
{	
	_outf << right << setw(59) << "Action Table\n" <<
			setw(59) << "------------\n";
	_outf << left << setw(12) << " " << setw(12) << "Letter" << setw(12) << "Digit" <<
			setw(12) << "Period" << setw(12) << "Delimiter" << setw(12) << "Blank" <<
			setw(12) << "% or $" << setw(12) << "EOLN" << setw(12) << "Illegal" << endl;
	_outf << left << setfill('-') << setw(108) << "-" << setfill(' ') << endl;
	for (int i = newtkn; i < laststate; i++)
	{
		_outf << setw(10) << enumtostring((statetype)i) << "| ";
		for (int j = letter; j < lastchar; j++)
			_outf << setw(12) << _a[i][j];
		_outf << endl;
	}
	_outf << endl;
}

void writeexp(ofstream& _outf)
{
	ifstream _inf("explanationofaction.dat");
	string _temp;
	_outf << "Explanation of Action Table entries: " <<
			"\n------------------------------------" << endl;
	while (!_inf.eof())
	{
		getline(_inf, _temp);
		_outf << _temp << endl;
	}
	_outf << endl;
	_inf.close();
}

string enumtostring(statetype _s)
{
	string _temp;
	if(_s == newtkn)
		return "newtoken";
	else if(_s == resvd)
		return "reserved";
	else if(_s == var)
		return "variable";
	else if(_s == intr)
		return "integer";
	else if(_s == real)
		return "real";
	else if(_s == del1)
		return "delimeter";
	else
		return "laststate";
}

statetype strtoenum(string _s)
{
	if (_s == "newtkn")
		return newtkn;
	else if (_s == "resvd")
		return resvd;
	else if (_s == "var")
		return var;
	else if (_s == "intr")
		return intr;
	else if (_s == "real")
		return real;
	else if (_s == "del1")
		return del1;
	else
		return laststate;
}

chartype charreturn(char _ch)
{
	if ((_ch >= 'A' && _ch <= 'Z') || (_ch >= 'a' && _ch <= 'z'))
		return letter;
	else if (_ch >= '0' && _ch <= '9')
		return digit;
	else if (_ch == '.')
		return period;
	else if(_ch == '+'|| _ch == '-' || _ch == '/' || _ch == '*' ||
			_ch == '^' || _ch == '=' || _ch == '<' || _ch == '>' ||
			_ch == ',' || _ch == '\"')
		return del2;
	else if (_ch == ' ')
		return blank;
	else if (_ch == '%' || _ch == '$')
		return pod;
	else if (_ch == '\n')
		return eoln;
	else
		return illegal;
}

void codetostring(string& _temp)
{
	ifstream _inf("prog1.bas");
	char _ch;
	while (!_inf.eof())
	{
		_inf.get(_ch);
		_temp += _ch;
	}
	_inf.close();
}

void compresvd(vector<string>& _resvd, string _token, statetype& _st)
{
	vector<string>::iterator iter;
	for (iter = _resvd.begin(); iter != _resvd.end(); ++iter)
	{
		if (_token == *iter)
		{
			_st = resvd;
			break;
		}
		else
			_st = var;
	}
}

void takeaction(int _act, int& i, string& _token, char _ch,  statetype& _st, vector<string>& _resvd, string& _code,
				vector<vector<statetype>>& _state, chartype _ct, ofstream& _outf)
{
	switch(_act)
	{
	case 1:
		_token += _ch;
		break;
	case 2:
		compresvd(_resvd, _token, _st);
		_outf << setw(12) << enumtostring(_st) << setw(12) << _token << endl;
		_token = "";
		break;
	case 3:
		_outf << setw(12) << enumtostring(_st) << setw(12) << _token << endl;
		_token = "";
		break;
	case 4:
		_outf << setw(12) << enumtostring(_st) << setw(9) << _token <<
				 setw(16) << "Improper usage: " << _ch << endl;
		_token = "";
		break;
	case 5:
		_outf << setw(16) << "Improper usage: " << _ch << endl;
		break;
	case 6:
		break;
	case 7:
		_outf << setw(19) << "Illegal character: " << _ch << endl;
		break;
	case 8:
		compresvd(_resvd, _token, _st);
		_outf << setw(12) << enumtostring(_st) << setw(12) << _token << endl;
		_token = _ch;
		break;
	case 9:
		_outf << setw(12) << enumtostring(_st) << setw(12) << _token << endl;
		_token = _ch;
		break;
	case 10:
		_token += _ch;
		_st = var;
		_outf << setw(12) << enumtostring(_st) << setw(12) << _token << endl;
		_token = "";
		break;
	case 11:
		compresvd(_resvd, _token, _st);
		_outf << setw(12) << enumtostring(_st) << setw(12) << 
				 _token << setw(19) << "Illegal character" << _ch << endl;
		break;
	case 12:
		_token += _ch;
		_outf << setw(12) << enumtostring(_st) << setw(12) << _token << endl;
		_token = "";
		break;
	case 13:
		_outf << setw(12) << enumtostring(_st) << setw(12) << 
				 _token << setw(19) << "Illegal character" << _ch << endl;
		_token = "";
		break;
	default:
		;;
	}
}

void tokenizer(vector<string>& _resvd, vector<vector<statetype>>& _state, vector<vector<int>>& _action, ofstream& _outf)
{
	string _code = "";
	char _ch;
	chartype _ct;
	string _token = "";
	statetype _st = newtkn;
	int _act;

	codetostring(_code);
	_outf << left;

	for (int i = 0; i < _code.length(); i++)
	{
		_ch = _code[i];
		_ct = charreturn(_ch);
		_act = _action[_st][_ct];
		takeaction(_act, i, _token, _ch, _st, _resvd, _code, _state, _ct, _outf);
		_st = _state[_st][_ct];
	}
}
abellia (29)
You are posting too much code for someone to help you. Try to determine the particular issue and the relevant code.
Topic archived. No new replies allowed.