~bzr-pqm/bzr/bzr.dev

4354.3.1 by Jelmer Vernooij
Move core RIO parsing functionality to _rio_py.py.
1
# Copyright (C) 2009 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
4354.3.2 by Jelmer Vernooij
Provide custom implementation of _read_stanza_utf8 in Pyrex.
17
"""Python implementation of _read_stanza_*."""
18
4354.3.1 by Jelmer Vernooij
Move core RIO parsing functionality to _rio_py.py.
19
import re
20
21
from bzrlib.rio import (
22
    Stanza,
23
    )
24
25
_tag_re = re.compile(r'^[-a-zA-Z0-9_]+$')
26
def _valid_tag(tag):
4354.3.15 by Jelmer Vernooij
Extend valid_tags tests a bit, test that stanza pairs contain the right types.
27
    if type(tag) != str:
28
        raise TypeError(tag)
4354.3.1 by Jelmer Vernooij
Move core RIO parsing functionality to _rio_py.py.
29
    return bool(_tag_re.match(tag))
30
31
32
def _read_stanza_utf8(line_iter):
4354.3.15 by Jelmer Vernooij
Extend valid_tags tests a bit, test that stanza pairs contain the right types.
33
    def iter_unicode_lines():
34
        for line in line_iter:
35
            if type(line) != str:
36
                raise TypeError(line)
37
            yield line.decode('utf-8')
38
    return _read_stanza_unicode(iter_unicode_lines())
4354.3.1 by Jelmer Vernooij
Move core RIO parsing functionality to _rio_py.py.
39
40
41
def _read_stanza_unicode(unicode_iter):
42
    stanza = Stanza()
43
    tag = None
44
    accum_value = None
45
46
    # TODO: jam 20060922 This code should raise real errors rather than
47
    #       using 'assert' to process user input, or raising ValueError
48
    #       rather than a more specific error.
4354.3.18 by Jelmer Vernooij
Merge bzr.dev.
49
4354.3.1 by Jelmer Vernooij
Move core RIO parsing functionality to _rio_py.py.
50
    for line in unicode_iter:
4354.3.18 by Jelmer Vernooij
Merge bzr.dev.
51
        if line is None or line == u'':
4354.3.1 by Jelmer Vernooij
Move core RIO parsing functionality to _rio_py.py.
52
            break       # end of file
4354.3.18 by Jelmer Vernooij
Merge bzr.dev.
53
        if line == u'\n':
4354.3.1 by Jelmer Vernooij
Move core RIO parsing functionality to _rio_py.py.
54
            break       # end of stanza
55
        real_l = line
4354.3.18 by Jelmer Vernooij
Merge bzr.dev.
56
        if line[0] == u'\t': # continues previous value
4354.3.1 by Jelmer Vernooij
Move core RIO parsing functionality to _rio_py.py.
57
            if tag is None:
58
                raise ValueError('invalid continuation line %r' % real_l)
4354.3.18 by Jelmer Vernooij
Merge bzr.dev.
59
            accum_value.append(u'\n' + line[1:-1])
4354.3.1 by Jelmer Vernooij
Move core RIO parsing functionality to _rio_py.py.
60
        else: # new tag:value line
61
            if tag is not None:
4354.3.18 by Jelmer Vernooij
Merge bzr.dev.
62
                stanza.add(tag, u''.join(accum_value))
4354.3.1 by Jelmer Vernooij
Move core RIO parsing functionality to _rio_py.py.
63
            try:
4354.3.18 by Jelmer Vernooij
Merge bzr.dev.
64
                colon_index = line.index(u': ')
4354.3.1 by Jelmer Vernooij
Move core RIO parsing functionality to _rio_py.py.
65
            except ValueError:
66
                raise ValueError('tag/value separator not found in line %r'
67
                                 % real_l)
68
            tag = str(line[:colon_index])
69
            if not _valid_tag(tag):
70
                raise ValueError("invalid rio tag %r" % (tag,))
4354.3.18 by Jelmer Vernooij
Merge bzr.dev.
71
            accum_value = [line[colon_index+2:-1]]
4354.3.1 by Jelmer Vernooij
Move core RIO parsing functionality to _rio_py.py.
72
73
    if tag is not None: # add last tag-value
4354.3.18 by Jelmer Vernooij
Merge bzr.dev.
74
        stanza.add(tag, u''.join(accum_value))
4354.3.1 by Jelmer Vernooij
Move core RIO parsing functionality to _rio_py.py.
75
        return stanza
76
    else:     # didn't see any content
77
        return None