My favorites | Sign in
Project Home Downloads Wiki Issues Source
Checkout   Browse   Changes  
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
"""A lexical analyzer class for simple shell-like syntaxes."""

## MODIFIED FROM UPSTREAM PYTHON, see:
## http://bugs.python.org/issue1170

# Module and documentation by Eric S. Raymond, 21 Dec 1998
# Input stacking and error message cleanup added by ESR, March 2000
# push_source() and pop_source() made explicit by ESR, January 2001.
# Posix compliance, split(), string arguments, and
# iterator interface by Gustavo Niemeyer, April 2003.
# Modified to support Unicode by Colin Walters, Dec 2007

import os.path
import sys
from collections import deque

from hotwire.unicodeutils import get_unichar_category, is_category_letter, is_category_number, is_category_whitespace

try:
from cStringIO import StringIO
except ImportError:
from StringIO import StringIO

__all__ = ["shlex", "split"]

class shlex:
"A lexical analyzer class for simple shell-like syntaxes."
def __init__(self, instream=None, infile=None, posix=False, utf=True):
if isinstance(instream, basestring):
instream = StringIO(instream)
if instream is not None:
self.instream = instream
self.infile = infile
else:
self.instream = sys.stdin
self.infile = None
self.posix = posix
if posix:
self.eof = None
else:
self.eof = ''
self.utf = utf
self.commenters = '#'
self.wordchars = ('abcdfeghijklmnopqrstuvwxyz'
'ABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789_')
if self.posix:
# We dynamically determine character classes below, except
# by default _ is a word character
self.wordchars = '_'
if not self.utf:
self.whitespace = ' \t\r\n'
else:
self.whitespace = ''
self.whitespace_split = False
self.quotes = '\'"'
self.escape = '\\'
self.escapedquotes = '"'
self.state = ' '
self.pushback = deque()
self.lineno = 1
self.debug = 0
self.token = ''
self.filestack = deque()
self.source = None
if self.debug:
print 'shlex: reading from %s, line %d' \
% (self.instream, self.lineno)

def push_token(self, tok):
"Push a token onto the stack popped by the get_token method"
if self.debug >= 1:
print "shlex: pushing token " + repr(tok)
self.pushback.appendleft(tok)

def push_source(self, newstream, newfile=None):
"Push an input source onto the lexer's input source stack."
if isinstance(newstream, basestring):
newstream = StringIO(newstream)
self.filestack.appendleft((self.infile, self.instream, self.lineno))
self.infile = newfile
self.instream = newstream
self.lineno = 1
if self.debug:
if newfile is not None:
print 'shlex: pushing to file %s' % (self.infile,)
else:
print 'shlex: pushing to stream %s' % (self.instream,)

def pop_source(self):
"Pop the input source stack."
self.instream.close()
(self.infile, self.instream, self.lineno) = self.filestack.popleft()
if self.debug:
print 'shlex: popping to %s, line %d' \
% (self.instream, self.lineno)
self.state = ' '

def get_token_info(self):
"Get a token from the input stream (or from stack if it's nonempty)"
if self.pushback:
tok = self.pushback.popleft()
if self.debug >= 1:
print "shlex: popping token " + repr(tok)
return tok
# No pushback. Get a token.
(raw, quoted) = self.read_token_info()
# Handle inclusions
if self.source is not None:
while raw == self.source:
spec = self.sourcehook(self.read_token())
if spec:
(newfile, newstream) = spec
self.push_source(newstream, newfile)
(raw, quoted) = self.get_token_info()
# Maybe we got EOF instead?
while raw == self.eof:
if not self.filestack:
return (self.eof, False)
else:
self.pop_source()
(raw, quoted) = self.get_token_info()
# Neither inclusion nor EOF
if self.debug >= 1:
if raw != self.eof:
print "shlex: token=" + repr(raw)
else:
print "shlex: token=EOF"
return (raw, quoted)

def get_token(self):
(raw, quoted) = self.get_token_info()
return raw

def __is_whitespace(self, c, category):
return c in self.whitespace or (self.utf and is_category_whitespace(category))

def __is_wordchar(self, c, category):
return c in self.wordchars or (self.utf and (is_category_number(category) or is_category_letter(category)))

def read_token_info(self):
quoted = False
escapedstate = ' '
while True:
nextchar = self.instream.read(1)
if nextchar and self.utf:
nextcategory = get_unichar_category(nextchar)
else:
nextcategory = None
if nextchar == '\n':
self.lineno = self.lineno + 1
if self.debug >= 3:
print "shlex: in state", repr(self.state), \
"I see character:", repr(nextchar)
if self.state is None:
self.token = '' # past end of file
break
elif self.state == ' ':
if not nextchar:
self.state = None # end of file
break
if self.__is_whitespace(nextchar, nextcategory):
if self.debug >= 2:
print "shlex: I see whitespace in whitespace state"
if self.token or (self.posix and quoted):
break # emit current token
else:
continue
elif nextchar in self.commenters:
self.instream.readline()
self.lineno = self.lineno + 1
elif self.posix and nextchar in self.escape:
escapedstate = 'a'
self.state = nextchar
elif self.__is_wordchar(nextchar, nextcategory):
self.token = nextchar
self.state = 'a'
elif nextchar in self.quotes:
if not self.posix:
self.token = nextchar
self.state = nextchar
elif self.whitespace_split:
self.token = nextchar
self.state = 'a'
else:
self.token = nextchar
if self.token or (self.posix and quoted):
break # emit current token
else:
continue
elif self.state in self.quotes:
quoted = True
if not nextchar: # end of file
if self.debug >= 2:
print "shlex: I see EOF in quotes state"
# XXX what error should be raised here?
raise ValueError, "No closing quotation"
if nextchar == self.state:
if not self.posix:
self.token = self.token + nextchar
self.state = ' '
break
else:
self.state = 'a'
elif self.posix and nextchar in self.escape and \
self.state in self.escapedquotes:
escapedstate = self.state
self.state = nextchar
else:
self.token = self.token + nextchar
elif self.state in self.escape:
if not nextchar: # end of file
if self.debug >= 2:
print "shlex: I see EOF in escape state"
# XXX what error should be raised here?
raise ValueError, "No escaped character"
# In posix shells, only the quote itself or the escape
# character may be escaped within quotes.
if escapedstate in self.quotes and \
nextchar != self.state and nextchar != escapedstate:
self.token = self.token + self.state
self.token = self.token + nextchar
self.state = escapedstate
elif self.state == 'a':
if not nextchar:
self.state = None # end of file
break
if self.__is_whitespace(nextchar, nextcategory):
if self.debug >= 2:
print "shlex: I see whitespace in word state"
self.state = ' '
if self.token or (self.posix and quoted):
break # emit current token
else:
continue
elif nextchar in self.commenters:
self.instream.readline()
self.lineno = self.lineno + 1
if self.posix:
self.state = ' '
if self.token or (self.posix and quoted):
break # emit current token
else:
continue
elif self.posix and nextchar in self.quotes:
self.state = nextchar
elif self.posix and nextchar in self.escape:
escapedstate = 'a'
self.state = nextchar
elif self.__is_wordchar(nextchar, nextcategory) or nextchar in self.quotes \
or self.whitespace_split:
self.token = self.token + nextchar
else:
self.pushback.appendleft((nextchar, quoted))
if self.debug >= 2:
print "shlex: I see punctuation in word state"
self.state = ' '
if self.token:
break # emit current token
else:
continue
result = self.token
self.token = ''
if self.posix and not quoted and result == '':
result = None
if self.debug > 1:
if result:
print "shlex: raw token=" + repr(result)
else:
print "shlex: raw token=EOF"
return (result, quoted)

def read_token(self):
(result, quoted) = self.read_token_info()
return result

def sourcehook(self, newfile):
"Hook called on a filename to be sourced."
if newfile[0] == '"':
newfile = newfile[1:-1]
# This implements cpp-like semantics for relative-path inclusion.
if isinstance(self.infile, basestring) and not os.path.isabs(newfile):
newfile = os.path.join(os.path.dirname(self.infile), newfile)
return (newfile, open(newfile, "r"))

def error_leader(self, infile=None, lineno=None):
"Emit a C-compiler-like, Emacs-friendly error-message leader."
if infile is None:
infile = self.infile
if lineno is None:
lineno = self.lineno
return "\"%s\", line %d: " % (infile, lineno)

def __iter__(self):
return self

def next(self):
token = self.get_token()
if token == self.eof:
raise StopIteration
return token

def split(s, comments=False):
lex = shlex(s, posix=True)
lex.whitespace_split = True
if not comments:
lex.commenters = ''
return list(lex)

if __name__ == '__main__':
if len(sys.argv) == 1:
lexer = shlex()
else:
file = sys.argv[1]
lexer = shlex(open(file), file)
while 1:
tt = lexer.get_token()
if tt:
print "Token: " + repr(tt)
else:
break

Change log

r1280 by cgwalters on Jul 1, 2008   Diff
[jython work] Kill more gobject and
unicodedata usage

New unicodeutils file which can replace
unicodedata
Go to: 
Project members, sign in to write a code review

Older revisions

r549 by cgwalters on Dec 22, 2007   Diff
Have shlex tell us whether the token
it parsed was quoted.
r541 by cgwalters on Dec 22, 2007   Diff
Create hotwire.externals to hold
modified outside source code.
r539 by cgwalters on Dec 22, 2007   Diff
Note link to upstream python bug.
All revisions of this file

File info

Size: 12307 bytes, 320 lines
Powered by Google Project Hosting