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
|
# -*- coding: utf-8 -*-
""" Re-Implementation of Python's shlex.split(), because shlex can't cope
with the input being Unicode.
Copyright (C) 2009, Michael "Svedrin" Ziegler <diese-addy@funzt-halt.net>
"""
def shlox( line, escape='\\', comment='#', sep=(' ', '\t', '\r', '\n' ) ):
ST_NORMAL, ST_ESCAPE, ST_SINGLE_QUOTED, ST_DOUBLE_QUOTED, ST_DOUBLE_ESCAPE = range(5)
state = ST_NORMAL
word = ''
empty = True
for char in line:
if state == ST_NORMAL:
if char == escape:
state = ST_ESCAPE
elif char == '"':
empty = False
state = ST_DOUBLE_QUOTED
elif char == "'":
empty = False
state = ST_SINGLE_QUOTED
elif char == comment:
if empty:
raise StopIteration
else:
word += char
elif char in sep:
if not empty:
yield word
empty = True
word = ''
else:
empty = False
word += char
elif state == ST_ESCAPE:
word += char
state = ST_NORMAL
elif state == ST_SINGLE_QUOTED:
if char == "'":
state = ST_NORMAL
else:
word += char
elif state == ST_DOUBLE_QUOTED:
if char == escape:
state = ST_DOUBLE_ESCAPE
elif char == '"':
state = ST_NORMAL
else:
word += char
elif state == ST_DOUBLE_ESCAPE:
if char in ( escape, comment, '"', "'" ) + sep:
word += char
else:
word += '\\' + char
state = ST_DOUBLE_QUOTED
if state != ST_NORMAL:
raise ValueError( "Unclosed quote or \\ at end of line." )
elif not empty:
yield word
|
