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
|
# vim: ft=python fileencoding=utf-8 sts=4 sw=4 et:
# Copyright 2014-2021 Florian Bruhin (The Compiler) <mail@qutebrowser.org>
#
# This file is part of qutebrowser.
#
# qutebrowser is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# qutebrowser 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 qutebrowser. If not, see <https://www.gnu.org/licenses/>.
"""Our own fork of shlex.split with some added and removed features."""
import re
from qutebrowser.utils import log, utils
class ShellLexer:
"""A lexical analyzer class for simple shell-like syntaxes.
Based on Python's shlex, but cleaned up, removed some features, and added
some features useful for qutebrowser.
Attributes:
FIXME
"""
def __init__(self, s):
self.string = s
self.whitespace = ' \t\r'
self.quotes = '\'"'
self.escape = '\\'
self.escapedquotes = '"'
self.keep = False
self.quoted = False
self.escapedstate = ' '
self.token = ''
self.state = ' '
def reset(self):
"""Reset the state machine state to the defaults."""
self.quoted = False
self.escapedstate = ' '
self.token = ''
self.state = ' '
def __iter__(self): # noqa: C901 pragma: no mccabe
"""Read a raw token from the input stream."""
self.reset()
for nextchar in self.string:
if self.state == ' ':
if self.keep:
self.token += nextchar
if nextchar in self.whitespace:
if self.token or self.quoted:
yield self.token
self.reset()
elif nextchar in self.escape:
self.escapedstate = 'a'
self.state = nextchar
elif nextchar in self.quotes:
self.state = nextchar
else:
self.token = nextchar
self.state = 'a'
elif self.state in self.quotes:
self.quoted = True
if nextchar == self.state:
if self.keep:
self.token += nextchar
self.state = 'a'
elif (nextchar in self.escape and
self.state in self.escapedquotes):
if self.keep:
self.token += nextchar
self.escapedstate = self.state
self.state = nextchar
else:
self.token += nextchar
elif self.state in self.escape:
# In posix shells, only the quote itself or the escape
# character may be escaped within quotes.
if (self.escapedstate in self.quotes and
nextchar != self.state and
nextchar != self.escapedstate and not self.keep):
self.token += self.state
self.token += nextchar
self.state = self.escapedstate
elif self.state == 'a':
if nextchar in self.whitespace:
self.state = ' '
assert self.token or self.quoted
yield self.token
self.reset()
if self.keep:
yield nextchar
elif nextchar in self.quotes:
if self.keep:
self.token += nextchar
self.state = nextchar
elif nextchar in self.escape:
if self.keep:
self.token += nextchar
self.escapedstate = 'a'
self.state = nextchar
else:
self.token += nextchar
else:
raise utils.Unreachable(
"Invalid state {!r}!".format(self.state))
if self.state in self.escape and not self.keep:
self.token += self.state
if self.token or self.quoted:
yield self.token
def split(s, keep=False):
"""Split a string via ShellLexer.
Args:
s: The string to split.
keep: Whether to keep special chars in the split output.
"""
lexer = ShellLexer(s)
lexer.keep = keep
tokens = list(lexer)
if not tokens:
return []
out = []
spaces = ""
log.shlexer.vdebug( # type: ignore[attr-defined]
"{!r} -> {!r}".format(s, tokens))
for t in tokens:
if t.isspace():
spaces += t
else:
out.append(spaces + t)
spaces = ""
if spaces:
out.append(spaces)
return out
def _combine_ws(parts, whitespace):
"""Combine whitespace in a list with the element following it.
Args:
parts: A list of strings.
whitespace: A string containing what's considered whitespace.
Return:
The modified list.
"""
out = []
ws = ''
for part in parts:
if not part:
continue
elif part in whitespace:
ws += part
else:
out.append(ws + part)
ws = ''
if ws:
out.append(ws)
return out
def simple_split(s, keep=False, maxsplit=None):
"""Split a string on whitespace, optionally keeping the whitespace.
Args:
s: The string to split.
keep: Whether to keep whitespace.
maxsplit: The maximum count of splits.
Return:
A list of split strings.
"""
whitespace = '\n\t '
if maxsplit == 0:
# re.split with maxsplit=0 splits everything, while str.split splits
# nothing (which is the behavior we want).
if keep:
return [s]
else:
return [s.strip(whitespace)]
elif maxsplit is None:
maxsplit = 0
if keep:
pattern = '([' + whitespace + '])'
parts = re.split(pattern, s, maxsplit)
return _combine_ws(parts, whitespace)
else:
pattern = '[' + whitespace + ']'
parts = re.split(pattern, s, maxsplit)
parts[-1] = parts[-1].rstrip()
return [p for p in parts if p]
|
