File: Lexer.cpp

package info (click to toggle)
frobby 0.9.6-1
  • links: PTS, VCS
  • area: main
  • in suites: forky, sid
  • size: 11,616 kB
  • sloc: cpp: 30,134; sh: 1,184; makefile: 306; ansic: 102; lisp: 10
file content (195 lines) | stat: -rw-r--r-- 3,509 bytes parent folder | download | duplicates (4)
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
class Lexer {
  enum TokenType {
    INTEGER = 0,
    END_OF_FILE = 1,
    IDENTIFIER = 2,
    CHARACTER = 3
  } _tokenType;

public:
  Lexer(istream& in):
    _in(in) {
    nextToken();
  }

  bool match(char c) {
    if ((_tokenType == IDENTIFIER &&
	 _identifier.size() == 1 &&
	 _identifier[0] == c) ||

	(_tokenType == CHARACTER &&
	 _character == c)) {
      nextToken();
      return true;
    } else
      return false;
  }

  bool match(const char* str) {
    if (_tokenType == IDENTIFIER &&
	_identifier == str) {
      nextToken();
      return true;
    } else
      return false;
  }

  void expect(char expected) {
    if (!match(expected)) {
      cerr << "ERROR: expected '" << expected << "' but got ";
      printToken(cerr);
      cerr << '.' << endl;
      exit(0);
    }
  }

  void expectIdentifier(const char* str) {
    if (!match(str)) {
      cerr << "ERROR: expected \"" << str << "\" but got ";
      printToken(cerr);
      cerr << '.' << endl;
      exit(0);
    }
  }

  void expectEOF() {
    ensureType(END_OF_FILE);
  }

  void readInteger(mpz_class& integer) {
    ensureType(INTEGER);
    integer = _integer;

    nextToken();
  }

  void readInteger(unsigned int& i) {
    ensureType(INTEGER);

    if (!_integer.fits_uint_p()) {
      cerr << "ERROR: expected 32 bit unsigned integer but got " << _integer << "." << endl;
      exit(0);
    }
    i = _integer.get_ui();

    nextToken();
  }

  void readIdentifier(string& identifier) {
    ensureType(IDENTIFIER);
    identifier = _identifier;

    nextToken();
  }


private:
  int getChar() {
    return _in.get();
  }

  int peek() {
    return _in.peek();
  }

  void ensureType(TokenType type) {
    if (_tokenType != type) {
      cerr << "Expected ";
      printTokenType(cerr, type);
      cerr << " but got ";
      printToken(cerr);
      cerr << '.' << endl;
      exit(0);
    }
  }

  void eatWhite() {
    while (isspace(peek()))
      getChar();
  }

  void nextToken() {
    eatWhite();

    int c = peek();
    if (c == EOF)
      _tokenType = END_OF_FILE;
    else if (isdigit(c)) {
      _tokenType = INTEGER;
      _in >> _integer;
    } else if (c == '-' || c == '+') {
      getChar();
      eatWhite();
      if (isdigit(peek())) {
	_tokenType = INTEGER;
	_in >> _integer;
	if (c == '-')
	  _integer *= -1; // TODO: look up more efficient way to swap sign
      } else {
	_tokenType = CHARACTER;
	_character = c;
      }
    } else if (isalpha(c)) {
      _tokenType = IDENTIFIER;
      _identifier.clear();
      do
	_identifier += getChar();
      while (isalnum(peek()));
    } else {
      _tokenType = CHARACTER;
      _character = getChar();
    }
  }

  void printTokenType(ostream& out, TokenType type) {
    switch (type) {
    case END_OF_FILE:
      out << "end of file";
      break;
      
    case INTEGER:
      out << "an integer";
      break;

    case CHARACTER:
      out << "a character";
      break;

    case IDENTIFIER:
      out << "an identifier";
      break;

    default:
      ASSERT(false);
    }
  }

  void printToken(ostream& out) {
    switch (_tokenType) {
    case END_OF_FILE:
      out << "end of file";
      break;
      
    case INTEGER:
      out << _integer;
      break;

    case CHARACTER:
      out << '\'' << _character << '\'';
      break;

    case IDENTIFIER:
      out << '"' << _identifier << '"';
      break;

    default:
      ASSERT(false);
    }
  }

  mpz_class _integer;
  string _identifier;
  char _character;

  istream& _in;
};