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
| from __future__ import absolute_import
import itertools
import lit.util
from lit.ShCommands import Command, GlobItem, Pipeline, Seq
class ShLexer:
def __init__(self, data, win32Escapes = False):
self.data = data
self.pos = 0
self.end = len(data)
self.win32Escapes = win32Escapes
def eat(self):
c = self.data[self.pos]
self.pos += 1
return c
def look(self):
return self.data[self.pos]
def maybe_eat(self, c):
"""
maybe_eat(c) - Consume the character c if it is the next character,
returning True if a character was consumed. """
if self.data[self.pos] == c:
self.pos += 1
return True
return False
def lex_arg_fast(self, c):
# Get the leading whitespace free section.
chunk = self.data[self.pos - 1:].split(None, 1)[0]
# If it has special characters, the fast path failed.
if ('|' in chunk or '&' in chunk or
'<' in chunk or '>' in chunk or
"'" in chunk or '"' in chunk or
';' in chunk or '\\' in chunk):
return None
self.pos = self.pos - 1 + len(chunk)
return GlobItem(chunk) if '*' in chunk or '?' in chunk else chunk
def lex_arg_slow(self, c):
if c in "'\"":
str = self.lex_arg_quoted(c)
else:
str = c
unquoted_glob_char = False
quoted_glob_char = False
while self.pos != self.end:
c = self.look()
if c.isspace() or c in "|&;":
break
elif c in '><':
# This is an annoying case; we treat '2>' as a single token so
# we don't have to track whitespace tokens.
# If the parse string isn't an integer, do the usual thing.
if not str.isdigit():
break
# Otherwise, lex the operator and convert to a redirection
# token.
num = int(str)
tok = self.lex_one_token()
assert isinstance(tok, tuple) and len(tok) == 1
return (tok[0], num)
elif c == '"' or c == "'":
self.eat()
quoted_arg = self.lex_arg_quoted(c)
if '*' in quoted_arg or '?' in quoted_arg:
quoted_glob_char = True
str += quoted_arg
elif not self.win32Escapes and c == '\\':
# Outside of a string, '\\' escapes everything.
self.eat()
if self.pos == self.end:
lit.util.warning(
"escape at end of quoted argument in: %r" % self.data)
return str
str += self.eat()
elif c in '*?':
unquoted_glob_char = True
str += self.eat()
else:
str += self.eat()
# If a quote character is present, lex_arg_quoted will remove the quotes
# and append the argument directly. This causes a problem when the
# quoted portion contains a glob character, as the character will no
# longer be treated literally. If glob characters occur *only* inside
# of quotes, then we can handle this by not globbing at all, and if
# glob characters occur *only* outside of quotes, we can still glob just
# fine. But if a glob character occurs both inside and outside of
# quotes this presents a problem. In practice this is such an obscure
# edge case that it doesn't seem worth the added complexity to support.
# By adding an assertion, it means some bot somewhere will catch this
# and flag the user of a non-portable test (which could almost certainly
# be re-written to work correctly without triggering this).
assert not (quoted_glob_char and unquoted_glob_char)
return GlobItem(str) if unquoted_glob_char else str
def lex_arg_quoted(self, delim):
str = ''
while self.pos != self.end:
c = self.eat()
if c == delim:
return str
elif c == '\\' and delim == '"':
# Inside a '"' quoted string, '\\' only escapes the quote
# character and backslash, otherwise it is preserved.
if self.pos == self.end:
lit.util.warning(
"escape at end of quoted argument in: %r" % self.data)
return str
c = self.eat()
if c == '"': #
str += '"'
elif c == '\\':
str += '\\'
else:
str += '\\' + c
else:
str += c
lit.util.warning("missing quote character in %r" % self.data)
return str
def lex_arg_checked(self, c):
pos = self.pos
res = self.lex_arg_fast(c)
end = self.pos
self.pos = pos
reference = self.lex_arg_slow(c)
if res is not None:
if res != reference:
raise ValueError("Fast path failure: %r != %r" % (
res, reference))
if self.pos != end:
raise ValueError("Fast path failure: %r != %r" % (
self.pos, end))
return reference
def lex_arg(self, c):
return self.lex_arg_fast(c) or self.lex_arg_slow(c)
def lex_one_token(self):
"""
lex_one_token - Lex a single 'sh' token. """
c = self.eat()
if c == ';':
return (c,)
if c == '|':
if self.maybe_eat('|'):
return ('||',)
return (c,)
if c == '&':
if self.maybe_eat('&'):
return ('&&',)
if self.maybe_eat('>'):
return ('&>',)
return (c,)
if c == '>':
if self.maybe_eat('&'):
return ('>&',)
if self.maybe_eat('>'):
return ('>>',)
return (c,)
if c == '<':
if self.maybe_eat('&'):
return ('<&',)
if self.maybe_eat('>'):
return ('<<',)
return (c,)
return self.lex_arg(c)
def lex(self):
while self.pos != self.end:
if self.look().isspace():
self.eat()
else:
yield self.lex_one_token()
###
class ShParser:
def __init__(self, data, win32Escapes = False, pipefail = False):
self.data = data
self.pipefail = pipefail
self.tokens = ShLexer(data, win32Escapes = win32Escapes).lex()
def lex(self):
for item in self.tokens:
return item
return None
def look(self):
token = self.lex()
if token is not None:
self.tokens = itertools.chain([token], self.tokens)
return token
def parse_command(self):
tok = self.lex()
if not tok:
raise ValueError("empty command!")
if isinstance(tok, tuple):
raise ValueError("syntax error near unexpected token %r" % tok[0])
args = [tok]
redirects = []
while 1:
tok = self.look()
# EOF?
if tok is None:
break
# If this is an argument, just add it to the current command.
if isinstance(tok, (str, GlobItem)):
args.append(self.lex())
continue
# Otherwise see if it is a terminator.
assert isinstance(tok, tuple)
if tok[0] in ('|',';','&','||','&&'):
break
# Otherwise it must be a redirection.
op = self.lex()
arg = self.lex()
if not arg:
raise ValueError("syntax error near token %r" % op[0])
redirects.append((op, arg))
return Command(args, redirects)
def parse_pipeline(self):
negate = False
commands = [self.parse_command()]
while self.look() == ('|',):
self.lex()
commands.append(self.parse_command())
return Pipeline(commands, negate, self.pipefail)
def parse(self):
lhs = self.parse_pipeline()
while self.look():
operator = self.lex()
assert isinstance(operator, tuple) and len(operator) == 1
if not self.look():
raise ValueError(
"missing argument to operator %r" % operator[0])
# FIXME: Operator precedence!!
lhs = Seq(lhs, operator[0], self.parse_pipeline())
return lhs
|