~bzr-pqm/bzr/bzr.dev

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
# Copyright (C) 2010-2011 Canonical Ltd
#
# This program 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 2 of the License, or
# (at your option) any later version.
#
# This program 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 this program; if not, write to the Free Software
# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA

"""Unicode-compatible command-line splitter for all platforms.

The user-visible behaviour of this module is described in
configuring_bazaar.txt.
"""

from __future__ import absolute_import

import re


_whitespace_match = re.compile(u'\s', re.UNICODE).match


class _PushbackSequence(object):
    def __init__(self, orig):
        self._iter = iter(orig)
        self._pushback_buffer = []

    def next(self):
        if len(self._pushback_buffer) > 0:
            return self._pushback_buffer.pop()
        else:
            return self._iter.next()

    def pushback(self, char):
        self._pushback_buffer.append(char)

    def __iter__(self):
        return self


class _Whitespace(object):
    def process(self, next_char, context):
        if _whitespace_match(next_char):
            if len(context.token) > 0:
                return None
            else:
                return self
        elif next_char in context.allowed_quote_chars:
            context.quoted = True
            return _Quotes(next_char, self)
        elif next_char == u'\\':
            return _Backslash(self)
        else:
            context.token.append(next_char)
            return _Word()


class _Quotes(object):
    def __init__(self, quote_char, exit_state):
        self.quote_char = quote_char
        self.exit_state = exit_state

    def process(self, next_char, context):
        if next_char == u'\\':
            return _Backslash(self)
        elif next_char == self.quote_char:
            context.token.append(u'')
            return self.exit_state
        else:
            context.token.append(next_char)
            return self


class _Backslash(object):
    # See http://msdn.microsoft.com/en-us/library/bb776391(VS.85).aspx
    def __init__(self, exit_state):
        self.exit_state = exit_state
        self.count = 1

    def process(self, next_char, context):
        if next_char == u'\\':
            self.count += 1
            return self
        elif next_char in context.allowed_quote_chars:
            # 2N backslashes followed by a quote are N backslashes
            context.token.append(u'\\' * (self.count/2))
            # 2N+1 backslashes follwed by a quote are N backslashes followed by
            # the quote which should not be processed as the start or end of
            # the quoted arg
            if self.count % 2 == 1:
                # odd number of \ escapes the quote
                context.token.append(next_char)
            else:
                # let exit_state handle next_char
                context.seq.pushback(next_char)
            self.count = 0
            return self.exit_state
        else:
            # N backslashes not followed by a quote are just N backslashes
            if self.count > 0:
                context.token.append(u'\\' * self.count)
                self.count = 0
            # let exit_state handle next_char
            context.seq.pushback(next_char)
            return self.exit_state

    def finish(self, context):
        if self.count > 0:
            context.token.append(u'\\' * self.count)


class _Word(object):
    def process(self, next_char, context):
        if _whitespace_match(next_char):
            return None
        elif next_char in context.allowed_quote_chars:
            return _Quotes(next_char, self)
        elif next_char == u'\\':
            return _Backslash(self)
        else:
            context.token.append(next_char)
            return self


class Splitter(object):
    def __init__(self, command_line, single_quotes_allowed):
        self.seq = _PushbackSequence(command_line)
        self.allowed_quote_chars = u'"'
        if single_quotes_allowed:
            self.allowed_quote_chars += u"'"

    def __iter__(self):
        return self

    def next(self):
        quoted, token = self._get_token()
        if token is None:
            raise StopIteration
        return quoted, token

    def _get_token(self):
        self.quoted = False
        self.token = []
        state = _Whitespace()
        for next_char in self.seq:
            state = state.process(next_char, self)
            if state is None:
                break
        if not state is None and not getattr(state, 'finish', None) is None:
            state.finish(self)
        result = u''.join(self.token)
        if not self.quoted and result == '':
            result = None
        return self.quoted, result


def split(unsplit, single_quotes_allowed=True):
    splitter = Splitter(unsplit, single_quotes_allowed=single_quotes_allowed)
    return [arg for quoted, arg in splitter]