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
|
#############################################################################
# Copyright (c) 2015-2016 Balabit
#
# This program is free software; you can redistribute it and/or modify it
# under the terms of the GNU General Public License version 2 as published
# by the Free Software Foundation, or (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program; if not, write to the Free Software
# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
#
# As an additional exemption you are allowed to compile & link against the
# OpenSSL libraries as published by the OpenSSL project. See the file
# COPYING for details.
#
#############################################################################
from __future__ import print_function, absolute_import
from ply import lex
from .lexertoken import LexerToken
from .lexer import Lexer
class LexBasedLexer(Lexer):
def __init__(self):
self._lexer = lex.lex(object=self)
self._lexer.current_token = ''
self._lexer.current_token_pos = -1
def token(self):
token = self._lexer.token()
if token is None and self._lexer.lexstate != 'INITIAL':
return LexerToken('LITERAL',
value=self._lexer.current_token,
partial=True,
lexpos=self._lexer.current_token_pos)
return token
def input(self, text):
while self._lexer.lexstatestack:
self._lexer.pop_state()
return self._lexer.input(text)
def get_position(self):
return self._lexer.lexpos
class TemplateLexerError(Exception):
pass
class TemplateLexer(LexBasedLexer):
# pylint: disable=invalid-name
tokens = (
'LITERAL', 'MACRO', "TEMPLATE_FUNC"
)
states = (
('dollar', 'exclusive'),
('dollarbrace', 'exclusive'),
('dollarparen', 'exclusive'),
('string', 'exclusive'),
('qstring', 'exclusive'),
)
# Tokens
def t_LITERAL(self, t):
r'[^\$]+'
t.type = "LITERAL"
return t
def t_DOLLAR(self, t):
r'\$'
t.lexer.push_state('dollar')
t.lexer.current_token = '$'
t.lexer.current_token_pos = t.lexpos
def t_dollar_MACRO(self, t):
r'[a-zA-Z0-9_]+'
t.lexer.pop_state()
t.value = '$' + t.value
t.lexpos = t.lexer.current_token_pos
return t
def t_dollar_BRACE_OPEN(self, t):
r'{'
t.lexer.push_state('dollarbrace')
t.lexer.current_token = '$' + t.value
def t_dollarbrace_MACRO(self, t):
r'[^}]+'
t.lexer.current_token += t.value
def t_dollarbrace_BRACE_CLOSE(self, t):
r'}'
t.lexer.current_token += t.value
# go back to INITIAL
t.lexer.pop_state()
t.lexer.pop_state()
t.type = 'MACRO'
t.value = t.lexer.current_token
t.lexpos = t.lexer.current_token_pos
return t
def t_dollar_PAREN_OPEN(self, t):
r'\('
t.lexer.push_state('dollarparen')
t.lexer.paren_count = 1
t.lexer.current_token = '$('
t.lexer.current_token_pos = t.lexpos - 1
def t_dollarparen_PAREN_OPEN(self, t):
r'\('
t.lexer.paren_count += 1
t.lexer.current_token += '('
def t_dollarparen_TEMPLATE_FUNC(self, t):
r'''[^()'"]+'''
t.lexer.current_token += t.value
def t_dollarparen_PAREN_CLOSE(self, t):
r'\)'
t.lexer.current_token += ')'
t.lexer.paren_count -= 1
if t.lexer.paren_count == 0:
t.type = 'TEMPLATE_FUNC'
t.value = t.lexer.current_token
t.lexpos = t.lexer.current_token_pos
t.lexer.pop_state()
t.lexer.pop_state()
return t
return None
def t_dollarparen_QUOTE(self, t):
r'"'
t.lexer.current_token += t.value
t.lexer.push_state('string')
def t_dollarparen_APOSTROPHE(self, t):
r"'"
t.lexer.current_token += t.value
t.lexer.push_state('qstring')
def t_string_CHARS(self, t):
r'[^"\\]'
t.lexer.current_token += t.value
def t_string_backslash_plus_character(self, t):
r'\\.'
t.lexer.current_token += t.value
def t_string_QUOTE(self, t):
r'"'
# closing quote character
t.lexer.current_token += t.value
t.lexer.pop_state()
def t_qstring_CHARS(self, t):
r"[^']"
t.lexer.current_token += t.value
def t_qstring_APOSTROPHE(self, t):
r"'"
# closing apostrophe
t.lexer.current_token += t.value
t.lexer.pop_state()
def t_error(self, t):
raise TemplateLexerError(f"Illegal character {t.value} in state {self._lexer.lexstate}")
def t_dollar_error(self, t):
return self.t_error(t)
def t_dollarbrace_error(self, t):
return self.t_error(t)
def t_dollarparen_error(self, t):
return self.t_error(t)
def t_string_error(self, t):
return self.t_error(t)
def t_qstring_error(self, t):
return self.t_error(t)
|
