-
Notifications
You must be signed in to change notification settings - Fork 0
/
lexer.cpp
338 lines (309 loc) · 9.39 KB
/
lexer.cpp
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
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
#include <map>
#include <cassert>
#include <cctype>
#include <string>
#include <iostream>
#include "token.h"
#include "exceptions.h"
#include "lexer.h"
////////////////////////////////////////////////////////////////////////
// Lexer implementation
////////////////////////////////////////////////////////////////////////
Lexer::Lexer(FILE *in, const std::string &filename)
: m_in(in), m_filename(filename), m_line(1), m_col(1), m_eof(false) {
}
Lexer::~Lexer() {
// delete any cached lookahead tokens
for (auto i = m_lookahead.begin(); i != m_lookahead.end(); ++i) {
delete *i;
}
fclose(m_in);
}
Node *Lexer::next() {
fill(1);
if (m_lookahead.empty()) {
SyntaxError::raise(get_current_loc(), "Unexpected end of input");
}
Node *tok = m_lookahead.front();
m_lookahead.pop_front();
return tok;
}
Node *Lexer::peek(int how_many) {
// try to get as many lookahead tokens as required
fill(how_many);
// if there aren't enough lookahead tokens,
// then the input ended before the token we want
if (int(m_lookahead.size()) < how_many) {
return nullptr;
}
// return the pointer to the Node representing the token
return m_lookahead.at(how_many - 1);
}
Location Lexer::get_current_loc() const {
return Location(m_filename, m_line, m_col);
}
// Read the next character of input, returning -1 (and setting m_eof to true)
// if the end of input has been reached.
int Lexer::read() {
if (m_eof) {
return -1;
}
int c = fgetc(m_in);
if (c < 0) {
m_eof = true;
} else if (c == '\n') {
m_col = 1;
m_line++;
} else {
m_col++;
}
return c;
}
// "Unread" a character. Useful for when reading a character indicates
// that the current token has ended and the next one has begun.
void Lexer::unread(int c) {
ungetc(c, m_in);
m_col--;
}
void Lexer::fill(int how_many) {
assert(how_many > 0);
while (!m_eof && int(m_lookahead.size()) < how_many) {
Node *tok = read_token();
if (tok != nullptr) {
m_lookahead.push_back(tok);
}
}
}
Node *Lexer::read_token() {
int c, line = -1, col = -1;
// skip whitespace characters until a non-whitespace character is read
for (;;) {
line = m_line;
col = m_col;
c = read();
if (c < 0 || !isspace(c)) {
break;
}
}
if (c < 0) {
// reached end of file
return nullptr;
}
std::string lexeme;
lexeme.push_back(char(c));
if (isalpha(c)) {
Node *tok = read_continued_token(TOK_IDENTIFIER, lexeme, line, col, isalnum);
std::string word = tok->get_str();
if (word == "var") {
tok->set_tag(TOK_VAR);
} else if (word == "function") {
tok->set_tag(TOK_FN);
} else if (word == "if") {
tok->set_tag(TOK_IF);
} else if (word == "else") {
tok->set_tag(TOK_ELSE);
} else if (word == "while") {
tok->set_tag(TOK_WHILE);
}
return tok;
} else if (isdigit(c)) {
return read_continued_token(TOK_INTEGER_LITERAL, lexeme, line, col, isdigit);
} else {
switch (c) {
case '+':
return token_create(TOK_PLUS, lexeme, line, col);
case '-':
return token_create(TOK_MINUS, lexeme, line, col);
case '*':
return token_create(TOK_TIMES, lexeme, line, col);
case '/':
return token_create(TOK_DIVIDE, lexeme, line, col);
case '(':
return token_create(TOK_LPAREN, lexeme, line, col);
case ')':
return token_create(TOK_RPAREN, lexeme, line, col);
case '{':
return token_create(TOK_LBRACE, lexeme, line, col);
case '}':
return token_create(TOK_RBRACE, lexeme, line, col);
case ',':
return token_create(TOK_COMMA, lexeme, line, col);
case ';':
return token_create(TOK_SEMICOLON, lexeme, line, col);
case '=':
return read_multi_equal(lexeme, line, col);
case '<':
return read_multi_less(lexeme, line, col);
case '>':
return read_multi_greater(lexeme, line, col);
case '|':
return read_continued_token(TOK_OR, lexeme, line, col, ispunct);
case '&':
return read_continued_token(TOK_AND, lexeme, line, col, ispunct);
case '!':
return read_continued_token(TOK_NOTEQUAL, lexeme, line, col, ispunct);
case '"':
return read_multi_string(lexeme, line, col);
default:
SyntaxError::raise(get_current_loc(), "Unrecognized character '%c'", c);
}
}
}
// Helper function to create a Node object to represent a token.
Node *Lexer::token_create(enum TokenKind kind, const std::string &lexeme, int line, int col) {
Node *token = new Node(kind, lexeme);
Location source_info(m_filename, line, col);
token->set_loc(source_info);
return token;
}
// Read the continuation of a (possibly) multi-character token, such as
// an identifier or integer literal. pred is a pointer to a predicate
// function to determine which characters are valid continuations.
Node *
Lexer::read_continued_token(enum TokenKind kind, const std::string &lexeme_start, int line, int col, int (*pred)(int)) {
std::string lexeme(lexeme_start);
for (;;) {
int c = read();
if (c >= 0 && pred(c)) {
// token has finished
lexeme.push_back(char(c));
} else {
if (c >= 0) {
unread(c);
}
return token_create(kind, lexeme, line, col);
}
}
}
Node *Lexer::read_multi_equal(const std::string &lexeme, int line, int col) {
enum TokenKind kind;
int next_c = read();
if (next_c < 0) {
// at eof
kind = TOK_ASSIGN;
} else if (next_c == '=') {
kind = TOK_EQUAL;
} else {
// because we read in a token, this would prevent the next value being read correctly
unread(next_c);
kind = TOK_ASSIGN;
}
return token_create(kind, lexeme, line, col);
}
Node *Lexer::read_multi_less(const std::string &lexeme, int line, int col) {
enum TokenKind kind;
int next_c = read();
if (next_c < 0) {
// at eof
kind = TOK_LESS;
} else if (next_c == '=') {
kind = TOK_LESSEQUAL;
} else {
unread(next_c);
kind = TOK_LESS;
}
return token_create(kind, lexeme, line, col);
}
Node *Lexer::read_multi_greater(const std::string &lexeme, int line, int col) {
enum TokenKind kind;
int next_c = read();
if (next_c < 0) {
// at eof
kind = TOK_GREATER;
} else if (next_c == '=') {
kind = TOK_GREATEREQUAL;
} else {
unread(next_c);
kind = TOK_GREATER;
}
return token_create(kind, lexeme, line, col);
}
Node *Lexer::read_multi_string(const std::string &lexeme, int line, int col) {
int next_c = read();
std::string word;
while (next_c != '"') {
if (next_c == '\\') {
int next_next = read();
switch (next_next) {
case '"':
next_c = '\"';
break;
case 'n':
next_c = '\n';
break;
case 'r':
next_c = '\r';
break;
case 't':
next_c = '\t';
break;
default:
unread(next_next);
}
}
word.push_back(next_c);
next_c = read();
}
return token_create(TOK_STRING, word, line, col);
}
std::string Lexer::node_tag_to_string(int tag) {
// was used for debugging, will keep in case of future modifications to lexer
switch (tag) {
case TOK_FN:
return "FUNCTION";
case TOK_IF:
return "IF";
case TOK_ELSE:
return "ELSE";
case TOK_WHILE:
return "WHILE";
case TOK_IDENTIFIER:
return "VARREF";
case TOK_VAR:
return "VARDEF";
case TOK_ASSIGN:
return "ASSIGN";
case TOK_INTEGER_LITERAL:
return "INT_LITERAL";
case TOK_STRING:
return "STRING";
case TOK_PLUS:
return "ADD";
case TOK_MINUS:
return "SUB";
case TOK_TIMES:
return "MULTIPLY";
case TOK_DIVIDE:
return "DIVIDE";
case TOK_LPAREN:
return "LPAREN";
case TOK_RPAREN:
return "RPAREN";
case TOK_LBRACE:
return "LBRACE";
case TOK_RBRACE:
return "RBRACE";
case TOK_OR:
return "OR";
case TOK_AND:
return "AND";
case TOK_LESS:
return "LESS";
case TOK_LESSEQUAL:
return "LESSEQUAL";
case TOK_GREATER:
return "GREATER";
case TOK_GREATEREQUAL:
return "GREATEREQUAL";
case TOK_EQUAL:
return "EQUAL";
case TOK_NOTEQUAL:
return "NOT";
case TOK_SEMICOLON:
return "SEMI";
case TOK_COMMA:
return "COMMA";
default:
return "";
}
}