summaryrefslogtreecommitdiff
path: root/gcc/go/gofrontend/lex.h
blob: 4202ed3748cd733fbd37615f46d7ae5abd04d54f (plain)
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
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
// lex.h -- Go frontend lexer.     -*- C++ -*-

// Copyright 2009 The Go Authors. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.

#ifndef GO_LEX_H
#define GO_LEX_H

#include <gmp.h>
#include <mpfr.h>

#include "operator.h"

struct Unicode_range;

// The keywords.  These must be in sorted order, other than
// KEYWORD_INVALID.  They must match the Keywords::mapping_ array in
// lex.cc.

enum Keyword
{
  KEYWORD_INVALID,	// Not a keyword.
  KEYWORD_ASM,
  KEYWORD_BREAK,
  KEYWORD_CASE,
  KEYWORD_CHAN,
  KEYWORD_CONST,
  KEYWORD_CONTINUE,
  KEYWORD_DEFAULT,
  KEYWORD_DEFER,
  KEYWORD_ELSE,
  KEYWORD_FALLTHROUGH,
  KEYWORD_FOR,
  KEYWORD_FUNC,
  KEYWORD_GO,
  KEYWORD_GOTO,
  KEYWORD_IF,
  KEYWORD_IMPORT,
  KEYWORD_INTERFACE,
  KEYWORD_MAP,
  KEYWORD_PACKAGE,
  KEYWORD_RANGE,
  KEYWORD_RETURN,
  KEYWORD_SELECT,
  KEYWORD_STRUCT,
  KEYWORD_SWITCH,
  KEYWORD_TYPE,
  KEYWORD_VAR
};

// A token returned from the lexer.

class Token
{
 public:
  // Token classification.
  enum Classification
  {
    // Token is invalid.
    TOKEN_INVALID,
    // Token indicates end of input.
    TOKEN_EOF,
    // Token is a keyword.
    TOKEN_KEYWORD,
    // Token is an identifier.
    TOKEN_IDENTIFIER,
    // Token is a string of characters.
    TOKEN_STRING,
    // Token is an operator.
    TOKEN_OPERATOR,
    // Token is an integer.
    TOKEN_INTEGER,
    // Token is a floating point number.
    TOKEN_FLOAT,
    // Token is an imaginary number.
    TOKEN_IMAGINARY
  };

  ~Token();
  Token(const Token&);
  Token& operator=(const Token&);

  // Get token classification.
  Classification
  classification() const
  { return this->classification_; }

  // Make a token for an invalid value.
  static Token
  make_invalid_token(source_location location)
  { return Token(TOKEN_INVALID, location); }

  // Make a token representing end of file.
  static Token
  make_eof_token(source_location location)
  { return Token(TOKEN_EOF, location); }

  // Make a keyword token.
  static Token
  make_keyword_token(Keyword keyword, source_location location)
  {
    Token tok(TOKEN_KEYWORD, location);
    tok.u_.keyword = keyword;
    return tok;
  }

  // Make an identifier token.
  static Token
  make_identifier_token(const std::string& value, bool is_exported,
			source_location location)
  {
    Token tok(TOKEN_IDENTIFIER, location);
    tok.u_.identifier_value.name = new std::string(value);
    tok.u_.identifier_value.is_exported = is_exported;
    return tok;
  }

  // Make a quoted string token.
  static Token
  make_string_token(const std::string& value, source_location location)
  {
    Token tok(TOKEN_STRING, location);
    tok.u_.string_value = new std::string(value);
    return tok;
  }

  // Make an operator token.
  static Token
  make_operator_token(Operator op, source_location location)
  {
    Token tok(TOKEN_OPERATOR, location);
    tok.u_.op = op;
    return tok;
  }

  // Make an integer token.
  static Token
  make_integer_token(mpz_t val, source_location location)
  {
    Token tok(TOKEN_INTEGER, location);
    mpz_init(tok.u_.integer_value);
    mpz_swap(tok.u_.integer_value, val);
    return tok;
  }

  // Make a float token.
  static Token
  make_float_token(mpfr_t val, source_location location)
  {
    Token tok(TOKEN_FLOAT, location);
    mpfr_init(tok.u_.float_value);
    mpfr_swap(tok.u_.float_value, val);
    return tok;
  }

  // Make a token for an imaginary number.
  static Token
  make_imaginary_token(mpfr_t val, source_location location)
  {
    Token tok(TOKEN_IMAGINARY, location);
    mpfr_init(tok.u_.float_value);
    mpfr_swap(tok.u_.float_value, val);
    return tok;
  }

  // Get the location of the token.
  source_location
  location() const
  { return this->location_; }

  // Return whether this is an invalid token.
  bool
  is_invalid() const
  { return this->classification_ == TOKEN_INVALID; }

  // Return whether this is the EOF token.
  bool
  is_eof() const
  { return this->classification_ == TOKEN_EOF; }

  // Return the keyword value for a keyword token.
  Keyword
  keyword() const
  {
    gcc_assert(this->classification_ == TOKEN_KEYWORD);
    return this->u_.keyword;
  }

  // Return whether this is an identifier.
  bool
  is_identifier() const
  { return this->classification_ == TOKEN_IDENTIFIER; }

  // Return the identifier.
  const std::string&
  identifier() const
  {
    gcc_assert(this->classification_ == TOKEN_IDENTIFIER);
    return *this->u_.identifier_value.name;
  }

  // Return whether the identifier is exported.
  bool
  is_identifier_exported() const
  {
    gcc_assert(this->classification_ == TOKEN_IDENTIFIER);
    return this->u_.identifier_value.is_exported;
  }

  // Return whether this is a string.
  bool
  is_string() const
  {
    return this->classification_ == TOKEN_STRING;
  }

  // Return the value of a string.  The returned value is a string of
  // UTF-8 characters.
  std::string
  string_value() const
  {
    gcc_assert(this->classification_ == TOKEN_STRING);
    return *this->u_.string_value;
  }

  // Return the value of an integer.
  const mpz_t*
  integer_value() const
  {
    gcc_assert(this->classification_ == TOKEN_INTEGER);
    return &this->u_.integer_value;
  }

  // Return the value of a float.
  const mpfr_t*
  float_value() const
  {
    gcc_assert(this->classification_ == TOKEN_FLOAT);
    return &this->u_.float_value;
  }

  // Return the value of an imaginary number.
  const mpfr_t*
  imaginary_value() const
  {
    gcc_assert(this->classification_ == TOKEN_IMAGINARY);
    return &this->u_.float_value;
  }

  // Return the operator value for an operator token.
  Operator
  op() const
  {
    gcc_assert(this->classification_ == TOKEN_OPERATOR);
    return this->u_.op;
  }

  // Return whether this token is KEYWORD.
  bool
  is_keyword(Keyword keyword) const
  {
    return (this->classification_ == TOKEN_KEYWORD
	    && this->u_.keyword == keyword);
  }

  // Return whether this token is OP.
  bool
  is_op(Operator op) const
  { return this->classification_ == TOKEN_OPERATOR && this->u_.op == op; }

  // Print the token for debugging.
  void
  print(FILE*) const;

 private:
  // Private constructor used by make_..._token functions above.
  Token(Classification, source_location);

  // Clear the token.
  void
  clear();

  // The token classification.
  Classification classification_;
  union
  {
    // The keyword value for TOKEN_KEYWORD.
    Keyword keyword;
    // The token value for TOKEN_IDENTIFIER.
    struct
    {
      // The name of the identifier.  This has been mangled to only
      // include ASCII characters.
      std::string* name;
      // Whether this name should be exported.  This is true if the
      // first letter in the name is upper case.
      bool is_exported;
    } identifier_value;
    // The string value for TOKEN_STRING.
    std::string* string_value;
    // The token value for TOKEN_INTEGER.
    mpz_t integer_value;
    // The token value for TOKEN_FLOAT or TOKEN_IMAGINARY.
    mpfr_t float_value;
    // The token value for TOKEN_OPERATOR or the keyword value
    Operator op;
  } u_;
  // The source location.
  source_location location_;
};

// The lexer itself.

class Lex
{
 public:
  Lex(const char* input_file_name, FILE* input_file);

  ~Lex();

  // Return the next token.
  Token
  next_token();

  // Return whether the identifier NAME should be exported.  NAME is a
  // mangled name which includes only ASCII characters.
  static bool
  is_exported_name(const std::string& name);

  // A helper function.  Append V to STR.  IS_CHARACTER is true if V
  // is a Unicode character which should be converted into UTF-8,
  // false if it is a byte value to be appended directly.  The
  // location is used to warn about an out of range character.
  static void
  append_char(unsigned int v, bool is_charater, std::string* str,
	      source_location);

  // A helper function.  Fetch a UTF-8 character from STR and store it
  // in *VALUE.  Return the number of bytes read from STR.  Return 0
  // if STR does not point to a valid UTF-8 character.
  static int
  fetch_char(const char* str, unsigned int *value);

 private:
  ssize_t
  get_line();

  bool
  require_line();

  // The current location.
  source_location
  location() const;

  // A position CHARS column positions before the current location.
  source_location
  earlier_location(int chars) const;

  static bool
  is_hex_digit(char);

  static unsigned char
  octal_value(char c)
  { return c - '0'; }

  Token
  make_invalid_token()
  { return Token::make_invalid_token(this->location()); }

  Token
  make_eof_token()
  { return Token::make_eof_token(this->location()); }

  Token
  make_operator(Operator op, int chars)
  { return Token::make_operator_token(op, this->earlier_location(chars)); }

  Token
  gather_identifier();

  static bool
  could_be_exponent(const char*, const char*);

  Token
  gather_number();

  Token
  gather_character();

  Token
  gather_string();

  Token
  gather_raw_string();

  const char*
  advance_one_utf8_char(const char*, unsigned int*, bool*);

  const char*
  advance_one_char(const char*, bool, unsigned int*, bool*);

  static bool
  is_unicode_digit(unsigned int c);

  static bool
  is_unicode_letter(unsigned int c);

  static bool
  is_unicode_uppercase(unsigned int c);

  static bool
  is_in_unicode_range(unsigned int C, const Unicode_range* ranges,
		      size_t range_size);

  Operator
  three_character_operator(char, char, char);

  Operator
  two_character_operator(char, char);

  Operator
  one_character_operator(char);

  bool
  skip_c_comment();

  void
  skip_cpp_comment();

  // The input file name.
  const char* input_file_name_;
  // The input file.
  FILE* input_file_;
  // The line buffer.  This holds the current line.
  char* linebuf_;
  // The size of the line buffer.
  size_t linebufsize_;
  // The nmber of characters in the current line.
  size_t linesize_;
  // The current offset in linebuf_.
  size_t lineoff_;
  // The current line number.
  size_t lineno_;
  // Whether to add a semicolon if we see a newline now.
  bool add_semi_at_eol_;
};

#endif // !defined(GO_LEX_H)