/brz/remove-bazaar

To get this branch, use:
bzr branch http://gegoxaren.bato24.eu/bzr/brz/remove-bazaar

« back to all changes in this revision

Viewing changes to breezy/cmdline.py

  • Committer: John Arbash Meinel
  • Date: 2006-04-25 15:05:42 UTC
  • mfrom: (1185.85.85 bzr-encoding)
  • mto: This revision was merged to the branch mainline in revision 1752.
  • Revision ID: john@arbash-meinel.com-20060425150542-c7b518dca9928691
[merge] the old bzr-encoding changes, reparenting them on bzr.dev

Show diffs side-by-side

added added

removed removed

Lines of Context:
breezy/cmdline.py
1
 
# Copyright (C) 2010-2011 Canonical Ltd
2
 
#
3
 
# This program is free software; you can redistribute it and/or modify
4
 
# it under the terms of the GNU General Public License as published by
5
 
# the Free Software Foundation; either version 2 of the License, or
6
 
# (at your option) any later version.
7
 
#
8
 
# This program is distributed in the hope that it will be useful,
9
 
# but WITHOUT ANY WARRANTY; without even the implied warranty of
10
 
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
11
 
# GNU General Public License for more details.
12
 
#
13
 
# You should have received a copy of the GNU General Public License
14
 
# along with this program; if not, write to the Free Software
15
 
# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
16
 
 
17
 
"""Unicode-compatible command-line splitter for all platforms.
18
 
 
19
 
The user-visible behaviour of this module is described in
20
 
configuring_bazaar.txt.
21
 
"""
22
 
 
23
 
from __future__ import absolute_import
24
 
 
25
 
import re
26
 
 
27
 
 
28
 
_whitespace_match = re.compile(u'\\s', re.UNICODE).match
29
 
 
30
 
 
31
 
class _PushbackSequence(object):
32
 
    def __init__(self, orig):
33
 
        self._iter = iter(orig)
34
 
        self._pushback_buffer = []
35
 
 
36
 
    def __next__(self):
37
 
        if len(self._pushback_buffer) > 0:
38
 
            return self._pushback_buffer.pop()
39
 
        else:
40
 
            return next(self._iter)
41
 
 
42
 
    next = __next__
43
 
 
44
 
    def pushback(self, char):
45
 
        self._pushback_buffer.append(char)
46
 
 
47
 
    def __iter__(self):
48
 
        return self
49
 
 
50
 
 
51
 
class _Whitespace(object):
52
 
    def process(self, next_char, context):
53
 
        if _whitespace_match(next_char):
54
 
            if len(context.token) > 0:
55
 
                return None
56
 
            else:
57
 
                return self
58
 
        elif next_char in context.allowed_quote_chars:
59
 
            context.quoted = True
60
 
            return _Quotes(next_char, self)
61
 
        elif next_char == u'\\':
62
 
            return _Backslash(self)
63
 
        else:
64
 
            context.token.append(next_char)
65
 
            return _Word()
66
 
 
67
 
 
68
 
class _Quotes(object):
69
 
    def __init__(self, quote_char, exit_state):
70
 
        self.quote_char = quote_char
71
 
        self.exit_state = exit_state
72
 
 
73
 
    def process(self, next_char, context):
74
 
        if next_char == u'\\':
75
 
            return _Backslash(self)
76
 
        elif next_char == self.quote_char:
77
 
            context.token.append(u'')
78
 
            return self.exit_state
79
 
        else:
80
 
            context.token.append(next_char)
81
 
            return self
82
 
 
83
 
 
84
 
class _Backslash(object):
85
 
    # See http://msdn.microsoft.com/en-us/library/bb776391(VS.85).aspx
86
 
    def __init__(self, exit_state):
87
 
        self.exit_state = exit_state
88
 
        self.count = 1
89
 
 
90
 
    def process(self, next_char, context):
91
 
        if next_char == u'\\':
92
 
            self.count += 1
93
 
            return self
94
 
        elif next_char in context.allowed_quote_chars:
95
 
            # 2N backslashes followed by a quote are N backslashes
96
 
            context.token.append(u'\\' * (self.count // 2))
97
 
            # 2N+1 backslashes follwed by a quote are N backslashes followed by
98
 
            # the quote which should not be processed as the start or end of
99
 
            # the quoted arg
100
 
            if self.count % 2 == 1:
101
 
                # odd number of \ escapes the quote
102
 
                context.token.append(next_char)
103
 
            else:
104
 
                # let exit_state handle next_char
105
 
                context.seq.pushback(next_char)
106
 
            self.count = 0
107
 
            return self.exit_state
108
 
        else:
109
 
            # N backslashes not followed by a quote are just N backslashes
110
 
            if self.count > 0:
111
 
                context.token.append(u'\\' * self.count)
112
 
                self.count = 0
113
 
            # let exit_state handle next_char
114
 
            context.seq.pushback(next_char)
115
 
            return self.exit_state
116
 
 
117
 
    def finish(self, context):
118
 
        if self.count > 0:
119
 
            context.token.append(u'\\' * self.count)
120
 
 
121
 
 
122
 
class _Word(object):
123
 
    def process(self, next_char, context):
124
 
        if _whitespace_match(next_char):
125
 
            return None
126
 
        elif next_char in context.allowed_quote_chars:
127
 
            return _Quotes(next_char, self)
128
 
        elif next_char == u'\\':
129
 
            return _Backslash(self)
130
 
        else:
131
 
            context.token.append(next_char)
132
 
            return self
133
 
 
134
 
 
135
 
class Splitter(object):
136
 
    def __init__(self, command_line, single_quotes_allowed):
137
 
        self.seq = _PushbackSequence(command_line)
138
 
        self.allowed_quote_chars = u'"'
139
 
        if single_quotes_allowed:
140
 
            self.allowed_quote_chars += u"'"
141
 
 
142
 
    def __iter__(self):
143
 
        return self
144
 
 
145
 
    def __next__(self):
146
 
        quoted, token = self._get_token()
147
 
        if token is None:
148
 
            raise StopIteration
149
 
        return quoted, token
150
 
 
151
 
    next = __next__
152
 
 
153
 
    def _get_token(self):
154
 
        self.quoted = False
155
 
        self.token = []
156
 
        state = _Whitespace()
157
 
        for next_char in self.seq:
158
 
            state = state.process(next_char, self)
159
 
            if state is None:
160
 
                break
161
 
        if state is not None and not getattr(state, 'finish', None) is None:
162
 
            state.finish(self)
163
 
        result = u''.join(self.token)
164
 
        if not self.quoted and result == '':
165
 
            result = None
166
 
        return self.quoted, result
167
 
 
168
 
 
169
 
def split(unsplit, single_quotes_allowed=True):
170
 
    splitter = Splitter(unsplit, single_quotes_allowed=single_quotes_allowed)
171
 
    return [arg for quoted, arg in splitter]