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
|
# Copyright 2014 The Chromium Authors
# Use of this source code is governed by a BSD-style license that can be
# found in the LICENSE file.
import os.path
import sys
from mojom import fileutil
from mojom.error import Error
fileutil.AddLocalRepoThirdPartyDirToModulePath()
from ply.lex import TOKEN
class LexError(Error):
"""Class for errors from the lexer."""
def __init__(self, filename, message, lineno):
Error.__init__(self, filename, message, lineno=lineno)
# We have methods which look like they could be functions:
# pylint: disable=R0201
class Lexer:
def __init__(self, filename):
self.filename = filename
######################-- PRIVATE --######################
##
## Internal auxiliary methods
##
def _error(self, msg, token):
raise LexError(self.filename, msg, token.lineno)
##
## Reserved keywords
##
keywords = (
'HANDLE',
'IMPORT',
'MODULE',
'STRUCT',
'UNION',
'INTERFACE',
'ENUM',
'CONST',
'TRUE',
'FALSE',
'DEFAULT',
'ARRAY',
'MAP',
'ASSOCIATED',
'PENDING_REMOTE',
'PENDING_RECEIVER',
'PENDING_ASSOCIATED_REMOTE',
'PENDING_ASSOCIATED_RECEIVER',
'FEATURE',
)
keyword_map = {}
for keyword in keywords:
keyword_map[keyword.lower()] = keyword
##
## All the tokens recognized by the lexer
##
tokens = keywords + (
# Identifiers
'NAME',
# Constants
'ORDINAL',
'INT_CONST_DEC',
'INT_CONST_HEX',
'FLOAT_CONST',
# String literals
'STRING_LITERAL',
# Operators
'MINUS',
'PLUS',
'QSTN',
# Assignment
'EQUALS',
# Request / response
'RESPONSE',
# Delimiters
'LPAREN',
'RPAREN', # ( )
'LBRACKET',
'RBRACKET', # [ ]
'LBRACE',
'RBRACE', # { }
'LANGLE',
'RANGLE', # < >
'SEMI', # ;
'COMMA',
'DOT' # , .
)
##
## Regexes for use in tokens
##
# valid C identifiers (K&R2: A.2.3)
identifier = r'[a-zA-Z_][0-9a-zA-Z_]*'
hex_prefix = '0[xX]'
hex_digits = '[0-9a-fA-F]+'
# integer constants (K&R2: A.2.5.1)
decimal_constant = '0|([1-9][0-9]*)'
hex_constant = hex_prefix + hex_digits
# Don't allow octal constants (even invalid octal).
octal_constant_disallowed = '0[0-9]+'
# 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+'))'
# string literals (K&R2: A.2.6)
string_char = r"""([^"\\\n]|""" + escape_sequence + ')'
string_literal = '"' + string_char + '*"'
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+')))'
# Ordinals
ordinal = r'@[0-9]+'
missing_ordinal_value = r'@'
# Don't allow ordinal values in octal (even invalid octal, like 09) or
# hexadecimal.
octal_or_hex_ordinal_disallowed = (
r'@((0[0-9]+)|(' + hex_prefix + hex_digits + '))')
##
## Rules for the normal state
##
t_ignore = ' \t\r'
# Newlines
def t_NEWLINE(self, t):
r'\n+'
t.lexer.lineno += len(t.value)
# Operators
t_MINUS = r'-'
t_PLUS = r'\+'
t_QSTN = r'\?'
# =
t_EQUALS = r'='
# =>
t_RESPONSE = r'=>'
# Delimiters
t_LPAREN = r'\('
t_RPAREN = r'\)'
t_LBRACKET = r'\['
t_RBRACKET = r'\]'
t_LBRACE = r'\{'
t_RBRACE = r'\}'
t_LANGLE = r'<'
t_RANGLE = r'>'
t_COMMA = r','
t_DOT = r'\.'
t_SEMI = r';'
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_constant)
def t_INT_CONST_HEX(self, t):
return t
@TOKEN(octal_constant_disallowed)
def t_OCTAL_CONSTANT_DISALLOWED(self, t):
msg = "Octal values not allowed"
self._error(msg, t)
@TOKEN(decimal_constant)
def t_INT_CONST_DEC(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)
# Handle ordinal-related tokens in the right order:
@TOKEN(octal_or_hex_ordinal_disallowed)
def t_OCTAL_OR_HEX_ORDINAL_DISALLOWED(self, t):
msg = "Octal and hexadecimal ordinal values not allowed"
self._error(msg, t)
@TOKEN(ordinal)
def t_ORDINAL(self, t):
return t
@TOKEN(missing_ordinal_value)
def t_BAD_ORDINAL(self, t):
msg = "Missing ordinal value"
self._error(msg, t)
@TOKEN(identifier)
def t_NAME(self, t):
t.type = self.keyword_map.get(t.value, "NAME")
return t
# Ignore C and C++ style comments
def t_COMMENT(self, t):
r'(/\*(.|\n)*?\*/)|(//.*(\n[ \t]*//.*)*)'
t.lexer.lineno += t.value.count("\n")
def t_error(self, t):
msg = "Illegal character %s" % repr(t.value[0])
self._error(msg, t)
|
