File: c_lexer.py

package info (click to toggle)
pycparser 2.19-1
  • links: PTS, VCS
  • area: main
  • in suites: buster, sid
  • size: 1,620 kB
  • sloc: python: 9,147; ansic: 1,788; makefile: 20; sh: 10
file content (484 lines) | stat: -rw-r--r-- 14,462 bytes parent folder | download
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
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
#------------------------------------------------------------------------------
# pycparser: c_lexer.py
#
# CLexer class: lexer for the C language
#
# Eli Bendersky [https://eli.thegreenplace.net/]
# License: BSD
#------------------------------------------------------------------------------
import re
import sys

from ply import lex
from ply.lex import TOKEN


class CLexer(object):
    """ A lexer for the C language. After building it, set the
        input text with input(), and call token() to get new
        tokens.

        The public attribute filename can be set to an initial
        filaneme, but the lexer will update it upon #line
        directives.
    """
    def __init__(self, error_func, on_lbrace_func, on_rbrace_func,
                 type_lookup_func):
        """ Create a new Lexer.

            error_func:
                An error function. Will be called with an error
                message, line and column as arguments, in case of
                an error during lexing.

            on_lbrace_func, on_rbrace_func:
                Called when an LBRACE or RBRACE is encountered
                (likely to push/pop type_lookup_func's scope)

            type_lookup_func:
                A type lookup function. Given a string, it must
                return True IFF this string is a name of a type
                that was defined with a typedef earlier.
        """
        self.error_func = error_func
        self.on_lbrace_func = on_lbrace_func
        self.on_rbrace_func = on_rbrace_func
        self.type_lookup_func = type_lookup_func
        self.filename = ''

        # Keeps track of the last token returned from self.token()
        self.last_token = None

        # Allow either "# line" or "# <num>" to support GCC's
        # cpp output
        #
        self.line_pattern = re.compile(r'([ \t]*line\W)|([ \t]*\d+)')
        self.pragma_pattern = re.compile(r'[ \t]*pragma\W')

    def build(self, **kwargs):
        """ Builds the lexer from the specification. Must be
            called after the lexer object is created.

            This method exists separately, because the PLY
            manual warns against calling lex.lex inside
            __init__
        """
        self.lexer = lex.lex(object=self, **kwargs)

    def reset_lineno(self):
        """ Resets the internal line number counter of the lexer.
        """
        self.lexer.lineno = 1

    def input(self, text):
        self.lexer.input(text)

    def token(self):
        self.last_token = self.lexer.token()
        return self.last_token

    def find_tok_column(self, token):
        """ Find the column of the token in its line.
        """
        last_cr = self.lexer.lexdata.rfind('\n', 0, token.lexpos)
        return token.lexpos - last_cr

    ######################--   PRIVATE   --######################

    ##
    ## Internal auxiliary methods
    ##
    def _error(self, msg, token):
        location = self._make_tok_location(token)
        self.error_func(msg, location[0], location[1])
        self.lexer.skip(1)

    def _make_tok_location(self, token):
        return (token.lineno, self.find_tok_column(token))

    ##
    ## Reserved keywords
    ##
    keywords = (
        '_BOOL', '_COMPLEX', 'AUTO', 'BREAK', 'CASE', 'CHAR', 'CONST',
        'CONTINUE', 'DEFAULT', 'DO', 'DOUBLE', 'ELSE', 'ENUM', 'EXTERN',
        'FLOAT', 'FOR', 'GOTO', 'IF', 'INLINE', 'INT', 'LONG',
        'REGISTER', 'OFFSETOF',
        'RESTRICT', 'RETURN', 'SHORT', 'SIGNED', 'SIZEOF', 'STATIC', 'STRUCT',
        'SWITCH', 'TYPEDEF', 'UNION', 'UNSIGNED', 'VOID',
        'VOLATILE', 'WHILE', '__INT128',
    )

    keyword_map = {}
    for keyword in keywords:
        if keyword == '_BOOL':
            keyword_map['_Bool'] = keyword
        elif keyword == '_COMPLEX':
            keyword_map['_Complex'] = keyword
        else:
            keyword_map[keyword.lower()] = keyword

    ##
    ## All the tokens recognized by the lexer
    ##
    tokens = keywords + (
        # Identifiers
        'ID',

        # Type identifiers (identifiers previously defined as
        # types with typedef)
        'TYPEID',

        # constants
        'INT_CONST_DEC', 'INT_CONST_OCT', 'INT_CONST_HEX', 'INT_CONST_BIN',
        'FLOAT_CONST', 'HEX_FLOAT_CONST',
        'CHAR_CONST',
        'WCHAR_CONST',

        # String literals
        'STRING_LITERAL',
        'WSTRING_LITERAL',

        # Operators
        'PLUS', 'MINUS', 'TIMES', 'DIVIDE', 'MOD',
        'OR', 'AND', 'NOT', 'XOR', 'LSHIFT', 'RSHIFT',
        'LOR', 'LAND', 'LNOT',
        'LT', 'LE', 'GT', 'GE', 'EQ', 'NE',

        # Assignment
        'EQUALS', 'TIMESEQUAL', 'DIVEQUAL', 'MODEQUAL',
        'PLUSEQUAL', 'MINUSEQUAL',
        'LSHIFTEQUAL','RSHIFTEQUAL', 'ANDEQUAL', 'XOREQUAL',
        'OREQUAL',

        # Increment/decrement
        'PLUSPLUS', 'MINUSMINUS',

        # Structure dereference (->)
        'ARROW',

        # Conditional operator (?)
        'CONDOP',

        # Delimeters
        'LPAREN', 'RPAREN',         # ( )
        'LBRACKET', 'RBRACKET',     # [ ]
        'LBRACE', 'RBRACE',         # { }
        'COMMA', 'PERIOD',          # . ,
        'SEMI', 'COLON',            # ; :

        # Ellipsis (...)
        'ELLIPSIS',

        # pre-processor
        'PPHASH',       # '#'
        'PPPRAGMA',     # 'pragma'
        'PPPRAGMASTR',
    )

    ##
    ## Regexes for use in tokens
    ##
    ##

    # valid C identifiers (K&R2: A.2.3), plus '$' (supported by some compilers)
    identifier = r'[a-zA-Z_$][0-9a-zA-Z_$]*'

    hex_prefix = '0[xX]'
    hex_digits = '[0-9a-fA-F]+'
    bin_prefix = '0[bB]'
    bin_digits = '[01]+'

    # integer constants (K&R2: A.2.5.1)
    integer_suffix_opt = r'(([uU]ll)|([uU]LL)|(ll[uU]?)|(LL[uU]?)|([uU][lL])|([lL][uU]?)|[uU])?'
    decimal_constant = '(0'+integer_suffix_opt+')|([1-9][0-9]*'+integer_suffix_opt+')'
    octal_constant = '0[0-7]*'+integer_suffix_opt
    hex_constant = hex_prefix+hex_digits+integer_suffix_opt
    bin_constant = bin_prefix+bin_digits+integer_suffix_opt

    bad_octal_constant = '0[0-7]*[89]'

    # character constants (K&R2: A.2.5.2)
    # Note: a-zA-Z and '.-~^_!=&;,' are allowed as escape chars to support #line
    # directives with Windows paths as filenames (..\..\dir\file)
    # For the same reason, decimal_escape allows all digit sequences. We want to
    # parse all correct code, even if it means to sometimes parse incorrect
    # code.
    #
    simple_escape = r"""([a-zA-Z._~!=&\^\-\\?'"])"""
    decimal_escape = r"""(\d+)"""
    hex_escape = r"""(x[0-9a-fA-F]+)"""
    bad_escape = r"""([\\][^a-zA-Z._~^!=&\^\-\\?'"x0-7])"""

    escape_sequence = r"""(\\("""+simple_escape+'|'+decimal_escape+'|'+hex_escape+'))'
    cconst_char = r"""([^'\\\n]|"""+escape_sequence+')'
    char_const = "'"+cconst_char+"'"
    wchar_const = 'L'+char_const
    unmatched_quote = "('"+cconst_char+"*\\n)|('"+cconst_char+"*$)"
    bad_char_const = r"""('"""+cconst_char+"""[^'\n]+')|('')|('"""+bad_escape+r"""[^'\n]*')"""

    # string literals (K&R2: A.2.6)
    string_char = r"""([^"\\\n]|"""+escape_sequence+')'
    string_literal = '"'+string_char+'*"'
    wstring_literal = 'L'+string_literal
    bad_string_literal = '"'+string_char+'*?'+bad_escape+string_char+'*"'

    # floating constants (K&R2: A.2.5.3)
    exponent_part = r"""([eE][-+]?[0-9]+)"""
    fractional_constant = r"""([0-9]*\.[0-9]+)|([0-9]+\.)"""
    floating_constant = '(((('+fractional_constant+')'+exponent_part+'?)|([0-9]+'+exponent_part+'))[FfLl]?)'
    binary_exponent_part = r'''([pP][+-]?[0-9]+)'''
    hex_fractional_constant = '((('+hex_digits+r""")?\."""+hex_digits+')|('+hex_digits+r"""\.))"""
    hex_floating_constant = '('+hex_prefix+'('+hex_digits+'|'+hex_fractional_constant+')'+binary_exponent_part+'[FfLl]?)'

    ##
    ## Lexer states: used for preprocessor \n-terminated directives
    ##
    states = (
        # ppline: preprocessor line directives
        #
        ('ppline', 'exclusive'),

        # pppragma: pragma
        #
        ('pppragma', 'exclusive'),
    )

    def t_PPHASH(self, t):
        r'[ \t]*\#'
        if self.line_pattern.match(t.lexer.lexdata, pos=t.lexer.lexpos):
            t.lexer.begin('ppline')
            self.pp_line = self.pp_filename = None
        elif self.pragma_pattern.match(t.lexer.lexdata, pos=t.lexer.lexpos):
            t.lexer.begin('pppragma')
        else:
            t.type = 'PPHASH'
            return t

    ##
    ## Rules for the ppline state
    ##
    @TOKEN(string_literal)
    def t_ppline_FILENAME(self, t):
        if self.pp_line is None:
            self._error('filename before line number in #line', t)
        else:
            self.pp_filename = t.value.lstrip('"').rstrip('"')

    @TOKEN(decimal_constant)
    def t_ppline_LINE_NUMBER(self, t):
        if self.pp_line is None:
            self.pp_line = t.value
        else:
            # Ignore: GCC's cpp sometimes inserts a numeric flag
            # after the file name
            pass

    def t_ppline_NEWLINE(self, t):
        r'\n'
        if self.pp_line is None:
            self._error('line number missing in #line', t)
        else:
            self.lexer.lineno = int(self.pp_line)

            if self.pp_filename is not None:
                self.filename = self.pp_filename

        t.lexer.begin('INITIAL')

    def t_ppline_PPLINE(self, t):
        r'line'
        pass

    t_ppline_ignore = ' \t'

    def t_ppline_error(self, t):
        self._error('invalid #line directive', t)

    ##
    ## Rules for the pppragma state
    ##
    def t_pppragma_NEWLINE(self, t):
        r'\n'
        t.lexer.lineno += 1
        t.lexer.begin('INITIAL')

    def t_pppragma_PPPRAGMA(self, t):
        r'pragma'
        return t

    t_pppragma_ignore = ' \t'

    def t_pppragma_STR(self, t):
        '.+'
        t.type = 'PPPRAGMASTR'
        return t

    def t_pppragma_error(self, t):
        self._error('invalid #pragma directive', t)

    ##
    ## Rules for the normal state
    ##
    t_ignore = ' \t'

    # Newlines
    def t_NEWLINE(self, t):
        r'\n+'
        t.lexer.lineno += t.value.count("\n")

    # Operators
    t_PLUS              = r'\+'
    t_MINUS             = r'-'
    t_TIMES             = r'\*'
    t_DIVIDE            = r'/'
    t_MOD               = r'%'
    t_OR                = r'\|'
    t_AND               = r'&'
    t_NOT               = r'~'
    t_XOR               = r'\^'
    t_LSHIFT            = r'<<'
    t_RSHIFT            = r'>>'
    t_LOR               = r'\|\|'
    t_LAND              = r'&&'
    t_LNOT              = r'!'
    t_LT                = r'<'
    t_GT                = r'>'
    t_LE                = r'<='
    t_GE                = r'>='
    t_EQ                = r'=='
    t_NE                = r'!='

    # Assignment operators
    t_EQUALS            = r'='
    t_TIMESEQUAL        = r'\*='
    t_DIVEQUAL          = r'/='
    t_MODEQUAL          = r'%='
    t_PLUSEQUAL         = r'\+='
    t_MINUSEQUAL        = r'-='
    t_LSHIFTEQUAL       = r'<<='
    t_RSHIFTEQUAL       = r'>>='
    t_ANDEQUAL          = r'&='
    t_OREQUAL           = r'\|='
    t_XOREQUAL          = r'\^='

    # Increment/decrement
    t_PLUSPLUS          = r'\+\+'
    t_MINUSMINUS        = r'--'

    # ->
    t_ARROW             = r'->'

    # ?
    t_CONDOP            = r'\?'

    # Delimeters
    t_LPAREN            = r'\('
    t_RPAREN            = r'\)'
    t_LBRACKET          = r'\['
    t_RBRACKET          = r'\]'
    t_COMMA             = r','
    t_PERIOD            = r'\.'
    t_SEMI              = r';'
    t_COLON             = r':'
    t_ELLIPSIS          = r'\.\.\.'

    # Scope delimiters
    # To see why on_lbrace_func is needed, consider:
    #   typedef char TT;
    #   void foo(int TT) { TT = 10; }
    #   TT x = 5;
    # Outside the function, TT is a typedef, but inside (starting and ending
    # with the braces) it's a parameter.  The trouble begins with yacc's
    # lookahead token.  If we open a new scope in brace_open, then TT has
    # already been read and incorrectly interpreted as TYPEID.  So, we need
    # to open and close scopes from within the lexer.
    # Similar for the TT immediately outside the end of the function.
    #
    @TOKEN(r'\{')
    def t_LBRACE(self, t):
        self.on_lbrace_func()
        return t
    @TOKEN(r'\}')
    def t_RBRACE(self, t):
        self.on_rbrace_func()
        return t

    t_STRING_LITERAL = string_literal

    # The following floating and integer constants are defined as
    # functions to impose a strict order (otherwise, decimal
    # is placed before the others because its regex is longer,
    # and this is bad)
    #
    @TOKEN(floating_constant)
    def t_FLOAT_CONST(self, t):
        return t

    @TOKEN(hex_floating_constant)
    def t_HEX_FLOAT_CONST(self, t):
        return t

    @TOKEN(hex_constant)
    def t_INT_CONST_HEX(self, t):
        return t

    @TOKEN(bin_constant)
    def t_INT_CONST_BIN(self, t):
        return t

    @TOKEN(bad_octal_constant)
    def t_BAD_CONST_OCT(self, t):
        msg = "Invalid octal constant"
        self._error(msg, t)

    @TOKEN(octal_constant)
    def t_INT_CONST_OCT(self, t):
        return t

    @TOKEN(decimal_constant)
    def t_INT_CONST_DEC(self, t):
        return t

    # Must come before bad_char_const, to prevent it from
    # catching valid char constants as invalid
    #
    @TOKEN(char_const)
    def t_CHAR_CONST(self, t):
        return t

    @TOKEN(wchar_const)
    def t_WCHAR_CONST(self, t):
        return t

    @TOKEN(unmatched_quote)
    def t_UNMATCHED_QUOTE(self, t):
        msg = "Unmatched '"
        self._error(msg, t)

    @TOKEN(bad_char_const)
    def t_BAD_CHAR_CONST(self, t):
        msg = "Invalid char constant %s" % t.value
        self._error(msg, t)

    @TOKEN(wstring_literal)
    def t_WSTRING_LITERAL(self, t):
        return t

    # unmatched string literals are caught by the preprocessor

    @TOKEN(bad_string_literal)
    def t_BAD_STRING_LITERAL(self, t):
        msg = "String contains invalid escape code"
        self._error(msg, t)

    @TOKEN(identifier)
    def t_ID(self, t):
        t.type = self.keyword_map.get(t.value, "ID")
        if t.type == 'ID' and self.type_lookup_func(t.value):
            t.type = "TYPEID"
        return t

    def t_error(self, t):
        msg = 'Illegal character %s' % repr(t.value[0])
        self._error(msg, t)